{"current_steps": 5, "total_steps": 42420, "loss": 0.6057, "lr": 4.714757190004715e-08, "epoch": 0.0023573785950023575, "percentage": 0.01, "elapsed_time": "0:00:01", "remaining_time": "4:16:53", "throughput": 2853.03, "total_tokens": 5184} {"current_steps": 10, "total_steps": 42420, "loss": 0.5862, "lr": 1.0608203677510608e-07, "epoch": 0.004714757190004715, "percentage": 0.02, "elapsed_time": "0:00:02", "remaining_time": "3:13:39", "throughput": 3503.96, "total_tokens": 9600} {"current_steps": 15, "total_steps": 42420, "loss": 0.3688, "lr": 1.6501650165016504e-07, "epoch": 0.007072135785007072, "percentage": 0.04, "elapsed_time": "0:00:03", "remaining_time": "2:57:35", "throughput": 3803.35, "total_tokens": 14336} {"current_steps": 20, "total_steps": 42420, "loss": 0.3121, "lr": 2.2395096652522396e-07, "epoch": 0.00942951438000943, "percentage": 0.05, "elapsed_time": "0:00:04", "remaining_time": "2:53:24", "throughput": 4010.03, "total_tokens": 19680} {"current_steps": 25, "total_steps": 42420, "loss": 0.9506, "lr": 2.828854314002829e-07, "epoch": 0.011786892975011787, "percentage": 0.06, "elapsed_time": "0:00:05", "remaining_time": "2:47:12", "throughput": 4153.88, "total_tokens": 24576} {"current_steps": 30, "total_steps": 42420, "loss": 0.342, "lr": 3.4181989627534184e-07, "epoch": 0.014144271570014143, "percentage": 0.07, "elapsed_time": "0:00:06", "remaining_time": "2:42:21", "throughput": 4237.66, "total_tokens": 29216} {"current_steps": 35, "total_steps": 42420, "loss": 0.119, "lr": 4.007543611504008e-07, "epoch": 0.0165016501650165, "percentage": 0.08, "elapsed_time": "0:00:07", "remaining_time": "2:38:12", "throughput": 4266.03, "total_tokens": 33440} {"current_steps": 40, "total_steps": 42420, "loss": 0.5443, "lr": 4.5968882602545973e-07, "epoch": 0.01885902876001886, "percentage": 0.09, "elapsed_time": "0:00:08", "remaining_time": "2:35:54", "throughput": 4331.04, "total_tokens": 38240} {"current_steps": 45, "total_steps": 42420, "loss": 0.3394, "lr": 5.186232909005186e-07, "epoch": 0.021216407355021217, "percentage": 0.11, "elapsed_time": "0:00:09", "remaining_time": "2:34:42", "throughput": 4392.01, "total_tokens": 43296} {"current_steps": 50, "total_steps": 42420, "loss": 0.1801, "lr": 5.775577557755775e-07, "epoch": 0.023573785950023574, "percentage": 0.12, "elapsed_time": "0:00:10", "remaining_time": "2:32:34", "throughput": 4422.6, "total_tokens": 47776} {"current_steps": 55, "total_steps": 42420, "loss": 0.6421, "lr": 6.364922206506365e-07, "epoch": 0.02593116454502593, "percentage": 0.13, "elapsed_time": "0:00:11", "remaining_time": "2:31:04", "throughput": 4465.08, "total_tokens": 52544} {"current_steps": 60, "total_steps": 42420, "loss": 0.3972, "lr": 6.954266855256955e-07, "epoch": 0.028288543140028287, "percentage": 0.14, "elapsed_time": "0:00:12", "remaining_time": "2:31:50", "throughput": 4508.2, "total_tokens": 58176} {"current_steps": 65, "total_steps": 42420, "loss": 0.7584, "lr": 7.543611504007544e-07, "epoch": 0.030645921735030647, "percentage": 0.15, "elapsed_time": "0:00:13", "remaining_time": "2:31:10", "throughput": 4519.7, "total_tokens": 62912} {"current_steps": 70, "total_steps": 42420, "loss": 0.6401, "lr": 8.132956152758133e-07, "epoch": 0.033003300330033, "percentage": 0.17, "elapsed_time": "0:00:15", "remaining_time": "2:32:50", "throughput": 4551.77, "total_tokens": 68992} {"current_steps": 75, "total_steps": 42420, "loss": 0.8128, "lr": 8.722300801508723e-07, "epoch": 0.03536067892503536, "percentage": 0.18, "elapsed_time": "0:00:16", "remaining_time": "2:31:00", "throughput": 4568.32, "total_tokens": 73312} {"current_steps": 80, "total_steps": 42420, "loss": 0.6709, "lr": 9.311645450259312e-07, "epoch": 0.03771805752003772, "percentage": 0.19, "elapsed_time": "0:00:17", "remaining_time": "2:32:07", "throughput": 4579.57, "total_tokens": 78976} {"current_steps": 85, "total_steps": 42420, "loss": 0.4635, "lr": 9.900990099009902e-07, "epoch": 0.040075436115040074, "percentage": 0.2, "elapsed_time": "0:00:18", "remaining_time": "2:31:30", "throughput": 4586.32, "total_tokens": 83712} {"current_steps": 90, "total_steps": 42420, "loss": 0.3784, "lr": 1.0490334747760492e-06, "epoch": 0.042432814710042434, "percentage": 0.21, "elapsed_time": "0:00:19", "remaining_time": "2:30:19", "throughput": 4585.64, "total_tokens": 87936} {"current_steps": 95, "total_steps": 42420, "loss": 0.2236, "lr": 1.107967939651108e-06, "epoch": 0.04479019330504479, "percentage": 0.22, "elapsed_time": "0:00:20", "remaining_time": "2:29:48", "throughput": 4594.74, "total_tokens": 92704} {"current_steps": 100, "total_steps": 42420, "loss": 0.1863, "lr": 1.166902404526167e-06, "epoch": 0.04714757190004715, "percentage": 0.24, "elapsed_time": "0:00:21", "remaining_time": "2:29:33", "throughput": 4605.83, "total_tokens": 97664} {"current_steps": 105, "total_steps": 42420, "loss": 0.1942, "lr": 1.2258368694012257e-06, "epoch": 0.04950495049504951, "percentage": 0.25, "elapsed_time": "0:00:22", "remaining_time": "2:28:57", "throughput": 4610.2, "total_tokens": 102240} {"current_steps": 110, "total_steps": 42420, "loss": 0.2198, "lr": 1.284771334276285e-06, "epoch": 0.05186232909005186, "percentage": 0.26, "elapsed_time": "0:00:23", "remaining_time": "2:29:06", "throughput": 4613.13, "total_tokens": 107296} {"current_steps": 115, "total_steps": 42420, "loss": 0.3155, "lr": 1.343705799151344e-06, "epoch": 0.05421970768505422, "percentage": 0.27, "elapsed_time": "0:00:24", "remaining_time": "2:29:41", "throughput": 4627.89, "total_tokens": 112992} {"current_steps": 120, "total_steps": 42420, "loss": 0.3416, "lr": 1.4026402640264027e-06, "epoch": 0.056577086280056574, "percentage": 0.28, "elapsed_time": "0:00:25", "remaining_time": "2:30:13", "throughput": 4632.94, "total_tokens": 118464} {"current_steps": 125, "total_steps": 42420, "loss": 0.4174, "lr": 1.4615747289014617e-06, "epoch": 0.058934464875058934, "percentage": 0.29, "elapsed_time": "0:00:26", "remaining_time": "2:31:25", "throughput": 4640.38, "total_tokens": 124608} {"current_steps": 130, "total_steps": 42420, "loss": 0.4644, "lr": 1.5205091937765205e-06, "epoch": 0.061291843470061294, "percentage": 0.31, "elapsed_time": "0:00:28", "remaining_time": "2:32:50", "throughput": 4647.51, "total_tokens": 131008} {"current_steps": 135, "total_steps": 42420, "loss": 0.2333, "lr": 1.5794436586515793e-06, "epoch": 0.06364922206506365, "percentage": 0.32, "elapsed_time": "0:00:29", "remaining_time": "2:33:02", "throughput": 4655.44, "total_tokens": 136480} {"current_steps": 140, "total_steps": 42420, "loss": 0.6784, "lr": 1.6383781235266383e-06, "epoch": 0.066006600660066, "percentage": 0.33, "elapsed_time": "0:00:30", "remaining_time": "2:32:39", "throughput": 4658.27, "total_tokens": 141280} {"current_steps": 145, "total_steps": 42420, "loss": 0.6606, "lr": 1.6973125884016973e-06, "epoch": 0.06836397925506836, "percentage": 0.34, "elapsed_time": "0:00:31", "remaining_time": "2:32:33", "throughput": 4662.93, "total_tokens": 146400} {"current_steps": 150, "total_steps": 42420, "loss": 0.4081, "lr": 1.7562470532767563e-06, "epoch": 0.07072135785007072, "percentage": 0.35, "elapsed_time": "0:00:32", "remaining_time": "2:32:17", "throughput": 4669.16, "total_tokens": 151392} {"current_steps": 155, "total_steps": 42420, "loss": 0.4494, "lr": 1.8151815181518153e-06, "epoch": 0.07307873644507308, "percentage": 0.37, "elapsed_time": "0:00:33", "remaining_time": "2:32:36", "throughput": 4668.53, "total_tokens": 156768} {"current_steps": 160, "total_steps": 42420, "loss": 0.2098, "lr": 1.874115983026874e-06, "epoch": 0.07543611504007544, "percentage": 0.38, "elapsed_time": "0:00:34", "remaining_time": "2:32:05", "throughput": 4666.36, "total_tokens": 161216} {"current_steps": 165, "total_steps": 42420, "loss": 0.3315, "lr": 1.933050447901933e-06, "epoch": 0.07779349363507779, "percentage": 0.39, "elapsed_time": "0:00:35", "remaining_time": "2:32:06", "throughput": 4672.62, "total_tokens": 166528} {"current_steps": 170, "total_steps": 42420, "loss": 0.3994, "lr": 1.991984912776992e-06, "epoch": 0.08015087223008015, "percentage": 0.4, "elapsed_time": "0:00:36", "remaining_time": "2:32:24", "throughput": 4676.29, "total_tokens": 172064} {"current_steps": 175, "total_steps": 42420, "loss": 0.4331, "lr": 2.050919377652051e-06, "epoch": 0.08250825082508251, "percentage": 0.41, "elapsed_time": "0:00:37", "remaining_time": "2:32:21", "throughput": 4681.31, "total_tokens": 177280} {"current_steps": 180, "total_steps": 42420, "loss": 0.5134, "lr": 2.1098538425271103e-06, "epoch": 0.08486562942008487, "percentage": 0.42, "elapsed_time": "0:00:38", "remaining_time": "2:31:38", "throughput": 4679.86, "total_tokens": 181440} {"current_steps": 185, "total_steps": 42420, "loss": 0.4929, "lr": 2.1687883074021686e-06, "epoch": 0.08722300801508723, "percentage": 0.44, "elapsed_time": "0:00:39", "remaining_time": "2:31:24", "throughput": 4686.59, "total_tokens": 186496} {"current_steps": 190, "total_steps": 42420, "loss": 0.213, "lr": 2.227722772277228e-06, "epoch": 0.08958038661008957, "percentage": 0.45, "elapsed_time": "0:00:40", "remaining_time": "2:30:46", "throughput": 4685.15, "total_tokens": 190688} {"current_steps": 195, "total_steps": 42420, "loss": 0.3682, "lr": 2.2866572371522866e-06, "epoch": 0.09193776520509193, "percentage": 0.46, "elapsed_time": "0:00:41", "remaining_time": "2:30:38", "throughput": 4687.34, "total_tokens": 195648} {"current_steps": 200, "total_steps": 42420, "loss": 0.3624, "lr": 2.345591702027346e-06, "epoch": 0.0942951438000943, "percentage": 0.47, "elapsed_time": "0:00:42", "remaining_time": "2:30:26", "throughput": 4689.53, "total_tokens": 200512} {"current_steps": 205, "total_steps": 42420, "loss": 0.7829, "lr": 2.4045261669024046e-06, "epoch": 0.09665252239509665, "percentage": 0.48, "elapsed_time": "0:00:43", "remaining_time": "2:30:28", "throughput": 4695.17, "total_tokens": 205856} {"current_steps": 210, "total_steps": 42420, "loss": 0.5748, "lr": 2.463460631777464e-06, "epoch": 0.09900990099009901, "percentage": 0.5, "elapsed_time": "0:00:44", "remaining_time": "2:30:18", "throughput": 4697.79, "total_tokens": 210784} {"current_steps": 215, "total_steps": 42420, "loss": 0.4732, "lr": 2.5223950966525226e-06, "epoch": 0.10136727958510136, "percentage": 0.51, "elapsed_time": "0:00:45", "remaining_time": "2:29:58", "throughput": 4697.91, "total_tokens": 215360} {"current_steps": 220, "total_steps": 42420, "loss": 0.7254, "lr": 2.5813295615275814e-06, "epoch": 0.10372465818010372, "percentage": 0.52, "elapsed_time": "0:00:46", "remaining_time": "2:29:44", "throughput": 4698.24, "total_tokens": 220064} {"current_steps": 225, "total_steps": 42420, "loss": 0.5303, "lr": 2.6402640264026406e-06, "epoch": 0.10608203677510608, "percentage": 0.53, "elapsed_time": "0:00:47", "remaining_time": "2:29:16", "throughput": 4697.27, "total_tokens": 224352} {"current_steps": 230, "total_steps": 42420, "loss": 0.4151, "lr": 2.6991984912776994e-06, "epoch": 0.10843941537010844, "percentage": 0.54, "elapsed_time": "0:00:48", "remaining_time": "2:29:01", "throughput": 4699.52, "total_tokens": 229088} {"current_steps": 235, "total_steps": 42420, "loss": 0.3585, "lr": 2.7581329561527586e-06, "epoch": 0.1107967939651108, "percentage": 0.55, "elapsed_time": "0:00:49", "remaining_time": "2:28:49", "throughput": 4700.79, "total_tokens": 233824} {"current_steps": 240, "total_steps": 42420, "loss": 0.6327, "lr": 2.817067421027817e-06, "epoch": 0.11315417256011315, "percentage": 0.57, "elapsed_time": "0:00:50", "remaining_time": "2:28:42", "throughput": 4703.88, "total_tokens": 238816} {"current_steps": 245, "total_steps": 42420, "loss": 0.6112, "lr": 2.876001885902876e-06, "epoch": 0.11551155115511551, "percentage": 0.58, "elapsed_time": "0:00:51", "remaining_time": "2:28:21", "throughput": 4705.45, "total_tokens": 243328} {"current_steps": 250, "total_steps": 42420, "loss": 0.34, "lr": 2.934936350777935e-06, "epoch": 0.11786892975011787, "percentage": 0.59, "elapsed_time": "0:00:52", "remaining_time": "2:28:35", "throughput": 4709.14, "total_tokens": 248896} {"current_steps": 255, "total_steps": 42420, "loss": 0.2976, "lr": 2.993870815652994e-06, "epoch": 0.12022630834512023, "percentage": 0.6, "elapsed_time": "0:00:53", "remaining_time": "2:28:15", "throughput": 4711.13, "total_tokens": 253440} {"current_steps": 260, "total_steps": 42420, "loss": 0.4665, "lr": 3.052805280528053e-06, "epoch": 0.12258368694012259, "percentage": 0.61, "elapsed_time": "0:00:54", "remaining_time": "2:28:07", "throughput": 4710.98, "total_tokens": 258208} {"current_steps": 265, "total_steps": 42420, "loss": 0.1089, "lr": 3.1117397454031117e-06, "epoch": 0.12494106553512493, "percentage": 0.62, "elapsed_time": "0:00:55", "remaining_time": "2:27:43", "throughput": 4712.58, "total_tokens": 262592} {"current_steps": 270, "total_steps": 42420, "loss": 0.526, "lr": 3.170674210278171e-06, "epoch": 0.1272984441301273, "percentage": 0.64, "elapsed_time": "0:00:56", "remaining_time": "2:27:38", "throughput": 4716.81, "total_tokens": 267648} {"current_steps": 275, "total_steps": 42420, "loss": 0.8014, "lr": 3.2296086751532297e-06, "epoch": 0.12965582272512965, "percentage": 0.65, "elapsed_time": "0:00:57", "remaining_time": "2:27:27", "throughput": 4718.28, "total_tokens": 272384} {"current_steps": 280, "total_steps": 42420, "loss": 0.3956, "lr": 3.2885431400282885e-06, "epoch": 0.132013201320132, "percentage": 0.66, "elapsed_time": "0:00:58", "remaining_time": "2:27:54", "throughput": 4722.32, "total_tokens": 278464} {"current_steps": 285, "total_steps": 42420, "loss": 0.2679, "lr": 3.3474776049033477e-06, "epoch": 0.13437057991513437, "percentage": 0.67, "elapsed_time": "0:00:59", "remaining_time": "2:27:29", "throughput": 4718.17, "total_tokens": 282432} {"current_steps": 290, "total_steps": 42420, "loss": 0.4537, "lr": 3.4064120697784065e-06, "epoch": 0.13672795851013672, "percentage": 0.68, "elapsed_time": "0:01:00", "remaining_time": "2:27:35", "throughput": 4720.31, "total_tokens": 287744} {"current_steps": 295, "total_steps": 42420, "loss": 0.5024, "lr": 3.4653465346534657e-06, "epoch": 0.1390853371051391, "percentage": 0.7, "elapsed_time": "0:01:01", "remaining_time": "2:27:13", "throughput": 4717.77, "total_tokens": 291840} {"current_steps": 300, "total_steps": 42420, "loss": 0.5184, "lr": 3.5242809995285245e-06, "epoch": 0.14144271570014144, "percentage": 0.71, "elapsed_time": "0:01:02", "remaining_time": "2:27:11", "throughput": 4720.67, "total_tokens": 296928} {"current_steps": 305, "total_steps": 42420, "loss": 0.3396, "lr": 3.5832154644035833e-06, "epoch": 0.1438000942951438, "percentage": 0.72, "elapsed_time": "0:01:04", "remaining_time": "2:27:18", "throughput": 4722.54, "total_tokens": 302272} {"current_steps": 310, "total_steps": 42420, "loss": 0.5679, "lr": 3.6421499292786425e-06, "epoch": 0.14615747289014616, "percentage": 0.73, "elapsed_time": "0:01:04", "remaining_time": "2:27:00", "throughput": 4722.94, "total_tokens": 306688} {"current_steps": 315, "total_steps": 42420, "loss": 0.7053, "lr": 3.7010843941537013e-06, "epoch": 0.1485148514851485, "percentage": 0.74, "elapsed_time": "0:01:05", "remaining_time": "2:26:31", "throughput": 4721.3, "total_tokens": 310528} {"current_steps": 320, "total_steps": 42420, "loss": 0.4407, "lr": 3.7600188590287605e-06, "epoch": 0.15087223008015088, "percentage": 0.75, "elapsed_time": "0:01:06", "remaining_time": "2:26:15", "throughput": 4721.17, "total_tokens": 314912} {"current_steps": 325, "total_steps": 42420, "loss": 0.2513, "lr": 3.818953323903819e-06, "epoch": 0.15322960867515323, "percentage": 0.77, "elapsed_time": "0:01:07", "remaining_time": "2:26:08", "throughput": 4722.49, "total_tokens": 319712} {"current_steps": 330, "total_steps": 42420, "loss": 0.7585, "lr": 3.877887788778878e-06, "epoch": 0.15558698727015557, "percentage": 0.78, "elapsed_time": "0:01:08", "remaining_time": "2:26:07", "throughput": 4723.69, "total_tokens": 324704} {"current_steps": 335, "total_steps": 42420, "loss": 0.4442, "lr": 3.936822253653937e-06, "epoch": 0.15794436586515795, "percentage": 0.79, "elapsed_time": "0:01:09", "remaining_time": "2:26:13", "throughput": 4726.58, "total_tokens": 330112} {"current_steps": 340, "total_steps": 42420, "loss": 0.592, "lr": 3.995756718528996e-06, "epoch": 0.1603017444601603, "percentage": 0.8, "elapsed_time": "0:01:11", "remaining_time": "2:27:19", "throughput": 4732.21, "total_tokens": 337984} {"current_steps": 345, "total_steps": 42420, "loss": 0.6602, "lr": 4.054691183404055e-06, "epoch": 0.16265912305516267, "percentage": 0.81, "elapsed_time": "0:01:12", "remaining_time": "2:27:18", "throughput": 4734.87, "total_tokens": 343136} {"current_steps": 350, "total_steps": 42420, "loss": 0.4025, "lr": 4.113625648279114e-06, "epoch": 0.16501650165016502, "percentage": 0.83, "elapsed_time": "0:01:13", "remaining_time": "2:27:34", "throughput": 4737.58, "total_tokens": 348992} {"current_steps": 355, "total_steps": 42420, "loss": 0.6274, "lr": 4.172560113154173e-06, "epoch": 0.16737388024516736, "percentage": 0.84, "elapsed_time": "0:01:14", "remaining_time": "2:27:20", "throughput": 4738.24, "total_tokens": 353504} {"current_steps": 360, "total_steps": 42420, "loss": 0.4134, "lr": 4.231494578029232e-06, "epoch": 0.16973125884016974, "percentage": 0.85, "elapsed_time": "0:01:15", "remaining_time": "2:27:30", "throughput": 4740.35, "total_tokens": 359104} {"current_steps": 365, "total_steps": 42420, "loss": 0.3022, "lr": 4.29042904290429e-06, "epoch": 0.17208863743517208, "percentage": 0.86, "elapsed_time": "0:01:16", "remaining_time": "2:27:23", "throughput": 4739.01, "total_tokens": 363744} {"current_steps": 370, "total_steps": 42420, "loss": 0.6321, "lr": 4.34936350777935e-06, "epoch": 0.17444601603017446, "percentage": 0.87, "elapsed_time": "0:01:17", "remaining_time": "2:27:22", "throughput": 4740.64, "total_tokens": 368864} {"current_steps": 375, "total_steps": 42420, "loss": 0.4408, "lr": 4.408297972654409e-06, "epoch": 0.1768033946251768, "percentage": 0.88, "elapsed_time": "0:01:18", "remaining_time": "2:27:20", "throughput": 4741.12, "total_tokens": 373824} {"current_steps": 380, "total_steps": 42420, "loss": 0.4899, "lr": 4.467232437529468e-06, "epoch": 0.17916077322017915, "percentage": 0.9, "elapsed_time": "0:01:19", "remaining_time": "2:27:18", "throughput": 4736.98, "total_tokens": 378432} {"current_steps": 385, "total_steps": 42420, "loss": 0.3939, "lr": 4.526166902404526e-06, "epoch": 0.18151815181518152, "percentage": 0.91, "elapsed_time": "0:01:20", "remaining_time": "2:27:21", "throughput": 4736.47, "total_tokens": 383552} {"current_steps": 390, "total_steps": 42420, "loss": 0.5403, "lr": 4.585101367279585e-06, "epoch": 0.18387553041018387, "percentage": 0.92, "elapsed_time": "0:01:22", "remaining_time": "2:27:23", "throughput": 4737.41, "total_tokens": 388768} {"current_steps": 395, "total_steps": 42420, "loss": 0.2605, "lr": 4.644035832154645e-06, "epoch": 0.18623290900518624, "percentage": 0.93, "elapsed_time": "0:01:22", "remaining_time": "2:27:09", "throughput": 4737.09, "total_tokens": 393120} {"current_steps": 400, "total_steps": 42420, "loss": 0.2928, "lr": 4.702970297029704e-06, "epoch": 0.1885902876001886, "percentage": 0.94, "elapsed_time": "0:01:23", "remaining_time": "2:27:02", "throughput": 4737.52, "total_tokens": 397856} {"current_steps": 405, "total_steps": 42420, "loss": 0.5416, "lr": 4.7619047619047615e-06, "epoch": 0.19094766619519093, "percentage": 0.95, "elapsed_time": "0:01:25", "remaining_time": "2:26:58", "throughput": 4739.14, "total_tokens": 402848} {"current_steps": 410, "total_steps": 42420, "loss": 0.4452, "lr": 4.820839226779821e-06, "epoch": 0.1933050447901933, "percentage": 0.97, "elapsed_time": "0:01:26", "remaining_time": "2:26:56", "throughput": 4741.03, "total_tokens": 407936} {"current_steps": 415, "total_steps": 42420, "loss": 0.5347, "lr": 4.87977369165488e-06, "epoch": 0.19566242338519566, "percentage": 0.98, "elapsed_time": "0:01:27", "remaining_time": "2:26:55", "throughput": 4742.18, "total_tokens": 413024} {"current_steps": 420, "total_steps": 42420, "loss": 0.6823, "lr": 4.93870815652994e-06, "epoch": 0.19801980198019803, "percentage": 0.99, "elapsed_time": "0:01:28", "remaining_time": "2:27:08", "throughput": 4742.57, "total_tokens": 418720} {"current_steps": 425, "total_steps": 42420, "loss": 0.4375, "lr": 4.9976426214049975e-06, "epoch": 0.20037718057520038, "percentage": 1.0, "elapsed_time": "0:01:29", "remaining_time": "2:27:41", "throughput": 4743.87, "total_tokens": 425440} {"current_steps": 430, "total_steps": 42420, "loss": 0.796, "lr": 5.056577086280056e-06, "epoch": 0.20273455917020272, "percentage": 1.01, "elapsed_time": "0:01:30", "remaining_time": "2:27:40", "throughput": 4744.18, "total_tokens": 430464} {"current_steps": 435, "total_steps": 42420, "loss": 0.5042, "lr": 5.115511551155116e-06, "epoch": 0.2050919377652051, "percentage": 1.03, "elapsed_time": "0:01:31", "remaining_time": "2:27:43", "throughput": 4745.53, "total_tokens": 435776} {"current_steps": 440, "total_steps": 42420, "loss": 0.3152, "lr": 5.174446016030175e-06, "epoch": 0.20744931636020744, "percentage": 1.04, "elapsed_time": "0:01:32", "remaining_time": "2:27:36", "throughput": 4743.68, "total_tokens": 440352} {"current_steps": 445, "total_steps": 42420, "loss": 0.4815, "lr": 5.2333804809052335e-06, "epoch": 0.20980669495520982, "percentage": 1.05, "elapsed_time": "0:01:33", "remaining_time": "2:27:22", "throughput": 4744.37, "total_tokens": 444768} {"current_steps": 450, "total_steps": 42420, "loss": 0.6835, "lr": 5.292314945780292e-06, "epoch": 0.21216407355021216, "percentage": 1.06, "elapsed_time": "0:01:34", "remaining_time": "2:27:32", "throughput": 4746.47, "total_tokens": 450528} {"current_steps": 455, "total_steps": 42420, "loss": 0.969, "lr": 5.351249410655351e-06, "epoch": 0.2145214521452145, "percentage": 1.07, "elapsed_time": "0:01:35", "remaining_time": "2:27:23", "throughput": 4745.31, "total_tokens": 454976} {"current_steps": 460, "total_steps": 42420, "loss": 0.9386, "lr": 5.410183875530411e-06, "epoch": 0.21687883074021688, "percentage": 1.08, "elapsed_time": "0:01:36", "remaining_time": "2:27:04", "throughput": 4745.22, "total_tokens": 459072} {"current_steps": 465, "total_steps": 42420, "loss": 0.4296, "lr": 5.4691183404054695e-06, "epoch": 0.21923620933521923, "percentage": 1.1, "elapsed_time": "0:01:37", "remaining_time": "2:27:06", "throughput": 4746.44, "total_tokens": 464320} {"current_steps": 470, "total_steps": 42420, "loss": 0.2475, "lr": 5.528052805280528e-06, "epoch": 0.2215935879302216, "percentage": 1.11, "elapsed_time": "0:01:38", "remaining_time": "2:27:00", "throughput": 4746.98, "total_tokens": 469120} {"current_steps": 475, "total_steps": 42420, "loss": 0.6134, "lr": 5.586987270155587e-06, "epoch": 0.22395096652522395, "percentage": 1.12, "elapsed_time": "0:01:39", "remaining_time": "2:26:55", "throughput": 4747.25, "total_tokens": 473920} {"current_steps": 480, "total_steps": 42420, "loss": 0.7439, "lr": 5.645921735030646e-06, "epoch": 0.2263083451202263, "percentage": 1.13, "elapsed_time": "0:01:40", "remaining_time": "2:26:41", "throughput": 4744.61, "total_tokens": 477920} {"current_steps": 485, "total_steps": 42420, "loss": 0.639, "lr": 5.7048561999057055e-06, "epoch": 0.22866572371522867, "percentage": 1.14, "elapsed_time": "0:01:41", "remaining_time": "2:26:41", "throughput": 4745.35, "total_tokens": 483040} {"current_steps": 490, "total_steps": 42420, "loss": 0.8233, "lr": 5.763790664780764e-06, "epoch": 0.23102310231023102, "percentage": 1.16, "elapsed_time": "0:01:42", "remaining_time": "2:26:37", "throughput": 4745.18, "total_tokens": 487872} {"current_steps": 495, "total_steps": 42420, "loss": 0.287, "lr": 5.822725129655823e-06, "epoch": 0.2333804809052334, "percentage": 1.17, "elapsed_time": "0:01:43", "remaining_time": "2:26:35", "throughput": 4747.18, "total_tokens": 492960} {"current_steps": 500, "total_steps": 42420, "loss": 0.1795, "lr": 5.881659594530882e-06, "epoch": 0.23573785950023574, "percentage": 1.18, "elapsed_time": "0:01:44", "remaining_time": "2:26:39", "throughput": 4748.49, "total_tokens": 498400} {"current_steps": 505, "total_steps": 42420, "loss": 0.27, "lr": 5.940594059405941e-06, "epoch": 0.23809523809523808, "percentage": 1.19, "elapsed_time": "0:01:45", "remaining_time": "2:26:27", "throughput": 4748.69, "total_tokens": 502784} {"current_steps": 510, "total_steps": 42420, "loss": 0.4226, "lr": 5.999528524281e-06, "epoch": 0.24045261669024046, "percentage": 1.2, "elapsed_time": "0:01:46", "remaining_time": "2:26:26", "throughput": 4748.99, "total_tokens": 507776} {"current_steps": 515, "total_steps": 42420, "loss": 0.2738, "lr": 6.058462989156059e-06, "epoch": 0.2428099952852428, "percentage": 1.21, "elapsed_time": "0:01:47", "remaining_time": "2:26:19", "throughput": 4749.65, "total_tokens": 512480} {"current_steps": 520, "total_steps": 42420, "loss": 0.4753, "lr": 6.117397454031118e-06, "epoch": 0.24516737388024518, "percentage": 1.23, "elapsed_time": "0:01:49", "remaining_time": "2:26:24", "throughput": 4747.97, "total_tokens": 517600} {"current_steps": 525, "total_steps": 42420, "loss": 0.5113, "lr": 6.176331918906177e-06, "epoch": 0.24752475247524752, "percentage": 1.24, "elapsed_time": "0:01:50", "remaining_time": "2:26:35", "throughput": 4749.79, "total_tokens": 523520} {"current_steps": 530, "total_steps": 42420, "loss": 0.321, "lr": 6.235266383781235e-06, "epoch": 0.24988213107024987, "percentage": 1.25, "elapsed_time": "0:01:51", "remaining_time": "2:26:20", "throughput": 4748.94, "total_tokens": 527584} {"current_steps": 535, "total_steps": 42420, "loss": 0.621, "lr": 6.294200848656294e-06, "epoch": 0.2522395096652522, "percentage": 1.26, "elapsed_time": "0:01:52", "remaining_time": "2:26:21", "throughput": 4749.35, "total_tokens": 532736} {"current_steps": 540, "total_steps": 42420, "loss": 0.6177, "lr": 6.353135313531354e-06, "epoch": 0.2545968882602546, "percentage": 1.27, "elapsed_time": "0:01:53", "remaining_time": "2:26:19", "throughput": 4747.44, "total_tokens": 537440} {"current_steps": 545, "total_steps": 42420, "loss": 0.4219, "lr": 6.412069778406413e-06, "epoch": 0.25695426685525696, "percentage": 1.28, "elapsed_time": "0:01:54", "remaining_time": "2:26:25", "throughput": 4749.18, "total_tokens": 543040} {"current_steps": 550, "total_steps": 42420, "loss": 0.7427, "lr": 6.471004243281471e-06, "epoch": 0.2593116454502593, "percentage": 1.3, "elapsed_time": "0:01:55", "remaining_time": "2:26:16", "throughput": 4748.95, "total_tokens": 547520} {"current_steps": 555, "total_steps": 42420, "loss": 0.2734, "lr": 6.52993870815653e-06, "epoch": 0.26166902404526166, "percentage": 1.31, "elapsed_time": "0:01:56", "remaining_time": "2:26:19", "throughput": 4749.44, "total_tokens": 552800} {"current_steps": 560, "total_steps": 42420, "loss": 0.097, "lr": 6.588873173031589e-06, "epoch": 0.264026402640264, "percentage": 1.32, "elapsed_time": "0:01:57", "remaining_time": "2:26:12", "throughput": 4749.43, "total_tokens": 557376} {"current_steps": 565, "total_steps": 42420, "loss": 0.2308, "lr": 6.647807637906649e-06, "epoch": 0.2663837812352664, "percentage": 1.33, "elapsed_time": "0:01:58", "remaining_time": "2:26:29", "throughput": 4751.59, "total_tokens": 563776} {"current_steps": 570, "total_steps": 42420, "loss": 0.5513, "lr": 6.706742102781707e-06, "epoch": 0.26874115983026875, "percentage": 1.34, "elapsed_time": "0:01:59", "remaining_time": "2:26:13", "throughput": 4750.66, "total_tokens": 567712} {"current_steps": 575, "total_steps": 42420, "loss": 0.4007, "lr": 6.765676567656766e-06, "epoch": 0.2710985384252711, "percentage": 1.36, "elapsed_time": "0:02:00", "remaining_time": "2:26:16", "throughput": 4751.1, "total_tokens": 572992} {"current_steps": 580, "total_steps": 42420, "loss": 0.3548, "lr": 6.824611032531825e-06, "epoch": 0.27345591702027344, "percentage": 1.37, "elapsed_time": "0:02:01", "remaining_time": "2:26:24", "throughput": 4753.16, "total_tokens": 578816} {"current_steps": 585, "total_steps": 42420, "loss": 0.4592, "lr": 6.883545497406884e-06, "epoch": 0.2758132956152758, "percentage": 1.38, "elapsed_time": "0:02:02", "remaining_time": "2:26:18", "throughput": 4753.75, "total_tokens": 583552} {"current_steps": 590, "total_steps": 42420, "loss": 0.3921, "lr": 6.942479962281943e-06, "epoch": 0.2781706742102782, "percentage": 1.39, "elapsed_time": "0:02:03", "remaining_time": "2:26:26", "throughput": 4751.73, "total_tokens": 588864} {"current_steps": 595, "total_steps": 42420, "loss": 0.294, "lr": 7.001414427157002e-06, "epoch": 0.28052805280528054, "percentage": 1.4, "elapsed_time": "0:02:04", "remaining_time": "2:26:16", "throughput": 4751.38, "total_tokens": 593248} {"current_steps": 600, "total_steps": 42420, "loss": 0.4681, "lr": 7.060348892032061e-06, "epoch": 0.2828854314002829, "percentage": 1.41, "elapsed_time": "0:02:06", "remaining_time": "2:26:28", "throughput": 4753.28, "total_tokens": 599360} {"current_steps": 605, "total_steps": 42420, "loss": 0.3951, "lr": 7.11928335690712e-06, "epoch": 0.28524280999528523, "percentage": 1.43, "elapsed_time": "0:02:07", "remaining_time": "2:26:28", "throughput": 4752.7, "total_tokens": 604352} {"current_steps": 610, "total_steps": 42420, "loss": 0.3012, "lr": 7.178217821782178e-06, "epoch": 0.2876001885902876, "percentage": 1.44, "elapsed_time": "0:02:08", "remaining_time": "2:26:32", "throughput": 4754.95, "total_tokens": 609952} {"current_steps": 615, "total_steps": 42420, "loss": 0.2812, "lr": 7.237152286657238e-06, "epoch": 0.28995756718529, "percentage": 1.45, "elapsed_time": "0:02:09", "remaining_time": "2:26:27", "throughput": 4752.89, "total_tokens": 614400} {"current_steps": 620, "total_steps": 42420, "loss": 0.5168, "lr": 7.296086751532297e-06, "epoch": 0.2923149457802923, "percentage": 1.46, "elapsed_time": "0:02:10", "remaining_time": "2:26:27", "throughput": 4753.46, "total_tokens": 619552} {"current_steps": 625, "total_steps": 42420, "loss": 0.4996, "lr": 7.355021216407356e-06, "epoch": 0.29467232437529467, "percentage": 1.47, "elapsed_time": "0:02:11", "remaining_time": "2:26:29", "throughput": 4754.6, "total_tokens": 624960} {"current_steps": 630, "total_steps": 42420, "loss": 0.5305, "lr": 7.413955681282414e-06, "epoch": 0.297029702970297, "percentage": 1.49, "elapsed_time": "0:02:12", "remaining_time": "2:26:46", "throughput": 4756.8, "total_tokens": 631520} {"current_steps": 635, "total_steps": 42420, "loss": 0.5969, "lr": 7.472890146157472e-06, "epoch": 0.29938708156529936, "percentage": 1.5, "elapsed_time": "0:02:13", "remaining_time": "2:26:57", "throughput": 4758.14, "total_tokens": 637568} {"current_steps": 640, "total_steps": 42420, "loss": 0.3699, "lr": 7.531824611032533e-06, "epoch": 0.30174446016030176, "percentage": 1.51, "elapsed_time": "0:02:15", "remaining_time": "2:26:58", "throughput": 4757.54, "total_tokens": 642688} {"current_steps": 645, "total_steps": 42420, "loss": 0.2283, "lr": 7.590759075907592e-06, "epoch": 0.3041018387553041, "percentage": 1.52, "elapsed_time": "0:02:16", "remaining_time": "2:26:52", "throughput": 4757.98, "total_tokens": 647392} {"current_steps": 650, "total_steps": 42420, "loss": 0.4409, "lr": 7.64969354078265e-06, "epoch": 0.30645921735030646, "percentage": 1.53, "elapsed_time": "0:02:17", "remaining_time": "2:26:55", "throughput": 4758.68, "total_tokens": 652800} {"current_steps": 655, "total_steps": 42420, "loss": 0.3304, "lr": 7.708628005657708e-06, "epoch": 0.3088165959453088, "percentage": 1.54, "elapsed_time": "0:02:18", "remaining_time": "2:27:11", "throughput": 4760.13, "total_tokens": 659328} {"current_steps": 660, "total_steps": 42420, "loss": 0.2569, "lr": 7.767562470532768e-06, "epoch": 0.31117397454031115, "percentage": 1.56, "elapsed_time": "0:02:19", "remaining_time": "2:27:00", "throughput": 4759.31, "total_tokens": 663488} {"current_steps": 665, "total_steps": 42420, "loss": 0.1859, "lr": 7.826496935407828e-06, "epoch": 0.31353135313531355, "percentage": 1.57, "elapsed_time": "0:02:20", "remaining_time": "2:26:55", "throughput": 4759.42, "total_tokens": 668192} {"current_steps": 670, "total_steps": 42420, "loss": 0.7881, "lr": 7.885431400282886e-06, "epoch": 0.3158887317303159, "percentage": 1.58, "elapsed_time": "0:02:21", "remaining_time": "2:26:58", "throughput": 4759.59, "total_tokens": 673568} {"current_steps": 675, "total_steps": 42420, "loss": 0.3943, "lr": 7.944365865157945e-06, "epoch": 0.31824611032531824, "percentage": 1.59, "elapsed_time": "0:02:23", "remaining_time": "2:27:26", "throughput": 4761.23, "total_tokens": 681056} {"current_steps": 680, "total_steps": 42420, "loss": 0.3098, "lr": 8.003300330033003e-06, "epoch": 0.3206034889203206, "percentage": 1.6, "elapsed_time": "0:02:24", "remaining_time": "2:27:25", "throughput": 4759.77, "total_tokens": 685920} {"current_steps": 685, "total_steps": 42420, "loss": 0.3183, "lr": 8.062234794908063e-06, "epoch": 0.32296086751532294, "percentage": 1.61, "elapsed_time": "0:02:25", "remaining_time": "2:27:21", "throughput": 4760.24, "total_tokens": 690816} {"current_steps": 690, "total_steps": 42420, "loss": 0.2954, "lr": 8.121169259783122e-06, "epoch": 0.32531824611032534, "percentage": 1.63, "elapsed_time": "0:02:26", "remaining_time": "2:27:17", "throughput": 4760.83, "total_tokens": 695648} {"current_steps": 695, "total_steps": 42420, "loss": 0.0966, "lr": 8.18010372465818e-06, "epoch": 0.3276756247053277, "percentage": 1.64, "elapsed_time": "0:02:27", "remaining_time": "2:27:18", "throughput": 4761.17, "total_tokens": 700960} {"current_steps": 700, "total_steps": 42420, "loss": 0.119, "lr": 8.23903818953324e-06, "epoch": 0.33003300330033003, "percentage": 1.65, "elapsed_time": "0:02:28", "remaining_time": "2:27:14", "throughput": 4761.92, "total_tokens": 705856} {"current_steps": 705, "total_steps": 42420, "loss": 0.2717, "lr": 8.297972654408298e-06, "epoch": 0.3323903818953324, "percentage": 1.66, "elapsed_time": "0:02:29", "remaining_time": "2:27:05", "throughput": 4761.8, "total_tokens": 710272} {"current_steps": 710, "total_steps": 42420, "loss": 0.4655, "lr": 8.356907119283356e-06, "epoch": 0.3347477604903347, "percentage": 1.67, "elapsed_time": "0:02:30", "remaining_time": "2:26:59", "throughput": 4761.43, "total_tokens": 714816} {"current_steps": 715, "total_steps": 42420, "loss": 1.053, "lr": 8.415841584158417e-06, "epoch": 0.3371051390853371, "percentage": 1.69, "elapsed_time": "0:02:31", "remaining_time": "2:27:07", "throughput": 4762.26, "total_tokens": 720736} {"current_steps": 720, "total_steps": 42420, "loss": 0.2614, "lr": 8.474776049033475e-06, "epoch": 0.33946251768033947, "percentage": 1.7, "elapsed_time": "0:02:32", "remaining_time": "2:27:17", "throughput": 4763.18, "total_tokens": 726848} {"current_steps": 725, "total_steps": 42420, "loss": 0.6954, "lr": 8.533710513908535e-06, "epoch": 0.3418198962753418, "percentage": 1.71, "elapsed_time": "0:02:33", "remaining_time": "2:27:21", "throughput": 4764.57, "total_tokens": 732512} {"current_steps": 730, "total_steps": 42420, "loss": 0.3064, "lr": 8.592644978783593e-06, "epoch": 0.34417727487034416, "percentage": 1.72, "elapsed_time": "0:02:34", "remaining_time": "2:27:23", "throughput": 4765.38, "total_tokens": 737952} {"current_steps": 735, "total_steps": 42420, "loss": 0.2503, "lr": 8.65157944365865e-06, "epoch": 0.3465346534653465, "percentage": 1.73, "elapsed_time": "0:02:35", "remaining_time": "2:27:18", "throughput": 4765.93, "total_tokens": 742752} {"current_steps": 740, "total_steps": 42420, "loss": 0.9087, "lr": 8.710513908533712e-06, "epoch": 0.3488920320603489, "percentage": 1.74, "elapsed_time": "0:02:36", "remaining_time": "2:27:16", "throughput": 4767.32, "total_tokens": 747968} {"current_steps": 745, "total_steps": 42420, "loss": 0.4773, "lr": 8.76944837340877e-06, "epoch": 0.35124941065535126, "percentage": 1.76, "elapsed_time": "0:02:38", "remaining_time": "2:27:20", "throughput": 4768.47, "total_tokens": 753632} {"current_steps": 750, "total_steps": 42420, "loss": 0.3417, "lr": 8.82838283828383e-06, "epoch": 0.3536067892503536, "percentage": 1.77, "elapsed_time": "0:02:39", "remaining_time": "2:27:31", "throughput": 4769.7, "total_tokens": 759904} {"current_steps": 755, "total_steps": 42420, "loss": 0.8336, "lr": 8.887317303158887e-06, "epoch": 0.35596416784535595, "percentage": 1.78, "elapsed_time": "0:02:40", "remaining_time": "2:27:29", "throughput": 4770.03, "total_tokens": 764960} {"current_steps": 760, "total_steps": 42420, "loss": 0.3557, "lr": 8.946251768033945e-06, "epoch": 0.3583215464403583, "percentage": 1.79, "elapsed_time": "0:02:41", "remaining_time": "2:27:20", "throughput": 4769.6, "total_tokens": 769184} {"current_steps": 765, "total_steps": 42420, "loss": 0.3932, "lr": 9.005186232909007e-06, "epoch": 0.3606789250353607, "percentage": 1.8, "elapsed_time": "0:02:42", "remaining_time": "2:27:26", "throughput": 4770.93, "total_tokens": 775104} {"current_steps": 770, "total_steps": 42420, "loss": 0.2737, "lr": 9.064120697784065e-06, "epoch": 0.36303630363036304, "percentage": 1.82, "elapsed_time": "0:02:43", "remaining_time": "2:27:20", "throughput": 4770.79, "total_tokens": 779744} {"current_steps": 775, "total_steps": 42420, "loss": 0.1985, "lr": 9.123055162659123e-06, "epoch": 0.3653936822253654, "percentage": 1.83, "elapsed_time": "0:02:44", "remaining_time": "2:27:18", "throughput": 4771.35, "total_tokens": 784832} {"current_steps": 780, "total_steps": 42420, "loss": 0.2983, "lr": 9.181989627534182e-06, "epoch": 0.36775106082036774, "percentage": 1.84, "elapsed_time": "0:02:45", "remaining_time": "2:27:17", "throughput": 4771.54, "total_tokens": 789920} {"current_steps": 785, "total_steps": 42420, "loss": 0.1321, "lr": 9.24092409240924e-06, "epoch": 0.3701084394153701, "percentage": 1.85, "elapsed_time": "0:02:46", "remaining_time": "2:27:19", "throughput": 4770.85, "total_tokens": 795168} {"current_steps": 790, "total_steps": 42420, "loss": 0.2687, "lr": 9.299858557284302e-06, "epoch": 0.3724658180103725, "percentage": 1.86, "elapsed_time": "0:02:47", "remaining_time": "2:27:17", "throughput": 4770.97, "total_tokens": 800096} {"current_steps": 795, "total_steps": 42420, "loss": 0.4568, "lr": 9.35879302215936e-06, "epoch": 0.37482319660537483, "percentage": 1.87, "elapsed_time": "0:02:48", "remaining_time": "2:27:20", "throughput": 4771.57, "total_tokens": 805632} {"current_steps": 800, "total_steps": 42420, "loss": 0.4557, "lr": 9.417727487034417e-06, "epoch": 0.3771805752003772, "percentage": 1.89, "elapsed_time": "0:02:49", "remaining_time": "2:27:18", "throughput": 4771.67, "total_tokens": 810688} {"current_steps": 805, "total_steps": 42420, "loss": 0.4632, "lr": 9.476661951909477e-06, "epoch": 0.3795379537953795, "percentage": 1.9, "elapsed_time": "0:02:50", "remaining_time": "2:27:13", "throughput": 4771.14, "total_tokens": 815264} {"current_steps": 810, "total_steps": 42420, "loss": 0.3664, "lr": 9.535596416784535e-06, "epoch": 0.38189533239038187, "percentage": 1.91, "elapsed_time": "0:02:51", "remaining_time": "2:27:13", "throughput": 4770.75, "total_tokens": 820320} {"current_steps": 815, "total_steps": 42420, "loss": 0.5474, "lr": 9.594530881659596e-06, "epoch": 0.38425271098538427, "percentage": 1.92, "elapsed_time": "0:02:52", "remaining_time": "2:27:01", "throughput": 4768.58, "total_tokens": 824064} {"current_steps": 820, "total_steps": 42420, "loss": 0.1674, "lr": 9.653465346534654e-06, "epoch": 0.3866100895803866, "percentage": 1.93, "elapsed_time": "0:02:53", "remaining_time": "2:26:59", "throughput": 4769.16, "total_tokens": 829120} {"current_steps": 825, "total_steps": 42420, "loss": 0.4126, "lr": 9.712399811409712e-06, "epoch": 0.38896746817538896, "percentage": 1.94, "elapsed_time": "0:02:55", "remaining_time": "2:27:04", "throughput": 4769.89, "total_tokens": 834816} {"current_steps": 830, "total_steps": 42420, "loss": 0.2481, "lr": 9.771334276284772e-06, "epoch": 0.3913248467703913, "percentage": 1.96, "elapsed_time": "0:02:56", "remaining_time": "2:27:05", "throughput": 4770.55, "total_tokens": 840256} {"current_steps": 835, "total_steps": 42420, "loss": 0.1093, "lr": 9.83026874115983e-06, "epoch": 0.39368222536539366, "percentage": 1.97, "elapsed_time": "0:02:57", "remaining_time": "2:26:59", "throughput": 4770.68, "total_tokens": 844864} {"current_steps": 840, "total_steps": 42420, "loss": 0.2687, "lr": 9.88920320603489e-06, "epoch": 0.39603960396039606, "percentage": 1.98, "elapsed_time": "0:02:58", "remaining_time": "2:27:01", "throughput": 4771.3, "total_tokens": 850304} {"current_steps": 845, "total_steps": 42420, "loss": 0.085, "lr": 9.948137670909949e-06, "epoch": 0.3983969825553984, "percentage": 1.99, "elapsed_time": "0:02:59", "remaining_time": "2:26:58", "throughput": 4771.42, "total_tokens": 855232} {"current_steps": 850, "total_steps": 42420, "loss": 0.4871, "lr": 1.0007072135785007e-05, "epoch": 0.40075436115040075, "percentage": 2.0, "elapsed_time": "0:03:00", "remaining_time": "2:26:55", "throughput": 4771.9, "total_tokens": 860128} {"current_steps": 855, "total_steps": 42420, "loss": 0.4733, "lr": 1.0066006600660067e-05, "epoch": 0.4031117397454031, "percentage": 2.02, "elapsed_time": "0:03:01", "remaining_time": "2:26:49", "throughput": 4772.57, "total_tokens": 864896} {"current_steps": 860, "total_steps": 42420, "loss": 0.4257, "lr": 1.0124941065535125e-05, "epoch": 0.40546911834040544, "percentage": 2.03, "elapsed_time": "0:03:02", "remaining_time": "2:26:43", "throughput": 4772.61, "total_tokens": 869408} {"current_steps": 865, "total_steps": 42420, "loss": 0.2301, "lr": 1.0183875530410184e-05, "epoch": 0.40782649693540785, "percentage": 2.04, "elapsed_time": "0:03:03", "remaining_time": "2:26:39", "throughput": 4772.49, "total_tokens": 874144} {"current_steps": 870, "total_steps": 42420, "loss": 0.5145, "lr": 1.0242809995285244e-05, "epoch": 0.4101838755304102, "percentage": 2.05, "elapsed_time": "0:03:04", "remaining_time": "2:26:36", "throughput": 4772.28, "total_tokens": 879040} {"current_steps": 875, "total_steps": 42420, "loss": 0.3263, "lr": 1.0301744460160302e-05, "epoch": 0.41254125412541254, "percentage": 2.06, "elapsed_time": "0:03:05", "remaining_time": "2:26:32", "throughput": 4771.94, "total_tokens": 883712} {"current_steps": 880, "total_steps": 42420, "loss": 0.3429, "lr": 1.0360678925035361e-05, "epoch": 0.4148986327204149, "percentage": 2.07, "elapsed_time": "0:03:06", "remaining_time": "2:26:26", "throughput": 4771.39, "total_tokens": 888128} {"current_steps": 885, "total_steps": 42420, "loss": 0.1917, "lr": 1.041961338991042e-05, "epoch": 0.41725601131541723, "percentage": 2.09, "elapsed_time": "0:03:07", "remaining_time": "2:26:34", "throughput": 4772.04, "total_tokens": 894240} {"current_steps": 890, "total_steps": 42420, "loss": 0.1971, "lr": 1.0478547854785479e-05, "epoch": 0.41961338991041963, "percentage": 2.1, "elapsed_time": "0:03:08", "remaining_time": "2:26:33", "throughput": 4772.95, "total_tokens": 899456} {"current_steps": 895, "total_steps": 42420, "loss": 0.1898, "lr": 1.0537482319660539e-05, "epoch": 0.421970768505422, "percentage": 2.11, "elapsed_time": "0:03:09", "remaining_time": "2:26:34", "throughput": 4772.96, "total_tokens": 904672} {"current_steps": 900, "total_steps": 42420, "loss": 0.2383, "lr": 1.0596416784535597e-05, "epoch": 0.4243281471004243, "percentage": 2.12, "elapsed_time": "0:03:11", "remaining_time": "2:27:05", "throughput": 4773.55, "total_tokens": 913216} {"current_steps": 905, "total_steps": 42420, "loss": 0.4947, "lr": 1.0655351249410656e-05, "epoch": 0.42668552569542667, "percentage": 2.13, "elapsed_time": "0:03:12", "remaining_time": "2:26:58", "throughput": 4773.38, "total_tokens": 917664} {"current_steps": 910, "total_steps": 42420, "loss": 0.2127, "lr": 1.0714285714285714e-05, "epoch": 0.429042904290429, "percentage": 2.15, "elapsed_time": "0:03:13", "remaining_time": "2:27:02", "throughput": 4774.22, "total_tokens": 923360} {"current_steps": 915, "total_steps": 42420, "loss": 0.1959, "lr": 1.0773220179160774e-05, "epoch": 0.4314002828854314, "percentage": 2.16, "elapsed_time": "0:03:14", "remaining_time": "2:27:02", "throughput": 4774.2, "total_tokens": 928608} {"current_steps": 920, "total_steps": 42420, "loss": 0.15, "lr": 1.0832154644035833e-05, "epoch": 0.43375766148043376, "percentage": 2.17, "elapsed_time": "0:03:15", "remaining_time": "2:26:58", "throughput": 4774.22, "total_tokens": 933312} {"current_steps": 925, "total_steps": 42420, "loss": 0.3495, "lr": 1.0891089108910891e-05, "epoch": 0.4361150400754361, "percentage": 2.18, "elapsed_time": "0:03:16", "remaining_time": "2:26:51", "throughput": 4774.25, "total_tokens": 937824} {"current_steps": 930, "total_steps": 42420, "loss": 0.4271, "lr": 1.0950023573785951e-05, "epoch": 0.43847241867043846, "percentage": 2.19, "elapsed_time": "0:03:17", "remaining_time": "2:26:44", "throughput": 4773.15, "total_tokens": 942016} {"current_steps": 935, "total_steps": 42420, "loss": 0.3949, "lr": 1.1008958038661009e-05, "epoch": 0.4408297972654408, "percentage": 2.2, "elapsed_time": "0:03:18", "remaining_time": "2:26:36", "throughput": 4772.24, "total_tokens": 946080} {"current_steps": 940, "total_steps": 42420, "loss": 0.0851, "lr": 1.1067892503536068e-05, "epoch": 0.4431871758604432, "percentage": 2.22, "elapsed_time": "0:03:19", "remaining_time": "2:26:34", "throughput": 4772.61, "total_tokens": 951168} {"current_steps": 945, "total_steps": 42420, "loss": 0.2705, "lr": 1.1126826968411128e-05, "epoch": 0.44554455445544555, "percentage": 2.23, "elapsed_time": "0:03:20", "remaining_time": "2:26:39", "throughput": 4773.16, "total_tokens": 956992} {"current_steps": 950, "total_steps": 42420, "loss": 0.1497, "lr": 1.1185761433286186e-05, "epoch": 0.4479019330504479, "percentage": 2.24, "elapsed_time": "0:03:21", "remaining_time": "2:26:31", "throughput": 4772.72, "total_tokens": 961248} {"current_steps": 955, "total_steps": 42420, "loss": 0.3383, "lr": 1.1244695898161246e-05, "epoch": 0.45025931164545024, "percentage": 2.25, "elapsed_time": "0:03:22", "remaining_time": "2:26:22", "throughput": 4772.5, "total_tokens": 965376} {"current_steps": 960, "total_steps": 42420, "loss": 0.4261, "lr": 1.1303630363036304e-05, "epoch": 0.4526166902404526, "percentage": 2.26, "elapsed_time": "0:03:23", "remaining_time": "2:26:16", "throughput": 4771.67, "total_tokens": 969664} {"current_steps": 965, "total_steps": 42420, "loss": 0.1665, "lr": 1.1362564827911363e-05, "epoch": 0.454974068835455, "percentage": 2.27, "elapsed_time": "0:03:24", "remaining_time": "2:26:10", "throughput": 4770.99, "total_tokens": 974016} {"current_steps": 970, "total_steps": 42420, "loss": 0.5085, "lr": 1.1421499292786423e-05, "epoch": 0.45733144743045734, "percentage": 2.29, "elapsed_time": "0:03:25", "remaining_time": "2:26:08", "throughput": 4771.62, "total_tokens": 979072} {"current_steps": 975, "total_steps": 42420, "loss": 0.2772, "lr": 1.148043375766148e-05, "epoch": 0.4596888260254597, "percentage": 2.3, "elapsed_time": "0:03:26", "remaining_time": "2:26:07", "throughput": 4771.07, "total_tokens": 984032} {"current_steps": 980, "total_steps": 42420, "loss": 0.0745, "lr": 1.1539368222536539e-05, "epoch": 0.46204620462046203, "percentage": 2.31, "elapsed_time": "0:03:27", "remaining_time": "2:26:01", "throughput": 4771.04, "total_tokens": 988544} {"current_steps": 985, "total_steps": 42420, "loss": 0.3092, "lr": 1.1598302687411598e-05, "epoch": 0.4644035832154644, "percentage": 2.32, "elapsed_time": "0:03:28", "remaining_time": "2:25:59", "throughput": 4771.37, "total_tokens": 993504} {"current_steps": 990, "total_steps": 42420, "loss": 0.246, "lr": 1.1657237152286658e-05, "epoch": 0.4667609618104668, "percentage": 2.33, "elapsed_time": "0:03:29", "remaining_time": "2:26:01", "throughput": 4772.27, "total_tokens": 999104} {"current_steps": 995, "total_steps": 42420, "loss": 0.2047, "lr": 1.1716171617161718e-05, "epoch": 0.4691183404054691, "percentage": 2.35, "elapsed_time": "0:03:30", "remaining_time": "2:26:05", "throughput": 4772.6, "total_tokens": 1004864} {"current_steps": 1000, "total_steps": 42420, "loss": 0.1107, "lr": 1.1775106082036776e-05, "epoch": 0.47147571900047147, "percentage": 2.36, "elapsed_time": "0:03:31", "remaining_time": "2:26:01", "throughput": 4772.37, "total_tokens": 1009472} {"current_steps": 1005, "total_steps": 42420, "loss": 0.1808, "lr": 1.1834040546911834e-05, "epoch": 0.4738330975954738, "percentage": 2.37, "elapsed_time": "0:03:32", "remaining_time": "2:25:52", "throughput": 4771.93, "total_tokens": 1013536} {"current_steps": 1010, "total_steps": 42420, "loss": 0.1219, "lr": 1.1892975011786893e-05, "epoch": 0.47619047619047616, "percentage": 2.38, "elapsed_time": "0:03:33", "remaining_time": "2:25:47", "throughput": 4772.04, "total_tokens": 1018144} {"current_steps": 1015, "total_steps": 42420, "loss": 0.4522, "lr": 1.1951909476661953e-05, "epoch": 0.47854785478547857, "percentage": 2.39, "elapsed_time": "0:03:34", "remaining_time": "2:25:44", "throughput": 4771.49, "total_tokens": 1022848} {"current_steps": 1020, "total_steps": 42420, "loss": 0.2205, "lr": 1.2010843941537012e-05, "epoch": 0.4809052333804809, "percentage": 2.4, "elapsed_time": "0:03:35", "remaining_time": "2:25:40", "throughput": 4770.86, "total_tokens": 1027424} {"current_steps": 1025, "total_steps": 42420, "loss": 0.3865, "lr": 1.206977840641207e-05, "epoch": 0.48326261197548326, "percentage": 2.42, "elapsed_time": "0:03:36", "remaining_time": "2:25:41", "throughput": 4771.45, "total_tokens": 1032768} {"current_steps": 1030, "total_steps": 42420, "loss": 0.0864, "lr": 1.2128712871287128e-05, "epoch": 0.4856199905704856, "percentage": 2.43, "elapsed_time": "0:03:37", "remaining_time": "2:25:37", "throughput": 4771.33, "total_tokens": 1037440} {"current_steps": 1035, "total_steps": 42420, "loss": 0.1539, "lr": 1.2187647336162188e-05, "epoch": 0.48797736916548795, "percentage": 2.44, "elapsed_time": "0:03:38", "remaining_time": "2:25:35", "throughput": 4771.61, "total_tokens": 1042400} {"current_steps": 1040, "total_steps": 42420, "loss": 0.2106, "lr": 1.2246581801037248e-05, "epoch": 0.49033474776049035, "percentage": 2.45, "elapsed_time": "0:03:39", "remaining_time": "2:25:38", "throughput": 4772.16, "total_tokens": 1048032} {"current_steps": 1045, "total_steps": 42420, "loss": 0.1902, "lr": 1.2305516265912306e-05, "epoch": 0.4926921263554927, "percentage": 2.46, "elapsed_time": "0:03:40", "remaining_time": "2:25:38", "throughput": 4772.71, "total_tokens": 1053408} {"current_steps": 1050, "total_steps": 42420, "loss": 0.2207, "lr": 1.2364450730787365e-05, "epoch": 0.49504950495049505, "percentage": 2.48, "elapsed_time": "0:03:41", "remaining_time": "2:25:41", "throughput": 4773.42, "total_tokens": 1059008} {"current_steps": 1055, "total_steps": 42420, "loss": 0.2487, "lr": 1.2423385195662423e-05, "epoch": 0.4974068835454974, "percentage": 2.49, "elapsed_time": "0:03:42", "remaining_time": "2:25:36", "throughput": 4773.57, "total_tokens": 1063712} {"current_steps": 1060, "total_steps": 42420, "loss": 0.833, "lr": 1.2482319660537483e-05, "epoch": 0.49976426214049974, "percentage": 2.5, "elapsed_time": "0:03:43", "remaining_time": "2:25:33", "throughput": 4772.93, "total_tokens": 1068320} {"current_steps": 1065, "total_steps": 42420, "loss": 0.1598, "lr": 1.254125412541254e-05, "epoch": 0.5021216407355021, "percentage": 2.51, "elapsed_time": "0:03:44", "remaining_time": "2:25:32", "throughput": 4772.69, "total_tokens": 1073280} {"current_steps": 1070, "total_steps": 42420, "loss": 0.2317, "lr": 1.26001885902876e-05, "epoch": 0.5044790193305044, "percentage": 2.52, "elapsed_time": "0:03:45", "remaining_time": "2:25:23", "throughput": 4771.78, "total_tokens": 1077184} {"current_steps": 1075, "total_steps": 42420, "loss": 0.3032, "lr": 1.2659123055162662e-05, "epoch": 0.5068363979255068, "percentage": 2.53, "elapsed_time": "0:03:46", "remaining_time": "2:25:19", "throughput": 4770.87, "total_tokens": 1081664} {"current_steps": 1080, "total_steps": 42420, "loss": 0.2338, "lr": 1.2718057520037718e-05, "epoch": 0.5091937765205092, "percentage": 2.55, "elapsed_time": "0:03:47", "remaining_time": "2:25:15", "throughput": 4770.81, "total_tokens": 1086304} {"current_steps": 1085, "total_steps": 42420, "loss": 0.2001, "lr": 1.277699198491278e-05, "epoch": 0.5115511551155115, "percentage": 2.56, "elapsed_time": "0:03:48", "remaining_time": "2:25:16", "throughput": 4771.01, "total_tokens": 1091616} {"current_steps": 1090, "total_steps": 42420, "loss": 0.1441, "lr": 1.2835926449787835e-05, "epoch": 0.5139085337105139, "percentage": 2.57, "elapsed_time": "0:03:49", "remaining_time": "2:25:08", "throughput": 4770.16, "total_tokens": 1095616} {"current_steps": 1095, "total_steps": 42420, "loss": 0.5524, "lr": 1.2894860914662895e-05, "epoch": 0.5162659123055162, "percentage": 2.58, "elapsed_time": "0:03:50", "remaining_time": "2:25:14", "throughput": 4770.82, "total_tokens": 1101632} {"current_steps": 1100, "total_steps": 42420, "loss": 0.2054, "lr": 1.2953795379537956e-05, "epoch": 0.5186232909005186, "percentage": 2.59, "elapsed_time": "0:03:51", "remaining_time": "2:25:08", "throughput": 4770.78, "total_tokens": 1106080} {"current_steps": 1105, "total_steps": 42420, "loss": 0.1222, "lr": 1.3012729844413013e-05, "epoch": 0.520980669495521, "percentage": 2.6, "elapsed_time": "0:03:52", "remaining_time": "2:25:10", "throughput": 4770.85, "total_tokens": 1111456} {"current_steps": 1110, "total_steps": 42420, "loss": 0.1466, "lr": 1.3071664309288072e-05, "epoch": 0.5233380480905233, "percentage": 2.62, "elapsed_time": "0:03:54", "remaining_time": "2:25:16", "throughput": 4771.82, "total_tokens": 1117632} {"current_steps": 1115, "total_steps": 42420, "loss": 0.1511, "lr": 1.313059877416313e-05, "epoch": 0.5256954266855257, "percentage": 2.63, "elapsed_time": "0:03:55", "remaining_time": "2:25:14", "throughput": 4771.8, "total_tokens": 1122496} {"current_steps": 1120, "total_steps": 42420, "loss": 0.1124, "lr": 1.318953323903819e-05, "epoch": 0.528052805280528, "percentage": 2.64, "elapsed_time": "0:03:56", "remaining_time": "2:25:06", "throughput": 4769.6, "total_tokens": 1126176} {"current_steps": 1125, "total_steps": 42420, "loss": 0.0938, "lr": 1.3248467703913251e-05, "epoch": 0.5304101838755304, "percentage": 2.65, "elapsed_time": "0:03:57", "remaining_time": "2:25:18", "throughput": 4770.06, "total_tokens": 1133024} {"current_steps": 1130, "total_steps": 42420, "loss": 0.0714, "lr": 1.3307402168788307e-05, "epoch": 0.5327675624705328, "percentage": 2.66, "elapsed_time": "0:03:58", "remaining_time": "2:25:17", "throughput": 4770.39, "total_tokens": 1138112} {"current_steps": 1135, "total_steps": 42420, "loss": 0.0988, "lr": 1.3366336633663367e-05, "epoch": 0.5351249410655351, "percentage": 2.68, "elapsed_time": "0:03:59", "remaining_time": "2:25:22", "throughput": 4771.14, "total_tokens": 1144064} {"current_steps": 1140, "total_steps": 42420, "loss": 0.1838, "lr": 1.3425271098538425e-05, "epoch": 0.5374823196605375, "percentage": 2.69, "elapsed_time": "0:04:00", "remaining_time": "2:25:20", "throughput": 4771.05, "total_tokens": 1148992} {"current_steps": 1145, "total_steps": 42420, "loss": 0.1091, "lr": 1.3484205563413485e-05, "epoch": 0.5398396982555398, "percentage": 2.7, "elapsed_time": "0:04:01", "remaining_time": "2:25:23", "throughput": 4771.24, "total_tokens": 1154592} {"current_steps": 1150, "total_steps": 42420, "loss": 0.1669, "lr": 1.3543140028288546e-05, "epoch": 0.5421970768505422, "percentage": 2.71, "elapsed_time": "0:04:03", "remaining_time": "2:25:23", "throughput": 4771.63, "total_tokens": 1159936} {"current_steps": 1155, "total_steps": 42420, "loss": 0.2084, "lr": 1.3602074493163602e-05, "epoch": 0.5445544554455446, "percentage": 2.72, "elapsed_time": "0:04:04", "remaining_time": "2:25:19", "throughput": 4771.47, "total_tokens": 1164448} {"current_steps": 1160, "total_steps": 42420, "loss": 0.1912, "lr": 1.3661008958038662e-05, "epoch": 0.5469118340405469, "percentage": 2.73, "elapsed_time": "0:04:04", "remaining_time": "2:25:11", "throughput": 4771.26, "total_tokens": 1168544} {"current_steps": 1165, "total_steps": 42420, "loss": 0.1213, "lr": 1.371994342291372e-05, "epoch": 0.5492692126355493, "percentage": 2.75, "elapsed_time": "0:04:05", "remaining_time": "2:25:05", "throughput": 4771.42, "total_tokens": 1172960} {"current_steps": 1170, "total_steps": 42420, "loss": 0.1908, "lr": 1.377887788778878e-05, "epoch": 0.5516265912305516, "percentage": 2.76, "elapsed_time": "0:04:06", "remaining_time": "2:25:05", "throughput": 4771.54, "total_tokens": 1178144} {"current_steps": 1175, "total_steps": 42420, "loss": 0.3895, "lr": 1.3837812352663839e-05, "epoch": 0.553983969825554, "percentage": 2.77, "elapsed_time": "0:04:08", "remaining_time": "2:25:11", "throughput": 4772.65, "total_tokens": 1184448} {"current_steps": 1180, "total_steps": 42420, "loss": 0.3661, "lr": 1.3896746817538897e-05, "epoch": 0.5563413484205564, "percentage": 2.78, "elapsed_time": "0:04:09", "remaining_time": "2:25:09", "throughput": 4772.8, "total_tokens": 1189472} {"current_steps": 1185, "total_steps": 42420, "loss": 0.1873, "lr": 1.3955681282413957e-05, "epoch": 0.5586987270155587, "percentage": 2.79, "elapsed_time": "0:04:10", "remaining_time": "2:25:11", "throughput": 4773.44, "total_tokens": 1195072} {"current_steps": 1190, "total_steps": 42420, "loss": 0.334, "lr": 1.4014615747289015e-05, "epoch": 0.5610561056105611, "percentage": 2.81, "elapsed_time": "0:04:11", "remaining_time": "2:25:03", "throughput": 4771.71, "total_tokens": 1198656} {"current_steps": 1195, "total_steps": 42420, "loss": 0.1862, "lr": 1.4073550212164074e-05, "epoch": 0.5634134842055634, "percentage": 2.82, "elapsed_time": "0:04:12", "remaining_time": "2:25:01", "throughput": 4771.72, "total_tokens": 1203616} {"current_steps": 1200, "total_steps": 42420, "loss": 0.2472, "lr": 1.4132484677039134e-05, "epoch": 0.5657708628005658, "percentage": 2.83, "elapsed_time": "0:04:13", "remaining_time": "2:24:58", "throughput": 4771.19, "total_tokens": 1208224} {"current_steps": 1205, "total_steps": 42420, "loss": 0.3519, "lr": 1.4191419141914192e-05, "epoch": 0.5681282413955682, "percentage": 2.84, "elapsed_time": "0:04:14", "remaining_time": "2:24:53", "throughput": 4771.02, "total_tokens": 1212608} {"current_steps": 1210, "total_steps": 42420, "loss": 0.1084, "lr": 1.4250353606789251e-05, "epoch": 0.5704856199905705, "percentage": 2.85, "elapsed_time": "0:04:15", "remaining_time": "2:24:56", "throughput": 4771.27, "total_tokens": 1218336} {"current_steps": 1215, "total_steps": 42420, "loss": 0.2362, "lr": 1.430928807166431e-05, "epoch": 0.5728429985855729, "percentage": 2.86, "elapsed_time": "0:04:16", "remaining_time": "2:24:54", "throughput": 4771.83, "total_tokens": 1223296} {"current_steps": 1220, "total_steps": 42420, "loss": 0.2409, "lr": 1.4368222536539369e-05, "epoch": 0.5752003771805752, "percentage": 2.88, "elapsed_time": "0:04:17", "remaining_time": "2:24:52", "throughput": 4772.26, "total_tokens": 1228448} {"current_steps": 1225, "total_steps": 42420, "loss": 0.5625, "lr": 1.4427157001414429e-05, "epoch": 0.5775577557755776, "percentage": 2.89, "elapsed_time": "0:04:18", "remaining_time": "2:24:48", "throughput": 4772.16, "total_tokens": 1233024} {"current_steps": 1230, "total_steps": 42420, "loss": 0.4444, "lr": 1.4486091466289486e-05, "epoch": 0.57991513437058, "percentage": 2.9, "elapsed_time": "0:04:19", "remaining_time": "2:24:47", "throughput": 4772.25, "total_tokens": 1238080} {"current_steps": 1235, "total_steps": 42420, "loss": 0.1018, "lr": 1.4545025931164546e-05, "epoch": 0.5822725129655822, "percentage": 2.91, "elapsed_time": "0:04:20", "remaining_time": "2:24:47", "throughput": 4772.78, "total_tokens": 1243296} {"current_steps": 1240, "total_steps": 42420, "loss": 0.3606, "lr": 1.4603960396039604e-05, "epoch": 0.5846298915605846, "percentage": 2.92, "elapsed_time": "0:04:21", "remaining_time": "2:24:44", "throughput": 4773.04, "total_tokens": 1248128} {"current_steps": 1245, "total_steps": 42420, "loss": 0.0974, "lr": 1.4662894860914664e-05, "epoch": 0.5869872701555869, "percentage": 2.93, "elapsed_time": "0:04:22", "remaining_time": "2:24:42", "throughput": 4772.42, "total_tokens": 1252864} {"current_steps": 1250, "total_steps": 42420, "loss": 0.4528, "lr": 1.4721829325789723e-05, "epoch": 0.5893446487505893, "percentage": 2.95, "elapsed_time": "0:04:23", "remaining_time": "2:24:40", "throughput": 4772.66, "total_tokens": 1257856} {"current_steps": 1255, "total_steps": 42420, "loss": 0.2641, "lr": 1.4780763790664781e-05, "epoch": 0.5917020273455917, "percentage": 2.96, "elapsed_time": "0:04:24", "remaining_time": "2:24:36", "throughput": 4771.88, "total_tokens": 1262240} {"current_steps": 1260, "total_steps": 42420, "loss": 0.2806, "lr": 1.4839698255539841e-05, "epoch": 0.594059405940594, "percentage": 2.97, "elapsed_time": "0:04:25", "remaining_time": "2:24:35", "throughput": 4772.36, "total_tokens": 1267392} {"current_steps": 1265, "total_steps": 42420, "loss": 0.1672, "lr": 1.4898632720414899e-05, "epoch": 0.5964167845355964, "percentage": 2.98, "elapsed_time": "0:04:26", "remaining_time": "2:24:31", "throughput": 4772.63, "total_tokens": 1272064} {"current_steps": 1270, "total_steps": 42420, "loss": 0.1886, "lr": 1.4957567185289958e-05, "epoch": 0.5987741631305987, "percentage": 2.99, "elapsed_time": "0:04:27", "remaining_time": "2:24:22", "throughput": 4772.51, "total_tokens": 1275968} {"current_steps": 1275, "total_steps": 42420, "loss": 0.1855, "lr": 1.5016501650165018e-05, "epoch": 0.6011315417256011, "percentage": 3.01, "elapsed_time": "0:04:28", "remaining_time": "2:24:16", "throughput": 4772.31, "total_tokens": 1280096} {"current_steps": 1280, "total_steps": 42420, "loss": 0.2385, "lr": 1.5075436115040076e-05, "epoch": 0.6034889203206035, "percentage": 3.02, "elapsed_time": "0:04:29", "remaining_time": "2:24:11", "throughput": 4772.61, "total_tokens": 1284704} {"current_steps": 1285, "total_steps": 42420, "loss": 0.1119, "lr": 1.5134370579915136e-05, "epoch": 0.6058462989156058, "percentage": 3.03, "elapsed_time": "0:04:30", "remaining_time": "2:24:07", "throughput": 4772.8, "total_tokens": 1289312} {"current_steps": 1290, "total_steps": 42420, "loss": 0.6526, "lr": 1.5193305044790194e-05, "epoch": 0.6082036775106082, "percentage": 3.04, "elapsed_time": "0:04:31", "remaining_time": "2:24:01", "throughput": 4772.51, "total_tokens": 1293440} {"current_steps": 1295, "total_steps": 42420, "loss": 0.2308, "lr": 1.5252239509665253e-05, "epoch": 0.6105610561056105, "percentage": 3.05, "elapsed_time": "0:04:31", "remaining_time": "2:23:53", "throughput": 4772.0, "total_tokens": 1297408} {"current_steps": 1300, "total_steps": 42420, "loss": 0.215, "lr": 1.5311173974540313e-05, "epoch": 0.6129184347006129, "percentage": 3.06, "elapsed_time": "0:04:32", "remaining_time": "2:23:52", "throughput": 4771.89, "total_tokens": 1302304} {"current_steps": 1305, "total_steps": 42420, "loss": 0.393, "lr": 1.537010843941537e-05, "epoch": 0.6152758132956153, "percentage": 3.08, "elapsed_time": "0:04:33", "remaining_time": "2:23:45", "throughput": 4771.92, "total_tokens": 1306368} {"current_steps": 1310, "total_steps": 42420, "loss": 0.2529, "lr": 1.5429042904290432e-05, "epoch": 0.6176331918906176, "percentage": 3.09, "elapsed_time": "0:04:34", "remaining_time": "2:23:45", "throughput": 4772.31, "total_tokens": 1311712} {"current_steps": 1315, "total_steps": 42420, "loss": 0.2564, "lr": 1.548797736916549e-05, "epoch": 0.61999057048562, "percentage": 3.1, "elapsed_time": "0:04:36", "remaining_time": "2:24:04", "throughput": 4773.24, "total_tokens": 1320000} {"current_steps": 1320, "total_steps": 42420, "loss": 0.3685, "lr": 1.5546911834040548e-05, "epoch": 0.6223479490806223, "percentage": 3.11, "elapsed_time": "0:04:37", "remaining_time": "2:24:00", "throughput": 4772.85, "total_tokens": 1324448} {"current_steps": 1325, "total_steps": 42420, "loss": 0.4194, "lr": 1.5605846298915608e-05, "epoch": 0.6247053276756247, "percentage": 3.12, "elapsed_time": "0:04:38", "remaining_time": "2:23:56", "throughput": 4772.91, "total_tokens": 1329088} {"current_steps": 1330, "total_steps": 42420, "loss": 0.2135, "lr": 1.5664780763790664e-05, "epoch": 0.6270627062706271, "percentage": 3.14, "elapsed_time": "0:04:39", "remaining_time": "2:23:53", "throughput": 4773.36, "total_tokens": 1333920} {"current_steps": 1335, "total_steps": 42420, "loss": 0.1912, "lr": 1.5723715228665727e-05, "epoch": 0.6294200848656294, "percentage": 3.15, "elapsed_time": "0:04:40", "remaining_time": "2:23:51", "throughput": 4773.76, "total_tokens": 1338848} {"current_steps": 1340, "total_steps": 42420, "loss": 0.3977, "lr": 1.5782649693540783e-05, "epoch": 0.6317774634606318, "percentage": 3.16, "elapsed_time": "0:04:41", "remaining_time": "2:23:55", "throughput": 4774.23, "total_tokens": 1344864} {"current_steps": 1345, "total_steps": 42420, "loss": 0.2709, "lr": 1.5841584158415843e-05, "epoch": 0.6341348420556341, "percentage": 3.17, "elapsed_time": "0:04:42", "remaining_time": "2:23:54", "throughput": 4775.03, "total_tokens": 1350144} {"current_steps": 1350, "total_steps": 42420, "loss": 0.2211, "lr": 1.5900518623290902e-05, "epoch": 0.6364922206506365, "percentage": 3.18, "elapsed_time": "0:04:43", "remaining_time": "2:23:49", "throughput": 4775.42, "total_tokens": 1354592} {"current_steps": 1355, "total_steps": 42420, "loss": 0.3181, "lr": 1.595945308816596e-05, "epoch": 0.6388495992456389, "percentage": 3.19, "elapsed_time": "0:04:44", "remaining_time": "2:23:41", "throughput": 4774.72, "total_tokens": 1358368} {"current_steps": 1360, "total_steps": 42420, "loss": 0.1759, "lr": 1.6018387553041018e-05, "epoch": 0.6412069778406412, "percentage": 3.21, "elapsed_time": "0:04:45", "remaining_time": "2:23:37", "throughput": 4774.72, "total_tokens": 1362848} {"current_steps": 1365, "total_steps": 42420, "loss": 0.2985, "lr": 1.6077322017916078e-05, "epoch": 0.6435643564356436, "percentage": 3.22, "elapsed_time": "0:04:46", "remaining_time": "2:23:35", "throughput": 4773.9, "total_tokens": 1367456} {"current_steps": 1370, "total_steps": 42420, "loss": 0.3404, "lr": 1.6136256482791138e-05, "epoch": 0.6459217350306459, "percentage": 3.23, "elapsed_time": "0:04:47", "remaining_time": "2:23:41", "throughput": 4774.74, "total_tokens": 1373888} {"current_steps": 1375, "total_steps": 42420, "loss": 0.3731, "lr": 1.6195190947666197e-05, "epoch": 0.6482791136256483, "percentage": 3.24, "elapsed_time": "0:04:48", "remaining_time": "2:23:40", "throughput": 4774.87, "total_tokens": 1378944} {"current_steps": 1380, "total_steps": 42420, "loss": 0.5236, "lr": 1.6254125412541253e-05, "epoch": 0.6506364922206507, "percentage": 3.25, "elapsed_time": "0:04:49", "remaining_time": "2:23:36", "throughput": 4774.63, "total_tokens": 1383328} {"current_steps": 1385, "total_steps": 42420, "loss": 0.2276, "lr": 1.6313059877416313e-05, "epoch": 0.652993870815653, "percentage": 3.26, "elapsed_time": "0:04:50", "remaining_time": "2:23:37", "throughput": 4775.28, "total_tokens": 1388928} {"current_steps": 1390, "total_steps": 42420, "loss": 0.269, "lr": 1.6371994342291373e-05, "epoch": 0.6553512494106554, "percentage": 3.28, "elapsed_time": "0:04:52", "remaining_time": "2:23:46", "throughput": 4776.07, "total_tokens": 1395712} {"current_steps": 1395, "total_steps": 42420, "loss": 0.4696, "lr": 1.6430928807166432e-05, "epoch": 0.6577086280056577, "percentage": 3.29, "elapsed_time": "0:04:53", "remaining_time": "2:23:41", "throughput": 4775.51, "total_tokens": 1399936} {"current_steps": 1400, "total_steps": 42420, "loss": 0.2222, "lr": 1.6489863272041492e-05, "epoch": 0.6600660066006601, "percentage": 3.3, "elapsed_time": "0:04:54", "remaining_time": "2:23:40", "throughput": 4775.62, "total_tokens": 1404992} {"current_steps": 1405, "total_steps": 42420, "loss": 0.4071, "lr": 1.6548797736916548e-05, "epoch": 0.6624233851956625, "percentage": 3.31, "elapsed_time": "0:04:55", "remaining_time": "2:23:36", "throughput": 4775.73, "total_tokens": 1409568} {"current_steps": 1410, "total_steps": 42420, "loss": 0.2935, "lr": 1.6607732201791608e-05, "epoch": 0.6647807637906648, "percentage": 3.32, "elapsed_time": "0:04:56", "remaining_time": "2:23:36", "throughput": 4776.43, "total_tokens": 1415072} {"current_steps": 1415, "total_steps": 42420, "loss": 0.1782, "lr": 1.6666666666666667e-05, "epoch": 0.6671381423856672, "percentage": 3.34, "elapsed_time": "0:04:57", "remaining_time": "2:23:32", "throughput": 4776.68, "total_tokens": 1419552} {"current_steps": 1420, "total_steps": 42420, "loss": 0.0904, "lr": 1.6725601131541727e-05, "epoch": 0.6694955209806694, "percentage": 3.35, "elapsed_time": "0:04:58", "remaining_time": "2:23:30", "throughput": 4776.98, "total_tokens": 1424544} {"current_steps": 1425, "total_steps": 42420, "loss": 0.4594, "lr": 1.6784535596416787e-05, "epoch": 0.6718528995756718, "percentage": 3.36, "elapsed_time": "0:04:59", "remaining_time": "2:23:28", "throughput": 4777.36, "total_tokens": 1429504} {"current_steps": 1430, "total_steps": 42420, "loss": 0.2362, "lr": 1.6843470061291843e-05, "epoch": 0.6742102781706742, "percentage": 3.37, "elapsed_time": "0:05:00", "remaining_time": "2:23:25", "throughput": 4777.58, "total_tokens": 1434336} {"current_steps": 1435, "total_steps": 42420, "loss": 0.0993, "lr": 1.6902404526166903e-05, "epoch": 0.6765676567656765, "percentage": 3.38, "elapsed_time": "0:05:01", "remaining_time": "2:23:19", "throughput": 4777.39, "total_tokens": 1438496} {"current_steps": 1440, "total_steps": 42420, "loss": 0.322, "lr": 1.6961338991041962e-05, "epoch": 0.6789250353606789, "percentage": 3.39, "elapsed_time": "0:05:02", "remaining_time": "2:23:21", "throughput": 4777.69, "total_tokens": 1444032} {"current_steps": 1445, "total_steps": 42420, "loss": 0.1563, "lr": 1.7020273455917022e-05, "epoch": 0.6812824139556812, "percentage": 3.41, "elapsed_time": "0:05:03", "remaining_time": "2:23:19", "throughput": 4777.65, "total_tokens": 1448864} {"current_steps": 1450, "total_steps": 42420, "loss": 0.2006, "lr": 1.707920792079208e-05, "epoch": 0.6836397925506836, "percentage": 3.42, "elapsed_time": "0:05:04", "remaining_time": "2:23:15", "throughput": 4777.73, "total_tokens": 1453376} {"current_steps": 1455, "total_steps": 42420, "loss": 0.1758, "lr": 1.7138142385667138e-05, "epoch": 0.685997171145686, "percentage": 3.43, "elapsed_time": "0:05:05", "remaining_time": "2:23:09", "throughput": 4776.82, "total_tokens": 1457376} {"current_steps": 1460, "total_steps": 42420, "loss": 0.2783, "lr": 1.7197076850542197e-05, "epoch": 0.6883545497406883, "percentage": 3.44, "elapsed_time": "0:05:06", "remaining_time": "2:23:10", "throughput": 4777.17, "total_tokens": 1462848} {"current_steps": 1465, "total_steps": 42420, "loss": 0.3199, "lr": 1.7256011315417257e-05, "epoch": 0.6907119283356907, "percentage": 3.45, "elapsed_time": "0:05:07", "remaining_time": "2:23:09", "throughput": 4777.38, "total_tokens": 1467872} {"current_steps": 1470, "total_steps": 42420, "loss": 0.0979, "lr": 1.7314945780292317e-05, "epoch": 0.693069306930693, "percentage": 3.47, "elapsed_time": "0:05:08", "remaining_time": "2:23:03", "throughput": 4777.37, "total_tokens": 1472096} {"current_steps": 1475, "total_steps": 42420, "loss": 0.281, "lr": 1.7373880245167376e-05, "epoch": 0.6954266855256954, "percentage": 3.48, "elapsed_time": "0:05:09", "remaining_time": "2:23:04", "throughput": 4777.94, "total_tokens": 1477632} {"current_steps": 1480, "total_steps": 42420, "loss": 0.2936, "lr": 1.7432814710042433e-05, "epoch": 0.6977840641206978, "percentage": 3.49, "elapsed_time": "0:05:10", "remaining_time": "2:23:05", "throughput": 4778.07, "total_tokens": 1482944} {"current_steps": 1485, "total_steps": 42420, "loss": 0.0579, "lr": 1.7491749174917492e-05, "epoch": 0.7001414427157001, "percentage": 3.5, "elapsed_time": "0:05:11", "remaining_time": "2:22:59", "throughput": 4777.82, "total_tokens": 1486976} {"current_steps": 1490, "total_steps": 42420, "loss": 0.2443, "lr": 1.7550683639792552e-05, "epoch": 0.7024988213107025, "percentage": 3.51, "elapsed_time": "0:05:12", "remaining_time": "2:22:54", "throughput": 4777.01, "total_tokens": 1491168} {"current_steps": 1495, "total_steps": 42420, "loss": 0.3282, "lr": 1.760961810466761e-05, "epoch": 0.7048561999057048, "percentage": 3.52, "elapsed_time": "0:05:13", "remaining_time": "2:22:52", "throughput": 4777.22, "total_tokens": 1496000} {"current_steps": 1500, "total_steps": 42420, "loss": 0.1869, "lr": 1.766855256954267e-05, "epoch": 0.7072135785007072, "percentage": 3.54, "elapsed_time": "0:05:14", "remaining_time": "2:22:46", "throughput": 4776.81, "total_tokens": 1500064} {"current_steps": 1505, "total_steps": 42420, "loss": 0.0588, "lr": 1.7727487034417727e-05, "epoch": 0.7095709570957096, "percentage": 3.55, "elapsed_time": "0:05:15", "remaining_time": "2:22:45", "throughput": 4777.08, "total_tokens": 1505120} {"current_steps": 1510, "total_steps": 42420, "loss": 0.3558, "lr": 1.7786421499292787e-05, "epoch": 0.7119283356907119, "percentage": 3.56, "elapsed_time": "0:05:16", "remaining_time": "2:22:44", "throughput": 4777.44, "total_tokens": 1510240} {"current_steps": 1515, "total_steps": 42420, "loss": 0.2256, "lr": 1.7845355964167847e-05, "epoch": 0.7142857142857143, "percentage": 3.57, "elapsed_time": "0:05:17", "remaining_time": "2:22:45", "throughput": 4778.06, "total_tokens": 1515712} {"current_steps": 1520, "total_steps": 42420, "loss": 0.0456, "lr": 1.7904290429042906e-05, "epoch": 0.7166430928807166, "percentage": 3.58, "elapsed_time": "0:05:18", "remaining_time": "2:22:43", "throughput": 4777.74, "total_tokens": 1520512} {"current_steps": 1525, "total_steps": 42420, "loss": 0.2285, "lr": 1.7963224893917966e-05, "epoch": 0.719000471475719, "percentage": 3.6, "elapsed_time": "0:05:19", "remaining_time": "2:22:36", "throughput": 4777.03, "total_tokens": 1524288} {"current_steps": 1530, "total_steps": 42420, "loss": 0.1156, "lr": 1.8022159358793022e-05, "epoch": 0.7213578500707214, "percentage": 3.61, "elapsed_time": "0:05:20", "remaining_time": "2:22:33", "throughput": 4776.95, "total_tokens": 1528896} {"current_steps": 1535, "total_steps": 42420, "loss": 0.1196, "lr": 1.8081093823668082e-05, "epoch": 0.7237152286657237, "percentage": 3.62, "elapsed_time": "0:05:21", "remaining_time": "2:22:35", "throughput": 4777.51, "total_tokens": 1534656} {"current_steps": 1540, "total_steps": 42420, "loss": 0.3813, "lr": 1.814002828854314e-05, "epoch": 0.7260726072607261, "percentage": 3.63, "elapsed_time": "0:05:22", "remaining_time": "2:22:31", "throughput": 4777.15, "total_tokens": 1538848} {"current_steps": 1545, "total_steps": 42420, "loss": 0.3749, "lr": 1.81989627534182e-05, "epoch": 0.7284299858557284, "percentage": 3.64, "elapsed_time": "0:05:23", "remaining_time": "2:22:28", "throughput": 4777.36, "total_tokens": 1543712} {"current_steps": 1550, "total_steps": 42420, "loss": 0.4939, "lr": 1.825789721829326e-05, "epoch": 0.7307873644507308, "percentage": 3.65, "elapsed_time": "0:05:24", "remaining_time": "2:22:30", "throughput": 4777.01, "total_tokens": 1549152} {"current_steps": 1555, "total_steps": 42420, "loss": 0.0758, "lr": 1.8316831683168317e-05, "epoch": 0.7331447430457332, "percentage": 3.67, "elapsed_time": "0:05:25", "remaining_time": "2:22:29", "throughput": 4776.81, "total_tokens": 1554080} {"current_steps": 1560, "total_steps": 42420, "loss": 0.0781, "lr": 1.8375766148043376e-05, "epoch": 0.7355021216407355, "percentage": 3.68, "elapsed_time": "0:05:26", "remaining_time": "2:22:28", "throughput": 4777.05, "total_tokens": 1559104} {"current_steps": 1565, "total_steps": 42420, "loss": 0.1049, "lr": 1.8434700612918436e-05, "epoch": 0.7378595002357379, "percentage": 3.69, "elapsed_time": "0:05:27", "remaining_time": "2:22:31", "throughput": 4777.91, "total_tokens": 1565152} {"current_steps": 1570, "total_steps": 42420, "loss": 0.3828, "lr": 1.8493635077793496e-05, "epoch": 0.7402168788307402, "percentage": 3.7, "elapsed_time": "0:05:28", "remaining_time": "2:22:32", "throughput": 4778.35, "total_tokens": 1570688} {"current_steps": 1575, "total_steps": 42420, "loss": 0.3156, "lr": 1.8552569542668555e-05, "epoch": 0.7425742574257426, "percentage": 3.71, "elapsed_time": "0:05:29", "remaining_time": "2:22:34", "throughput": 4778.6, "total_tokens": 1576256} {"current_steps": 1580, "total_steps": 42420, "loss": 0.4078, "lr": 1.861150400754361e-05, "epoch": 0.744931636020745, "percentage": 3.72, "elapsed_time": "0:05:30", "remaining_time": "2:22:31", "throughput": 4778.82, "total_tokens": 1581056} {"current_steps": 1585, "total_steps": 42420, "loss": 0.165, "lr": 1.867043847241867e-05, "epoch": 0.7472890146157473, "percentage": 3.74, "elapsed_time": "0:05:31", "remaining_time": "2:22:31", "throughput": 4779.42, "total_tokens": 1586464} {"current_steps": 1590, "total_steps": 42420, "loss": 0.3333, "lr": 1.872937293729373e-05, "epoch": 0.7496463932107497, "percentage": 3.75, "elapsed_time": "0:05:32", "remaining_time": "2:22:29", "throughput": 4779.83, "total_tokens": 1591296} {"current_steps": 1595, "total_steps": 42420, "loss": 0.2179, "lr": 1.878830740216879e-05, "epoch": 0.752003771805752, "percentage": 3.76, "elapsed_time": "0:05:33", "remaining_time": "2:22:24", "throughput": 4779.48, "total_tokens": 1595488} {"current_steps": 1600, "total_steps": 42420, "loss": 0.1738, "lr": 1.884724186704385e-05, "epoch": 0.7543611504007544, "percentage": 3.77, "elapsed_time": "0:05:35", "remaining_time": "2:22:26", "throughput": 4779.88, "total_tokens": 1601312} {"current_steps": 1605, "total_steps": 42420, "loss": 0.3845, "lr": 1.8906176331918906e-05, "epoch": 0.7567185289957568, "percentage": 3.78, "elapsed_time": "0:05:36", "remaining_time": "2:22:26", "throughput": 4779.39, "total_tokens": 1606336} {"current_steps": 1610, "total_steps": 42420, "loss": 0.0949, "lr": 1.8965110796793966e-05, "epoch": 0.759075907590759, "percentage": 3.8, "elapsed_time": "0:05:37", "remaining_time": "2:22:23", "throughput": 4779.65, "total_tokens": 1611008} {"current_steps": 1615, "total_steps": 42420, "loss": 0.1648, "lr": 1.9024045261669026e-05, "epoch": 0.7614332861857614, "percentage": 3.81, "elapsed_time": "0:05:37", "remaining_time": "2:22:19", "throughput": 4779.58, "total_tokens": 1615328} {"current_steps": 1620, "total_steps": 42420, "loss": 0.3604, "lr": 1.9082979726544085e-05, "epoch": 0.7637906647807637, "percentage": 3.82, "elapsed_time": "0:05:39", "remaining_time": "2:22:17", "throughput": 4779.67, "total_tokens": 1620320} {"current_steps": 1625, "total_steps": 42420, "loss": 0.263, "lr": 1.9141914191419145e-05, "epoch": 0.7661480433757661, "percentage": 3.83, "elapsed_time": "0:05:40", "remaining_time": "2:22:16", "throughput": 4780.06, "total_tokens": 1625344} {"current_steps": 1630, "total_steps": 42420, "loss": 0.1152, "lr": 1.92008486562942e-05, "epoch": 0.7685054219707685, "percentage": 3.84, "elapsed_time": "0:05:41", "remaining_time": "2:22:15", "throughput": 4780.6, "total_tokens": 1630624} {"current_steps": 1635, "total_steps": 42420, "loss": 0.3091, "lr": 1.925978312116926e-05, "epoch": 0.7708628005657708, "percentage": 3.85, "elapsed_time": "0:05:42", "remaining_time": "2:22:12", "throughput": 4780.59, "total_tokens": 1635136} {"current_steps": 1640, "total_steps": 42420, "loss": 0.3795, "lr": 1.9318717586044317e-05, "epoch": 0.7732201791607732, "percentage": 3.87, "elapsed_time": "0:05:43", "remaining_time": "2:22:12", "throughput": 4781.12, "total_tokens": 1640640} {"current_steps": 1645, "total_steps": 42420, "loss": 0.1843, "lr": 1.937765205091938e-05, "epoch": 0.7755775577557755, "percentage": 3.88, "elapsed_time": "0:05:44", "remaining_time": "2:22:19", "throughput": 4781.04, "total_tokens": 1647040} {"current_steps": 1650, "total_steps": 42420, "loss": 0.4343, "lr": 1.943658651579444e-05, "epoch": 0.7779349363507779, "percentage": 3.89, "elapsed_time": "0:05:45", "remaining_time": "2:22:16", "throughput": 4781.08, "total_tokens": 1651712} {"current_steps": 1655, "total_steps": 42420, "loss": 0.0954, "lr": 1.9495520980669496e-05, "epoch": 0.7802923149457803, "percentage": 3.9, "elapsed_time": "0:05:46", "remaining_time": "2:22:19", "throughput": 4781.28, "total_tokens": 1657536} {"current_steps": 1660, "total_steps": 42420, "loss": 0.3075, "lr": 1.9554455445544556e-05, "epoch": 0.7826496935407826, "percentage": 3.91, "elapsed_time": "0:05:47", "remaining_time": "2:22:22", "throughput": 4781.99, "total_tokens": 1663616} {"current_steps": 1665, "total_steps": 42420, "loss": 0.5526, "lr": 1.9613389910419612e-05, "epoch": 0.785007072135785, "percentage": 3.93, "elapsed_time": "0:05:49", "remaining_time": "2:22:25", "throughput": 4782.5, "total_tokens": 1669600} {"current_steps": 1670, "total_steps": 42420, "loss": 0.2544, "lr": 1.9672324375294675e-05, "epoch": 0.7873644507307873, "percentage": 3.94, "elapsed_time": "0:05:50", "remaining_time": "2:22:23", "throughput": 4782.83, "total_tokens": 1674560} {"current_steps": 1675, "total_steps": 42420, "loss": 0.2861, "lr": 1.9731258840169734e-05, "epoch": 0.7897218293257897, "percentage": 3.95, "elapsed_time": "0:05:51", "remaining_time": "2:22:22", "throughput": 4783.05, "total_tokens": 1679616} {"current_steps": 1680, "total_steps": 42420, "loss": 0.0816, "lr": 1.979019330504479e-05, "epoch": 0.7920792079207921, "percentage": 3.96, "elapsed_time": "0:05:52", "remaining_time": "2:22:18", "throughput": 4783.32, "total_tokens": 1684160} {"current_steps": 1685, "total_steps": 42420, "loss": 0.4813, "lr": 1.984912776991985e-05, "epoch": 0.7944365865157944, "percentage": 3.97, "elapsed_time": "0:05:53", "remaining_time": "2:22:17", "throughput": 4783.2, "total_tokens": 1689280} {"current_steps": 1690, "total_steps": 42420, "loss": 0.1395, "lr": 1.9908062234794907e-05, "epoch": 0.7967939651107968, "percentage": 3.98, "elapsed_time": "0:05:54", "remaining_time": "2:22:16", "throughput": 4783.62, "total_tokens": 1694368} {"current_steps": 1695, "total_steps": 42420, "loss": 0.2475, "lr": 1.996699669966997e-05, "epoch": 0.7991513437057991, "percentage": 4.0, "elapsed_time": "0:05:55", "remaining_time": "2:22:13", "throughput": 4783.75, "total_tokens": 1699072} {"current_steps": 1700, "total_steps": 42420, "loss": 0.1527, "lr": 2.002593116454503e-05, "epoch": 0.8015087223008015, "percentage": 4.01, "elapsed_time": "0:05:56", "remaining_time": "2:22:13", "throughput": 4784.12, "total_tokens": 1704352} {"current_steps": 1705, "total_steps": 42420, "loss": 0.4713, "lr": 2.0084865629420085e-05, "epoch": 0.8038661008958039, "percentage": 4.02, "elapsed_time": "0:05:57", "remaining_time": "2:22:11", "throughput": 4783.99, "total_tokens": 1709088} {"current_steps": 1710, "total_steps": 42420, "loss": 0.1139, "lr": 2.0143800094295145e-05, "epoch": 0.8062234794908062, "percentage": 4.03, "elapsed_time": "0:05:58", "remaining_time": "2:22:07", "throughput": 4783.92, "total_tokens": 1713600} {"current_steps": 1715, "total_steps": 42420, "loss": 0.2536, "lr": 2.02027345591702e-05, "epoch": 0.8085808580858086, "percentage": 4.04, "elapsed_time": "0:05:59", "remaining_time": "2:22:13", "throughput": 4784.56, "total_tokens": 1720224} {"current_steps": 1720, "total_steps": 42420, "loss": 0.3335, "lr": 2.0261669024045264e-05, "epoch": 0.8109382366808109, "percentage": 4.05, "elapsed_time": "0:06:00", "remaining_time": "2:22:11", "throughput": 4785.04, "total_tokens": 1725280} {"current_steps": 1725, "total_steps": 42420, "loss": 0.2141, "lr": 2.0320603488920324e-05, "epoch": 0.8132956152758133, "percentage": 4.07, "elapsed_time": "0:06:01", "remaining_time": "2:22:17", "throughput": 4785.43, "total_tokens": 1731904} {"current_steps": 1730, "total_steps": 42420, "loss": 0.1601, "lr": 2.037953795379538e-05, "epoch": 0.8156529938708157, "percentage": 4.08, "elapsed_time": "0:06:02", "remaining_time": "2:22:16", "throughput": 4785.84, "total_tokens": 1737056} {"current_steps": 1735, "total_steps": 42420, "loss": 0.1023, "lr": 2.043847241867044e-05, "epoch": 0.818010372465818, "percentage": 4.09, "elapsed_time": "0:06:03", "remaining_time": "2:22:13", "throughput": 4785.89, "total_tokens": 1741568} {"current_steps": 1740, "total_steps": 42420, "loss": 0.3312, "lr": 2.0497406883545496e-05, "epoch": 0.8203677510608204, "percentage": 4.1, "elapsed_time": "0:06:04", "remaining_time": "2:22:09", "throughput": 4785.66, "total_tokens": 1745984} {"current_steps": 1745, "total_steps": 42420, "loss": 0.3677, "lr": 2.055634134842056e-05, "epoch": 0.8227251296558227, "percentage": 4.11, "elapsed_time": "0:06:05", "remaining_time": "2:22:07", "throughput": 4785.47, "total_tokens": 1750688} {"current_steps": 1750, "total_steps": 42420, "loss": 0.3251, "lr": 2.061527581329562e-05, "epoch": 0.8250825082508251, "percentage": 4.13, "elapsed_time": "0:06:06", "remaining_time": "2:22:05", "throughput": 4785.57, "total_tokens": 1755648} {"current_steps": 1755, "total_steps": 42420, "loss": 0.499, "lr": 2.0674210278170675e-05, "epoch": 0.8274398868458275, "percentage": 4.14, "elapsed_time": "0:06:08", "remaining_time": "2:22:07", "throughput": 4785.91, "total_tokens": 1761408} {"current_steps": 1760, "total_steps": 42420, "loss": 0.2298, "lr": 2.0733144743045735e-05, "epoch": 0.8297972654408298, "percentage": 4.15, "elapsed_time": "0:06:08", "remaining_time": "2:22:04", "throughput": 4785.97, "total_tokens": 1765984} {"current_steps": 1765, "total_steps": 42420, "loss": 0.1537, "lr": 2.079207920792079e-05, "epoch": 0.8321546440358322, "percentage": 4.16, "elapsed_time": "0:06:10", "remaining_time": "2:22:03", "throughput": 4786.22, "total_tokens": 1771040} {"current_steps": 1770, "total_steps": 42420, "loss": 0.2474, "lr": 2.085101367279585e-05, "epoch": 0.8345120226308345, "percentage": 4.17, "elapsed_time": "0:06:11", "remaining_time": "2:22:02", "throughput": 4786.49, "total_tokens": 1776288} {"current_steps": 1775, "total_steps": 42420, "loss": 0.2176, "lr": 2.0909948137670914e-05, "epoch": 0.8368694012258369, "percentage": 4.18, "elapsed_time": "0:06:12", "remaining_time": "2:22:02", "throughput": 4786.75, "total_tokens": 1781632} {"current_steps": 1780, "total_steps": 42420, "loss": 0.1939, "lr": 2.096888260254597e-05, "epoch": 0.8392267798208393, "percentage": 4.2, "elapsed_time": "0:06:13", "remaining_time": "2:21:58", "throughput": 4786.88, "total_tokens": 1786048} {"current_steps": 1785, "total_steps": 42420, "loss": 0.2347, "lr": 2.102781706742103e-05, "epoch": 0.8415841584158416, "percentage": 4.21, "elapsed_time": "0:06:14", "remaining_time": "2:21:56", "throughput": 4786.85, "total_tokens": 1790848} {"current_steps": 1790, "total_steps": 42420, "loss": 0.0876, "lr": 2.1086751532296086e-05, "epoch": 0.843941537010844, "percentage": 4.22, "elapsed_time": "0:06:15", "remaining_time": "2:21:54", "throughput": 4787.22, "total_tokens": 1795680} {"current_steps": 1795, "total_steps": 42420, "loss": 0.2951, "lr": 2.1145685997171145e-05, "epoch": 0.8462989156058462, "percentage": 4.23, "elapsed_time": "0:06:16", "remaining_time": "2:21:51", "throughput": 4787.3, "total_tokens": 1800448} {"current_steps": 1800, "total_steps": 42420, "loss": 0.2409, "lr": 2.120462046204621e-05, "epoch": 0.8486562942008486, "percentage": 4.24, "elapsed_time": "0:06:17", "remaining_time": "2:21:50", "throughput": 4787.52, "total_tokens": 1805568} {"current_steps": 1805, "total_steps": 42420, "loss": 0.264, "lr": 2.1263554926921265e-05, "epoch": 0.851013672795851, "percentage": 4.26, "elapsed_time": "0:06:18", "remaining_time": "2:21:47", "throughput": 4787.51, "total_tokens": 1810080} {"current_steps": 1810, "total_steps": 42420, "loss": 0.2488, "lr": 2.1322489391796324e-05, "epoch": 0.8533710513908533, "percentage": 4.27, "elapsed_time": "0:06:19", "remaining_time": "2:21:43", "throughput": 4787.11, "total_tokens": 1814400} {"current_steps": 1815, "total_steps": 42420, "loss": 0.6154, "lr": 2.138142385667138e-05, "epoch": 0.8557284299858557, "percentage": 4.28, "elapsed_time": "0:06:20", "remaining_time": "2:21:42", "throughput": 4787.11, "total_tokens": 1819296} {"current_steps": 1820, "total_steps": 42420, "loss": 0.1989, "lr": 2.144035832154644e-05, "epoch": 0.858085808580858, "percentage": 4.29, "elapsed_time": "0:06:21", "remaining_time": "2:21:40", "throughput": 4787.26, "total_tokens": 1824160} {"current_steps": 1825, "total_steps": 42420, "loss": 0.5156, "lr": 2.1499292786421503e-05, "epoch": 0.8604431871758604, "percentage": 4.3, "elapsed_time": "0:06:22", "remaining_time": "2:21:44", "throughput": 4787.19, "total_tokens": 1830240} {"current_steps": 1830, "total_steps": 42420, "loss": 0.1872, "lr": 2.155822725129656e-05, "epoch": 0.8628005657708628, "percentage": 4.31, "elapsed_time": "0:06:23", "remaining_time": "2:21:42", "throughput": 4786.43, "total_tokens": 1834752} {"current_steps": 1835, "total_steps": 42420, "loss": 0.4061, "lr": 2.161716171617162e-05, "epoch": 0.8651579443658651, "percentage": 4.33, "elapsed_time": "0:06:24", "remaining_time": "2:21:41", "throughput": 4786.5, "total_tokens": 1839936} {"current_steps": 1840, "total_steps": 42420, "loss": 0.0982, "lr": 2.1676096181046675e-05, "epoch": 0.8675153229608675, "percentage": 4.34, "elapsed_time": "0:06:25", "remaining_time": "2:21:38", "throughput": 4786.3, "total_tokens": 1844448} {"current_steps": 1845, "total_steps": 42420, "loss": 0.1379, "lr": 2.1735030645921735e-05, "epoch": 0.8698727015558698, "percentage": 4.35, "elapsed_time": "0:06:26", "remaining_time": "2:21:34", "throughput": 4786.06, "total_tokens": 1848704} {"current_steps": 1850, "total_steps": 42420, "loss": 0.0753, "lr": 2.1793965110796798e-05, "epoch": 0.8722300801508722, "percentage": 4.36, "elapsed_time": "0:06:27", "remaining_time": "2:21:35", "throughput": 4786.18, "total_tokens": 1854144} {"current_steps": 1855, "total_steps": 42420, "loss": 0.1825, "lr": 2.1852899575671854e-05, "epoch": 0.8745874587458746, "percentage": 4.37, "elapsed_time": "0:06:28", "remaining_time": "2:21:34", "throughput": 4786.29, "total_tokens": 1859232} {"current_steps": 1860, "total_steps": 42420, "loss": 0.0802, "lr": 2.1911834040546914e-05, "epoch": 0.8769448373408769, "percentage": 4.38, "elapsed_time": "0:06:29", "remaining_time": "2:21:35", "throughput": 4786.47, "total_tokens": 1864736} {"current_steps": 1865, "total_steps": 42420, "loss": 0.1101, "lr": 2.197076850542197e-05, "epoch": 0.8793022159358793, "percentage": 4.4, "elapsed_time": "0:06:30", "remaining_time": "2:21:36", "throughput": 4786.6, "total_tokens": 1870336} {"current_steps": 1870, "total_steps": 42420, "loss": 0.0761, "lr": 2.202970297029703e-05, "epoch": 0.8816595945308816, "percentage": 4.41, "elapsed_time": "0:06:31", "remaining_time": "2:21:37", "throughput": 4786.79, "total_tokens": 1875872} {"current_steps": 1875, "total_steps": 42420, "loss": 0.1346, "lr": 2.208863743517209e-05, "epoch": 0.884016973125884, "percentage": 4.42, "elapsed_time": "0:06:32", "remaining_time": "2:21:34", "throughput": 4786.67, "total_tokens": 1880288} {"current_steps": 1880, "total_steps": 42420, "loss": 0.4116, "lr": 2.214757190004715e-05, "epoch": 0.8863743517208864, "percentage": 4.43, "elapsed_time": "0:06:33", "remaining_time": "2:21:33", "throughput": 4786.81, "total_tokens": 1885376} {"current_steps": 1885, "total_steps": 42420, "loss": 0.1925, "lr": 2.220650636492221e-05, "epoch": 0.8887317303158887, "percentage": 4.44, "elapsed_time": "0:06:34", "remaining_time": "2:21:32", "throughput": 4786.53, "total_tokens": 1890272} {"current_steps": 1890, "total_steps": 42420, "loss": 0.0604, "lr": 2.2265440829797265e-05, "epoch": 0.8910891089108911, "percentage": 4.46, "elapsed_time": "0:06:35", "remaining_time": "2:21:29", "throughput": 4786.77, "total_tokens": 1894976} {"current_steps": 1895, "total_steps": 42420, "loss": 0.1662, "lr": 2.2324375294672324e-05, "epoch": 0.8934464875058934, "percentage": 4.47, "elapsed_time": "0:06:37", "remaining_time": "2:21:32", "throughput": 4786.72, "total_tokens": 1900992} {"current_steps": 1900, "total_steps": 42420, "loss": 0.3383, "lr": 2.2383309759547384e-05, "epoch": 0.8958038661008958, "percentage": 4.48, "elapsed_time": "0:06:38", "remaining_time": "2:21:31", "throughput": 4786.83, "total_tokens": 1905984} {"current_steps": 1905, "total_steps": 42420, "loss": 0.1294, "lr": 2.2442244224422444e-05, "epoch": 0.8981612446958982, "percentage": 4.49, "elapsed_time": "0:06:39", "remaining_time": "2:21:30", "throughput": 4786.53, "total_tokens": 1910848} {"current_steps": 1910, "total_steps": 42420, "loss": 0.1594, "lr": 2.2501178689297503e-05, "epoch": 0.9005186232909005, "percentage": 4.5, "elapsed_time": "0:06:40", "remaining_time": "2:21:31", "throughput": 4786.81, "total_tokens": 1916448} {"current_steps": 1915, "total_steps": 42420, "loss": 0.1016, "lr": 2.256011315417256e-05, "epoch": 0.9028760018859029, "percentage": 4.51, "elapsed_time": "0:06:41", "remaining_time": "2:21:29", "throughput": 4787.0, "total_tokens": 1921440} {"current_steps": 1920, "total_steps": 42420, "loss": 0.0926, "lr": 2.261904761904762e-05, "epoch": 0.9052333804809052, "percentage": 4.53, "elapsed_time": "0:06:42", "remaining_time": "2:21:26", "throughput": 4786.99, "total_tokens": 1925984} {"current_steps": 1925, "total_steps": 42420, "loss": 0.3353, "lr": 2.267798208392268e-05, "epoch": 0.9075907590759076, "percentage": 4.54, "elapsed_time": "0:06:43", "remaining_time": "2:21:30", "throughput": 4787.19, "total_tokens": 1932096} {"current_steps": 1930, "total_steps": 42420, "loss": 0.3191, "lr": 2.273691654879774e-05, "epoch": 0.90994813767091, "percentage": 4.55, "elapsed_time": "0:06:44", "remaining_time": "2:21:27", "throughput": 4787.1, "total_tokens": 1936640} {"current_steps": 1935, "total_steps": 42420, "loss": 0.3887, "lr": 2.2795851013672798e-05, "epoch": 0.9123055162659123, "percentage": 4.56, "elapsed_time": "0:06:45", "remaining_time": "2:21:25", "throughput": 4787.12, "total_tokens": 1941472} {"current_steps": 1940, "total_steps": 42420, "loss": 0.5009, "lr": 2.2854785478547854e-05, "epoch": 0.9146628948609147, "percentage": 4.57, "elapsed_time": "0:06:46", "remaining_time": "2:21:24", "throughput": 4787.2, "total_tokens": 1946528} {"current_steps": 1945, "total_steps": 42420, "loss": 0.1029, "lr": 2.2913719943422914e-05, "epoch": 0.917020273455917, "percentage": 4.59, "elapsed_time": "0:06:47", "remaining_time": "2:21:26", "throughput": 4787.33, "total_tokens": 1952352} {"current_steps": 1950, "total_steps": 42420, "loss": 0.5685, "lr": 2.2972654408297974e-05, "epoch": 0.9193776520509194, "percentage": 4.6, "elapsed_time": "0:06:48", "remaining_time": "2:21:25", "throughput": 4787.47, "total_tokens": 1957344} {"current_steps": 1955, "total_steps": 42420, "loss": 0.1706, "lr": 2.3031588873173033e-05, "epoch": 0.9217350306459218, "percentage": 4.61, "elapsed_time": "0:06:49", "remaining_time": "2:21:22", "throughput": 4787.31, "total_tokens": 1961824} {"current_steps": 1960, "total_steps": 42420, "loss": 0.2204, "lr": 2.3090523338048093e-05, "epoch": 0.9240924092409241, "percentage": 4.62, "elapsed_time": "0:06:50", "remaining_time": "2:21:19", "throughput": 4787.25, "total_tokens": 1966368} {"current_steps": 1965, "total_steps": 42420, "loss": 0.1322, "lr": 2.314945780292315e-05, "epoch": 0.9264497878359265, "percentage": 4.63, "elapsed_time": "0:06:52", "remaining_time": "2:21:26", "throughput": 4787.92, "total_tokens": 1973600} {"current_steps": 1970, "total_steps": 42420, "loss": 0.1577, "lr": 2.320839226779821e-05, "epoch": 0.9288071664309288, "percentage": 4.64, "elapsed_time": "0:06:53", "remaining_time": "2:21:26", "throughput": 4788.13, "total_tokens": 1978880} {"current_steps": 1975, "total_steps": 42420, "loss": 0.2507, "lr": 2.326732673267327e-05, "epoch": 0.9311645450259312, "percentage": 4.66, "elapsed_time": "0:06:54", "remaining_time": "2:21:27", "throughput": 4788.76, "total_tokens": 1984864} {"current_steps": 1980, "total_steps": 42420, "loss": 0.2153, "lr": 2.3326261197548328e-05, "epoch": 0.9335219236209336, "percentage": 4.67, "elapsed_time": "0:06:55", "remaining_time": "2:21:29", "throughput": 4789.13, "total_tokens": 1990592} {"current_steps": 1985, "total_steps": 42420, "loss": 0.1532, "lr": 2.3385195662423388e-05, "epoch": 0.9358793022159358, "percentage": 4.68, "elapsed_time": "0:06:56", "remaining_time": "2:21:31", "throughput": 4789.24, "total_tokens": 1996512} {"current_steps": 1990, "total_steps": 42420, "loss": 0.0845, "lr": 2.3444130127298444e-05, "epoch": 0.9382366808109383, "percentage": 4.69, "elapsed_time": "0:06:57", "remaining_time": "2:21:29", "throughput": 4788.81, "total_tokens": 2000960} {"current_steps": 1995, "total_steps": 42420, "loss": 0.0906, "lr": 2.3503064592173503e-05, "epoch": 0.9405940594059405, "percentage": 4.7, "elapsed_time": "0:06:58", "remaining_time": "2:21:24", "throughput": 4788.68, "total_tokens": 2005056} {"current_steps": 2000, "total_steps": 42420, "loss": 0.1802, "lr": 2.3561999057048563e-05, "epoch": 0.9429514380009429, "percentage": 4.71, "elapsed_time": "0:06:59", "remaining_time": "2:21:20", "throughput": 4788.6, "total_tokens": 2009472} {"current_steps": 2005, "total_steps": 42420, "loss": 0.615, "lr": 2.3620933521923623e-05, "epoch": 0.9453088165959453, "percentage": 4.73, "elapsed_time": "0:07:00", "remaining_time": "2:21:17", "throughput": 4788.58, "total_tokens": 2013888} {"current_steps": 2010, "total_steps": 42420, "loss": 0.2034, "lr": 2.3679867986798682e-05, "epoch": 0.9476661951909476, "percentage": 4.74, "elapsed_time": "0:07:01", "remaining_time": "2:21:19", "throughput": 4788.88, "total_tokens": 2019808} {"current_steps": 2015, "total_steps": 42420, "loss": 0.2061, "lr": 2.373880245167374e-05, "epoch": 0.95002357378595, "percentage": 4.75, "elapsed_time": "0:07:02", "remaining_time": "2:21:20", "throughput": 4789.16, "total_tokens": 2025440} {"current_steps": 2020, "total_steps": 42420, "loss": 0.2288, "lr": 2.3797736916548798e-05, "epoch": 0.9523809523809523, "percentage": 4.76, "elapsed_time": "0:07:03", "remaining_time": "2:21:19", "throughput": 4789.33, "total_tokens": 2030464} {"current_steps": 2025, "total_steps": 42420, "loss": 0.2549, "lr": 2.3856671381423858e-05, "epoch": 0.9547383309759547, "percentage": 4.77, "elapsed_time": "0:07:04", "remaining_time": "2:21:17", "throughput": 4789.44, "total_tokens": 2035328} {"current_steps": 2030, "total_steps": 42420, "loss": 0.1494, "lr": 2.3915605846298918e-05, "epoch": 0.9570957095709571, "percentage": 4.79, "elapsed_time": "0:07:05", "remaining_time": "2:21:13", "throughput": 4789.34, "total_tokens": 2039616} {"current_steps": 2035, "total_steps": 42420, "loss": 0.2502, "lr": 2.3974540311173977e-05, "epoch": 0.9594530881659594, "percentage": 4.8, "elapsed_time": "0:07:07", "remaining_time": "2:21:14", "throughput": 4789.62, "total_tokens": 2045408} {"current_steps": 2040, "total_steps": 42420, "loss": 0.1787, "lr": 2.4033474776049033e-05, "epoch": 0.9618104667609618, "percentage": 4.81, "elapsed_time": "0:07:08", "remaining_time": "2:21:15", "throughput": 4789.86, "total_tokens": 2050816} {"current_steps": 2045, "total_steps": 42420, "loss": 0.1263, "lr": 2.4092409240924093e-05, "epoch": 0.9641678453559641, "percentage": 4.82, "elapsed_time": "0:07:09", "remaining_time": "2:21:15", "throughput": 4789.76, "total_tokens": 2056128} {"current_steps": 2050, "total_steps": 42420, "loss": 0.2049, "lr": 2.4151343705799153e-05, "epoch": 0.9665252239509665, "percentage": 4.83, "elapsed_time": "0:07:10", "remaining_time": "2:21:14", "throughput": 4789.53, "total_tokens": 2061120} {"current_steps": 2055, "total_steps": 42420, "loss": 0.3396, "lr": 2.4210278170674212e-05, "epoch": 0.9688826025459689, "percentage": 4.84, "elapsed_time": "0:07:11", "remaining_time": "2:21:13", "throughput": 4789.97, "total_tokens": 2066400} {"current_steps": 2060, "total_steps": 42420, "loss": 0.2418, "lr": 2.4269212635549272e-05, "epoch": 0.9712399811409712, "percentage": 4.86, "elapsed_time": "0:07:12", "remaining_time": "2:21:11", "throughput": 4790.1, "total_tokens": 2071200} {"current_steps": 2065, "total_steps": 42420, "loss": 0.2156, "lr": 2.4328147100424328e-05, "epoch": 0.9735973597359736, "percentage": 4.87, "elapsed_time": "0:07:13", "remaining_time": "2:21:10", "throughput": 4790.37, "total_tokens": 2076320} {"current_steps": 2070, "total_steps": 42420, "loss": 0.8193, "lr": 2.4387081565299388e-05, "epoch": 0.9759547383309759, "percentage": 4.88, "elapsed_time": "0:07:14", "remaining_time": "2:21:11", "throughput": 4790.85, "total_tokens": 2082016} {"current_steps": 2075, "total_steps": 42420, "loss": 0.1686, "lr": 2.4446016030174447e-05, "epoch": 0.9783121169259783, "percentage": 4.89, "elapsed_time": "0:07:15", "remaining_time": "2:21:10", "throughput": 4791.13, "total_tokens": 2087136} {"current_steps": 2080, "total_steps": 42420, "loss": 0.5385, "lr": 2.4504950495049507e-05, "epoch": 0.9806694955209807, "percentage": 4.9, "elapsed_time": "0:07:16", "remaining_time": "2:21:09", "throughput": 4791.47, "total_tokens": 2092352} {"current_steps": 2085, "total_steps": 42420, "loss": 0.0883, "lr": 2.4563884959924567e-05, "epoch": 0.983026874115983, "percentage": 4.92, "elapsed_time": "0:07:17", "remaining_time": "2:21:05", "throughput": 4791.27, "total_tokens": 2096576} {"current_steps": 2090, "total_steps": 42420, "loss": 0.1547, "lr": 2.4622819424799623e-05, "epoch": 0.9853842527109854, "percentage": 4.93, "elapsed_time": "0:07:18", "remaining_time": "2:21:03", "throughput": 4791.32, "total_tokens": 2101472} {"current_steps": 2095, "total_steps": 42420, "loss": 0.5854, "lr": 2.4681753889674683e-05, "epoch": 0.9877416313059877, "percentage": 4.94, "elapsed_time": "0:07:19", "remaining_time": "2:21:00", "throughput": 4791.46, "total_tokens": 2106144} {"current_steps": 2100, "total_steps": 42420, "loss": 0.4764, "lr": 2.4740688354549742e-05, "epoch": 0.9900990099009901, "percentage": 4.95, "elapsed_time": "0:07:20", "remaining_time": "2:20:58", "throughput": 4791.6, "total_tokens": 2110880} {"current_steps": 2105, "total_steps": 42420, "loss": 0.1748, "lr": 2.4799622819424802e-05, "epoch": 0.9924563884959925, "percentage": 4.96, "elapsed_time": "0:07:21", "remaining_time": "2:20:56", "throughput": 4791.33, "total_tokens": 2115712} {"current_steps": 2110, "total_steps": 42420, "loss": 0.1007, "lr": 2.485855728429986e-05, "epoch": 0.9948137670909948, "percentage": 4.97, "elapsed_time": "0:07:22", "remaining_time": "2:20:53", "throughput": 4791.48, "total_tokens": 2120192} {"current_steps": 2115, "total_steps": 42420, "loss": 0.1933, "lr": 2.4917491749174918e-05, "epoch": 0.9971711456859972, "percentage": 4.99, "elapsed_time": "0:07:23", "remaining_time": "2:20:53", "throughput": 4791.87, "total_tokens": 2125728} {"current_steps": 2120, "total_steps": 42420, "loss": 0.2441, "lr": 2.4976426214049977e-05, "epoch": 0.9995285242809995, "percentage": 5.0, "elapsed_time": "0:07:24", "remaining_time": "2:20:51", "throughput": 4792.06, "total_tokens": 2130624} {"current_steps": 2121, "total_steps": 42420, "eval_loss": 0.21642036736011505, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:07:40", "remaining_time": "2:25:42", "throughput": 4633.48, "total_tokens": 2131904} {"current_steps": 2125, "total_steps": 42420, "loss": 0.1318, "lr": 2.5035360678925034e-05, "epoch": 1.0018859028760019, "percentage": 5.01, "elapsed_time": "0:07:42", "remaining_time": "2:26:07", "throughput": 4619.88, "total_tokens": 2136160} {"current_steps": 2130, "total_steps": 42420, "loss": 0.1356, "lr": 2.5094295143800097e-05, "epoch": 1.0042432814710043, "percentage": 5.02, "elapsed_time": "0:07:43", "remaining_time": "2:26:03", "throughput": 4619.89, "total_tokens": 2140320} {"current_steps": 2135, "total_steps": 42420, "loss": 0.3517, "lr": 2.5153229608675156e-05, "epoch": 1.0066006600660067, "percentage": 5.03, "elapsed_time": "0:07:44", "remaining_time": "2:26:03", "throughput": 4620.73, "total_tokens": 2145952} {"current_steps": 2140, "total_steps": 42420, "loss": 0.2544, "lr": 2.5212164073550216e-05, "epoch": 1.0089580386610089, "percentage": 5.04, "elapsed_time": "0:07:45", "remaining_time": "2:26:04", "throughput": 4621.53, "total_tokens": 2151936} {"current_steps": 2145, "total_steps": 42420, "loss": 0.0446, "lr": 2.527109853842527e-05, "epoch": 1.0113154172560113, "percentage": 5.06, "elapsed_time": "0:07:46", "remaining_time": "2:26:05", "throughput": 4622.12, "total_tokens": 2157824} {"current_steps": 2150, "total_steps": 42420, "loss": 0.131, "lr": 2.533003300330033e-05, "epoch": 1.0136727958510137, "percentage": 5.07, "elapsed_time": "0:07:48", "remaining_time": "2:26:06", "throughput": 4622.79, "total_tokens": 2163744} {"current_steps": 2155, "total_steps": 42420, "loss": 0.1303, "lr": 2.538896746817539e-05, "epoch": 1.016030174446016, "percentage": 5.08, "elapsed_time": "0:07:49", "remaining_time": "2:26:04", "throughput": 4623.27, "total_tokens": 2168608} {"current_steps": 2160, "total_steps": 42420, "loss": 0.1154, "lr": 2.544790193305045e-05, "epoch": 1.0183875530410185, "percentage": 5.09, "elapsed_time": "0:07:50", "remaining_time": "2:26:01", "throughput": 4623.48, "total_tokens": 2173312} {"current_steps": 2165, "total_steps": 42420, "loss": 0.3404, "lr": 2.550683639792551e-05, "epoch": 1.0207449316360206, "percentage": 5.1, "elapsed_time": "0:07:51", "remaining_time": "2:26:01", "throughput": 4624.35, "total_tokens": 2179008} {"current_steps": 2170, "total_steps": 42420, "loss": 0.3197, "lr": 2.5565770862800564e-05, "epoch": 1.023102310231023, "percentage": 5.12, "elapsed_time": "0:07:52", "remaining_time": "2:26:00", "throughput": 4624.87, "total_tokens": 2184320} {"current_steps": 2175, "total_steps": 42420, "loss": 0.3234, "lr": 2.5624705327675623e-05, "epoch": 1.0254596888260255, "percentage": 5.13, "elapsed_time": "0:07:53", "remaining_time": "2:25:57", "throughput": 4625.07, "total_tokens": 2188928} {"current_steps": 2180, "total_steps": 42420, "loss": 0.117, "lr": 2.5683639792550683e-05, "epoch": 1.0278170674210279, "percentage": 5.14, "elapsed_time": "0:07:54", "remaining_time": "2:25:55", "throughput": 4625.4, "total_tokens": 2194016} {"current_steps": 2185, "total_steps": 42420, "loss": 0.3228, "lr": 2.5742574257425746e-05, "epoch": 1.0301744460160303, "percentage": 5.15, "elapsed_time": "0:07:55", "remaining_time": "2:25:50", "throughput": 4624.87, "total_tokens": 2197632} {"current_steps": 2190, "total_steps": 42420, "loss": 0.1585, "lr": 2.5801508722300805e-05, "epoch": 1.0325318246110324, "percentage": 5.16, "elapsed_time": "0:07:56", "remaining_time": "2:25:50", "throughput": 4625.22, "total_tokens": 2203328} {"current_steps": 2195, "total_steps": 42420, "loss": 0.1932, "lr": 2.5860443187175858e-05, "epoch": 1.0348892032060348, "percentage": 5.17, "elapsed_time": "0:07:57", "remaining_time": "2:25:47", "throughput": 4624.37, "total_tokens": 2207424} {"current_steps": 2200, "total_steps": 42420, "loss": 0.2348, "lr": 2.5919377652050918e-05, "epoch": 1.0372465818010372, "percentage": 5.19, "elapsed_time": "0:07:58", "remaining_time": "2:25:43", "throughput": 4624.47, "total_tokens": 2211616} {"current_steps": 2205, "total_steps": 42420, "loss": 0.2061, "lr": 2.5978312116925978e-05, "epoch": 1.0396039603960396, "percentage": 5.2, "elapsed_time": "0:07:59", "remaining_time": "2:25:38", "throughput": 4624.66, "total_tokens": 2215776} {"current_steps": 2210, "total_steps": 42420, "loss": 0.3564, "lr": 2.603724658180104e-05, "epoch": 1.041961338991042, "percentage": 5.21, "elapsed_time": "0:08:00", "remaining_time": "2:25:36", "throughput": 4624.64, "total_tokens": 2220576} {"current_steps": 2215, "total_steps": 42420, "loss": 0.444, "lr": 2.60961810466761e-05, "epoch": 1.0443187175860442, "percentage": 5.22, "elapsed_time": "0:08:01", "remaining_time": "2:25:33", "throughput": 4624.36, "total_tokens": 2225024} {"current_steps": 2220, "total_steps": 42420, "loss": 0.228, "lr": 2.6155115511551153e-05, "epoch": 1.0466760961810466, "percentage": 5.23, "elapsed_time": "0:08:02", "remaining_time": "2:25:32", "throughput": 4624.21, "total_tokens": 2229888} {"current_steps": 2225, "total_steps": 42420, "loss": 0.3389, "lr": 2.6214049976426213e-05, "epoch": 1.049033474776049, "percentage": 5.25, "elapsed_time": "0:08:03", "remaining_time": "2:25:29", "throughput": 4624.21, "total_tokens": 2234624} {"current_steps": 2230, "total_steps": 42420, "loss": 0.0992, "lr": 2.6272984441301272e-05, "epoch": 1.0513908533710514, "percentage": 5.26, "elapsed_time": "0:08:04", "remaining_time": "2:25:25", "throughput": 4623.91, "total_tokens": 2238656} {"current_steps": 2235, "total_steps": 42420, "loss": 0.0696, "lr": 2.6331918906176335e-05, "epoch": 1.0537482319660538, "percentage": 5.27, "elapsed_time": "0:08:05", "remaining_time": "2:25:23", "throughput": 4624.32, "total_tokens": 2243552} {"current_steps": 2240, "total_steps": 42420, "loss": 0.1282, "lr": 2.6390853371051395e-05, "epoch": 1.056105610561056, "percentage": 5.28, "elapsed_time": "0:08:06", "remaining_time": "2:25:22", "throughput": 4624.85, "total_tokens": 2249056} {"current_steps": 2245, "total_steps": 42420, "loss": 0.3155, "lr": 2.6449787835926448e-05, "epoch": 1.0584629891560584, "percentage": 5.29, "elapsed_time": "0:08:07", "remaining_time": "2:25:21", "throughput": 4625.16, "total_tokens": 2254080} {"current_steps": 2250, "total_steps": 42420, "loss": 0.1008, "lr": 2.6508722300801507e-05, "epoch": 1.0608203677510608, "percentage": 5.3, "elapsed_time": "0:08:08", "remaining_time": "2:25:19", "throughput": 4625.69, "total_tokens": 2259232} {"current_steps": 2255, "total_steps": 42420, "loss": 0.1357, "lr": 2.6567656765676567e-05, "epoch": 1.0631777463460632, "percentage": 5.32, "elapsed_time": "0:08:09", "remaining_time": "2:25:16", "throughput": 4625.76, "total_tokens": 2263680} {"current_steps": 2260, "total_steps": 42420, "loss": 0.2266, "lr": 2.662659123055163e-05, "epoch": 1.0655351249410656, "percentage": 5.33, "elapsed_time": "0:08:10", "remaining_time": "2:25:12", "throughput": 4625.76, "total_tokens": 2267904} {"current_steps": 2265, "total_steps": 42420, "loss": 0.1956, "lr": 2.668552569542669e-05, "epoch": 1.0678925035360678, "percentage": 5.34, "elapsed_time": "0:08:11", "remaining_time": "2:25:10", "throughput": 4626.39, "total_tokens": 2272992} {"current_steps": 2270, "total_steps": 42420, "loss": 0.3177, "lr": 2.6744460160301743e-05, "epoch": 1.0702498821310702, "percentage": 5.35, "elapsed_time": "0:08:12", "remaining_time": "2:25:05", "throughput": 4626.0, "total_tokens": 2276864} {"current_steps": 2275, "total_steps": 42420, "loss": 0.3144, "lr": 2.6803394625176802e-05, "epoch": 1.0726072607260726, "percentage": 5.36, "elapsed_time": "0:08:13", "remaining_time": "2:25:06", "throughput": 4626.73, "total_tokens": 2282688} {"current_steps": 2280, "total_steps": 42420, "loss": 0.4353, "lr": 2.6862329090051862e-05, "epoch": 1.074964639321075, "percentage": 5.37, "elapsed_time": "0:08:14", "remaining_time": "2:25:01", "throughput": 4626.54, "total_tokens": 2286720} {"current_steps": 2285, "total_steps": 42420, "loss": 0.1366, "lr": 2.6921263554926925e-05, "epoch": 1.0773220179160774, "percentage": 5.39, "elapsed_time": "0:08:15", "remaining_time": "2:24:58", "throughput": 4626.97, "total_tokens": 2291488} {"current_steps": 2290, "total_steps": 42420, "loss": 0.2038, "lr": 2.6980198019801985e-05, "epoch": 1.0796793965110796, "percentage": 5.4, "elapsed_time": "0:08:16", "remaining_time": "2:24:58", "throughput": 4627.09, "total_tokens": 2296736} {"current_steps": 2295, "total_steps": 42420, "loss": 0.3165, "lr": 2.7039132484677037e-05, "epoch": 1.082036775106082, "percentage": 5.41, "elapsed_time": "0:08:17", "remaining_time": "2:24:54", "throughput": 4627.18, "total_tokens": 2301184} {"current_steps": 2300, "total_steps": 42420, "loss": 0.2067, "lr": 2.7098066949552097e-05, "epoch": 1.0843941537010844, "percentage": 5.42, "elapsed_time": "0:08:18", "remaining_time": "2:24:51", "throughput": 4627.38, "total_tokens": 2305536} {"current_steps": 2305, "total_steps": 42420, "loss": 0.1162, "lr": 2.7157001414427157e-05, "epoch": 1.0867515322960868, "percentage": 5.43, "elapsed_time": "0:08:19", "remaining_time": "2:24:52", "throughput": 4627.83, "total_tokens": 2311584} {"current_steps": 2310, "total_steps": 42420, "loss": 0.1575, "lr": 2.7215935879302216e-05, "epoch": 1.0891089108910892, "percentage": 5.45, "elapsed_time": "0:08:20", "remaining_time": "2:24:49", "throughput": 4628.09, "total_tokens": 2316192} {"current_steps": 2315, "total_steps": 42420, "loss": 0.2278, "lr": 2.727487034417728e-05, "epoch": 1.0914662894860914, "percentage": 5.46, "elapsed_time": "0:08:21", "remaining_time": "2:24:45", "throughput": 4627.73, "total_tokens": 2320256} {"current_steps": 2320, "total_steps": 42420, "loss": 0.2527, "lr": 2.7333804809052332e-05, "epoch": 1.0938236680810938, "percentage": 5.47, "elapsed_time": "0:08:22", "remaining_time": "2:24:41", "throughput": 4627.77, "total_tokens": 2324384} {"current_steps": 2325, "total_steps": 42420, "loss": 0.1136, "lr": 2.7392739273927392e-05, "epoch": 1.0961810466760962, "percentage": 5.48, "elapsed_time": "0:08:23", "remaining_time": "2:24:38", "throughput": 4628.05, "total_tokens": 2328960} {"current_steps": 2330, "total_steps": 42420, "loss": 0.2339, "lr": 2.745167373880245e-05, "epoch": 1.0985384252710986, "percentage": 5.49, "elapsed_time": "0:08:24", "remaining_time": "2:24:37", "throughput": 4628.56, "total_tokens": 2334368} {"current_steps": 2335, "total_steps": 42420, "loss": 0.1549, "lr": 2.751060820367751e-05, "epoch": 1.100895803866101, "percentage": 5.5, "elapsed_time": "0:08:25", "remaining_time": "2:24:35", "throughput": 4628.67, "total_tokens": 2339008} {"current_steps": 2340, "total_steps": 42420, "loss": 0.2015, "lr": 2.7569542668552574e-05, "epoch": 1.1032531824611032, "percentage": 5.52, "elapsed_time": "0:08:26", "remaining_time": "2:24:31", "throughput": 4628.77, "total_tokens": 2343392} {"current_steps": 2345, "total_steps": 42420, "loss": 0.2196, "lr": 2.7628477133427627e-05, "epoch": 1.1056105610561056, "percentage": 5.53, "elapsed_time": "0:08:27", "remaining_time": "2:24:31", "throughput": 4629.51, "total_tokens": 2349184} {"current_steps": 2350, "total_steps": 42420, "loss": 0.181, "lr": 2.7687411598302687e-05, "epoch": 1.107967939651108, "percentage": 5.54, "elapsed_time": "0:08:28", "remaining_time": "2:24:27", "throughput": 4629.19, "total_tokens": 2353024} {"current_steps": 2355, "total_steps": 42420, "loss": 0.3456, "lr": 2.7746346063177746e-05, "epoch": 1.1103253182461104, "percentage": 5.55, "elapsed_time": "0:08:29", "remaining_time": "2:24:24", "throughput": 4629.43, "total_tokens": 2357856} {"current_steps": 2360, "total_steps": 42420, "loss": 0.2579, "lr": 2.7805280528052806e-05, "epoch": 1.1126826968411128, "percentage": 5.56, "elapsed_time": "0:08:31", "remaining_time": "2:24:34", "throughput": 4630.04, "total_tokens": 2366080} {"current_steps": 2365, "total_steps": 42420, "loss": 0.5999, "lr": 2.786421499292787e-05, "epoch": 1.115040075436115, "percentage": 5.58, "elapsed_time": "0:08:32", "remaining_time": "2:24:33", "throughput": 4630.5, "total_tokens": 2371424} {"current_steps": 2370, "total_steps": 42420, "loss": 0.1537, "lr": 2.792314945780292e-05, "epoch": 1.1173974540311173, "percentage": 5.59, "elapsed_time": "0:08:33", "remaining_time": "2:24:36", "throughput": 4631.45, "total_tokens": 2378112} {"current_steps": 2375, "total_steps": 42420, "loss": 0.1186, "lr": 2.798208392267798e-05, "epoch": 1.1197548326261197, "percentage": 5.6, "elapsed_time": "0:08:34", "remaining_time": "2:24:35", "throughput": 4631.71, "total_tokens": 2383040} {"current_steps": 2380, "total_steps": 42420, "loss": 0.1502, "lr": 2.804101838755304e-05, "epoch": 1.1221122112211221, "percentage": 5.61, "elapsed_time": "0:08:35", "remaining_time": "2:24:31", "throughput": 4631.91, "total_tokens": 2387360} {"current_steps": 2385, "total_steps": 42420, "loss": 0.2728, "lr": 2.80999528524281e-05, "epoch": 1.1244695898161245, "percentage": 5.62, "elapsed_time": "0:08:36", "remaining_time": "2:24:29", "throughput": 4632.51, "total_tokens": 2392576} {"current_steps": 2390, "total_steps": 42420, "loss": 0.1072, "lr": 2.8158887317303164e-05, "epoch": 1.1268269684111267, "percentage": 5.63, "elapsed_time": "0:08:37", "remaining_time": "2:24:27", "throughput": 4633.17, "total_tokens": 2397760} {"current_steps": 2395, "total_steps": 42420, "loss": 0.1299, "lr": 2.8217821782178216e-05, "epoch": 1.1291843470061291, "percentage": 5.65, "elapsed_time": "0:08:38", "remaining_time": "2:24:23", "throughput": 4633.14, "total_tokens": 2401792} {"current_steps": 2400, "total_steps": 42420, "loss": 0.2337, "lr": 2.8276756247053276e-05, "epoch": 1.1315417256011315, "percentage": 5.66, "elapsed_time": "0:08:39", "remaining_time": "2:24:24", "throughput": 4633.74, "total_tokens": 2407680} {"current_steps": 2405, "total_steps": 42420, "loss": 0.1614, "lr": 2.8335690711928336e-05, "epoch": 1.133899104196134, "percentage": 5.67, "elapsed_time": "0:08:40", "remaining_time": "2:24:21", "throughput": 4634.23, "total_tokens": 2412512} {"current_steps": 2410, "total_steps": 42420, "loss": 0.2188, "lr": 2.8394625176803395e-05, "epoch": 1.1362564827911363, "percentage": 5.68, "elapsed_time": "0:08:41", "remaining_time": "2:24:20", "throughput": 4634.62, "total_tokens": 2417696} {"current_steps": 2415, "total_steps": 42420, "loss": 0.2638, "lr": 2.8453559641678455e-05, "epoch": 1.1386138613861387, "percentage": 5.69, "elapsed_time": "0:08:42", "remaining_time": "2:24:17", "throughput": 4634.9, "total_tokens": 2422304} {"current_steps": 2420, "total_steps": 42420, "loss": 0.0477, "lr": 2.851249410655351e-05, "epoch": 1.140971239981141, "percentage": 5.7, "elapsed_time": "0:08:43", "remaining_time": "2:24:16", "throughput": 4635.48, "total_tokens": 2427552} {"current_steps": 2425, "total_steps": 42420, "loss": 0.0658, "lr": 2.857142857142857e-05, "epoch": 1.1433286185761433, "percentage": 5.72, "elapsed_time": "0:08:44", "remaining_time": "2:24:14", "throughput": 4635.88, "total_tokens": 2432544} {"current_steps": 2430, "total_steps": 42420, "loss": 0.3126, "lr": 2.863036303630363e-05, "epoch": 1.1456859971711457, "percentage": 5.73, "elapsed_time": "0:08:45", "remaining_time": "2:24:11", "throughput": 4635.97, "total_tokens": 2437248} {"current_steps": 2435, "total_steps": 42420, "loss": 0.116, "lr": 2.868929750117869e-05, "epoch": 1.1480433757661481, "percentage": 5.74, "elapsed_time": "0:08:46", "remaining_time": "2:24:11", "throughput": 4636.52, "total_tokens": 2442912} {"current_steps": 2440, "total_steps": 42420, "loss": 0.4469, "lr": 2.874823196605375e-05, "epoch": 1.1504007543611503, "percentage": 5.75, "elapsed_time": "0:08:48", "remaining_time": "2:24:13", "throughput": 4637.24, "total_tokens": 2449184} {"current_steps": 2445, "total_steps": 42420, "loss": 0.6151, "lr": 2.8807166430928806e-05, "epoch": 1.1527581329561527, "percentage": 5.76, "elapsed_time": "0:08:49", "remaining_time": "2:24:14", "throughput": 4637.98, "total_tokens": 2455008} {"current_steps": 2450, "total_steps": 42420, "loss": 0.2803, "lr": 2.8866100895803866e-05, "epoch": 1.155115511551155, "percentage": 5.78, "elapsed_time": "0:08:50", "remaining_time": "2:24:11", "throughput": 4638.43, "total_tokens": 2459872} {"current_steps": 2455, "total_steps": 42420, "loss": 0.2926, "lr": 2.8925035360678925e-05, "epoch": 1.1574728901461575, "percentage": 5.79, "elapsed_time": "0:08:51", "remaining_time": "2:24:13", "throughput": 4639.09, "total_tokens": 2466016} {"current_steps": 2460, "total_steps": 42420, "loss": 0.153, "lr": 2.8983969825553985e-05, "epoch": 1.15983026874116, "percentage": 5.8, "elapsed_time": "0:08:52", "remaining_time": "2:24:13", "throughput": 4639.43, "total_tokens": 2471584} {"current_steps": 2465, "total_steps": 42420, "loss": 0.2378, "lr": 2.9042904290429045e-05, "epoch": 1.1621876473361623, "percentage": 5.81, "elapsed_time": "0:08:54", "remaining_time": "2:24:17", "throughput": 4639.99, "total_tokens": 2478400} {"current_steps": 2470, "total_steps": 42420, "loss": 0.1393, "lr": 2.91018387553041e-05, "epoch": 1.1645450259311645, "percentage": 5.82, "elapsed_time": "0:08:55", "remaining_time": "2:24:14", "throughput": 4640.06, "total_tokens": 2482752} {"current_steps": 2475, "total_steps": 42420, "loss": 0.2291, "lr": 2.916077322017916e-05, "epoch": 1.166902404526167, "percentage": 5.83, "elapsed_time": "0:08:56", "remaining_time": "2:24:12", "throughput": 4640.2, "total_tokens": 2487584} {"current_steps": 2480, "total_steps": 42420, "loss": 0.3368, "lr": 2.921970768505422e-05, "epoch": 1.1692597831211693, "percentage": 5.85, "elapsed_time": "0:08:56", "remaining_time": "2:24:08", "throughput": 4640.49, "total_tokens": 2491872} {"current_steps": 2485, "total_steps": 42420, "loss": 0.143, "lr": 2.927864214992928e-05, "epoch": 1.1716171617161717, "percentage": 5.86, "elapsed_time": "0:08:58", "remaining_time": "2:24:06", "throughput": 4641.03, "total_tokens": 2497056} {"current_steps": 2490, "total_steps": 42420, "loss": 0.2634, "lr": 2.933757661480434e-05, "epoch": 1.1739745403111739, "percentage": 5.87, "elapsed_time": "0:08:59", "remaining_time": "2:24:06", "throughput": 4641.81, "total_tokens": 2502880} {"current_steps": 2495, "total_steps": 42420, "loss": 0.1662, "lr": 2.9396511079679396e-05, "epoch": 1.1763319189061763, "percentage": 5.88, "elapsed_time": "0:09:00", "remaining_time": "2:24:06", "throughput": 4642.37, "total_tokens": 2508480} {"current_steps": 2500, "total_steps": 42420, "loss": 0.1313, "lr": 2.9455445544554455e-05, "epoch": 1.1786892975011787, "percentage": 5.89, "elapsed_time": "0:09:01", "remaining_time": "2:24:03", "throughput": 4642.4, "total_tokens": 2512960} {"current_steps": 2505, "total_steps": 42420, "loss": 0.2914, "lr": 2.9514380009429515e-05, "epoch": 1.181046676096181, "percentage": 5.91, "elapsed_time": "0:09:02", "remaining_time": "2:24:06", "throughput": 4643.16, "total_tokens": 2519456} {"current_steps": 2510, "total_steps": 42420, "loss": 0.1418, "lr": 2.9573314474304574e-05, "epoch": 1.1834040546911835, "percentage": 5.92, "elapsed_time": "0:09:03", "remaining_time": "2:24:06", "throughput": 4643.6, "total_tokens": 2525216} {"current_steps": 2515, "total_steps": 42420, "loss": 0.2274, "lr": 2.9632248939179634e-05, "epoch": 1.1857614332861859, "percentage": 5.93, "elapsed_time": "0:09:04", "remaining_time": "2:24:04", "throughput": 4643.95, "total_tokens": 2530240} {"current_steps": 2520, "total_steps": 42420, "loss": 0.1312, "lr": 2.969118340405469e-05, "epoch": 1.188118811881188, "percentage": 5.94, "elapsed_time": "0:09:05", "remaining_time": "2:24:04", "throughput": 4644.17, "total_tokens": 2535552} {"current_steps": 2525, "total_steps": 42420, "loss": 0.1527, "lr": 2.975011786892975e-05, "epoch": 1.1904761904761905, "percentage": 5.95, "elapsed_time": "0:09:07", "remaining_time": "2:24:02", "throughput": 4644.62, "total_tokens": 2540704} {"current_steps": 2530, "total_steps": 42420, "loss": 0.1019, "lr": 2.980905233380481e-05, "epoch": 1.1928335690711929, "percentage": 5.96, "elapsed_time": "0:09:08", "remaining_time": "2:24:00", "throughput": 4644.5, "total_tokens": 2545376} {"current_steps": 2535, "total_steps": 42420, "loss": 0.2135, "lr": 2.986798679867987e-05, "epoch": 1.1951909476661953, "percentage": 5.98, "elapsed_time": "0:09:09", "remaining_time": "2:23:59", "throughput": 4644.75, "total_tokens": 2550592} {"current_steps": 2540, "total_steps": 42420, "loss": 0.1192, "lr": 2.992692126355493e-05, "epoch": 1.1975483262611974, "percentage": 5.99, "elapsed_time": "0:09:10", "remaining_time": "2:23:56", "throughput": 4644.59, "total_tokens": 2554912} {"current_steps": 2545, "total_steps": 42420, "loss": 0.1427, "lr": 2.9985855728429985e-05, "epoch": 1.1999057048561999, "percentage": 6.0, "elapsed_time": "0:09:11", "remaining_time": "2:23:55", "throughput": 4645.11, "total_tokens": 2560064} {"current_steps": 2550, "total_steps": 42420, "loss": 0.1616, "lr": 3.0044790193305045e-05, "epoch": 1.2022630834512023, "percentage": 6.01, "elapsed_time": "0:09:12", "remaining_time": "2:23:53", "throughput": 4645.45, "total_tokens": 2565184} {"current_steps": 2555, "total_steps": 42420, "loss": 0.3848, "lr": 3.0103724658180104e-05, "epoch": 1.2046204620462047, "percentage": 6.02, "elapsed_time": "0:09:13", "remaining_time": "2:23:50", "throughput": 4645.47, "total_tokens": 2569696} {"current_steps": 2560, "total_steps": 42420, "loss": 0.1893, "lr": 3.0162659123055164e-05, "epoch": 1.206977840641207, "percentage": 6.03, "elapsed_time": "0:09:14", "remaining_time": "2:23:47", "throughput": 4645.56, "total_tokens": 2574112} {"current_steps": 2565, "total_steps": 42420, "loss": 0.2794, "lr": 3.0221593587930224e-05, "epoch": 1.2093352192362095, "percentage": 6.05, "elapsed_time": "0:09:15", "remaining_time": "2:23:44", "throughput": 4645.63, "total_tokens": 2578688} {"current_steps": 2570, "total_steps": 42420, "loss": 0.1863, "lr": 3.028052805280528e-05, "epoch": 1.2116925978312116, "percentage": 6.06, "elapsed_time": "0:09:16", "remaining_time": "2:23:42", "throughput": 4645.96, "total_tokens": 2583552} {"current_steps": 2575, "total_steps": 42420, "loss": 0.236, "lr": 3.033946251768034e-05, "epoch": 1.214049976426214, "percentage": 6.07, "elapsed_time": "0:09:17", "remaining_time": "2:23:40", "throughput": 4646.36, "total_tokens": 2588384} {"current_steps": 2580, "total_steps": 42420, "loss": 0.2431, "lr": 3.03983969825554e-05, "epoch": 1.2164073550212164, "percentage": 6.08, "elapsed_time": "0:09:18", "remaining_time": "2:23:38", "throughput": 4646.67, "total_tokens": 2593504} {"current_steps": 2585, "total_steps": 42420, "loss": 0.0945, "lr": 3.045733144743046e-05, "epoch": 1.2187647336162188, "percentage": 6.09, "elapsed_time": "0:09:19", "remaining_time": "2:23:37", "throughput": 4647.27, "total_tokens": 2598752} {"current_steps": 2590, "total_steps": 42420, "loss": 0.2637, "lr": 3.051626591230552e-05, "epoch": 1.221122112211221, "percentage": 6.11, "elapsed_time": "0:09:20", "remaining_time": "2:23:36", "throughput": 4647.79, "total_tokens": 2604096} {"current_steps": 2595, "total_steps": 42420, "loss": 0.1845, "lr": 3.057520037718057e-05, "epoch": 1.2234794908062234, "percentage": 6.12, "elapsed_time": "0:09:21", "remaining_time": "2:23:34", "throughput": 4648.05, "total_tokens": 2608960} {"current_steps": 2600, "total_steps": 42420, "loss": 0.3413, "lr": 3.063413484205563e-05, "epoch": 1.2258368694012258, "percentage": 6.13, "elapsed_time": "0:09:22", "remaining_time": "2:23:34", "throughput": 4648.44, "total_tokens": 2614528} {"current_steps": 2605, "total_steps": 42420, "loss": 0.1082, "lr": 3.06930693069307e-05, "epoch": 1.2281942479962282, "percentage": 6.14, "elapsed_time": "0:09:23", "remaining_time": "2:23:32", "throughput": 4649.01, "total_tokens": 2619712} {"current_steps": 2610, "total_steps": 42420, "loss": 0.1438, "lr": 3.075200377180576e-05, "epoch": 1.2305516265912306, "percentage": 6.15, "elapsed_time": "0:09:24", "remaining_time": "2:23:29", "throughput": 4649.03, "total_tokens": 2624096} {"current_steps": 2615, "total_steps": 42420, "loss": 0.2804, "lr": 3.0810938236680817e-05, "epoch": 1.232909005186233, "percentage": 6.16, "elapsed_time": "0:09:25", "remaining_time": "2:23:25", "throughput": 4648.96, "total_tokens": 2628256} {"current_steps": 2620, "total_steps": 42420, "loss": 0.2549, "lr": 3.086987270155587e-05, "epoch": 1.2352663837812352, "percentage": 6.18, "elapsed_time": "0:09:26", "remaining_time": "2:23:21", "throughput": 4648.93, "total_tokens": 2632448} {"current_steps": 2625, "total_steps": 42420, "loss": 0.1158, "lr": 3.092880716643093e-05, "epoch": 1.2376237623762376, "percentage": 6.19, "elapsed_time": "0:09:27", "remaining_time": "2:23:20", "throughput": 4649.36, "total_tokens": 2637696} {"current_steps": 2630, "total_steps": 42420, "loss": 0.0608, "lr": 3.098774163130599e-05, "epoch": 1.23998114097124, "percentage": 6.2, "elapsed_time": "0:09:28", "remaining_time": "2:23:17", "throughput": 4649.52, "total_tokens": 2642240} {"current_steps": 2635, "total_steps": 42420, "loss": 0.1709, "lr": 3.104667609618105e-05, "epoch": 1.2423385195662424, "percentage": 6.21, "elapsed_time": "0:09:29", "remaining_time": "2:23:15", "throughput": 4649.71, "total_tokens": 2647040} {"current_steps": 2640, "total_steps": 42420, "loss": 0.0587, "lr": 3.110561056105611e-05, "epoch": 1.2446958981612446, "percentage": 6.22, "elapsed_time": "0:09:30", "remaining_time": "2:23:13", "throughput": 4649.93, "total_tokens": 2652032} {"current_steps": 2645, "total_steps": 42420, "loss": 0.3198, "lr": 3.116454502593116e-05, "epoch": 1.247053276756247, "percentage": 6.24, "elapsed_time": "0:09:31", "remaining_time": "2:23:11", "throughput": 4650.01, "total_tokens": 2656768} {"current_steps": 2650, "total_steps": 42420, "loss": 0.1711, "lr": 3.122347949080622e-05, "epoch": 1.2494106553512494, "percentage": 6.25, "elapsed_time": "0:09:32", "remaining_time": "2:23:13", "throughput": 4650.66, "total_tokens": 2663008} {"current_steps": 2655, "total_steps": 42420, "loss": 0.09, "lr": 3.128241395568128e-05, "epoch": 1.2517680339462518, "percentage": 6.26, "elapsed_time": "0:09:33", "remaining_time": "2:23:13", "throughput": 4651.21, "total_tokens": 2668704} {"current_steps": 2660, "total_steps": 42420, "loss": 0.2109, "lr": 3.1341348420556346e-05, "epoch": 1.2541254125412542, "percentage": 6.27, "elapsed_time": "0:09:34", "remaining_time": "2:23:10", "throughput": 4651.35, "total_tokens": 2673056} {"current_steps": 2665, "total_steps": 42420, "loss": 0.2679, "lr": 3.1400282885431406e-05, "epoch": 1.2564827911362566, "percentage": 6.28, "elapsed_time": "0:09:35", "remaining_time": "2:23:07", "throughput": 4651.72, "total_tokens": 2677760} {"current_steps": 2670, "total_steps": 42420, "loss": 0.1996, "lr": 3.145921735030646e-05, "epoch": 1.2588401697312588, "percentage": 6.29, "elapsed_time": "0:09:36", "remaining_time": "2:23:04", "throughput": 4652.04, "total_tokens": 2682560} {"current_steps": 2675, "total_steps": 42420, "loss": 0.1452, "lr": 3.151815181518152e-05, "epoch": 1.2611975483262612, "percentage": 6.31, "elapsed_time": "0:09:37", "remaining_time": "2:23:04", "throughput": 4652.54, "total_tokens": 2688000} {"current_steps": 2680, "total_steps": 42420, "loss": 0.2253, "lr": 3.157708628005658e-05, "epoch": 1.2635549269212636, "percentage": 6.32, "elapsed_time": "0:09:38", "remaining_time": "2:23:02", "throughput": 4652.77, "total_tokens": 2692832} {"current_steps": 2685, "total_steps": 42420, "loss": 0.1981, "lr": 3.163602074493164e-05, "epoch": 1.265912305516266, "percentage": 6.33, "elapsed_time": "0:09:39", "remaining_time": "2:23:02", "throughput": 4653.14, "total_tokens": 2698528} {"current_steps": 2690, "total_steps": 42420, "loss": 0.1174, "lr": 3.16949552098067e-05, "epoch": 1.2682696841112682, "percentage": 6.34, "elapsed_time": "0:09:40", "remaining_time": "2:22:58", "throughput": 4652.7, "total_tokens": 2702336} {"current_steps": 2695, "total_steps": 42420, "loss": 0.2298, "lr": 3.175388967468175e-05, "epoch": 1.2706270627062706, "percentage": 6.35, "elapsed_time": "0:09:41", "remaining_time": "2:22:56", "throughput": 4652.63, "total_tokens": 2707008} {"current_steps": 2700, "total_steps": 42420, "loss": 0.4129, "lr": 3.181282413955681e-05, "epoch": 1.272984441301273, "percentage": 6.36, "elapsed_time": "0:09:42", "remaining_time": "2:22:53", "throughput": 4652.56, "total_tokens": 2711392} {"current_steps": 2705, "total_steps": 42420, "loss": 0.3058, "lr": 3.187175860443187e-05, "epoch": 1.2753418198962754, "percentage": 6.38, "elapsed_time": "0:09:43", "remaining_time": "2:22:50", "throughput": 4652.51, "total_tokens": 2716000} {"current_steps": 2710, "total_steps": 42420, "loss": 0.1856, "lr": 3.1930693069306936e-05, "epoch": 1.2776991984912778, "percentage": 6.39, "elapsed_time": "0:09:44", "remaining_time": "2:22:48", "throughput": 4652.9, "total_tokens": 2720736} {"current_steps": 2715, "total_steps": 42420, "loss": 0.1979, "lr": 3.1989627534181996e-05, "epoch": 1.2800565770862802, "percentage": 6.4, "elapsed_time": "0:09:45", "remaining_time": "2:22:46", "throughput": 4653.34, "total_tokens": 2725824} {"current_steps": 2720, "total_steps": 42420, "loss": 0.1629, "lr": 3.204856199905705e-05, "epoch": 1.2824139556812824, "percentage": 6.41, "elapsed_time": "0:09:46", "remaining_time": "2:22:45", "throughput": 4653.89, "total_tokens": 2731168} {"current_steps": 2725, "total_steps": 42420, "loss": 0.1152, "lr": 3.210749646393211e-05, "epoch": 1.2847713342762848, "percentage": 6.42, "elapsed_time": "0:09:47", "remaining_time": "2:22:43", "throughput": 4654.1, "total_tokens": 2736128} {"current_steps": 2730, "total_steps": 42420, "loss": 0.2051, "lr": 3.216643092880717e-05, "epoch": 1.2871287128712872, "percentage": 6.44, "elapsed_time": "0:09:48", "remaining_time": "2:22:40", "throughput": 4653.85, "total_tokens": 2740256} {"current_steps": 2735, "total_steps": 42420, "loss": 0.2841, "lr": 3.222536539368223e-05, "epoch": 1.2894860914662896, "percentage": 6.45, "elapsed_time": "0:09:49", "remaining_time": "2:22:40", "throughput": 4654.01, "total_tokens": 2745728} {"current_steps": 2740, "total_steps": 42420, "loss": 0.2234, "lr": 3.228429985855729e-05, "epoch": 1.2918434700612917, "percentage": 6.46, "elapsed_time": "0:09:50", "remaining_time": "2:22:38", "throughput": 4654.0, "total_tokens": 2750368} {"current_steps": 2745, "total_steps": 42420, "loss": 0.3475, "lr": 3.234323432343234e-05, "epoch": 1.2942008486562941, "percentage": 6.47, "elapsed_time": "0:09:52", "remaining_time": "2:22:44", "throughput": 4650.08, "total_tokens": 2755520} {"current_steps": 2750, "total_steps": 42420, "loss": 0.2435, "lr": 3.24021687883074e-05, "epoch": 1.2965582272512965, "percentage": 6.48, "elapsed_time": "0:09:53", "remaining_time": "2:22:41", "throughput": 4650.47, "total_tokens": 2760192} {"current_steps": 2755, "total_steps": 42420, "loss": 0.3016, "lr": 3.246110325318246e-05, "epoch": 1.298915605846299, "percentage": 6.49, "elapsed_time": "0:09:54", "remaining_time": "2:22:41", "throughput": 4651.1, "total_tokens": 2765920} {"current_steps": 2760, "total_steps": 42420, "loss": 0.1226, "lr": 3.2520037718057526e-05, "epoch": 1.3012729844413014, "percentage": 6.51, "elapsed_time": "0:09:55", "remaining_time": "2:22:38", "throughput": 4651.6, "total_tokens": 2770624} {"current_steps": 2765, "total_steps": 42420, "loss": 0.2106, "lr": 3.2578972182932585e-05, "epoch": 1.3036303630363038, "percentage": 6.52, "elapsed_time": "0:09:56", "remaining_time": "2:22:40", "throughput": 4652.42, "total_tokens": 2776960} {"current_steps": 2770, "total_steps": 42420, "loss": 0.1392, "lr": 3.263790664780764e-05, "epoch": 1.305987741631306, "percentage": 6.53, "elapsed_time": "0:09:57", "remaining_time": "2:22:38", "throughput": 4652.88, "total_tokens": 2782048} {"current_steps": 2775, "total_steps": 42420, "loss": 0.1255, "lr": 3.26968411126827e-05, "epoch": 1.3083451202263083, "percentage": 6.54, "elapsed_time": "0:09:59", "remaining_time": "2:22:38", "throughput": 4653.23, "total_tokens": 2787520} {"current_steps": 2780, "total_steps": 42420, "loss": 0.1106, "lr": 3.275577557755776e-05, "epoch": 1.3107024988213107, "percentage": 6.55, "elapsed_time": "0:10:00", "remaining_time": "2:22:35", "throughput": 4653.3, "total_tokens": 2792128} {"current_steps": 2785, "total_steps": 42420, "loss": 0.2465, "lr": 3.281471004243282e-05, "epoch": 1.3130598774163131, "percentage": 6.57, "elapsed_time": "0:10:01", "remaining_time": "2:22:36", "throughput": 4653.89, "total_tokens": 2797920} {"current_steps": 2790, "total_steps": 42420, "loss": 0.1842, "lr": 3.2873644507307877e-05, "epoch": 1.3154172560113153, "percentage": 6.58, "elapsed_time": "0:10:02", "remaining_time": "2:22:32", "throughput": 4654.05, "total_tokens": 2802368} {"current_steps": 2795, "total_steps": 42420, "loss": 0.221, "lr": 3.293257897218293e-05, "epoch": 1.3177746346063177, "percentage": 6.59, "elapsed_time": "0:10:03", "remaining_time": "2:22:29", "throughput": 4654.25, "total_tokens": 2806592} {"current_steps": 2800, "total_steps": 42420, "loss": 0.1556, "lr": 3.299151343705799e-05, "epoch": 1.3201320132013201, "percentage": 6.6, "elapsed_time": "0:10:04", "remaining_time": "2:22:27", "throughput": 4654.72, "total_tokens": 2811648} {"current_steps": 2805, "total_steps": 42420, "loss": 0.2001, "lr": 3.305044790193305e-05, "epoch": 1.3224893917963225, "percentage": 6.61, "elapsed_time": "0:10:05", "remaining_time": "2:22:26", "throughput": 4655.19, "total_tokens": 2817088} {"current_steps": 2810, "total_steps": 42420, "loss": 0.1427, "lr": 3.310938236680811e-05, "epoch": 1.324846770391325, "percentage": 6.62, "elapsed_time": "0:10:06", "remaining_time": "2:22:25", "throughput": 4655.36, "total_tokens": 2822240} {"current_steps": 2815, "total_steps": 42420, "loss": 0.1845, "lr": 3.3168316831683175e-05, "epoch": 1.3272041489863273, "percentage": 6.64, "elapsed_time": "0:10:07", "remaining_time": "2:22:21", "throughput": 4655.34, "total_tokens": 2826400} {"current_steps": 2820, "total_steps": 42420, "loss": 0.3437, "lr": 3.322725129655823e-05, "epoch": 1.3295615275813295, "percentage": 6.65, "elapsed_time": "0:10:08", "remaining_time": "2:22:22", "throughput": 4655.6, "total_tokens": 2832032} {"current_steps": 2825, "total_steps": 42420, "loss": 0.3661, "lr": 3.328618576143329e-05, "epoch": 1.331918906176332, "percentage": 6.66, "elapsed_time": "0:10:09", "remaining_time": "2:22:28", "throughput": 4656.36, "total_tokens": 2840000} {"current_steps": 2830, "total_steps": 42420, "loss": 0.2404, "lr": 3.334512022630835e-05, "epoch": 1.3342762847713343, "percentage": 6.67, "elapsed_time": "0:10:10", "remaining_time": "2:22:27", "throughput": 4656.89, "total_tokens": 2845312} {"current_steps": 2835, "total_steps": 42420, "loss": 0.3893, "lr": 3.3404054691183406e-05, "epoch": 1.3366336633663367, "percentage": 6.68, "elapsed_time": "0:10:11", "remaining_time": "2:22:24", "throughput": 4657.1, "total_tokens": 2849984} {"current_steps": 2840, "total_steps": 42420, "loss": 0.1307, "lr": 3.3462989156058466e-05, "epoch": 1.338991041961339, "percentage": 6.69, "elapsed_time": "0:10:12", "remaining_time": "2:22:22", "throughput": 4657.54, "total_tokens": 2854944} {"current_steps": 2845, "total_steps": 42420, "loss": 0.148, "lr": 3.352192362093352e-05, "epoch": 1.3413484205563413, "percentage": 6.71, "elapsed_time": "0:10:13", "remaining_time": "2:22:20", "throughput": 4657.81, "total_tokens": 2859776} {"current_steps": 2850, "total_steps": 42420, "loss": 0.1417, "lr": 3.358085808580858e-05, "epoch": 1.3437057991513437, "percentage": 6.72, "elapsed_time": "0:10:15", "remaining_time": "2:22:21", "throughput": 4657.94, "total_tokens": 2865472} {"current_steps": 2855, "total_steps": 42420, "loss": 0.1871, "lr": 3.363979255068364e-05, "epoch": 1.346063177746346, "percentage": 6.73, "elapsed_time": "0:10:16", "remaining_time": "2:22:20", "throughput": 4658.14, "total_tokens": 2870560} {"current_steps": 2860, "total_steps": 42420, "loss": 0.1038, "lr": 3.36987270155587e-05, "epoch": 1.3484205563413485, "percentage": 6.74, "elapsed_time": "0:10:17", "remaining_time": "2:22:16", "throughput": 4657.94, "total_tokens": 2874592} {"current_steps": 2865, "total_steps": 42420, "loss": 0.151, "lr": 3.3757661480433764e-05, "epoch": 1.350777934936351, "percentage": 6.75, "elapsed_time": "0:10:18", "remaining_time": "2:22:13", "throughput": 4658.12, "total_tokens": 2879264} {"current_steps": 2870, "total_steps": 42420, "loss": 0.0987, "lr": 3.381659594530882e-05, "epoch": 1.353135313531353, "percentage": 6.77, "elapsed_time": "0:10:19", "remaining_time": "2:22:12", "throughput": 4658.45, "total_tokens": 2884416} {"current_steps": 2875, "total_steps": 42420, "loss": 0.1138, "lr": 3.387553041018388e-05, "epoch": 1.3554926921263555, "percentage": 6.78, "elapsed_time": "0:10:20", "remaining_time": "2:22:10", "throughput": 4658.38, "total_tokens": 2889088} {"current_steps": 2880, "total_steps": 42420, "loss": 0.2459, "lr": 3.3934464875058936e-05, "epoch": 1.3578500707213579, "percentage": 6.79, "elapsed_time": "0:10:21", "remaining_time": "2:22:06", "throughput": 4658.29, "total_tokens": 2893088} {"current_steps": 2885, "total_steps": 42420, "loss": 0.0998, "lr": 3.3993399339933996e-05, "epoch": 1.3602074493163603, "percentage": 6.8, "elapsed_time": "0:10:22", "remaining_time": "2:22:09", "throughput": 4658.7, "total_tokens": 2899776} {"current_steps": 2890, "total_steps": 42420, "loss": 0.3344, "lr": 3.4052333804809056e-05, "epoch": 1.3625648279113625, "percentage": 6.81, "elapsed_time": "0:10:23", "remaining_time": "2:22:10", "throughput": 4659.04, "total_tokens": 2905536} {"current_steps": 2895, "total_steps": 42420, "loss": 0.1775, "lr": 3.411126826968411e-05, "epoch": 1.3649222065063649, "percentage": 6.82, "elapsed_time": "0:10:24", "remaining_time": "2:22:07", "throughput": 4659.29, "total_tokens": 2910240} {"current_steps": 2900, "total_steps": 42420, "loss": 0.2822, "lr": 3.417020273455917e-05, "epoch": 1.3672795851013673, "percentage": 6.84, "elapsed_time": "0:10:25", "remaining_time": "2:22:05", "throughput": 4659.3, "total_tokens": 2915040} {"current_steps": 2905, "total_steps": 42420, "loss": 0.3562, "lr": 3.422913719943423e-05, "epoch": 1.3696369636963697, "percentage": 6.85, "elapsed_time": "0:10:26", "remaining_time": "2:22:04", "throughput": 4659.57, "total_tokens": 2919968} {"current_steps": 2910, "total_steps": 42420, "loss": 0.1204, "lr": 3.428807166430929e-05, "epoch": 1.371994342291372, "percentage": 6.86, "elapsed_time": "0:10:27", "remaining_time": "2:22:02", "throughput": 4659.78, "total_tokens": 2924992} {"current_steps": 2915, "total_steps": 42420, "loss": 0.218, "lr": 3.434700612918435e-05, "epoch": 1.3743517208863745, "percentage": 6.87, "elapsed_time": "0:10:28", "remaining_time": "2:22:02", "throughput": 4660.45, "total_tokens": 2930912} {"current_steps": 2920, "total_steps": 42420, "loss": 0.1747, "lr": 3.440594059405941e-05, "epoch": 1.3767090994813767, "percentage": 6.88, "elapsed_time": "0:10:29", "remaining_time": "2:22:00", "throughput": 4660.64, "total_tokens": 2935744} {"current_steps": 2925, "total_steps": 42420, "loss": 0.4606, "lr": 3.4464875058934466e-05, "epoch": 1.379066478076379, "percentage": 6.9, "elapsed_time": "0:10:30", "remaining_time": "2:21:58", "throughput": 4660.75, "total_tokens": 2940256} {"current_steps": 2930, "total_steps": 42420, "loss": 0.1528, "lr": 3.4523809523809526e-05, "epoch": 1.3814238566713815, "percentage": 6.91, "elapsed_time": "0:10:31", "remaining_time": "2:21:57", "throughput": 4661.1, "total_tokens": 2945696} {"current_steps": 2935, "total_steps": 42420, "loss": 0.3017, "lr": 3.4582743988684586e-05, "epoch": 1.3837812352663839, "percentage": 6.92, "elapsed_time": "0:10:32", "remaining_time": "2:21:55", "throughput": 4661.22, "total_tokens": 2950304} {"current_steps": 2940, "total_steps": 42420, "loss": 0.1651, "lr": 3.4641678453559645e-05, "epoch": 1.386138613861386, "percentage": 6.93, "elapsed_time": "0:10:33", "remaining_time": "2:21:53", "throughput": 4661.46, "total_tokens": 2955200} {"current_steps": 2945, "total_steps": 42420, "loss": 0.2846, "lr": 3.47006129184347e-05, "epoch": 1.3884959924563884, "percentage": 6.94, "elapsed_time": "0:10:35", "remaining_time": "2:21:51", "throughput": 4661.72, "total_tokens": 2960256} {"current_steps": 2950, "total_steps": 42420, "loss": 0.08, "lr": 3.475954738330976e-05, "epoch": 1.3908533710513908, "percentage": 6.95, "elapsed_time": "0:10:35", "remaining_time": "2:21:48", "throughput": 4661.97, "total_tokens": 2964704} {"current_steps": 2955, "total_steps": 42420, "loss": 0.2769, "lr": 3.481848184818482e-05, "epoch": 1.3932107496463932, "percentage": 6.97, "elapsed_time": "0:10:36", "remaining_time": "2:21:46", "throughput": 4662.09, "total_tokens": 2969312} {"current_steps": 2960, "total_steps": 42420, "loss": 0.233, "lr": 3.487741631305988e-05, "epoch": 1.3955681282413956, "percentage": 6.98, "elapsed_time": "0:10:37", "remaining_time": "2:21:43", "throughput": 4662.16, "total_tokens": 2973728} {"current_steps": 2965, "total_steps": 42420, "loss": 0.3202, "lr": 3.4936350777934937e-05, "epoch": 1.397925506836398, "percentage": 6.99, "elapsed_time": "0:10:39", "remaining_time": "2:21:43", "throughput": 4662.5, "total_tokens": 2979424} {"current_steps": 2970, "total_steps": 42420, "loss": 0.0514, "lr": 3.4995285242809996e-05, "epoch": 1.4002828854314002, "percentage": 7.0, "elapsed_time": "0:10:40", "remaining_time": "2:21:41", "throughput": 4662.93, "total_tokens": 2984608} {"current_steps": 2975, "total_steps": 42420, "loss": 0.0863, "lr": 3.5054219707685056e-05, "epoch": 1.4026402640264026, "percentage": 7.01, "elapsed_time": "0:10:41", "remaining_time": "2:21:39", "throughput": 4662.99, "total_tokens": 2989248} {"current_steps": 2980, "total_steps": 42420, "loss": 0.2726, "lr": 3.5113154172560115e-05, "epoch": 1.404997642621405, "percentage": 7.02, "elapsed_time": "0:10:41", "remaining_time": "2:21:35", "throughput": 4662.87, "total_tokens": 2993248} {"current_steps": 2985, "total_steps": 42420, "loss": 0.1436, "lr": 3.5172088637435175e-05, "epoch": 1.4073550212164074, "percentage": 7.04, "elapsed_time": "0:10:42", "remaining_time": "2:21:33", "throughput": 4662.84, "total_tokens": 2997920} {"current_steps": 2990, "total_steps": 42420, "loss": 0.2163, "lr": 3.5231023102310235e-05, "epoch": 1.4097123998114096, "percentage": 7.05, "elapsed_time": "0:10:44", "remaining_time": "2:21:34", "throughput": 4663.3, "total_tokens": 3003776} {"current_steps": 2995, "total_steps": 42420, "loss": 0.2643, "lr": 3.528995756718529e-05, "epoch": 1.412069778406412, "percentage": 7.06, "elapsed_time": "0:10:45", "remaining_time": "2:21:31", "throughput": 4663.44, "total_tokens": 3008096} {"current_steps": 3000, "total_steps": 42420, "loss": 0.064, "lr": 3.534889203206035e-05, "epoch": 1.4144271570014144, "percentage": 7.07, "elapsed_time": "0:10:46", "remaining_time": "2:21:29", "throughput": 4663.63, "total_tokens": 3013152} {"current_steps": 3005, "total_steps": 42420, "loss": 0.133, "lr": 3.540782649693541e-05, "epoch": 1.4167845355964168, "percentage": 7.08, "elapsed_time": "0:10:46", "remaining_time": "2:21:25", "throughput": 4663.46, "total_tokens": 3017088} {"current_steps": 3010, "total_steps": 42420, "loss": 0.3245, "lr": 3.5466760961810467e-05, "epoch": 1.4191419141914192, "percentage": 7.1, "elapsed_time": "0:10:47", "remaining_time": "2:21:23", "throughput": 4663.7, "total_tokens": 3021824} {"current_steps": 3015, "total_steps": 42420, "loss": 0.2222, "lr": 3.5525695426685526e-05, "epoch": 1.4214992927864216, "percentage": 7.11, "elapsed_time": "0:10:48", "remaining_time": "2:21:20", "throughput": 4663.82, "total_tokens": 3026144} {"current_steps": 3020, "total_steps": 42420, "loss": 0.0537, "lr": 3.5584629891560586e-05, "epoch": 1.4238566713814238, "percentage": 7.12, "elapsed_time": "0:10:49", "remaining_time": "2:21:18", "throughput": 4663.89, "total_tokens": 3030784} {"current_steps": 3025, "total_steps": 42420, "loss": 0.1737, "lr": 3.5643564356435645e-05, "epoch": 1.4262140499764262, "percentage": 7.13, "elapsed_time": "0:10:50", "remaining_time": "2:21:15", "throughput": 4663.96, "total_tokens": 3035328} {"current_steps": 3030, "total_steps": 42420, "loss": 0.3717, "lr": 3.5702498821310705e-05, "epoch": 1.4285714285714286, "percentage": 7.14, "elapsed_time": "0:10:51", "remaining_time": "2:21:13", "throughput": 4664.2, "total_tokens": 3040224} {"current_steps": 3035, "total_steps": 42420, "loss": 0.2187, "lr": 3.5761433286185765e-05, "epoch": 1.430928807166431, "percentage": 7.15, "elapsed_time": "0:10:52", "remaining_time": "2:21:12", "throughput": 4664.37, "total_tokens": 3045344} {"current_steps": 3040, "total_steps": 42420, "loss": 0.1488, "lr": 3.5820367751060824e-05, "epoch": 1.4332861857614332, "percentage": 7.17, "elapsed_time": "0:10:53", "remaining_time": "2:21:09", "throughput": 4663.98, "total_tokens": 3049376} {"current_steps": 3045, "total_steps": 42420, "loss": 0.1562, "lr": 3.587930221593588e-05, "epoch": 1.4356435643564356, "percentage": 7.18, "elapsed_time": "0:10:54", "remaining_time": "2:21:09", "throughput": 4664.31, "total_tokens": 3054944} {"current_steps": 3050, "total_steps": 42420, "loss": 0.1922, "lr": 3.593823668081094e-05, "epoch": 1.438000942951438, "percentage": 7.19, "elapsed_time": "0:10:56", "remaining_time": "2:21:09", "throughput": 4664.76, "total_tokens": 3060672} {"current_steps": 3055, "total_steps": 42420, "loss": 0.2601, "lr": 3.5997171145685996e-05, "epoch": 1.4403583215464404, "percentage": 7.2, "elapsed_time": "0:10:57", "remaining_time": "2:21:06", "throughput": 4664.87, "total_tokens": 3065056} {"current_steps": 3060, "total_steps": 42420, "loss": 0.1398, "lr": 3.6056105610561056e-05, "epoch": 1.4427157001414428, "percentage": 7.21, "elapsed_time": "0:10:57", "remaining_time": "2:21:03", "throughput": 4665.06, "total_tokens": 3069536} {"current_steps": 3065, "total_steps": 42420, "loss": 0.2525, "lr": 3.6115040075436116e-05, "epoch": 1.4450730787364452, "percentage": 7.23, "elapsed_time": "0:10:59", "remaining_time": "2:21:02", "throughput": 4665.1, "total_tokens": 3074560} {"current_steps": 3070, "total_steps": 42420, "loss": 0.2915, "lr": 3.6173974540311175e-05, "epoch": 1.4474304573314474, "percentage": 7.24, "elapsed_time": "0:10:59", "remaining_time": "2:20:58", "throughput": 4665.16, "total_tokens": 3078688} {"current_steps": 3075, "total_steps": 42420, "loss": 0.1606, "lr": 3.6232909005186235e-05, "epoch": 1.4497878359264498, "percentage": 7.25, "elapsed_time": "0:11:00", "remaining_time": "2:20:56", "throughput": 4665.36, "total_tokens": 3083552} {"current_steps": 3080, "total_steps": 42420, "loss": 0.3675, "lr": 3.6291843470061295e-05, "epoch": 1.4521452145214522, "percentage": 7.26, "elapsed_time": "0:11:01", "remaining_time": "2:20:55", "throughput": 4665.23, "total_tokens": 3088352} {"current_steps": 3085, "total_steps": 42420, "loss": 0.3275, "lr": 3.6350777934936354e-05, "epoch": 1.4545025931164546, "percentage": 7.27, "elapsed_time": "0:11:02", "remaining_time": "2:20:52", "throughput": 4665.55, "total_tokens": 3092960} {"current_steps": 3090, "total_steps": 42420, "loss": 0.1466, "lr": 3.6409712399811414e-05, "epoch": 1.4568599717114568, "percentage": 7.28, "elapsed_time": "0:11:04", "remaining_time": "2:20:52", "throughput": 4666.01, "total_tokens": 3098592} {"current_steps": 3095, "total_steps": 42420, "loss": 0.0944, "lr": 3.646864686468647e-05, "epoch": 1.4592173503064592, "percentage": 7.3, "elapsed_time": "0:11:05", "remaining_time": "2:20:51", "throughput": 4666.2, "total_tokens": 3103840} {"current_steps": 3100, "total_steps": 42420, "loss": 0.0922, "lr": 3.6527581329561526e-05, "epoch": 1.4615747289014616, "percentage": 7.31, "elapsed_time": "0:11:06", "remaining_time": "2:20:51", "throughput": 4666.6, "total_tokens": 3109312} {"current_steps": 3105, "total_steps": 42420, "loss": 0.2874, "lr": 3.6586515794436586e-05, "epoch": 1.463932107496464, "percentage": 7.32, "elapsed_time": "0:11:07", "remaining_time": "2:20:49", "throughput": 4666.58, "total_tokens": 3113984} {"current_steps": 3110, "total_steps": 42420, "loss": 0.1784, "lr": 3.6645450259311646e-05, "epoch": 1.4662894860914664, "percentage": 7.33, "elapsed_time": "0:11:08", "remaining_time": "2:20:46", "throughput": 4666.46, "total_tokens": 3118400} {"current_steps": 3115, "total_steps": 42420, "loss": 0.194, "lr": 3.6704384724186705e-05, "epoch": 1.4686468646864688, "percentage": 7.34, "elapsed_time": "0:11:09", "remaining_time": "2:20:45", "throughput": 4666.61, "total_tokens": 3123488} {"current_steps": 3120, "total_steps": 42420, "loss": 0.4643, "lr": 3.6763319189061765e-05, "epoch": 1.471004243281471, "percentage": 7.36, "elapsed_time": "0:11:10", "remaining_time": "2:20:43", "throughput": 4666.62, "total_tokens": 3128256} {"current_steps": 3125, "total_steps": 42420, "loss": 0.3057, "lr": 3.6822253653936824e-05, "epoch": 1.4733616218764733, "percentage": 7.37, "elapsed_time": "0:11:11", "remaining_time": "2:20:41", "throughput": 4666.92, "total_tokens": 3133088} {"current_steps": 3130, "total_steps": 42420, "loss": 0.1826, "lr": 3.6881188118811884e-05, "epoch": 1.4757190004714758, "percentage": 7.38, "elapsed_time": "0:11:12", "remaining_time": "2:20:40", "throughput": 4667.19, "total_tokens": 3138336} {"current_steps": 3135, "total_steps": 42420, "loss": 0.1673, "lr": 3.6940122583686944e-05, "epoch": 1.4780763790664782, "percentage": 7.39, "elapsed_time": "0:11:13", "remaining_time": "2:20:38", "throughput": 4667.11, "total_tokens": 3142912} {"current_steps": 3140, "total_steps": 42420, "loss": 0.0362, "lr": 3.6999057048562003e-05, "epoch": 1.4804337576614803, "percentage": 7.4, "elapsed_time": "0:11:14", "remaining_time": "2:20:38", "throughput": 4667.23, "total_tokens": 3148256} {"current_steps": 3145, "total_steps": 42420, "loss": 0.1538, "lr": 3.7057991513437056e-05, "epoch": 1.4827911362564827, "percentage": 7.41, "elapsed_time": "0:11:15", "remaining_time": "2:20:36", "throughput": 4666.94, "total_tokens": 3152800} {"current_steps": 3150, "total_steps": 42420, "loss": 0.1385, "lr": 3.7116925978312116e-05, "epoch": 1.4851485148514851, "percentage": 7.43, "elapsed_time": "0:11:16", "remaining_time": "2:20:36", "throughput": 4667.48, "total_tokens": 3158432} {"current_steps": 3155, "total_steps": 42420, "loss": 0.1162, "lr": 3.7175860443187176e-05, "epoch": 1.4875058934464875, "percentage": 7.44, "elapsed_time": "0:11:17", "remaining_time": "2:20:32", "throughput": 4666.95, "total_tokens": 3162176} {"current_steps": 3160, "total_steps": 42420, "loss": 0.1272, "lr": 3.7234794908062235e-05, "epoch": 1.48986327204149, "percentage": 7.45, "elapsed_time": "0:11:18", "remaining_time": "2:20:31", "throughput": 4666.82, "total_tokens": 3167008} {"current_steps": 3165, "total_steps": 42420, "loss": 0.1279, "lr": 3.7293729372937295e-05, "epoch": 1.4922206506364923, "percentage": 7.46, "elapsed_time": "0:11:19", "remaining_time": "2:20:32", "throughput": 4667.22, "total_tokens": 3173056} {"current_steps": 3170, "total_steps": 42420, "loss": 0.3029, "lr": 3.7352663837812354e-05, "epoch": 1.4945780292314945, "percentage": 7.47, "elapsed_time": "0:11:21", "remaining_time": "2:20:31", "throughput": 4667.57, "total_tokens": 3178624} {"current_steps": 3175, "total_steps": 42420, "loss": 0.1916, "lr": 3.7411598302687414e-05, "epoch": 1.496935407826497, "percentage": 7.48, "elapsed_time": "0:11:22", "remaining_time": "2:20:30", "throughput": 4667.73, "total_tokens": 3183744} {"current_steps": 3180, "total_steps": 42420, "loss": 0.1416, "lr": 3.7470532767562474e-05, "epoch": 1.4992927864214993, "percentage": 7.5, "elapsed_time": "0:11:23", "remaining_time": "2:20:32", "throughput": 4668.3, "total_tokens": 3190240} {"current_steps": 3185, "total_steps": 42420, "loss": 0.1629, "lr": 3.752946723243753e-05, "epoch": 1.5016501650165015, "percentage": 7.51, "elapsed_time": "0:11:24", "remaining_time": "2:20:34", "throughput": 4668.87, "total_tokens": 3196864} {"current_steps": 3190, "total_steps": 42420, "loss": 0.2149, "lr": 3.758840169731259e-05, "epoch": 1.504007543611504, "percentage": 7.52, "elapsed_time": "0:11:25", "remaining_time": "2:20:33", "throughput": 4669.19, "total_tokens": 3202144} {"current_steps": 3195, "total_steps": 42420, "loss": 0.7549, "lr": 3.764733616218765e-05, "epoch": 1.5063649222065063, "percentage": 7.53, "elapsed_time": "0:11:26", "remaining_time": "2:20:33", "throughput": 4669.35, "total_tokens": 3207680} {"current_steps": 3200, "total_steps": 42420, "loss": 0.1651, "lr": 3.7706270627062705e-05, "epoch": 1.5087223008015087, "percentage": 7.54, "elapsed_time": "0:11:28", "remaining_time": "2:20:32", "throughput": 4669.48, "total_tokens": 3212864} {"current_steps": 3205, "total_steps": 42420, "loss": 0.2348, "lr": 3.7765205091937765e-05, "epoch": 1.511079679396511, "percentage": 7.56, "elapsed_time": "0:11:29", "remaining_time": "2:20:33", "throughput": 4669.7, "total_tokens": 3218528} {"current_steps": 3210, "total_steps": 42420, "loss": 0.1801, "lr": 3.7824139556812825e-05, "epoch": 1.5134370579915135, "percentage": 7.57, "elapsed_time": "0:11:30", "remaining_time": "2:20:35", "throughput": 4670.15, "total_tokens": 3225152} {"current_steps": 3215, "total_steps": 42420, "loss": 0.1434, "lr": 3.7883074021687884e-05, "epoch": 1.515794436586516, "percentage": 7.58, "elapsed_time": "0:11:31", "remaining_time": "2:20:34", "throughput": 4670.5, "total_tokens": 3230272} {"current_steps": 3220, "total_steps": 42420, "loss": 0.2873, "lr": 3.7942008486562944e-05, "epoch": 1.5181518151815183, "percentage": 7.59, "elapsed_time": "0:11:32", "remaining_time": "2:20:33", "throughput": 4670.9, "total_tokens": 3235584} {"current_steps": 3225, "total_steps": 42420, "loss": 0.1418, "lr": 3.8000942951438004e-05, "epoch": 1.5205091937765205, "percentage": 7.6, "elapsed_time": "0:11:33", "remaining_time": "2:20:30", "throughput": 4670.87, "total_tokens": 3240064} {"current_steps": 3230, "total_steps": 42420, "loss": 0.1365, "lr": 3.805987741631306e-05, "epoch": 1.522866572371523, "percentage": 7.61, "elapsed_time": "0:11:34", "remaining_time": "2:20:28", "throughput": 4671.07, "total_tokens": 3244704} {"current_steps": 3235, "total_steps": 42420, "loss": 0.1875, "lr": 3.811881188118812e-05, "epoch": 1.525223950966525, "percentage": 7.63, "elapsed_time": "0:11:35", "remaining_time": "2:20:26", "throughput": 4670.55, "total_tokens": 3248992} {"current_steps": 3240, "total_steps": 42420, "loss": 0.3738, "lr": 3.817774634606318e-05, "epoch": 1.5275813295615275, "percentage": 7.64, "elapsed_time": "0:11:36", "remaining_time": "2:20:25", "throughput": 4670.84, "total_tokens": 3254368} {"current_steps": 3245, "total_steps": 42420, "loss": 0.077, "lr": 3.823668081093824e-05, "epoch": 1.5299387081565299, "percentage": 7.65, "elapsed_time": "0:11:37", "remaining_time": "2:20:24", "throughput": 4671.03, "total_tokens": 3259488} {"current_steps": 3250, "total_steps": 42420, "loss": 0.2672, "lr": 3.8295615275813295e-05, "epoch": 1.5322960867515323, "percentage": 7.66, "elapsed_time": "0:11:38", "remaining_time": "2:20:22", "throughput": 4671.16, "total_tokens": 3264224} {"current_steps": 3255, "total_steps": 42420, "loss": 0.3221, "lr": 3.8354549740688355e-05, "epoch": 1.5346534653465347, "percentage": 7.67, "elapsed_time": "0:11:39", "remaining_time": "2:20:22", "throughput": 4671.59, "total_tokens": 3269888} {"current_steps": 3260, "total_steps": 42420, "loss": 0.2261, "lr": 3.8413484205563414e-05, "epoch": 1.537010843941537, "percentage": 7.69, "elapsed_time": "0:11:41", "remaining_time": "2:20:21", "throughput": 4671.56, "total_tokens": 3275040} {"current_steps": 3265, "total_steps": 42420, "loss": 0.0279, "lr": 3.8472418670438474e-05, "epoch": 1.5393682225365395, "percentage": 7.7, "elapsed_time": "0:11:42", "remaining_time": "2:20:19", "throughput": 4671.66, "total_tokens": 3279712} {"current_steps": 3270, "total_steps": 42420, "loss": 0.3793, "lr": 3.8531353135313534e-05, "epoch": 1.541725601131542, "percentage": 7.71, "elapsed_time": "0:11:42", "remaining_time": "2:20:16", "throughput": 4671.26, "total_tokens": 3283776} {"current_steps": 3275, "total_steps": 42420, "loss": 0.2034, "lr": 3.859028760018859e-05, "epoch": 1.544082979726544, "percentage": 7.72, "elapsed_time": "0:11:44", "remaining_time": "2:20:14", "throughput": 4671.62, "total_tokens": 3288928} {"current_steps": 3280, "total_steps": 42420, "loss": 0.1766, "lr": 3.864922206506365e-05, "epoch": 1.5464403583215465, "percentage": 7.73, "elapsed_time": "0:11:44", "remaining_time": "2:20:12", "throughput": 4671.88, "total_tokens": 3293504} {"current_steps": 3285, "total_steps": 42420, "loss": 0.1817, "lr": 3.870815652993871e-05, "epoch": 1.5487977369165487, "percentage": 7.74, "elapsed_time": "0:11:45", "remaining_time": "2:20:09", "throughput": 4671.86, "total_tokens": 3297792} {"current_steps": 3290, "total_steps": 42420, "loss": 0.1087, "lr": 3.876709099481377e-05, "epoch": 1.551155115511551, "percentage": 7.76, "elapsed_time": "0:11:47", "remaining_time": "2:20:12", "throughput": 4672.22, "total_tokens": 3304736} {"current_steps": 3295, "total_steps": 42420, "loss": 0.3212, "lr": 3.882602545968883e-05, "epoch": 1.5535124941065535, "percentage": 7.77, "elapsed_time": "0:11:48", "remaining_time": "2:20:11", "throughput": 4672.36, "total_tokens": 3310048} {"current_steps": 3300, "total_steps": 42420, "loss": 0.1803, "lr": 3.8884959924563885e-05, "epoch": 1.5558698727015559, "percentage": 7.78, "elapsed_time": "0:11:49", "remaining_time": "2:20:11", "throughput": 4672.61, "total_tokens": 3315328} {"current_steps": 3305, "total_steps": 42420, "loss": 0.3587, "lr": 3.8943894389438944e-05, "epoch": 1.5582272512965583, "percentage": 7.79, "elapsed_time": "0:11:50", "remaining_time": "2:20:10", "throughput": 4672.58, "total_tokens": 3320416} {"current_steps": 3310, "total_steps": 42420, "loss": 0.1102, "lr": 3.9002828854314004e-05, "epoch": 1.5605846298915607, "percentage": 7.8, "elapsed_time": "0:11:51", "remaining_time": "2:20:07", "throughput": 4672.74, "total_tokens": 3325056} {"current_steps": 3315, "total_steps": 42420, "loss": 0.1581, "lr": 3.9061763319189063e-05, "epoch": 1.562942008486563, "percentage": 7.81, "elapsed_time": "0:11:52", "remaining_time": "2:20:03", "throughput": 4672.51, "total_tokens": 3328672} {"current_steps": 3320, "total_steps": 42420, "loss": 0.1692, "lr": 3.912069778406412e-05, "epoch": 1.5652993870815655, "percentage": 7.83, "elapsed_time": "0:11:53", "remaining_time": "2:20:01", "throughput": 4672.77, "total_tokens": 3333376} {"current_steps": 3325, "total_steps": 42420, "loss": 0.2747, "lr": 3.917963224893918e-05, "epoch": 1.5676567656765676, "percentage": 7.84, "elapsed_time": "0:11:54", "remaining_time": "2:20:01", "throughput": 4673.28, "total_tokens": 3339424} {"current_steps": 3330, "total_steps": 42420, "loss": 0.206, "lr": 3.923856671381424e-05, "epoch": 1.57001414427157, "percentage": 7.85, "elapsed_time": "0:11:55", "remaining_time": "2:19:59", "throughput": 4673.37, "total_tokens": 3343968} {"current_steps": 3335, "total_steps": 42420, "loss": 0.1555, "lr": 3.92975011786893e-05, "epoch": 1.5723715228665722, "percentage": 7.86, "elapsed_time": "0:11:56", "remaining_time": "2:19:59", "throughput": 4673.82, "total_tokens": 3349856} {"current_steps": 3340, "total_steps": 42420, "loss": 0.1255, "lr": 3.935643564356436e-05, "epoch": 1.5747289014615746, "percentage": 7.87, "elapsed_time": "0:11:57", "remaining_time": "2:19:59", "throughput": 4674.1, "total_tokens": 3355232} {"current_steps": 3345, "total_steps": 42420, "loss": 0.0713, "lr": 3.941537010843942e-05, "epoch": 1.577086280056577, "percentage": 7.89, "elapsed_time": "0:11:58", "remaining_time": "2:19:57", "throughput": 4674.23, "total_tokens": 3360288} {"current_steps": 3350, "total_steps": 42420, "loss": 0.4066, "lr": 3.9474304573314474e-05, "epoch": 1.5794436586515794, "percentage": 7.9, "elapsed_time": "0:11:59", "remaining_time": "2:19:55", "throughput": 4674.41, "total_tokens": 3364768} {"current_steps": 3355, "total_steps": 42420, "loss": 0.2224, "lr": 3.9533239038189534e-05, "epoch": 1.5818010372465818, "percentage": 7.91, "elapsed_time": "0:12:00", "remaining_time": "2:19:53", "throughput": 4674.47, "total_tokens": 3369632} {"current_steps": 3360, "total_steps": 42420, "loss": 0.1434, "lr": 3.959217350306459e-05, "epoch": 1.5841584158415842, "percentage": 7.92, "elapsed_time": "0:12:02", "remaining_time": "2:19:53", "throughput": 4674.85, "total_tokens": 3375264} {"current_steps": 3365, "total_steps": 42420, "loss": 0.0848, "lr": 3.965110796793965e-05, "epoch": 1.5865157944365866, "percentage": 7.93, "elapsed_time": "0:12:02", "remaining_time": "2:19:51", "throughput": 4675.17, "total_tokens": 3380064} {"current_steps": 3370, "total_steps": 42420, "loss": 0.0757, "lr": 3.971004243281471e-05, "epoch": 1.588873173031589, "percentage": 7.94, "elapsed_time": "0:12:03", "remaining_time": "2:19:48", "throughput": 4675.36, "total_tokens": 3384768} {"current_steps": 3375, "total_steps": 42420, "loss": 0.1806, "lr": 3.976897689768977e-05, "epoch": 1.5912305516265912, "percentage": 7.96, "elapsed_time": "0:12:04", "remaining_time": "2:19:45", "throughput": 4675.16, "total_tokens": 3388832} {"current_steps": 3380, "total_steps": 42420, "loss": 0.1452, "lr": 3.982791136256483e-05, "epoch": 1.5935879302215936, "percentage": 7.97, "elapsed_time": "0:12:05", "remaining_time": "2:19:42", "throughput": 4674.96, "total_tokens": 3392896} {"current_steps": 3385, "total_steps": 42420, "loss": 0.2301, "lr": 3.988684582743989e-05, "epoch": 1.5959453088165958, "percentage": 7.98, "elapsed_time": "0:12:06", "remaining_time": "2:19:41", "throughput": 4675.27, "total_tokens": 3398144} {"current_steps": 3390, "total_steps": 42420, "loss": 0.1512, "lr": 3.994578029231495e-05, "epoch": 1.5983026874115982, "percentage": 7.99, "elapsed_time": "0:12:07", "remaining_time": "2:19:40", "throughput": 4675.35, "total_tokens": 3403232} {"current_steps": 3395, "total_steps": 42420, "loss": 0.2082, "lr": 4.000471475719001e-05, "epoch": 1.6006600660066006, "percentage": 8.0, "elapsed_time": "0:12:08", "remaining_time": "2:19:38", "throughput": 4675.55, "total_tokens": 3408128} {"current_steps": 3400, "total_steps": 42420, "loss": 0.1216, "lr": 4.0063649222065064e-05, "epoch": 1.603017444601603, "percentage": 8.02, "elapsed_time": "0:12:09", "remaining_time": "2:19:37", "throughput": 4675.43, "total_tokens": 3412864} {"current_steps": 3405, "total_steps": 42420, "loss": 0.2849, "lr": 4.012258368694012e-05, "epoch": 1.6053748231966054, "percentage": 8.03, "elapsed_time": "0:12:11", "remaining_time": "2:19:36", "throughput": 4675.7, "total_tokens": 3418016} {"current_steps": 3410, "total_steps": 42420, "loss": 0.1243, "lr": 4.018151815181518e-05, "epoch": 1.6077322017916078, "percentage": 8.04, "elapsed_time": "0:12:11", "remaining_time": "2:19:33", "throughput": 4675.84, "total_tokens": 3422688} {"current_steps": 3415, "total_steps": 42420, "loss": 0.1473, "lr": 4.024045261669024e-05, "epoch": 1.6100895803866102, "percentage": 8.05, "elapsed_time": "0:12:13", "remaining_time": "2:19:33", "throughput": 4676.19, "total_tokens": 3428192} {"current_steps": 3420, "total_steps": 42420, "loss": 0.2863, "lr": 4.02993870815653e-05, "epoch": 1.6124469589816126, "percentage": 8.06, "elapsed_time": "0:12:14", "remaining_time": "2:19:31", "throughput": 4676.35, "total_tokens": 3432960} {"current_steps": 3425, "total_steps": 42420, "loss": 0.1922, "lr": 4.035832154644036e-05, "epoch": 1.6148043375766148, "percentage": 8.07, "elapsed_time": "0:12:15", "remaining_time": "2:19:29", "throughput": 4676.31, "total_tokens": 3437664} {"current_steps": 3430, "total_steps": 42420, "loss": 0.336, "lr": 4.041725601131542e-05, "epoch": 1.6171617161716172, "percentage": 8.09, "elapsed_time": "0:12:16", "remaining_time": "2:19:28", "throughput": 4676.61, "total_tokens": 3443008} {"current_steps": 3435, "total_steps": 42420, "loss": 0.107, "lr": 4.047619047619048e-05, "epoch": 1.6195190947666194, "percentage": 8.1, "elapsed_time": "0:12:17", "remaining_time": "2:19:26", "throughput": 4676.74, "total_tokens": 3447648} {"current_steps": 3440, "total_steps": 42420, "loss": 0.2047, "lr": 4.053512494106554e-05, "epoch": 1.6218764733616218, "percentage": 8.11, "elapsed_time": "0:12:18", "remaining_time": "2:19:23", "throughput": 4676.92, "total_tokens": 3452032} {"current_steps": 3445, "total_steps": 42420, "loss": 0.1509, "lr": 4.05940594059406e-05, "epoch": 1.6242338519566242, "percentage": 8.12, "elapsed_time": "0:12:19", "remaining_time": "2:19:22", "throughput": 4677.25, "total_tokens": 3457408} {"current_steps": 3450, "total_steps": 42420, "loss": 0.1994, "lr": 4.065299387081565e-05, "epoch": 1.6265912305516266, "percentage": 8.13, "elapsed_time": "0:12:20", "remaining_time": "2:19:21", "throughput": 4677.43, "total_tokens": 3462400} {"current_steps": 3455, "total_steps": 42420, "loss": 0.3536, "lr": 4.071192833569071e-05, "epoch": 1.628948609146629, "percentage": 8.14, "elapsed_time": "0:12:21", "remaining_time": "2:19:18", "throughput": 4677.67, "total_tokens": 3466816} {"current_steps": 3460, "total_steps": 42420, "loss": 0.1817, "lr": 4.077086280056577e-05, "epoch": 1.6313059877416314, "percentage": 8.16, "elapsed_time": "0:12:22", "remaining_time": "2:19:16", "throughput": 4677.94, "total_tokens": 3471744} {"current_steps": 3465, "total_steps": 42420, "loss": 0.1122, "lr": 4.082979726544083e-05, "epoch": 1.6336633663366338, "percentage": 8.17, "elapsed_time": "0:12:23", "remaining_time": "2:19:14", "throughput": 4678.15, "total_tokens": 3476608} {"current_steps": 3470, "total_steps": 42420, "loss": 0.1543, "lr": 4.088873173031589e-05, "epoch": 1.6360207449316362, "percentage": 8.18, "elapsed_time": "0:12:24", "remaining_time": "2:19:11", "throughput": 4678.01, "total_tokens": 3480544} {"current_steps": 3475, "total_steps": 42420, "loss": 0.2408, "lr": 4.094766619519095e-05, "epoch": 1.6383781235266384, "percentage": 8.19, "elapsed_time": "0:12:25", "remaining_time": "2:19:13", "throughput": 4678.21, "total_tokens": 3486944} {"current_steps": 3480, "total_steps": 42420, "loss": 0.3887, "lr": 4.100660066006601e-05, "epoch": 1.6407355021216408, "percentage": 8.2, "elapsed_time": "0:12:26", "remaining_time": "2:19:12", "throughput": 4678.62, "total_tokens": 3492256} {"current_steps": 3485, "total_steps": 42420, "loss": 0.0909, "lr": 4.106553512494107e-05, "epoch": 1.643092880716643, "percentage": 8.22, "elapsed_time": "0:12:27", "remaining_time": "2:19:14", "throughput": 4678.96, "total_tokens": 3499072} {"current_steps": 3490, "total_steps": 42420, "loss": 0.2094, "lr": 4.112446958981613e-05, "epoch": 1.6454502593116453, "percentage": 8.23, "elapsed_time": "0:12:28", "remaining_time": "2:19:11", "throughput": 4678.65, "total_tokens": 3502912} {"current_steps": 3495, "total_steps": 42420, "loss": 0.2561, "lr": 4.118340405469119e-05, "epoch": 1.6478076379066477, "percentage": 8.24, "elapsed_time": "0:12:29", "remaining_time": "2:19:10", "throughput": 4678.7, "total_tokens": 3507808} {"current_steps": 3500, "total_steps": 42420, "loss": 0.2033, "lr": 4.124233851956624e-05, "epoch": 1.6501650165016502, "percentage": 8.25, "elapsed_time": "0:12:30", "remaining_time": "2:19:08", "throughput": 4679.02, "total_tokens": 3512896} {"current_steps": 3505, "total_steps": 42420, "loss": 0.214, "lr": 4.13012729844413e-05, "epoch": 1.6525223950966526, "percentage": 8.26, "elapsed_time": "0:12:31", "remaining_time": "2:19:06", "throughput": 4679.13, "total_tokens": 3517632} {"current_steps": 3510, "total_steps": 42420, "loss": 0.1487, "lr": 4.136020744931636e-05, "epoch": 1.654879773691655, "percentage": 8.27, "elapsed_time": "0:12:32", "remaining_time": "2:19:04", "throughput": 4679.27, "total_tokens": 3522464} {"current_steps": 3515, "total_steps": 42420, "loss": 0.1694, "lr": 4.141914191419142e-05, "epoch": 1.6572371522866574, "percentage": 8.29, "elapsed_time": "0:12:33", "remaining_time": "2:19:02", "throughput": 4679.49, "total_tokens": 3527008} {"current_steps": 3520, "total_steps": 42420, "loss": 0.2047, "lr": 4.147807637906648e-05, "epoch": 1.6595945308816598, "percentage": 8.3, "elapsed_time": "0:12:34", "remaining_time": "2:18:59", "throughput": 4679.69, "total_tokens": 3531584} {"current_steps": 3525, "total_steps": 42420, "loss": 0.1161, "lr": 4.1537010843941534e-05, "epoch": 1.661951909476662, "percentage": 8.31, "elapsed_time": "0:12:35", "remaining_time": "2:19:01", "throughput": 4679.97, "total_tokens": 3537920} {"current_steps": 3530, "total_steps": 42420, "loss": 0.1707, "lr": 4.15959453088166e-05, "epoch": 1.6643092880716643, "percentage": 8.32, "elapsed_time": "0:12:37", "remaining_time": "2:19:00", "throughput": 4680.17, "total_tokens": 3543360} {"current_steps": 3535, "total_steps": 42420, "loss": 0.2729, "lr": 4.165487977369166e-05, "epoch": 1.6666666666666665, "percentage": 8.33, "elapsed_time": "0:12:38", "remaining_time": "2:18:59", "throughput": 4680.19, "total_tokens": 3548160} {"current_steps": 3540, "total_steps": 42420, "loss": 0.4044, "lr": 4.171381423856672e-05, "epoch": 1.669024045261669, "percentage": 8.35, "elapsed_time": "0:12:39", "remaining_time": "2:18:56", "throughput": 4680.2, "total_tokens": 3552288} {"current_steps": 3545, "total_steps": 42420, "loss": 0.1268, "lr": 4.177274870344178e-05, "epoch": 1.6713814238566713, "percentage": 8.36, "elapsed_time": "0:12:39", "remaining_time": "2:18:53", "throughput": 4680.21, "total_tokens": 3556704} {"current_steps": 3550, "total_steps": 42420, "loss": 0.2321, "lr": 4.183168316831683e-05, "epoch": 1.6737388024516737, "percentage": 8.37, "elapsed_time": "0:12:41", "remaining_time": "2:18:52", "throughput": 4680.57, "total_tokens": 3561952} {"current_steps": 3555, "total_steps": 42420, "loss": 0.2324, "lr": 4.189061763319189e-05, "epoch": 1.6760961810466761, "percentage": 8.38, "elapsed_time": "0:12:41", "remaining_time": "2:18:50", "throughput": 4680.5, "total_tokens": 3566304} {"current_steps": 3560, "total_steps": 42420, "loss": 0.1032, "lr": 4.194955209806695e-05, "epoch": 1.6784535596416785, "percentage": 8.39, "elapsed_time": "0:12:43", "remaining_time": "2:18:49", "throughput": 4680.89, "total_tokens": 3571648} {"current_steps": 3565, "total_steps": 42420, "loss": 0.1453, "lr": 4.200848656294201e-05, "epoch": 1.680810938236681, "percentage": 8.4, "elapsed_time": "0:12:44", "remaining_time": "2:18:49", "throughput": 4681.23, "total_tokens": 3577728} {"current_steps": 3570, "total_steps": 42420, "loss": 0.2624, "lr": 4.206742102781707e-05, "epoch": 1.6831683168316833, "percentage": 8.42, "elapsed_time": "0:12:45", "remaining_time": "2:18:47", "throughput": 4681.52, "total_tokens": 3582400} {"current_steps": 3575, "total_steps": 42420, "loss": 0.2139, "lr": 4.2126355492692124e-05, "epoch": 1.6855256954266855, "percentage": 8.43, "elapsed_time": "0:12:46", "remaining_time": "2:18:46", "throughput": 4681.88, "total_tokens": 3587968} {"current_steps": 3580, "total_steps": 42420, "loss": 0.1524, "lr": 4.218528995756719e-05, "epoch": 1.687883074021688, "percentage": 8.44, "elapsed_time": "0:12:47", "remaining_time": "2:18:46", "throughput": 4682.18, "total_tokens": 3593408} {"current_steps": 3585, "total_steps": 42420, "loss": 0.377, "lr": 4.224422442244225e-05, "epoch": 1.69024045261669, "percentage": 8.45, "elapsed_time": "0:12:48", "remaining_time": "2:18:45", "throughput": 4682.41, "total_tokens": 3598592} {"current_steps": 3590, "total_steps": 42420, "loss": 0.205, "lr": 4.230315888731731e-05, "epoch": 1.6925978312116925, "percentage": 8.46, "elapsed_time": "0:12:49", "remaining_time": "2:18:44", "throughput": 4682.73, "total_tokens": 3603872} {"current_steps": 3595, "total_steps": 42420, "loss": 0.6257, "lr": 4.236209335219237e-05, "epoch": 1.694955209806695, "percentage": 8.47, "elapsed_time": "0:12:50", "remaining_time": "2:18:41", "throughput": 4682.93, "total_tokens": 3608448} {"current_steps": 3600, "total_steps": 42420, "loss": 0.1876, "lr": 4.242102781706742e-05, "epoch": 1.6973125884016973, "percentage": 8.49, "elapsed_time": "0:12:51", "remaining_time": "2:18:39", "throughput": 4682.92, "total_tokens": 3612896} {"current_steps": 3605, "total_steps": 42420, "loss": 0.1506, "lr": 4.247996228194248e-05, "epoch": 1.6996699669966997, "percentage": 8.5, "elapsed_time": "0:12:52", "remaining_time": "2:18:38", "throughput": 4683.19, "total_tokens": 3618336} {"current_steps": 3610, "total_steps": 42420, "loss": 0.1067, "lr": 4.253889674681754e-05, "epoch": 1.702027345591702, "percentage": 8.51, "elapsed_time": "0:12:53", "remaining_time": "2:18:36", "throughput": 4683.18, "total_tokens": 3622656} {"current_steps": 3615, "total_steps": 42420, "loss": 0.1703, "lr": 4.25978312116926e-05, "epoch": 1.7043847241867045, "percentage": 8.52, "elapsed_time": "0:12:54", "remaining_time": "2:18:37", "throughput": 4683.63, "total_tokens": 3628896} {"current_steps": 3620, "total_steps": 42420, "loss": 0.1686, "lr": 4.265676567656766e-05, "epoch": 1.706742102781707, "percentage": 8.53, "elapsed_time": "0:12:55", "remaining_time": "2:18:35", "throughput": 4683.96, "total_tokens": 3633952} {"current_steps": 3625, "total_steps": 42420, "loss": 0.1043, "lr": 4.271570014144271e-05, "epoch": 1.709099481376709, "percentage": 8.55, "elapsed_time": "0:12:56", "remaining_time": "2:18:33", "throughput": 4684.07, "total_tokens": 3638752} {"current_steps": 3630, "total_steps": 42420, "loss": 0.205, "lr": 4.277463460631777e-05, "epoch": 1.7114568599717115, "percentage": 8.56, "elapsed_time": "0:12:57", "remaining_time": "2:18:30", "throughput": 4684.01, "total_tokens": 3642912} {"current_steps": 3635, "total_steps": 42420, "loss": 0.1035, "lr": 4.283356907119284e-05, "epoch": 1.7138142385667137, "percentage": 8.57, "elapsed_time": "0:12:58", "remaining_time": "2:18:30", "throughput": 4684.29, "total_tokens": 3648352} {"current_steps": 3640, "total_steps": 42420, "loss": 0.0915, "lr": 4.28925035360679e-05, "epoch": 1.716171617161716, "percentage": 8.58, "elapsed_time": "0:12:59", "remaining_time": "2:18:28", "throughput": 4684.24, "total_tokens": 3652928} {"current_steps": 3645, "total_steps": 42420, "loss": 0.2806, "lr": 4.295143800094296e-05, "epoch": 1.7185289957567185, "percentage": 8.59, "elapsed_time": "0:13:00", "remaining_time": "2:18:26", "throughput": 4684.49, "total_tokens": 3658016} {"current_steps": 3650, "total_steps": 42420, "loss": 0.122, "lr": 4.301037246581801e-05, "epoch": 1.7208863743517209, "percentage": 8.6, "elapsed_time": "0:13:01", "remaining_time": "2:18:24", "throughput": 4684.59, "total_tokens": 3662400} {"current_steps": 3655, "total_steps": 42420, "loss": 0.2285, "lr": 4.306930693069307e-05, "epoch": 1.7232437529467233, "percentage": 8.62, "elapsed_time": "0:13:02", "remaining_time": "2:18:21", "throughput": 4684.24, "total_tokens": 3666400} {"current_steps": 3660, "total_steps": 42420, "loss": 0.1843, "lr": 4.312824139556813e-05, "epoch": 1.7256011315417257, "percentage": 8.63, "elapsed_time": "0:13:03", "remaining_time": "2:18:21", "throughput": 4684.6, "total_tokens": 3672128} {"current_steps": 3665, "total_steps": 42420, "loss": 0.262, "lr": 4.318717586044319e-05, "epoch": 1.727958510136728, "percentage": 8.64, "elapsed_time": "0:13:04", "remaining_time": "2:18:19", "throughput": 4684.47, "total_tokens": 3676576} {"current_steps": 3670, "total_steps": 42420, "loss": 0.1058, "lr": 4.324611032531825e-05, "epoch": 1.7303158887317305, "percentage": 8.65, "elapsed_time": "0:13:05", "remaining_time": "2:18:19", "throughput": 4684.8, "total_tokens": 3682240} {"current_steps": 3675, "total_steps": 42420, "loss": 0.3555, "lr": 4.33050447901933e-05, "epoch": 1.7326732673267327, "percentage": 8.66, "elapsed_time": "0:13:07", "remaining_time": "2:18:19", "throughput": 4684.99, "total_tokens": 3688128} {"current_steps": 3680, "total_steps": 42420, "loss": 0.1095, "lr": 4.336397925506836e-05, "epoch": 1.735030645921735, "percentage": 8.68, "elapsed_time": "0:13:08", "remaining_time": "2:18:19", "throughput": 4685.22, "total_tokens": 3693888} {"current_steps": 3685, "total_steps": 42420, "loss": 0.3682, "lr": 4.342291371994343e-05, "epoch": 1.7373880245167372, "percentage": 8.69, "elapsed_time": "0:13:09", "remaining_time": "2:18:17", "throughput": 4685.18, "total_tokens": 3698368} {"current_steps": 3690, "total_steps": 42420, "loss": 0.1722, "lr": 4.348184818481849e-05, "epoch": 1.7397454031117396, "percentage": 8.7, "elapsed_time": "0:13:10", "remaining_time": "2:18:15", "throughput": 4685.34, "total_tokens": 3703040} {"current_steps": 3695, "total_steps": 42420, "loss": 0.209, "lr": 4.354078264969355e-05, "epoch": 1.742102781706742, "percentage": 8.71, "elapsed_time": "0:13:11", "remaining_time": "2:18:13", "throughput": 4685.26, "total_tokens": 3707616} {"current_steps": 3700, "total_steps": 42420, "loss": 0.1809, "lr": 4.35997171145686e-05, "epoch": 1.7444601603017444, "percentage": 8.72, "elapsed_time": "0:13:12", "remaining_time": "2:18:12", "throughput": 4685.4, "total_tokens": 3712832} {"current_steps": 3705, "total_steps": 42420, "loss": 0.1949, "lr": 4.365865157944366e-05, "epoch": 1.7468175388967468, "percentage": 8.73, "elapsed_time": "0:13:13", "remaining_time": "2:18:10", "throughput": 4685.57, "total_tokens": 3717440} {"current_steps": 3710, "total_steps": 42420, "loss": 0.3181, "lr": 4.371758604431872e-05, "epoch": 1.7491749174917492, "percentage": 8.75, "elapsed_time": "0:13:14", "remaining_time": "2:18:09", "throughput": 4685.85, "total_tokens": 3722592} {"current_steps": 3715, "total_steps": 42420, "loss": 0.1315, "lr": 4.377652050919378e-05, "epoch": 1.7515322960867516, "percentage": 8.76, "elapsed_time": "0:13:15", "remaining_time": "2:18:07", "throughput": 4686.02, "total_tokens": 3727520} {"current_steps": 3720, "total_steps": 42420, "loss": 0.1038, "lr": 4.383545497406884e-05, "epoch": 1.753889674681754, "percentage": 8.77, "elapsed_time": "0:13:16", "remaining_time": "2:18:05", "throughput": 4685.99, "total_tokens": 3732096} {"current_steps": 3725, "total_steps": 42420, "loss": 0.2275, "lr": 4.389438943894389e-05, "epoch": 1.7562470532767562, "percentage": 8.78, "elapsed_time": "0:13:17", "remaining_time": "2:18:03", "throughput": 4685.93, "total_tokens": 3736480} {"current_steps": 3730, "total_steps": 42420, "loss": 0.197, "lr": 4.395332390381895e-05, "epoch": 1.7586044318717586, "percentage": 8.79, "elapsed_time": "0:13:18", "remaining_time": "2:18:01", "throughput": 4686.08, "total_tokens": 3741152} {"current_steps": 3735, "total_steps": 42420, "loss": 0.1707, "lr": 4.401225836869401e-05, "epoch": 1.7609618104667608, "percentage": 8.8, "elapsed_time": "0:13:19", "remaining_time": "2:17:59", "throughput": 4686.21, "total_tokens": 3746080} {"current_steps": 3740, "total_steps": 42420, "loss": 0.0941, "lr": 4.407119283356908e-05, "epoch": 1.7633191890617632, "percentage": 8.82, "elapsed_time": "0:13:20", "remaining_time": "2:17:59", "throughput": 4686.5, "total_tokens": 3751616} {"current_steps": 3745, "total_steps": 42420, "loss": 0.0605, "lr": 4.413012729844414e-05, "epoch": 1.7656765676567656, "percentage": 8.83, "elapsed_time": "0:13:21", "remaining_time": "2:17:58", "throughput": 4686.67, "total_tokens": 3757024} {"current_steps": 3750, "total_steps": 42420, "loss": 0.0821, "lr": 4.418906176331919e-05, "epoch": 1.768033946251768, "percentage": 8.84, "elapsed_time": "0:13:22", "remaining_time": "2:17:55", "throughput": 4686.78, "total_tokens": 3761344} {"current_steps": 3755, "total_steps": 42420, "loss": 0.1537, "lr": 4.424799622819425e-05, "epoch": 1.7703913248467704, "percentage": 8.85, "elapsed_time": "0:13:23", "remaining_time": "2:17:54", "throughput": 4687.01, "total_tokens": 3766336} {"current_steps": 3760, "total_steps": 42420, "loss": 0.2289, "lr": 4.430693069306931e-05, "epoch": 1.7727487034417728, "percentage": 8.86, "elapsed_time": "0:13:24", "remaining_time": "2:17:51", "throughput": 4687.08, "total_tokens": 3770560} {"current_steps": 3765, "total_steps": 42420, "loss": 0.436, "lr": 4.436586515794437e-05, "epoch": 1.7751060820367752, "percentage": 8.88, "elapsed_time": "0:13:25", "remaining_time": "2:17:48", "throughput": 4687.04, "total_tokens": 3774592} {"current_steps": 3770, "total_steps": 42420, "loss": 0.27, "lr": 4.442479962281943e-05, "epoch": 1.7774634606317776, "percentage": 8.89, "elapsed_time": "0:13:26", "remaining_time": "2:17:47", "throughput": 4687.37, "total_tokens": 3780064} {"current_steps": 3775, "total_steps": 42420, "loss": 0.2418, "lr": 4.448373408769448e-05, "epoch": 1.7798208392267798, "percentage": 8.9, "elapsed_time": "0:13:27", "remaining_time": "2:17:45", "throughput": 4687.37, "total_tokens": 3784480} {"current_steps": 3780, "total_steps": 42420, "loss": 0.1639, "lr": 4.454266855256954e-05, "epoch": 1.7821782178217822, "percentage": 8.91, "elapsed_time": "0:13:28", "remaining_time": "2:17:47", "throughput": 4687.86, "total_tokens": 3791424} {"current_steps": 3785, "total_steps": 42420, "loss": 0.1755, "lr": 4.46016030174446e-05, "epoch": 1.7845355964167844, "percentage": 8.92, "elapsed_time": "0:13:29", "remaining_time": "2:17:46", "throughput": 4688.12, "total_tokens": 3796736} {"current_steps": 3790, "total_steps": 42420, "loss": 0.3421, "lr": 4.466053748231967e-05, "epoch": 1.7868929750117868, "percentage": 8.93, "elapsed_time": "0:13:30", "remaining_time": "2:17:45", "throughput": 4688.48, "total_tokens": 3802016} {"current_steps": 3795, "total_steps": 42420, "loss": 0.0958, "lr": 4.471947194719473e-05, "epoch": 1.7892503536067892, "percentage": 8.95, "elapsed_time": "0:13:31", "remaining_time": "2:17:43", "throughput": 4688.58, "total_tokens": 3806848} {"current_steps": 3800, "total_steps": 42420, "loss": 0.1774, "lr": 4.477840641206978e-05, "epoch": 1.7916077322017916, "percentage": 8.96, "elapsed_time": "0:13:33", "remaining_time": "2:17:42", "throughput": 4688.82, "total_tokens": 3812160} {"current_steps": 3805, "total_steps": 42420, "loss": 0.1648, "lr": 4.483734087694484e-05, "epoch": 1.793965110796794, "percentage": 8.97, "elapsed_time": "0:13:34", "remaining_time": "2:17:41", "throughput": 4689.0, "total_tokens": 3817184} {"current_steps": 3810, "total_steps": 42420, "loss": 0.1884, "lr": 4.48962753418199e-05, "epoch": 1.7963224893917964, "percentage": 8.98, "elapsed_time": "0:13:35", "remaining_time": "2:17:41", "throughput": 4689.12, "total_tokens": 3822848} {"current_steps": 3815, "total_steps": 42420, "loss": 0.2533, "lr": 4.495520980669496e-05, "epoch": 1.7986798679867988, "percentage": 8.99, "elapsed_time": "0:13:36", "remaining_time": "2:17:39", "throughput": 4689.1, "total_tokens": 3827296} {"current_steps": 3820, "total_steps": 42420, "loss": 0.1609, "lr": 4.501414427157002e-05, "epoch": 1.8010372465818012, "percentage": 9.01, "elapsed_time": "0:13:37", "remaining_time": "2:17:36", "throughput": 4689.09, "total_tokens": 3831616} {"current_steps": 3825, "total_steps": 42420, "loss": 0.1471, "lr": 4.507307873644507e-05, "epoch": 1.8033946251768034, "percentage": 9.02, "elapsed_time": "0:13:38", "remaining_time": "2:17:35", "throughput": 4689.3, "total_tokens": 3836480} {"current_steps": 3830, "total_steps": 42420, "loss": 0.1063, "lr": 4.513201320132013e-05, "epoch": 1.8057520037718058, "percentage": 9.03, "elapsed_time": "0:13:39", "remaining_time": "2:17:34", "throughput": 4689.49, "total_tokens": 3841920} {"current_steps": 3835, "total_steps": 42420, "loss": 0.3338, "lr": 4.519094766619519e-05, "epoch": 1.808109382366808, "percentage": 9.04, "elapsed_time": "0:13:40", "remaining_time": "2:17:35", "throughput": 4689.84, "total_tokens": 3847968} {"current_steps": 3840, "total_steps": 42420, "loss": 0.1257, "lr": 4.524988213107026e-05, "epoch": 1.8104667609618104, "percentage": 9.05, "elapsed_time": "0:13:41", "remaining_time": "2:17:33", "throughput": 4690.02, "total_tokens": 3852736} {"current_steps": 3845, "total_steps": 42420, "loss": 0.2372, "lr": 4.530881659594532e-05, "epoch": 1.8128241395568128, "percentage": 9.06, "elapsed_time": "0:13:42", "remaining_time": "2:17:31", "throughput": 4690.26, "total_tokens": 3857824} {"current_steps": 3850, "total_steps": 42420, "loss": 0.142, "lr": 4.536775106082037e-05, "epoch": 1.8151815181518152, "percentage": 9.08, "elapsed_time": "0:13:43", "remaining_time": "2:17:33", "throughput": 4690.59, "total_tokens": 3864256} {"current_steps": 3855, "total_steps": 42420, "loss": 0.1228, "lr": 4.542668552569543e-05, "epoch": 1.8175388967468176, "percentage": 9.09, "elapsed_time": "0:13:44", "remaining_time": "2:17:33", "throughput": 4690.88, "total_tokens": 3869920} {"current_steps": 3860, "total_steps": 42420, "loss": 0.1373, "lr": 4.548561999057049e-05, "epoch": 1.81989627534182, "percentage": 9.1, "elapsed_time": "0:13:46", "remaining_time": "2:17:33", "throughput": 4691.21, "total_tokens": 3876128} {"current_steps": 3865, "total_steps": 42420, "loss": 0.1774, "lr": 4.554455445544555e-05, "epoch": 1.8222536539368224, "percentage": 9.11, "elapsed_time": "0:13:47", "remaining_time": "2:17:32", "throughput": 4691.28, "total_tokens": 3880896} {"current_steps": 3870, "total_steps": 42420, "loss": 0.2223, "lr": 4.560348892032061e-05, "epoch": 1.8246110325318248, "percentage": 9.12, "elapsed_time": "0:13:48", "remaining_time": "2:17:30", "throughput": 4691.29, "total_tokens": 3885504} {"current_steps": 3875, "total_steps": 42420, "loss": 0.1457, "lr": 4.566242338519566e-05, "epoch": 1.826968411126827, "percentage": 9.13, "elapsed_time": "0:13:49", "remaining_time": "2:17:28", "throughput": 4691.25, "total_tokens": 3890048} {"current_steps": 3880, "total_steps": 42420, "loss": 0.053, "lr": 4.572135785007072e-05, "epoch": 1.8293257897218294, "percentage": 9.15, "elapsed_time": "0:13:50", "remaining_time": "2:17:27", "throughput": 4691.56, "total_tokens": 3895296} {"current_steps": 3885, "total_steps": 42420, "loss": 0.1475, "lr": 4.578029231494578e-05, "epoch": 1.8316831683168315, "percentage": 9.16, "elapsed_time": "0:13:51", "remaining_time": "2:17:24", "throughput": 4691.7, "total_tokens": 3899808} {"current_steps": 3890, "total_steps": 42420, "loss": 0.2721, "lr": 4.583922677982084e-05, "epoch": 1.834040546911834, "percentage": 9.17, "elapsed_time": "0:13:52", "remaining_time": "2:17:25", "throughput": 4691.95, "total_tokens": 3905760} {"current_steps": 3895, "total_steps": 42420, "loss": 0.3463, "lr": 4.5898161244695906e-05, "epoch": 1.8363979255068363, "percentage": 9.18, "elapsed_time": "0:13:53", "remaining_time": "2:17:26", "throughput": 4692.22, "total_tokens": 3912160} {"current_steps": 3900, "total_steps": 42420, "loss": 0.1597, "lr": 4.595709570957096e-05, "epoch": 1.8387553041018387, "percentage": 9.19, "elapsed_time": "0:13:54", "remaining_time": "2:17:25", "throughput": 4692.41, "total_tokens": 3917120} {"current_steps": 3905, "total_steps": 42420, "loss": 0.072, "lr": 4.601603017444602e-05, "epoch": 1.8411126826968411, "percentage": 9.21, "elapsed_time": "0:13:55", "remaining_time": "2:17:24", "throughput": 4692.82, "total_tokens": 3922752} {"current_steps": 3910, "total_steps": 42420, "loss": 0.2213, "lr": 4.607496463932108e-05, "epoch": 1.8434700612918435, "percentage": 9.22, "elapsed_time": "0:13:56", "remaining_time": "2:17:23", "throughput": 4693.03, "total_tokens": 3927840} {"current_steps": 3915, "total_steps": 42420, "loss": 0.3436, "lr": 4.613389910419614e-05, "epoch": 1.845827439886846, "percentage": 9.23, "elapsed_time": "0:13:57", "remaining_time": "2:17:21", "throughput": 4693.21, "total_tokens": 3932864} {"current_steps": 3920, "total_steps": 42420, "loss": 0.327, "lr": 4.61928335690712e-05, "epoch": 1.8481848184818483, "percentage": 9.24, "elapsed_time": "0:13:59", "remaining_time": "2:17:20", "throughput": 4693.42, "total_tokens": 3938016} {"current_steps": 3925, "total_steps": 42420, "loss": 0.2611, "lr": 4.625176803394625e-05, "epoch": 1.8505421970768505, "percentage": 9.25, "elapsed_time": "0:14:00", "remaining_time": "2:17:22", "throughput": 4694.07, "total_tokens": 3944960} {"current_steps": 3930, "total_steps": 42420, "loss": 0.1393, "lr": 4.631070249882131e-05, "epoch": 1.852899575671853, "percentage": 9.26, "elapsed_time": "0:14:01", "remaining_time": "2:17:20", "throughput": 4694.19, "total_tokens": 3949760} {"current_steps": 3935, "total_steps": 42420, "loss": 0.0452, "lr": 4.636963696369637e-05, "epoch": 1.855256954266855, "percentage": 9.28, "elapsed_time": "0:14:02", "remaining_time": "2:17:19", "throughput": 4694.28, "total_tokens": 3954656} {"current_steps": 3940, "total_steps": 42420, "loss": 0.1239, "lr": 4.642857142857143e-05, "epoch": 1.8576143328618575, "percentage": 9.29, "elapsed_time": "0:14:03", "remaining_time": "2:17:16", "throughput": 4694.44, "total_tokens": 3959136} {"current_steps": 3945, "total_steps": 42420, "loss": 0.1074, "lr": 4.6487505893446496e-05, "epoch": 1.85997171145686, "percentage": 9.3, "elapsed_time": "0:14:04", "remaining_time": "2:17:14", "throughput": 4694.56, "total_tokens": 3963776} {"current_steps": 3950, "total_steps": 42420, "loss": 0.3, "lr": 4.654644035832155e-05, "epoch": 1.8623290900518623, "percentage": 9.31, "elapsed_time": "0:14:05", "remaining_time": "2:17:13", "throughput": 4694.75, "total_tokens": 3968896} {"current_steps": 3955, "total_steps": 42420, "loss": 0.0706, "lr": 4.660537482319661e-05, "epoch": 1.8646864686468647, "percentage": 9.32, "elapsed_time": "0:14:06", "remaining_time": "2:17:11", "throughput": 4694.87, "total_tokens": 3973824} {"current_steps": 3960, "total_steps": 42420, "loss": 0.0748, "lr": 4.666430928807167e-05, "epoch": 1.8670438472418671, "percentage": 9.34, "elapsed_time": "0:14:07", "remaining_time": "2:17:12", "throughput": 4695.1, "total_tokens": 3979776} {"current_steps": 3965, "total_steps": 42420, "loss": 0.2252, "lr": 4.672324375294673e-05, "epoch": 1.8694012258368695, "percentage": 9.35, "elapsed_time": "0:14:08", "remaining_time": "2:17:12", "throughput": 4695.35, "total_tokens": 3985344} {"current_steps": 3970, "total_steps": 42420, "loss": 0.1499, "lr": 4.678217821782179e-05, "epoch": 1.871758604431872, "percentage": 9.36, "elapsed_time": "0:14:09", "remaining_time": "2:17:10", "throughput": 4695.49, "total_tokens": 3990144} {"current_steps": 3975, "total_steps": 42420, "loss": 0.2843, "lr": 4.684111268269684e-05, "epoch": 1.874115983026874, "percentage": 9.37, "elapsed_time": "0:14:10", "remaining_time": "2:17:07", "throughput": 4695.48, "total_tokens": 3994464} {"current_steps": 3980, "total_steps": 42420, "loss": 0.0721, "lr": 4.69000471475719e-05, "epoch": 1.8764733616218765, "percentage": 9.38, "elapsed_time": "0:14:11", "remaining_time": "2:17:06", "throughput": 4695.71, "total_tokens": 3999808} {"current_steps": 3985, "total_steps": 42420, "loss": 0.1247, "lr": 4.695898161244696e-05, "epoch": 1.8788307402168787, "percentage": 9.39, "elapsed_time": "0:14:12", "remaining_time": "2:17:04", "throughput": 4695.59, "total_tokens": 4004032} {"current_steps": 3990, "total_steps": 42420, "loss": 0.169, "lr": 4.701791607732202e-05, "epoch": 1.881188118811881, "percentage": 9.41, "elapsed_time": "0:14:13", "remaining_time": "2:17:02", "throughput": 4695.82, "total_tokens": 4008960} {"current_steps": 3995, "total_steps": 42420, "loss": 0.1067, "lr": 4.707685054219708e-05, "epoch": 1.8835454974068835, "percentage": 9.42, "elapsed_time": "0:14:14", "remaining_time": "2:17:00", "throughput": 4695.63, "total_tokens": 4013120} {"current_steps": 4000, "total_steps": 42420, "loss": 0.2095, "lr": 4.713578500707214e-05, "epoch": 1.8859028760018859, "percentage": 9.43, "elapsed_time": "0:14:15", "remaining_time": "2:16:58", "throughput": 4695.74, "total_tokens": 4017696} {"current_steps": 4005, "total_steps": 42420, "loss": 0.2541, "lr": 4.71947194719472e-05, "epoch": 1.8882602545968883, "percentage": 9.44, "elapsed_time": "0:14:16", "remaining_time": "2:16:56", "throughput": 4695.96, "total_tokens": 4022464} {"current_steps": 4010, "total_steps": 42420, "loss": 0.2387, "lr": 4.725365393682226e-05, "epoch": 1.8906176331918907, "percentage": 9.45, "elapsed_time": "0:14:17", "remaining_time": "2:16:53", "throughput": 4696.0, "total_tokens": 4026912} {"current_steps": 4015, "total_steps": 42420, "loss": 0.4184, "lr": 4.731258840169732e-05, "epoch": 1.892975011786893, "percentage": 9.46, "elapsed_time": "0:14:18", "remaining_time": "2:16:52", "throughput": 4696.25, "total_tokens": 4032000} {"current_steps": 4020, "total_steps": 42420, "loss": 0.4128, "lr": 4.737152286657238e-05, "epoch": 1.8953323903818955, "percentage": 9.48, "elapsed_time": "0:14:19", "remaining_time": "2:16:50", "throughput": 4696.38, "total_tokens": 4036608} {"current_steps": 4025, "total_steps": 42420, "loss": 0.1142, "lr": 4.743045733144743e-05, "epoch": 1.8976897689768977, "percentage": 9.49, "elapsed_time": "0:14:20", "remaining_time": "2:16:48", "throughput": 4696.52, "total_tokens": 4041280} {"current_steps": 4030, "total_steps": 42420, "loss": 0.1576, "lr": 4.748939179632249e-05, "epoch": 1.9000471475719, "percentage": 9.5, "elapsed_time": "0:14:21", "remaining_time": "2:16:49", "throughput": 4696.77, "total_tokens": 4047520} {"current_steps": 4035, "total_steps": 42420, "loss": 0.1118, "lr": 4.754832626119755e-05, "epoch": 1.9024045261669023, "percentage": 9.51, "elapsed_time": "0:14:23", "remaining_time": "2:16:49", "throughput": 4697.09, "total_tokens": 4053696} {"current_steps": 4040, "total_steps": 42420, "loss": 0.1884, "lr": 4.760726072607261e-05, "epoch": 1.9047619047619047, "percentage": 9.52, "elapsed_time": "0:14:23", "remaining_time": "2:16:47", "throughput": 4697.06, "total_tokens": 4057888} {"current_steps": 4045, "total_steps": 42420, "loss": 0.2492, "lr": 4.766619519094767e-05, "epoch": 1.907119283356907, "percentage": 9.54, "elapsed_time": "0:14:25", "remaining_time": "2:16:47", "throughput": 4697.24, "total_tokens": 4063520} {"current_steps": 4050, "total_steps": 42420, "loss": 0.0893, "lr": 4.772512965582273e-05, "epoch": 1.9094766619519095, "percentage": 9.55, "elapsed_time": "0:14:26", "remaining_time": "2:16:45", "throughput": 4697.28, "total_tokens": 4068384} {"current_steps": 4055, "total_steps": 42420, "loss": 0.0781, "lr": 4.778406412069779e-05, "epoch": 1.9118340405469119, "percentage": 9.56, "elapsed_time": "0:14:27", "remaining_time": "2:16:43", "throughput": 4697.21, "total_tokens": 4072768} {"current_steps": 4060, "total_steps": 42420, "loss": 0.1648, "lr": 4.784299858557285e-05, "epoch": 1.9141914191419143, "percentage": 9.57, "elapsed_time": "0:14:28", "remaining_time": "2:16:42", "throughput": 4697.53, "total_tokens": 4078400} {"current_steps": 4065, "total_steps": 42420, "loss": 0.1965, "lr": 4.7901933050447907e-05, "epoch": 1.9165487977369167, "percentage": 9.58, "elapsed_time": "0:14:29", "remaining_time": "2:16:41", "throughput": 4697.52, "total_tokens": 4083168} {"current_steps": 4070, "total_steps": 42420, "loss": 0.22, "lr": 4.7960867515322966e-05, "epoch": 1.918906176331919, "percentage": 9.59, "elapsed_time": "0:14:30", "remaining_time": "2:16:39", "throughput": 4697.64, "total_tokens": 4087904} {"current_steps": 4075, "total_steps": 42420, "loss": 0.2343, "lr": 4.801980198019802e-05, "epoch": 1.9212635549269212, "percentage": 9.61, "elapsed_time": "0:14:31", "remaining_time": "2:16:37", "throughput": 4697.71, "total_tokens": 4092704} {"current_steps": 4080, "total_steps": 42420, "loss": 0.2084, "lr": 4.807873644507308e-05, "epoch": 1.9236209335219236, "percentage": 9.62, "elapsed_time": "0:14:32", "remaining_time": "2:16:37", "throughput": 4697.75, "total_tokens": 4097984} {"current_steps": 4085, "total_steps": 42420, "loss": 0.1266, "lr": 4.813767090994814e-05, "epoch": 1.9259783121169258, "percentage": 9.63, "elapsed_time": "0:14:33", "remaining_time": "2:16:36", "throughput": 4697.7, "total_tokens": 4102976} {"current_steps": 4090, "total_steps": 42420, "loss": 0.2855, "lr": 4.81966053748232e-05, "epoch": 1.9283356907119282, "percentage": 9.64, "elapsed_time": "0:14:34", "remaining_time": "2:16:36", "throughput": 4698.03, "total_tokens": 4108896} {"current_steps": 4095, "total_steps": 42420, "loss": 0.3036, "lr": 4.825553983969826e-05, "epoch": 1.9306930693069306, "percentage": 9.65, "elapsed_time": "0:14:35", "remaining_time": "2:16:35", "throughput": 4698.36, "total_tokens": 4114336} {"current_steps": 4100, "total_steps": 42420, "loss": 0.2837, "lr": 4.831447430457332e-05, "epoch": 1.933050447901933, "percentage": 9.67, "elapsed_time": "0:14:36", "remaining_time": "2:16:33", "throughput": 4698.26, "total_tokens": 4118944} {"current_steps": 4105, "total_steps": 42420, "loss": 0.335, "lr": 4.837340876944838e-05, "epoch": 1.9354078264969354, "percentage": 9.68, "elapsed_time": "0:14:37", "remaining_time": "2:16:32", "throughput": 4698.24, "total_tokens": 4123968} {"current_steps": 4110, "total_steps": 42420, "loss": 0.3248, "lr": 4.8432343234323437e-05, "epoch": 1.9377652050919378, "percentage": 9.69, "elapsed_time": "0:14:38", "remaining_time": "2:16:31", "throughput": 4698.51, "total_tokens": 4129120} {"current_steps": 4115, "total_steps": 42420, "loss": 0.434, "lr": 4.8491277699198496e-05, "epoch": 1.9401225836869402, "percentage": 9.7, "elapsed_time": "0:14:39", "remaining_time": "2:16:29", "throughput": 4698.57, "total_tokens": 4133536} {"current_steps": 4120, "total_steps": 42420, "loss": 0.1755, "lr": 4.8550212164073556e-05, "epoch": 1.9424799622819426, "percentage": 9.71, "elapsed_time": "0:14:40", "remaining_time": "2:16:27", "throughput": 4698.75, "total_tokens": 4138208} {"current_steps": 4125, "total_steps": 42420, "loss": 0.1332, "lr": 4.860914662894861e-05, "epoch": 1.9448373408769448, "percentage": 9.72, "elapsed_time": "0:14:41", "remaining_time": "2:16:24", "throughput": 4698.79, "total_tokens": 4142656} {"current_steps": 4130, "total_steps": 42420, "loss": 0.0874, "lr": 4.866808109382367e-05, "epoch": 1.9471947194719472, "percentage": 9.74, "elapsed_time": "0:14:42", "remaining_time": "2:16:24", "throughput": 4699.08, "total_tokens": 4148224} {"current_steps": 4135, "total_steps": 42420, "loss": 0.0573, "lr": 4.872701555869873e-05, "epoch": 1.9495520980669494, "percentage": 9.75, "elapsed_time": "0:14:43", "remaining_time": "2:16:22", "throughput": 4699.26, "total_tokens": 4152800} {"current_steps": 4140, "total_steps": 42420, "loss": 0.0535, "lr": 4.878595002357379e-05, "epoch": 1.9519094766619518, "percentage": 9.76, "elapsed_time": "0:14:45", "remaining_time": "2:16:25", "throughput": 4699.67, "total_tokens": 4160608} {"current_steps": 4145, "total_steps": 42420, "loss": 0.1817, "lr": 4.884488448844885e-05, "epoch": 1.9542668552569542, "percentage": 9.77, "elapsed_time": "0:14:46", "remaining_time": "2:16:23", "throughput": 4699.73, "total_tokens": 4165056} {"current_steps": 4150, "total_steps": 42420, "loss": 0.1462, "lr": 4.890381895332391e-05, "epoch": 1.9566242338519566, "percentage": 9.78, "elapsed_time": "0:14:47", "remaining_time": "2:16:22", "throughput": 4699.87, "total_tokens": 4170048} {"current_steps": 4155, "total_steps": 42420, "loss": 0.1509, "lr": 4.8962753418198966e-05, "epoch": 1.958981612446959, "percentage": 9.79, "elapsed_time": "0:14:48", "remaining_time": "2:16:21", "throughput": 4700.22, "total_tokens": 4175520} {"current_steps": 4160, "total_steps": 42420, "loss": 0.4019, "lr": 4.9021687883074026e-05, "epoch": 1.9613389910419614, "percentage": 9.81, "elapsed_time": "0:14:49", "remaining_time": "2:16:22", "throughput": 4700.78, "total_tokens": 4182176} {"current_steps": 4165, "total_steps": 42420, "loss": 0.1826, "lr": 4.9080622347949086e-05, "epoch": 1.9636963696369638, "percentage": 9.82, "elapsed_time": "0:14:50", "remaining_time": "2:16:21", "throughput": 4701.01, "total_tokens": 4187552} {"current_steps": 4170, "total_steps": 42420, "loss": 0.2342, "lr": 4.9139556812824145e-05, "epoch": 1.9660537482319662, "percentage": 9.83, "elapsed_time": "0:14:51", "remaining_time": "2:16:21", "throughput": 4701.25, "total_tokens": 4193056} {"current_steps": 4175, "total_steps": 42420, "loss": 0.2252, "lr": 4.91984912776992e-05, "epoch": 1.9684111268269684, "percentage": 9.84, "elapsed_time": "0:14:52", "remaining_time": "2:16:19", "throughput": 4701.35, "total_tokens": 4197792} {"current_steps": 4180, "total_steps": 42420, "loss": 0.1708, "lr": 4.925742574257426e-05, "epoch": 1.9707685054219708, "percentage": 9.85, "elapsed_time": "0:14:53", "remaining_time": "2:16:16", "throughput": 4701.43, "total_tokens": 4201984} {"current_steps": 4185, "total_steps": 42420, "loss": 0.1578, "lr": 4.931636020744932e-05, "epoch": 1.973125884016973, "percentage": 9.87, "elapsed_time": "0:14:55", "remaining_time": "2:16:16", "throughput": 4701.66, "total_tokens": 4208000} {"current_steps": 4190, "total_steps": 42420, "loss": 0.1405, "lr": 4.937529467232438e-05, "epoch": 1.9754832626119754, "percentage": 9.88, "elapsed_time": "0:14:56", "remaining_time": "2:16:15", "throughput": 4701.86, "total_tokens": 4213056} {"current_steps": 4195, "total_steps": 42420, "loss": 0.3588, "lr": 4.943422913719944e-05, "epoch": 1.9778406412069778, "percentage": 9.89, "elapsed_time": "0:14:57", "remaining_time": "2:16:14", "throughput": 4701.97, "total_tokens": 4217952} {"current_steps": 4200, "total_steps": 42420, "loss": 0.0854, "lr": 4.9493163602074496e-05, "epoch": 1.9801980198019802, "percentage": 9.9, "elapsed_time": "0:14:57", "remaining_time": "2:16:11", "throughput": 4702.06, "total_tokens": 4222336} {"current_steps": 4205, "total_steps": 42420, "loss": 0.1082, "lr": 4.9552098066949556e-05, "epoch": 1.9825553983969826, "percentage": 9.91, "elapsed_time": "0:14:59", "remaining_time": "2:16:10", "throughput": 4702.32, "total_tokens": 4227840} {"current_steps": 4210, "total_steps": 42420, "loss": 0.1998, "lr": 4.9611032531824616e-05, "epoch": 1.984912776991985, "percentage": 9.92, "elapsed_time": "0:15:00", "remaining_time": "2:16:10", "throughput": 4702.45, "total_tokens": 4233280} {"current_steps": 4215, "total_steps": 42420, "loss": 0.1522, "lr": 4.9669966996699675e-05, "epoch": 1.9872701555869874, "percentage": 9.94, "elapsed_time": "0:15:01", "remaining_time": "2:16:07", "throughput": 4702.4, "total_tokens": 4237280} {"current_steps": 4220, "total_steps": 42420, "loss": 0.1116, "lr": 4.9728901461574735e-05, "epoch": 1.9896275341819898, "percentage": 9.95, "elapsed_time": "0:15:02", "remaining_time": "2:16:05", "throughput": 4702.37, "total_tokens": 4242016} {"current_steps": 4225, "total_steps": 42420, "loss": 0.2507, "lr": 4.978783592644979e-05, "epoch": 1.991984912776992, "percentage": 9.96, "elapsed_time": "0:15:03", "remaining_time": "2:16:04", "throughput": 4702.41, "total_tokens": 4247008} {"current_steps": 4230, "total_steps": 42420, "loss": 0.2106, "lr": 4.984677039132485e-05, "epoch": 1.9943422913719944, "percentage": 9.97, "elapsed_time": "0:15:04", "remaining_time": "2:16:04", "throughput": 4702.63, "total_tokens": 4252768} {"current_steps": 4235, "total_steps": 42420, "loss": 0.2623, "lr": 4.990570485619991e-05, "epoch": 1.9966996699669965, "percentage": 9.98, "elapsed_time": "0:15:05", "remaining_time": "2:16:02", "throughput": 4702.79, "total_tokens": 4257568} {"current_steps": 4240, "total_steps": 42420, "loss": 0.1636, "lr": 4.996463932107497e-05, "epoch": 1.999057048561999, "percentage": 10.0, "elapsed_time": "0:15:06", "remaining_time": "2:16:01", "throughput": 4703.01, "total_tokens": 4262496} {"current_steps": 4242, "total_steps": 42420, "eval_loss": 0.18287692964076996, "epoch": 2.0, "percentage": 10.0, "elapsed_time": "0:15:22", "remaining_time": "2:18:18", "throughput": 4625.36, "total_tokens": 4264768} {"current_steps": 4245, "total_steps": 42420, "loss": 0.1177, "lr": 4.999999966143396e-05, "epoch": 2.0014144271570014, "percentage": 10.01, "elapsed_time": "0:15:24", "remaining_time": "2:18:30", "throughput": 4617.75, "total_tokens": 4267584} {"current_steps": 4250, "total_steps": 42420, "loss": 0.1442, "lr": 4.9999995852566046e-05, "epoch": 2.0037718057520038, "percentage": 10.02, "elapsed_time": "0:15:25", "remaining_time": "2:18:29", "throughput": 4617.88, "total_tokens": 4272640} {"current_steps": 4255, "total_steps": 42420, "loss": 0.1178, "lr": 4.999998781162331e-05, "epoch": 2.006129184347006, "percentage": 10.03, "elapsed_time": "0:15:26", "remaining_time": "2:18:28", "throughput": 4618.14, "total_tokens": 4278080} {"current_steps": 4260, "total_steps": 42420, "loss": 0.1881, "lr": 4.999997553860712e-05, "epoch": 2.0084865629420086, "percentage": 10.04, "elapsed_time": "0:15:27", "remaining_time": "2:18:26", "throughput": 4617.99, "total_tokens": 4282496} {"current_steps": 4265, "total_steps": 42420, "loss": 0.2509, "lr": 4.999995903351954e-05, "epoch": 2.010843941537011, "percentage": 10.05, "elapsed_time": "0:15:28", "remaining_time": "2:18:25", "throughput": 4618.08, "total_tokens": 4287456} {"current_steps": 4270, "total_steps": 42420, "loss": 0.0696, "lr": 4.999993829636337e-05, "epoch": 2.0132013201320134, "percentage": 10.07, "elapsed_time": "0:15:29", "remaining_time": "2:18:24", "throughput": 4618.23, "total_tokens": 4292576} {"current_steps": 4275, "total_steps": 42420, "loss": 0.1788, "lr": 4.999991332714212e-05, "epoch": 2.0155586987270158, "percentage": 10.08, "elapsed_time": "0:15:30", "remaining_time": "2:18:23", "throughput": 4618.4, "total_tokens": 4297600} {"current_steps": 4280, "total_steps": 42420, "loss": 0.0787, "lr": 4.999988412586003e-05, "epoch": 2.0179160773220177, "percentage": 10.09, "elapsed_time": "0:15:31", "remaining_time": "2:18:23", "throughput": 4618.84, "total_tokens": 4303744} {"current_steps": 4285, "total_steps": 42420, "loss": 0.1922, "lr": 4.999985069252202e-05, "epoch": 2.02027345591702, "percentage": 10.1, "elapsed_time": "0:15:32", "remaining_time": "2:18:22", "throughput": 4619.06, "total_tokens": 4309312} {"current_steps": 4290, "total_steps": 42420, "loss": 0.1598, "lr": 4.999981302713377e-05, "epoch": 2.0226308345120225, "percentage": 10.11, "elapsed_time": "0:15:34", "remaining_time": "2:18:21", "throughput": 4619.25, "total_tokens": 4314496} {"current_steps": 4295, "total_steps": 42420, "loss": 0.1732, "lr": 4.999977112970164e-05, "epoch": 2.024988213107025, "percentage": 10.12, "elapsed_time": "0:15:35", "remaining_time": "2:18:20", "throughput": 4619.35, "total_tokens": 4319552} {"current_steps": 4300, "total_steps": 42420, "loss": 0.2166, "lr": 4.9999725000232734e-05, "epoch": 2.0273455917020273, "percentage": 10.14, "elapsed_time": "0:15:36", "remaining_time": "2:18:18", "throughput": 4619.49, "total_tokens": 4324448} {"current_steps": 4305, "total_steps": 42420, "loss": 0.2296, "lr": 4.999967463873485e-05, "epoch": 2.0297029702970297, "percentage": 10.15, "elapsed_time": "0:15:37", "remaining_time": "2:18:17", "throughput": 4619.85, "total_tokens": 4329760} {"current_steps": 4310, "total_steps": 42420, "loss": 0.1161, "lr": 4.999962004521652e-05, "epoch": 2.032060348892032, "percentage": 10.16, "elapsed_time": "0:15:38", "remaining_time": "2:18:16", "throughput": 4620.18, "total_tokens": 4334880} {"current_steps": 4315, "total_steps": 42420, "loss": 0.1988, "lr": 4.9999561219686995e-05, "epoch": 2.0344177274870345, "percentage": 10.17, "elapsed_time": "0:15:39", "remaining_time": "2:18:15", "throughput": 4620.37, "total_tokens": 4340096} {"current_steps": 4320, "total_steps": 42420, "loss": 0.0612, "lr": 4.999949816215622e-05, "epoch": 2.036775106082037, "percentage": 10.18, "elapsed_time": "0:15:40", "remaining_time": "2:18:14", "throughput": 4620.38, "total_tokens": 4345344} {"current_steps": 4325, "total_steps": 42420, "loss": 0.406, "lr": 4.999943087263487e-05, "epoch": 2.0391324846770393, "percentage": 10.2, "elapsed_time": "0:15:41", "remaining_time": "2:18:14", "throughput": 4620.7, "total_tokens": 4351360} {"current_steps": 4330, "total_steps": 42420, "loss": 0.1697, "lr": 4.9999359351134346e-05, "epoch": 2.0414898632720413, "percentage": 10.21, "elapsed_time": "0:15:42", "remaining_time": "2:18:13", "throughput": 4620.66, "total_tokens": 4356192} {"current_steps": 4335, "total_steps": 42420, "loss": 0.1303, "lr": 4.999928359766674e-05, "epoch": 2.0438472418670437, "percentage": 10.22, "elapsed_time": "0:15:44", "remaining_time": "2:18:13", "throughput": 4621.08, "total_tokens": 4362496} {"current_steps": 4340, "total_steps": 42420, "loss": 0.173, "lr": 4.9999203612244896e-05, "epoch": 2.046204620462046, "percentage": 10.23, "elapsed_time": "0:15:44", "remaining_time": "2:18:11", "throughput": 4621.13, "total_tokens": 4366752} {"current_steps": 4345, "total_steps": 42420, "loss": 0.0573, "lr": 4.9999119394882334e-05, "epoch": 2.0485619990570485, "percentage": 10.24, "elapsed_time": "0:15:45", "remaining_time": "2:18:09", "throughput": 4621.32, "total_tokens": 4371648} {"current_steps": 4350, "total_steps": 42420, "loss": 0.2652, "lr": 4.999903094559332e-05, "epoch": 2.050919377652051, "percentage": 10.25, "elapsed_time": "0:15:47", "remaining_time": "2:18:08", "throughput": 4621.54, "total_tokens": 4376864} {"current_steps": 4355, "total_steps": 42420, "loss": 0.1949, "lr": 4.999893826439283e-05, "epoch": 2.0532767562470533, "percentage": 10.27, "elapsed_time": "0:15:48", "remaining_time": "2:18:06", "throughput": 4621.65, "total_tokens": 4381408} {"current_steps": 4360, "total_steps": 42420, "loss": 0.2849, "lr": 4.9998841351296546e-05, "epoch": 2.0556341348420557, "percentage": 10.28, "elapsed_time": "0:15:48", "remaining_time": "2:18:03", "throughput": 4621.81, "total_tokens": 4385888} {"current_steps": 4365, "total_steps": 42420, "loss": 0.1308, "lr": 4.999874020632087e-05, "epoch": 2.057991513437058, "percentage": 10.29, "elapsed_time": "0:15:49", "remaining_time": "2:18:02", "throughput": 4621.59, "total_tokens": 4390432} {"current_steps": 4370, "total_steps": 42420, "loss": 0.2624, "lr": 4.9998634829482945e-05, "epoch": 2.0603488920320605, "percentage": 10.3, "elapsed_time": "0:15:51", "remaining_time": "2:18:00", "throughput": 4621.76, "total_tokens": 4395296} {"current_steps": 4375, "total_steps": 42420, "loss": 0.4059, "lr": 4.999852522080059e-05, "epoch": 2.062706270627063, "percentage": 10.31, "elapsed_time": "0:15:52", "remaining_time": "2:17:58", "throughput": 4621.92, "total_tokens": 4400192} {"current_steps": 4380, "total_steps": 42420, "loss": 0.1495, "lr": 4.9998411380292364e-05, "epoch": 2.065063649222065, "percentage": 10.33, "elapsed_time": "0:15:53", "remaining_time": "2:17:57", "throughput": 4622.23, "total_tokens": 4405632} {"current_steps": 4385, "total_steps": 42420, "loss": 0.0704, "lr": 4.999829330797755e-05, "epoch": 2.0674210278170673, "percentage": 10.34, "elapsed_time": "0:15:54", "remaining_time": "2:17:56", "throughput": 4622.42, "total_tokens": 4410656} {"current_steps": 4390, "total_steps": 42420, "loss": 0.1198, "lr": 4.999817100387612e-05, "epoch": 2.0697784064120697, "percentage": 10.35, "elapsed_time": "0:15:55", "remaining_time": "2:17:54", "throughput": 4622.68, "total_tokens": 4415680} {"current_steps": 4395, "total_steps": 42420, "loss": 0.1239, "lr": 4.9998044468008775e-05, "epoch": 2.072135785007072, "percentage": 10.36, "elapsed_time": "0:15:56", "remaining_time": "2:17:54", "throughput": 4622.85, "total_tokens": 4421024} {"current_steps": 4400, "total_steps": 42420, "loss": 0.2587, "lr": 4.999791370039696e-05, "epoch": 2.0744931636020745, "percentage": 10.37, "elapsed_time": "0:15:57", "remaining_time": "2:17:51", "throughput": 4622.76, "total_tokens": 4425376} {"current_steps": 4405, "total_steps": 42420, "loss": 0.1921, "lr": 4.999777870106278e-05, "epoch": 2.076850542197077, "percentage": 10.38, "elapsed_time": "0:15:58", "remaining_time": "2:17:50", "throughput": 4622.85, "total_tokens": 4430304} {"current_steps": 4410, "total_steps": 42420, "loss": 0.1604, "lr": 4.999763947002911e-05, "epoch": 2.0792079207920793, "percentage": 10.4, "elapsed_time": "0:15:59", "remaining_time": "2:17:49", "throughput": 4622.97, "total_tokens": 4435520} {"current_steps": 4415, "total_steps": 42420, "loss": 0.2568, "lr": 4.999749600731952e-05, "epoch": 2.0815652993870817, "percentage": 10.41, "elapsed_time": "0:16:00", "remaining_time": "2:17:47", "throughput": 4623.0, "total_tokens": 4440256} {"current_steps": 4420, "total_steps": 42420, "loss": 0.1545, "lr": 4.9997348312958285e-05, "epoch": 2.083922677982084, "percentage": 10.42, "elapsed_time": "0:16:01", "remaining_time": "2:17:46", "throughput": 4623.22, "total_tokens": 4445152} {"current_steps": 4425, "total_steps": 42420, "loss": 0.2303, "lr": 4.9997196386970416e-05, "epoch": 2.0862800565770865, "percentage": 10.43, "elapsed_time": "0:16:02", "remaining_time": "2:17:43", "throughput": 4623.38, "total_tokens": 4449632} {"current_steps": 4430, "total_steps": 42420, "loss": 0.11, "lr": 4.9997040229381616e-05, "epoch": 2.0886374351720884, "percentage": 10.44, "elapsed_time": "0:16:03", "remaining_time": "2:17:43", "throughput": 4623.58, "total_tokens": 4455136} {"current_steps": 4435, "total_steps": 42420, "loss": 0.0555, "lr": 4.9996879840218335e-05, "epoch": 2.090994813767091, "percentage": 10.45, "elapsed_time": "0:16:04", "remaining_time": "2:17:41", "throughput": 4623.65, "total_tokens": 4459808} {"current_steps": 4440, "total_steps": 42420, "loss": 0.2321, "lr": 4.999671521950773e-05, "epoch": 2.0933521923620932, "percentage": 10.47, "elapsed_time": "0:16:05", "remaining_time": "2:17:41", "throughput": 4624.14, "total_tokens": 4466080} {"current_steps": 4445, "total_steps": 42420, "loss": 0.2017, "lr": 4.999654636727764e-05, "epoch": 2.0957095709570956, "percentage": 10.48, "elapsed_time": "0:16:07", "remaining_time": "2:17:43", "throughput": 4624.73, "total_tokens": 4473184} {"current_steps": 4450, "total_steps": 42420, "loss": 0.1929, "lr": 4.999637328355669e-05, "epoch": 2.098066949552098, "percentage": 10.49, "elapsed_time": "0:16:08", "remaining_time": "2:17:41", "throughput": 4624.87, "total_tokens": 4477824} {"current_steps": 4455, "total_steps": 42420, "loss": 0.1705, "lr": 4.999619596837414e-05, "epoch": 2.1004243281471005, "percentage": 10.5, "elapsed_time": "0:16:09", "remaining_time": "2:17:39", "throughput": 4625.07, "total_tokens": 4482624} {"current_steps": 4460, "total_steps": 42420, "loss": 0.2294, "lr": 4.999601442176003e-05, "epoch": 2.102781706742103, "percentage": 10.51, "elapsed_time": "0:16:10", "remaining_time": "2:17:37", "throughput": 4625.27, "total_tokens": 4487488} {"current_steps": 4465, "total_steps": 42420, "loss": 0.1349, "lr": 4.999582864374508e-05, "epoch": 2.1051390853371053, "percentage": 10.53, "elapsed_time": "0:16:11", "remaining_time": "2:17:36", "throughput": 4625.49, "total_tokens": 4492768} {"current_steps": 4470, "total_steps": 42420, "loss": 0.4007, "lr": 4.999563863436075e-05, "epoch": 2.1074964639321077, "percentage": 10.54, "elapsed_time": "0:16:12", "remaining_time": "2:17:35", "throughput": 4625.85, "total_tokens": 4498208} {"current_steps": 4475, "total_steps": 42420, "loss": 0.2358, "lr": 4.99954443936392e-05, "epoch": 2.10985384252711, "percentage": 10.55, "elapsed_time": "0:16:13", "remaining_time": "2:17:33", "throughput": 4625.98, "total_tokens": 4502880} {"current_steps": 4480, "total_steps": 42420, "loss": 0.1194, "lr": 4.999524592161332e-05, "epoch": 2.112211221122112, "percentage": 10.56, "elapsed_time": "0:16:14", "remaining_time": "2:17:32", "throughput": 4626.1, "total_tokens": 4508032} {"current_steps": 4485, "total_steps": 42420, "loss": 0.185, "lr": 4.9995043218316694e-05, "epoch": 2.1145685997171144, "percentage": 10.57, "elapsed_time": "0:16:15", "remaining_time": "2:17:31", "throughput": 4626.38, "total_tokens": 4513568} {"current_steps": 4490, "total_steps": 42420, "loss": 0.221, "lr": 4.999483628378364e-05, "epoch": 2.116925978312117, "percentage": 10.58, "elapsed_time": "0:16:16", "remaining_time": "2:17:31", "throughput": 4626.68, "total_tokens": 4518976} {"current_steps": 4495, "total_steps": 42420, "loss": 0.143, "lr": 4.99946251180492e-05, "epoch": 2.119283356907119, "percentage": 10.6, "elapsed_time": "0:16:17", "remaining_time": "2:17:27", "throughput": 4626.67, "total_tokens": 4522912} {"current_steps": 4500, "total_steps": 42420, "loss": 0.1215, "lr": 4.999440972114911e-05, "epoch": 2.1216407355021216, "percentage": 10.61, "elapsed_time": "0:16:18", "remaining_time": "2:17:25", "throughput": 4626.88, "total_tokens": 4527520} {"current_steps": 4505, "total_steps": 42420, "loss": 0.0553, "lr": 4.999419009311983e-05, "epoch": 2.123998114097124, "percentage": 10.62, "elapsed_time": "0:16:19", "remaining_time": "2:17:24", "throughput": 4627.08, "total_tokens": 4532416} {"current_steps": 4510, "total_steps": 42420, "loss": 0.2425, "lr": 4.999396623399855e-05, "epoch": 2.1263554926921264, "percentage": 10.63, "elapsed_time": "0:16:20", "remaining_time": "2:17:23", "throughput": 4627.4, "total_tokens": 4537952} {"current_steps": 4515, "total_steps": 42420, "loss": 0.0592, "lr": 4.999373814382315e-05, "epoch": 2.128712871287129, "percentage": 10.64, "elapsed_time": "0:16:21", "remaining_time": "2:17:21", "throughput": 4627.46, "total_tokens": 4542528} {"current_steps": 4520, "total_steps": 42420, "loss": 0.1042, "lr": 4.999350582263226e-05, "epoch": 2.1310702498821312, "percentage": 10.66, "elapsed_time": "0:16:22", "remaining_time": "2:17:19", "throughput": 4627.52, "total_tokens": 4547008} {"current_steps": 4525, "total_steps": 42420, "loss": 0.2061, "lr": 4.99932692704652e-05, "epoch": 2.1334276284771336, "percentage": 10.67, "elapsed_time": "0:16:23", "remaining_time": "2:17:17", "throughput": 4627.61, "total_tokens": 4551680} {"current_steps": 4530, "total_steps": 42420, "loss": 0.2424, "lr": 4.9993028487362006e-05, "epoch": 2.1357850070721356, "percentage": 10.68, "elapsed_time": "0:16:24", "remaining_time": "2:17:16", "throughput": 4627.95, "total_tokens": 4557216} {"current_steps": 4535, "total_steps": 42420, "loss": 0.1709, "lr": 4.9992783473363455e-05, "epoch": 2.138142385667138, "percentage": 10.69, "elapsed_time": "0:16:25", "remaining_time": "2:17:15", "throughput": 4628.13, "total_tokens": 4562464} {"current_steps": 4540, "total_steps": 42420, "loss": 0.1855, "lr": 4.999253422851101e-05, "epoch": 2.1404997642621404, "percentage": 10.7, "elapsed_time": "0:16:26", "remaining_time": "2:17:14", "throughput": 4628.35, "total_tokens": 4567776} {"current_steps": 4545, "total_steps": 42420, "loss": 0.2982, "lr": 4.999228075284688e-05, "epoch": 2.142857142857143, "percentage": 10.71, "elapsed_time": "0:16:28", "remaining_time": "2:17:13", "throughput": 4628.65, "total_tokens": 4573152} {"current_steps": 4550, "total_steps": 42420, "loss": 0.3138, "lr": 4.999202304641395e-05, "epoch": 2.145214521452145, "percentage": 10.73, "elapsed_time": "0:16:29", "remaining_time": "2:17:11", "throughput": 4628.74, "total_tokens": 4578048} {"current_steps": 4555, "total_steps": 42420, "loss": 0.1863, "lr": 4.9991761109255864e-05, "epoch": 2.1475719000471476, "percentage": 10.74, "elapsed_time": "0:16:29", "remaining_time": "2:17:09", "throughput": 4628.74, "total_tokens": 4582336} {"current_steps": 4560, "total_steps": 42420, "loss": 0.0781, "lr": 4.999149494141696e-05, "epoch": 2.14992927864215, "percentage": 10.75, "elapsed_time": "0:16:31", "remaining_time": "2:17:08", "throughput": 4628.91, "total_tokens": 4587360} {"current_steps": 4565, "total_steps": 42420, "loss": 0.3029, "lr": 4.9991224542942294e-05, "epoch": 2.1522866572371524, "percentage": 10.76, "elapsed_time": "0:16:31", "remaining_time": "2:17:05", "throughput": 4629.01, "total_tokens": 4591872} {"current_steps": 4570, "total_steps": 42420, "loss": 0.1447, "lr": 4.999094991387764e-05, "epoch": 2.154644035832155, "percentage": 10.77, "elapsed_time": "0:16:32", "remaining_time": "2:17:04", "throughput": 4629.11, "total_tokens": 4596640} {"current_steps": 4575, "total_steps": 42420, "loss": 0.1378, "lr": 4.9990671054269485e-05, "epoch": 2.157001414427157, "percentage": 10.79, "elapsed_time": "0:16:33", "remaining_time": "2:17:01", "throughput": 4629.05, "total_tokens": 4600672} {"current_steps": 4580, "total_steps": 42420, "loss": 0.1404, "lr": 4.999038796416503e-05, "epoch": 2.159358793022159, "percentage": 10.8, "elapsed_time": "0:16:34", "remaining_time": "2:17:00", "throughput": 4629.35, "total_tokens": 4606080} {"current_steps": 4585, "total_steps": 42420, "loss": 0.2588, "lr": 4.9990100643612226e-05, "epoch": 2.1617161716171616, "percentage": 10.81, "elapsed_time": "0:16:35", "remaining_time": "2:16:58", "throughput": 4629.61, "total_tokens": 4610816} {"current_steps": 4590, "total_steps": 42420, "loss": 0.1606, "lr": 4.998980909265967e-05, "epoch": 2.164073550212164, "percentage": 10.82, "elapsed_time": "0:16:36", "remaining_time": "2:16:57", "throughput": 4629.86, "total_tokens": 4615968} {"current_steps": 4595, "total_steps": 42420, "loss": 0.2086, "lr": 4.998951331135675e-05, "epoch": 2.1664309288071664, "percentage": 10.83, "elapsed_time": "0:16:37", "remaining_time": "2:16:54", "throughput": 4630.04, "total_tokens": 4620288} {"current_steps": 4600, "total_steps": 42420, "loss": 0.2687, "lr": 4.998921329975352e-05, "epoch": 2.1687883074021688, "percentage": 10.84, "elapsed_time": "0:16:38", "remaining_time": "2:16:53", "throughput": 4630.36, "total_tokens": 4625568} {"current_steps": 4605, "total_steps": 42420, "loss": 0.3419, "lr": 4.9988909057900777e-05, "epoch": 2.171145685997171, "percentage": 10.86, "elapsed_time": "0:16:40", "remaining_time": "2:16:51", "throughput": 4630.56, "total_tokens": 4630560} {"current_steps": 4610, "total_steps": 42420, "loss": 0.0989, "lr": 4.998860058585001e-05, "epoch": 2.1735030645921736, "percentage": 10.87, "elapsed_time": "0:16:41", "remaining_time": "2:16:51", "throughput": 4630.92, "total_tokens": 4636192} {"current_steps": 4615, "total_steps": 42420, "loss": 0.1, "lr": 4.998828788365344e-05, "epoch": 2.175860443187176, "percentage": 10.88, "elapsed_time": "0:16:42", "remaining_time": "2:16:49", "throughput": 4631.15, "total_tokens": 4641344} {"current_steps": 4620, "total_steps": 42420, "loss": 0.1575, "lr": 4.998797095136403e-05, "epoch": 2.1782178217821784, "percentage": 10.89, "elapsed_time": "0:16:43", "remaining_time": "2:16:48", "throughput": 4631.39, "total_tokens": 4646528} {"current_steps": 4625, "total_steps": 42420, "loss": 0.0995, "lr": 4.998764978903539e-05, "epoch": 2.1805752003771808, "percentage": 10.9, "elapsed_time": "0:16:44", "remaining_time": "2:16:47", "throughput": 4631.56, "total_tokens": 4651616} {"current_steps": 4630, "total_steps": 42420, "loss": 0.0902, "lr": 4.9987324396721915e-05, "epoch": 2.1829325789721827, "percentage": 10.91, "elapsed_time": "0:16:45", "remaining_time": "2:16:45", "throughput": 4631.77, "total_tokens": 4656672} {"current_steps": 4635, "total_steps": 42420, "loss": 0.2266, "lr": 4.998699477447868e-05, "epoch": 2.185289957567185, "percentage": 10.93, "elapsed_time": "0:16:46", "remaining_time": "2:16:45", "throughput": 4632.04, "total_tokens": 4662144} {"current_steps": 4640, "total_steps": 42420, "loss": 0.3005, "lr": 4.998666092236148e-05, "epoch": 2.1876473361621875, "percentage": 10.94, "elapsed_time": "0:16:47", "remaining_time": "2:16:43", "throughput": 4632.36, "total_tokens": 4667488} {"current_steps": 4645, "total_steps": 42420, "loss": 0.107, "lr": 4.9986322840426835e-05, "epoch": 2.19000471475719, "percentage": 10.95, "elapsed_time": "0:16:48", "remaining_time": "2:16:42", "throughput": 4632.57, "total_tokens": 4672480} {"current_steps": 4650, "total_steps": 42420, "loss": 0.2422, "lr": 4.9985980528731976e-05, "epoch": 2.1923620933521923, "percentage": 10.96, "elapsed_time": "0:16:49", "remaining_time": "2:16:40", "throughput": 4632.64, "total_tokens": 4677024} {"current_steps": 4655, "total_steps": 42420, "loss": 0.318, "lr": 4.998563398733486e-05, "epoch": 2.1947194719471947, "percentage": 10.97, "elapsed_time": "0:16:50", "remaining_time": "2:16:38", "throughput": 4632.83, "total_tokens": 4681728} {"current_steps": 4660, "total_steps": 42420, "loss": 0.1489, "lr": 4.998528321629414e-05, "epoch": 2.197076850542197, "percentage": 10.99, "elapsed_time": "0:16:51", "remaining_time": "2:16:35", "throughput": 4632.97, "total_tokens": 4686016} {"current_steps": 4665, "total_steps": 42420, "loss": 0.0489, "lr": 4.998492821566919e-05, "epoch": 2.1994342291371995, "percentage": 11.0, "elapsed_time": "0:16:52", "remaining_time": "2:16:33", "throughput": 4632.91, "total_tokens": 4690240} {"current_steps": 4670, "total_steps": 42420, "loss": 0.1072, "lr": 4.998456898552012e-05, "epoch": 2.201791607732202, "percentage": 11.01, "elapsed_time": "0:16:53", "remaining_time": "2:16:31", "throughput": 4632.92, "total_tokens": 4694848} {"current_steps": 4675, "total_steps": 42420, "loss": 0.1934, "lr": 4.9984205525907736e-05, "epoch": 2.2041489863272044, "percentage": 11.02, "elapsed_time": "0:16:54", "remaining_time": "2:16:29", "throughput": 4632.87, "total_tokens": 4699136} {"current_steps": 4680, "total_steps": 42420, "loss": 0.1687, "lr": 4.998383783689356e-05, "epoch": 2.2065063649222063, "percentage": 11.03, "elapsed_time": "0:16:55", "remaining_time": "2:16:28", "throughput": 4633.14, "total_tokens": 4704384} {"current_steps": 4685, "total_steps": 42420, "loss": 0.2021, "lr": 4.998346591853984e-05, "epoch": 2.2088637435172087, "percentage": 11.04, "elapsed_time": "0:16:56", "remaining_time": "2:16:27", "throughput": 4633.37, "total_tokens": 4709632} {"current_steps": 4690, "total_steps": 42420, "loss": 0.1126, "lr": 4.998308977090953e-05, "epoch": 2.211221122112211, "percentage": 11.06, "elapsed_time": "0:16:57", "remaining_time": "2:16:25", "throughput": 4633.62, "total_tokens": 4714560} {"current_steps": 4695, "total_steps": 42420, "loss": 0.1309, "lr": 4.998270939406632e-05, "epoch": 2.2135785007072135, "percentage": 11.07, "elapsed_time": "0:16:58", "remaining_time": "2:16:23", "throughput": 4633.61, "total_tokens": 4719008} {"current_steps": 4700, "total_steps": 42420, "loss": 0.1533, "lr": 4.9982324788074585e-05, "epoch": 2.215935879302216, "percentage": 11.08, "elapsed_time": "0:16:59", "remaining_time": "2:16:20", "throughput": 4633.43, "total_tokens": 4723136} {"current_steps": 4705, "total_steps": 42420, "loss": 0.0857, "lr": 4.9981935952999445e-05, "epoch": 2.2182932578972183, "percentage": 11.09, "elapsed_time": "0:17:00", "remaining_time": "2:16:20", "throughput": 4633.78, "total_tokens": 4729024} {"current_steps": 4710, "total_steps": 42420, "loss": 0.1657, "lr": 4.998154288890671e-05, "epoch": 2.2206506364922207, "percentage": 11.1, "elapsed_time": "0:17:01", "remaining_time": "2:16:17", "throughput": 4633.85, "total_tokens": 4733152} {"current_steps": 4715, "total_steps": 42420, "loss": 0.2276, "lr": 4.998114559586293e-05, "epoch": 2.223008015087223, "percentage": 11.12, "elapsed_time": "0:17:02", "remaining_time": "2:16:16", "throughput": 4633.88, "total_tokens": 4737824} {"current_steps": 4720, "total_steps": 42420, "loss": 0.1667, "lr": 4.998074407393536e-05, "epoch": 2.2253653936822255, "percentage": 11.13, "elapsed_time": "0:17:03", "remaining_time": "2:16:13", "throughput": 4633.88, "total_tokens": 4741792} {"current_steps": 4725, "total_steps": 42420, "loss": 0.1881, "lr": 4.9980338323191964e-05, "epoch": 2.227722772277228, "percentage": 11.14, "elapsed_time": "0:17:04", "remaining_time": "2:16:12", "throughput": 4634.08, "total_tokens": 4746976} {"current_steps": 4730, "total_steps": 42420, "loss": 0.0887, "lr": 4.9979928343701435e-05, "epoch": 2.23008015087223, "percentage": 11.15, "elapsed_time": "0:17:05", "remaining_time": "2:16:11", "throughput": 4634.16, "total_tokens": 4752544} {"current_steps": 4735, "total_steps": 42420, "loss": 0.2566, "lr": 4.997951413553317e-05, "epoch": 2.2324375294672323, "percentage": 11.16, "elapsed_time": "0:17:06", "remaining_time": "2:16:09", "throughput": 4634.29, "total_tokens": 4756928} {"current_steps": 4740, "total_steps": 42420, "loss": 0.2493, "lr": 4.9979095698757286e-05, "epoch": 2.2347949080622347, "percentage": 11.17, "elapsed_time": "0:17:08", "remaining_time": "2:16:12", "throughput": 4634.61, "total_tokens": 4764800} {"current_steps": 4745, "total_steps": 42420, "loss": 0.1484, "lr": 4.9978673033444624e-05, "epoch": 2.237152286657237, "percentage": 11.19, "elapsed_time": "0:17:09", "remaining_time": "2:16:14", "throughput": 4634.89, "total_tokens": 4771712} {"current_steps": 4750, "total_steps": 42420, "loss": 0.0937, "lr": 4.997824613966673e-05, "epoch": 2.2395096652522395, "percentage": 11.2, "elapsed_time": "0:17:10", "remaining_time": "2:16:13", "throughput": 4635.15, "total_tokens": 4776896} {"current_steps": 4755, "total_steps": 42420, "loss": 0.4588, "lr": 4.9977815017495874e-05, "epoch": 2.241867043847242, "percentage": 11.21, "elapsed_time": "0:17:11", "remaining_time": "2:16:12", "throughput": 4635.34, "total_tokens": 4782496} {"current_steps": 4760, "total_steps": 42420, "loss": 0.3253, "lr": 4.997737966700503e-05, "epoch": 2.2442244224422443, "percentage": 11.22, "elapsed_time": "0:17:12", "remaining_time": "2:16:12", "throughput": 4635.54, "total_tokens": 4788480} {"current_steps": 4765, "total_steps": 42420, "loss": 0.1231, "lr": 4.99769400882679e-05, "epoch": 2.2465818010372467, "percentage": 11.23, "elapsed_time": "0:17:13", "remaining_time": "2:16:10", "throughput": 4635.71, "total_tokens": 4793024} {"current_steps": 4770, "total_steps": 42420, "loss": 0.0573, "lr": 4.997649628135891e-05, "epoch": 2.248939179632249, "percentage": 11.24, "elapsed_time": "0:17:15", "remaining_time": "2:16:09", "throughput": 4636.01, "total_tokens": 4798336} {"current_steps": 4775, "total_steps": 42420, "loss": 0.4415, "lr": 4.997604824635316e-05, "epoch": 2.251296558227251, "percentage": 11.26, "elapsed_time": "0:17:15", "remaining_time": "2:16:06", "throughput": 4636.05, "total_tokens": 4802336} {"current_steps": 4780, "total_steps": 42420, "loss": 0.1112, "lr": 4.9975595983326514e-05, "epoch": 2.2536539368222535, "percentage": 11.27, "elapsed_time": "0:17:17", "remaining_time": "2:16:05", "throughput": 4636.23, "total_tokens": 4807776} {"current_steps": 4785, "total_steps": 42420, "loss": 0.1002, "lr": 4.997513949235554e-05, "epoch": 2.256011315417256, "percentage": 11.28, "elapsed_time": "0:17:18", "remaining_time": "2:16:04", "throughput": 4636.28, "total_tokens": 4812896} {"current_steps": 4790, "total_steps": 42420, "loss": 0.1804, "lr": 4.9974678773517495e-05, "epoch": 2.2583686940122583, "percentage": 11.29, "elapsed_time": "0:17:19", "remaining_time": "2:16:04", "throughput": 4636.48, "total_tokens": 4818560} {"current_steps": 4795, "total_steps": 42420, "loss": 0.2054, "lr": 4.9974213826890384e-05, "epoch": 2.2607260726072607, "percentage": 11.3, "elapsed_time": "0:17:20", "remaining_time": "2:16:02", "throughput": 4636.21, "total_tokens": 4822912} {"current_steps": 4800, "total_steps": 42420, "loss": 0.0719, "lr": 4.997374465255291e-05, "epoch": 2.263083451202263, "percentage": 11.32, "elapsed_time": "0:17:21", "remaining_time": "2:16:00", "throughput": 4636.41, "total_tokens": 4827456} {"current_steps": 4805, "total_steps": 42420, "loss": 0.2403, "lr": 4.997327125058449e-05, "epoch": 2.2654408297972655, "percentage": 11.33, "elapsed_time": "0:17:22", "remaining_time": "2:15:58", "throughput": 4636.7, "total_tokens": 4832576} {"current_steps": 4810, "total_steps": 42420, "loss": 0.2088, "lr": 4.997279362106527e-05, "epoch": 2.267798208392268, "percentage": 11.34, "elapsed_time": "0:17:23", "remaining_time": "2:15:56", "throughput": 4636.5, "total_tokens": 4836736} {"current_steps": 4815, "total_steps": 42420, "loss": 0.1471, "lr": 4.9972311764076105e-05, "epoch": 2.2701555869872703, "percentage": 11.35, "elapsed_time": "0:17:24", "remaining_time": "2:15:55", "throughput": 4636.43, "total_tokens": 4841312} {"current_steps": 4820, "total_steps": 42420, "loss": 0.1743, "lr": 4.997182567969857e-05, "epoch": 2.2725129655822727, "percentage": 11.36, "elapsed_time": "0:17:25", "remaining_time": "2:15:53", "throughput": 4636.6, "total_tokens": 4845984} {"current_steps": 4825, "total_steps": 42420, "loss": 0.2044, "lr": 4.997133536801494e-05, "epoch": 2.274870344177275, "percentage": 11.37, "elapsed_time": "0:17:26", "remaining_time": "2:15:51", "throughput": 4636.88, "total_tokens": 4851104} {"current_steps": 4830, "total_steps": 42420, "loss": 0.1128, "lr": 4.997084082910822e-05, "epoch": 2.2772277227722775, "percentage": 11.39, "elapsed_time": "0:17:27", "remaining_time": "2:15:50", "throughput": 4637.14, "total_tokens": 4856384} {"current_steps": 4835, "total_steps": 42420, "loss": 0.1627, "lr": 4.997034206306214e-05, "epoch": 2.2795851013672794, "percentage": 11.4, "elapsed_time": "0:17:28", "remaining_time": "2:15:49", "throughput": 4637.33, "total_tokens": 4861632} {"current_steps": 4840, "total_steps": 42420, "loss": 0.3689, "lr": 4.996983906996111e-05, "epoch": 2.281942479962282, "percentage": 11.41, "elapsed_time": "0:17:29", "remaining_time": "2:15:47", "throughput": 4637.51, "total_tokens": 4866400} {"current_steps": 4845, "total_steps": 42420, "loss": 0.1265, "lr": 4.996933184989029e-05, "epoch": 2.2842998585572842, "percentage": 11.42, "elapsed_time": "0:17:30", "remaining_time": "2:15:46", "throughput": 4637.86, "total_tokens": 4871744} {"current_steps": 4850, "total_steps": 42420, "loss": 0.1261, "lr": 4.996882040293555e-05, "epoch": 2.2866572371522866, "percentage": 11.43, "elapsed_time": "0:17:31", "remaining_time": "2:15:45", "throughput": 4638.14, "total_tokens": 4876992} {"current_steps": 4855, "total_steps": 42420, "loss": 0.3047, "lr": 4.996830472918345e-05, "epoch": 2.289014615747289, "percentage": 11.45, "elapsed_time": "0:17:32", "remaining_time": "2:15:44", "throughput": 4638.43, "total_tokens": 4882304} {"current_steps": 4860, "total_steps": 42420, "loss": 0.2495, "lr": 4.9967784828721304e-05, "epoch": 2.2913719943422914, "percentage": 11.46, "elapsed_time": "0:17:33", "remaining_time": "2:15:41", "throughput": 4638.4, "total_tokens": 4886080} {"current_steps": 4865, "total_steps": 42420, "loss": 0.16, "lr": 4.9967260701637115e-05, "epoch": 2.293729372937294, "percentage": 11.47, "elapsed_time": "0:17:34", "remaining_time": "2:15:40", "throughput": 4638.43, "total_tokens": 4891264} {"current_steps": 4870, "total_steps": 42420, "loss": 0.2015, "lr": 4.9966732348019605e-05, "epoch": 2.2960867515322962, "percentage": 11.48, "elapsed_time": "0:17:35", "remaining_time": "2:15:41", "throughput": 4638.81, "total_tokens": 4897856} {"current_steps": 4875, "total_steps": 42420, "loss": 0.1614, "lr": 4.996619976795823e-05, "epoch": 2.298444130127298, "percentage": 11.49, "elapsed_time": "0:17:36", "remaining_time": "2:15:38", "throughput": 4638.85, "total_tokens": 4902240} {"current_steps": 4880, "total_steps": 42420, "loss": 0.2593, "lr": 4.9965662961543126e-05, "epoch": 2.3008015087223006, "percentage": 11.5, "elapsed_time": "0:17:37", "remaining_time": "2:15:36", "throughput": 4639.0, "total_tokens": 4906912} {"current_steps": 4885, "total_steps": 42420, "loss": 0.1337, "lr": 4.996512192886518e-05, "epoch": 2.303158887317303, "percentage": 11.52, "elapsed_time": "0:17:38", "remaining_time": "2:15:34", "throughput": 4639.07, "total_tokens": 4911488} {"current_steps": 4890, "total_steps": 42420, "loss": 0.1365, "lr": 4.996457667001597e-05, "epoch": 2.3055162659123054, "percentage": 11.53, "elapsed_time": "0:17:39", "remaining_time": "2:15:33", "throughput": 4638.85, "total_tokens": 4916032} {"current_steps": 4895, "total_steps": 42420, "loss": 0.1035, "lr": 4.996402718508781e-05, "epoch": 2.307873644507308, "percentage": 11.54, "elapsed_time": "0:17:40", "remaining_time": "2:15:32", "throughput": 4639.09, "total_tokens": 4921152} {"current_steps": 4900, "total_steps": 42420, "loss": 0.1787, "lr": 4.996347347417371e-05, "epoch": 2.31023102310231, "percentage": 11.55, "elapsed_time": "0:17:41", "remaining_time": "2:15:29", "throughput": 4639.17, "total_tokens": 4925280} {"current_steps": 4905, "total_steps": 42420, "loss": 0.2647, "lr": 4.99629155373674e-05, "epoch": 2.3125884016973126, "percentage": 11.56, "elapsed_time": "0:17:42", "remaining_time": "2:15:28", "throughput": 4639.4, "total_tokens": 4930496} {"current_steps": 4910, "total_steps": 42420, "loss": 0.2122, "lr": 4.996235337476335e-05, "epoch": 2.314945780292315, "percentage": 11.57, "elapsed_time": "0:17:43", "remaining_time": "2:15:27", "throughput": 4639.62, "total_tokens": 4935968} {"current_steps": 4915, "total_steps": 42420, "loss": 0.0757, "lr": 4.9961786986456707e-05, "epoch": 2.3173031588873174, "percentage": 11.59, "elapsed_time": "0:17:44", "remaining_time": "2:15:26", "throughput": 4639.94, "total_tokens": 4941312} {"current_steps": 4920, "total_steps": 42420, "loss": 0.0924, "lr": 4.996121637254335e-05, "epoch": 2.31966053748232, "percentage": 11.6, "elapsed_time": "0:17:45", "remaining_time": "2:15:24", "throughput": 4640.1, "total_tokens": 4946208} {"current_steps": 4925, "total_steps": 42420, "loss": 0.3685, "lr": 4.996064153311988e-05, "epoch": 2.322017916077322, "percentage": 11.61, "elapsed_time": "0:17:46", "remaining_time": "2:15:23", "throughput": 4640.27, "total_tokens": 4951072} {"current_steps": 4930, "total_steps": 42420, "loss": 0.1283, "lr": 4.99600624682836e-05, "epoch": 2.3243752946723246, "percentage": 11.62, "elapsed_time": "0:17:47", "remaining_time": "2:15:19", "throughput": 4640.06, "total_tokens": 4954624} {"current_steps": 4935, "total_steps": 42420, "loss": 0.0904, "lr": 4.995947917813255e-05, "epoch": 2.3267326732673266, "percentage": 11.63, "elapsed_time": "0:17:48", "remaining_time": "2:15:18", "throughput": 4640.29, "total_tokens": 4959584} {"current_steps": 4940, "total_steps": 42420, "loss": 0.2194, "lr": 4.995889166276546e-05, "epoch": 2.329090051862329, "percentage": 11.65, "elapsed_time": "0:17:49", "remaining_time": "2:15:15", "throughput": 4640.38, "total_tokens": 4963776} {"current_steps": 4945, "total_steps": 42420, "loss": 0.1594, "lr": 4.9958299922281785e-05, "epoch": 2.3314474304573314, "percentage": 11.66, "elapsed_time": "0:17:50", "remaining_time": "2:15:13", "throughput": 4640.59, "total_tokens": 4968448} {"current_steps": 4950, "total_steps": 42420, "loss": 0.1475, "lr": 4.995770395678171e-05, "epoch": 2.333804809052334, "percentage": 11.67, "elapsed_time": "0:17:51", "remaining_time": "2:15:12", "throughput": 4640.61, "total_tokens": 4973280} {"current_steps": 4955, "total_steps": 42420, "loss": 0.223, "lr": 4.995710376636611e-05, "epoch": 2.336162187647336, "percentage": 11.68, "elapsed_time": "0:17:52", "remaining_time": "2:15:10", "throughput": 4640.74, "total_tokens": 4977984} {"current_steps": 4960, "total_steps": 42420, "loss": 0.2644, "lr": 4.995649935113658e-05, "epoch": 2.3385195662423386, "percentage": 11.69, "elapsed_time": "0:17:53", "remaining_time": "2:15:09", "throughput": 4640.95, "total_tokens": 4983136} {"current_steps": 4965, "total_steps": 42420, "loss": 0.1948, "lr": 4.995589071119546e-05, "epoch": 2.340876944837341, "percentage": 11.7, "elapsed_time": "0:17:54", "remaining_time": "2:15:07", "throughput": 4641.21, "total_tokens": 4988032} {"current_steps": 4970, "total_steps": 42420, "loss": 0.1785, "lr": 4.995527784664577e-05, "epoch": 2.3432343234323434, "percentage": 11.72, "elapsed_time": "0:17:55", "remaining_time": "2:15:07", "throughput": 4641.59, "total_tokens": 4994176} {"current_steps": 4975, "total_steps": 42420, "loss": 0.1146, "lr": 4.9954660757591244e-05, "epoch": 2.3455917020273453, "percentage": 11.73, "elapsed_time": "0:17:57", "remaining_time": "2:15:07", "throughput": 4641.98, "total_tokens": 5000480} {"current_steps": 4980, "total_steps": 42420, "loss": 0.087, "lr": 4.995403944413636e-05, "epoch": 2.3479490806223478, "percentage": 11.74, "elapsed_time": "0:17:58", "remaining_time": "2:15:05", "throughput": 4642.07, "total_tokens": 5004960} {"current_steps": 4985, "total_steps": 42420, "loss": 0.0908, "lr": 4.9953413906386305e-05, "epoch": 2.35030645921735, "percentage": 11.75, "elapsed_time": "0:17:59", "remaining_time": "2:15:03", "throughput": 4642.21, "total_tokens": 5009120} {"current_steps": 4990, "total_steps": 42420, "loss": 0.0896, "lr": 4.995278414444695e-05, "epoch": 2.3526638378123526, "percentage": 11.76, "elapsed_time": "0:18:00", "remaining_time": "2:15:01", "throughput": 4642.43, "total_tokens": 5013984} {"current_steps": 4995, "total_steps": 42420, "loss": 0.1746, "lr": 4.995215015842492e-05, "epoch": 2.355021216407355, "percentage": 11.78, "elapsed_time": "0:18:01", "remaining_time": "2:14:59", "throughput": 4642.64, "total_tokens": 5018880} {"current_steps": 5000, "total_steps": 42420, "loss": 0.2027, "lr": 4.995151194842753e-05, "epoch": 2.3573785950023574, "percentage": 11.79, "elapsed_time": "0:18:02", "remaining_time": "2:14:58", "throughput": 4642.82, "total_tokens": 5024000} {"current_steps": 5005, "total_steps": 42420, "loss": 0.1012, "lr": 4.995086951456282e-05, "epoch": 2.3597359735973598, "percentage": 11.8, "elapsed_time": "0:18:02", "remaining_time": "2:14:55", "throughput": 4642.92, "total_tokens": 5028064} {"current_steps": 5010, "total_steps": 42420, "loss": 0.1164, "lr": 4.995022285693954e-05, "epoch": 2.362093352192362, "percentage": 11.81, "elapsed_time": "0:18:03", "remaining_time": "2:14:53", "throughput": 4643.1, "total_tokens": 5032768} {"current_steps": 5015, "total_steps": 42420, "loss": 0.4146, "lr": 4.9949571975667166e-05, "epoch": 2.3644507307873646, "percentage": 11.82, "elapsed_time": "0:18:04", "remaining_time": "2:14:51", "throughput": 4643.16, "total_tokens": 5037024} {"current_steps": 5020, "total_steps": 42420, "loss": 0.182, "lr": 4.994891687085587e-05, "epoch": 2.366808109382367, "percentage": 11.83, "elapsed_time": "0:18:05", "remaining_time": "2:14:50", "throughput": 4643.47, "total_tokens": 5042688} {"current_steps": 5025, "total_steps": 42420, "loss": 0.1114, "lr": 4.994825754261656e-05, "epoch": 2.3691654879773694, "percentage": 11.85, "elapsed_time": "0:18:07", "remaining_time": "2:14:51", "throughput": 4643.91, "total_tokens": 5049120} {"current_steps": 5030, "total_steps": 42420, "loss": 0.071, "lr": 4.994759399106085e-05, "epoch": 2.3715228665723718, "percentage": 11.86, "elapsed_time": "0:18:08", "remaining_time": "2:14:50", "throughput": 4644.15, "total_tokens": 5054560} {"current_steps": 5035, "total_steps": 42420, "loss": 0.0988, "lr": 4.994692621630105e-05, "epoch": 2.3738802451673737, "percentage": 11.87, "elapsed_time": "0:18:09", "remaining_time": "2:14:48", "throughput": 4644.31, "total_tokens": 5059232} {"current_steps": 5040, "total_steps": 42420, "loss": 0.264, "lr": 4.9946254218450225e-05, "epoch": 2.376237623762376, "percentage": 11.88, "elapsed_time": "0:18:10", "remaining_time": "2:14:46", "throughput": 4644.49, "total_tokens": 5063936} {"current_steps": 5045, "total_steps": 42420, "loss": 0.2079, "lr": 4.9945577997622126e-05, "epoch": 2.3785950023573785, "percentage": 11.89, "elapsed_time": "0:18:11", "remaining_time": "2:14:46", "throughput": 4644.81, "total_tokens": 5069920} {"current_steps": 5050, "total_steps": 42420, "loss": 0.268, "lr": 4.994489755393122e-05, "epoch": 2.380952380952381, "percentage": 11.9, "elapsed_time": "0:18:12", "remaining_time": "2:14:46", "throughput": 4645.28, "total_tokens": 5076128} {"current_steps": 5055, "total_steps": 42420, "loss": 0.1646, "lr": 4.9944212887492704e-05, "epoch": 2.3833097595473833, "percentage": 11.92, "elapsed_time": "0:18:13", "remaining_time": "2:14:44", "throughput": 4645.24, "total_tokens": 5080448} {"current_steps": 5060, "total_steps": 42420, "loss": 0.1405, "lr": 4.9943523998422465e-05, "epoch": 2.3856671381423857, "percentage": 11.93, "elapsed_time": "0:18:14", "remaining_time": "2:14:42", "throughput": 4645.19, "total_tokens": 5085312} {"current_steps": 5065, "total_steps": 42420, "loss": 0.2061, "lr": 4.9942830886837134e-05, "epoch": 2.388024516737388, "percentage": 11.94, "elapsed_time": "0:18:15", "remaining_time": "2:14:40", "throughput": 4645.17, "total_tokens": 5089632} {"current_steps": 5070, "total_steps": 42420, "loss": 0.1957, "lr": 4.994213355285404e-05, "epoch": 2.3903818953323905, "percentage": 11.95, "elapsed_time": "0:18:16", "remaining_time": "2:14:38", "throughput": 4645.2, "total_tokens": 5094208} {"current_steps": 5075, "total_steps": 42420, "loss": 0.2041, "lr": 4.994143199659123e-05, "epoch": 2.3927392739273925, "percentage": 11.96, "elapsed_time": "0:18:17", "remaining_time": "2:14:37", "throughput": 4645.35, "total_tokens": 5099424} {"current_steps": 5080, "total_steps": 42420, "loss": 0.2556, "lr": 4.994072621816746e-05, "epoch": 2.395096652522395, "percentage": 11.98, "elapsed_time": "0:18:18", "remaining_time": "2:14:37", "throughput": 4645.64, "total_tokens": 5104896} {"current_steps": 5085, "total_steps": 42420, "loss": 0.272, "lr": 4.9940016217702216e-05, "epoch": 2.3974540311173973, "percentage": 11.99, "elapsed_time": "0:18:19", "remaining_time": "2:14:35", "throughput": 4645.87, "total_tokens": 5109952} {"current_steps": 5090, "total_steps": 42420, "loss": 0.4237, "lr": 4.993930199531569e-05, "epoch": 2.3998114097123997, "percentage": 12.0, "elapsed_time": "0:18:20", "remaining_time": "2:14:34", "throughput": 4645.91, "total_tokens": 5115040} {"current_steps": 5095, "total_steps": 42420, "loss": 0.2114, "lr": 4.9938583551128774e-05, "epoch": 2.402168788307402, "percentage": 12.01, "elapsed_time": "0:18:22", "remaining_time": "2:14:34", "throughput": 4646.21, "total_tokens": 5120864} {"current_steps": 5100, "total_steps": 42420, "loss": 0.1339, "lr": 4.993786088526309e-05, "epoch": 2.4045261669024045, "percentage": 12.02, "elapsed_time": "0:18:23", "remaining_time": "2:14:32", "throughput": 4646.27, "total_tokens": 5125408} {"current_steps": 5105, "total_steps": 42420, "loss": 0.1197, "lr": 4.993713399784098e-05, "epoch": 2.406883545497407, "percentage": 12.03, "elapsed_time": "0:18:24", "remaining_time": "2:14:31", "throughput": 4646.45, "total_tokens": 5130560} {"current_steps": 5110, "total_steps": 42420, "loss": 0.3248, "lr": 4.9936402888985504e-05, "epoch": 2.4092409240924093, "percentage": 12.05, "elapsed_time": "0:18:25", "remaining_time": "2:14:28", "throughput": 4646.47, "total_tokens": 5134784} {"current_steps": 5115, "total_steps": 42420, "loss": 0.2367, "lr": 4.9935667558820405e-05, "epoch": 2.4115983026874117, "percentage": 12.06, "elapsed_time": "0:18:26", "remaining_time": "2:14:30", "throughput": 4646.87, "total_tokens": 5142208} {"current_steps": 5120, "total_steps": 42420, "loss": 0.2467, "lr": 4.993492800747017e-05, "epoch": 2.413955681282414, "percentage": 12.07, "elapsed_time": "0:18:27", "remaining_time": "2:14:29", "throughput": 4647.12, "total_tokens": 5147744} {"current_steps": 5125, "total_steps": 42420, "loss": 0.098, "lr": 4.993418423506e-05, "epoch": 2.4163130598774165, "percentage": 12.08, "elapsed_time": "0:18:29", "remaining_time": "2:14:30", "throughput": 4647.45, "total_tokens": 5154272} {"current_steps": 5130, "total_steps": 42420, "loss": 0.1549, "lr": 4.99334362417158e-05, "epoch": 2.418670438472419, "percentage": 12.09, "elapsed_time": "0:18:30", "remaining_time": "2:14:29", "throughput": 4647.57, "total_tokens": 5159488} {"current_steps": 5135, "total_steps": 42420, "loss": 0.2419, "lr": 4.993268402756418e-05, "epoch": 2.421027817067421, "percentage": 12.11, "elapsed_time": "0:18:31", "remaining_time": "2:14:28", "throughput": 4647.72, "total_tokens": 5164352} {"current_steps": 5140, "total_steps": 42420, "loss": 0.1835, "lr": 4.99319275927325e-05, "epoch": 2.4233851956624233, "percentage": 12.12, "elapsed_time": "0:18:32", "remaining_time": "2:14:27", "throughput": 4647.97, "total_tokens": 5169920} {"current_steps": 5145, "total_steps": 42420, "loss": 0.1705, "lr": 4.9931166937348785e-05, "epoch": 2.4257425742574257, "percentage": 12.13, "elapsed_time": "0:18:33", "remaining_time": "2:14:24", "throughput": 4647.94, "total_tokens": 5173792} {"current_steps": 5150, "total_steps": 42420, "loss": 0.2339, "lr": 4.993040206154183e-05, "epoch": 2.428099952852428, "percentage": 12.14, "elapsed_time": "0:18:34", "remaining_time": "2:14:27", "throughput": 4648.35, "total_tokens": 5181568} {"current_steps": 5155, "total_steps": 42420, "loss": 0.1507, "lr": 4.9929632965441084e-05, "epoch": 2.4304573314474305, "percentage": 12.15, "elapsed_time": "0:18:36", "remaining_time": "2:14:29", "throughput": 4648.73, "total_tokens": 5188992} {"current_steps": 5160, "total_steps": 42420, "loss": 0.088, "lr": 4.992885964917676e-05, "epoch": 2.432814710042433, "percentage": 12.16, "elapsed_time": "0:18:37", "remaining_time": "2:14:27", "throughput": 4649.0, "total_tokens": 5194176} {"current_steps": 5165, "total_steps": 42420, "loss": 0.3511, "lr": 4.9928082112879776e-05, "epoch": 2.4351720886374353, "percentage": 12.18, "elapsed_time": "0:18:38", "remaining_time": "2:14:25", "throughput": 4649.1, "total_tokens": 5198656} {"current_steps": 5170, "total_steps": 42420, "loss": 0.2211, "lr": 4.992730035668174e-05, "epoch": 2.4375294672324377, "percentage": 12.19, "elapsed_time": "0:18:39", "remaining_time": "2:14:24", "throughput": 4649.29, "total_tokens": 5203968} {"current_steps": 5175, "total_steps": 42420, "loss": 0.2857, "lr": 4.992651438071499e-05, "epoch": 2.4398868458274396, "percentage": 12.2, "elapsed_time": "0:18:40", "remaining_time": "2:14:22", "throughput": 4649.4, "total_tokens": 5208384} {"current_steps": 5180, "total_steps": 42420, "loss": 0.1075, "lr": 4.9925724185112594e-05, "epoch": 2.442244224422442, "percentage": 12.21, "elapsed_time": "0:18:41", "remaining_time": "2:14:19", "throughput": 4649.41, "total_tokens": 5212544} {"current_steps": 5185, "total_steps": 42420, "loss": 0.2938, "lr": 4.99249297700083e-05, "epoch": 2.4446016030174444, "percentage": 12.22, "elapsed_time": "0:18:42", "remaining_time": "2:14:19", "throughput": 4649.74, "total_tokens": 5218080} {"current_steps": 5190, "total_steps": 42420, "loss": 0.1628, "lr": 4.99241311355366e-05, "epoch": 2.446958981612447, "percentage": 12.23, "elapsed_time": "0:18:43", "remaining_time": "2:14:17", "throughput": 4649.89, "total_tokens": 5222784} {"current_steps": 5195, "total_steps": 42420, "loss": 0.3317, "lr": 4.992332828183269e-05, "epoch": 2.4493163602074493, "percentage": 12.25, "elapsed_time": "0:18:44", "remaining_time": "2:14:17", "throughput": 4650.11, "total_tokens": 5228832} {"current_steps": 5200, "total_steps": 42420, "loss": 0.2336, "lr": 4.992252120903247e-05, "epoch": 2.4516737388024517, "percentage": 12.26, "elapsed_time": "0:18:45", "remaining_time": "2:14:15", "throughput": 4650.15, "total_tokens": 5233536} {"current_steps": 5205, "total_steps": 42420, "loss": 0.205, "lr": 4.9921709917272576e-05, "epoch": 2.454031117397454, "percentage": 12.27, "elapsed_time": "0:18:46", "remaining_time": "2:14:14", "throughput": 4650.34, "total_tokens": 5238560} {"current_steps": 5210, "total_steps": 42420, "loss": 0.1581, "lr": 4.9920894406690336e-05, "epoch": 2.4563884959924565, "percentage": 12.28, "elapsed_time": "0:18:47", "remaining_time": "2:14:11", "throughput": 4650.34, "total_tokens": 5242560} {"current_steps": 5215, "total_steps": 42420, "loss": 0.2302, "lr": 4.99200746774238e-05, "epoch": 2.458745874587459, "percentage": 12.29, "elapsed_time": "0:18:48", "remaining_time": "2:14:10", "throughput": 4650.4, "total_tokens": 5247552} {"current_steps": 5220, "total_steps": 42420, "loss": 0.1578, "lr": 4.991925072961174e-05, "epoch": 2.4611032531824613, "percentage": 12.31, "elapsed_time": "0:18:49", "remaining_time": "2:14:08", "throughput": 4650.55, "total_tokens": 5252448} {"current_steps": 5225, "total_steps": 42420, "loss": 0.0761, "lr": 4.991842256339364e-05, "epoch": 2.4634606317774637, "percentage": 12.32, "elapsed_time": "0:18:50", "remaining_time": "2:14:06", "throughput": 4650.48, "total_tokens": 5256544} {"current_steps": 5230, "total_steps": 42420, "loss": 0.1943, "lr": 4.991759017890969e-05, "epoch": 2.465818010372466, "percentage": 12.33, "elapsed_time": "0:18:51", "remaining_time": "2:14:04", "throughput": 4650.53, "total_tokens": 5261184} {"current_steps": 5235, "total_steps": 42420, "loss": 0.1542, "lr": 4.991675357630081e-05, "epoch": 2.468175388967468, "percentage": 12.34, "elapsed_time": "0:18:52", "remaining_time": "2:14:03", "throughput": 4650.65, "total_tokens": 5266144} {"current_steps": 5240, "total_steps": 42420, "loss": 0.1958, "lr": 4.99159127557086e-05, "epoch": 2.4705327675624704, "percentage": 12.35, "elapsed_time": "0:18:53", "remaining_time": "2:14:04", "throughput": 4650.93, "total_tokens": 5272960} {"current_steps": 5245, "total_steps": 42420, "loss": 0.1902, "lr": 4.991506771727541e-05, "epoch": 2.472890146157473, "percentage": 12.36, "elapsed_time": "0:18:54", "remaining_time": "2:14:04", "throughput": 4651.29, "total_tokens": 5279136} {"current_steps": 5250, "total_steps": 42420, "loss": 0.2063, "lr": 4.991421846114429e-05, "epoch": 2.4752475247524752, "percentage": 12.38, "elapsed_time": "0:18:56", "remaining_time": "2:14:03", "throughput": 4651.48, "total_tokens": 5284448} {"current_steps": 5255, "total_steps": 42420, "loss": 0.1641, "lr": 4.991336498745901e-05, "epoch": 2.4776049033474776, "percentage": 12.39, "elapsed_time": "0:18:57", "remaining_time": "2:14:02", "throughput": 4651.57, "total_tokens": 5289408} {"current_steps": 5260, "total_steps": 42420, "loss": 0.1601, "lr": 4.991250729636403e-05, "epoch": 2.47996228194248, "percentage": 12.4, "elapsed_time": "0:18:58", "remaining_time": "2:14:01", "throughput": 4651.66, "total_tokens": 5294688} {"current_steps": 5265, "total_steps": 42420, "loss": 0.2242, "lr": 4.991164538800457e-05, "epoch": 2.4823196605374824, "percentage": 12.41, "elapsed_time": "0:18:59", "remaining_time": "2:13:59", "throughput": 4651.72, "total_tokens": 5299360} {"current_steps": 5270, "total_steps": 42420, "loss": 0.1753, "lr": 4.991077926252651e-05, "epoch": 2.484677039132485, "percentage": 12.42, "elapsed_time": "0:19:00", "remaining_time": "2:13:59", "throughput": 4652.0, "total_tokens": 5305472} {"current_steps": 5275, "total_steps": 42420, "loss": 0.1033, "lr": 4.9909908920076484e-05, "epoch": 2.487034417727487, "percentage": 12.44, "elapsed_time": "0:19:01", "remaining_time": "2:13:59", "throughput": 4652.3, "total_tokens": 5311680} {"current_steps": 5280, "total_steps": 42420, "loss": 0.2243, "lr": 4.990903436080183e-05, "epoch": 2.489391796322489, "percentage": 12.45, "elapsed_time": "0:19:02", "remaining_time": "2:13:59", "throughput": 4652.45, "total_tokens": 5317184} {"current_steps": 5285, "total_steps": 42420, "loss": 0.0337, "lr": 4.990815558485058e-05, "epoch": 2.4917491749174916, "percentage": 12.46, "elapsed_time": "0:19:03", "remaining_time": "2:13:57", "throughput": 4652.53, "total_tokens": 5321952} {"current_steps": 5290, "total_steps": 42420, "loss": 0.1322, "lr": 4.9907272592371515e-05, "epoch": 2.494106553512494, "percentage": 12.47, "elapsed_time": "0:19:05", "remaining_time": "2:13:58", "throughput": 4652.88, "total_tokens": 5328800} {"current_steps": 5295, "total_steps": 42420, "loss": 0.201, "lr": 4.9906385383514095e-05, "epoch": 2.4964639321074964, "percentage": 12.48, "elapsed_time": "0:19:06", "remaining_time": "2:13:56", "throughput": 4652.94, "total_tokens": 5333472} {"current_steps": 5300, "total_steps": 42420, "loss": 0.1395, "lr": 4.990549395842852e-05, "epoch": 2.498821310702499, "percentage": 12.49, "elapsed_time": "0:19:07", "remaining_time": "2:13:55", "throughput": 4653.07, "total_tokens": 5338368} {"current_steps": 5305, "total_steps": 42420, "loss": 0.215, "lr": 4.990459831726568e-05, "epoch": 2.501178689297501, "percentage": 12.51, "elapsed_time": "0:19:08", "remaining_time": "2:13:53", "throughput": 4653.31, "total_tokens": 5343200} {"current_steps": 5310, "total_steps": 42420, "loss": 0.3365, "lr": 4.9903698460177214e-05, "epoch": 2.5035360678925036, "percentage": 12.52, "elapsed_time": "0:19:09", "remaining_time": "2:13:51", "throughput": 4653.46, "total_tokens": 5348128} {"current_steps": 5315, "total_steps": 42420, "loss": 0.2673, "lr": 4.9902794387315434e-05, "epoch": 2.505893446487506, "percentage": 12.53, "elapsed_time": "0:19:10", "remaining_time": "2:13:50", "throughput": 4653.74, "total_tokens": 5353504} {"current_steps": 5320, "total_steps": 42420, "loss": 0.3361, "lr": 4.9901886098833396e-05, "epoch": 2.5082508250825084, "percentage": 12.54, "elapsed_time": "0:19:11", "remaining_time": "2:13:48", "throughput": 4653.87, "total_tokens": 5357760} {"current_steps": 5325, "total_steps": 42420, "loss": 0.1863, "lr": 4.9900973594884834e-05, "epoch": 2.510608203677511, "percentage": 12.55, "elapsed_time": "0:19:12", "remaining_time": "2:13:46", "throughput": 4653.87, "total_tokens": 5362144} {"current_steps": 5330, "total_steps": 42420, "loss": 0.2443, "lr": 4.990005687562426e-05, "epoch": 2.512965582272513, "percentage": 12.56, "elapsed_time": "0:19:13", "remaining_time": "2:13:44", "throughput": 4654.01, "total_tokens": 5366560} {"current_steps": 5335, "total_steps": 42420, "loss": 0.1653, "lr": 4.989913594120682e-05, "epoch": 2.515322960867515, "percentage": 12.58, "elapsed_time": "0:19:14", "remaining_time": "2:13:42", "throughput": 4654.14, "total_tokens": 5371168} {"current_steps": 5340, "total_steps": 42420, "loss": 0.1921, "lr": 4.989821079178843e-05, "epoch": 2.5176803394625176, "percentage": 12.59, "elapsed_time": "0:19:15", "remaining_time": "2:13:40", "throughput": 4654.38, "total_tokens": 5376096} {"current_steps": 5345, "total_steps": 42420, "loss": 0.1516, "lr": 4.98972814275257e-05, "epoch": 2.52003771805752, "percentage": 12.6, "elapsed_time": "0:19:16", "remaining_time": "2:13:38", "throughput": 4654.59, "total_tokens": 5380928} {"current_steps": 5350, "total_steps": 42420, "loss": 0.257, "lr": 4.9896347848575964e-05, "epoch": 2.5223950966525224, "percentage": 12.61, "elapsed_time": "0:19:17", "remaining_time": "2:13:37", "throughput": 4654.64, "total_tokens": 5385600} {"current_steps": 5355, "total_steps": 42420, "loss": 0.1552, "lr": 4.989541005509725e-05, "epoch": 2.5247524752475248, "percentage": 12.62, "elapsed_time": "0:19:17", "remaining_time": "2:13:34", "throughput": 4654.59, "total_tokens": 5389760} {"current_steps": 5360, "total_steps": 42420, "loss": 0.2798, "lr": 4.989446804724831e-05, "epoch": 2.527109853842527, "percentage": 12.64, "elapsed_time": "0:19:19", "remaining_time": "2:13:33", "throughput": 4654.87, "total_tokens": 5395296} {"current_steps": 5365, "total_steps": 42420, "loss": 0.2447, "lr": 4.9893521825188615e-05, "epoch": 2.5294672324375296, "percentage": 12.65, "elapsed_time": "0:19:19", "remaining_time": "2:13:31", "throughput": 4654.87, "total_tokens": 5399072} {"current_steps": 5370, "total_steps": 42420, "loss": 0.1394, "lr": 4.989257138907834e-05, "epoch": 2.531824611032532, "percentage": 12.66, "elapsed_time": "0:19:20", "remaining_time": "2:13:29", "throughput": 4655.03, "total_tokens": 5404128} {"current_steps": 5375, "total_steps": 42420, "loss": 0.0794, "lr": 4.989161673907839e-05, "epoch": 2.534181989627534, "percentage": 12.67, "elapsed_time": "0:19:21", "remaining_time": "2:13:27", "throughput": 4655.17, "total_tokens": 5408736} {"current_steps": 5380, "total_steps": 42420, "loss": 0.1039, "lr": 4.989065787535035e-05, "epoch": 2.5365393682225363, "percentage": 12.68, "elapsed_time": "0:19:22", "remaining_time": "2:13:26", "throughput": 4655.45, "total_tokens": 5414080} {"current_steps": 5385, "total_steps": 42420, "loss": 0.1816, "lr": 4.9889694798056555e-05, "epoch": 2.5388967468175387, "percentage": 12.69, "elapsed_time": "0:19:23", "remaining_time": "2:13:24", "throughput": 4655.66, "total_tokens": 5418784} {"current_steps": 5390, "total_steps": 42420, "loss": 0.1609, "lr": 4.988872750736003e-05, "epoch": 2.541254125412541, "percentage": 12.71, "elapsed_time": "0:19:25", "remaining_time": "2:13:24", "throughput": 4655.87, "total_tokens": 5424704} {"current_steps": 5395, "total_steps": 42420, "loss": 0.2696, "lr": 4.9887756003424534e-05, "epoch": 2.5436115040075435, "percentage": 12.72, "elapsed_time": "0:19:26", "remaining_time": "2:13:22", "throughput": 4656.01, "total_tokens": 5428928} {"current_steps": 5400, "total_steps": 42420, "loss": 0.1765, "lr": 4.988678028641451e-05, "epoch": 2.545968882602546, "percentage": 12.73, "elapsed_time": "0:19:27", "remaining_time": "2:13:20", "throughput": 4656.22, "total_tokens": 5433856} {"current_steps": 5405, "total_steps": 42420, "loss": 0.2205, "lr": 4.988580035649515e-05, "epoch": 2.5483262611975483, "percentage": 12.74, "elapsed_time": "0:19:28", "remaining_time": "2:13:18", "throughput": 4656.3, "total_tokens": 5438688} {"current_steps": 5410, "total_steps": 42420, "loss": 0.2364, "lr": 4.9884816213832306e-05, "epoch": 2.5506836397925507, "percentage": 12.75, "elapsed_time": "0:19:29", "remaining_time": "2:13:18", "throughput": 4656.55, "total_tokens": 5444672} {"current_steps": 5415, "total_steps": 42420, "loss": 0.247, "lr": 4.9883827858592615e-05, "epoch": 2.553041018387553, "percentage": 12.77, "elapsed_time": "0:19:30", "remaining_time": "2:13:18", "throughput": 4656.9, "total_tokens": 5450720} {"current_steps": 5420, "total_steps": 42420, "loss": 0.178, "lr": 4.988283529094336e-05, "epoch": 2.5553983969825556, "percentage": 12.78, "elapsed_time": "0:19:31", "remaining_time": "2:13:15", "throughput": 4656.72, "total_tokens": 5454432} {"current_steps": 5425, "total_steps": 42420, "loss": 0.1489, "lr": 4.988183851105258e-05, "epoch": 2.557755775577558, "percentage": 12.79, "elapsed_time": "0:19:32", "remaining_time": "2:13:14", "throughput": 4656.92, "total_tokens": 5459424} {"current_steps": 5430, "total_steps": 42420, "loss": 0.2034, "lr": 4.988083751908901e-05, "epoch": 2.5601131541725604, "percentage": 12.8, "elapsed_time": "0:19:33", "remaining_time": "2:13:13", "throughput": 4657.01, "total_tokens": 5464288} {"current_steps": 5435, "total_steps": 42420, "loss": 0.2182, "lr": 4.9879832315222096e-05, "epoch": 2.5624705327675623, "percentage": 12.81, "elapsed_time": "0:19:34", "remaining_time": "2:13:10", "throughput": 4657.17, "total_tokens": 5468736} {"current_steps": 5440, "total_steps": 42420, "loss": 0.1144, "lr": 4.987882289962201e-05, "epoch": 2.5648279113625647, "percentage": 12.82, "elapsed_time": "0:19:35", "remaining_time": "2:13:10", "throughput": 4657.27, "total_tokens": 5474400} {"current_steps": 5445, "total_steps": 42420, "loss": 0.0851, "lr": 4.987780927245963e-05, "epoch": 2.567185289957567, "percentage": 12.84, "elapsed_time": "0:19:36", "remaining_time": "2:13:09", "throughput": 4657.57, "total_tokens": 5479808} {"current_steps": 5450, "total_steps": 42420, "loss": 0.173, "lr": 4.987679143390653e-05, "epoch": 2.5695426685525695, "percentage": 12.85, "elapsed_time": "0:19:37", "remaining_time": "2:13:09", "throughput": 4657.86, "total_tokens": 5485632} {"current_steps": 5455, "total_steps": 42420, "loss": 0.1999, "lr": 4.987576938413504e-05, "epoch": 2.571900047147572, "percentage": 12.86, "elapsed_time": "0:19:39", "remaining_time": "2:13:09", "throughput": 4658.19, "total_tokens": 5492128} {"current_steps": 5460, "total_steps": 42420, "loss": 0.1993, "lr": 4.987474312331815e-05, "epoch": 2.5742574257425743, "percentage": 12.87, "elapsed_time": "0:19:39", "remaining_time": "2:13:07", "throughput": 4658.24, "total_tokens": 5496480} {"current_steps": 5465, "total_steps": 42420, "loss": 0.1127, "lr": 4.98737126516296e-05, "epoch": 2.5766148043375767, "percentage": 12.88, "elapsed_time": "0:19:40", "remaining_time": "2:13:05", "throughput": 4658.33, "total_tokens": 5501344} {"current_steps": 5470, "total_steps": 42420, "loss": 0.1772, "lr": 4.987267796924383e-05, "epoch": 2.578972182932579, "percentage": 12.89, "elapsed_time": "0:19:41", "remaining_time": "2:13:04", "throughput": 4658.51, "total_tokens": 5506304} {"current_steps": 5475, "total_steps": 42420, "loss": 0.0877, "lr": 4.987163907633599e-05, "epoch": 2.581329561527581, "percentage": 12.91, "elapsed_time": "0:19:42", "remaining_time": "2:13:01", "throughput": 4658.38, "total_tokens": 5510016} {"current_steps": 5480, "total_steps": 42420, "loss": 0.2462, "lr": 4.9870595973081956e-05, "epoch": 2.5836869401225835, "percentage": 12.92, "elapsed_time": "0:19:43", "remaining_time": "2:13:00", "throughput": 4658.54, "total_tokens": 5515456} {"current_steps": 5485, "total_steps": 42420, "loss": 0.497, "lr": 4.98695486596583e-05, "epoch": 2.586044318717586, "percentage": 12.93, "elapsed_time": "0:19:45", "remaining_time": "2:13:00", "throughput": 4658.9, "total_tokens": 5521568} {"current_steps": 5490, "total_steps": 42420, "loss": 0.1149, "lr": 4.986849713624231e-05, "epoch": 2.5884016973125883, "percentage": 12.94, "elapsed_time": "0:19:46", "remaining_time": "2:12:58", "throughput": 4659.04, "total_tokens": 5526304} {"current_steps": 5495, "total_steps": 42420, "loss": 0.1624, "lr": 4.986744140301201e-05, "epoch": 2.5907590759075907, "percentage": 12.95, "elapsed_time": "0:19:47", "remaining_time": "2:12:59", "throughput": 4659.34, "total_tokens": 5532608} {"current_steps": 5500, "total_steps": 42420, "loss": 0.1642, "lr": 4.98663814601461e-05, "epoch": 2.593116454502593, "percentage": 12.97, "elapsed_time": "0:19:48", "remaining_time": "2:12:57", "throughput": 4659.5, "total_tokens": 5537312} {"current_steps": 5505, "total_steps": 42420, "loss": 0.1713, "lr": 4.9865317307824016e-05, "epoch": 2.5954738330975955, "percentage": 12.98, "elapsed_time": "0:19:49", "remaining_time": "2:12:56", "throughput": 4659.76, "total_tokens": 5542720} {"current_steps": 5510, "total_steps": 42420, "loss": 0.1454, "lr": 4.98642489462259e-05, "epoch": 2.597831211692598, "percentage": 12.99, "elapsed_time": "0:19:50", "remaining_time": "2:12:53", "throughput": 4659.83, "total_tokens": 5546816} {"current_steps": 5515, "total_steps": 42420, "loss": 0.1779, "lr": 4.986317637553261e-05, "epoch": 2.6001885902876003, "percentage": 13.0, "elapsed_time": "0:19:51", "remaining_time": "2:12:52", "throughput": 4659.98, "total_tokens": 5551936} {"current_steps": 5520, "total_steps": 42420, "loss": 0.2325, "lr": 4.9862099595925716e-05, "epoch": 2.6025459688826027, "percentage": 13.01, "elapsed_time": "0:19:52", "remaining_time": "2:12:51", "throughput": 4660.19, "total_tokens": 5557120} {"current_steps": 5525, "total_steps": 42420, "loss": 0.2029, "lr": 4.9861018607587485e-05, "epoch": 2.604903347477605, "percentage": 13.02, "elapsed_time": "0:19:53", "remaining_time": "2:12:49", "throughput": 4660.21, "total_tokens": 5561728} {"current_steps": 5530, "total_steps": 42420, "loss": 0.1595, "lr": 4.985993341070093e-05, "epoch": 2.6072607260726075, "percentage": 13.04, "elapsed_time": "0:19:54", "remaining_time": "2:12:48", "throughput": 4660.32, "total_tokens": 5566656} {"current_steps": 5535, "total_steps": 42420, "loss": 0.1446, "lr": 4.985884400544974e-05, "epoch": 2.6096181046676095, "percentage": 13.05, "elapsed_time": "0:19:55", "remaining_time": "2:12:45", "throughput": 4660.36, "total_tokens": 5570720} {"current_steps": 5540, "total_steps": 42420, "loss": 0.2652, "lr": 4.9857750392018346e-05, "epoch": 2.611975483262612, "percentage": 13.06, "elapsed_time": "0:19:56", "remaining_time": "2:12:43", "throughput": 4660.53, "total_tokens": 5575328} {"current_steps": 5545, "total_steps": 42420, "loss": 0.1351, "lr": 4.985665257059186e-05, "epoch": 2.6143328618576143, "percentage": 13.07, "elapsed_time": "0:19:57", "remaining_time": "2:12:42", "throughput": 4660.64, "total_tokens": 5580352} {"current_steps": 5550, "total_steps": 42420, "loss": 0.2087, "lr": 4.9855550541356145e-05, "epoch": 2.6166902404526167, "percentage": 13.08, "elapsed_time": "0:19:58", "remaining_time": "2:12:41", "throughput": 4660.87, "total_tokens": 5585440} {"current_steps": 5555, "total_steps": 42420, "loss": 0.1121, "lr": 4.9854444304497735e-05, "epoch": 2.619047619047619, "percentage": 13.1, "elapsed_time": "0:19:59", "remaining_time": "2:12:39", "throughput": 4661.07, "total_tokens": 5590208} {"current_steps": 5560, "total_steps": 42420, "loss": 0.1772, "lr": 4.985333386020392e-05, "epoch": 2.6214049976426215, "percentage": 13.11, "elapsed_time": "0:20:00", "remaining_time": "2:12:38", "throughput": 4661.37, "total_tokens": 5595872} {"current_steps": 5565, "total_steps": 42420, "loss": 0.2124, "lr": 4.9852219208662666e-05, "epoch": 2.623762376237624, "percentage": 13.12, "elapsed_time": "0:20:01", "remaining_time": "2:12:37", "throughput": 4661.67, "total_tokens": 5601536} {"current_steps": 5570, "total_steps": 42420, "loss": 0.2902, "lr": 4.9851100350062665e-05, "epoch": 2.6261197548326263, "percentage": 13.13, "elapsed_time": "0:20:02", "remaining_time": "2:12:35", "throughput": 4661.49, "total_tokens": 5605760} {"current_steps": 5575, "total_steps": 42420, "loss": 0.1525, "lr": 4.984997728459332e-05, "epoch": 2.6284771334276282, "percentage": 13.14, "elapsed_time": "0:20:03", "remaining_time": "2:12:34", "throughput": 4661.71, "total_tokens": 5610976} {"current_steps": 5580, "total_steps": 42420, "loss": 0.1203, "lr": 4.984885001244476e-05, "epoch": 2.6308345120226306, "percentage": 13.15, "elapsed_time": "0:20:04", "remaining_time": "2:12:33", "throughput": 4661.9, "total_tokens": 5616352} {"current_steps": 5585, "total_steps": 42420, "loss": 0.1216, "lr": 4.9847718533807797e-05, "epoch": 2.633191890617633, "percentage": 13.17, "elapsed_time": "0:20:05", "remaining_time": "2:12:32", "throughput": 4661.79, "total_tokens": 5621312} {"current_steps": 5590, "total_steps": 42420, "loss": 0.0769, "lr": 4.9846582848873965e-05, "epoch": 2.6355492692126354, "percentage": 13.18, "elapsed_time": "0:20:06", "remaining_time": "2:12:32", "throughput": 4662.02, "total_tokens": 5626880} {"current_steps": 5595, "total_steps": 42420, "loss": 0.2171, "lr": 4.984544295783554e-05, "epoch": 2.637906647807638, "percentage": 13.19, "elapsed_time": "0:20:08", "remaining_time": "2:12:31", "throughput": 4662.26, "total_tokens": 5632192} {"current_steps": 5600, "total_steps": 42420, "loss": 0.092, "lr": 4.9844298860885474e-05, "epoch": 2.6402640264026402, "percentage": 13.2, "elapsed_time": "0:20:09", "remaining_time": "2:12:30", "throughput": 4662.45, "total_tokens": 5637536} {"current_steps": 5605, "total_steps": 42420, "loss": 0.1205, "lr": 4.984315055821744e-05, "epoch": 2.6426214049976426, "percentage": 13.21, "elapsed_time": "0:20:10", "remaining_time": "2:12:29", "throughput": 4662.67, "total_tokens": 5642944} {"current_steps": 5610, "total_steps": 42420, "loss": 0.3221, "lr": 4.984199805002583e-05, "epoch": 2.644978783592645, "percentage": 13.22, "elapsed_time": "0:20:11", "remaining_time": "2:12:27", "throughput": 4662.76, "total_tokens": 5647808} {"current_steps": 5615, "total_steps": 42420, "loss": 0.1417, "lr": 4.984084133650574e-05, "epoch": 2.6473361621876474, "percentage": 13.24, "elapsed_time": "0:20:12", "remaining_time": "2:12:26", "throughput": 4662.86, "total_tokens": 5652576} {"current_steps": 5620, "total_steps": 42420, "loss": 0.1971, "lr": 4.983968041785298e-05, "epoch": 2.64969354078265, "percentage": 13.25, "elapsed_time": "0:20:13", "remaining_time": "2:12:28", "throughput": 4661.85, "total_tokens": 5658592} {"current_steps": 5625, "total_steps": 42420, "loss": 0.121, "lr": 4.983851529426409e-05, "epoch": 2.6520509193776522, "percentage": 13.26, "elapsed_time": "0:20:14", "remaining_time": "2:12:25", "throughput": 4661.98, "total_tokens": 5663040} {"current_steps": 5630, "total_steps": 42420, "loss": 0.2426, "lr": 4.9837345965936296e-05, "epoch": 2.6544082979726547, "percentage": 13.27, "elapsed_time": "0:20:15", "remaining_time": "2:12:23", "throughput": 4662.14, "total_tokens": 5667456} {"current_steps": 5635, "total_steps": 42420, "loss": 0.0934, "lr": 4.983617243306754e-05, "epoch": 2.6567656765676566, "percentage": 13.28, "elapsed_time": "0:20:16", "remaining_time": "2:12:22", "throughput": 4662.34, "total_tokens": 5672736} {"current_steps": 5640, "total_steps": 42420, "loss": 0.0935, "lr": 4.983499469585648e-05, "epoch": 2.659123055162659, "percentage": 13.3, "elapsed_time": "0:20:17", "remaining_time": "2:12:21", "throughput": 4662.52, "total_tokens": 5678080} {"current_steps": 5645, "total_steps": 42420, "loss": 0.087, "lr": 4.9833812754502495e-05, "epoch": 2.6614804337576614, "percentage": 13.31, "elapsed_time": "0:20:18", "remaining_time": "2:12:19", "throughput": 4662.44, "total_tokens": 5682304} {"current_steps": 5650, "total_steps": 42420, "loss": 0.1478, "lr": 4.983262660920567e-05, "epoch": 2.663837812352664, "percentage": 13.32, "elapsed_time": "0:20:19", "remaining_time": "2:12:19", "throughput": 4662.68, "total_tokens": 5688032} {"current_steps": 5655, "total_steps": 42420, "loss": 0.2607, "lr": 4.9831436260166783e-05, "epoch": 2.666195190947666, "percentage": 13.33, "elapsed_time": "0:20:20", "remaining_time": "2:12:16", "throughput": 4662.65, "total_tokens": 5692256} {"current_steps": 5660, "total_steps": 42420, "loss": 0.0676, "lr": 4.9830241707587365e-05, "epoch": 2.6685525695426686, "percentage": 13.34, "elapsed_time": "0:20:21", "remaining_time": "2:12:14", "throughput": 4662.6, "total_tokens": 5696448} {"current_steps": 5665, "total_steps": 42420, "loss": 0.2864, "lr": 4.982904295166961e-05, "epoch": 2.670909948137671, "percentage": 13.35, "elapsed_time": "0:20:22", "remaining_time": "2:12:13", "throughput": 4662.69, "total_tokens": 5701088} {"current_steps": 5670, "total_steps": 42420, "loss": 0.1283, "lr": 4.982783999261647e-05, "epoch": 2.6732673267326734, "percentage": 13.37, "elapsed_time": "0:20:23", "remaining_time": "2:12:12", "throughput": 4663.01, "total_tokens": 5707008} {"current_steps": 5675, "total_steps": 42420, "loss": 0.2287, "lr": 4.982663283063155e-05, "epoch": 2.6756247053276754, "percentage": 13.38, "elapsed_time": "0:20:24", "remaining_time": "2:12:10", "throughput": 4663.08, "total_tokens": 5711648} {"current_steps": 5680, "total_steps": 42420, "loss": 0.2661, "lr": 4.9825421465919244e-05, "epoch": 2.677982083922678, "percentage": 13.39, "elapsed_time": "0:20:25", "remaining_time": "2:12:09", "throughput": 4663.19, "total_tokens": 5716384} {"current_steps": 5685, "total_steps": 42420, "loss": 0.1101, "lr": 4.9824205898684586e-05, "epoch": 2.68033946251768, "percentage": 13.4, "elapsed_time": "0:20:26", "remaining_time": "2:12:07", "throughput": 4663.29, "total_tokens": 5721408} {"current_steps": 5690, "total_steps": 42420, "loss": 0.1255, "lr": 4.982298612913335e-05, "epoch": 2.6826968411126826, "percentage": 13.41, "elapsed_time": "0:20:28", "remaining_time": "2:12:08", "throughput": 4663.36, "total_tokens": 5727552} {"current_steps": 5695, "total_steps": 42420, "loss": 0.0974, "lr": 4.982176215747205e-05, "epoch": 2.685054219707685, "percentage": 13.43, "elapsed_time": "0:20:29", "remaining_time": "2:12:05", "throughput": 4663.22, "total_tokens": 5731424} {"current_steps": 5700, "total_steps": 42420, "loss": 0.129, "lr": 4.982053398390786e-05, "epoch": 2.6874115983026874, "percentage": 13.44, "elapsed_time": "0:20:30", "remaining_time": "2:12:05", "throughput": 4663.51, "total_tokens": 5737504} {"current_steps": 5705, "total_steps": 42420, "loss": 0.1904, "lr": 4.981930160864869e-05, "epoch": 2.68976897689769, "percentage": 13.45, "elapsed_time": "0:20:31", "remaining_time": "2:12:03", "throughput": 4663.32, "total_tokens": 5741600} {"current_steps": 5710, "total_steps": 42420, "loss": 0.0432, "lr": 4.981806503190318e-05, "epoch": 2.692126355492692, "percentage": 13.46, "elapsed_time": "0:20:32", "remaining_time": "2:12:02", "throughput": 4663.34, "total_tokens": 5746528} {"current_steps": 5715, "total_steps": 42420, "loss": 0.1403, "lr": 4.9816824253880636e-05, "epoch": 2.6944837340876946, "percentage": 13.47, "elapsed_time": "0:20:33", "remaining_time": "2:12:00", "throughput": 4663.3, "total_tokens": 5751040} {"current_steps": 5720, "total_steps": 42420, "loss": 0.2384, "lr": 4.9815579274791116e-05, "epoch": 2.696841112682697, "percentage": 13.48, "elapsed_time": "0:20:34", "remaining_time": "2:12:00", "throughput": 4663.54, "total_tokens": 5756736} {"current_steps": 5725, "total_steps": 42420, "loss": 0.2188, "lr": 4.9814330094845366e-05, "epoch": 2.6991984912776994, "percentage": 13.5, "elapsed_time": "0:20:35", "remaining_time": "2:11:58", "throughput": 4663.58, "total_tokens": 5761376} {"current_steps": 5730, "total_steps": 42420, "loss": 0.1931, "lr": 4.981307671425485e-05, "epoch": 2.701555869872702, "percentage": 13.51, "elapsed_time": "0:20:36", "remaining_time": "2:11:56", "throughput": 4663.74, "total_tokens": 5766272} {"current_steps": 5735, "total_steps": 42420, "loss": 0.2924, "lr": 4.981181913323175e-05, "epoch": 2.7039132484677038, "percentage": 13.52, "elapsed_time": "0:20:37", "remaining_time": "2:11:55", "throughput": 4663.87, "total_tokens": 5770944} {"current_steps": 5740, "total_steps": 42420, "loss": 0.0651, "lr": 4.9810557351988955e-05, "epoch": 2.706270627062706, "percentage": 13.53, "elapsed_time": "0:20:38", "remaining_time": "2:11:54", "throughput": 4664.0, "total_tokens": 5776288} {"current_steps": 5745, "total_steps": 42420, "loss": 0.2447, "lr": 4.9809291370740066e-05, "epoch": 2.7086280056577086, "percentage": 13.54, "elapsed_time": "0:20:39", "remaining_time": "2:11:51", "throughput": 4664.1, "total_tokens": 5780544} {"current_steps": 5750, "total_steps": 42420, "loss": 0.2215, "lr": 4.980802118969937e-05, "epoch": 2.710985384252711, "percentage": 13.55, "elapsed_time": "0:20:40", "remaining_time": "2:11:50", "throughput": 4664.23, "total_tokens": 5785600} {"current_steps": 5755, "total_steps": 42420, "loss": 0.0786, "lr": 4.980674680908192e-05, "epoch": 2.7133427628477134, "percentage": 13.57, "elapsed_time": "0:20:41", "remaining_time": "2:11:48", "throughput": 4664.28, "total_tokens": 5790080} {"current_steps": 5760, "total_steps": 42420, "loss": 0.1321, "lr": 4.9805468229103414e-05, "epoch": 2.7157001414427158, "percentage": 13.58, "elapsed_time": "0:20:42", "remaining_time": "2:11:46", "throughput": 4664.12, "total_tokens": 5794368} {"current_steps": 5765, "total_steps": 42420, "loss": 0.4667, "lr": 4.980418544998032e-05, "epoch": 2.718057520037718, "percentage": 13.59, "elapsed_time": "0:20:43", "remaining_time": "2:11:44", "throughput": 4664.17, "total_tokens": 5798784} {"current_steps": 5770, "total_steps": 42420, "loss": 0.0542, "lr": 4.980289847192978e-05, "epoch": 2.7204148986327206, "percentage": 13.6, "elapsed_time": "0:20:44", "remaining_time": "2:11:43", "throughput": 4664.25, "total_tokens": 5803456} {"current_steps": 5775, "total_steps": 42420, "loss": 0.1967, "lr": 4.980160729516965e-05, "epoch": 2.7227722772277225, "percentage": 13.61, "elapsed_time": "0:20:45", "remaining_time": "2:11:42", "throughput": 4664.51, "total_tokens": 5809088} {"current_steps": 5780, "total_steps": 42420, "loss": 0.1306, "lr": 4.980031191991852e-05, "epoch": 2.725129655822725, "percentage": 13.63, "elapsed_time": "0:20:46", "remaining_time": "2:11:42", "throughput": 4664.81, "total_tokens": 5815488} {"current_steps": 5785, "total_steps": 42420, "loss": 0.1076, "lr": 4.979901234639567e-05, "epoch": 2.7274870344177273, "percentage": 13.64, "elapsed_time": "0:20:47", "remaining_time": "2:11:41", "throughput": 4664.95, "total_tokens": 5820512} {"current_steps": 5790, "total_steps": 42420, "loss": 0.1246, "lr": 4.979770857482108e-05, "epoch": 2.7298444130127297, "percentage": 13.65, "elapsed_time": "0:20:48", "remaining_time": "2:11:39", "throughput": 4665.05, "total_tokens": 5824864} {"current_steps": 5795, "total_steps": 42420, "loss": 0.1315, "lr": 4.979640060541548e-05, "epoch": 2.732201791607732, "percentage": 13.66, "elapsed_time": "0:20:49", "remaining_time": "2:11:37", "throughput": 4665.16, "total_tokens": 5829312} {"current_steps": 5800, "total_steps": 42420, "loss": 0.1425, "lr": 4.979508843840027e-05, "epoch": 2.7345591702027345, "percentage": 13.67, "elapsed_time": "0:20:50", "remaining_time": "2:11:35", "throughput": 4665.31, "total_tokens": 5833824} {"current_steps": 5805, "total_steps": 42420, "loss": 0.0716, "lr": 4.979377207399759e-05, "epoch": 2.736916548797737, "percentage": 13.68, "elapsed_time": "0:20:51", "remaining_time": "2:11:34", "throughput": 4665.48, "total_tokens": 5839488} {"current_steps": 5810, "total_steps": 42420, "loss": 0.1054, "lr": 4.979245151243027e-05, "epoch": 2.7392739273927393, "percentage": 13.7, "elapsed_time": "0:20:52", "remaining_time": "2:11:33", "throughput": 4665.58, "total_tokens": 5844288} {"current_steps": 5815, "total_steps": 42420, "loss": 0.103, "lr": 4.9791126753921864e-05, "epoch": 2.7416313059877417, "percentage": 13.71, "elapsed_time": "0:20:53", "remaining_time": "2:11:31", "throughput": 4665.67, "total_tokens": 5848736} {"current_steps": 5820, "total_steps": 42420, "loss": 0.3742, "lr": 4.9789797798696627e-05, "epoch": 2.743988684582744, "percentage": 13.72, "elapsed_time": "0:20:54", "remaining_time": "2:11:29", "throughput": 4665.87, "total_tokens": 5853856} {"current_steps": 5825, "total_steps": 42420, "loss": 0.1089, "lr": 4.978846464697953e-05, "epoch": 2.7463460631777465, "percentage": 13.73, "elapsed_time": "0:20:55", "remaining_time": "2:11:29", "throughput": 4666.16, "total_tokens": 5859712} {"current_steps": 5830, "total_steps": 42420, "loss": 0.1408, "lr": 4.978712729899624e-05, "epoch": 2.748703441772749, "percentage": 13.74, "elapsed_time": "0:20:56", "remaining_time": "2:11:27", "throughput": 4666.33, "total_tokens": 5864448} {"current_steps": 5835, "total_steps": 42420, "loss": 0.0986, "lr": 4.978578575497317e-05, "epoch": 2.751060820367751, "percentage": 13.76, "elapsed_time": "0:20:57", "remaining_time": "2:11:26", "throughput": 4666.45, "total_tokens": 5869408} {"current_steps": 5840, "total_steps": 42420, "loss": 0.1857, "lr": 4.9784440015137414e-05, "epoch": 2.7534181989627533, "percentage": 13.77, "elapsed_time": "0:20:58", "remaining_time": "2:11:25", "throughput": 4666.62, "total_tokens": 5874816} {"current_steps": 5845, "total_steps": 42420, "loss": 0.2596, "lr": 4.978309007971678e-05, "epoch": 2.7557755775577557, "percentage": 13.78, "elapsed_time": "0:21:00", "remaining_time": "2:11:26", "throughput": 4666.9, "total_tokens": 5881536} {"current_steps": 5850, "total_steps": 42420, "loss": 0.097, "lr": 4.978173594893978e-05, "epoch": 2.758132956152758, "percentage": 13.79, "elapsed_time": "0:21:01", "remaining_time": "2:11:24", "throughput": 4667.04, "total_tokens": 5886336} {"current_steps": 5855, "total_steps": 42420, "loss": 0.2139, "lr": 4.978037762303566e-05, "epoch": 2.7604903347477605, "percentage": 13.8, "elapsed_time": "0:21:02", "remaining_time": "2:11:22", "throughput": 4667.21, "total_tokens": 5891200} {"current_steps": 5860, "total_steps": 42420, "loss": 0.1234, "lr": 4.977901510223435e-05, "epoch": 2.762847713342763, "percentage": 13.81, "elapsed_time": "0:21:03", "remaining_time": "2:11:21", "throughput": 4667.42, "total_tokens": 5896128} {"current_steps": 5865, "total_steps": 42420, "loss": 0.0868, "lr": 4.9777648386766506e-05, "epoch": 2.7652050919377653, "percentage": 13.83, "elapsed_time": "0:21:04", "remaining_time": "2:11:19", "throughput": 4667.44, "total_tokens": 5900480} {"current_steps": 5870, "total_steps": 42420, "loss": 0.0693, "lr": 4.977627747686349e-05, "epoch": 2.7675624705327677, "percentage": 13.84, "elapsed_time": "0:21:05", "remaining_time": "2:11:17", "throughput": 4667.62, "total_tokens": 5905120} {"current_steps": 5875, "total_steps": 42420, "loss": 0.0877, "lr": 4.977490237275738e-05, "epoch": 2.7699198491277697, "percentage": 13.85, "elapsed_time": "0:21:06", "remaining_time": "2:11:15", "throughput": 4667.82, "total_tokens": 5909984} {"current_steps": 5880, "total_steps": 42420, "loss": 0.0842, "lr": 4.977352307468095e-05, "epoch": 2.772277227722772, "percentage": 13.86, "elapsed_time": "0:21:07", "remaining_time": "2:11:14", "throughput": 4667.94, "total_tokens": 5914848} {"current_steps": 5885, "total_steps": 42420, "loss": 0.3234, "lr": 4.9772139582867695e-05, "epoch": 2.7746346063177745, "percentage": 13.87, "elapsed_time": "0:21:08", "remaining_time": "2:11:12", "throughput": 4668.07, "total_tokens": 5919872} {"current_steps": 5890, "total_steps": 42420, "loss": 0.1614, "lr": 4.9770751897551816e-05, "epoch": 2.776991984912777, "percentage": 13.88, "elapsed_time": "0:21:09", "remaining_time": "2:11:11", "throughput": 4668.22, "total_tokens": 5924672} {"current_steps": 5895, "total_steps": 42420, "loss": 0.1484, "lr": 4.976936001896823e-05, "epoch": 2.7793493635077793, "percentage": 13.9, "elapsed_time": "0:21:10", "remaining_time": "2:11:10", "throughput": 4668.49, "total_tokens": 5930496} {"current_steps": 5900, "total_steps": 42420, "loss": 0.2859, "lr": 4.976796394735254e-05, "epoch": 2.7817067421027817, "percentage": 13.91, "elapsed_time": "0:21:11", "remaining_time": "2:11:09", "throughput": 4668.72, "total_tokens": 5935808} {"current_steps": 5905, "total_steps": 42420, "loss": 0.2071, "lr": 4.9766563682941094e-05, "epoch": 2.784064120697784, "percentage": 13.92, "elapsed_time": "0:21:12", "remaining_time": "2:11:07", "throughput": 4668.75, "total_tokens": 5940352} {"current_steps": 5910, "total_steps": 42420, "loss": 0.3465, "lr": 4.976515922597094e-05, "epoch": 2.7864214992927865, "percentage": 13.93, "elapsed_time": "0:21:13", "remaining_time": "2:11:06", "throughput": 4668.87, "total_tokens": 5945184} {"current_steps": 5915, "total_steps": 42420, "loss": 0.2187, "lr": 4.97637505766798e-05, "epoch": 2.788778877887789, "percentage": 13.94, "elapsed_time": "0:21:14", "remaining_time": "2:11:05", "throughput": 4669.07, "total_tokens": 5950208} {"current_steps": 5920, "total_steps": 42420, "loss": 0.2417, "lr": 4.976233773530616e-05, "epoch": 2.7911362564827913, "percentage": 13.96, "elapsed_time": "0:21:15", "remaining_time": "2:11:04", "throughput": 4669.36, "total_tokens": 5956224} {"current_steps": 5925, "total_steps": 42420, "loss": 0.2026, "lr": 4.9760920702089186e-05, "epoch": 2.7934936350777937, "percentage": 13.97, "elapsed_time": "0:21:16", "remaining_time": "2:11:03", "throughput": 4669.55, "total_tokens": 5961408} {"current_steps": 5930, "total_steps": 42420, "loss": 0.1109, "lr": 4.9759499477268745e-05, "epoch": 2.795851013672796, "percentage": 13.98, "elapsed_time": "0:21:17", "remaining_time": "2:11:01", "throughput": 4669.61, "total_tokens": 5966144} {"current_steps": 5935, "total_steps": 42420, "loss": 0.1546, "lr": 4.9758074061085444e-05, "epoch": 2.798208392267798, "percentage": 13.99, "elapsed_time": "0:21:18", "remaining_time": "2:11:01", "throughput": 4669.74, "total_tokens": 5971712} {"current_steps": 5940, "total_steps": 42420, "loss": 0.2747, "lr": 4.9756644453780565e-05, "epoch": 2.8005657708628005, "percentage": 14.0, "elapsed_time": "0:21:19", "remaining_time": "2:11:00", "throughput": 4669.87, "total_tokens": 5976736} {"current_steps": 5945, "total_steps": 42420, "loss": 0.2302, "lr": 4.975521065559613e-05, "epoch": 2.802923149457803, "percentage": 14.01, "elapsed_time": "0:21:20", "remaining_time": "2:10:59", "throughput": 4670.02, "total_tokens": 5982176} {"current_steps": 5950, "total_steps": 42420, "loss": 0.2952, "lr": 4.9753772666774844e-05, "epoch": 2.8052805280528053, "percentage": 14.03, "elapsed_time": "0:21:21", "remaining_time": "2:10:57", "throughput": 4670.13, "total_tokens": 5987072} {"current_steps": 5955, "total_steps": 42420, "loss": 0.132, "lr": 4.9752330487560144e-05, "epoch": 2.8076379066478077, "percentage": 14.04, "elapsed_time": "0:21:23", "remaining_time": "2:10:57", "throughput": 4670.25, "total_tokens": 5992736} {"current_steps": 5960, "total_steps": 42420, "loss": 0.1054, "lr": 4.9750884118196165e-05, "epoch": 2.80999528524281, "percentage": 14.05, "elapsed_time": "0:21:24", "remaining_time": "2:10:57", "throughput": 4670.38, "total_tokens": 5998464} {"current_steps": 5965, "total_steps": 42420, "loss": 0.0567, "lr": 4.974943355892775e-05, "epoch": 2.8123526638378125, "percentage": 14.06, "elapsed_time": "0:21:25", "remaining_time": "2:10:55", "throughput": 4670.59, "total_tokens": 6003584} {"current_steps": 5970, "total_steps": 42420, "loss": 0.1338, "lr": 4.974797881000045e-05, "epoch": 2.814710042432815, "percentage": 14.07, "elapsed_time": "0:21:26", "remaining_time": "2:10:53", "throughput": 4670.67, "total_tokens": 6008160} {"current_steps": 5975, "total_steps": 42420, "loss": 0.1188, "lr": 4.974651987166054e-05, "epoch": 2.817067421027817, "percentage": 14.09, "elapsed_time": "0:21:27", "remaining_time": "2:10:52", "throughput": 4670.79, "total_tokens": 6012864} {"current_steps": 5980, "total_steps": 42420, "loss": 0.0551, "lr": 4.974505674415498e-05, "epoch": 2.8194247996228192, "percentage": 14.1, "elapsed_time": "0:21:28", "remaining_time": "2:10:51", "throughput": 4670.84, "total_tokens": 6018176} {"current_steps": 5985, "total_steps": 42420, "loss": 0.2008, "lr": 4.974358942773147e-05, "epoch": 2.8217821782178216, "percentage": 14.11, "elapsed_time": "0:21:29", "remaining_time": "2:10:51", "throughput": 4671.03, "total_tokens": 6024192} {"current_steps": 5990, "total_steps": 42420, "loss": 0.0746, "lr": 4.974211792263839e-05, "epoch": 2.824139556812824, "percentage": 14.12, "elapsed_time": "0:21:30", "remaining_time": "2:10:49", "throughput": 4671.17, "total_tokens": 6028960} {"current_steps": 5995, "total_steps": 42420, "loss": 0.2703, "lr": 4.974064222912484e-05, "epoch": 2.8264969354078264, "percentage": 14.13, "elapsed_time": "0:21:31", "remaining_time": "2:10:48", "throughput": 4671.38, "total_tokens": 6034464} {"current_steps": 6000, "total_steps": 42420, "loss": 0.1023, "lr": 4.973916234744064e-05, "epoch": 2.828854314002829, "percentage": 14.14, "elapsed_time": "0:21:32", "remaining_time": "2:10:47", "throughput": 4671.5, "total_tokens": 6039296} {"current_steps": 6005, "total_steps": 42420, "loss": 0.1123, "lr": 4.973767827783629e-05, "epoch": 2.8312116925978312, "percentage": 14.16, "elapsed_time": "0:21:33", "remaining_time": "2:10:45", "throughput": 4671.48, "total_tokens": 6043744} {"current_steps": 6010, "total_steps": 42420, "loss": 0.021, "lr": 4.973619002056303e-05, "epoch": 2.8335690711928336, "percentage": 14.17, "elapsed_time": "0:21:34", "remaining_time": "2:10:43", "throughput": 4671.62, "total_tokens": 6048384} {"current_steps": 6015, "total_steps": 42420, "loss": 0.1344, "lr": 4.9734697575872813e-05, "epoch": 2.835926449787836, "percentage": 14.18, "elapsed_time": "0:21:35", "remaining_time": "2:10:42", "throughput": 4671.77, "total_tokens": 6053824} {"current_steps": 6020, "total_steps": 42420, "loss": 0.2385, "lr": 4.9733200944018254e-05, "epoch": 2.8382838283828384, "percentage": 14.19, "elapsed_time": "0:21:36", "remaining_time": "2:10:41", "throughput": 4671.9, "total_tokens": 6058592} {"current_steps": 6025, "total_steps": 42420, "loss": 0.1833, "lr": 4.9731700125252724e-05, "epoch": 2.840641206977841, "percentage": 14.2, "elapsed_time": "0:21:37", "remaining_time": "2:10:39", "throughput": 4672.07, "total_tokens": 6063680} {"current_steps": 6030, "total_steps": 42420, "loss": 0.3052, "lr": 4.973019511983028e-05, "epoch": 2.8429985855728432, "percentage": 14.21, "elapsed_time": "0:21:38", "remaining_time": "2:10:38", "throughput": 4672.27, "total_tokens": 6069056} {"current_steps": 6035, "total_steps": 42420, "loss": 0.0816, "lr": 4.97286859280057e-05, "epoch": 2.845355964167845, "percentage": 14.23, "elapsed_time": "0:21:40", "remaining_time": "2:10:39", "throughput": 4672.42, "total_tokens": 6075168} {"current_steps": 6040, "total_steps": 42420, "loss": 0.1032, "lr": 4.972717255003446e-05, "epoch": 2.8477133427628476, "percentage": 14.24, "elapsed_time": "0:21:41", "remaining_time": "2:10:39", "throughput": 4672.68, "total_tokens": 6081728} {"current_steps": 6045, "total_steps": 42420, "loss": 0.1496, "lr": 4.972565498617276e-05, "epoch": 2.85007072135785, "percentage": 14.25, "elapsed_time": "0:21:42", "remaining_time": "2:10:37", "throughput": 4672.83, "total_tokens": 6086592} {"current_steps": 6050, "total_steps": 42420, "loss": 0.3393, "lr": 4.9724133236677476e-05, "epoch": 2.8524280999528524, "percentage": 14.26, "elapsed_time": "0:21:43", "remaining_time": "2:10:35", "throughput": 4672.9, "total_tokens": 6091008} {"current_steps": 6055, "total_steps": 42420, "loss": 0.2521, "lr": 4.9722607301806224e-05, "epoch": 2.854785478547855, "percentage": 14.27, "elapsed_time": "0:21:44", "remaining_time": "2:10:35", "throughput": 4673.11, "total_tokens": 6096928} {"current_steps": 6060, "total_steps": 42420, "loss": 0.1734, "lr": 4.9721077181817334e-05, "epoch": 2.857142857142857, "percentage": 14.29, "elapsed_time": "0:21:45", "remaining_time": "2:10:34", "throughput": 4673.34, "total_tokens": 6101888} {"current_steps": 6065, "total_steps": 42420, "loss": 0.0548, "lr": 4.971954287696981e-05, "epoch": 2.8595002357378596, "percentage": 14.3, "elapsed_time": "0:21:46", "remaining_time": "2:10:33", "throughput": 4673.53, "total_tokens": 6107680} {"current_steps": 6070, "total_steps": 42420, "loss": 0.1269, "lr": 4.971800438752339e-05, "epoch": 2.861857614332862, "percentage": 14.31, "elapsed_time": "0:21:47", "remaining_time": "2:10:32", "throughput": 4673.62, "total_tokens": 6112608} {"current_steps": 6075, "total_steps": 42420, "loss": 0.0706, "lr": 4.971646171373852e-05, "epoch": 2.864214992927864, "percentage": 14.32, "elapsed_time": "0:21:48", "remaining_time": "2:10:30", "throughput": 4673.72, "total_tokens": 6117536} {"current_steps": 6080, "total_steps": 42420, "loss": 0.2016, "lr": 4.9714914855876336e-05, "epoch": 2.8665723715228664, "percentage": 14.33, "elapsed_time": "0:21:49", "remaining_time": "2:10:29", "throughput": 4673.9, "total_tokens": 6122400} {"current_steps": 6085, "total_steps": 42420, "loss": 0.1609, "lr": 4.971336381419871e-05, "epoch": 2.8689297501178688, "percentage": 14.34, "elapsed_time": "0:21:50", "remaining_time": "2:10:27", "throughput": 4673.97, "total_tokens": 6126976} {"current_steps": 6090, "total_steps": 42420, "loss": 0.1109, "lr": 4.97118085889682e-05, "epoch": 2.871287128712871, "percentage": 14.36, "elapsed_time": "0:21:52", "remaining_time": "2:10:26", "throughput": 4674.27, "total_tokens": 6132704} {"current_steps": 6095, "total_steps": 42420, "loss": 0.159, "lr": 4.9710249180448075e-05, "epoch": 2.8736445073078736, "percentage": 14.37, "elapsed_time": "0:21:52", "remaining_time": "2:10:24", "throughput": 4674.27, "total_tokens": 6137024} {"current_steps": 6100, "total_steps": 42420, "loss": 0.1284, "lr": 4.970868558890232e-05, "epoch": 2.876001885902876, "percentage": 14.38, "elapsed_time": "0:21:54", "remaining_time": "2:10:24", "throughput": 4674.49, "total_tokens": 6142784} {"current_steps": 6105, "total_steps": 42420, "loss": 0.2579, "lr": 4.970711781459563e-05, "epoch": 2.8783592644978784, "percentage": 14.39, "elapsed_time": "0:21:55", "remaining_time": "2:10:23", "throughput": 4674.72, "total_tokens": 6148672} {"current_steps": 6110, "total_steps": 42420, "loss": 0.1125, "lr": 4.9705545857793386e-05, "epoch": 2.880716643092881, "percentage": 14.4, "elapsed_time": "0:21:56", "remaining_time": "2:10:23", "throughput": 4674.89, "total_tokens": 6154208} {"current_steps": 6115, "total_steps": 42420, "loss": 0.2309, "lr": 4.970396971876171e-05, "epoch": 2.883074021687883, "percentage": 14.42, "elapsed_time": "0:21:57", "remaining_time": "2:10:22", "throughput": 4674.92, "total_tokens": 6159232} {"current_steps": 6120, "total_steps": 42420, "loss": 0.0857, "lr": 4.9702389397767414e-05, "epoch": 2.8854314002828856, "percentage": 14.43, "elapsed_time": "0:21:58", "remaining_time": "2:10:21", "throughput": 4675.15, "total_tokens": 6164768} {"current_steps": 6125, "total_steps": 42420, "loss": 0.4121, "lr": 4.970080489507801e-05, "epoch": 2.887788778877888, "percentage": 14.44, "elapsed_time": "0:21:59", "remaining_time": "2:10:19", "throughput": 4675.2, "total_tokens": 6169248} {"current_steps": 6130, "total_steps": 42420, "loss": 0.0831, "lr": 4.969921621096174e-05, "epoch": 2.8901461574728904, "percentage": 14.45, "elapsed_time": "0:22:00", "remaining_time": "2:10:17", "throughput": 4675.34, "total_tokens": 6174016} {"current_steps": 6135, "total_steps": 42420, "loss": 0.229, "lr": 4.969762334568753e-05, "epoch": 2.8925035360678923, "percentage": 14.46, "elapsed_time": "0:22:01", "remaining_time": "2:10:17", "throughput": 4675.49, "total_tokens": 6179616} {"current_steps": 6140, "total_steps": 42420, "loss": 0.1896, "lr": 4.9696026299525024e-05, "epoch": 2.8948609146628947, "percentage": 14.47, "elapsed_time": "0:22:02", "remaining_time": "2:10:15", "throughput": 4675.46, "total_tokens": 6184352} {"current_steps": 6145, "total_steps": 42420, "loss": 0.2158, "lr": 4.969442507274459e-05, "epoch": 2.897218293257897, "percentage": 14.49, "elapsed_time": "0:22:03", "remaining_time": "2:10:13", "throughput": 4675.45, "total_tokens": 6188608} {"current_steps": 6150, "total_steps": 42420, "loss": 0.2206, "lr": 4.9692819665617265e-05, "epoch": 2.8995756718528995, "percentage": 14.5, "elapsed_time": "0:22:04", "remaining_time": "2:10:12", "throughput": 4675.5, "total_tokens": 6193440} {"current_steps": 6155, "total_steps": 42420, "loss": 0.0911, "lr": 4.969121007841484e-05, "epoch": 2.901933050447902, "percentage": 14.51, "elapsed_time": "0:22:05", "remaining_time": "2:10:11", "throughput": 4675.66, "total_tokens": 6199296} {"current_steps": 6160, "total_steps": 42420, "loss": 0.048, "lr": 4.968959631140978e-05, "epoch": 2.9042904290429044, "percentage": 14.52, "elapsed_time": "0:22:07", "remaining_time": "2:10:11", "throughput": 4675.74, "total_tokens": 6204800} {"current_steps": 6165, "total_steps": 42420, "loss": 0.1502, "lr": 4.9687978364875274e-05, "epoch": 2.9066478076379068, "percentage": 14.53, "elapsed_time": "0:22:08", "remaining_time": "2:10:10", "throughput": 4675.93, "total_tokens": 6210144} {"current_steps": 6170, "total_steps": 42420, "loss": 0.1546, "lr": 4.9686356239085206e-05, "epoch": 2.909005186232909, "percentage": 14.55, "elapsed_time": "0:22:09", "remaining_time": "2:10:08", "throughput": 4676.03, "total_tokens": 6215040} {"current_steps": 6175, "total_steps": 42420, "loss": 0.2391, "lr": 4.968472993431418e-05, "epoch": 2.911362564827911, "percentage": 14.56, "elapsed_time": "0:22:10", "remaining_time": "2:10:07", "throughput": 4676.02, "total_tokens": 6219488} {"current_steps": 6180, "total_steps": 42420, "loss": 0.1847, "lr": 4.96830994508375e-05, "epoch": 2.9137199434229135, "percentage": 14.57, "elapsed_time": "0:22:11", "remaining_time": "2:10:05", "throughput": 4676.13, "total_tokens": 6224320} {"current_steps": 6185, "total_steps": 42420, "loss": 0.0577, "lr": 4.9681464788931166e-05, "epoch": 2.916077322017916, "percentage": 14.58, "elapsed_time": "0:22:12", "remaining_time": "2:10:05", "throughput": 4676.32, "total_tokens": 6230272} {"current_steps": 6190, "total_steps": 42420, "loss": 0.2073, "lr": 4.967982594887192e-05, "epoch": 2.9184347006129183, "percentage": 14.59, "elapsed_time": "0:22:13", "remaining_time": "2:10:03", "throughput": 4676.34, "total_tokens": 6234784} {"current_steps": 6195, "total_steps": 42420, "loss": 0.188, "lr": 4.967818293093718e-05, "epoch": 2.9207920792079207, "percentage": 14.6, "elapsed_time": "0:22:14", "remaining_time": "2:10:02", "throughput": 4676.45, "total_tokens": 6239904} {"current_steps": 6200, "total_steps": 42420, "loss": 0.2653, "lr": 4.9676535735405084e-05, "epoch": 2.923149457802923, "percentage": 14.62, "elapsed_time": "0:22:15", "remaining_time": "2:10:01", "throughput": 4676.67, "total_tokens": 6245344} {"current_steps": 6205, "total_steps": 42420, "loss": 0.1254, "lr": 4.9674884362554466e-05, "epoch": 2.9255068363979255, "percentage": 14.63, "elapsed_time": "0:22:16", "remaining_time": "2:09:59", "throughput": 4676.53, "total_tokens": 6249440} {"current_steps": 6210, "total_steps": 42420, "loss": 0.2433, "lr": 4.9673228812664884e-05, "epoch": 2.927864214992928, "percentage": 14.64, "elapsed_time": "0:22:17", "remaining_time": "2:09:58", "throughput": 4676.62, "total_tokens": 6254432} {"current_steps": 6215, "total_steps": 42420, "loss": 0.0563, "lr": 4.967156908601659e-05, "epoch": 2.9302215935879303, "percentage": 14.65, "elapsed_time": "0:22:18", "remaining_time": "2:09:57", "throughput": 4676.7, "total_tokens": 6259520} {"current_steps": 6220, "total_steps": 42420, "loss": 0.1161, "lr": 4.966990518289055e-05, "epoch": 2.9325789721829327, "percentage": 14.66, "elapsed_time": "0:22:19", "remaining_time": "2:09:55", "throughput": 4676.9, "total_tokens": 6264448} {"current_steps": 6225, "total_steps": 42420, "loss": 0.0765, "lr": 4.966823710356844e-05, "epoch": 2.934936350777935, "percentage": 14.67, "elapsed_time": "0:22:20", "remaining_time": "2:09:54", "throughput": 4677.05, "total_tokens": 6269664} {"current_steps": 6230, "total_steps": 42420, "loss": 0.1116, "lr": 4.966656484833262e-05, "epoch": 2.9372937293729375, "percentage": 14.69, "elapsed_time": "0:22:21", "remaining_time": "2:09:52", "throughput": 4677.14, "total_tokens": 6274400} {"current_steps": 6235, "total_steps": 42420, "loss": 0.3109, "lr": 4.966488841746619e-05, "epoch": 2.9396511079679395, "percentage": 14.7, "elapsed_time": "0:22:22", "remaining_time": "2:09:51", "throughput": 4677.22, "total_tokens": 6279296} {"current_steps": 6240, "total_steps": 42420, "loss": 0.2476, "lr": 4.9663207811252936e-05, "epoch": 2.942008486562942, "percentage": 14.71, "elapsed_time": "0:22:23", "remaining_time": "2:09:50", "throughput": 4677.2, "total_tokens": 6284224} {"current_steps": 6245, "total_steps": 42420, "loss": 0.0857, "lr": 4.9661523029977365e-05, "epoch": 2.9443658651579443, "percentage": 14.72, "elapsed_time": "0:22:24", "remaining_time": "2:09:48", "throughput": 4677.25, "total_tokens": 6288512} {"current_steps": 6250, "total_steps": 42420, "loss": 0.1525, "lr": 4.965983407392466e-05, "epoch": 2.9467232437529467, "percentage": 14.73, "elapsed_time": "0:22:25", "remaining_time": "2:09:47", "throughput": 4677.57, "total_tokens": 6294688} {"current_steps": 6255, "total_steps": 42420, "loss": 0.0602, "lr": 4.965814094338076e-05, "epoch": 2.949080622347949, "percentage": 14.75, "elapsed_time": "0:22:26", "remaining_time": "2:09:46", "throughput": 4677.63, "total_tokens": 6299392} {"current_steps": 6260, "total_steps": 42420, "loss": 0.1794, "lr": 4.965644363863226e-05, "epoch": 2.9514380009429515, "percentage": 14.76, "elapsed_time": "0:22:27", "remaining_time": "2:09:44", "throughput": 4677.72, "total_tokens": 6304160} {"current_steps": 6265, "total_steps": 42420, "loss": 0.1713, "lr": 4.96547421599665e-05, "epoch": 2.953795379537954, "percentage": 14.77, "elapsed_time": "0:22:29", "remaining_time": "2:09:45", "throughput": 4678.02, "total_tokens": 6311136} {"current_steps": 6270, "total_steps": 42420, "loss": 0.1328, "lr": 4.96530365076715e-05, "epoch": 2.9561527581329563, "percentage": 14.78, "elapsed_time": "0:22:30", "remaining_time": "2:09:43", "throughput": 4677.92, "total_tokens": 6315264} {"current_steps": 6275, "total_steps": 42420, "loss": 0.2936, "lr": 4.965132668203601e-05, "epoch": 2.9585101367279583, "percentage": 14.79, "elapsed_time": "0:22:31", "remaining_time": "2:09:42", "throughput": 4678.03, "total_tokens": 6320192} {"current_steps": 6280, "total_steps": 42420, "loss": 0.1535, "lr": 4.964961268334947e-05, "epoch": 2.9608675153229607, "percentage": 14.8, "elapsed_time": "0:22:31", "remaining_time": "2:09:40", "throughput": 4678.16, "total_tokens": 6324864} {"current_steps": 6285, "total_steps": 42420, "loss": 0.181, "lr": 4.9647894511902024e-05, "epoch": 2.963224893917963, "percentage": 14.82, "elapsed_time": "0:22:32", "remaining_time": "2:09:38", "throughput": 4678.26, "total_tokens": 6329536} {"current_steps": 6290, "total_steps": 42420, "loss": 0.1445, "lr": 4.964617216798454e-05, "epoch": 2.9655822725129655, "percentage": 14.83, "elapsed_time": "0:22:34", "remaining_time": "2:09:38", "throughput": 4678.52, "total_tokens": 6335424} {"current_steps": 6295, "total_steps": 42420, "loss": 0.0892, "lr": 4.964444565188857e-05, "epoch": 2.967939651107968, "percentage": 14.84, "elapsed_time": "0:22:35", "remaining_time": "2:09:36", "throughput": 4678.63, "total_tokens": 6340160} {"current_steps": 6300, "total_steps": 42420, "loss": 0.2841, "lr": 4.964271496390639e-05, "epoch": 2.9702970297029703, "percentage": 14.85, "elapsed_time": "0:22:36", "remaining_time": "2:09:34", "throughput": 4678.66, "total_tokens": 6344288} {"current_steps": 6305, "total_steps": 42420, "loss": 0.1226, "lr": 4.964098010433098e-05, "epoch": 2.9726544082979727, "percentage": 14.86, "elapsed_time": "0:22:36", "remaining_time": "2:09:32", "throughput": 4678.81, "total_tokens": 6349088} {"current_steps": 6310, "total_steps": 42420, "loss": 0.0651, "lr": 4.963924107345602e-05, "epoch": 2.975011786892975, "percentage": 14.88, "elapsed_time": "0:22:37", "remaining_time": "2:09:30", "throughput": 4678.78, "total_tokens": 6353248} {"current_steps": 6315, "total_steps": 42420, "loss": 0.0921, "lr": 4.963749787157589e-05, "epoch": 2.9773691654879775, "percentage": 14.89, "elapsed_time": "0:22:39", "remaining_time": "2:09:30", "throughput": 4678.93, "total_tokens": 6359200} {"current_steps": 6320, "total_steps": 42420, "loss": 0.0909, "lr": 4.96357504989857e-05, "epoch": 2.97972654408298, "percentage": 14.9, "elapsed_time": "0:22:40", "remaining_time": "2:09:29", "throughput": 4679.08, "total_tokens": 6364448} {"current_steps": 6325, "total_steps": 42420, "loss": 0.2525, "lr": 4.963399895598123e-05, "epoch": 2.9820839226779823, "percentage": 14.91, "elapsed_time": "0:22:41", "remaining_time": "2:09:27", "throughput": 4679.07, "total_tokens": 6368928} {"current_steps": 6330, "total_steps": 42420, "loss": 0.2307, "lr": 4.963224324285901e-05, "epoch": 2.9844413012729847, "percentage": 14.92, "elapsed_time": "0:22:42", "remaining_time": "2:09:26", "throughput": 4679.17, "total_tokens": 6374016} {"current_steps": 6335, "total_steps": 42420, "loss": 0.2064, "lr": 4.963048335991624e-05, "epoch": 2.9867986798679866, "percentage": 14.93, "elapsed_time": "0:22:43", "remaining_time": "2:09:25", "throughput": 4679.1, "total_tokens": 6378816} {"current_steps": 6340, "total_steps": 42420, "loss": 0.1297, "lr": 4.9628719307450835e-05, "epoch": 2.989156058462989, "percentage": 14.95, "elapsed_time": "0:22:44", "remaining_time": "2:09:24", "throughput": 4679.22, "total_tokens": 6384416} {"current_steps": 6345, "total_steps": 42420, "loss": 0.2136, "lr": 4.962695108576142e-05, "epoch": 2.9915134370579914, "percentage": 14.96, "elapsed_time": "0:22:45", "remaining_time": "2:09:22", "throughput": 4679.3, "total_tokens": 6388768} {"current_steps": 6350, "total_steps": 42420, "loss": 0.1228, "lr": 4.962517869514733e-05, "epoch": 2.993870815652994, "percentage": 14.97, "elapsed_time": "0:22:46", "remaining_time": "2:09:21", "throughput": 4679.22, "total_tokens": 6393312} {"current_steps": 6355, "total_steps": 42420, "loss": 0.1204, "lr": 4.96234021359086e-05, "epoch": 2.9962281942479962, "percentage": 14.98, "elapsed_time": "0:22:47", "remaining_time": "2:09:19", "throughput": 4679.35, "total_tokens": 6397728} {"current_steps": 6360, "total_steps": 42420, "loss": 0.1143, "lr": 4.962162140834596e-05, "epoch": 2.9985855728429986, "percentage": 14.99, "elapsed_time": "0:22:48", "remaining_time": "2:09:17", "throughput": 4679.35, "total_tokens": 6402080} {"current_steps": 6363, "total_steps": 42420, "eval_loss": 0.17026710510253906, "epoch": 3.0, "percentage": 15.0, "elapsed_time": "0:23:04", "remaining_time": "2:10:42", "throughput": 4627.7, "total_tokens": 6404896} {"current_steps": 6365, "total_steps": 42420, "loss": 0.152, "lr": 4.961983651276089e-05, "epoch": 3.000942951438001, "percentage": 15.0, "elapsed_time": "0:23:05", "remaining_time": "2:10:50", "throughput": 4622.94, "total_tokens": 6407104} {"current_steps": 6370, "total_steps": 42420, "loss": 0.4126, "lr": 4.9618047449455496e-05, "epoch": 3.0033003300330035, "percentage": 15.02, "elapsed_time": "0:23:06", "remaining_time": "2:10:48", "throughput": 4623.09, "total_tokens": 6411808} {"current_steps": 6375, "total_steps": 42420, "loss": 0.1451, "lr": 4.9616254218732674e-05, "epoch": 3.005657708628006, "percentage": 15.03, "elapsed_time": "0:23:08", "remaining_time": "2:10:49", "throughput": 4623.53, "total_tokens": 6418912} {"current_steps": 6380, "total_steps": 42420, "loss": 0.2506, "lr": 4.9614456820895974e-05, "epoch": 3.008015087223008, "percentage": 15.04, "elapsed_time": "0:23:09", "remaining_time": "2:10:49", "throughput": 4623.74, "total_tokens": 6424864} {"current_steps": 6385, "total_steps": 42420, "loss": 0.1241, "lr": 4.961265525624965e-05, "epoch": 3.01037246581801, "percentage": 15.05, "elapsed_time": "0:23:10", "remaining_time": "2:10:48", "throughput": 4623.93, "total_tokens": 6430496} {"current_steps": 6390, "total_steps": 42420, "loss": 0.2899, "lr": 4.96108495250987e-05, "epoch": 3.0127298444130126, "percentage": 15.06, "elapsed_time": "0:23:11", "remaining_time": "2:10:47", "throughput": 4624.2, "total_tokens": 6436160} {"current_steps": 6395, "total_steps": 42420, "loss": 0.1618, "lr": 4.9609039627748794e-05, "epoch": 3.015087223008015, "percentage": 15.08, "elapsed_time": "0:23:13", "remaining_time": "2:10:50", "throughput": 4624.54, "total_tokens": 6444320} {"current_steps": 6400, "total_steps": 42420, "loss": 0.1042, "lr": 4.960722556450631e-05, "epoch": 3.0174446016030174, "percentage": 15.09, "elapsed_time": "0:23:14", "remaining_time": "2:10:48", "throughput": 4624.66, "total_tokens": 6449120} {"current_steps": 6405, "total_steps": 42420, "loss": 0.1729, "lr": 4.9605407335678354e-05, "epoch": 3.01980198019802, "percentage": 15.1, "elapsed_time": "0:23:15", "remaining_time": "2:10:46", "throughput": 4624.62, "total_tokens": 6453248} {"current_steps": 6410, "total_steps": 42420, "loss": 0.0778, "lr": 4.9603584941572704e-05, "epoch": 3.022159358793022, "percentage": 15.11, "elapsed_time": "0:23:16", "remaining_time": "2:10:44", "throughput": 4624.61, "total_tokens": 6457664} {"current_steps": 6415, "total_steps": 42420, "loss": 0.0968, "lr": 4.9601758382497875e-05, "epoch": 3.0245167373880246, "percentage": 15.12, "elapsed_time": "0:23:17", "remaining_time": "2:10:43", "throughput": 4624.88, "total_tokens": 6463520} {"current_steps": 6420, "total_steps": 42420, "loss": 0.4115, "lr": 4.959992765876306e-05, "epoch": 3.026874115983027, "percentage": 15.13, "elapsed_time": "0:23:18", "remaining_time": "2:10:42", "throughput": 4625.01, "total_tokens": 6468672} {"current_steps": 6425, "total_steps": 42420, "loss": 0.1014, "lr": 4.9598092770678186e-05, "epoch": 3.0292314945780294, "percentage": 15.15, "elapsed_time": "0:23:19", "remaining_time": "2:10:41", "throughput": 4625.2, "total_tokens": 6474048} {"current_steps": 6430, "total_steps": 42420, "loss": 0.1433, "lr": 4.959625371855384e-05, "epoch": 3.0315888731730314, "percentage": 15.16, "elapsed_time": "0:23:20", "remaining_time": "2:10:41", "throughput": 4625.49, "total_tokens": 6479936} {"current_steps": 6435, "total_steps": 42420, "loss": 0.0506, "lr": 4.959441050270138e-05, "epoch": 3.033946251768034, "percentage": 15.17, "elapsed_time": "0:23:22", "remaining_time": "2:10:41", "throughput": 4625.9, "total_tokens": 6486528} {"current_steps": 6440, "total_steps": 42420, "loss": 0.0895, "lr": 4.95925631234328e-05, "epoch": 3.036303630363036, "percentage": 15.18, "elapsed_time": "0:23:23", "remaining_time": "2:10:41", "throughput": 4626.16, "total_tokens": 6492928} {"current_steps": 6445, "total_steps": 42420, "loss": 0.0746, "lr": 4.9590711581060844e-05, "epoch": 3.0386610089580386, "percentage": 15.19, "elapsed_time": "0:23:24", "remaining_time": "2:10:39", "throughput": 4626.01, "total_tokens": 6496992} {"current_steps": 6450, "total_steps": 42420, "loss": 0.332, "lr": 4.958885587589894e-05, "epoch": 3.041018387553041, "percentage": 15.21, "elapsed_time": "0:23:25", "remaining_time": "2:10:38", "throughput": 4626.14, "total_tokens": 6502368} {"current_steps": 6455, "total_steps": 42420, "loss": 0.4023, "lr": 4.9586996008261235e-05, "epoch": 3.0433757661480434, "percentage": 15.22, "elapsed_time": "0:23:26", "remaining_time": "2:10:37", "throughput": 4626.44, "total_tokens": 6507840} {"current_steps": 6460, "total_steps": 42420, "loss": 0.2802, "lr": 4.958513197846257e-05, "epoch": 3.045733144743046, "percentage": 15.23, "elapsed_time": "0:23:27", "remaining_time": "2:10:36", "throughput": 4626.56, "total_tokens": 6512832} {"current_steps": 6465, "total_steps": 42420, "loss": 0.2499, "lr": 4.958326378681849e-05, "epoch": 3.048090523338048, "percentage": 15.24, "elapsed_time": "0:23:28", "remaining_time": "2:10:35", "throughput": 4626.78, "total_tokens": 6518400} {"current_steps": 6470, "total_steps": 42420, "loss": 0.3188, "lr": 4.9581391433645254e-05, "epoch": 3.0504479019330506, "percentage": 15.25, "elapsed_time": "0:23:29", "remaining_time": "2:10:33", "throughput": 4626.92, "total_tokens": 6523200} {"current_steps": 6475, "total_steps": 42420, "loss": 0.1879, "lr": 4.9579514919259806e-05, "epoch": 3.052805280528053, "percentage": 15.26, "elapsed_time": "0:23:30", "remaining_time": "2:10:31", "throughput": 4627.04, "total_tokens": 6527904} {"current_steps": 6480, "total_steps": 42420, "loss": 0.0725, "lr": 4.957763424397983e-05, "epoch": 3.055162659123055, "percentage": 15.28, "elapsed_time": "0:23:31", "remaining_time": "2:10:29", "throughput": 4627.07, "total_tokens": 6532192} {"current_steps": 6485, "total_steps": 42420, "loss": 0.3633, "lr": 4.957574940812368e-05, "epoch": 3.0575200377180574, "percentage": 15.29, "elapsed_time": "0:23:32", "remaining_time": "2:10:28", "throughput": 4627.32, "total_tokens": 6537216} {"current_steps": 6490, "total_steps": 42420, "loss": 0.0302, "lr": 4.9573860412010426e-05, "epoch": 3.0598774163130598, "percentage": 15.3, "elapsed_time": "0:23:33", "remaining_time": "2:10:26", "throughput": 4627.34, "total_tokens": 6541664} {"current_steps": 6495, "total_steps": 42420, "loss": 0.1029, "lr": 4.957196725595985e-05, "epoch": 3.062234794908062, "percentage": 15.31, "elapsed_time": "0:23:34", "remaining_time": "2:10:25", "throughput": 4627.48, "total_tokens": 6547008} {"current_steps": 6500, "total_steps": 42420, "loss": 0.2329, "lr": 4.957006994029241e-05, "epoch": 3.0645921735030646, "percentage": 15.32, "elapsed_time": "0:23:35", "remaining_time": "2:10:23", "throughput": 4627.56, "total_tokens": 6551552} {"current_steps": 6505, "total_steps": 42420, "loss": 0.4256, "lr": 4.9568168465329317e-05, "epoch": 3.066949552098067, "percentage": 15.33, "elapsed_time": "0:23:36", "remaining_time": "2:10:22", "throughput": 4627.76, "total_tokens": 6556640} {"current_steps": 6510, "total_steps": 42420, "loss": 0.232, "lr": 4.9566262831392446e-05, "epoch": 3.0693069306930694, "percentage": 15.35, "elapsed_time": "0:23:37", "remaining_time": "2:10:20", "throughput": 4627.9, "total_tokens": 6561152} {"current_steps": 6515, "total_steps": 42420, "loss": 0.2633, "lr": 4.956435303880439e-05, "epoch": 3.0716643092880718, "percentage": 15.36, "elapsed_time": "0:23:38", "remaining_time": "2:10:19", "throughput": 4628.12, "total_tokens": 6566560} {"current_steps": 6520, "total_steps": 42420, "loss": 0.1973, "lr": 4.956243908788844e-05, "epoch": 3.074021687883074, "percentage": 15.37, "elapsed_time": "0:23:39", "remaining_time": "2:10:18", "throughput": 4628.33, "total_tokens": 6571680} {"current_steps": 6525, "total_steps": 42420, "loss": 0.0817, "lr": 4.95605209789686e-05, "epoch": 3.0763790664780766, "percentage": 15.38, "elapsed_time": "0:23:40", "remaining_time": "2:10:16", "throughput": 4628.33, "total_tokens": 6576032} {"current_steps": 6530, "total_steps": 42420, "loss": 0.2144, "lr": 4.9558598712369574e-05, "epoch": 3.0787364450730785, "percentage": 15.39, "elapsed_time": "0:23:41", "remaining_time": "2:10:15", "throughput": 4628.43, "total_tokens": 6581280} {"current_steps": 6535, "total_steps": 42420, "loss": 0.1426, "lr": 4.955667228841676e-05, "epoch": 3.081093823668081, "percentage": 15.41, "elapsed_time": "0:23:42", "remaining_time": "2:10:13", "throughput": 4628.54, "total_tokens": 6585696} {"current_steps": 6540, "total_steps": 42420, "loss": 0.1965, "lr": 4.955474170743629e-05, "epoch": 3.0834512022630833, "percentage": 15.42, "elapsed_time": "0:23:43", "remaining_time": "2:10:12", "throughput": 4628.65, "total_tokens": 6591104} {"current_steps": 6545, "total_steps": 42420, "loss": 0.1529, "lr": 4.955280696975495e-05, "epoch": 3.0858085808580857, "percentage": 15.43, "elapsed_time": "0:23:45", "remaining_time": "2:10:11", "throughput": 4628.87, "total_tokens": 6596448} {"current_steps": 6550, "total_steps": 42420, "loss": 0.093, "lr": 4.955086807570028e-05, "epoch": 3.088165959453088, "percentage": 15.44, "elapsed_time": "0:23:45", "remaining_time": "2:10:08", "throughput": 4628.85, "total_tokens": 6600256} {"current_steps": 6555, "total_steps": 42420, "loss": 0.2642, "lr": 4.95489250256005e-05, "epoch": 3.0905233380480905, "percentage": 15.45, "elapsed_time": "0:23:47", "remaining_time": "2:10:07", "throughput": 4629.08, "total_tokens": 6605792} {"current_steps": 6560, "total_steps": 42420, "loss": 0.1107, "lr": 4.954697781978452e-05, "epoch": 3.092880716643093, "percentage": 15.46, "elapsed_time": "0:23:47", "remaining_time": "2:10:05", "throughput": 4629.12, "total_tokens": 6610048} {"current_steps": 6565, "total_steps": 42420, "loss": 0.0651, "lr": 4.954502645858199e-05, "epoch": 3.0952380952380953, "percentage": 15.48, "elapsed_time": "0:23:48", "remaining_time": "2:10:04", "throughput": 4629.24, "total_tokens": 6614848} {"current_steps": 6570, "total_steps": 42420, "loss": 0.0848, "lr": 4.954307094232322e-05, "epoch": 3.0975954738330977, "percentage": 15.49, "elapsed_time": "0:23:50", "remaining_time": "2:10:03", "throughput": 4629.44, "total_tokens": 6620256} {"current_steps": 6575, "total_steps": 42420, "loss": 0.1435, "lr": 4.954111127133926e-05, "epoch": 3.0999528524281, "percentage": 15.5, "elapsed_time": "0:23:51", "remaining_time": "2:10:02", "throughput": 4629.47, "total_tokens": 6625440} {"current_steps": 6580, "total_steps": 42420, "loss": 0.0955, "lr": 4.9539147445961854e-05, "epoch": 3.102310231023102, "percentage": 15.51, "elapsed_time": "0:23:52", "remaining_time": "2:10:01", "throughput": 4629.73, "total_tokens": 6631200} {"current_steps": 6585, "total_steps": 42420, "loss": 0.1351, "lr": 4.9537179466523426e-05, "epoch": 3.1046676096181045, "percentage": 15.52, "elapsed_time": "0:23:53", "remaining_time": "2:10:00", "throughput": 4629.9, "total_tokens": 6636160} {"current_steps": 6590, "total_steps": 42420, "loss": 0.2229, "lr": 4.9535207333357134e-05, "epoch": 3.107024988213107, "percentage": 15.54, "elapsed_time": "0:23:54", "remaining_time": "2:09:59", "throughput": 4630.11, "total_tokens": 6641792} {"current_steps": 6595, "total_steps": 42420, "loss": 0.1007, "lr": 4.953323104679683e-05, "epoch": 3.1093823668081093, "percentage": 15.55, "elapsed_time": "0:23:55", "remaining_time": "2:09:57", "throughput": 4630.27, "total_tokens": 6646656} {"current_steps": 6600, "total_steps": 42420, "loss": 0.2019, "lr": 4.953125060717706e-05, "epoch": 3.1117397454031117, "percentage": 15.56, "elapsed_time": "0:23:56", "remaining_time": "2:09:55", "throughput": 4630.29, "total_tokens": 6651168} {"current_steps": 6605, "total_steps": 42420, "loss": 0.0616, "lr": 4.952926601483308e-05, "epoch": 3.114097123998114, "percentage": 15.57, "elapsed_time": "0:23:57", "remaining_time": "2:09:54", "throughput": 4630.34, "total_tokens": 6655744} {"current_steps": 6610, "total_steps": 42420, "loss": 0.0837, "lr": 4.9527277270100836e-05, "epoch": 3.1164545025931165, "percentage": 15.58, "elapsed_time": "0:23:58", "remaining_time": "2:09:53", "throughput": 4630.55, "total_tokens": 6661536} {"current_steps": 6615, "total_steps": 42420, "loss": 0.1264, "lr": 4.952528437331701e-05, "epoch": 3.118811881188119, "percentage": 15.59, "elapsed_time": "0:23:59", "remaining_time": "2:09:51", "throughput": 4630.55, "total_tokens": 6665728} {"current_steps": 6620, "total_steps": 42420, "loss": 0.1449, "lr": 4.952328732481895e-05, "epoch": 3.1211692597831213, "percentage": 15.61, "elapsed_time": "0:24:00", "remaining_time": "2:09:50", "throughput": 4630.66, "total_tokens": 6670688} {"current_steps": 6625, "total_steps": 42420, "loss": 0.2267, "lr": 4.952128612494473e-05, "epoch": 3.1235266383781237, "percentage": 15.62, "elapsed_time": "0:24:01", "remaining_time": "2:09:48", "throughput": 4630.7, "total_tokens": 6674816} {"current_steps": 6630, "total_steps": 42420, "loss": 0.2343, "lr": 4.951928077403312e-05, "epoch": 3.1258840169731257, "percentage": 15.63, "elapsed_time": "0:24:02", "remaining_time": "2:09:46", "throughput": 4630.97, "total_tokens": 6680192} {"current_steps": 6635, "total_steps": 42420, "loss": 0.0268, "lr": 4.9517271272423585e-05, "epoch": 3.128241395568128, "percentage": 15.64, "elapsed_time": "0:24:03", "remaining_time": "2:09:45", "throughput": 4631.11, "total_tokens": 6685120} {"current_steps": 6640, "total_steps": 42420, "loss": 0.1816, "lr": 4.95152576204563e-05, "epoch": 3.1305987741631305, "percentage": 15.65, "elapsed_time": "0:24:04", "remaining_time": "2:09:44", "throughput": 4631.21, "total_tokens": 6690528} {"current_steps": 6645, "total_steps": 42420, "loss": 0.0703, "lr": 4.9513239818472154e-05, "epoch": 3.132956152758133, "percentage": 15.66, "elapsed_time": "0:24:05", "remaining_time": "2:09:43", "throughput": 4631.49, "total_tokens": 6696352} {"current_steps": 6650, "total_steps": 42420, "loss": 0.1116, "lr": 4.9511217866812706e-05, "epoch": 3.1353135313531353, "percentage": 15.68, "elapsed_time": "0:24:06", "remaining_time": "2:09:42", "throughput": 4631.73, "total_tokens": 6701280} {"current_steps": 6655, "total_steps": 42420, "loss": 0.1041, "lr": 4.950919176582026e-05, "epoch": 3.1376709099481377, "percentage": 15.69, "elapsed_time": "0:24:07", "remaining_time": "2:09:40", "throughput": 4631.88, "total_tokens": 6706144} {"current_steps": 6660, "total_steps": 42420, "loss": 0.1412, "lr": 4.9507161515837785e-05, "epoch": 3.14002828854314, "percentage": 15.7, "elapsed_time": "0:24:09", "remaining_time": "2:09:40", "throughput": 4632.05, "total_tokens": 6711936} {"current_steps": 6665, "total_steps": 42420, "loss": 0.3026, "lr": 4.950512711720898e-05, "epoch": 3.1423856671381425, "percentage": 15.71, "elapsed_time": "0:24:09", "remaining_time": "2:09:38", "throughput": 4632.1, "total_tokens": 6716384} {"current_steps": 6670, "total_steps": 42420, "loss": 0.2784, "lr": 4.9503088570278224e-05, "epoch": 3.144743045733145, "percentage": 15.72, "elapsed_time": "0:24:11", "remaining_time": "2:09:37", "throughput": 4632.28, "total_tokens": 6721664} {"current_steps": 6675, "total_steps": 42420, "loss": 0.0888, "lr": 4.95010458753906e-05, "epoch": 3.1471004243281473, "percentage": 15.74, "elapsed_time": "0:24:12", "remaining_time": "2:09:36", "throughput": 4632.44, "total_tokens": 6726880} {"current_steps": 6680, "total_steps": 42420, "loss": 0.0849, "lr": 4.949899903289193e-05, "epoch": 3.1494578029231493, "percentage": 15.75, "elapsed_time": "0:24:13", "remaining_time": "2:09:35", "throughput": 4632.7, "total_tokens": 6732544} {"current_steps": 6685, "total_steps": 42420, "loss": 0.1592, "lr": 4.949694804312869e-05, "epoch": 3.1518151815181517, "percentage": 15.76, "elapsed_time": "0:24:14", "remaining_time": "2:09:37", "throughput": 4632.96, "total_tokens": 6740288} {"current_steps": 6690, "total_steps": 42420, "loss": 0.1171, "lr": 4.949489290644808e-05, "epoch": 3.154172560113154, "percentage": 15.77, "elapsed_time": "0:24:16", "remaining_time": "2:09:37", "throughput": 4633.17, "total_tokens": 6747040} {"current_steps": 6695, "total_steps": 42420, "loss": 0.338, "lr": 4.949283362319799e-05, "epoch": 3.1565299387081565, "percentage": 15.78, "elapsed_time": "0:24:17", "remaining_time": "2:09:36", "throughput": 4633.37, "total_tokens": 6752096} {"current_steps": 6700, "total_steps": 42420, "loss": 0.0894, "lr": 4.949077019372704e-05, "epoch": 3.158887317303159, "percentage": 15.79, "elapsed_time": "0:24:18", "remaining_time": "2:09:34", "throughput": 4633.52, "total_tokens": 6757184} {"current_steps": 6705, "total_steps": 42420, "loss": 0.287, "lr": 4.948870261838453e-05, "epoch": 3.1612446958981613, "percentage": 15.81, "elapsed_time": "0:24:19", "remaining_time": "2:09:34", "throughput": 4633.64, "total_tokens": 6762688} {"current_steps": 6710, "total_steps": 42420, "loss": 0.1628, "lr": 4.948663089752046e-05, "epoch": 3.1636020744931637, "percentage": 15.82, "elapsed_time": "0:24:20", "remaining_time": "2:09:31", "throughput": 4633.55, "total_tokens": 6766720} {"current_steps": 6715, "total_steps": 42420, "loss": 0.1321, "lr": 4.948455503148554e-05, "epoch": 3.165959453088166, "percentage": 15.83, "elapsed_time": "0:24:21", "remaining_time": "2:09:30", "throughput": 4633.66, "total_tokens": 6771200} {"current_steps": 6720, "total_steps": 42420, "loss": 0.1946, "lr": 4.948247502063117e-05, "epoch": 3.1683168316831685, "percentage": 15.84, "elapsed_time": "0:24:22", "remaining_time": "2:09:28", "throughput": 4633.74, "total_tokens": 6776096} {"current_steps": 6725, "total_steps": 42420, "loss": 0.1014, "lr": 4.9480390865309466e-05, "epoch": 3.170674210278171, "percentage": 15.85, "elapsed_time": "0:24:23", "remaining_time": "2:09:26", "throughput": 4633.75, "total_tokens": 6780192} {"current_steps": 6730, "total_steps": 42420, "loss": 0.1148, "lr": 4.9478302565873245e-05, "epoch": 3.173031588873173, "percentage": 15.87, "elapsed_time": "0:24:24", "remaining_time": "2:09:25", "throughput": 4633.61, "total_tokens": 6784896} {"current_steps": 6735, "total_steps": 42420, "loss": 0.26, "lr": 4.9476210122676025e-05, "epoch": 3.1753889674681752, "percentage": 15.88, "elapsed_time": "0:24:25", "remaining_time": "2:09:23", "throughput": 4633.76, "total_tokens": 6789568} {"current_steps": 6740, "total_steps": 42420, "loss": 0.2349, "lr": 4.947411353607201e-05, "epoch": 3.1777463460631776, "percentage": 15.89, "elapsed_time": "0:24:26", "remaining_time": "2:09:21", "throughput": 4633.81, "total_tokens": 6793664} {"current_steps": 6745, "total_steps": 42420, "loss": 0.2738, "lr": 4.9472012806416114e-05, "epoch": 3.18010372465818, "percentage": 15.9, "elapsed_time": "0:24:27", "remaining_time": "2:09:20", "throughput": 4633.94, "total_tokens": 6798816} {"current_steps": 6750, "total_steps": 42420, "loss": 0.14, "lr": 4.946990793406396e-05, "epoch": 3.1824611032531824, "percentage": 15.91, "elapsed_time": "0:24:28", "remaining_time": "2:09:19", "throughput": 4634.13, "total_tokens": 6804416} {"current_steps": 6755, "total_steps": 42420, "loss": 0.212, "lr": 4.9467798919371874e-05, "epoch": 3.184818481848185, "percentage": 15.92, "elapsed_time": "0:24:29", "remaining_time": "2:09:18", "throughput": 4634.31, "total_tokens": 6809568} {"current_steps": 6760, "total_steps": 42420, "loss": 0.2004, "lr": 4.9465685762696874e-05, "epoch": 3.1871758604431872, "percentage": 15.94, "elapsed_time": "0:24:30", "remaining_time": "2:09:17", "throughput": 4634.35, "total_tokens": 6814912} {"current_steps": 6765, "total_steps": 42420, "loss": 0.1068, "lr": 4.946356846439667e-05, "epoch": 3.1895332390381896, "percentage": 15.95, "elapsed_time": "0:24:31", "remaining_time": "2:09:15", "throughput": 4634.43, "total_tokens": 6819584} {"current_steps": 6770, "total_steps": 42420, "loss": 0.1054, "lr": 4.9461447024829696e-05, "epoch": 3.191890617633192, "percentage": 15.96, "elapsed_time": "0:24:32", "remaining_time": "2:09:15", "throughput": 4634.66, "total_tokens": 6825536} {"current_steps": 6775, "total_steps": 42420, "loss": 0.2415, "lr": 4.9459321444355077e-05, "epoch": 3.1942479962281944, "percentage": 15.97, "elapsed_time": "0:24:33", "remaining_time": "2:09:14", "throughput": 4634.86, "total_tokens": 6831264} {"current_steps": 6780, "total_steps": 42420, "loss": 0.342, "lr": 4.945719172333263e-05, "epoch": 3.1966053748231964, "percentage": 15.98, "elapsed_time": "0:24:34", "remaining_time": "2:09:12", "throughput": 4634.87, "total_tokens": 6835648} {"current_steps": 6785, "total_steps": 42420, "loss": 0.0627, "lr": 4.945505786212288e-05, "epoch": 3.198962753418199, "percentage": 15.99, "elapsed_time": "0:24:35", "remaining_time": "2:09:10", "throughput": 4634.92, "total_tokens": 6839936} {"current_steps": 6790, "total_steps": 42420, "loss": 0.27, "lr": 4.945291986108707e-05, "epoch": 3.201320132013201, "percentage": 16.01, "elapsed_time": "0:24:36", "remaining_time": "2:09:09", "throughput": 4634.98, "total_tokens": 6844736} {"current_steps": 6795, "total_steps": 42420, "loss": 0.3456, "lr": 4.945077772058709e-05, "epoch": 3.2036775106082036, "percentage": 16.02, "elapsed_time": "0:24:37", "remaining_time": "2:09:07", "throughput": 4635.02, "total_tokens": 6849536} {"current_steps": 6800, "total_steps": 42420, "loss": 0.2046, "lr": 4.944863144098562e-05, "epoch": 3.206034889203206, "percentage": 16.03, "elapsed_time": "0:24:38", "remaining_time": "2:09:05", "throughput": 4635.11, "total_tokens": 6853728} {"current_steps": 6805, "total_steps": 42420, "loss": 0.1131, "lr": 4.9446481022645944e-05, "epoch": 3.2083922677982084, "percentage": 16.04, "elapsed_time": "0:24:39", "remaining_time": "2:09:04", "throughput": 4635.37, "total_tokens": 6859264} {"current_steps": 6810, "total_steps": 42420, "loss": 0.0635, "lr": 4.944432646593211e-05, "epoch": 3.210749646393211, "percentage": 16.05, "elapsed_time": "0:24:40", "remaining_time": "2:09:03", "throughput": 4635.56, "total_tokens": 6864352} {"current_steps": 6815, "total_steps": 42420, "loss": 0.0785, "lr": 4.944216777120885e-05, "epoch": 3.213107024988213, "percentage": 16.07, "elapsed_time": "0:24:41", "remaining_time": "2:09:01", "throughput": 4635.5, "total_tokens": 6868576} {"current_steps": 6820, "total_steps": 42420, "loss": 0.2133, "lr": 4.9440004938841587e-05, "epoch": 3.2154644035832156, "percentage": 16.08, "elapsed_time": "0:24:42", "remaining_time": "2:09:00", "throughput": 4635.71, "total_tokens": 6874080} {"current_steps": 6825, "total_steps": 42420, "loss": 0.2976, "lr": 4.943783796919646e-05, "epoch": 3.217821782178218, "percentage": 16.09, "elapsed_time": "0:24:43", "remaining_time": "2:08:59", "throughput": 4635.9, "total_tokens": 6879680} {"current_steps": 6830, "total_steps": 42420, "loss": 0.1254, "lr": 4.9435666862640294e-05, "epoch": 3.22017916077322, "percentage": 16.1, "elapsed_time": "0:24:45", "remaining_time": "2:08:59", "throughput": 4636.17, "total_tokens": 6885760} {"current_steps": 6835, "total_steps": 42420, "loss": 0.2815, "lr": 4.943349161954062e-05, "epoch": 3.2225365393682224, "percentage": 16.11, "elapsed_time": "0:24:46", "remaining_time": "2:08:57", "throughput": 4636.31, "total_tokens": 6890784} {"current_steps": 6840, "total_steps": 42420, "loss": 0.0555, "lr": 4.9431312240265674e-05, "epoch": 3.2248939179632248, "percentage": 16.12, "elapsed_time": "0:24:47", "remaining_time": "2:08:56", "throughput": 4636.57, "total_tokens": 6896352} {"current_steps": 6845, "total_steps": 42420, "loss": 0.2245, "lr": 4.9429128725184385e-05, "epoch": 3.227251296558227, "percentage": 16.14, "elapsed_time": "0:24:48", "remaining_time": "2:08:55", "throughput": 4636.74, "total_tokens": 6901216} {"current_steps": 6850, "total_steps": 42420, "loss": 0.23, "lr": 4.9426941074666386e-05, "epoch": 3.2296086751532296, "percentage": 16.15, "elapsed_time": "0:24:49", "remaining_time": "2:08:53", "throughput": 4636.84, "total_tokens": 6906016} {"current_steps": 6855, "total_steps": 42420, "loss": 0.2107, "lr": 4.942474928908201e-05, "epoch": 3.231966053748232, "percentage": 16.16, "elapsed_time": "0:24:50", "remaining_time": "2:08:52", "throughput": 4637.01, "total_tokens": 6911040} {"current_steps": 6860, "total_steps": 42420, "loss": 0.1973, "lr": 4.9422553368802294e-05, "epoch": 3.2343234323432344, "percentage": 16.17, "elapsed_time": "0:24:51", "remaining_time": "2:08:51", "throughput": 4637.16, "total_tokens": 6916160} {"current_steps": 6865, "total_steps": 42420, "loss": 0.2826, "lr": 4.9420353314198954e-05, "epoch": 3.236680810938237, "percentage": 16.18, "elapsed_time": "0:24:52", "remaining_time": "2:08:49", "throughput": 4637.2, "total_tokens": 6920384} {"current_steps": 6870, "total_steps": 42420, "loss": 0.1876, "lr": 4.941814912564444e-05, "epoch": 3.239038189533239, "percentage": 16.2, "elapsed_time": "0:24:53", "remaining_time": "2:08:47", "throughput": 4637.21, "total_tokens": 6924960} {"current_steps": 6875, "total_steps": 42420, "loss": 0.0812, "lr": 4.9415940803511864e-05, "epoch": 3.2413955681282416, "percentage": 16.21, "elapsed_time": "0:24:54", "remaining_time": "2:08:45", "throughput": 4637.19, "total_tokens": 6929280} {"current_steps": 6880, "total_steps": 42420, "loss": 0.1457, "lr": 4.941372834817508e-05, "epoch": 3.2437529467232435, "percentage": 16.22, "elapsed_time": "0:24:55", "remaining_time": "2:08:45", "throughput": 4637.4, "total_tokens": 6935488} {"current_steps": 6885, "total_steps": 42420, "loss": 0.1172, "lr": 4.94115117600086e-05, "epoch": 3.246110325318246, "percentage": 16.23, "elapsed_time": "0:24:56", "remaining_time": "2:08:43", "throughput": 4637.44, "total_tokens": 6939616} {"current_steps": 6890, "total_steps": 42420, "loss": 0.0793, "lr": 4.940929103938767e-05, "epoch": 3.2484677039132484, "percentage": 16.24, "elapsed_time": "0:24:57", "remaining_time": "2:08:43", "throughput": 4637.66, "total_tokens": 6946464} {"current_steps": 6895, "total_steps": 42420, "loss": 0.1558, "lr": 4.940706618668821e-05, "epoch": 3.2508250825082508, "percentage": 16.25, "elapsed_time": "0:24:58", "remaining_time": "2:08:42", "throughput": 4637.73, "total_tokens": 6951104} {"current_steps": 6900, "total_steps": 42420, "loss": 0.1548, "lr": 4.940483720228685e-05, "epoch": 3.253182461103253, "percentage": 16.27, "elapsed_time": "0:25:00", "remaining_time": "2:08:41", "throughput": 4637.95, "total_tokens": 6957088} {"current_steps": 6905, "total_steps": 42420, "loss": 0.2396, "lr": 4.940260408656093e-05, "epoch": 3.2555398396982556, "percentage": 16.28, "elapsed_time": "0:25:01", "remaining_time": "2:08:42", "throughput": 4638.24, "total_tokens": 6963776} {"current_steps": 6910, "total_steps": 42420, "loss": 0.2265, "lr": 4.940036683988847e-05, "epoch": 3.257897218293258, "percentage": 16.29, "elapsed_time": "0:25:02", "remaining_time": "2:08:41", "throughput": 4638.36, "total_tokens": 6968960} {"current_steps": 6915, "total_steps": 42420, "loss": 0.1529, "lr": 4.9398125462648195e-05, "epoch": 3.2602545968882604, "percentage": 16.3, "elapsed_time": "0:25:03", "remaining_time": "2:08:39", "throughput": 4638.58, "total_tokens": 6974240} {"current_steps": 6920, "total_steps": 42420, "loss": 0.1742, "lr": 4.9395879955219534e-05, "epoch": 3.2626119754832628, "percentage": 16.31, "elapsed_time": "0:25:04", "remaining_time": "2:08:38", "throughput": 4638.72, "total_tokens": 6979104} {"current_steps": 6925, "total_steps": 42420, "loss": 0.1808, "lr": 4.9393630317982616e-05, "epoch": 3.264969354078265, "percentage": 16.32, "elapsed_time": "0:25:05", "remaining_time": "2:08:37", "throughput": 4638.87, "total_tokens": 6984864} {"current_steps": 6930, "total_steps": 42420, "loss": 0.0715, "lr": 4.9391376551318265e-05, "epoch": 3.2673267326732676, "percentage": 16.34, "elapsed_time": "0:25:06", "remaining_time": "2:08:35", "throughput": 4638.7, "total_tokens": 6988768} {"current_steps": 6935, "total_steps": 42420, "loss": 0.3164, "lr": 4.9389118655608e-05, "epoch": 3.2696841112682695, "percentage": 16.35, "elapsed_time": "0:25:07", "remaining_time": "2:08:35", "throughput": 4638.91, "total_tokens": 6995040} {"current_steps": 6940, "total_steps": 42420, "loss": 0.1177, "lr": 4.9386856631234065e-05, "epoch": 3.272041489863272, "percentage": 16.36, "elapsed_time": "0:25:08", "remaining_time": "2:08:34", "throughput": 4639.03, "total_tokens": 7000032} {"current_steps": 6945, "total_steps": 42420, "loss": 0.3025, "lr": 4.9384590478579355e-05, "epoch": 3.2743988684582743, "percentage": 16.37, "elapsed_time": "0:25:09", "remaining_time": "2:08:32", "throughput": 4639.07, "total_tokens": 7004480} {"current_steps": 6950, "total_steps": 42420, "loss": 0.1527, "lr": 4.938232019802751e-05, "epoch": 3.2767562470532767, "percentage": 16.38, "elapsed_time": "0:25:10", "remaining_time": "2:08:30", "throughput": 4639.18, "total_tokens": 7009216} {"current_steps": 6955, "total_steps": 42420, "loss": 0.1262, "lr": 4.938004578996284e-05, "epoch": 3.279113625648279, "percentage": 16.4, "elapsed_time": "0:25:11", "remaining_time": "2:08:29", "throughput": 4639.22, "total_tokens": 7014368} {"current_steps": 6960, "total_steps": 42420, "loss": 0.2074, "lr": 4.9377767254770377e-05, "epoch": 3.2814710042432815, "percentage": 16.41, "elapsed_time": "0:25:12", "remaining_time": "2:08:28", "throughput": 4639.25, "total_tokens": 7018880} {"current_steps": 6965, "total_steps": 42420, "loss": 0.1769, "lr": 4.937548459283582e-05, "epoch": 3.283828382838284, "percentage": 16.42, "elapsed_time": "0:25:13", "remaining_time": "2:08:26", "throughput": 4639.23, "total_tokens": 7023264} {"current_steps": 6970, "total_steps": 42420, "loss": 0.2032, "lr": 4.937319780454559e-05, "epoch": 3.2861857614332863, "percentage": 16.43, "elapsed_time": "0:25:14", "remaining_time": "2:08:24", "throughput": 4639.35, "total_tokens": 7028000} {"current_steps": 6975, "total_steps": 42420, "loss": 0.1625, "lr": 4.9370906890286815e-05, "epoch": 3.2885431400282887, "percentage": 16.44, "elapsed_time": "0:25:15", "remaining_time": "2:08:23", "throughput": 4639.48, "total_tokens": 7032960} {"current_steps": 6980, "total_steps": 42420, "loss": 0.2326, "lr": 4.9368611850447287e-05, "epoch": 3.2909005186232907, "percentage": 16.45, "elapsed_time": "0:25:16", "remaining_time": "2:08:21", "throughput": 4639.56, "total_tokens": 7037504} {"current_steps": 6985, "total_steps": 42420, "loss": 0.1388, "lr": 4.936631268541554e-05, "epoch": 3.293257897218293, "percentage": 16.47, "elapsed_time": "0:25:17", "remaining_time": "2:08:19", "throughput": 4639.71, "total_tokens": 7042304} {"current_steps": 6990, "total_steps": 42420, "loss": 0.1729, "lr": 4.936400939558076e-05, "epoch": 3.2956152758132955, "percentage": 16.48, "elapsed_time": "0:25:18", "remaining_time": "2:08:17", "throughput": 4639.72, "total_tokens": 7046528} {"current_steps": 6995, "total_steps": 42420, "loss": 0.1109, "lr": 4.9361701981332875e-05, "epoch": 3.297972654408298, "percentage": 16.49, "elapsed_time": "0:25:19", "remaining_time": "2:08:15", "throughput": 4639.6, "total_tokens": 7050496} {"current_steps": 7000, "total_steps": 42420, "loss": 0.2513, "lr": 4.9359390443062484e-05, "epoch": 3.3003300330033003, "percentage": 16.5, "elapsed_time": "0:25:20", "remaining_time": "2:08:14", "throughput": 4639.78, "total_tokens": 7055776} {"current_steps": 7005, "total_steps": 42420, "loss": 0.1309, "lr": 4.935707478116089e-05, "epoch": 3.3026874115983027, "percentage": 16.51, "elapsed_time": "0:25:21", "remaining_time": "2:08:13", "throughput": 4639.93, "total_tokens": 7061248} {"current_steps": 7010, "total_steps": 42420, "loss": 0.147, "lr": 4.9354754996020084e-05, "epoch": 3.305044790193305, "percentage": 16.53, "elapsed_time": "0:25:22", "remaining_time": "2:08:12", "throughput": 4639.93, "total_tokens": 7065856} {"current_steps": 7015, "total_steps": 42420, "loss": 0.1193, "lr": 4.935243108803279e-05, "epoch": 3.3074021687883075, "percentage": 16.54, "elapsed_time": "0:25:23", "remaining_time": "2:08:10", "throughput": 4639.75, "total_tokens": 7069568} {"current_steps": 7020, "total_steps": 42420, "loss": 0.1827, "lr": 4.935010305759238e-05, "epoch": 3.30975954738331, "percentage": 16.55, "elapsed_time": "0:25:24", "remaining_time": "2:08:08", "throughput": 4639.84, "total_tokens": 7074592} {"current_steps": 7025, "total_steps": 42420, "loss": 0.2869, "lr": 4.9347770905092976e-05, "epoch": 3.3121169259783123, "percentage": 16.56, "elapsed_time": "0:25:25", "remaining_time": "2:08:08", "throughput": 4639.99, "total_tokens": 7080032} {"current_steps": 7030, "total_steps": 42420, "loss": 0.1718, "lr": 4.9345434630929353e-05, "epoch": 3.3144743045733147, "percentage": 16.57, "elapsed_time": "0:25:26", "remaining_time": "2:08:05", "throughput": 4639.93, "total_tokens": 7083968} {"current_steps": 7035, "total_steps": 42420, "loss": 0.0985, "lr": 4.934309423549701e-05, "epoch": 3.3168316831683167, "percentage": 16.58, "elapsed_time": "0:25:27", "remaining_time": "2:08:05", "throughput": 4640.14, "total_tokens": 7089600} {"current_steps": 7040, "total_steps": 42420, "loss": 0.1094, "lr": 4.9340749719192136e-05, "epoch": 3.319189061763319, "percentage": 16.6, "elapsed_time": "0:25:28", "remaining_time": "2:08:04", "throughput": 4640.3, "total_tokens": 7094976} {"current_steps": 7045, "total_steps": 42420, "loss": 0.2823, "lr": 4.933840108241162e-05, "epoch": 3.3215464403583215, "percentage": 16.61, "elapsed_time": "0:25:29", "remaining_time": "2:08:02", "throughput": 4640.32, "total_tokens": 7099424} {"current_steps": 7050, "total_steps": 42420, "loss": 0.1926, "lr": 4.933604832555304e-05, "epoch": 3.323903818953324, "percentage": 16.62, "elapsed_time": "0:25:30", "remaining_time": "2:08:00", "throughput": 4640.48, "total_tokens": 7104448} {"current_steps": 7055, "total_steps": 42420, "loss": 0.2503, "lr": 4.9333691449014686e-05, "epoch": 3.3262611975483263, "percentage": 16.63, "elapsed_time": "0:25:32", "remaining_time": "2:07:59", "throughput": 4640.58, "total_tokens": 7109440} {"current_steps": 7060, "total_steps": 42420, "loss": 0.1661, "lr": 4.933133045319552e-05, "epoch": 3.3286185761433287, "percentage": 16.64, "elapsed_time": "0:25:33", "remaining_time": "2:07:58", "throughput": 4640.68, "total_tokens": 7114496} {"current_steps": 7065, "total_steps": 42420, "loss": 0.2245, "lr": 4.932896533849524e-05, "epoch": 3.330975954738331, "percentage": 16.65, "elapsed_time": "0:25:34", "remaining_time": "2:07:56", "throughput": 4640.78, "total_tokens": 7119360} {"current_steps": 7070, "total_steps": 42420, "loss": 0.182, "lr": 4.9326596105314214e-05, "epoch": 3.3333333333333335, "percentage": 16.67, "elapsed_time": "0:25:35", "remaining_time": "2:07:55", "throughput": 4640.87, "total_tokens": 7124160} {"current_steps": 7075, "total_steps": 42420, "loss": 0.4256, "lr": 4.932422275405351e-05, "epoch": 3.335690711928336, "percentage": 16.68, "elapsed_time": "0:25:36", "remaining_time": "2:07:54", "throughput": 4640.81, "total_tokens": 7128960} {"current_steps": 7080, "total_steps": 42420, "loss": 0.147, "lr": 4.9321845285114884e-05, "epoch": 3.338048090523338, "percentage": 16.69, "elapsed_time": "0:25:37", "remaining_time": "2:07:52", "throughput": 4640.86, "total_tokens": 7133888} {"current_steps": 7085, "total_steps": 42420, "loss": 0.1763, "lr": 4.9319463698900817e-05, "epoch": 3.3404054691183402, "percentage": 16.7, "elapsed_time": "0:25:38", "remaining_time": "2:07:51", "throughput": 4640.94, "total_tokens": 7138400} {"current_steps": 7090, "total_steps": 42420, "loss": 0.1279, "lr": 4.931707799581447e-05, "epoch": 3.3427628477133426, "percentage": 16.71, "elapsed_time": "0:25:39", "remaining_time": "2:07:50", "throughput": 4641.2, "total_tokens": 7144544} {"current_steps": 7095, "total_steps": 42420, "loss": 0.0906, "lr": 4.9314688176259694e-05, "epoch": 3.345120226308345, "percentage": 16.73, "elapsed_time": "0:25:40", "remaining_time": "2:07:49", "throughput": 4641.21, "total_tokens": 7149312} {"current_steps": 7100, "total_steps": 42420, "loss": 0.143, "lr": 4.931229424064105e-05, "epoch": 3.3474776049033474, "percentage": 16.74, "elapsed_time": "0:25:41", "remaining_time": "2:07:48", "throughput": 4641.22, "total_tokens": 7154208} {"current_steps": 7105, "total_steps": 42420, "loss": 0.1592, "lr": 4.93098961893638e-05, "epoch": 3.34983498349835, "percentage": 16.75, "elapsed_time": "0:25:42", "remaining_time": "2:07:46", "throughput": 4641.31, "total_tokens": 7158528} {"current_steps": 7110, "total_steps": 42420, "loss": 0.2855, "lr": 4.930749402283388e-05, "epoch": 3.3521923620933523, "percentage": 16.76, "elapsed_time": "0:25:43", "remaining_time": "2:07:44", "throughput": 4641.22, "total_tokens": 7163040} {"current_steps": 7115, "total_steps": 42420, "loss": 0.2073, "lr": 4.9305087741457935e-05, "epoch": 3.3545497406883547, "percentage": 16.77, "elapsed_time": "0:25:44", "remaining_time": "2:07:44", "throughput": 4641.46, "total_tokens": 7169024} {"current_steps": 7120, "total_steps": 42420, "loss": 0.2195, "lr": 4.930267734564331e-05, "epoch": 3.356907119283357, "percentage": 16.78, "elapsed_time": "0:25:45", "remaining_time": "2:07:42", "throughput": 4641.38, "total_tokens": 7173664} {"current_steps": 7125, "total_steps": 42420, "loss": 0.2795, "lr": 4.930026283579805e-05, "epoch": 3.3592644978783595, "percentage": 16.8, "elapsed_time": "0:25:46", "remaining_time": "2:07:41", "throughput": 4641.53, "total_tokens": 7178688} {"current_steps": 7130, "total_steps": 42420, "loss": 0.0922, "lr": 4.929784421233089e-05, "epoch": 3.361621876473362, "percentage": 16.81, "elapsed_time": "0:25:47", "remaining_time": "2:07:40", "throughput": 4641.69, "total_tokens": 7183680} {"current_steps": 7135, "total_steps": 42420, "loss": 0.236, "lr": 4.9295421475651256e-05, "epoch": 3.363979255068364, "percentage": 16.82, "elapsed_time": "0:25:48", "remaining_time": "2:07:38", "throughput": 4641.78, "total_tokens": 7188352} {"current_steps": 7140, "total_steps": 42420, "loss": 0.2867, "lr": 4.9292994626169276e-05, "epoch": 3.366336633663366, "percentage": 16.83, "elapsed_time": "0:25:49", "remaining_time": "2:07:37", "throughput": 4641.91, "total_tokens": 7193632} {"current_steps": 7145, "total_steps": 42420, "loss": 0.2128, "lr": 4.9290563664295785e-05, "epoch": 3.3686940122583686, "percentage": 16.84, "elapsed_time": "0:25:50", "remaining_time": "2:07:35", "throughput": 4641.9, "total_tokens": 7197568} {"current_steps": 7150, "total_steps": 42420, "loss": 0.2403, "lr": 4.928812859044228e-05, "epoch": 3.371051390853371, "percentage": 16.86, "elapsed_time": "0:25:51", "remaining_time": "2:07:34", "throughput": 4641.99, "total_tokens": 7202880} {"current_steps": 7155, "total_steps": 42420, "loss": 0.1166, "lr": 4.928568940502101e-05, "epoch": 3.3734087694483734, "percentage": 16.87, "elapsed_time": "0:25:52", "remaining_time": "2:07:32", "throughput": 4641.93, "total_tokens": 7207264} {"current_steps": 7160, "total_steps": 42420, "loss": 0.1851, "lr": 4.928324610844487e-05, "epoch": 3.375766148043376, "percentage": 16.88, "elapsed_time": "0:25:53", "remaining_time": "2:07:32", "throughput": 4642.12, "total_tokens": 7213472} {"current_steps": 7165, "total_steps": 42420, "loss": 0.1604, "lr": 4.928079870112746e-05, "epoch": 3.3781235266383782, "percentage": 16.89, "elapsed_time": "0:25:54", "remaining_time": "2:07:31", "throughput": 4642.24, "total_tokens": 7218656} {"current_steps": 7170, "total_steps": 42420, "loss": 0.2417, "lr": 4.927834718348311e-05, "epoch": 3.3804809052333806, "percentage": 16.9, "elapsed_time": "0:25:56", "remaining_time": "2:07:30", "throughput": 4642.43, "total_tokens": 7224224} {"current_steps": 7175, "total_steps": 42420, "loss": 0.0834, "lr": 4.927589155592679e-05, "epoch": 3.382838283828383, "percentage": 16.91, "elapsed_time": "0:25:57", "remaining_time": "2:07:28", "throughput": 4642.52, "total_tokens": 7228864} {"current_steps": 7180, "total_steps": 42420, "loss": 0.1975, "lr": 4.927343181887422e-05, "epoch": 3.385195662423385, "percentage": 16.93, "elapsed_time": "0:25:58", "remaining_time": "2:07:27", "throughput": 4642.55, "total_tokens": 7233824} {"current_steps": 7185, "total_steps": 42420, "loss": 0.053, "lr": 4.927096797274178e-05, "epoch": 3.3875530410183874, "percentage": 16.94, "elapsed_time": "0:25:59", "remaining_time": "2:07:26", "throughput": 4642.7, "total_tokens": 7239584} {"current_steps": 7190, "total_steps": 42420, "loss": 0.1343, "lr": 4.926850001794655e-05, "epoch": 3.38991041961339, "percentage": 16.95, "elapsed_time": "0:26:00", "remaining_time": "2:07:26", "throughput": 4642.86, "total_tokens": 7244992} {"current_steps": 7195, "total_steps": 42420, "loss": 0.1511, "lr": 4.926602795490633e-05, "epoch": 3.392267798208392, "percentage": 16.96, "elapsed_time": "0:26:01", "remaining_time": "2:07:24", "throughput": 4642.84, "total_tokens": 7249184} {"current_steps": 7200, "total_steps": 42420, "loss": 0.1454, "lr": 4.9263551784039595e-05, "epoch": 3.3946251768033946, "percentage": 16.97, "elapsed_time": "0:26:02", "remaining_time": "2:07:23", "throughput": 4643.08, "total_tokens": 7254976} {"current_steps": 7205, "total_steps": 42420, "loss": 0.0987, "lr": 4.926107150576551e-05, "epoch": 3.396982555398397, "percentage": 16.98, "elapsed_time": "0:26:03", "remaining_time": "2:07:21", "throughput": 4643.15, "total_tokens": 7259712} {"current_steps": 7210, "total_steps": 42420, "loss": 0.3942, "lr": 4.925858712050395e-05, "epoch": 3.3993399339933994, "percentage": 17.0, "elapsed_time": "0:26:04", "remaining_time": "2:07:19", "throughput": 4643.11, "total_tokens": 7263904} {"current_steps": 7215, "total_steps": 42420, "loss": 0.065, "lr": 4.9256098628675476e-05, "epoch": 3.401697312588402, "percentage": 17.01, "elapsed_time": "0:26:05", "remaining_time": "2:07:18", "throughput": 4643.05, "total_tokens": 7268288} {"current_steps": 7220, "total_steps": 42420, "loss": 0.1392, "lr": 4.925360603070135e-05, "epoch": 3.404054691183404, "percentage": 17.02, "elapsed_time": "0:26:06", "remaining_time": "2:07:15", "throughput": 4643.03, "total_tokens": 7272128} {"current_steps": 7225, "total_steps": 42420, "loss": 0.2349, "lr": 4.925110932700353e-05, "epoch": 3.4064120697784066, "percentage": 17.03, "elapsed_time": "0:26:07", "remaining_time": "2:07:14", "throughput": 4643.06, "total_tokens": 7276448} {"current_steps": 7230, "total_steps": 42420, "loss": 0.2057, "lr": 4.9248608518004656e-05, "epoch": 3.408769448373409, "percentage": 17.04, "elapsed_time": "0:26:08", "remaining_time": "2:07:12", "throughput": 4643.14, "total_tokens": 7280896} {"current_steps": 7235, "total_steps": 42420, "loss": 0.1759, "lr": 4.924610360412808e-05, "epoch": 3.411126826968411, "percentage": 17.06, "elapsed_time": "0:26:09", "remaining_time": "2:07:11", "throughput": 4643.23, "total_tokens": 7286080} {"current_steps": 7240, "total_steps": 42420, "loss": 0.2029, "lr": 4.9243594585797836e-05, "epoch": 3.4134842055634134, "percentage": 17.07, "elapsed_time": "0:26:10", "remaining_time": "2:07:09", "throughput": 4643.38, "total_tokens": 7291232} {"current_steps": 7245, "total_steps": 42420, "loss": 0.1034, "lr": 4.924108146343867e-05, "epoch": 3.4158415841584158, "percentage": 17.08, "elapsed_time": "0:26:11", "remaining_time": "2:07:09", "throughput": 4643.57, "total_tokens": 7297184} {"current_steps": 7250, "total_steps": 42420, "loss": 0.0798, "lr": 4.9238564237475995e-05, "epoch": 3.418198962753418, "percentage": 17.09, "elapsed_time": "0:26:12", "remaining_time": "2:07:09", "throughput": 4643.7, "total_tokens": 7303360} {"current_steps": 7255, "total_steps": 42420, "loss": 0.0876, "lr": 4.923604290833594e-05, "epoch": 3.4205563413484206, "percentage": 17.1, "elapsed_time": "0:26:13", "remaining_time": "2:07:08", "throughput": 4643.83, "total_tokens": 7308544} {"current_steps": 7260, "total_steps": 42420, "loss": 0.13, "lr": 4.9233517476445335e-05, "epoch": 3.422913719943423, "percentage": 17.11, "elapsed_time": "0:26:14", "remaining_time": "2:07:06", "throughput": 4643.94, "total_tokens": 7313120} {"current_steps": 7265, "total_steps": 42420, "loss": 0.2195, "lr": 4.923098794223168e-05, "epoch": 3.4252710985384254, "percentage": 17.13, "elapsed_time": "0:26:15", "remaining_time": "2:07:05", "throughput": 4644.12, "total_tokens": 7318464} {"current_steps": 7270, "total_steps": 42420, "loss": 0.0984, "lr": 4.922845430612318e-05, "epoch": 3.4276284771334278, "percentage": 17.14, "elapsed_time": "0:26:16", "remaining_time": "2:07:03", "throughput": 4644.19, "total_tokens": 7323168} {"current_steps": 7275, "total_steps": 42420, "loss": 0.1493, "lr": 4.9225916568548744e-05, "epoch": 3.42998585572843, "percentage": 17.15, "elapsed_time": "0:26:17", "remaining_time": "2:07:02", "throughput": 4644.26, "total_tokens": 7328320} {"current_steps": 7280, "total_steps": 42420, "loss": 0.2109, "lr": 4.922337472993796e-05, "epoch": 3.432343234323432, "percentage": 17.16, "elapsed_time": "0:26:19", "remaining_time": "2:07:02", "throughput": 4644.51, "total_tokens": 7334656} {"current_steps": 7285, "total_steps": 42420, "loss": 0.103, "lr": 4.922082879072113e-05, "epoch": 3.4347006129184345, "percentage": 17.17, "elapsed_time": "0:26:20", "remaining_time": "2:07:01", "throughput": 4644.64, "total_tokens": 7339616} {"current_steps": 7290, "total_steps": 42420, "loss": 0.1321, "lr": 4.921827875132924e-05, "epoch": 3.437057991513437, "percentage": 17.19, "elapsed_time": "0:26:21", "remaining_time": "2:06:59", "throughput": 4644.68, "total_tokens": 7344256} {"current_steps": 7295, "total_steps": 42420, "loss": 0.0375, "lr": 4.9215724612193946e-05, "epoch": 3.4394153701084393, "percentage": 17.2, "elapsed_time": "0:26:22", "remaining_time": "2:06:57", "throughput": 4644.65, "total_tokens": 7348320} {"current_steps": 7300, "total_steps": 42420, "loss": 0.1469, "lr": 4.921316637374764e-05, "epoch": 3.4417727487034417, "percentage": 17.21, "elapsed_time": "0:26:23", "remaining_time": "2:06:55", "throughput": 4644.67, "total_tokens": 7352640} {"current_steps": 7305, "total_steps": 42420, "loss": 0.0997, "lr": 4.921060403642338e-05, "epoch": 3.444130127298444, "percentage": 17.22, "elapsed_time": "0:26:24", "remaining_time": "2:06:54", "throughput": 4644.72, "total_tokens": 7357376} {"current_steps": 7310, "total_steps": 42420, "loss": 0.101, "lr": 4.920803760065494e-05, "epoch": 3.4464875058934465, "percentage": 17.23, "elapsed_time": "0:26:24", "remaining_time": "2:06:52", "throughput": 4644.72, "total_tokens": 7361600} {"current_steps": 7315, "total_steps": 42420, "loss": 0.1894, "lr": 4.920546706687675e-05, "epoch": 3.448844884488449, "percentage": 17.24, "elapsed_time": "0:26:25", "remaining_time": "2:06:51", "throughput": 4644.84, "total_tokens": 7366592} {"current_steps": 7320, "total_steps": 42420, "loss": 0.0516, "lr": 4.9202892435523987e-05, "epoch": 3.4512022630834513, "percentage": 17.26, "elapsed_time": "0:26:26", "remaining_time": "2:06:49", "throughput": 4644.96, "total_tokens": 7371520} {"current_steps": 7325, "total_steps": 42420, "loss": 0.1449, "lr": 4.920031370703246e-05, "epoch": 3.4535596416784538, "percentage": 17.27, "elapsed_time": "0:26:28", "remaining_time": "2:06:48", "throughput": 4645.09, "total_tokens": 7376896} {"current_steps": 7330, "total_steps": 42420, "loss": 0.1088, "lr": 4.9197730881838724e-05, "epoch": 3.455917020273456, "percentage": 17.28, "elapsed_time": "0:26:29", "remaining_time": "2:06:47", "throughput": 4645.04, "total_tokens": 7381472} {"current_steps": 7335, "total_steps": 42420, "loss": 0.0283, "lr": 4.9195143960380006e-05, "epoch": 3.458274398868458, "percentage": 17.29, "elapsed_time": "0:26:30", "remaining_time": "2:06:45", "throughput": 4645.06, "total_tokens": 7385728} {"current_steps": 7340, "total_steps": 42420, "loss": 0.1295, "lr": 4.9192552943094225e-05, "epoch": 3.4606317774634605, "percentage": 17.3, "elapsed_time": "0:26:31", "remaining_time": "2:06:44", "throughput": 4645.0, "total_tokens": 7390432} {"current_steps": 7345, "total_steps": 42420, "loss": 0.116, "lr": 4.918995783042e-05, "epoch": 3.462989156058463, "percentage": 17.31, "elapsed_time": "0:26:32", "remaining_time": "2:06:43", "throughput": 4645.13, "total_tokens": 7396128} {"current_steps": 7350, "total_steps": 42420, "loss": 0.0903, "lr": 4.9187358622796636e-05, "epoch": 3.4653465346534653, "percentage": 17.33, "elapsed_time": "0:26:33", "remaining_time": "2:06:42", "throughput": 4645.17, "total_tokens": 7400960} {"current_steps": 7355, "total_steps": 42420, "loss": 0.0845, "lr": 4.918475532066413e-05, "epoch": 3.4677039132484677, "percentage": 17.34, "elapsed_time": "0:26:34", "remaining_time": "2:06:40", "throughput": 4645.27, "total_tokens": 7405888} {"current_steps": 7360, "total_steps": 42420, "loss": 0.3794, "lr": 4.918214792446319e-05, "epoch": 3.47006129184347, "percentage": 17.35, "elapsed_time": "0:26:35", "remaining_time": "2:06:39", "throughput": 4645.3, "total_tokens": 7411072} {"current_steps": 7365, "total_steps": 42420, "loss": 0.1961, "lr": 4.9179536434635195e-05, "epoch": 3.4724186704384725, "percentage": 17.36, "elapsed_time": "0:26:36", "remaining_time": "2:06:39", "throughput": 4645.54, "total_tokens": 7417120} {"current_steps": 7370, "total_steps": 42420, "loss": 0.1095, "lr": 4.917692085162222e-05, "epoch": 3.474776049033475, "percentage": 17.37, "elapsed_time": "0:26:37", "remaining_time": "2:06:38", "throughput": 4645.7, "total_tokens": 7422592} {"current_steps": 7375, "total_steps": 42420, "loss": 0.1384, "lr": 4.917430117586705e-05, "epoch": 3.4771334276284773, "percentage": 17.39, "elapsed_time": "0:26:38", "remaining_time": "2:06:36", "throughput": 4645.72, "total_tokens": 7426848} {"current_steps": 7380, "total_steps": 42420, "loss": 0.1534, "lr": 4.9171677407813146e-05, "epoch": 3.4794908062234793, "percentage": 17.4, "elapsed_time": "0:26:39", "remaining_time": "2:06:35", "throughput": 4645.79, "total_tokens": 7431712} {"current_steps": 7385, "total_steps": 42420, "loss": 0.2677, "lr": 4.916904954790467e-05, "epoch": 3.4818481848184817, "percentage": 17.41, "elapsed_time": "0:26:40", "remaining_time": "2:06:34", "throughput": 4645.97, "total_tokens": 7437088} {"current_steps": 7390, "total_steps": 42420, "loss": 0.1956, "lr": 4.9166417596586464e-05, "epoch": 3.484205563413484, "percentage": 17.42, "elapsed_time": "0:26:41", "remaining_time": "2:06:32", "throughput": 4646.11, "total_tokens": 7442240} {"current_steps": 7395, "total_steps": 42420, "loss": 0.044, "lr": 4.916378155430409e-05, "epoch": 3.4865629420084865, "percentage": 17.43, "elapsed_time": "0:26:42", "remaining_time": "2:06:31", "throughput": 4646.25, "total_tokens": 7446944} {"current_steps": 7400, "total_steps": 42420, "loss": 0.1725, "lr": 4.916114142150378e-05, "epoch": 3.488920320603489, "percentage": 17.44, "elapsed_time": "0:26:43", "remaining_time": "2:06:29", "throughput": 4646.26, "total_tokens": 7451328} {"current_steps": 7405, "total_steps": 42420, "loss": 0.255, "lr": 4.915849719863245e-05, "epoch": 3.4912776991984913, "percentage": 17.46, "elapsed_time": "0:26:44", "remaining_time": "2:06:28", "throughput": 4646.26, "total_tokens": 7456000} {"current_steps": 7410, "total_steps": 42420, "loss": 0.1793, "lr": 4.915584888613775e-05, "epoch": 3.4936350777934937, "percentage": 17.47, "elapsed_time": "0:26:45", "remaining_time": "2:06:26", "throughput": 4646.26, "total_tokens": 7460384} {"current_steps": 7415, "total_steps": 42420, "loss": 0.1451, "lr": 4.915319648446795e-05, "epoch": 3.495992456388496, "percentage": 17.48, "elapsed_time": "0:26:46", "remaining_time": "2:06:25", "throughput": 4646.45, "total_tokens": 7465920} {"current_steps": 7420, "total_steps": 42420, "loss": 0.2229, "lr": 4.9150539994072103e-05, "epoch": 3.4983498349834985, "percentage": 17.49, "elapsed_time": "0:26:47", "remaining_time": "2:06:23", "throughput": 4646.56, "total_tokens": 7470752} {"current_steps": 7425, "total_steps": 42420, "loss": 0.2288, "lr": 4.914787941539988e-05, "epoch": 3.500707213578501, "percentage": 17.5, "elapsed_time": "0:26:48", "remaining_time": "2:06:22", "throughput": 4646.58, "total_tokens": 7475168} {"current_steps": 7430, "total_steps": 42420, "loss": 0.2017, "lr": 4.914521474890168e-05, "epoch": 3.5030645921735033, "percentage": 17.52, "elapsed_time": "0:26:49", "remaining_time": "2:06:20", "throughput": 4646.58, "total_tokens": 7479648} {"current_steps": 7435, "total_steps": 42420, "loss": 0.0546, "lr": 4.9142545995028586e-05, "epoch": 3.5054219707685053, "percentage": 17.53, "elapsed_time": "0:26:50", "remaining_time": "2:06:18", "throughput": 4646.52, "total_tokens": 7483872} {"current_steps": 7440, "total_steps": 42420, "loss": 0.0871, "lr": 4.913987315423237e-05, "epoch": 3.5077793493635077, "percentage": 17.54, "elapsed_time": "0:26:51", "remaining_time": "2:06:17", "throughput": 4646.58, "total_tokens": 7489152} {"current_steps": 7445, "total_steps": 42420, "loss": 0.1702, "lr": 4.913719622696551e-05, "epoch": 3.51013672795851, "percentage": 17.55, "elapsed_time": "0:26:52", "remaining_time": "2:06:16", "throughput": 4646.67, "total_tokens": 7493760} {"current_steps": 7450, "total_steps": 42420, "loss": 0.1967, "lr": 4.9134515213681154e-05, "epoch": 3.5124941065535125, "percentage": 17.56, "elapsed_time": "0:26:53", "remaining_time": "2:06:14", "throughput": 4646.75, "total_tokens": 7497952} {"current_steps": 7455, "total_steps": 42420, "loss": 0.1543, "lr": 4.913183011483314e-05, "epoch": 3.514851485148515, "percentage": 17.57, "elapsed_time": "0:26:54", "remaining_time": "2:06:13", "throughput": 4646.84, "total_tokens": 7503872} {"current_steps": 7460, "total_steps": 42420, "loss": 0.1466, "lr": 4.9129140930876036e-05, "epoch": 3.5172088637435173, "percentage": 17.59, "elapsed_time": "0:26:55", "remaining_time": "2:06:12", "throughput": 4646.99, "total_tokens": 7509152} {"current_steps": 7465, "total_steps": 42420, "loss": 0.1066, "lr": 4.912644766226505e-05, "epoch": 3.5195662423385197, "percentage": 17.6, "elapsed_time": "0:26:56", "remaining_time": "2:06:11", "throughput": 4647.1, "total_tokens": 7513952} {"current_steps": 7470, "total_steps": 42420, "loss": 0.3186, "lr": 4.912375030945613e-05, "epoch": 3.521923620933522, "percentage": 17.61, "elapsed_time": "0:26:57", "remaining_time": "2:06:10", "throughput": 4647.02, "total_tokens": 7518720} {"current_steps": 7475, "total_steps": 42420, "loss": 0.1832, "lr": 4.912104887290587e-05, "epoch": 3.524280999528524, "percentage": 17.62, "elapsed_time": "0:26:59", "remaining_time": "2:06:08", "throughput": 4647.08, "total_tokens": 7523648} {"current_steps": 7480, "total_steps": 42420, "loss": 0.1126, "lr": 4.91183433530716e-05, "epoch": 3.5266383781235264, "percentage": 17.63, "elapsed_time": "0:26:59", "remaining_time": "2:06:07", "throughput": 4647.1, "total_tokens": 7528256} {"current_steps": 7485, "total_steps": 42420, "loss": 0.1206, "lr": 4.91156337504113e-05, "epoch": 3.528995756718529, "percentage": 17.64, "elapsed_time": "0:27:01", "remaining_time": "2:06:05", "throughput": 4647.13, "total_tokens": 7533248} {"current_steps": 7490, "total_steps": 42420, "loss": 0.376, "lr": 4.911292006538367e-05, "epoch": 3.5313531353135312, "percentage": 17.66, "elapsed_time": "0:27:02", "remaining_time": "2:06:04", "throughput": 4647.24, "total_tokens": 7538272} {"current_steps": 7495, "total_steps": 42420, "loss": 0.1718, "lr": 4.911020229844808e-05, "epoch": 3.5337105139085336, "percentage": 17.67, "elapsed_time": "0:27:03", "remaining_time": "2:06:03", "throughput": 4647.4, "total_tokens": 7543872} {"current_steps": 7500, "total_steps": 42420, "loss": 0.17, "lr": 4.9107480450064616e-05, "epoch": 3.536067892503536, "percentage": 17.68, "elapsed_time": "0:27:04", "remaining_time": "2:06:02", "throughput": 4647.52, "total_tokens": 7548576} {"current_steps": 7505, "total_steps": 42420, "loss": 0.2481, "lr": 4.910475452069403e-05, "epoch": 3.5384252710985384, "percentage": 17.69, "elapsed_time": "0:27:05", "remaining_time": "2:06:01", "throughput": 4647.73, "total_tokens": 7554336} {"current_steps": 7510, "total_steps": 42420, "loss": 0.0779, "lr": 4.9102024510797775e-05, "epoch": 3.540782649693541, "percentage": 17.7, "elapsed_time": "0:27:06", "remaining_time": "2:06:00", "throughput": 4647.78, "total_tokens": 7558880} {"current_steps": 7515, "total_steps": 42420, "loss": 0.095, "lr": 4.9099290420838e-05, "epoch": 3.5431400282885432, "percentage": 17.72, "elapsed_time": "0:27:07", "remaining_time": "2:05:58", "throughput": 4647.74, "total_tokens": 7563264} {"current_steps": 7520, "total_steps": 42420, "loss": 0.1982, "lr": 4.9096552251277544e-05, "epoch": 3.5454974068835456, "percentage": 17.73, "elapsed_time": "0:27:08", "remaining_time": "2:05:56", "throughput": 4647.77, "total_tokens": 7568064} {"current_steps": 7525, "total_steps": 42420, "loss": 0.116, "lr": 4.909381000257993e-05, "epoch": 3.547854785478548, "percentage": 17.74, "elapsed_time": "0:27:09", "remaining_time": "2:05:56", "throughput": 4647.99, "total_tokens": 7574432} {"current_steps": 7530, "total_steps": 42420, "loss": 0.2374, "lr": 4.909106367520937e-05, "epoch": 3.5502121640735504, "percentage": 17.75, "elapsed_time": "0:27:10", "remaining_time": "2:05:55", "throughput": 4648.05, "total_tokens": 7579328} {"current_steps": 7535, "total_steps": 42420, "loss": 0.1258, "lr": 4.908831326963077e-05, "epoch": 3.5525695426685524, "percentage": 17.76, "elapsed_time": "0:27:11", "remaining_time": "2:05:54", "throughput": 4648.12, "total_tokens": 7584608} {"current_steps": 7540, "total_steps": 42420, "loss": 0.1575, "lr": 4.9085558786309726e-05, "epoch": 3.554926921263555, "percentage": 17.77, "elapsed_time": "0:27:12", "remaining_time": "2:05:53", "throughput": 4648.25, "total_tokens": 7589600} {"current_steps": 7545, "total_steps": 42420, "loss": 0.0908, "lr": 4.908280022571254e-05, "epoch": 3.557284299858557, "percentage": 17.79, "elapsed_time": "0:27:13", "remaining_time": "2:05:52", "throughput": 4648.34, "total_tokens": 7594624} {"current_steps": 7550, "total_steps": 42420, "loss": 0.2299, "lr": 4.908003758830617e-05, "epoch": 3.5596416784535596, "percentage": 17.8, "elapsed_time": "0:27:14", "remaining_time": "2:05:50", "throughput": 4648.41, "total_tokens": 7599360} {"current_steps": 7555, "total_steps": 42420, "loss": 0.2312, "lr": 4.9077270874558296e-05, "epoch": 3.561999057048562, "percentage": 17.81, "elapsed_time": "0:27:15", "remaining_time": "2:05:48", "throughput": 4648.46, "total_tokens": 7603872} {"current_steps": 7560, "total_steps": 42420, "loss": 0.0706, "lr": 4.907450008493727e-05, "epoch": 3.5643564356435644, "percentage": 17.82, "elapsed_time": "0:27:16", "remaining_time": "2:05:47", "throughput": 4648.46, "total_tokens": 7608160} {"current_steps": 7565, "total_steps": 42420, "loss": 0.1772, "lr": 4.9071725219912143e-05, "epoch": 3.566713814238567, "percentage": 17.83, "elapsed_time": "0:27:17", "remaining_time": "2:05:46", "throughput": 4648.65, "total_tokens": 7614336} {"current_steps": 7570, "total_steps": 42420, "loss": 0.1923, "lr": 4.906894627995265e-05, "epoch": 3.569071192833569, "percentage": 17.85, "elapsed_time": "0:27:18", "remaining_time": "2:05:44", "throughput": 4648.75, "total_tokens": 7618592} {"current_steps": 7575, "total_steps": 42420, "loss": 0.0806, "lr": 4.9066163265529216e-05, "epoch": 3.571428571428571, "percentage": 17.86, "elapsed_time": "0:27:19", "remaining_time": "2:05:43", "throughput": 4648.84, "total_tokens": 7623296} {"current_steps": 7580, "total_steps": 42420, "loss": 0.1026, "lr": 4.9063376177112966e-05, "epoch": 3.5737859500235736, "percentage": 17.87, "elapsed_time": "0:27:21", "remaining_time": "2:05:42", "throughput": 4649.0, "total_tokens": 7629152} {"current_steps": 7585, "total_steps": 42420, "loss": 0.0392, "lr": 4.9060585015175695e-05, "epoch": 3.576143328618576, "percentage": 17.88, "elapsed_time": "0:27:21", "remaining_time": "2:05:40", "throughput": 4649.05, "total_tokens": 7633312} {"current_steps": 7590, "total_steps": 42420, "loss": 0.0673, "lr": 4.905778978018992e-05, "epoch": 3.5785007072135784, "percentage": 17.89, "elapsed_time": "0:27:22", "remaining_time": "2:05:38", "throughput": 4649.08, "total_tokens": 7637376} {"current_steps": 7595, "total_steps": 42420, "loss": 0.2387, "lr": 4.90549904726288e-05, "epoch": 3.580858085808581, "percentage": 17.9, "elapsed_time": "0:27:23", "remaining_time": "2:05:37", "throughput": 4649.12, "total_tokens": 7642080} {"current_steps": 7600, "total_steps": 42420, "loss": 0.1214, "lr": 4.9052187092966225e-05, "epoch": 3.583215464403583, "percentage": 17.92, "elapsed_time": "0:27:24", "remaining_time": "2:05:35", "throughput": 4649.03, "total_tokens": 7646752} {"current_steps": 7605, "total_steps": 42420, "loss": 0.2618, "lr": 4.904937964167676e-05, "epoch": 3.5855728429985856, "percentage": 17.93, "elapsed_time": "0:27:25", "remaining_time": "2:05:33", "throughput": 4649.15, "total_tokens": 7651200} {"current_steps": 7610, "total_steps": 42420, "loss": 0.2343, "lr": 4.904656811923567e-05, "epoch": 3.587930221593588, "percentage": 17.94, "elapsed_time": "0:27:26", "remaining_time": "2:05:32", "throughput": 4649.14, "total_tokens": 7655456} {"current_steps": 7615, "total_steps": 42420, "loss": 0.0823, "lr": 4.904375252611887e-05, "epoch": 3.5902876001885904, "percentage": 17.95, "elapsed_time": "0:27:27", "remaining_time": "2:05:30", "throughput": 4649.1, "total_tokens": 7659360} {"current_steps": 7620, "total_steps": 42420, "loss": 0.2061, "lr": 4.9040932862803014e-05, "epoch": 3.592644978783593, "percentage": 17.96, "elapsed_time": "0:27:28", "remaining_time": "2:05:28", "throughput": 4649.15, "total_tokens": 7663904} {"current_steps": 7625, "total_steps": 42420, "loss": 0.1298, "lr": 4.9038109129765405e-05, "epoch": 3.595002357378595, "percentage": 17.98, "elapsed_time": "0:27:29", "remaining_time": "2:05:26", "throughput": 4649.24, "total_tokens": 7668352} {"current_steps": 7630, "total_steps": 42420, "loss": 0.0807, "lr": 4.9035281327484075e-05, "epoch": 3.5973597359735976, "percentage": 17.99, "elapsed_time": "0:27:30", "remaining_time": "2:05:25", "throughput": 4649.37, "total_tokens": 7673952} {"current_steps": 7635, "total_steps": 42420, "loss": 0.1476, "lr": 4.9032449456437706e-05, "epoch": 3.5997171145685996, "percentage": 18.0, "elapsed_time": "0:27:31", "remaining_time": "2:05:25", "throughput": 4649.51, "total_tokens": 7679648} {"current_steps": 7640, "total_steps": 42420, "loss": 0.0787, "lr": 4.90296135171057e-05, "epoch": 3.602074493163602, "percentage": 18.01, "elapsed_time": "0:27:32", "remaining_time": "2:05:23", "throughput": 4649.62, "total_tokens": 7684192} {"current_steps": 7645, "total_steps": 42420, "loss": 0.0634, "lr": 4.9026773509968115e-05, "epoch": 3.6044318717586044, "percentage": 18.02, "elapsed_time": "0:27:33", "remaining_time": "2:05:22", "throughput": 4649.76, "total_tokens": 7689376} {"current_steps": 7650, "total_steps": 42420, "loss": 0.0526, "lr": 4.902392943550573e-05, "epoch": 3.6067892503536068, "percentage": 18.03, "elapsed_time": "0:27:34", "remaining_time": "2:05:20", "throughput": 4649.87, "total_tokens": 7694336} {"current_steps": 7655, "total_steps": 42420, "loss": 0.1138, "lr": 4.90210812942e-05, "epoch": 3.609146628948609, "percentage": 18.05, "elapsed_time": "0:27:35", "remaining_time": "2:05:19", "throughput": 4649.97, "total_tokens": 7699648} {"current_steps": 7660, "total_steps": 42420, "loss": 0.113, "lr": 4.901822908653305e-05, "epoch": 3.6115040075436116, "percentage": 18.06, "elapsed_time": "0:27:36", "remaining_time": "2:05:19", "throughput": 4650.19, "total_tokens": 7705184} {"current_steps": 7665, "total_steps": 42420, "loss": 0.106, "lr": 4.9015372812987734e-05, "epoch": 3.613861386138614, "percentage": 18.07, "elapsed_time": "0:27:38", "remaining_time": "2:05:19", "throughput": 4650.47, "total_tokens": 7712064} {"current_steps": 7670, "total_steps": 42420, "loss": 0.1521, "lr": 4.901251247404756e-05, "epoch": 3.6162187647336164, "percentage": 18.08, "elapsed_time": "0:27:39", "remaining_time": "2:05:18", "throughput": 4650.6, "total_tokens": 7717216} {"current_steps": 7675, "total_steps": 42420, "loss": 0.0978, "lr": 4.900964807019672e-05, "epoch": 3.6185761433286183, "percentage": 18.09, "elapsed_time": "0:27:40", "remaining_time": "2:05:17", "throughput": 4650.75, "total_tokens": 7722848} {"current_steps": 7680, "total_steps": 42420, "loss": 0.0757, "lr": 4.900677960192013e-05, "epoch": 3.6209335219236207, "percentage": 18.1, "elapsed_time": "0:27:41", "remaining_time": "2:05:16", "throughput": 4650.9, "total_tokens": 7727872} {"current_steps": 7685, "total_steps": 42420, "loss": 0.1945, "lr": 4.9003907069703364e-05, "epoch": 3.623290900518623, "percentage": 18.12, "elapsed_time": "0:27:42", "remaining_time": "2:05:15", "throughput": 4650.95, "total_tokens": 7733056} {"current_steps": 7690, "total_steps": 42420, "loss": 0.1034, "lr": 4.9001030474032695e-05, "epoch": 3.6256482791136255, "percentage": 18.13, "elapsed_time": "0:27:43", "remaining_time": "2:05:13", "throughput": 4651.01, "total_tokens": 7737792} {"current_steps": 7695, "total_steps": 42420, "loss": 0.1711, "lr": 4.899814981539508e-05, "epoch": 3.628005657708628, "percentage": 18.14, "elapsed_time": "0:27:44", "remaining_time": "2:05:11", "throughput": 4650.98, "total_tokens": 7742016} {"current_steps": 7700, "total_steps": 42420, "loss": 0.1318, "lr": 4.899526509427817e-05, "epoch": 3.6303630363036303, "percentage": 18.15, "elapsed_time": "0:27:46", "remaining_time": "2:05:12", "throughput": 4651.24, "total_tokens": 7749632} {"current_steps": 7705, "total_steps": 42420, "loss": 0.0966, "lr": 4.8992376311170296e-05, "epoch": 3.6327204148986327, "percentage": 18.16, "elapsed_time": "0:27:47", "remaining_time": "2:05:11", "throughput": 4651.37, "total_tokens": 7754656} {"current_steps": 7710, "total_steps": 42420, "loss": 0.1708, "lr": 4.8989483466560475e-05, "epoch": 3.635077793493635, "percentage": 18.18, "elapsed_time": "0:27:48", "remaining_time": "2:05:09", "throughput": 4651.49, "total_tokens": 7759424} {"current_steps": 7715, "total_steps": 42420, "loss": 0.051, "lr": 4.8986586560938426e-05, "epoch": 3.6374351720886375, "percentage": 18.19, "elapsed_time": "0:27:49", "remaining_time": "2:05:08", "throughput": 4651.69, "total_tokens": 7764672} {"current_steps": 7720, "total_steps": 42420, "loss": 0.1125, "lr": 4.898368559479454e-05, "epoch": 3.63979255068364, "percentage": 18.2, "elapsed_time": "0:27:50", "remaining_time": "2:05:08", "throughput": 4651.88, "total_tokens": 7770880} {"current_steps": 7725, "total_steps": 42420, "loss": 0.027, "lr": 4.89807805686199e-05, "epoch": 3.6421499292786423, "percentage": 18.21, "elapsed_time": "0:27:51", "remaining_time": "2:05:07", "throughput": 4652.02, "total_tokens": 7775744} {"current_steps": 7730, "total_steps": 42420, "loss": 0.1876, "lr": 4.897787148290628e-05, "epoch": 3.6445073078736447, "percentage": 18.22, "elapsed_time": "0:27:52", "remaining_time": "2:05:05", "throughput": 4652.09, "total_tokens": 7780320} {"current_steps": 7735, "total_steps": 42420, "loss": 0.1216, "lr": 4.897495833814614e-05, "epoch": 3.6468646864686467, "percentage": 18.23, "elapsed_time": "0:27:53", "remaining_time": "2:05:03", "throughput": 4652.15, "total_tokens": 7784768} {"current_steps": 7740, "total_steps": 42420, "loss": 0.1781, "lr": 4.8972041134832626e-05, "epoch": 3.649222065063649, "percentage": 18.25, "elapsed_time": "0:27:54", "remaining_time": "2:05:02", "throughput": 4652.43, "total_tokens": 7790464} {"current_steps": 7745, "total_steps": 42420, "loss": 0.298, "lr": 4.896911987345957e-05, "epoch": 3.6515794436586515, "percentage": 18.26, "elapsed_time": "0:27:55", "remaining_time": "2:05:01", "throughput": 4652.56, "total_tokens": 7795584} {"current_steps": 7750, "total_steps": 42420, "loss": 0.1831, "lr": 4.896619455452149e-05, "epoch": 3.653936822253654, "percentage": 18.27, "elapsed_time": "0:27:56", "remaining_time": "2:05:00", "throughput": 4652.66, "total_tokens": 7800864} {"current_steps": 7755, "total_steps": 42420, "loss": 0.0736, "lr": 4.89632651785136e-05, "epoch": 3.6562942008486563, "percentage": 18.28, "elapsed_time": "0:27:57", "remaining_time": "2:04:58", "throughput": 4652.67, "total_tokens": 7804896} {"current_steps": 7760, "total_steps": 42420, "loss": 0.2575, "lr": 4.8960331745931783e-05, "epoch": 3.6586515794436587, "percentage": 18.29, "elapsed_time": "0:27:58", "remaining_time": "2:04:56", "throughput": 4652.75, "total_tokens": 7809376} {"current_steps": 7765, "total_steps": 42420, "loss": 0.2276, "lr": 4.895739425727263e-05, "epoch": 3.661008958038661, "percentage": 18.31, "elapsed_time": "0:27:59", "remaining_time": "2:04:55", "throughput": 4652.75, "total_tokens": 7813920} {"current_steps": 7770, "total_steps": 42420, "loss": 0.213, "lr": 4.89544527130334e-05, "epoch": 3.6633663366336635, "percentage": 18.32, "elapsed_time": "0:28:00", "remaining_time": "2:04:53", "throughput": 4652.8, "total_tokens": 7818112} {"current_steps": 7775, "total_steps": 42420, "loss": 0.2047, "lr": 4.8951507113712045e-05, "epoch": 3.6657237152286655, "percentage": 18.33, "elapsed_time": "0:28:01", "remaining_time": "2:04:51", "throughput": 4652.94, "total_tokens": 7823104} {"current_steps": 7780, "total_steps": 42420, "loss": 0.2075, "lr": 4.894855745980722e-05, "epoch": 3.668081093823668, "percentage": 18.34, "elapsed_time": "0:28:02", "remaining_time": "2:04:50", "throughput": 4653.09, "total_tokens": 7828256} {"current_steps": 7785, "total_steps": 42420, "loss": 0.1392, "lr": 4.894560375181823e-05, "epoch": 3.6704384724186703, "percentage": 18.35, "elapsed_time": "0:28:03", "remaining_time": "2:04:49", "throughput": 4653.24, "total_tokens": 7833600} {"current_steps": 7790, "total_steps": 42420, "loss": 0.1918, "lr": 4.8942645990245095e-05, "epoch": 3.6727958510136727, "percentage": 18.36, "elapsed_time": "0:28:04", "remaining_time": "2:04:48", "throughput": 4653.32, "total_tokens": 7838208} {"current_steps": 7795, "total_steps": 42420, "loss": 0.1692, "lr": 4.893968417558853e-05, "epoch": 3.675153229608675, "percentage": 18.38, "elapsed_time": "0:28:05", "remaining_time": "2:04:46", "throughput": 4653.41, "total_tokens": 7843296} {"current_steps": 7800, "total_steps": 42420, "loss": 0.2146, "lr": 4.8936718308349894e-05, "epoch": 3.6775106082036775, "percentage": 18.39, "elapsed_time": "0:28:06", "remaining_time": "2:04:46", "throughput": 4653.58, "total_tokens": 7849024} {"current_steps": 7805, "total_steps": 42420, "loss": 0.2808, "lr": 4.8933748389031276e-05, "epoch": 3.67986798679868, "percentage": 18.4, "elapsed_time": "0:28:07", "remaining_time": "2:04:44", "throughput": 4653.71, "total_tokens": 7853792} {"current_steps": 7810, "total_steps": 42420, "loss": 0.1465, "lr": 4.893077441813543e-05, "epoch": 3.6822253653936823, "percentage": 18.41, "elapsed_time": "0:28:08", "remaining_time": "2:04:42", "throughput": 4653.71, "total_tokens": 7857824} {"current_steps": 7815, "total_steps": 42420, "loss": 0.0439, "lr": 4.892779639616579e-05, "epoch": 3.6845827439886847, "percentage": 18.42, "elapsed_time": "0:28:09", "remaining_time": "2:04:41", "throughput": 4653.84, "total_tokens": 7863008} {"current_steps": 7820, "total_steps": 42420, "loss": 0.2856, "lr": 4.89248143236265e-05, "epoch": 3.686940122583687, "percentage": 18.43, "elapsed_time": "0:28:10", "remaining_time": "2:04:40", "throughput": 4653.99, "total_tokens": 7867968} {"current_steps": 7825, "total_steps": 42420, "loss": 0.0462, "lr": 4.8921828201022365e-05, "epoch": 3.6892975011786895, "percentage": 18.45, "elapsed_time": "0:28:11", "remaining_time": "2:04:38", "throughput": 4654.09, "total_tokens": 7872928} {"current_steps": 7830, "total_steps": 42420, "loss": 0.1371, "lr": 4.8918838028858874e-05, "epoch": 3.691654879773692, "percentage": 18.46, "elapsed_time": "0:28:12", "remaining_time": "2:04:37", "throughput": 4654.2, "total_tokens": 7878304} {"current_steps": 7835, "total_steps": 42420, "loss": 0.1063, "lr": 4.891584380764224e-05, "epoch": 3.694012258368694, "percentage": 18.47, "elapsed_time": "0:28:13", "remaining_time": "2:04:36", "throughput": 4654.29, "total_tokens": 7883168} {"current_steps": 7840, "total_steps": 42420, "loss": 0.1652, "lr": 4.8912845537879305e-05, "epoch": 3.6963696369636962, "percentage": 18.48, "elapsed_time": "0:28:14", "remaining_time": "2:04:34", "throughput": 4654.29, "total_tokens": 7887456} {"current_steps": 7845, "total_steps": 42420, "loss": 0.072, "lr": 4.890984322007763e-05, "epoch": 3.6987270155586986, "percentage": 18.49, "elapsed_time": "0:28:15", "remaining_time": "2:04:33", "throughput": 4654.31, "total_tokens": 7892000} {"current_steps": 7850, "total_steps": 42420, "loss": 0.0889, "lr": 4.890683685474548e-05, "epoch": 3.701084394153701, "percentage": 18.51, "elapsed_time": "0:28:16", "remaining_time": "2:04:31", "throughput": 4654.4, "total_tokens": 7896544} {"current_steps": 7855, "total_steps": 42420, "loss": 0.0989, "lr": 4.890382644239176e-05, "epoch": 3.7034417727487035, "percentage": 18.52, "elapsed_time": "0:28:17", "remaining_time": "2:04:30", "throughput": 4654.51, "total_tokens": 7901536} {"current_steps": 7860, "total_steps": 42420, "loss": 0.1182, "lr": 4.890081198352609e-05, "epoch": 3.705799151343706, "percentage": 18.53, "elapsed_time": "0:28:18", "remaining_time": "2:04:28", "throughput": 4654.64, "total_tokens": 7906592} {"current_steps": 7865, "total_steps": 42420, "loss": 0.17, "lr": 4.889779347865876e-05, "epoch": 3.7081565299387083, "percentage": 18.54, "elapsed_time": "0:28:19", "remaining_time": "2:04:27", "throughput": 4654.8, "total_tokens": 7911776} {"current_steps": 7870, "total_steps": 42420, "loss": 0.3424, "lr": 4.889477092830075e-05, "epoch": 3.7105139085337107, "percentage": 18.55, "elapsed_time": "0:28:20", "remaining_time": "2:04:26", "throughput": 4654.92, "total_tokens": 7917024} {"current_steps": 7875, "total_steps": 42420, "loss": 0.1809, "lr": 4.889174433296374e-05, "epoch": 3.7128712871287126, "percentage": 18.56, "elapsed_time": "0:28:21", "remaining_time": "2:04:25", "throughput": 4655.08, "total_tokens": 7922592} {"current_steps": 7880, "total_steps": 42420, "loss": 0.162, "lr": 4.888871369316007e-05, "epoch": 3.715228665723715, "percentage": 18.58, "elapsed_time": "0:28:22", "remaining_time": "2:04:24", "throughput": 4655.26, "total_tokens": 7927776} {"current_steps": 7885, "total_steps": 42420, "loss": 0.0542, "lr": 4.888567900940278e-05, "epoch": 3.7175860443187174, "percentage": 18.59, "elapsed_time": "0:28:24", "remaining_time": "2:04:23", "throughput": 4655.33, "total_tokens": 7933184} {"current_steps": 7890, "total_steps": 42420, "loss": 0.1217, "lr": 4.888264028220559e-05, "epoch": 3.71994342291372, "percentage": 18.6, "elapsed_time": "0:28:24", "remaining_time": "2:04:21", "throughput": 4655.32, "total_tokens": 7937152} {"current_steps": 7895, "total_steps": 42420, "loss": 0.0829, "lr": 4.88795975120829e-05, "epoch": 3.7223008015087222, "percentage": 18.61, "elapsed_time": "0:28:26", "remaining_time": "2:04:20", "throughput": 4655.47, "total_tokens": 7942464} {"current_steps": 7900, "total_steps": 42420, "loss": 0.0709, "lr": 4.887655069954981e-05, "epoch": 3.7246581801037246, "percentage": 18.62, "elapsed_time": "0:28:26", "remaining_time": "2:04:18", "throughput": 4655.52, "total_tokens": 7946848} {"current_steps": 7905, "total_steps": 42420, "loss": 0.0626, "lr": 4.8873499845122084e-05, "epoch": 3.727015558698727, "percentage": 18.64, "elapsed_time": "0:28:28", "remaining_time": "2:04:17", "throughput": 4655.63, "total_tokens": 7951872} {"current_steps": 7910, "total_steps": 42420, "loss": 0.1276, "lr": 4.8870444949316186e-05, "epoch": 3.7293729372937294, "percentage": 18.65, "elapsed_time": "0:28:29", "remaining_time": "2:04:16", "throughput": 4655.81, "total_tokens": 7957120} {"current_steps": 7915, "total_steps": 42420, "loss": 0.1536, "lr": 4.886738601264925e-05, "epoch": 3.731730315888732, "percentage": 18.66, "elapsed_time": "0:28:30", "remaining_time": "2:04:16", "throughput": 4656.0, "total_tokens": 7963616} {"current_steps": 7920, "total_steps": 42420, "loss": 0.081, "lr": 4.8864323035639117e-05, "epoch": 3.7340876944837342, "percentage": 18.67, "elapsed_time": "0:28:31", "remaining_time": "2:04:15", "throughput": 4656.11, "total_tokens": 7969248} {"current_steps": 7925, "total_steps": 42420, "loss": 0.1931, "lr": 4.886125601880428e-05, "epoch": 3.7364450730787366, "percentage": 18.68, "elapsed_time": "0:28:32", "remaining_time": "2:04:14", "throughput": 4656.3, "total_tokens": 7974656} {"current_steps": 7930, "total_steps": 42420, "loss": 0.0733, "lr": 4.885818496266394e-05, "epoch": 3.738802451673739, "percentage": 18.69, "elapsed_time": "0:28:33", "remaining_time": "2:04:14", "throughput": 4656.65, "total_tokens": 7981184} {"current_steps": 7935, "total_steps": 42420, "loss": 0.179, "lr": 4.885510986773797e-05, "epoch": 3.741159830268741, "percentage": 18.71, "elapsed_time": "0:28:34", "remaining_time": "2:04:12", "throughput": 4656.7, "total_tokens": 7985856} {"current_steps": 7940, "total_steps": 42420, "loss": 0.1332, "lr": 4.8852030734546946e-05, "epoch": 3.7435172088637434, "percentage": 18.72, "elapsed_time": "0:28:36", "remaining_time": "2:04:13", "throughput": 4657.03, "total_tokens": 7993088} {"current_steps": 7945, "total_steps": 42420, "loss": 0.1482, "lr": 4.88489475636121e-05, "epoch": 3.745874587458746, "percentage": 18.73, "elapsed_time": "0:28:37", "remaining_time": "2:04:11", "throughput": 4657.12, "total_tokens": 7997760} {"current_steps": 7950, "total_steps": 42420, "loss": 0.0709, "lr": 4.884586035545536e-05, "epoch": 3.748231966053748, "percentage": 18.74, "elapsed_time": "0:28:38", "remaining_time": "2:04:11", "throughput": 4657.32, "total_tokens": 8003648} {"current_steps": 7955, "total_steps": 42420, "loss": 0.0724, "lr": 4.884276911059934e-05, "epoch": 3.7505893446487506, "percentage": 18.75, "elapsed_time": "0:28:39", "remaining_time": "2:04:10", "throughput": 4657.55, "total_tokens": 8009248} {"current_steps": 7960, "total_steps": 42420, "loss": 0.1726, "lr": 4.8839673829567343e-05, "epoch": 3.752946723243753, "percentage": 18.76, "elapsed_time": "0:28:40", "remaining_time": "2:04:09", "throughput": 4657.68, "total_tokens": 8014464} {"current_steps": 7965, "total_steps": 42420, "loss": 0.118, "lr": 4.883657451288334e-05, "epoch": 3.7553041018387554, "percentage": 18.78, "elapsed_time": "0:28:41", "remaining_time": "2:04:07", "throughput": 4657.73, "total_tokens": 8018560} {"current_steps": 7970, "total_steps": 42420, "loss": 0.1693, "lr": 4.8833471161071995e-05, "epoch": 3.757661480433758, "percentage": 18.79, "elapsed_time": "0:28:42", "remaining_time": "2:04:06", "throughput": 4657.76, "total_tokens": 8023712} {"current_steps": 7975, "total_steps": 42420, "loss": 0.1595, "lr": 4.883036377465864e-05, "epoch": 3.7600188590287598, "percentage": 18.8, "elapsed_time": "0:28:43", "remaining_time": "2:04:04", "throughput": 4657.86, "total_tokens": 8028736} {"current_steps": 7980, "total_steps": 42420, "loss": 0.1182, "lr": 4.8827252354169325e-05, "epoch": 3.762376237623762, "percentage": 18.81, "elapsed_time": "0:28:44", "remaining_time": "2:04:03", "throughput": 4658.0, "total_tokens": 8033632} {"current_steps": 7985, "total_steps": 42420, "loss": 0.107, "lr": 4.882413690013076e-05, "epoch": 3.7647336162187646, "percentage": 18.82, "elapsed_time": "0:28:45", "remaining_time": "2:04:01", "throughput": 4657.86, "total_tokens": 8037376} {"current_steps": 7990, "total_steps": 42420, "loss": 0.1694, "lr": 4.882101741307031e-05, "epoch": 3.767090994813767, "percentage": 18.84, "elapsed_time": "0:28:46", "remaining_time": "2:03:59", "throughput": 4657.94, "total_tokens": 8041952} {"current_steps": 7995, "total_steps": 42420, "loss": 0.1066, "lr": 4.8817893893516076e-05, "epoch": 3.7694483734087694, "percentage": 18.85, "elapsed_time": "0:28:47", "remaining_time": "2:03:58", "throughput": 4658.02, "total_tokens": 8046752} {"current_steps": 8000, "total_steps": 42420, "loss": 0.1654, "lr": 4.8814766341996816e-05, "epoch": 3.7718057520037718, "percentage": 18.86, "elapsed_time": "0:28:48", "remaining_time": "2:03:56", "throughput": 4658.06, "total_tokens": 8051136} {"current_steps": 8005, "total_steps": 42420, "loss": 0.1843, "lr": 4.881163475904196e-05, "epoch": 3.774163130598774, "percentage": 18.87, "elapsed_time": "0:28:49", "remaining_time": "2:03:56", "throughput": 4658.29, "total_tokens": 8057280} {"current_steps": 8010, "total_steps": 42420, "loss": 0.0708, "lr": 4.880849914518164e-05, "epoch": 3.7765205091937766, "percentage": 18.88, "elapsed_time": "0:28:50", "remaining_time": "2:03:55", "throughput": 4658.45, "total_tokens": 8062688} {"current_steps": 8015, "total_steps": 42420, "loss": 0.0787, "lr": 4.8805359500946655e-05, "epoch": 3.778877887788779, "percentage": 18.89, "elapsed_time": "0:28:51", "remaining_time": "2:03:53", "throughput": 4658.55, "total_tokens": 8067584} {"current_steps": 8020, "total_steps": 42420, "loss": 0.0754, "lr": 4.880221582686851e-05, "epoch": 3.7812352663837814, "percentage": 18.91, "elapsed_time": "0:28:52", "remaining_time": "2:03:53", "throughput": 4658.6, "total_tokens": 8073056} {"current_steps": 8025, "total_steps": 42420, "loss": 0.1237, "lr": 4.879906812347935e-05, "epoch": 3.783592644978784, "percentage": 18.92, "elapsed_time": "0:28:53", "remaining_time": "2:03:51", "throughput": 4658.64, "total_tokens": 8077504} {"current_steps": 8030, "total_steps": 42420, "loss": 0.0917, "lr": 4.879591639131206e-05, "epoch": 3.785950023573786, "percentage": 18.93, "elapsed_time": "0:28:54", "remaining_time": "2:03:50", "throughput": 4658.78, "total_tokens": 8082720} {"current_steps": 8035, "total_steps": 42420, "loss": 0.2862, "lr": 4.879276063090014e-05, "epoch": 3.7883074021687886, "percentage": 18.94, "elapsed_time": "0:28:55", "remaining_time": "2:03:48", "throughput": 4658.77, "total_tokens": 8086944} {"current_steps": 8040, "total_steps": 42420, "loss": 0.1976, "lr": 4.8789600842777824e-05, "epoch": 3.7906647807637905, "percentage": 18.95, "elapsed_time": "0:28:57", "remaining_time": "2:03:47", "throughput": 4658.82, "total_tokens": 8092448} {"current_steps": 8045, "total_steps": 42420, "loss": 0.1515, "lr": 4.8786437027480024e-05, "epoch": 3.793022159358793, "percentage": 18.97, "elapsed_time": "0:28:58", "remaining_time": "2:03:46", "throughput": 4658.95, "total_tokens": 8097344} {"current_steps": 8050, "total_steps": 42420, "loss": 0.0964, "lr": 4.878326918554229e-05, "epoch": 3.7953795379537953, "percentage": 18.98, "elapsed_time": "0:28:58", "remaining_time": "2:03:44", "throughput": 4659.03, "total_tokens": 8102016} {"current_steps": 8055, "total_steps": 42420, "loss": 0.2829, "lr": 4.878009731750091e-05, "epoch": 3.7977369165487977, "percentage": 18.99, "elapsed_time": "0:29:00", "remaining_time": "2:03:43", "throughput": 4659.09, "total_tokens": 8107456} {"current_steps": 8060, "total_steps": 42420, "loss": 0.1887, "lr": 4.877692142389282e-05, "epoch": 3.8000942951438, "percentage": 19.0, "elapsed_time": "0:29:01", "remaining_time": "2:03:42", "throughput": 4659.2, "total_tokens": 8112576} {"current_steps": 8065, "total_steps": 42420, "loss": 0.0392, "lr": 4.877374150525563e-05, "epoch": 3.8024516737388026, "percentage": 19.01, "elapsed_time": "0:29:02", "remaining_time": "2:03:41", "throughput": 4659.14, "total_tokens": 8116928} {"current_steps": 8070, "total_steps": 42420, "loss": 0.1458, "lr": 4.877055756212767e-05, "epoch": 3.804809052333805, "percentage": 19.02, "elapsed_time": "0:29:03", "remaining_time": "2:03:39", "throughput": 4659.06, "total_tokens": 8121376} {"current_steps": 8075, "total_steps": 42420, "loss": 0.0816, "lr": 4.876736959504791e-05, "epoch": 3.807166430928807, "percentage": 19.04, "elapsed_time": "0:29:04", "remaining_time": "2:03:38", "throughput": 4659.03, "total_tokens": 8125952} {"current_steps": 8080, "total_steps": 42420, "loss": 0.1118, "lr": 4.8764177604556024e-05, "epoch": 3.8095238095238093, "percentage": 19.05, "elapsed_time": "0:29:05", "remaining_time": "2:03:36", "throughput": 4659.08, "total_tokens": 8130688} {"current_steps": 8085, "total_steps": 42420, "loss": 0.1105, "lr": 4.876098159119236e-05, "epoch": 3.8118811881188117, "percentage": 19.06, "elapsed_time": "0:29:06", "remaining_time": "2:03:35", "throughput": 4659.16, "total_tokens": 8136032} {"current_steps": 8090, "total_steps": 42420, "loss": 0.3174, "lr": 4.875778155549795e-05, "epoch": 3.814238566713814, "percentage": 19.07, "elapsed_time": "0:29:07", "remaining_time": "2:03:34", "throughput": 4659.26, "total_tokens": 8141024} {"current_steps": 8095, "total_steps": 42420, "loss": 0.0775, "lr": 4.875457749801451e-05, "epoch": 3.8165959453088165, "percentage": 19.08, "elapsed_time": "0:29:08", "remaining_time": "2:03:33", "throughput": 4659.38, "total_tokens": 8146176} {"current_steps": 8100, "total_steps": 42420, "loss": 0.1534, "lr": 4.875136941928444e-05, "epoch": 3.818953323903819, "percentage": 19.09, "elapsed_time": "0:29:09", "remaining_time": "2:03:32", "throughput": 4659.54, "total_tokens": 8151232} {"current_steps": 8105, "total_steps": 42420, "loss": 0.2398, "lr": 4.874815731985079e-05, "epoch": 3.8213107024988213, "percentage": 19.11, "elapsed_time": "0:29:10", "remaining_time": "2:03:30", "throughput": 4659.65, "total_tokens": 8156192} {"current_steps": 8110, "total_steps": 42420, "loss": 0.1152, "lr": 4.8744941200257325e-05, "epoch": 3.8236680810938237, "percentage": 19.12, "elapsed_time": "0:29:11", "remaining_time": "2:03:29", "throughput": 4659.68, "total_tokens": 8160640} {"current_steps": 8115, "total_steps": 42420, "loss": 0.0682, "lr": 4.874172106104849e-05, "epoch": 3.826025459688826, "percentage": 19.13, "elapsed_time": "0:29:12", "remaining_time": "2:03:27", "throughput": 4659.72, "total_tokens": 8165024} {"current_steps": 8120, "total_steps": 42420, "loss": 0.1126, "lr": 4.873849690276938e-05, "epoch": 3.8283828382838285, "percentage": 19.14, "elapsed_time": "0:29:13", "remaining_time": "2:03:27", "throughput": 4659.93, "total_tokens": 8171296} {"current_steps": 8125, "total_steps": 42420, "loss": 0.192, "lr": 4.873526872596581e-05, "epoch": 3.830740216878831, "percentage": 19.15, "elapsed_time": "0:29:14", "remaining_time": "2:03:25", "throughput": 4660.12, "total_tokens": 8176576} {"current_steps": 8130, "total_steps": 42420, "loss": 0.2558, "lr": 4.8732036531184247e-05, "epoch": 3.8330975954738333, "percentage": 19.17, "elapsed_time": "0:29:15", "remaining_time": "2:03:24", "throughput": 4660.14, "total_tokens": 8181216} {"current_steps": 8135, "total_steps": 42420, "loss": 0.1049, "lr": 4.8728800318971846e-05, "epoch": 3.8354549740688357, "percentage": 19.18, "elapsed_time": "0:29:16", "remaining_time": "2:03:23", "throughput": 4660.16, "total_tokens": 8186016} {"current_steps": 8140, "total_steps": 42420, "loss": 0.1138, "lr": 4.872556008987644e-05, "epoch": 3.8378123526638377, "percentage": 19.19, "elapsed_time": "0:29:17", "remaining_time": "2:03:22", "throughput": 4660.1, "total_tokens": 8190944} {"current_steps": 8145, "total_steps": 42420, "loss": 0.2512, "lr": 4.872231584444654e-05, "epoch": 3.84016973125884, "percentage": 19.2, "elapsed_time": "0:29:18", "remaining_time": "2:03:20", "throughput": 4660.07, "total_tokens": 8195200} {"current_steps": 8150, "total_steps": 42420, "loss": 0.2751, "lr": 4.871906758323136e-05, "epoch": 3.8425271098538425, "percentage": 19.21, "elapsed_time": "0:29:19", "remaining_time": "2:03:18", "throughput": 4660.04, "total_tokens": 8199552} {"current_steps": 8155, "total_steps": 42420, "loss": 0.2223, "lr": 4.8715815306780764e-05, "epoch": 3.844884488448845, "percentage": 19.22, "elapsed_time": "0:29:20", "remaining_time": "2:03:17", "throughput": 4660.11, "total_tokens": 8204064} {"current_steps": 8160, "total_steps": 42420, "loss": 0.1211, "lr": 4.871255901564531e-05, "epoch": 3.8472418670438473, "percentage": 19.24, "elapsed_time": "0:29:21", "remaining_time": "2:03:15", "throughput": 4660.2, "total_tokens": 8208832} {"current_steps": 8165, "total_steps": 42420, "loss": 0.2138, "lr": 4.870929871037623e-05, "epoch": 3.8495992456388497, "percentage": 19.25, "elapsed_time": "0:29:22", "remaining_time": "2:03:14", "throughput": 4660.32, "total_tokens": 8213696} {"current_steps": 8170, "total_steps": 42420, "loss": 0.3262, "lr": 4.870603439152543e-05, "epoch": 3.851956624233852, "percentage": 19.26, "elapsed_time": "0:29:23", "remaining_time": "2:03:12", "throughput": 4660.3, "total_tokens": 8218048} {"current_steps": 8175, "total_steps": 42420, "loss": 0.1378, "lr": 4.8702766059645523e-05, "epoch": 3.854314002828854, "percentage": 19.27, "elapsed_time": "0:29:24", "remaining_time": "2:03:10", "throughput": 4660.22, "total_tokens": 8221856} {"current_steps": 8180, "total_steps": 42420, "loss": 0.0841, "lr": 4.869949371528977e-05, "epoch": 3.8566713814238565, "percentage": 19.28, "elapsed_time": "0:29:25", "remaining_time": "2:03:09", "throughput": 4660.35, "total_tokens": 8227584} {"current_steps": 8185, "total_steps": 42420, "loss": 0.16, "lr": 4.869621735901213e-05, "epoch": 3.859028760018859, "percentage": 19.3, "elapsed_time": "0:29:26", "remaining_time": "2:03:09", "throughput": 4660.52, "total_tokens": 8233280} {"current_steps": 8190, "total_steps": 42420, "loss": 0.2135, "lr": 4.869293699136722e-05, "epoch": 3.8613861386138613, "percentage": 19.31, "elapsed_time": "0:29:27", "remaining_time": "2:03:07", "throughput": 4660.56, "total_tokens": 8237568} {"current_steps": 8195, "total_steps": 42420, "loss": 0.1426, "lr": 4.868965261291036e-05, "epoch": 3.8637435172088637, "percentage": 19.32, "elapsed_time": "0:29:28", "remaining_time": "2:03:06", "throughput": 4660.76, "total_tokens": 8243200} {"current_steps": 8200, "total_steps": 42420, "loss": 0.0523, "lr": 4.8686364224197556e-05, "epoch": 3.866100895803866, "percentage": 19.33, "elapsed_time": "0:29:29", "remaining_time": "2:03:04", "throughput": 4660.82, "total_tokens": 8247520} {"current_steps": 8205, "total_steps": 42420, "loss": 0.0815, "lr": 4.8683071825785446e-05, "epoch": 3.8684582743988685, "percentage": 19.34, "elapsed_time": "0:29:30", "remaining_time": "2:03:03", "throughput": 4660.84, "total_tokens": 8252192} {"current_steps": 8210, "total_steps": 42420, "loss": 0.1827, "lr": 4.86797754182314e-05, "epoch": 3.870815652993871, "percentage": 19.35, "elapsed_time": "0:29:31", "remaining_time": "2:03:01", "throughput": 4660.96, "total_tokens": 8257024} {"current_steps": 8215, "total_steps": 42420, "loss": 0.1853, "lr": 4.8676475002093424e-05, "epoch": 3.8731730315888733, "percentage": 19.37, "elapsed_time": "0:29:32", "remaining_time": "2:02:59", "throughput": 4660.95, "total_tokens": 8261216} {"current_steps": 8220, "total_steps": 42420, "loss": 0.152, "lr": 4.8673170577930246e-05, "epoch": 3.8755304101838757, "percentage": 19.38, "elapsed_time": "0:29:33", "remaining_time": "2:02:58", "throughput": 4661.05, "total_tokens": 8266176} {"current_steps": 8225, "total_steps": 42420, "loss": 0.1333, "lr": 4.866986214630123e-05, "epoch": 3.877887788778878, "percentage": 19.39, "elapsed_time": "0:29:34", "remaining_time": "2:02:57", "throughput": 4661.14, "total_tokens": 8271360} {"current_steps": 8230, "total_steps": 42420, "loss": 0.1303, "lr": 4.8666549707766446e-05, "epoch": 3.8802451673738805, "percentage": 19.4, "elapsed_time": "0:29:35", "remaining_time": "2:02:56", "throughput": 4661.31, "total_tokens": 8276800} {"current_steps": 8235, "total_steps": 42420, "loss": 0.129, "lr": 4.866323326288663e-05, "epoch": 3.882602545968883, "percentage": 19.41, "elapsed_time": "0:29:36", "remaining_time": "2:02:55", "throughput": 4661.48, "total_tokens": 8282560} {"current_steps": 8240, "total_steps": 42420, "loss": 0.0662, "lr": 4.8659912812223204e-05, "epoch": 3.884959924563885, "percentage": 19.42, "elapsed_time": "0:29:38", "remaining_time": "2:02:55", "throughput": 4661.63, "total_tokens": 8288480} {"current_steps": 8245, "total_steps": 42420, "loss": 0.1415, "lr": 4.865658835633826e-05, "epoch": 3.8873173031588872, "percentage": 19.44, "elapsed_time": "0:29:39", "remaining_time": "2:02:54", "throughput": 4661.84, "total_tokens": 8294592} {"current_steps": 8250, "total_steps": 42420, "loss": 0.078, "lr": 4.8653259895794566e-05, "epoch": 3.8896746817538896, "percentage": 19.45, "elapsed_time": "0:29:40", "remaining_time": "2:02:54", "throughput": 4661.9, "total_tokens": 8300192} {"current_steps": 8255, "total_steps": 42420, "loss": 0.2034, "lr": 4.8649927431155597e-05, "epoch": 3.892032060348892, "percentage": 19.46, "elapsed_time": "0:29:41", "remaining_time": "2:02:54", "throughput": 4662.07, "total_tokens": 8306720} {"current_steps": 8260, "total_steps": 42420, "loss": 0.2702, "lr": 4.864659096298546e-05, "epoch": 3.8943894389438944, "percentage": 19.47, "elapsed_time": "0:29:42", "remaining_time": "2:02:53", "throughput": 4662.15, "total_tokens": 8312096} {"current_steps": 8265, "total_steps": 42420, "loss": 0.1834, "lr": 4.8643250491848965e-05, "epoch": 3.896746817538897, "percentage": 19.48, "elapsed_time": "0:29:44", "remaining_time": "2:02:54", "throughput": 4662.47, "total_tokens": 8320704} {"current_steps": 8270, "total_steps": 42420, "loss": 0.1057, "lr": 4.86399060183116e-05, "epoch": 3.8991041961338992, "percentage": 19.5, "elapsed_time": "0:29:45", "remaining_time": "2:02:53", "throughput": 4662.54, "total_tokens": 8325120} {"current_steps": 8275, "total_steps": 42420, "loss": 0.1582, "lr": 4.863655754293953e-05, "epoch": 3.901461574728901, "percentage": 19.51, "elapsed_time": "0:29:46", "remaining_time": "2:02:52", "throughput": 4662.68, "total_tokens": 8330944} {"current_steps": 8280, "total_steps": 42420, "loss": 0.342, "lr": 4.86332050662996e-05, "epoch": 3.9038189533239036, "percentage": 19.52, "elapsed_time": "0:29:47", "remaining_time": "2:02:51", "throughput": 4662.72, "total_tokens": 8335968} {"current_steps": 8285, "total_steps": 42420, "loss": 0.1218, "lr": 4.862984858895931e-05, "epoch": 3.906176331918906, "percentage": 19.53, "elapsed_time": "0:29:48", "remaining_time": "2:02:49", "throughput": 4662.82, "total_tokens": 8340576} {"current_steps": 8290, "total_steps": 42420, "loss": 0.1876, "lr": 4.8626488111486876e-05, "epoch": 3.9085337105139084, "percentage": 19.54, "elapsed_time": "0:29:49", "remaining_time": "2:02:48", "throughput": 4662.94, "total_tokens": 8346080} {"current_steps": 8295, "total_steps": 42420, "loss": 0.3836, "lr": 4.862312363445116e-05, "epoch": 3.910891089108911, "percentage": 19.55, "elapsed_time": "0:29:51", "remaining_time": "2:02:48", "throughput": 4663.13, "total_tokens": 8352000} {"current_steps": 8300, "total_steps": 42420, "loss": 0.2326, "lr": 4.861975515842171e-05, "epoch": 3.913248467703913, "percentage": 19.57, "elapsed_time": "0:29:51", "remaining_time": "2:02:46", "throughput": 4663.12, "total_tokens": 8356064} {"current_steps": 8305, "total_steps": 42420, "loss": 0.1057, "lr": 4.861638268396875e-05, "epoch": 3.9156058462989156, "percentage": 19.58, "elapsed_time": "0:29:52", "remaining_time": "2:02:44", "throughput": 4663.21, "total_tokens": 8360448} {"current_steps": 8310, "total_steps": 42420, "loss": 0.1694, "lr": 4.861300621166318e-05, "epoch": 3.917963224893918, "percentage": 19.59, "elapsed_time": "0:29:53", "remaining_time": "2:02:42", "throughput": 4663.26, "total_tokens": 8364896} {"current_steps": 8315, "total_steps": 42420, "loss": 0.1217, "lr": 4.860962574207659e-05, "epoch": 3.9203206034889204, "percentage": 19.6, "elapsed_time": "0:29:54", "remaining_time": "2:02:42", "throughput": 4663.39, "total_tokens": 8370592} {"current_steps": 8320, "total_steps": 42420, "loss": 0.0849, "lr": 4.860624127578124e-05, "epoch": 3.922677982083923, "percentage": 19.61, "elapsed_time": "0:29:55", "remaining_time": "2:02:40", "throughput": 4663.32, "total_tokens": 8374688} {"current_steps": 8325, "total_steps": 42420, "loss": 0.2887, "lr": 4.8602852813350035e-05, "epoch": 3.9250353606789252, "percentage": 19.63, "elapsed_time": "0:29:56", "remaining_time": "2:02:39", "throughput": 4663.44, "total_tokens": 8379872} {"current_steps": 8330, "total_steps": 42420, "loss": 0.1058, "lr": 4.859946035535661e-05, "epoch": 3.9273927392739276, "percentage": 19.64, "elapsed_time": "0:29:57", "remaining_time": "2:02:37", "throughput": 4663.4, "total_tokens": 8383808} {"current_steps": 8335, "total_steps": 42420, "loss": 0.1802, "lr": 4.859606390237525e-05, "epoch": 3.92975011786893, "percentage": 19.65, "elapsed_time": "0:29:58", "remaining_time": "2:02:36", "throughput": 4663.46, "total_tokens": 8388800} {"current_steps": 8340, "total_steps": 42420, "loss": 0.1043, "lr": 4.85926634549809e-05, "epoch": 3.932107496463932, "percentage": 19.66, "elapsed_time": "0:29:59", "remaining_time": "2:02:34", "throughput": 4663.44, "total_tokens": 8393312} {"current_steps": 8345, "total_steps": 42420, "loss": 0.0446, "lr": 4.858925901374921e-05, "epoch": 3.9344648750589344, "percentage": 19.67, "elapsed_time": "0:30:00", "remaining_time": "2:02:33", "throughput": 4663.52, "total_tokens": 8398144} {"current_steps": 8350, "total_steps": 42420, "loss": 0.1293, "lr": 4.8585850579256486e-05, "epoch": 3.936822253653937, "percentage": 19.68, "elapsed_time": "0:30:01", "remaining_time": "2:02:31", "throughput": 4663.54, "total_tokens": 8402720} {"current_steps": 8355, "total_steps": 42420, "loss": 0.311, "lr": 4.858243815207973e-05, "epoch": 3.939179632248939, "percentage": 19.7, "elapsed_time": "0:30:02", "remaining_time": "2:02:31", "throughput": 4663.7, "total_tokens": 8408512} {"current_steps": 8360, "total_steps": 42420, "loss": 0.1104, "lr": 4.85790217327966e-05, "epoch": 3.9415370108439416, "percentage": 19.71, "elapsed_time": "0:30:03", "remaining_time": "2:02:29", "throughput": 4663.72, "total_tokens": 8413120} {"current_steps": 8365, "total_steps": 42420, "loss": 0.1682, "lr": 4.8575601321985445e-05, "epoch": 3.943894389438944, "percentage": 19.72, "elapsed_time": "0:30:04", "remaining_time": "2:02:28", "throughput": 4663.81, "total_tokens": 8417920} {"current_steps": 8370, "total_steps": 42420, "loss": 0.1139, "lr": 4.857217692022528e-05, "epoch": 3.9462517680339464, "percentage": 19.73, "elapsed_time": "0:30:05", "remaining_time": "2:02:26", "throughput": 4663.82, "total_tokens": 8422368} {"current_steps": 8375, "total_steps": 42420, "loss": 0.041, "lr": 4.856874852809579e-05, "epoch": 3.9486091466289484, "percentage": 19.74, "elapsed_time": "0:30:07", "remaining_time": "2:02:25", "throughput": 4664.0, "total_tokens": 8428160} {"current_steps": 8380, "total_steps": 42420, "loss": 0.28, "lr": 4.856531614617734e-05, "epoch": 3.9509665252239508, "percentage": 19.75, "elapsed_time": "0:30:07", "remaining_time": "2:02:24", "throughput": 4664.05, "total_tokens": 8432448} {"current_steps": 8385, "total_steps": 42420, "loss": 0.1667, "lr": 4.856187977505099e-05, "epoch": 3.953323903818953, "percentage": 19.77, "elapsed_time": "0:30:08", "remaining_time": "2:02:22", "throughput": 4664.06, "total_tokens": 8436928} {"current_steps": 8390, "total_steps": 42420, "loss": 0.2371, "lr": 4.855843941529846e-05, "epoch": 3.9556812824139556, "percentage": 19.78, "elapsed_time": "0:30:09", "remaining_time": "2:02:20", "throughput": 4664.13, "total_tokens": 8441408} {"current_steps": 8395, "total_steps": 42420, "loss": 0.1364, "lr": 4.855499506750213e-05, "epoch": 3.958038661008958, "percentage": 19.79, "elapsed_time": "0:30:10", "remaining_time": "2:02:18", "throughput": 4664.02, "total_tokens": 8445120} {"current_steps": 8400, "total_steps": 42420, "loss": 0.1149, "lr": 4.8551546732245065e-05, "epoch": 3.9603960396039604, "percentage": 19.8, "elapsed_time": "0:30:11", "remaining_time": "2:02:17", "throughput": 4664.06, "total_tokens": 8449632} {"current_steps": 8405, "total_steps": 42420, "loss": 0.1417, "lr": 4.854809441011103e-05, "epoch": 3.9627534181989628, "percentage": 19.81, "elapsed_time": "0:30:12", "remaining_time": "2:02:16", "throughput": 4664.25, "total_tokens": 8455392} {"current_steps": 8410, "total_steps": 42420, "loss": 0.0891, "lr": 4.854463810168444e-05, "epoch": 3.965110796793965, "percentage": 19.83, "elapsed_time": "0:30:14", "remaining_time": "2:02:15", "throughput": 4664.37, "total_tokens": 8461216} {"current_steps": 8415, "total_steps": 42420, "loss": 0.201, "lr": 4.854117780755039e-05, "epoch": 3.9674681753889676, "percentage": 19.84, "elapsed_time": "0:30:14", "remaining_time": "2:02:14", "throughput": 4664.47, "total_tokens": 8465888} {"current_steps": 8420, "total_steps": 42420, "loss": 0.2873, "lr": 4.853771352829463e-05, "epoch": 3.96982555398397, "percentage": 19.85, "elapsed_time": "0:30:16", "remaining_time": "2:02:13", "throughput": 4664.61, "total_tokens": 8471136} {"current_steps": 8425, "total_steps": 42420, "loss": 0.1103, "lr": 4.853424526450362e-05, "epoch": 3.9721829325789724, "percentage": 19.86, "elapsed_time": "0:30:17", "remaining_time": "2:02:12", "throughput": 4664.78, "total_tokens": 8477088} {"current_steps": 8430, "total_steps": 42420, "loss": 0.0895, "lr": 4.8530773016764475e-05, "epoch": 3.9745403111739748, "percentage": 19.87, "elapsed_time": "0:30:18", "remaining_time": "2:02:11", "throughput": 4664.74, "total_tokens": 8481440} {"current_steps": 8435, "total_steps": 42420, "loss": 0.0871, "lr": 4.852729678566499e-05, "epoch": 3.976897689768977, "percentage": 19.88, "elapsed_time": "0:30:19", "remaining_time": "2:02:09", "throughput": 4664.81, "total_tokens": 8486176} {"current_steps": 8440, "total_steps": 42420, "loss": 0.2232, "lr": 4.852381657179363e-05, "epoch": 3.979255068363979, "percentage": 19.9, "elapsed_time": "0:30:20", "remaining_time": "2:02:08", "throughput": 4664.94, "total_tokens": 8491648} {"current_steps": 8445, "total_steps": 42420, "loss": 0.1358, "lr": 4.8520332375739544e-05, "epoch": 3.9816124469589815, "percentage": 19.91, "elapsed_time": "0:30:21", "remaining_time": "2:02:07", "throughput": 4664.84, "total_tokens": 8496512} {"current_steps": 8450, "total_steps": 42420, "loss": 0.2107, "lr": 4.851684419809253e-05, "epoch": 3.983969825553984, "percentage": 19.92, "elapsed_time": "0:30:22", "remaining_time": "2:02:06", "throughput": 4664.95, "total_tokens": 8502208} {"current_steps": 8455, "total_steps": 42420, "loss": 0.3449, "lr": 4.851335203944308e-05, "epoch": 3.9863272041489863, "percentage": 19.93, "elapsed_time": "0:30:23", "remaining_time": "2:02:05", "throughput": 4664.98, "total_tokens": 8507200} {"current_steps": 8460, "total_steps": 42420, "loss": 0.1471, "lr": 4.8509855900382374e-05, "epoch": 3.9886845827439887, "percentage": 19.94, "elapsed_time": "0:30:24", "remaining_time": "2:02:04", "throughput": 4665.02, "total_tokens": 8511648} {"current_steps": 8465, "total_steps": 42420, "loss": 0.2282, "lr": 4.850635578150224e-05, "epoch": 3.991041961338991, "percentage": 19.96, "elapsed_time": "0:30:26", "remaining_time": "2:02:05", "throughput": 4665.23, "total_tokens": 8519520} {"current_steps": 8470, "total_steps": 42420, "loss": 0.2205, "lr": 4.850285168339518e-05, "epoch": 3.9933993399339935, "percentage": 19.97, "elapsed_time": "0:30:27", "remaining_time": "2:02:03", "throughput": 4665.14, "total_tokens": 8523488} {"current_steps": 8475, "total_steps": 42420, "loss": 0.0561, "lr": 4.849934360665439e-05, "epoch": 3.9957567185289955, "percentage": 19.98, "elapsed_time": "0:30:28", "remaining_time": "2:02:02", "throughput": 4665.17, "total_tokens": 8528576} {"current_steps": 8480, "total_steps": 42420, "loss": 0.1735, "lr": 4.849583155187373e-05, "epoch": 3.998114097123998, "percentage": 19.99, "elapsed_time": "0:30:29", "remaining_time": "2:02:02", "throughput": 4664.5, "total_tokens": 8533824} {"current_steps": 8484, "total_steps": 42420, "eval_loss": 0.1634756624698639, "epoch": 4.0, "percentage": 20.0, "elapsed_time": "0:30:45", "remaining_time": "2:03:01", "throughput": 4626.07, "total_tokens": 8537088} {"current_steps": 8485, "total_steps": 42420, "loss": 0.1965, "lr": 4.849231551964771e-05, "epoch": 4.000471475719, "percentage": 20.0, "elapsed_time": "0:30:47", "remaining_time": "2:03:07", "throughput": 4622.33, "total_tokens": 8537824} {"current_steps": 8490, "total_steps": 42420, "loss": 0.1621, "lr": 4.848879551057156e-05, "epoch": 4.002828854314003, "percentage": 20.01, "elapsed_time": "0:30:48", "remaining_time": "2:03:05", "throughput": 4622.43, "total_tokens": 8542784} {"current_steps": 8495, "total_steps": 42420, "loss": 0.0765, "lr": 4.848527152524114e-05, "epoch": 4.005186232909005, "percentage": 20.03, "elapsed_time": "0:30:49", "remaining_time": "2:03:04", "throughput": 4622.49, "total_tokens": 8547456} {"current_steps": 8500, "total_steps": 42420, "loss": 0.1657, "lr": 4.8481743564253015e-05, "epoch": 4.0075436115040075, "percentage": 20.04, "elapsed_time": "0:30:50", "remaining_time": "2:03:03", "throughput": 4622.67, "total_tokens": 8552704} {"current_steps": 8505, "total_steps": 42420, "loss": 0.0898, "lr": 4.84782116282044e-05, "epoch": 4.00990099009901, "percentage": 20.05, "elapsed_time": "0:30:51", "remaining_time": "2:03:02", "throughput": 4622.83, "total_tokens": 8558112} {"current_steps": 8510, "total_steps": 42420, "loss": 0.2254, "lr": 4.8474675717693195e-05, "epoch": 4.012258368694012, "percentage": 20.06, "elapsed_time": "0:30:52", "remaining_time": "2:03:00", "throughput": 4622.99, "total_tokens": 8563200} {"current_steps": 8515, "total_steps": 42420, "loss": 0.0925, "lr": 4.847113583331796e-05, "epoch": 4.014615747289015, "percentage": 20.07, "elapsed_time": "0:30:53", "remaining_time": "2:02:59", "throughput": 4623.03, "total_tokens": 8568128} {"current_steps": 8520, "total_steps": 42420, "loss": 0.075, "lr": 4.846759197567796e-05, "epoch": 4.016973125884017, "percentage": 20.08, "elapsed_time": "0:30:54", "remaining_time": "2:02:58", "throughput": 4623.06, "total_tokens": 8572736} {"current_steps": 8525, "total_steps": 42420, "loss": 0.1458, "lr": 4.846404414537308e-05, "epoch": 4.0193305044790195, "percentage": 20.1, "elapsed_time": "0:30:55", "remaining_time": "2:02:56", "throughput": 4623.13, "total_tokens": 8577248} {"current_steps": 8530, "total_steps": 42420, "loss": 0.3683, "lr": 4.846049234300393e-05, "epoch": 4.021687883074022, "percentage": 20.11, "elapsed_time": "0:30:56", "remaining_time": "2:02:54", "throughput": 4623.04, "total_tokens": 8581120} {"current_steps": 8535, "total_steps": 42420, "loss": 0.1239, "lr": 4.845693656917176e-05, "epoch": 4.024045261669024, "percentage": 20.12, "elapsed_time": "0:30:57", "remaining_time": "2:02:53", "throughput": 4623.2, "total_tokens": 8586176} {"current_steps": 8540, "total_steps": 42420, "loss": 0.0665, "lr": 4.8453376824478513e-05, "epoch": 4.026402640264027, "percentage": 20.13, "elapsed_time": "0:30:58", "remaining_time": "2:02:51", "throughput": 4623.24, "total_tokens": 8590816} {"current_steps": 8545, "total_steps": 42420, "loss": 0.0731, "lr": 4.844981310952678e-05, "epoch": 4.028760018859029, "percentage": 20.14, "elapsed_time": "0:30:59", "remaining_time": "2:02:49", "throughput": 4623.33, "total_tokens": 8595104} {"current_steps": 8550, "total_steps": 42420, "loss": 0.272, "lr": 4.8446245424919845e-05, "epoch": 4.0311173974540315, "percentage": 20.16, "elapsed_time": "0:31:00", "remaining_time": "2:02:49", "throughput": 4623.63, "total_tokens": 8601632} {"current_steps": 8555, "total_steps": 42420, "loss": 0.1878, "lr": 4.844267377126165e-05, "epoch": 4.033474776049033, "percentage": 20.17, "elapsed_time": "0:31:01", "remaining_time": "2:02:47", "throughput": 4623.7, "total_tokens": 8605984} {"current_steps": 8560, "total_steps": 42420, "loss": 0.1971, "lr": 4.8439098149156827e-05, "epoch": 4.035832154644035, "percentage": 20.18, "elapsed_time": "0:31:02", "remaining_time": "2:02:46", "throughput": 4623.82, "total_tokens": 8611168} {"current_steps": 8565, "total_steps": 42420, "loss": 0.1107, "lr": 4.8435518559210654e-05, "epoch": 4.038189533239038, "percentage": 20.19, "elapsed_time": "0:31:03", "remaining_time": "2:02:45", "throughput": 4623.86, "total_tokens": 8615552} {"current_steps": 8570, "total_steps": 42420, "loss": 0.1752, "lr": 4.84319350020291e-05, "epoch": 4.04054691183404, "percentage": 20.2, "elapsed_time": "0:31:04", "remaining_time": "2:02:43", "throughput": 4624.06, "total_tokens": 8621024} {"current_steps": 8575, "total_steps": 42420, "loss": 0.1639, "lr": 4.8428347478218804e-05, "epoch": 4.042904290429043, "percentage": 20.21, "elapsed_time": "0:31:05", "remaining_time": "2:02:42", "throughput": 4624.14, "total_tokens": 8626016} {"current_steps": 8580, "total_steps": 42420, "loss": 0.083, "lr": 4.8424755988387074e-05, "epoch": 4.045261669024045, "percentage": 20.23, "elapsed_time": "0:31:06", "remaining_time": "2:02:41", "throughput": 4624.21, "total_tokens": 8630528} {"current_steps": 8585, "total_steps": 42420, "loss": 0.1134, "lr": 4.842116053314188e-05, "epoch": 4.0476190476190474, "percentage": 20.24, "elapsed_time": "0:31:07", "remaining_time": "2:02:40", "throughput": 4624.36, "total_tokens": 8636096} {"current_steps": 8590, "total_steps": 42420, "loss": 0.0751, "lr": 4.8417561113091884e-05, "epoch": 4.04997642621405, "percentage": 20.25, "elapsed_time": "0:31:08", "remaining_time": "2:02:38", "throughput": 4624.42, "total_tokens": 8640608} {"current_steps": 8595, "total_steps": 42420, "loss": 0.1547, "lr": 4.841395772884639e-05, "epoch": 4.052333804809052, "percentage": 20.26, "elapsed_time": "0:31:09", "remaining_time": "2:02:37", "throughput": 4624.56, "total_tokens": 8645664} {"current_steps": 8600, "total_steps": 42420, "loss": 0.3297, "lr": 4.84103503810154e-05, "epoch": 4.054691183404055, "percentage": 20.27, "elapsed_time": "0:31:10", "remaining_time": "2:02:35", "throughput": 4624.65, "total_tokens": 8650272} {"current_steps": 8605, "total_steps": 42420, "loss": 0.1711, "lr": 4.840673907020958e-05, "epoch": 4.057048561999057, "percentage": 20.29, "elapsed_time": "0:31:11", "remaining_time": "2:02:34", "throughput": 4624.79, "total_tokens": 8655360} {"current_steps": 8610, "total_steps": 42420, "loss": 0.0795, "lr": 4.840312379704026e-05, "epoch": 4.0594059405940595, "percentage": 20.3, "elapsed_time": "0:31:12", "remaining_time": "2:02:32", "throughput": 4624.91, "total_tokens": 8660160} {"current_steps": 8615, "total_steps": 42420, "loss": 0.2458, "lr": 4.839950456211944e-05, "epoch": 4.061763319189062, "percentage": 20.31, "elapsed_time": "0:31:13", "remaining_time": "2:02:31", "throughput": 4625.01, "total_tokens": 8664672} {"current_steps": 8620, "total_steps": 42420, "loss": 0.1017, "lr": 4.839588136605979e-05, "epoch": 4.064120697784064, "percentage": 20.32, "elapsed_time": "0:31:14", "remaining_time": "2:02:30", "throughput": 4625.21, "total_tokens": 8670176} {"current_steps": 8625, "total_steps": 42420, "loss": 0.0894, "lr": 4.839225420947468e-05, "epoch": 4.066478076379067, "percentage": 20.33, "elapsed_time": "0:31:15", "remaining_time": "2:02:29", "throughput": 4625.39, "total_tokens": 8675744} {"current_steps": 8630, "total_steps": 42420, "loss": 0.1317, "lr": 4.8388623092978104e-05, "epoch": 4.068835454974069, "percentage": 20.34, "elapsed_time": "0:31:16", "remaining_time": "2:02:27", "throughput": 4625.5, "total_tokens": 8680448} {"current_steps": 8635, "total_steps": 42420, "loss": 0.133, "lr": 4.838498801718475e-05, "epoch": 4.0711928335690715, "percentage": 20.36, "elapsed_time": "0:31:17", "remaining_time": "2:02:26", "throughput": 4625.65, "total_tokens": 8685216} {"current_steps": 8640, "total_steps": 42420, "loss": 0.1856, "lr": 4.838134898270998e-05, "epoch": 4.073550212164074, "percentage": 20.37, "elapsed_time": "0:31:18", "remaining_time": "2:02:25", "throughput": 4625.87, "total_tokens": 8690592} {"current_steps": 8645, "total_steps": 42420, "loss": 0.0551, "lr": 4.837770599016983e-05, "epoch": 4.075907590759076, "percentage": 20.38, "elapsed_time": "0:31:19", "remaining_time": "2:02:23", "throughput": 4626.03, "total_tokens": 8695680} {"current_steps": 8650, "total_steps": 42420, "loss": 0.1265, "lr": 4.837405904018098e-05, "epoch": 4.078264969354079, "percentage": 20.39, "elapsed_time": "0:31:20", "remaining_time": "2:02:22", "throughput": 4626.25, "total_tokens": 8701216} {"current_steps": 8655, "total_steps": 42420, "loss": 0.1299, "lr": 4.83704081333608e-05, "epoch": 4.08062234794908, "percentage": 20.4, "elapsed_time": "0:31:21", "remaining_time": "2:02:21", "throughput": 4626.35, "total_tokens": 8706176} {"current_steps": 8660, "total_steps": 42420, "loss": 0.1241, "lr": 4.836675327032734e-05, "epoch": 4.082979726544083, "percentage": 20.41, "elapsed_time": "0:31:22", "remaining_time": "2:02:20", "throughput": 4626.37, "total_tokens": 8711040} {"current_steps": 8665, "total_steps": 42420, "loss": 0.1239, "lr": 4.836309445169929e-05, "epoch": 4.085337105139085, "percentage": 20.43, "elapsed_time": "0:31:23", "remaining_time": "2:02:18", "throughput": 4626.44, "total_tokens": 8715520} {"current_steps": 8670, "total_steps": 42420, "loss": 0.2394, "lr": 4.835943167809603e-05, "epoch": 4.087694483734087, "percentage": 20.44, "elapsed_time": "0:31:24", "remaining_time": "2:02:17", "throughput": 4626.49, "total_tokens": 8720256} {"current_steps": 8675, "total_steps": 42420, "loss": 0.1008, "lr": 4.83557649501376e-05, "epoch": 4.09005186232909, "percentage": 20.45, "elapsed_time": "0:31:25", "remaining_time": "2:02:15", "throughput": 4626.41, "total_tokens": 8724256} {"current_steps": 8680, "total_steps": 42420, "loss": 0.3123, "lr": 4.8352094268444735e-05, "epoch": 4.092409240924092, "percentage": 20.46, "elapsed_time": "0:31:26", "remaining_time": "2:02:14", "throughput": 4626.58, "total_tokens": 8730048} {"current_steps": 8685, "total_steps": 42420, "loss": 0.1856, "lr": 4.834841963363881e-05, "epoch": 4.094766619519095, "percentage": 20.47, "elapsed_time": "0:31:27", "remaining_time": "2:02:13", "throughput": 4626.69, "total_tokens": 8734656} {"current_steps": 8690, "total_steps": 42420, "loss": 0.1884, "lr": 4.834474104634187e-05, "epoch": 4.097123998114097, "percentage": 20.49, "elapsed_time": "0:31:28", "remaining_time": "2:02:11", "throughput": 4626.78, "total_tokens": 8739488} {"current_steps": 8695, "total_steps": 42420, "loss": 0.2026, "lr": 4.834105850717663e-05, "epoch": 4.099481376709099, "percentage": 20.5, "elapsed_time": "0:31:29", "remaining_time": "2:02:10", "throughput": 4626.98, "total_tokens": 8744928} {"current_steps": 8700, "total_steps": 42420, "loss": 0.1638, "lr": 4.833737201676651e-05, "epoch": 4.101838755304102, "percentage": 20.51, "elapsed_time": "0:31:31", "remaining_time": "2:02:10", "throughput": 4627.25, "total_tokens": 8751872} {"current_steps": 8705, "total_steps": 42420, "loss": 0.1451, "lr": 4.833368157573555e-05, "epoch": 4.104196133899104, "percentage": 20.52, "elapsed_time": "0:31:32", "remaining_time": "2:02:09", "throughput": 4627.25, "total_tokens": 8756448} {"current_steps": 8710, "total_steps": 42420, "loss": 0.1175, "lr": 4.832998718470847e-05, "epoch": 4.106553512494107, "percentage": 20.53, "elapsed_time": "0:31:33", "remaining_time": "2:02:07", "throughput": 4627.31, "total_tokens": 8760832} {"current_steps": 8715, "total_steps": 42420, "loss": 0.1404, "lr": 4.832628884431069e-05, "epoch": 4.108910891089109, "percentage": 20.54, "elapsed_time": "0:31:34", "remaining_time": "2:02:05", "throughput": 4627.3, "total_tokens": 8764832} {"current_steps": 8720, "total_steps": 42420, "loss": 0.474, "lr": 4.832258655516827e-05, "epoch": 4.111268269684111, "percentage": 20.56, "elapsed_time": "0:31:35", "remaining_time": "2:02:03", "throughput": 4627.4, "total_tokens": 8769312} {"current_steps": 8725, "total_steps": 42420, "loss": 0.0742, "lr": 4.831888031790793e-05, "epoch": 4.113625648279114, "percentage": 20.57, "elapsed_time": "0:31:36", "remaining_time": "2:02:03", "throughput": 4627.56, "total_tokens": 8775360} {"current_steps": 8730, "total_steps": 42420, "loss": 0.0618, "lr": 4.8315170133157095e-05, "epoch": 4.115983026874116, "percentage": 20.58, "elapsed_time": "0:31:37", "remaining_time": "2:02:02", "throughput": 4627.83, "total_tokens": 8781536} {"current_steps": 8735, "total_steps": 42420, "loss": 0.1828, "lr": 4.831145600154382e-05, "epoch": 4.118340405469119, "percentage": 20.59, "elapsed_time": "0:31:38", "remaining_time": "2:02:02", "throughput": 4628.03, "total_tokens": 8787328} {"current_steps": 8740, "total_steps": 42420, "loss": 0.0875, "lr": 4.8307737923696855e-05, "epoch": 4.120697784064121, "percentage": 20.6, "elapsed_time": "0:31:39", "remaining_time": "2:02:01", "throughput": 4628.21, "total_tokens": 8793376} {"current_steps": 8745, "total_steps": 42420, "loss": 0.1568, "lr": 4.8304015900245595e-05, "epoch": 4.123055162659123, "percentage": 20.62, "elapsed_time": "0:31:40", "remaining_time": "2:02:00", "throughput": 4628.37, "total_tokens": 8798304} {"current_steps": 8750, "total_steps": 42420, "loss": 0.0575, "lr": 4.830028993182013e-05, "epoch": 4.125412541254126, "percentage": 20.63, "elapsed_time": "0:31:42", "remaining_time": "2:01:59", "throughput": 4628.57, "total_tokens": 8804800} {"current_steps": 8755, "total_steps": 42420, "loss": 0.08, "lr": 4.82965600190512e-05, "epoch": 4.127769919849127, "percentage": 20.64, "elapsed_time": "0:31:43", "remaining_time": "2:01:58", "throughput": 4628.6, "total_tokens": 8809152} {"current_steps": 8760, "total_steps": 42420, "loss": 0.1233, "lr": 4.82928261625702e-05, "epoch": 4.13012729844413, "percentage": 20.65, "elapsed_time": "0:31:44", "remaining_time": "2:01:56", "throughput": 4628.62, "total_tokens": 8813536} {"current_steps": 8765, "total_steps": 42420, "loss": 0.1418, "lr": 4.828908836300922e-05, "epoch": 4.132484677039132, "percentage": 20.66, "elapsed_time": "0:31:45", "remaining_time": "2:01:54", "throughput": 4628.67, "total_tokens": 8818048} {"current_steps": 8770, "total_steps": 42420, "loss": 0.3286, "lr": 4.8285346621001015e-05, "epoch": 4.1348420556341345, "percentage": 20.67, "elapsed_time": "0:31:46", "remaining_time": "2:01:53", "throughput": 4628.76, "total_tokens": 8823008} {"current_steps": 8775, "total_steps": 42420, "loss": 0.1444, "lr": 4.8281600937178986e-05, "epoch": 4.137199434229137, "percentage": 20.69, "elapsed_time": "0:31:47", "remaining_time": "2:01:53", "throughput": 4629.02, "total_tokens": 8829376} {"current_steps": 8780, "total_steps": 42420, "loss": 0.1069, "lr": 4.827785131217721e-05, "epoch": 4.139556812824139, "percentage": 20.7, "elapsed_time": "0:31:48", "remaining_time": "2:01:51", "throughput": 4629.06, "total_tokens": 8833376} {"current_steps": 8785, "total_steps": 42420, "loss": 0.0613, "lr": 4.827409774663045e-05, "epoch": 4.141914191419142, "percentage": 20.71, "elapsed_time": "0:31:49", "remaining_time": "2:01:50", "throughput": 4629.15, "total_tokens": 8838368} {"current_steps": 8790, "total_steps": 42420, "loss": 0.0873, "lr": 4.827034024117412e-05, "epoch": 4.144271570014144, "percentage": 20.72, "elapsed_time": "0:31:50", "remaining_time": "2:01:49", "throughput": 4629.39, "total_tokens": 8844096} {"current_steps": 8795, "total_steps": 42420, "loss": 0.166, "lr": 4.826657879644429e-05, "epoch": 4.1466289486091465, "percentage": 20.73, "elapsed_time": "0:31:51", "remaining_time": "2:01:48", "throughput": 4629.53, "total_tokens": 8849440} {"current_steps": 8800, "total_steps": 42420, "loss": 0.1293, "lr": 4.826281341307771e-05, "epoch": 4.148986327204149, "percentage": 20.74, "elapsed_time": "0:31:52", "remaining_time": "2:01:46", "throughput": 4629.63, "total_tokens": 8854144} {"current_steps": 8805, "total_steps": 42420, "loss": 0.1509, "lr": 4.82590440917118e-05, "epoch": 4.151343705799151, "percentage": 20.76, "elapsed_time": "0:31:53", "remaining_time": "2:01:44", "throughput": 4629.64, "total_tokens": 8858496} {"current_steps": 8810, "total_steps": 42420, "loss": 0.2528, "lr": 4.8255270832984645e-05, "epoch": 4.153701084394154, "percentage": 20.77, "elapsed_time": "0:31:54", "remaining_time": "2:01:43", "throughput": 4629.75, "total_tokens": 8863360} {"current_steps": 8815, "total_steps": 42420, "loss": 0.3044, "lr": 4.8251493637534985e-05, "epoch": 4.156058462989156, "percentage": 20.78, "elapsed_time": "0:31:55", "remaining_time": "2:01:42", "throughput": 4629.86, "total_tokens": 8868384} {"current_steps": 8820, "total_steps": 42420, "loss": 0.074, "lr": 4.824771250600224e-05, "epoch": 4.158415841584159, "percentage": 20.79, "elapsed_time": "0:31:56", "remaining_time": "2:01:40", "throughput": 4629.76, "total_tokens": 8872096} {"current_steps": 8825, "total_steps": 42420, "loss": 0.0885, "lr": 4.8243927439026495e-05, "epoch": 4.160773220179161, "percentage": 20.8, "elapsed_time": "0:31:57", "remaining_time": "2:01:38", "throughput": 4629.84, "total_tokens": 8876576} {"current_steps": 8830, "total_steps": 42420, "loss": 0.2534, "lr": 4.8240138437248494e-05, "epoch": 4.163130598774163, "percentage": 20.82, "elapsed_time": "0:31:58", "remaining_time": "2:01:38", "throughput": 4629.92, "total_tokens": 8882976} {"current_steps": 8835, "total_steps": 42420, "loss": 0.0888, "lr": 4.823634550130965e-05, "epoch": 4.165487977369166, "percentage": 20.83, "elapsed_time": "0:31:59", "remaining_time": "2:01:37", "throughput": 4630.01, "total_tokens": 8888064} {"current_steps": 8840, "total_steps": 42420, "loss": 0.08, "lr": 4.823254863185204e-05, "epoch": 4.167845355964168, "percentage": 20.84, "elapsed_time": "0:32:00", "remaining_time": "2:01:36", "throughput": 4630.21, "total_tokens": 8894048} {"current_steps": 8845, "total_steps": 42420, "loss": 0.1664, "lr": 4.8228747829518417e-05, "epoch": 4.170202734559171, "percentage": 20.85, "elapsed_time": "0:32:01", "remaining_time": "2:01:35", "throughput": 4630.33, "total_tokens": 8899008} {"current_steps": 8850, "total_steps": 42420, "loss": 0.1804, "lr": 4.822494309495219e-05, "epoch": 4.172560113154173, "percentage": 20.86, "elapsed_time": "0:32:02", "remaining_time": "2:01:33", "throughput": 4630.34, "total_tokens": 8903456} {"current_steps": 8855, "total_steps": 42420, "loss": 0.0826, "lr": 4.822113442879743e-05, "epoch": 4.174917491749175, "percentage": 20.87, "elapsed_time": "0:32:03", "remaining_time": "2:01:32", "throughput": 4630.46, "total_tokens": 8908384} {"current_steps": 8860, "total_steps": 42420, "loss": 0.1332, "lr": 4.821732183169888e-05, "epoch": 4.177274870344177, "percentage": 20.89, "elapsed_time": "0:32:04", "remaining_time": "2:01:30", "throughput": 4630.47, "total_tokens": 8912640} {"current_steps": 8865, "total_steps": 42420, "loss": 0.1171, "lr": 4.821350530430196e-05, "epoch": 4.179632248939179, "percentage": 20.9, "elapsed_time": "0:32:05", "remaining_time": "2:01:29", "throughput": 4630.56, "total_tokens": 8917792} {"current_steps": 8870, "total_steps": 42420, "loss": 0.0177, "lr": 4.820968484725273e-05, "epoch": 4.181989627534182, "percentage": 20.91, "elapsed_time": "0:32:06", "remaining_time": "2:01:27", "throughput": 4630.62, "total_tokens": 8922048} {"current_steps": 8875, "total_steps": 42420, "loss": 0.042, "lr": 4.8205860461197936e-05, "epoch": 4.184347006129184, "percentage": 20.92, "elapsed_time": "0:32:07", "remaining_time": "2:01:27", "throughput": 4630.83, "total_tokens": 8927904} {"current_steps": 8880, "total_steps": 42420, "loss": 0.2164, "lr": 4.820203214678497e-05, "epoch": 4.1867043847241865, "percentage": 20.93, "elapsed_time": "0:32:08", "remaining_time": "2:01:25", "throughput": 4630.95, "total_tokens": 8932800} {"current_steps": 8885, "total_steps": 42420, "loss": 0.2574, "lr": 4.8198199904661924e-05, "epoch": 4.189061763319189, "percentage": 20.95, "elapsed_time": "0:32:09", "remaining_time": "2:01:24", "throughput": 4631.01, "total_tokens": 8937312} {"current_steps": 8890, "total_steps": 42420, "loss": 0.2434, "lr": 4.819436373547751e-05, "epoch": 4.191419141914191, "percentage": 20.96, "elapsed_time": "0:32:11", "remaining_time": "2:01:23", "throughput": 4631.21, "total_tokens": 8943008} {"current_steps": 8895, "total_steps": 42420, "loss": 0.3451, "lr": 4.8190523639881135e-05, "epoch": 4.193776520509194, "percentage": 20.97, "elapsed_time": "0:32:12", "remaining_time": "2:01:22", "throughput": 4631.34, "total_tokens": 8949184} {"current_steps": 8900, "total_steps": 42420, "loss": 0.2036, "lr": 4.818667961852286e-05, "epoch": 4.196133899104196, "percentage": 20.98, "elapsed_time": "0:32:13", "remaining_time": "2:01:21", "throughput": 4631.55, "total_tokens": 8954816} {"current_steps": 8905, "total_steps": 42420, "loss": 0.1716, "lr": 4.818283167205341e-05, "epoch": 4.1984912776991985, "percentage": 20.99, "elapsed_time": "0:32:14", "remaining_time": "2:01:20", "throughput": 4631.65, "total_tokens": 8960064} {"current_steps": 8910, "total_steps": 42420, "loss": 0.1072, "lr": 4.817897980112418e-05, "epoch": 4.200848656294201, "percentage": 21.0, "elapsed_time": "0:32:15", "remaining_time": "2:01:19", "throughput": 4631.66, "total_tokens": 8964288} {"current_steps": 8915, "total_steps": 42420, "loss": 0.1785, "lr": 4.817512400638723e-05, "epoch": 4.203206034889203, "percentage": 21.02, "elapsed_time": "0:32:16", "remaining_time": "2:01:18", "throughput": 4631.82, "total_tokens": 8969888} {"current_steps": 8920, "total_steps": 42420, "loss": 0.2101, "lr": 4.8171264288495274e-05, "epoch": 4.205563413484206, "percentage": 21.03, "elapsed_time": "0:32:17", "remaining_time": "2:01:16", "throughput": 4631.94, "total_tokens": 8974400} {"current_steps": 8925, "total_steps": 42420, "loss": 0.0857, "lr": 4.81674006481017e-05, "epoch": 4.207920792079208, "percentage": 21.04, "elapsed_time": "0:32:18", "remaining_time": "2:01:15", "throughput": 4632.08, "total_tokens": 8980416} {"current_steps": 8930, "total_steps": 42420, "loss": 0.0442, "lr": 4.8163533085860556e-05, "epoch": 4.2102781706742105, "percentage": 21.05, "elapsed_time": "0:32:20", "remaining_time": "2:01:15", "throughput": 4632.16, "total_tokens": 8986880} {"current_steps": 8935, "total_steps": 42420, "loss": 0.2381, "lr": 4.815966160242656e-05, "epoch": 4.212635549269213, "percentage": 21.06, "elapsed_time": "0:32:21", "remaining_time": "2:01:14", "throughput": 4632.24, "total_tokens": 8991872} {"current_steps": 8940, "total_steps": 42420, "loss": 0.3307, "lr": 4.8155786198455075e-05, "epoch": 4.214992927864215, "percentage": 21.07, "elapsed_time": "0:32:22", "remaining_time": "2:01:13", "throughput": 4632.31, "total_tokens": 8996960} {"current_steps": 8945, "total_steps": 42420, "loss": 0.14, "lr": 4.815190687460216e-05, "epoch": 4.217350306459218, "percentage": 21.09, "elapsed_time": "0:32:23", "remaining_time": "2:01:11", "throughput": 4632.32, "total_tokens": 9001152} {"current_steps": 8950, "total_steps": 42420, "loss": 0.173, "lr": 4.81480236315245e-05, "epoch": 4.21970768505422, "percentage": 21.1, "elapsed_time": "0:32:24", "remaining_time": "2:01:11", "throughput": 4632.53, "total_tokens": 9007360} {"current_steps": 8955, "total_steps": 42420, "loss": 0.2162, "lr": 4.8144136469879476e-05, "epoch": 4.222065063649222, "percentage": 21.11, "elapsed_time": "0:32:25", "remaining_time": "2:01:10", "throughput": 4632.74, "total_tokens": 9013280} {"current_steps": 8960, "total_steps": 42420, "loss": 0.0734, "lr": 4.814024539032511e-05, "epoch": 4.224422442244224, "percentage": 21.12, "elapsed_time": "0:32:26", "remaining_time": "2:01:09", "throughput": 4632.89, "total_tokens": 9018528} {"current_steps": 8965, "total_steps": 42420, "loss": 0.1097, "lr": 4.813635039352009e-05, "epoch": 4.226779820839226, "percentage": 21.13, "elapsed_time": "0:32:27", "remaining_time": "2:01:07", "throughput": 4633.02, "total_tokens": 9023264} {"current_steps": 8970, "total_steps": 42420, "loss": 0.1649, "lr": 4.8132451480123794e-05, "epoch": 4.229137199434229, "percentage": 21.15, "elapsed_time": "0:32:28", "remaining_time": "2:01:06", "throughput": 4633.12, "total_tokens": 9028672} {"current_steps": 8975, "total_steps": 42420, "loss": 0.1033, "lr": 4.8128548650796226e-05, "epoch": 4.231494578029231, "percentage": 21.16, "elapsed_time": "0:32:29", "remaining_time": "2:01:05", "throughput": 4633.1, "total_tokens": 9032704} {"current_steps": 8980, "total_steps": 42420, "loss": 0.1919, "lr": 4.8124641906198065e-05, "epoch": 4.233851956624234, "percentage": 21.17, "elapsed_time": "0:32:30", "remaining_time": "2:01:03", "throughput": 4633.22, "total_tokens": 9037664} {"current_steps": 8985, "total_steps": 42420, "loss": 0.2465, "lr": 4.812073124699067e-05, "epoch": 4.236209335219236, "percentage": 21.18, "elapsed_time": "0:32:31", "remaining_time": "2:01:02", "throughput": 4633.34, "total_tokens": 9042880} {"current_steps": 8990, "total_steps": 42420, "loss": 0.1394, "lr": 4.811681667383604e-05, "epoch": 4.238566713814238, "percentage": 21.19, "elapsed_time": "0:32:32", "remaining_time": "2:01:02", "throughput": 4633.49, "total_tokens": 9048832} {"current_steps": 8995, "total_steps": 42420, "loss": 0.1623, "lr": 4.811289818739685e-05, "epoch": 4.240924092409241, "percentage": 21.2, "elapsed_time": "0:32:33", "remaining_time": "2:01:00", "throughput": 4633.58, "total_tokens": 9053984} {"current_steps": 9000, "total_steps": 42420, "loss": 0.0819, "lr": 4.810897578833643e-05, "epoch": 4.243281471004243, "percentage": 21.22, "elapsed_time": "0:32:35", "remaining_time": "2:01:00", "throughput": 4633.75, "total_tokens": 9059584} {"current_steps": 9005, "total_steps": 42420, "loss": 0.0592, "lr": 4.8105049477318775e-05, "epoch": 4.245638849599246, "percentage": 21.23, "elapsed_time": "0:32:36", "remaining_time": "2:00:58", "throughput": 4633.84, "total_tokens": 9064480} {"current_steps": 9010, "total_steps": 42420, "loss": 0.1775, "lr": 4.810111925500855e-05, "epoch": 4.247996228194248, "percentage": 21.24, "elapsed_time": "0:32:37", "remaining_time": "2:00:58", "throughput": 4634.06, "total_tokens": 9070528} {"current_steps": 9015, "total_steps": 42420, "loss": 0.2534, "lr": 4.8097185122071064e-05, "epoch": 4.2503536067892504, "percentage": 21.25, "elapsed_time": "0:32:38", "remaining_time": "2:00:56", "throughput": 4634.1, "total_tokens": 9075360} {"current_steps": 9020, "total_steps": 42420, "loss": 0.1635, "lr": 4.809324707917231e-05, "epoch": 4.252710985384253, "percentage": 21.26, "elapsed_time": "0:32:39", "remaining_time": "2:00:55", "throughput": 4634.12, "total_tokens": 9079808} {"current_steps": 9025, "total_steps": 42420, "loss": 0.0689, "lr": 4.808930512697892e-05, "epoch": 4.255068363979255, "percentage": 21.28, "elapsed_time": "0:32:40", "remaining_time": "2:00:53", "throughput": 4634.13, "total_tokens": 9083744} {"current_steps": 9030, "total_steps": 42420, "loss": 0.1105, "lr": 4.8085359266158216e-05, "epoch": 4.257425742574258, "percentage": 21.29, "elapsed_time": "0:32:41", "remaining_time": "2:00:51", "throughput": 4634.19, "total_tokens": 9088256} {"current_steps": 9035, "total_steps": 42420, "loss": 0.1627, "lr": 4.808140949737815e-05, "epoch": 4.25978312116926, "percentage": 21.3, "elapsed_time": "0:32:42", "remaining_time": "2:00:50", "throughput": 4634.29, "total_tokens": 9093504} {"current_steps": 9040, "total_steps": 42420, "loss": 0.122, "lr": 4.807745582130736e-05, "epoch": 4.2621404997642625, "percentage": 21.31, "elapsed_time": "0:32:43", "remaining_time": "2:00:49", "throughput": 4634.39, "total_tokens": 9098528} {"current_steps": 9045, "total_steps": 42420, "loss": 0.1046, "lr": 4.8073498238615125e-05, "epoch": 4.264497878359265, "percentage": 21.32, "elapsed_time": "0:32:44", "remaining_time": "2:00:47", "throughput": 4634.5, "total_tokens": 9103296} {"current_steps": 9050, "total_steps": 42420, "loss": 0.1367, "lr": 4.806953674997141e-05, "epoch": 4.266855256954267, "percentage": 21.33, "elapsed_time": "0:32:45", "remaining_time": "2:00:46", "throughput": 4634.6, "total_tokens": 9108064} {"current_steps": 9055, "total_steps": 42420, "loss": 0.1599, "lr": 4.806557135604682e-05, "epoch": 4.26921263554927, "percentage": 21.35, "elapsed_time": "0:32:46", "remaining_time": "2:00:44", "throughput": 4634.5, "total_tokens": 9112320} {"current_steps": 9060, "total_steps": 42420, "loss": 0.0521, "lr": 4.806160205751263e-05, "epoch": 4.271570014144271, "percentage": 21.36, "elapsed_time": "0:32:47", "remaining_time": "2:00:44", "throughput": 4634.72, "total_tokens": 9118368} {"current_steps": 9065, "total_steps": 42420, "loss": 0.1896, "lr": 4.805762885504077e-05, "epoch": 4.273927392739274, "percentage": 21.37, "elapsed_time": "0:32:48", "remaining_time": "2:00:43", "throughput": 4634.89, "total_tokens": 9124000} {"current_steps": 9070, "total_steps": 42420, "loss": 0.3093, "lr": 4.8053651749303854e-05, "epoch": 4.276284771334276, "percentage": 21.38, "elapsed_time": "0:32:49", "remaining_time": "2:00:42", "throughput": 4635.07, "total_tokens": 9129472} {"current_steps": 9075, "total_steps": 42420, "loss": 0.1147, "lr": 4.804967074097511e-05, "epoch": 4.278642149929278, "percentage": 21.39, "elapsed_time": "0:32:50", "remaining_time": "2:00:40", "throughput": 4635.1, "total_tokens": 9133952} {"current_steps": 9080, "total_steps": 42420, "loss": 0.2381, "lr": 4.804568583072848e-05, "epoch": 4.280999528524281, "percentage": 21.4, "elapsed_time": "0:32:51", "remaining_time": "2:00:39", "throughput": 4635.18, "total_tokens": 9138944} {"current_steps": 9085, "total_steps": 42420, "loss": 0.2199, "lr": 4.804169701923853e-05, "epoch": 4.283356907119283, "percentage": 21.42, "elapsed_time": "0:32:52", "remaining_time": "2:00:38", "throughput": 4635.34, "total_tokens": 9144352} {"current_steps": 9090, "total_steps": 42420, "loss": 0.0638, "lr": 4.8037704307180496e-05, "epoch": 4.285714285714286, "percentage": 21.43, "elapsed_time": "0:32:53", "remaining_time": "2:00:36", "throughput": 4635.42, "total_tokens": 9148896} {"current_steps": 9095, "total_steps": 42420, "loss": 0.104, "lr": 4.803370769523029e-05, "epoch": 4.288071664309288, "percentage": 21.44, "elapsed_time": "0:32:54", "remaining_time": "2:00:35", "throughput": 4635.47, "total_tokens": 9153472} {"current_steps": 9100, "total_steps": 42420, "loss": 0.3898, "lr": 4.802970718406446e-05, "epoch": 4.29042904290429, "percentage": 21.45, "elapsed_time": "0:32:55", "remaining_time": "2:00:34", "throughput": 4635.65, "total_tokens": 9159392} {"current_steps": 9105, "total_steps": 42420, "loss": 0.1301, "lr": 4.802570277436022e-05, "epoch": 4.292786421499293, "percentage": 21.46, "elapsed_time": "0:32:56", "remaining_time": "2:00:33", "throughput": 4635.78, "total_tokens": 9164032} {"current_steps": 9110, "total_steps": 42420, "loss": 0.2116, "lr": 4.802169446679546e-05, "epoch": 4.295143800094295, "percentage": 21.48, "elapsed_time": "0:32:57", "remaining_time": "2:00:31", "throughput": 4635.84, "total_tokens": 9168480} {"current_steps": 9115, "total_steps": 42420, "loss": 0.0671, "lr": 4.8017682262048714e-05, "epoch": 4.297501178689298, "percentage": 21.49, "elapsed_time": "0:32:58", "remaining_time": "2:00:29", "throughput": 4635.95, "total_tokens": 9172928} {"current_steps": 9120, "total_steps": 42420, "loss": 0.2382, "lr": 4.801366616079917e-05, "epoch": 4.2998585572843, "percentage": 21.5, "elapsed_time": "0:32:59", "remaining_time": "2:00:28", "throughput": 4636.03, "total_tokens": 9177504} {"current_steps": 9125, "total_steps": 42420, "loss": 0.1393, "lr": 4.80096461637267e-05, "epoch": 4.302215935879302, "percentage": 21.51, "elapsed_time": "0:33:00", "remaining_time": "2:00:27", "throughput": 4636.23, "total_tokens": 9183584} {"current_steps": 9130, "total_steps": 42420, "loss": 0.2302, "lr": 4.800562227151182e-05, "epoch": 4.304573314474305, "percentage": 21.52, "elapsed_time": "0:33:01", "remaining_time": "2:00:26", "throughput": 4636.33, "total_tokens": 9188640} {"current_steps": 9135, "total_steps": 42420, "loss": 0.091, "lr": 4.80015944848357e-05, "epoch": 4.306930693069307, "percentage": 21.53, "elapsed_time": "0:33:02", "remaining_time": "2:00:25", "throughput": 4636.46, "total_tokens": 9194016} {"current_steps": 9140, "total_steps": 42420, "loss": 0.1134, "lr": 4.799756280438017e-05, "epoch": 4.30928807166431, "percentage": 21.55, "elapsed_time": "0:33:04", "remaining_time": "2:00:24", "throughput": 4636.54, "total_tokens": 9199040} {"current_steps": 9145, "total_steps": 42420, "loss": 0.2248, "lr": 4.799352723082775e-05, "epoch": 4.311645450259312, "percentage": 21.56, "elapsed_time": "0:33:05", "remaining_time": "2:00:23", "throughput": 4636.73, "total_tokens": 9205472} {"current_steps": 9150, "total_steps": 42420, "loss": 0.1024, "lr": 4.7989487764861566e-05, "epoch": 4.314002828854314, "percentage": 21.57, "elapsed_time": "0:33:06", "remaining_time": "2:00:22", "throughput": 4636.55, "total_tokens": 9209600} {"current_steps": 9155, "total_steps": 42420, "loss": 0.0709, "lr": 4.798544440716544e-05, "epoch": 4.316360207449316, "percentage": 21.58, "elapsed_time": "0:33:07", "remaining_time": "2:00:20", "throughput": 4636.66, "total_tokens": 9214496} {"current_steps": 9160, "total_steps": 42420, "loss": 0.1886, "lr": 4.798139715842386e-05, "epoch": 4.318717586044318, "percentage": 21.59, "elapsed_time": "0:33:08", "remaining_time": "2:00:19", "throughput": 4636.73, "total_tokens": 9218912} {"current_steps": 9165, "total_steps": 42420, "loss": 0.0961, "lr": 4.797734601932193e-05, "epoch": 4.321074964639321, "percentage": 21.61, "elapsed_time": "0:33:09", "remaining_time": "2:00:17", "throughput": 4636.76, "total_tokens": 9223232} {"current_steps": 9170, "total_steps": 42420, "loss": 0.1314, "lr": 4.797329099054546e-05, "epoch": 4.323432343234323, "percentage": 21.62, "elapsed_time": "0:33:10", "remaining_time": "2:00:16", "throughput": 4636.89, "total_tokens": 9228224} {"current_steps": 9175, "total_steps": 42420, "loss": 0.1205, "lr": 4.796923207278088e-05, "epoch": 4.3257897218293255, "percentage": 21.63, "elapsed_time": "0:33:11", "remaining_time": "2:00:14", "throughput": 4637.0, "total_tokens": 9232768} {"current_steps": 9180, "total_steps": 42420, "loss": 0.0734, "lr": 4.7965169266715315e-05, "epoch": 4.328147100424328, "percentage": 21.64, "elapsed_time": "0:33:12", "remaining_time": "2:00:13", "throughput": 4637.16, "total_tokens": 9238080} {"current_steps": 9185, "total_steps": 42420, "loss": 0.3569, "lr": 4.796110257303652e-05, "epoch": 4.33050447901933, "percentage": 21.65, "elapsed_time": "0:33:13", "remaining_time": "2:00:12", "throughput": 4637.28, "total_tokens": 9243296} {"current_steps": 9190, "total_steps": 42420, "loss": 0.1727, "lr": 4.795703199243291e-05, "epoch": 4.332861857614333, "percentage": 21.66, "elapsed_time": "0:33:14", "remaining_time": "2:00:11", "throughput": 4637.49, "total_tokens": 9249440} {"current_steps": 9195, "total_steps": 42420, "loss": 0.1574, "lr": 4.7952957525593575e-05, "epoch": 4.335219236209335, "percentage": 21.68, "elapsed_time": "0:33:15", "remaining_time": "2:00:11", "throughput": 4637.69, "total_tokens": 9255392} {"current_steps": 9200, "total_steps": 42420, "loss": 0.1194, "lr": 4.794887917320825e-05, "epoch": 4.3375766148043375, "percentage": 21.69, "elapsed_time": "0:33:16", "remaining_time": "2:00:10", "throughput": 4637.81, "total_tokens": 9260768} {"current_steps": 9205, "total_steps": 42420, "loss": 0.2798, "lr": 4.794479693596733e-05, "epoch": 4.33993399339934, "percentage": 21.7, "elapsed_time": "0:33:17", "remaining_time": "2:00:09", "throughput": 4637.93, "total_tokens": 9266144} {"current_steps": 9210, "total_steps": 42420, "loss": 0.0722, "lr": 4.794071081456187e-05, "epoch": 4.342291371994342, "percentage": 21.71, "elapsed_time": "0:33:18", "remaining_time": "2:00:07", "throughput": 4637.97, "total_tokens": 9270336} {"current_steps": 9215, "total_steps": 42420, "loss": 0.1928, "lr": 4.793662080968358e-05, "epoch": 4.344648750589345, "percentage": 21.72, "elapsed_time": "0:33:19", "remaining_time": "2:00:06", "throughput": 4637.94, "total_tokens": 9275200} {"current_steps": 9220, "total_steps": 42420, "loss": 0.0456, "lr": 4.793252692202483e-05, "epoch": 4.347006129184347, "percentage": 21.74, "elapsed_time": "0:33:20", "remaining_time": "2:00:04", "throughput": 4638.0, "total_tokens": 9279360} {"current_steps": 9225, "total_steps": 42420, "loss": 0.2146, "lr": 4.792842915227864e-05, "epoch": 4.3493635077793495, "percentage": 21.75, "elapsed_time": "0:33:21", "remaining_time": "2:00:03", "throughput": 4638.16, "total_tokens": 9284544} {"current_steps": 9230, "total_steps": 42420, "loss": 0.3047, "lr": 4.79243275011387e-05, "epoch": 4.351720886374352, "percentage": 21.76, "elapsed_time": "0:33:22", "remaining_time": "2:00:01", "throughput": 4638.23, "total_tokens": 9289184} {"current_steps": 9235, "total_steps": 42420, "loss": 0.0921, "lr": 4.792022196929935e-05, "epoch": 4.354078264969354, "percentage": 21.77, "elapsed_time": "0:33:23", "remaining_time": "2:00:00", "throughput": 4638.41, "total_tokens": 9294208} {"current_steps": 9240, "total_steps": 42420, "loss": 0.0361, "lr": 4.7916112557455584e-05, "epoch": 4.356435643564357, "percentage": 21.78, "elapsed_time": "0:33:24", "remaining_time": "1:59:58", "throughput": 4638.51, "total_tokens": 9298656} {"current_steps": 9245, "total_steps": 42420, "loss": 0.1758, "lr": 4.791199926630305e-05, "epoch": 4.358793022159359, "percentage": 21.79, "elapsed_time": "0:33:25", "remaining_time": "1:59:58", "throughput": 4638.75, "total_tokens": 9304960} {"current_steps": 9250, "total_steps": 42420, "loss": 0.0824, "lr": 4.7907882096538066e-05, "epoch": 4.3611504007543616, "percentage": 21.81, "elapsed_time": "0:33:27", "remaining_time": "1:59:57", "throughput": 4638.9, "total_tokens": 9310496} {"current_steps": 9255, "total_steps": 42420, "loss": 0.1547, "lr": 4.79037610488576e-05, "epoch": 4.363507779349364, "percentage": 21.82, "elapsed_time": "0:33:27", "remaining_time": "1:59:55", "throughput": 4638.94, "total_tokens": 9314528} {"current_steps": 9260, "total_steps": 42420, "loss": 0.0799, "lr": 4.789963612395927e-05, "epoch": 4.3658651579443655, "percentage": 21.83, "elapsed_time": "0:33:28", "remaining_time": "1:59:54", "throughput": 4639.1, "total_tokens": 9319936} {"current_steps": 9265, "total_steps": 42420, "loss": 0.09, "lr": 4.789550732254135e-05, "epoch": 4.368222536539368, "percentage": 21.84, "elapsed_time": "0:33:29", "remaining_time": "1:59:52", "throughput": 4639.12, "total_tokens": 9324608} {"current_steps": 9270, "total_steps": 42420, "loss": 0.2163, "lr": 4.78913746453028e-05, "epoch": 4.37057991513437, "percentage": 21.85, "elapsed_time": "0:33:30", "remaining_time": "1:59:51", "throughput": 4639.27, "total_tokens": 9329568} {"current_steps": 9275, "total_steps": 42420, "loss": 0.22, "lr": 4.788723809294318e-05, "epoch": 4.372937293729373, "percentage": 21.86, "elapsed_time": "0:33:31", "remaining_time": "1:59:49", "throughput": 4639.26, "total_tokens": 9333888} {"current_steps": 9280, "total_steps": 42420, "loss": 0.2085, "lr": 4.7883097666162764e-05, "epoch": 4.375294672324375, "percentage": 21.88, "elapsed_time": "0:33:32", "remaining_time": "1:59:48", "throughput": 4639.36, "total_tokens": 9338528} {"current_steps": 9285, "total_steps": 42420, "loss": 0.2884, "lr": 4.787895336566244e-05, "epoch": 4.3776520509193775, "percentage": 21.89, "elapsed_time": "0:33:33", "remaining_time": "1:59:46", "throughput": 4639.49, "total_tokens": 9343488} {"current_steps": 9290, "total_steps": 42420, "loss": 0.2699, "lr": 4.787480519214378e-05, "epoch": 4.38000942951438, "percentage": 21.9, "elapsed_time": "0:33:34", "remaining_time": "1:59:45", "throughput": 4639.58, "total_tokens": 9348256} {"current_steps": 9295, "total_steps": 42420, "loss": 0.0716, "lr": 4.7870653146308984e-05, "epoch": 4.382366808109382, "percentage": 21.91, "elapsed_time": "0:33:35", "remaining_time": "1:59:44", "throughput": 4639.76, "total_tokens": 9353216} {"current_steps": 9300, "total_steps": 42420, "loss": 0.1922, "lr": 4.786649722886094e-05, "epoch": 4.384724186704385, "percentage": 21.92, "elapsed_time": "0:33:36", "remaining_time": "1:59:42", "throughput": 4639.85, "total_tokens": 9358144} {"current_steps": 9305, "total_steps": 42420, "loss": 0.1072, "lr": 4.786233744050317e-05, "epoch": 4.387081565299387, "percentage": 21.94, "elapsed_time": "0:33:37", "remaining_time": "1:59:41", "throughput": 4639.93, "total_tokens": 9363072} {"current_steps": 9310, "total_steps": 42420, "loss": 0.1475, "lr": 4.785817378193984e-05, "epoch": 4.3894389438943895, "percentage": 21.95, "elapsed_time": "0:33:39", "remaining_time": "1:59:41", "throughput": 4640.13, "total_tokens": 9370080} {"current_steps": 9315, "total_steps": 42420, "loss": 0.1062, "lr": 4.785400625387581e-05, "epoch": 4.391796322489392, "percentage": 21.96, "elapsed_time": "0:33:40", "remaining_time": "1:59:40", "throughput": 4640.32, "total_tokens": 9375424} {"current_steps": 9320, "total_steps": 42420, "loss": 0.0941, "lr": 4.784983485701655e-05, "epoch": 4.394153701084394, "percentage": 21.97, "elapsed_time": "0:33:41", "remaining_time": "1:59:39", "throughput": 4640.42, "total_tokens": 9380512} {"current_steps": 9325, "total_steps": 42420, "loss": 0.1701, "lr": 4.784565959206822e-05, "epoch": 4.396511079679397, "percentage": 21.98, "elapsed_time": "0:33:42", "remaining_time": "1:59:37", "throughput": 4640.46, "total_tokens": 9385024} {"current_steps": 9330, "total_steps": 42420, "loss": 0.1462, "lr": 4.784148045973762e-05, "epoch": 4.398868458274399, "percentage": 21.99, "elapsed_time": "0:33:43", "remaining_time": "1:59:35", "throughput": 4640.44, "total_tokens": 9388832} {"current_steps": 9335, "total_steps": 42420, "loss": 0.2319, "lr": 4.78372974607322e-05, "epoch": 4.4012258368694015, "percentage": 22.01, "elapsed_time": "0:33:44", "remaining_time": "1:59:34", "throughput": 4640.59, "total_tokens": 9393952} {"current_steps": 9340, "total_steps": 42420, "loss": 0.3165, "lr": 4.7833110595760076e-05, "epoch": 4.403583215464404, "percentage": 22.02, "elapsed_time": "0:33:45", "remaining_time": "1:59:32", "throughput": 4640.67, "total_tokens": 9398496} {"current_steps": 9345, "total_steps": 42420, "loss": 0.1058, "lr": 4.7828919865530016e-05, "epoch": 4.405940594059406, "percentage": 22.03, "elapsed_time": "0:33:46", "remaining_time": "1:59:31", "throughput": 4640.68, "total_tokens": 9402848} {"current_steps": 9350, "total_steps": 42420, "loss": 0.1046, "lr": 4.782472527075144e-05, "epoch": 4.408297972654409, "percentage": 22.04, "elapsed_time": "0:33:47", "remaining_time": "1:59:29", "throughput": 4640.74, "total_tokens": 9407520} {"current_steps": 9355, "total_steps": 42420, "loss": 0.1903, "lr": 4.7820526812134416e-05, "epoch": 4.41065535124941, "percentage": 22.05, "elapsed_time": "0:33:48", "remaining_time": "1:59:28", "throughput": 4640.85, "total_tokens": 9412096} {"current_steps": 9360, "total_steps": 42420, "loss": 0.2708, "lr": 4.781632449038966e-05, "epoch": 4.413012729844413, "percentage": 22.07, "elapsed_time": "0:33:49", "remaining_time": "1:59:27", "throughput": 4641.02, "total_tokens": 9417696} {"current_steps": 9365, "total_steps": 42420, "loss": 0.2023, "lr": 4.781211830622858e-05, "epoch": 4.415370108439415, "percentage": 22.08, "elapsed_time": "0:33:50", "remaining_time": "1:59:26", "throughput": 4641.19, "total_tokens": 9423008} {"current_steps": 9370, "total_steps": 42420, "loss": 0.0874, "lr": 4.78079082603632e-05, "epoch": 4.417727487034417, "percentage": 22.09, "elapsed_time": "0:33:51", "remaining_time": "1:59:24", "throughput": 4641.19, "total_tokens": 9427488} {"current_steps": 9375, "total_steps": 42420, "loss": 0.2436, "lr": 4.78036943535062e-05, "epoch": 4.42008486562942, "percentage": 22.1, "elapsed_time": "0:33:52", "remaining_time": "1:59:23", "throughput": 4641.29, "total_tokens": 9432352} {"current_steps": 9380, "total_steps": 42420, "loss": 0.1236, "lr": 4.779947658637093e-05, "epoch": 4.422442244224422, "percentage": 22.11, "elapsed_time": "0:33:53", "remaining_time": "1:59:22", "throughput": 4641.31, "total_tokens": 9437184} {"current_steps": 9385, "total_steps": 42420, "loss": 0.0893, "lr": 4.7795254959671396e-05, "epoch": 4.424799622819425, "percentage": 22.12, "elapsed_time": "0:33:54", "remaining_time": "1:59:21", "throughput": 4641.48, "total_tokens": 9443264} {"current_steps": 9390, "total_steps": 42420, "loss": 0.095, "lr": 4.779102947412223e-05, "epoch": 4.427157001414427, "percentage": 22.14, "elapsed_time": "0:33:55", "remaining_time": "1:59:19", "throughput": 4641.52, "total_tokens": 9447392} {"current_steps": 9395, "total_steps": 42420, "loss": 0.088, "lr": 4.7786800130438745e-05, "epoch": 4.429514380009429, "percentage": 22.15, "elapsed_time": "0:33:56", "remaining_time": "1:59:18", "throughput": 4641.61, "total_tokens": 9452064} {"current_steps": 9400, "total_steps": 42420, "loss": 0.131, "lr": 4.7782566929336895e-05, "epoch": 4.431871758604432, "percentage": 22.16, "elapsed_time": "0:33:57", "remaining_time": "1:59:16", "throughput": 4641.71, "total_tokens": 9456960} {"current_steps": 9405, "total_steps": 42420, "loss": 0.1404, "lr": 4.7778329871533296e-05, "epoch": 4.434229137199434, "percentage": 22.17, "elapsed_time": "0:33:58", "remaining_time": "1:59:15", "throughput": 4641.81, "total_tokens": 9461856} {"current_steps": 9410, "total_steps": 42420, "loss": 0.1663, "lr": 4.77740889577452e-05, "epoch": 4.436586515794437, "percentage": 22.18, "elapsed_time": "0:33:59", "remaining_time": "1:59:14", "throughput": 4641.94, "total_tokens": 9466848} {"current_steps": 9415, "total_steps": 42420, "loss": 0.1845, "lr": 4.7769844188690526e-05, "epoch": 4.438943894389439, "percentage": 22.19, "elapsed_time": "0:34:00", "remaining_time": "1:59:12", "throughput": 4642.05, "total_tokens": 9471648} {"current_steps": 9420, "total_steps": 42420, "loss": 0.1443, "lr": 4.776559556508784e-05, "epoch": 4.441301272984441, "percentage": 22.21, "elapsed_time": "0:34:01", "remaining_time": "1:59:11", "throughput": 4642.2, "total_tokens": 9476896} {"current_steps": 9425, "total_steps": 42420, "loss": 0.1308, "lr": 4.776134308765636e-05, "epoch": 4.443658651579444, "percentage": 22.22, "elapsed_time": "0:34:02", "remaining_time": "1:59:09", "throughput": 4642.2, "total_tokens": 9481056} {"current_steps": 9430, "total_steps": 42420, "loss": 0.0873, "lr": 4.775708675711597e-05, "epoch": 4.446016030174446, "percentage": 22.23, "elapsed_time": "0:34:03", "remaining_time": "1:59:08", "throughput": 4642.39, "total_tokens": 9486592} {"current_steps": 9435, "total_steps": 42420, "loss": 0.1183, "lr": 4.7752826574187174e-05, "epoch": 4.448373408769449, "percentage": 22.24, "elapsed_time": "0:34:04", "remaining_time": "1:59:07", "throughput": 4642.39, "total_tokens": 9491136} {"current_steps": 9440, "total_steps": 42420, "loss": 0.1737, "lr": 4.7748562539591167e-05, "epoch": 4.450730787364451, "percentage": 22.25, "elapsed_time": "0:34:05", "remaining_time": "1:59:05", "throughput": 4642.4, "total_tokens": 9495488} {"current_steps": 9445, "total_steps": 42420, "loss": 0.1514, "lr": 4.774429465404977e-05, "epoch": 4.4530881659594534, "percentage": 22.27, "elapsed_time": "0:34:06", "remaining_time": "1:59:04", "throughput": 4642.47, "total_tokens": 9500064} {"current_steps": 9450, "total_steps": 42420, "loss": 0.1461, "lr": 4.774002291828546e-05, "epoch": 4.455445544554456, "percentage": 22.28, "elapsed_time": "0:34:07", "remaining_time": "1:59:02", "throughput": 4642.58, "total_tokens": 9504960} {"current_steps": 9455, "total_steps": 42420, "loss": 0.1504, "lr": 4.773574733302138e-05, "epoch": 4.457802923149458, "percentage": 22.29, "elapsed_time": "0:34:08", "remaining_time": "1:59:03", "throughput": 4642.69, "total_tokens": 9511840} {"current_steps": 9460, "total_steps": 42420, "loss": 0.1877, "lr": 4.77314678989813e-05, "epoch": 4.46016030174446, "percentage": 22.3, "elapsed_time": "0:34:10", "remaining_time": "1:59:05", "throughput": 4642.97, "total_tokens": 9521920} {"current_steps": 9465, "total_steps": 42420, "loss": 0.119, "lr": 4.772718461688967e-05, "epoch": 4.462517680339462, "percentage": 22.31, "elapsed_time": "0:34:11", "remaining_time": "1:59:04", "throughput": 4643.13, "total_tokens": 9527552} {"current_steps": 9470, "total_steps": 42420, "loss": 0.2653, "lr": 4.772289748747156e-05, "epoch": 4.464875058934465, "percentage": 22.32, "elapsed_time": "0:34:13", "remaining_time": "1:59:03", "throughput": 4643.29, "total_tokens": 9532960} {"current_steps": 9475, "total_steps": 42420, "loss": 0.0612, "lr": 4.7718606511452734e-05, "epoch": 4.467232437529467, "percentage": 22.34, "elapsed_time": "0:34:14", "remaining_time": "1:59:02", "throughput": 4643.39, "total_tokens": 9537952} {"current_steps": 9480, "total_steps": 42420, "loss": 0.1325, "lr": 4.7714311689559556e-05, "epoch": 4.469589816124469, "percentage": 22.35, "elapsed_time": "0:34:15", "remaining_time": "1:59:00", "throughput": 4643.45, "total_tokens": 9542848} {"current_steps": 9485, "total_steps": 42420, "loss": 0.2062, "lr": 4.7710013022519073e-05, "epoch": 4.471947194719472, "percentage": 22.36, "elapsed_time": "0:34:16", "remaining_time": "1:58:59", "throughput": 4643.54, "total_tokens": 9547680} {"current_steps": 9490, "total_steps": 42420, "loss": 0.1433, "lr": 4.770571051105899e-05, "epoch": 4.474304573314474, "percentage": 22.37, "elapsed_time": "0:34:17", "remaining_time": "1:58:58", "throughput": 4643.62, "total_tokens": 9552352} {"current_steps": 9495, "total_steps": 42420, "loss": 0.2407, "lr": 4.770140415590762e-05, "epoch": 4.476661951909477, "percentage": 22.38, "elapsed_time": "0:34:18", "remaining_time": "1:58:57", "throughput": 4643.88, "total_tokens": 9559232} {"current_steps": 9500, "total_steps": 42420, "loss": 0.1524, "lr": 4.769709395779399e-05, "epoch": 4.479019330504479, "percentage": 22.4, "elapsed_time": "0:34:19", "remaining_time": "1:58:56", "throughput": 4643.95, "total_tokens": 9563968} {"current_steps": 9505, "total_steps": 42420, "loss": 0.0842, "lr": 4.7692779917447726e-05, "epoch": 4.481376709099481, "percentage": 22.41, "elapsed_time": "0:34:20", "remaining_time": "1:58:55", "throughput": 4644.01, "total_tokens": 9568800} {"current_steps": 9510, "total_steps": 42420, "loss": 0.1927, "lr": 4.7688462035599126e-05, "epoch": 4.483734087694484, "percentage": 22.42, "elapsed_time": "0:34:21", "remaining_time": "1:58:53", "throughput": 4644.04, "total_tokens": 9573472} {"current_steps": 9515, "total_steps": 42420, "loss": 0.1398, "lr": 4.768414031297912e-05, "epoch": 4.486091466289486, "percentage": 22.43, "elapsed_time": "0:34:22", "remaining_time": "1:58:52", "throughput": 4644.17, "total_tokens": 9578528} {"current_steps": 9520, "total_steps": 42420, "loss": 0.2447, "lr": 4.7679814750319324e-05, "epoch": 4.488448844884489, "percentage": 22.44, "elapsed_time": "0:34:23", "remaining_time": "1:58:51", "throughput": 4644.29, "total_tokens": 9583680} {"current_steps": 9525, "total_steps": 42420, "loss": 0.1341, "lr": 4.767548534835197e-05, "epoch": 4.490806223479491, "percentage": 22.45, "elapsed_time": "0:34:24", "remaining_time": "1:58:49", "throughput": 4644.39, "total_tokens": 9588352} {"current_steps": 9530, "total_steps": 42420, "loss": 0.0642, "lr": 4.767115210780995e-05, "epoch": 4.493163602074493, "percentage": 22.47, "elapsed_time": "0:34:25", "remaining_time": "1:58:48", "throughput": 4644.45, "total_tokens": 9593600} {"current_steps": 9535, "total_steps": 42420, "loss": 0.0503, "lr": 4.7666815029426816e-05, "epoch": 4.495520980669496, "percentage": 22.48, "elapsed_time": "0:34:26", "remaining_time": "1:58:48", "throughput": 4644.58, "total_tokens": 9599296} {"current_steps": 9540, "total_steps": 42420, "loss": 0.1123, "lr": 4.766247411393676e-05, "epoch": 4.497878359264498, "percentage": 22.49, "elapsed_time": "0:34:27", "remaining_time": "1:58:46", "throughput": 4644.58, "total_tokens": 9603296} {"current_steps": 9545, "total_steps": 42420, "loss": 0.1146, "lr": 4.7658129362074624e-05, "epoch": 4.500235737859501, "percentage": 22.5, "elapsed_time": "0:34:28", "remaining_time": "1:58:45", "throughput": 4644.76, "total_tokens": 9609088} {"current_steps": 9550, "total_steps": 42420, "loss": 0.1784, "lr": 4.76537807745759e-05, "epoch": 4.502593116454502, "percentage": 22.51, "elapsed_time": "0:34:29", "remaining_time": "1:58:44", "throughput": 4644.84, "total_tokens": 9613920} {"current_steps": 9555, "total_steps": 42420, "loss": 0.0685, "lr": 4.764942835217672e-05, "epoch": 4.5049504950495045, "percentage": 22.52, "elapsed_time": "0:34:30", "remaining_time": "1:58:42", "throughput": 4644.93, "total_tokens": 9619040} {"current_steps": 9560, "total_steps": 42420, "loss": 0.1175, "lr": 4.76450720956139e-05, "epoch": 4.507307873644507, "percentage": 22.54, "elapsed_time": "0:34:31", "remaining_time": "1:58:41", "throughput": 4645.08, "total_tokens": 9624576} {"current_steps": 9565, "total_steps": 42420, "loss": 0.191, "lr": 4.764071200562485e-05, "epoch": 4.509665252239509, "percentage": 22.55, "elapsed_time": "0:34:32", "remaining_time": "1:58:40", "throughput": 4645.1, "total_tokens": 9629280} {"current_steps": 9570, "total_steps": 42420, "loss": 0.2026, "lr": 4.763634808294768e-05, "epoch": 4.512022630834512, "percentage": 22.56, "elapsed_time": "0:34:34", "remaining_time": "1:58:39", "throughput": 4645.1, "total_tokens": 9633984} {"current_steps": 9575, "total_steps": 42420, "loss": 0.207, "lr": 4.763198032832113e-05, "epoch": 4.514380009429514, "percentage": 22.57, "elapsed_time": "0:34:35", "remaining_time": "1:58:37", "throughput": 4645.19, "total_tokens": 9638944} {"current_steps": 9580, "total_steps": 42420, "loss": 0.2082, "lr": 4.762760874248458e-05, "epoch": 4.5167373880245165, "percentage": 22.58, "elapsed_time": "0:34:35", "remaining_time": "1:58:36", "throughput": 4645.2, "total_tokens": 9643072} {"current_steps": 9585, "total_steps": 42420, "loss": 0.1249, "lr": 4.7623233326178055e-05, "epoch": 4.519094766619519, "percentage": 22.6, "elapsed_time": "0:34:36", "remaining_time": "1:58:34", "throughput": 4645.19, "total_tokens": 9647200} {"current_steps": 9590, "total_steps": 42420, "loss": 0.0968, "lr": 4.761885408014225e-05, "epoch": 4.521452145214521, "percentage": 22.61, "elapsed_time": "0:34:37", "remaining_time": "1:58:33", "throughput": 4645.37, "total_tokens": 9652960} {"current_steps": 9595, "total_steps": 42420, "loss": 0.1287, "lr": 4.76144710051185e-05, "epoch": 4.523809523809524, "percentage": 22.62, "elapsed_time": "0:34:38", "remaining_time": "1:58:32", "throughput": 4645.54, "total_tokens": 9657888} {"current_steps": 9600, "total_steps": 42420, "loss": 0.1938, "lr": 4.761008410184878e-05, "epoch": 4.526166902404526, "percentage": 22.63, "elapsed_time": "0:34:40", "remaining_time": "1:58:31", "throughput": 4645.73, "total_tokens": 9664320} {"current_steps": 9605, "total_steps": 42420, "loss": 0.1708, "lr": 4.760569337107572e-05, "epoch": 4.5285242809995285, "percentage": 22.64, "elapsed_time": "0:34:41", "remaining_time": "1:58:31", "throughput": 4645.89, "total_tokens": 9670176} {"current_steps": 9610, "total_steps": 42420, "loss": 0.1065, "lr": 4.7601298813542595e-05, "epoch": 4.530881659594531, "percentage": 22.65, "elapsed_time": "0:34:42", "remaining_time": "1:58:29", "throughput": 4645.9, "total_tokens": 9674176} {"current_steps": 9615, "total_steps": 42420, "loss": 0.0378, "lr": 4.759690042999333e-05, "epoch": 4.533239038189533, "percentage": 22.67, "elapsed_time": "0:34:43", "remaining_time": "1:58:28", "throughput": 4646.01, "total_tokens": 9679808} {"current_steps": 9620, "total_steps": 42420, "loss": 0.1916, "lr": 4.7592498221172496e-05, "epoch": 4.535596416784536, "percentage": 22.68, "elapsed_time": "0:34:44", "remaining_time": "1:58:27", "throughput": 4646.15, "total_tokens": 9685504} {"current_steps": 9625, "total_steps": 42420, "loss": 0.1394, "lr": 4.7588092187825305e-05, "epoch": 4.537953795379538, "percentage": 22.69, "elapsed_time": "0:34:45", "remaining_time": "1:58:26", "throughput": 4646.24, "total_tokens": 9690112} {"current_steps": 9630, "total_steps": 42420, "loss": 0.1071, "lr": 4.7583682330697635e-05, "epoch": 4.5403111739745405, "percentage": 22.7, "elapsed_time": "0:34:46", "remaining_time": "1:58:25", "throughput": 4646.35, "total_tokens": 9695392} {"current_steps": 9635, "total_steps": 42420, "loss": 0.1999, "lr": 4.7579268650536e-05, "epoch": 4.542668552569543, "percentage": 22.71, "elapsed_time": "0:34:47", "remaining_time": "1:58:23", "throughput": 4646.44, "total_tokens": 9699936} {"current_steps": 9640, "total_steps": 42420, "loss": 0.0896, "lr": 4.757485114808755e-05, "epoch": 4.545025931164545, "percentage": 22.73, "elapsed_time": "0:34:48", "remaining_time": "1:58:22", "throughput": 4646.53, "total_tokens": 9704736} {"current_steps": 9645, "total_steps": 42420, "loss": 0.0916, "lr": 4.757042982410011e-05, "epoch": 4.547383309759548, "percentage": 22.74, "elapsed_time": "0:34:49", "remaining_time": "1:58:21", "throughput": 4646.65, "total_tokens": 9710016} {"current_steps": 9650, "total_steps": 42420, "loss": 0.1967, "lr": 4.7566004679322114e-05, "epoch": 4.54974068835455, "percentage": 22.75, "elapsed_time": "0:34:50", "remaining_time": "1:58:19", "throughput": 4646.74, "total_tokens": 9714816} {"current_steps": 9655, "total_steps": 42420, "loss": 0.1904, "lr": 4.7561575714502676e-05, "epoch": 4.5520980669495525, "percentage": 22.76, "elapsed_time": "0:34:51", "remaining_time": "1:58:18", "throughput": 4646.84, "total_tokens": 9719744} {"current_steps": 9660, "total_steps": 42420, "loss": 0.0831, "lr": 4.755714293039155e-05, "epoch": 4.554455445544555, "percentage": 22.77, "elapsed_time": "0:34:52", "remaining_time": "1:58:17", "throughput": 4646.89, "total_tokens": 9724960} {"current_steps": 9665, "total_steps": 42420, "loss": 0.1512, "lr": 4.755270632773912e-05, "epoch": 4.5568128241395565, "percentage": 22.78, "elapsed_time": "0:34:53", "remaining_time": "1:58:15", "throughput": 4646.87, "total_tokens": 9729408} {"current_steps": 9670, "total_steps": 42420, "loss": 0.2232, "lr": 4.754826590729643e-05, "epoch": 4.559170202734559, "percentage": 22.8, "elapsed_time": "0:34:54", "remaining_time": "1:58:15", "throughput": 4647.03, "total_tokens": 9735360} {"current_steps": 9675, "total_steps": 42420, "loss": 0.1192, "lr": 4.754382166981517e-05, "epoch": 4.561527581329561, "percentage": 22.81, "elapsed_time": "0:34:56", "remaining_time": "1:58:14", "throughput": 4647.17, "total_tokens": 9740736} {"current_steps": 9680, "total_steps": 42420, "loss": 0.0456, "lr": 4.753937361604767e-05, "epoch": 4.563884959924564, "percentage": 22.82, "elapsed_time": "0:34:57", "remaining_time": "1:58:12", "throughput": 4647.26, "total_tokens": 9745312} {"current_steps": 9685, "total_steps": 42420, "loss": 0.1333, "lr": 4.753492174674692e-05, "epoch": 4.566242338519566, "percentage": 22.83, "elapsed_time": "0:34:57", "remaining_time": "1:58:10", "throughput": 4647.2, "total_tokens": 9749472} {"current_steps": 9690, "total_steps": 42420, "loss": 0.1384, "lr": 4.753046606266654e-05, "epoch": 4.5685997171145685, "percentage": 22.84, "elapsed_time": "0:34:58", "remaining_time": "1:58:09", "throughput": 4647.21, "total_tokens": 9753568} {"current_steps": 9695, "total_steps": 42420, "loss": 0.222, "lr": 4.75260065645608e-05, "epoch": 4.570957095709571, "percentage": 22.85, "elapsed_time": "0:34:59", "remaining_time": "1:58:07", "throughput": 4647.3, "total_tokens": 9758432} {"current_steps": 9700, "total_steps": 42420, "loss": 0.0822, "lr": 4.752154325318461e-05, "epoch": 4.573314474304573, "percentage": 22.87, "elapsed_time": "0:35:00", "remaining_time": "1:58:06", "throughput": 4647.43, "total_tokens": 9763872} {"current_steps": 9705, "total_steps": 42420, "loss": 0.1888, "lr": 4.7517076129293556e-05, "epoch": 4.575671852899576, "percentage": 22.88, "elapsed_time": "0:35:02", "remaining_time": "1:58:05", "throughput": 4647.55, "total_tokens": 9769248} {"current_steps": 9710, "total_steps": 42420, "loss": 0.0957, "lr": 4.7512605193643824e-05, "epoch": 4.578029231494578, "percentage": 22.89, "elapsed_time": "0:35:02", "remaining_time": "1:58:04", "throughput": 4647.63, "total_tokens": 9773600} {"current_steps": 9715, "total_steps": 42420, "loss": 0.2465, "lr": 4.750813044699227e-05, "epoch": 4.5803866100895805, "percentage": 22.9, "elapsed_time": "0:35:03", "remaining_time": "1:58:02", "throughput": 4647.63, "total_tokens": 9777696} {"current_steps": 9720, "total_steps": 42420, "loss": 0.092, "lr": 4.7503651890096404e-05, "epoch": 4.582743988684583, "percentage": 22.91, "elapsed_time": "0:35:04", "remaining_time": "1:58:00", "throughput": 4647.64, "total_tokens": 9781984} {"current_steps": 9725, "total_steps": 42420, "loss": 0.1451, "lr": 4.749916952371436e-05, "epoch": 4.585101367279585, "percentage": 22.93, "elapsed_time": "0:35:05", "remaining_time": "1:57:59", "throughput": 4647.71, "total_tokens": 9786912} {"current_steps": 9730, "total_steps": 42420, "loss": 0.2738, "lr": 4.749468334860493e-05, "epoch": 4.587458745874588, "percentage": 22.94, "elapsed_time": "0:35:06", "remaining_time": "1:57:58", "throughput": 4647.81, "total_tokens": 9791840} {"current_steps": 9735, "total_steps": 42420, "loss": 0.1109, "lr": 4.749019336552756e-05, "epoch": 4.58981612446959, "percentage": 22.95, "elapsed_time": "0:35:07", "remaining_time": "1:57:57", "throughput": 4647.96, "total_tokens": 9797184} {"current_steps": 9740, "total_steps": 42420, "loss": 0.1596, "lr": 4.7485699575242296e-05, "epoch": 4.5921735030645925, "percentage": 22.96, "elapsed_time": "0:35:08", "remaining_time": "1:57:55", "throughput": 4648.03, "total_tokens": 9802016} {"current_steps": 9745, "total_steps": 42420, "loss": 0.1625, "lr": 4.7481201978509894e-05, "epoch": 4.594530881659595, "percentage": 22.97, "elapsed_time": "0:35:10", "remaining_time": "1:57:54", "throughput": 4648.22, "total_tokens": 9807776} {"current_steps": 9750, "total_steps": 42420, "loss": 0.1742, "lr": 4.747670057609169e-05, "epoch": 4.596888260254596, "percentage": 22.98, "elapsed_time": "0:35:11", "remaining_time": "1:57:53", "throughput": 4648.31, "total_tokens": 9813312} {"current_steps": 9755, "total_steps": 42420, "loss": 0.0988, "lr": 4.747219536874973e-05, "epoch": 4.599245638849599, "percentage": 23.0, "elapsed_time": "0:35:12", "remaining_time": "1:57:52", "throughput": 4648.4, "total_tokens": 9818144} {"current_steps": 9760, "total_steps": 42420, "loss": 0.0906, "lr": 4.746768635724663e-05, "epoch": 4.601603017444601, "percentage": 23.01, "elapsed_time": "0:35:13", "remaining_time": "1:57:51", "throughput": 4648.46, "total_tokens": 9822816} {"current_steps": 9765, "total_steps": 42420, "loss": 0.1614, "lr": 4.746317354234573e-05, "epoch": 4.603960396039604, "percentage": 23.02, "elapsed_time": "0:35:14", "remaining_time": "1:57:49", "throughput": 4648.53, "total_tokens": 9827136} {"current_steps": 9770, "total_steps": 42420, "loss": 0.1285, "lr": 4.745865692481094e-05, "epoch": 4.606317774634606, "percentage": 23.03, "elapsed_time": "0:35:15", "remaining_time": "1:57:48", "throughput": 4648.54, "total_tokens": 9831872} {"current_steps": 9775, "total_steps": 42420, "loss": 0.1068, "lr": 4.745413650540686e-05, "epoch": 4.608675153229608, "percentage": 23.04, "elapsed_time": "0:35:16", "remaining_time": "1:57:46", "throughput": 4648.53, "total_tokens": 9836704} {"current_steps": 9780, "total_steps": 42420, "loss": 0.1801, "lr": 4.744961228489872e-05, "epoch": 4.611032531824611, "percentage": 23.06, "elapsed_time": "0:35:16", "remaining_time": "1:57:45", "throughput": 4648.55, "total_tokens": 9840928} {"current_steps": 9785, "total_steps": 42420, "loss": 0.2983, "lr": 4.74450842640524e-05, "epoch": 4.613389910419613, "percentage": 23.07, "elapsed_time": "0:35:17", "remaining_time": "1:57:43", "throughput": 4648.56, "total_tokens": 9845312} {"current_steps": 9790, "total_steps": 42420, "loss": 0.2053, "lr": 4.7440552443634404e-05, "epoch": 4.615747289014616, "percentage": 23.08, "elapsed_time": "0:35:18", "remaining_time": "1:57:42", "throughput": 4648.68, "total_tokens": 9850336} {"current_steps": 9795, "total_steps": 42420, "loss": 0.1273, "lr": 4.743601682441189e-05, "epoch": 4.618104667609618, "percentage": 23.09, "elapsed_time": "0:35:19", "remaining_time": "1:57:40", "throughput": 4648.72, "total_tokens": 9854816} {"current_steps": 9800, "total_steps": 42420, "loss": 0.1348, "lr": 4.743147740715268e-05, "epoch": 4.62046204620462, "percentage": 23.1, "elapsed_time": "0:35:20", "remaining_time": "1:57:39", "throughput": 4648.63, "total_tokens": 9858560} {"current_steps": 9805, "total_steps": 42420, "loss": 0.0532, "lr": 4.7426934192625204e-05, "epoch": 4.622819424799623, "percentage": 23.11, "elapsed_time": "0:35:21", "remaining_time": "1:57:38", "throughput": 4648.79, "total_tokens": 9864096} {"current_steps": 9810, "total_steps": 42420, "loss": 0.0276, "lr": 4.742238718159856e-05, "epoch": 4.625176803394625, "percentage": 23.13, "elapsed_time": "0:35:22", "remaining_time": "1:57:36", "throughput": 4648.87, "total_tokens": 9869024} {"current_steps": 9815, "total_steps": 42420, "loss": 0.103, "lr": 4.7417836374842474e-05, "epoch": 4.627534181989628, "percentage": 23.14, "elapsed_time": "0:35:23", "remaining_time": "1:57:35", "throughput": 4649.04, "total_tokens": 9874432} {"current_steps": 9820, "total_steps": 42420, "loss": 0.234, "lr": 4.741328177312733e-05, "epoch": 4.62989156058463, "percentage": 23.15, "elapsed_time": "0:35:24", "remaining_time": "1:57:33", "throughput": 4649.09, "total_tokens": 9878400} {"current_steps": 9825, "total_steps": 42420, "loss": 0.1443, "lr": 4.7408723377224126e-05, "epoch": 4.632248939179632, "percentage": 23.16, "elapsed_time": "0:35:25", "remaining_time": "1:57:33", "throughput": 4649.23, "total_tokens": 9884256} {"current_steps": 9830, "total_steps": 42420, "loss": 0.1771, "lr": 4.7404161187904545e-05, "epoch": 4.634606317774635, "percentage": 23.17, "elapsed_time": "0:35:26", "remaining_time": "1:57:31", "throughput": 4649.36, "total_tokens": 9889184} {"current_steps": 9835, "total_steps": 42420, "loss": 0.345, "lr": 4.7399595205940874e-05, "epoch": 4.636963696369637, "percentage": 23.18, "elapsed_time": "0:35:27", "remaining_time": "1:57:30", "throughput": 4649.4, "total_tokens": 9893472} {"current_steps": 9840, "total_steps": 42420, "loss": 0.1615, "lr": 4.739502543210605e-05, "epoch": 4.63932107496464, "percentage": 23.2, "elapsed_time": "0:35:28", "remaining_time": "1:57:28", "throughput": 4649.42, "total_tokens": 9897472} {"current_steps": 9845, "total_steps": 42420, "loss": 0.1583, "lr": 4.739045186717367e-05, "epoch": 4.641678453559642, "percentage": 23.21, "elapsed_time": "0:35:29", "remaining_time": "1:57:26", "throughput": 4649.41, "total_tokens": 9901568} {"current_steps": 9850, "total_steps": 42420, "loss": 0.1622, "lr": 4.738587451191796e-05, "epoch": 4.644035832154644, "percentage": 23.22, "elapsed_time": "0:35:30", "remaining_time": "1:57:25", "throughput": 4649.54, "total_tokens": 9907584} {"current_steps": 9855, "total_steps": 42420, "loss": 0.3234, "lr": 4.738129336711378e-05, "epoch": 4.646393210749647, "percentage": 23.23, "elapsed_time": "0:35:31", "remaining_time": "1:57:24", "throughput": 4649.6, "total_tokens": 9912160} {"current_steps": 9860, "total_steps": 42420, "loss": 0.2356, "lr": 4.737670843353665e-05, "epoch": 4.648750589344649, "percentage": 23.24, "elapsed_time": "0:35:32", "remaining_time": "1:57:23", "throughput": 4649.63, "total_tokens": 9916800} {"current_steps": 9865, "total_steps": 42420, "loss": 0.0101, "lr": 4.7372119711962714e-05, "epoch": 4.651107967939651, "percentage": 23.26, "elapsed_time": "0:35:33", "remaining_time": "1:57:21", "throughput": 4649.75, "total_tokens": 9922016} {"current_steps": 9870, "total_steps": 42420, "loss": 0.2442, "lr": 4.736752720316877e-05, "epoch": 4.653465346534653, "percentage": 23.27, "elapsed_time": "0:35:34", "remaining_time": "1:57:20", "throughput": 4649.81, "total_tokens": 9926720} {"current_steps": 9875, "total_steps": 42420, "loss": 0.1327, "lr": 4.7362930907932253e-05, "epoch": 4.655822725129656, "percentage": 23.28, "elapsed_time": "0:35:35", "remaining_time": "1:57:18", "throughput": 4649.94, "total_tokens": 9931392} {"current_steps": 9880, "total_steps": 42420, "loss": 0.2585, "lr": 4.7358330827031225e-05, "epoch": 4.658180103724658, "percentage": 23.29, "elapsed_time": "0:35:36", "remaining_time": "1:57:17", "throughput": 4650.08, "total_tokens": 9936576} {"current_steps": 9885, "total_steps": 42420, "loss": 0.2107, "lr": 4.735372696124442e-05, "epoch": 4.66053748231966, "percentage": 23.3, "elapsed_time": "0:35:37", "remaining_time": "1:57:16", "throughput": 4650.2, "total_tokens": 9941824} {"current_steps": 9890, "total_steps": 42420, "loss": 0.1623, "lr": 4.734911931135118e-05, "epoch": 4.662894860914663, "percentage": 23.31, "elapsed_time": "0:35:38", "remaining_time": "1:57:15", "throughput": 4650.24, "total_tokens": 9946688} {"current_steps": 9895, "total_steps": 42420, "loss": 0.1036, "lr": 4.734450787813151e-05, "epoch": 4.665252239509665, "percentage": 23.33, "elapsed_time": "0:35:40", "remaining_time": "1:57:15", "throughput": 4650.45, "total_tokens": 9953984} {"current_steps": 9900, "total_steps": 42420, "loss": 0.1872, "lr": 4.7339892662366045e-05, "epoch": 4.667609618104668, "percentage": 23.34, "elapsed_time": "0:35:41", "remaining_time": "1:57:15", "throughput": 4650.63, "total_tokens": 9960032} {"current_steps": 9905, "total_steps": 42420, "loss": 0.1641, "lr": 4.733527366483605e-05, "epoch": 4.66996699669967, "percentage": 23.35, "elapsed_time": "0:35:42", "remaining_time": "1:57:13", "throughput": 4650.69, "total_tokens": 9964704} {"current_steps": 9910, "total_steps": 42420, "loss": 0.1336, "lr": 4.733065088632347e-05, "epoch": 4.672324375294672, "percentage": 23.36, "elapsed_time": "0:35:43", "remaining_time": "1:57:12", "throughput": 4650.89, "total_tokens": 9970368} {"current_steps": 9915, "total_steps": 42420, "loss": 0.1568, "lr": 4.732602432761085e-05, "epoch": 4.674681753889675, "percentage": 23.37, "elapsed_time": "0:35:44", "remaining_time": "1:57:11", "throughput": 4650.89, "total_tokens": 9974880} {"current_steps": 9920, "total_steps": 42420, "loss": 0.1011, "lr": 4.7321393989481376e-05, "epoch": 4.677039132484677, "percentage": 23.39, "elapsed_time": "0:35:45", "remaining_time": "1:57:09", "throughput": 4651.03, "total_tokens": 9979936} {"current_steps": 9925, "total_steps": 42420, "loss": 0.1624, "lr": 4.73167598727189e-05, "epoch": 4.67939651107968, "percentage": 23.4, "elapsed_time": "0:35:46", "remaining_time": "1:57:09", "throughput": 4651.18, "total_tokens": 9986048} {"current_steps": 9930, "total_steps": 42420, "loss": 0.2243, "lr": 4.7312121978107896e-05, "epoch": 4.681753889674682, "percentage": 23.41, "elapsed_time": "0:35:48", "remaining_time": "1:57:08", "throughput": 4651.29, "total_tokens": 9991072} {"current_steps": 9935, "total_steps": 42420, "loss": 0.0935, "lr": 4.7307480306433473e-05, "epoch": 4.684111268269684, "percentage": 23.42, "elapsed_time": "0:35:49", "remaining_time": "1:57:06", "throughput": 4651.36, "total_tokens": 9995904} {"current_steps": 9940, "total_steps": 42420, "loss": 0.1694, "lr": 4.7302834858481394e-05, "epoch": 4.686468646864687, "percentage": 23.43, "elapsed_time": "0:35:49", "remaining_time": "1:57:05", "throughput": 4651.39, "total_tokens": 10000000} {"current_steps": 9945, "total_steps": 42420, "loss": 0.2033, "lr": 4.7298185635038056e-05, "epoch": 4.688826025459689, "percentage": 23.44, "elapsed_time": "0:35:51", "remaining_time": "1:57:04", "throughput": 4651.4, "total_tokens": 10005248} {"current_steps": 9950, "total_steps": 42420, "loss": 0.2245, "lr": 4.7293532636890495e-05, "epoch": 4.691183404054691, "percentage": 23.46, "elapsed_time": "0:35:52", "remaining_time": "1:57:03", "throughput": 4651.48, "total_tokens": 10010688} {"current_steps": 9955, "total_steps": 42420, "loss": 0.1247, "lr": 4.728887586482638e-05, "epoch": 4.693540782649693, "percentage": 23.47, "elapsed_time": "0:35:53", "remaining_time": "1:57:01", "throughput": 4651.46, "total_tokens": 10015392} {"current_steps": 9960, "total_steps": 42420, "loss": 0.0482, "lr": 4.728421531963402e-05, "epoch": 4.6958981612446955, "percentage": 23.48, "elapsed_time": "0:35:54", "remaining_time": "1:57:00", "throughput": 4651.55, "total_tokens": 10020512} {"current_steps": 9965, "total_steps": 42420, "loss": 0.0635, "lr": 4.7279551002102376e-05, "epoch": 4.698255539839698, "percentage": 23.49, "elapsed_time": "0:35:55", "remaining_time": "1:56:59", "throughput": 4651.58, "total_tokens": 10025344} {"current_steps": 9970, "total_steps": 42420, "loss": 0.097, "lr": 4.727488291302102e-05, "epoch": 4.7006129184347, "percentage": 23.5, "elapsed_time": "0:35:56", "remaining_time": "1:56:59", "throughput": 4651.77, "total_tokens": 10032320} {"current_steps": 9975, "total_steps": 42420, "loss": 0.1363, "lr": 4.727021105318021e-05, "epoch": 4.702970297029703, "percentage": 23.51, "elapsed_time": "0:35:57", "remaining_time": "1:56:58", "throughput": 4651.88, "total_tokens": 10037408} {"current_steps": 9980, "total_steps": 42420, "loss": 0.1572, "lr": 4.726553542337079e-05, "epoch": 4.705327675624705, "percentage": 23.53, "elapsed_time": "0:35:58", "remaining_time": "1:56:56", "throughput": 4651.96, "total_tokens": 10041984} {"current_steps": 9985, "total_steps": 42420, "loss": 0.2597, "lr": 4.726085602438426e-05, "epoch": 4.7076850542197075, "percentage": 23.54, "elapsed_time": "0:35:59", "remaining_time": "1:56:55", "throughput": 4652.11, "total_tokens": 10047296} {"current_steps": 9990, "total_steps": 42420, "loss": 0.1839, "lr": 4.7256172857012784e-05, "epoch": 4.71004243281471, "percentage": 23.55, "elapsed_time": "0:36:00", "remaining_time": "1:56:54", "throughput": 4652.28, "total_tokens": 10052608} {"current_steps": 9995, "total_steps": 42420, "loss": 0.1493, "lr": 4.725148592204913e-05, "epoch": 4.712399811409712, "percentage": 23.56, "elapsed_time": "0:36:02", "remaining_time": "1:56:53", "throughput": 4652.43, "total_tokens": 10058656} {"current_steps": 10000, "total_steps": 42420, "loss": 0.0758, "lr": 4.724679522028672e-05, "epoch": 4.714757190004715, "percentage": 23.57, "elapsed_time": "0:36:02", "remaining_time": "1:56:52", "throughput": 4652.43, "total_tokens": 10063008} {"current_steps": 10005, "total_steps": 42420, "loss": 0.0851, "lr": 4.72421007525196e-05, "epoch": 4.717114568599717, "percentage": 23.59, "elapsed_time": "0:36:03", "remaining_time": "1:56:50", "throughput": 4652.43, "total_tokens": 10067008} {"current_steps": 10010, "total_steps": 42420, "loss": 0.0897, "lr": 4.7237402519542486e-05, "epoch": 4.7194719471947195, "percentage": 23.6, "elapsed_time": "0:36:04", "remaining_time": "1:56:48", "throughput": 4652.41, "total_tokens": 10071360} {"current_steps": 10015, "total_steps": 42420, "loss": 0.0497, "lr": 4.723270052215068e-05, "epoch": 4.721829325789722, "percentage": 23.61, "elapsed_time": "0:36:05", "remaining_time": "1:56:47", "throughput": 4652.41, "total_tokens": 10075840} {"current_steps": 10020, "total_steps": 42420, "loss": 0.1143, "lr": 4.7227994761140174e-05, "epoch": 4.724186704384724, "percentage": 23.62, "elapsed_time": "0:36:06", "remaining_time": "1:56:46", "throughput": 4652.56, "total_tokens": 10081952} {"current_steps": 10025, "total_steps": 42420, "loss": 0.2007, "lr": 4.722328523730756e-05, "epoch": 4.726544082979727, "percentage": 23.63, "elapsed_time": "0:36:07", "remaining_time": "1:56:45", "throughput": 4652.6, "total_tokens": 10086624} {"current_steps": 10030, "total_steps": 42420, "loss": 0.2366, "lr": 4.721857195145008e-05, "epoch": 4.728901461574729, "percentage": 23.64, "elapsed_time": "0:36:08", "remaining_time": "1:56:43", "throughput": 4652.58, "total_tokens": 10090464} {"current_steps": 10035, "total_steps": 42420, "loss": 0.1496, "lr": 4.721385490436563e-05, "epoch": 4.7312588401697315, "percentage": 23.66, "elapsed_time": "0:36:09", "remaining_time": "1:56:42", "throughput": 4652.62, "total_tokens": 10095008} {"current_steps": 10040, "total_steps": 42420, "loss": 0.1297, "lr": 4.7209134096852717e-05, "epoch": 4.733616218764734, "percentage": 23.67, "elapsed_time": "0:36:10", "remaining_time": "1:56:40", "throughput": 4652.71, "total_tokens": 10099712} {"current_steps": 10045, "total_steps": 42420, "loss": 0.4051, "lr": 4.720440952971048e-05, "epoch": 4.735973597359736, "percentage": 23.68, "elapsed_time": "0:36:11", "remaining_time": "1:56:39", "throughput": 4652.75, "total_tokens": 10104544} {"current_steps": 10050, "total_steps": 42420, "loss": 0.1413, "lr": 4.719968120373873e-05, "epoch": 4.738330975954739, "percentage": 23.69, "elapsed_time": "0:36:12", "remaining_time": "1:56:38", "throughput": 4652.84, "total_tokens": 10109472} {"current_steps": 10055, "total_steps": 42420, "loss": 0.0896, "lr": 4.719494911973788e-05, "epoch": 4.740688354549741, "percentage": 23.7, "elapsed_time": "0:36:13", "remaining_time": "1:56:36", "throughput": 4652.93, "total_tokens": 10114400} {"current_steps": 10060, "total_steps": 42420, "loss": 0.333, "lr": 4.719021327850898e-05, "epoch": 4.7430457331447435, "percentage": 23.72, "elapsed_time": "0:36:14", "remaining_time": "1:56:35", "throughput": 4652.95, "total_tokens": 10119008} {"current_steps": 10065, "total_steps": 42420, "loss": 0.1193, "lr": 4.7185473680853753e-05, "epoch": 4.745403111739745, "percentage": 23.73, "elapsed_time": "0:36:15", "remaining_time": "1:56:34", "throughput": 4652.95, "total_tokens": 10123584} {"current_steps": 10070, "total_steps": 42420, "loss": 0.1236, "lr": 4.718073032757451e-05, "epoch": 4.7477604903347475, "percentage": 23.74, "elapsed_time": "0:36:16", "remaining_time": "1:56:32", "throughput": 4653.05, "total_tokens": 10128512} {"current_steps": 10075, "total_steps": 42420, "loss": 0.1472, "lr": 4.717598321947424e-05, "epoch": 4.75011786892975, "percentage": 23.75, "elapsed_time": "0:36:17", "remaining_time": "1:56:31", "throughput": 4653.12, "total_tokens": 10133216} {"current_steps": 10080, "total_steps": 42420, "loss": 0.0712, "lr": 4.7171232357356533e-05, "epoch": 4.752475247524752, "percentage": 23.76, "elapsed_time": "0:36:19", "remaining_time": "1:56:31", "throughput": 4653.23, "total_tokens": 10140288} {"current_steps": 10085, "total_steps": 42420, "loss": 0.1021, "lr": 4.716647774202563e-05, "epoch": 4.754832626119755, "percentage": 23.77, "elapsed_time": "0:36:20", "remaining_time": "1:56:30", "throughput": 4653.36, "total_tokens": 10145632} {"current_steps": 10090, "total_steps": 42420, "loss": 0.3678, "lr": 4.7161719374286415e-05, "epoch": 4.757190004714757, "percentage": 23.79, "elapsed_time": "0:36:21", "remaining_time": "1:56:29", "throughput": 4653.45, "total_tokens": 10150720} {"current_steps": 10095, "total_steps": 42420, "loss": 0.1873, "lr": 4.7156957254944386e-05, "epoch": 4.7595473833097595, "percentage": 23.8, "elapsed_time": "0:36:22", "remaining_time": "1:56:27", "throughput": 4653.43, "total_tokens": 10155264} {"current_steps": 10100, "total_steps": 42420, "loss": 0.0628, "lr": 4.7152191384805714e-05, "epoch": 4.761904761904762, "percentage": 23.81, "elapsed_time": "0:36:23", "remaining_time": "1:56:26", "throughput": 4653.49, "total_tokens": 10159744} {"current_steps": 10105, "total_steps": 42420, "loss": 0.0705, "lr": 4.714742176467715e-05, "epoch": 4.764262140499764, "percentage": 23.82, "elapsed_time": "0:36:24", "remaining_time": "1:56:24", "throughput": 4653.53, "total_tokens": 10164256} {"current_steps": 10110, "total_steps": 42420, "loss": 0.1826, "lr": 4.714264839536613e-05, "epoch": 4.766619519094767, "percentage": 23.83, "elapsed_time": "0:36:25", "remaining_time": "1:56:23", "throughput": 4653.63, "total_tokens": 10169088} {"current_steps": 10115, "total_steps": 42420, "loss": 0.0479, "lr": 4.713787127768069e-05, "epoch": 4.768976897689769, "percentage": 23.84, "elapsed_time": "0:36:26", "remaining_time": "1:56:22", "throughput": 4653.71, "total_tokens": 10175008} {"current_steps": 10120, "total_steps": 42420, "loss": 0.083, "lr": 4.7133090412429534e-05, "epoch": 4.7713342762847715, "percentage": 23.86, "elapsed_time": "0:36:27", "remaining_time": "1:56:21", "throughput": 4653.84, "total_tokens": 10180032} {"current_steps": 10125, "total_steps": 42420, "loss": 0.3275, "lr": 4.7128305800421965e-05, "epoch": 4.773691654879774, "percentage": 23.87, "elapsed_time": "0:36:28", "remaining_time": "1:56:20", "throughput": 4654.01, "total_tokens": 10185600} {"current_steps": 10130, "total_steps": 42420, "loss": 0.1933, "lr": 4.712351744246794e-05, "epoch": 4.776049033474776, "percentage": 23.88, "elapsed_time": "0:36:29", "remaining_time": "1:56:19", "throughput": 4654.18, "total_tokens": 10191296} {"current_steps": 10135, "total_steps": 42420, "loss": 0.1252, "lr": 4.711872533937804e-05, "epoch": 4.778406412069779, "percentage": 23.89, "elapsed_time": "0:36:30", "remaining_time": "1:56:18", "throughput": 4654.26, "total_tokens": 10196512} {"current_steps": 10140, "total_steps": 42420, "loss": 0.2143, "lr": 4.711392949196351e-05, "epoch": 4.780763790664781, "percentage": 23.9, "elapsed_time": "0:36:31", "remaining_time": "1:56:17", "throughput": 4654.36, "total_tokens": 10201888} {"current_steps": 10145, "total_steps": 42420, "loss": 0.0635, "lr": 4.7109129901036175e-05, "epoch": 4.7831211692597835, "percentage": 23.92, "elapsed_time": "0:36:33", "remaining_time": "1:56:16", "throughput": 4654.51, "total_tokens": 10207552} {"current_steps": 10150, "total_steps": 42420, "loss": 0.0897, "lr": 4.7104326567408554e-05, "epoch": 4.785478547854785, "percentage": 23.93, "elapsed_time": "0:36:34", "remaining_time": "1:56:16", "throughput": 4654.68, "total_tokens": 10213664} {"current_steps": 10155, "total_steps": 42420, "loss": 0.1762, "lr": 4.709951949189374e-05, "epoch": 4.787835926449787, "percentage": 23.94, "elapsed_time": "0:36:35", "remaining_time": "1:56:15", "throughput": 4654.81, "total_tokens": 10219360} {"current_steps": 10160, "total_steps": 42420, "loss": 0.1059, "lr": 4.709470867530552e-05, "epoch": 4.79019330504479, "percentage": 23.95, "elapsed_time": "0:36:36", "remaining_time": "1:56:14", "throughput": 4654.92, "total_tokens": 10224768} {"current_steps": 10165, "total_steps": 42420, "loss": 0.3333, "lr": 4.708989411845826e-05, "epoch": 4.792550683639792, "percentage": 23.96, "elapsed_time": "0:36:37", "remaining_time": "1:56:13", "throughput": 4655.07, "total_tokens": 10230208} {"current_steps": 10170, "total_steps": 42420, "loss": 0.2072, "lr": 4.708507582216699e-05, "epoch": 4.794908062234795, "percentage": 23.97, "elapsed_time": "0:36:38", "remaining_time": "1:56:12", "throughput": 4655.03, "total_tokens": 10235424} {"current_steps": 10175, "total_steps": 42420, "loss": 0.3984, "lr": 4.7080253787247365e-05, "epoch": 4.797265440829797, "percentage": 23.99, "elapsed_time": "0:36:39", "remaining_time": "1:56:10", "throughput": 4655.03, "total_tokens": 10239488} {"current_steps": 10180, "total_steps": 42420, "loss": 0.111, "lr": 4.7075428014515675e-05, "epoch": 4.799622819424799, "percentage": 24.0, "elapsed_time": "0:36:40", "remaining_time": "1:56:09", "throughput": 4655.02, "total_tokens": 10244608} {"current_steps": 10185, "total_steps": 42420, "loss": 0.1154, "lr": 4.707059850478884e-05, "epoch": 4.801980198019802, "percentage": 24.01, "elapsed_time": "0:36:41", "remaining_time": "1:56:08", "throughput": 4655.18, "total_tokens": 10250240} {"current_steps": 10190, "total_steps": 42420, "loss": 0.0638, "lr": 4.706576525888442e-05, "epoch": 4.804337576614804, "percentage": 24.02, "elapsed_time": "0:36:42", "remaining_time": "1:56:07", "throughput": 4655.24, "total_tokens": 10254784} {"current_steps": 10195, "total_steps": 42420, "loss": 0.124, "lr": 4.7060928277620604e-05, "epoch": 4.806694955209807, "percentage": 24.03, "elapsed_time": "0:36:43", "remaining_time": "1:56:06", "throughput": 4655.4, "total_tokens": 10260448} {"current_steps": 10200, "total_steps": 42420, "loss": 0.1046, "lr": 4.70560875618162e-05, "epoch": 4.809052333804809, "percentage": 24.05, "elapsed_time": "0:36:44", "remaining_time": "1:56:04", "throughput": 4655.35, "total_tokens": 10264352} {"current_steps": 10205, "total_steps": 42420, "loss": 0.2752, "lr": 4.7051243112290655e-05, "epoch": 4.811409712399811, "percentage": 24.06, "elapsed_time": "0:36:45", "remaining_time": "1:56:03", "throughput": 4655.47, "total_tokens": 10269952} {"current_steps": 10210, "total_steps": 42420, "loss": 0.2275, "lr": 4.704639492986407e-05, "epoch": 4.813767090994814, "percentage": 24.07, "elapsed_time": "0:36:47", "remaining_time": "1:56:02", "throughput": 4655.57, "total_tokens": 10275040} {"current_steps": 10215, "total_steps": 42420, "loss": 0.131, "lr": 4.704154301535714e-05, "epoch": 4.816124469589816, "percentage": 24.08, "elapsed_time": "0:36:48", "remaining_time": "1:56:01", "throughput": 4655.67, "total_tokens": 10280032} {"current_steps": 10220, "total_steps": 42420, "loss": 0.0805, "lr": 4.7036687369591226e-05, "epoch": 4.818481848184819, "percentage": 24.09, "elapsed_time": "0:36:49", "remaining_time": "1:56:00", "throughput": 4655.76, "total_tokens": 10285152} {"current_steps": 10225, "total_steps": 42420, "loss": 0.2058, "lr": 4.70318279933883e-05, "epoch": 4.820839226779821, "percentage": 24.1, "elapsed_time": "0:36:50", "remaining_time": "1:55:58", "throughput": 4655.86, "total_tokens": 10290144} {"current_steps": 10230, "total_steps": 42420, "loss": 0.2629, "lr": 4.702696488757098e-05, "epoch": 4.823196605374823, "percentage": 24.12, "elapsed_time": "0:36:51", "remaining_time": "1:55:58", "throughput": 4656.04, "total_tokens": 10295872} {"current_steps": 10235, "total_steps": 42420, "loss": 0.0803, "lr": 4.7022098052962496e-05, "epoch": 4.825553983969826, "percentage": 24.13, "elapsed_time": "0:36:52", "remaining_time": "1:55:56", "throughput": 4656.09, "total_tokens": 10300768} {"current_steps": 10240, "total_steps": 42420, "loss": 0.1172, "lr": 4.701722749038673e-05, "epoch": 4.827911362564828, "percentage": 24.14, "elapsed_time": "0:36:53", "remaining_time": "1:55:55", "throughput": 4656.2, "total_tokens": 10306080} {"current_steps": 10245, "total_steps": 42420, "loss": 0.0926, "lr": 4.701235320066817e-05, "epoch": 4.830268741159831, "percentage": 24.15, "elapsed_time": "0:36:54", "remaining_time": "1:55:54", "throughput": 4656.34, "total_tokens": 10311552} {"current_steps": 10250, "total_steps": 42420, "loss": 0.2586, "lr": 4.700747518463197e-05, "epoch": 4.832626119754833, "percentage": 24.16, "elapsed_time": "0:36:55", "remaining_time": "1:55:53", "throughput": 4656.45, "total_tokens": 10316736} {"current_steps": 10255, "total_steps": 42420, "loss": 0.0689, "lr": 4.7002593443103884e-05, "epoch": 4.834983498349835, "percentage": 24.17, "elapsed_time": "0:36:56", "remaining_time": "1:55:51", "throughput": 4656.49, "total_tokens": 10320960} {"current_steps": 10260, "total_steps": 42420, "loss": 0.1818, "lr": 4.6997707976910316e-05, "epoch": 4.837340876944838, "percentage": 24.19, "elapsed_time": "0:36:57", "remaining_time": "1:55:51", "throughput": 4656.58, "total_tokens": 10326336} {"current_steps": 10265, "total_steps": 42420, "loss": 0.1608, "lr": 4.6992818786878284e-05, "epoch": 4.839698255539839, "percentage": 24.2, "elapsed_time": "0:36:58", "remaining_time": "1:55:49", "throughput": 4656.64, "total_tokens": 10331136} {"current_steps": 10270, "total_steps": 42420, "loss": 0.1454, "lr": 4.698792587383545e-05, "epoch": 4.842055634134842, "percentage": 24.21, "elapsed_time": "0:36:59", "remaining_time": "1:55:48", "throughput": 4656.69, "total_tokens": 10336416} {"current_steps": 10275, "total_steps": 42420, "loss": 0.1745, "lr": 4.6983029238610096e-05, "epoch": 4.844413012729844, "percentage": 24.22, "elapsed_time": "0:37:00", "remaining_time": "1:55:47", "throughput": 4656.75, "total_tokens": 10340928} {"current_steps": 10280, "total_steps": 42420, "loss": 0.1067, "lr": 4.697812888203115e-05, "epoch": 4.8467703913248465, "percentage": 24.23, "elapsed_time": "0:37:01", "remaining_time": "1:55:45", "throughput": 4656.89, "total_tokens": 10346080} {"current_steps": 10285, "total_steps": 42420, "loss": 0.0567, "lr": 4.697322480492814e-05, "epoch": 4.849127769919849, "percentage": 24.25, "elapsed_time": "0:37:02", "remaining_time": "1:55:44", "throughput": 4656.89, "total_tokens": 10350080} {"current_steps": 10290, "total_steps": 42420, "loss": 0.1459, "lr": 4.696831700813126e-05, "epoch": 4.851485148514851, "percentage": 24.26, "elapsed_time": "0:37:03", "remaining_time": "1:55:43", "throughput": 4656.85, "total_tokens": 10354880} {"current_steps": 10295, "total_steps": 42420, "loss": 0.1394, "lr": 4.696340549247131e-05, "epoch": 4.853842527109854, "percentage": 24.27, "elapsed_time": "0:37:04", "remaining_time": "1:55:41", "throughput": 4656.84, "total_tokens": 10359200} {"current_steps": 10300, "total_steps": 42420, "loss": 0.0654, "lr": 4.695849025877973e-05, "epoch": 4.856199905704856, "percentage": 24.28, "elapsed_time": "0:37:05", "remaining_time": "1:55:40", "throughput": 4656.94, "total_tokens": 10364032} {"current_steps": 10305, "total_steps": 42420, "loss": 0.1741, "lr": 4.6953571307888587e-05, "epoch": 4.858557284299859, "percentage": 24.29, "elapsed_time": "0:37:06", "remaining_time": "1:55:39", "throughput": 4657.1, "total_tokens": 10369792} {"current_steps": 10310, "total_steps": 42420, "loss": 0.1229, "lr": 4.6948648640630565e-05, "epoch": 4.860914662894861, "percentage": 24.3, "elapsed_time": "0:37:07", "remaining_time": "1:55:38", "throughput": 4657.24, "total_tokens": 10375264} {"current_steps": 10315, "total_steps": 42420, "loss": 0.1079, "lr": 4.6943722257839e-05, "epoch": 4.863272041489863, "percentage": 24.32, "elapsed_time": "0:37:08", "remaining_time": "1:55:36", "throughput": 4657.26, "total_tokens": 10379712} {"current_steps": 10320, "total_steps": 42420, "loss": 0.3622, "lr": 4.693879216034784e-05, "epoch": 4.865629420084866, "percentage": 24.33, "elapsed_time": "0:37:09", "remaining_time": "1:55:35", "throughput": 4657.35, "total_tokens": 10385024} {"current_steps": 10325, "total_steps": 42420, "loss": 0.1201, "lr": 4.693385834899167e-05, "epoch": 4.867986798679868, "percentage": 24.34, "elapsed_time": "0:37:10", "remaining_time": "1:55:34", "throughput": 4657.38, "total_tokens": 10390272} {"current_steps": 10330, "total_steps": 42420, "loss": 0.1402, "lr": 4.692892082460568e-05, "epoch": 4.870344177274871, "percentage": 24.35, "elapsed_time": "0:37:11", "remaining_time": "1:55:33", "throughput": 4657.35, "total_tokens": 10394368} {"current_steps": 10335, "total_steps": 42420, "loss": 0.2697, "lr": 4.692397958802574e-05, "epoch": 4.872701555869873, "percentage": 24.36, "elapsed_time": "0:37:13", "remaining_time": "1:55:32", "throughput": 4657.51, "total_tokens": 10401056} {"current_steps": 10340, "total_steps": 42420, "loss": 0.1029, "lr": 4.69190346400883e-05, "epoch": 4.875058934464875, "percentage": 24.38, "elapsed_time": "0:37:14", "remaining_time": "1:55:31", "throughput": 4657.54, "total_tokens": 10405408} {"current_steps": 10345, "total_steps": 42420, "loss": 0.1353, "lr": 4.6914085981630465e-05, "epoch": 4.877416313059878, "percentage": 24.39, "elapsed_time": "0:37:15", "remaining_time": "1:55:29", "throughput": 4657.64, "total_tokens": 10410208} {"current_steps": 10350, "total_steps": 42420, "loss": 0.1782, "lr": 4.690913361348995e-05, "epoch": 4.879773691654879, "percentage": 24.4, "elapsed_time": "0:37:16", "remaining_time": "1:55:29", "throughput": 4657.79, "total_tokens": 10416000} {"current_steps": 10355, "total_steps": 42420, "loss": 0.1033, "lr": 4.6904177536505107e-05, "epoch": 4.882131070249882, "percentage": 24.41, "elapsed_time": "0:37:17", "remaining_time": "1:55:27", "throughput": 4657.91, "total_tokens": 10421120} {"current_steps": 10360, "total_steps": 42420, "loss": 0.1222, "lr": 4.6899217751514925e-05, "epoch": 4.884488448844884, "percentage": 24.42, "elapsed_time": "0:37:18", "remaining_time": "1:55:26", "throughput": 4657.91, "total_tokens": 10425376} {"current_steps": 10365, "total_steps": 42420, "loss": 0.0888, "lr": 4.689425425935899e-05, "epoch": 4.8868458274398865, "percentage": 24.43, "elapsed_time": "0:37:19", "remaining_time": "1:55:25", "throughput": 4658.1, "total_tokens": 10431392} {"current_steps": 10370, "total_steps": 42420, "loss": 0.1618, "lr": 4.6889287060877575e-05, "epoch": 4.889203206034889, "percentage": 24.45, "elapsed_time": "0:37:20", "remaining_time": "1:55:24", "throughput": 4658.1, "total_tokens": 10435968} {"current_steps": 10375, "total_steps": 42420, "loss": 0.0736, "lr": 4.68843161569115e-05, "epoch": 4.891560584629891, "percentage": 24.46, "elapsed_time": "0:37:21", "remaining_time": "1:55:22", "throughput": 4658.04, "total_tokens": 10440544} {"current_steps": 10380, "total_steps": 42420, "loss": 0.0975, "lr": 4.687934154830229e-05, "epoch": 4.893917963224894, "percentage": 24.47, "elapsed_time": "0:37:22", "remaining_time": "1:55:21", "throughput": 4658.09, "total_tokens": 10445408} {"current_steps": 10385, "total_steps": 42420, "loss": 0.121, "lr": 4.687436323589204e-05, "epoch": 4.896275341819896, "percentage": 24.48, "elapsed_time": "0:37:23", "remaining_time": "1:55:20", "throughput": 4658.15, "total_tokens": 10449888} {"current_steps": 10390, "total_steps": 42420, "loss": 0.1, "lr": 4.686938122052349e-05, "epoch": 4.8986327204148985, "percentage": 24.49, "elapsed_time": "0:37:24", "remaining_time": "1:55:19", "throughput": 4658.29, "total_tokens": 10455840} {"current_steps": 10395, "total_steps": 42420, "loss": 0.1872, "lr": 4.686439550304003e-05, "epoch": 4.900990099009901, "percentage": 24.5, "elapsed_time": "0:37:25", "remaining_time": "1:55:18", "throughput": 4658.41, "total_tokens": 10461280} {"current_steps": 10400, "total_steps": 42420, "loss": 0.0696, "lr": 4.685940608428565e-05, "epoch": 4.903347477604903, "percentage": 24.52, "elapsed_time": "0:37:26", "remaining_time": "1:55:17", "throughput": 4658.56, "total_tokens": 10467136} {"current_steps": 10405, "total_steps": 42420, "loss": 0.1428, "lr": 4.6854412965104965e-05, "epoch": 4.905704856199906, "percentage": 24.53, "elapsed_time": "0:37:28", "remaining_time": "1:55:16", "throughput": 4658.61, "total_tokens": 10472736} {"current_steps": 10410, "total_steps": 42420, "loss": 0.1502, "lr": 4.684941614634324e-05, "epoch": 4.908062234794908, "percentage": 24.54, "elapsed_time": "0:37:29", "remaining_time": "1:55:15", "throughput": 4658.74, "total_tokens": 10478112} {"current_steps": 10415, "total_steps": 42420, "loss": 0.034, "lr": 4.6844415628846336e-05, "epoch": 4.9104196133899105, "percentage": 24.55, "elapsed_time": "0:37:30", "remaining_time": "1:55:14", "throughput": 4658.87, "total_tokens": 10483456} {"current_steps": 10420, "total_steps": 42420, "loss": 0.2239, "lr": 4.6839411413460764e-05, "epoch": 4.912776991984913, "percentage": 24.56, "elapsed_time": "0:37:31", "remaining_time": "1:55:13", "throughput": 4658.98, "total_tokens": 10488704} {"current_steps": 10425, "total_steps": 42420, "loss": 0.2243, "lr": 4.683440350103365e-05, "epoch": 4.915134370579915, "percentage": 24.58, "elapsed_time": "0:37:32", "remaining_time": "1:55:12", "throughput": 4658.95, "total_tokens": 10492960} {"current_steps": 10430, "total_steps": 42420, "loss": 0.2653, "lr": 4.6829391892412756e-05, "epoch": 4.917491749174918, "percentage": 24.59, "elapsed_time": "0:37:33", "remaining_time": "1:55:11", "throughput": 4659.0, "total_tokens": 10498592} {"current_steps": 10435, "total_steps": 42420, "loss": 0.1943, "lr": 4.682437658844645e-05, "epoch": 4.91984912776992, "percentage": 24.6, "elapsed_time": "0:37:34", "remaining_time": "1:55:09", "throughput": 4659.08, "total_tokens": 10503232} {"current_steps": 10440, "total_steps": 42420, "loss": 0.2076, "lr": 4.681935758998375e-05, "epoch": 4.9222065063649225, "percentage": 24.61, "elapsed_time": "0:37:35", "remaining_time": "1:55:08", "throughput": 4659.2, "total_tokens": 10508448} {"current_steps": 10445, "total_steps": 42420, "loss": 0.12, "lr": 4.681433489787428e-05, "epoch": 4.924563884959925, "percentage": 24.62, "elapsed_time": "0:37:36", "remaining_time": "1:55:07", "throughput": 4659.23, "total_tokens": 10513184} {"current_steps": 10450, "total_steps": 42420, "loss": 0.1323, "lr": 4.68093085129683e-05, "epoch": 4.926921263554927, "percentage": 24.63, "elapsed_time": "0:37:37", "remaining_time": "1:55:06", "throughput": 4659.27, "total_tokens": 10518208} {"current_steps": 10455, "total_steps": 42420, "loss": 0.0836, "lr": 4.680427843611668e-05, "epoch": 4.92927864214993, "percentage": 24.65, "elapsed_time": "0:37:38", "remaining_time": "1:55:04", "throughput": 4659.33, "total_tokens": 10522912} {"current_steps": 10460, "total_steps": 42420, "loss": 0.1288, "lr": 4.679924466817095e-05, "epoch": 4.931636020744932, "percentage": 24.66, "elapsed_time": "0:37:39", "remaining_time": "1:55:03", "throughput": 4659.34, "total_tokens": 10527200} {"current_steps": 10465, "total_steps": 42420, "loss": 0.1696, "lr": 4.679420720998322e-05, "epoch": 4.933993399339934, "percentage": 24.67, "elapsed_time": "0:37:40", "remaining_time": "1:55:02", "throughput": 4659.44, "total_tokens": 10532448} {"current_steps": 10470, "total_steps": 42420, "loss": 0.2527, "lr": 4.678916606240625e-05, "epoch": 4.936350777934936, "percentage": 24.68, "elapsed_time": "0:37:41", "remaining_time": "1:55:01", "throughput": 4659.56, "total_tokens": 10537536} {"current_steps": 10475, "total_steps": 42420, "loss": 0.1203, "lr": 4.678412122629343e-05, "epoch": 4.938708156529938, "percentage": 24.69, "elapsed_time": "0:37:42", "remaining_time": "1:54:59", "throughput": 4659.68, "total_tokens": 10542784} {"current_steps": 10480, "total_steps": 42420, "loss": 0.1433, "lr": 4.677907270249876e-05, "epoch": 4.941065535124941, "percentage": 24.71, "elapsed_time": "0:37:43", "remaining_time": "1:54:58", "throughput": 4659.82, "total_tokens": 10547616} {"current_steps": 10485, "total_steps": 42420, "loss": 0.2529, "lr": 4.677402049187687e-05, "epoch": 4.943422913719943, "percentage": 24.72, "elapsed_time": "0:37:44", "remaining_time": "1:54:58", "throughput": 4659.99, "total_tokens": 10553952} {"current_steps": 10490, "total_steps": 42420, "loss": 0.2194, "lr": 4.676896459528301e-05, "epoch": 4.945780292314946, "percentage": 24.73, "elapsed_time": "0:37:46", "remaining_time": "1:54:57", "throughput": 4660.19, "total_tokens": 10560160} {"current_steps": 10495, "total_steps": 42420, "loss": 0.0489, "lr": 4.676390501357306e-05, "epoch": 4.948137670909948, "percentage": 24.74, "elapsed_time": "0:37:47", "remaining_time": "1:54:56", "throughput": 4660.33, "total_tokens": 10565760} {"current_steps": 10500, "total_steps": 42420, "loss": 0.0616, "lr": 4.675884174760353e-05, "epoch": 4.9504950495049505, "percentage": 24.75, "elapsed_time": "0:37:48", "remaining_time": "1:54:56", "throughput": 4660.46, "total_tokens": 10572256} {"current_steps": 10505, "total_steps": 42420, "loss": 0.1627, "lr": 4.675377479823153e-05, "epoch": 4.952852428099953, "percentage": 24.76, "elapsed_time": "0:37:49", "remaining_time": "1:54:54", "throughput": 4660.5, "total_tokens": 10576544} {"current_steps": 10510, "total_steps": 42420, "loss": 0.1544, "lr": 4.674870416631481e-05, "epoch": 4.955209806694955, "percentage": 24.78, "elapsed_time": "0:37:50", "remaining_time": "1:54:53", "throughput": 4660.63, "total_tokens": 10581632} {"current_steps": 10515, "total_steps": 42420, "loss": 0.1515, "lr": 4.674362985271175e-05, "epoch": 4.957567185289958, "percentage": 24.79, "elapsed_time": "0:37:51", "remaining_time": "1:54:51", "throughput": 4660.71, "total_tokens": 10586240} {"current_steps": 10520, "total_steps": 42420, "loss": 0.0892, "lr": 4.673855185828134e-05, "epoch": 4.95992456388496, "percentage": 24.8, "elapsed_time": "0:37:52", "remaining_time": "1:54:51", "throughput": 4660.85, "total_tokens": 10592000} {"current_steps": 10525, "total_steps": 42420, "loss": 0.0876, "lr": 4.67334701838832e-05, "epoch": 4.9622819424799625, "percentage": 24.81, "elapsed_time": "0:37:53", "remaining_time": "1:54:49", "throughput": 4660.94, "total_tokens": 10597056} {"current_steps": 10530, "total_steps": 42420, "loss": 0.2353, "lr": 4.6728384830377584e-05, "epoch": 4.964639321074965, "percentage": 24.82, "elapsed_time": "0:37:54", "remaining_time": "1:54:48", "throughput": 4660.92, "total_tokens": 10601568} {"current_steps": 10535, "total_steps": 42420, "loss": 0.0303, "lr": 4.6723295798625326e-05, "epoch": 4.966996699669967, "percentage": 24.83, "elapsed_time": "0:37:55", "remaining_time": "1:54:47", "throughput": 4661.03, "total_tokens": 10606880} {"current_steps": 10540, "total_steps": 42420, "loss": 0.1345, "lr": 4.671820308948793e-05, "epoch": 4.96935407826497, "percentage": 24.85, "elapsed_time": "0:37:56", "remaining_time": "1:54:45", "throughput": 4661.07, "total_tokens": 10611392} {"current_steps": 10545, "total_steps": 42420, "loss": 0.1678, "lr": 4.6713106703827514e-05, "epoch": 4.971711456859972, "percentage": 24.86, "elapsed_time": "0:37:57", "remaining_time": "1:54:44", "throughput": 4661.11, "total_tokens": 10615968} {"current_steps": 10550, "total_steps": 42420, "loss": 0.12, "lr": 4.6708006642506804e-05, "epoch": 4.974068835454974, "percentage": 24.87, "elapsed_time": "0:37:58", "remaining_time": "1:54:43", "throughput": 4661.22, "total_tokens": 10621120} {"current_steps": 10555, "total_steps": 42420, "loss": 0.2389, "lr": 4.670290290638915e-05, "epoch": 4.976426214049976, "percentage": 24.88, "elapsed_time": "0:37:59", "remaining_time": "1:54:41", "throughput": 4661.24, "total_tokens": 10625504} {"current_steps": 10560, "total_steps": 42420, "loss": 0.1237, "lr": 4.669779549633852e-05, "epoch": 4.978783592644978, "percentage": 24.89, "elapsed_time": "0:38:00", "remaining_time": "1:54:40", "throughput": 4661.37, "total_tokens": 10630560} {"current_steps": 10565, "total_steps": 42420, "loss": 0.1282, "lr": 4.669268441321952e-05, "epoch": 4.981140971239981, "percentage": 24.91, "elapsed_time": "0:38:01", "remaining_time": "1:54:39", "throughput": 4661.51, "total_tokens": 10635872} {"current_steps": 10570, "total_steps": 42420, "loss": 0.2436, "lr": 4.6687569657897367e-05, "epoch": 4.983498349834983, "percentage": 24.92, "elapsed_time": "0:38:02", "remaining_time": "1:54:38", "throughput": 4661.61, "total_tokens": 10641184} {"current_steps": 10575, "total_steps": 42420, "loss": 0.1477, "lr": 4.668245123123791e-05, "epoch": 4.985855728429986, "percentage": 24.93, "elapsed_time": "0:38:03", "remaining_time": "1:54:37", "throughput": 4661.69, "total_tokens": 10646304} {"current_steps": 10580, "total_steps": 42420, "loss": 0.1703, "lr": 4.66773291341076e-05, "epoch": 4.988213107024988, "percentage": 24.94, "elapsed_time": "0:38:04", "remaining_time": "1:54:35", "throughput": 4661.74, "total_tokens": 10651072} {"current_steps": 10585, "total_steps": 42420, "loss": 0.1773, "lr": 4.667220336737354e-05, "epoch": 4.99057048561999, "percentage": 24.95, "elapsed_time": "0:38:05", "remaining_time": "1:54:35", "throughput": 4661.89, "total_tokens": 10656864} {"current_steps": 10590, "total_steps": 42420, "loss": 0.2384, "lr": 4.666707393190342e-05, "epoch": 4.992927864214993, "percentage": 24.96, "elapsed_time": "0:38:07", "remaining_time": "1:54:34", "throughput": 4662.0, "total_tokens": 10662112} {"current_steps": 10595, "total_steps": 42420, "loss": 0.1186, "lr": 4.6661940828565566e-05, "epoch": 4.995285242809995, "percentage": 24.98, "elapsed_time": "0:38:07", "remaining_time": "1:54:32", "throughput": 4662.06, "total_tokens": 10666560} {"current_steps": 10600, "total_steps": 42420, "loss": 0.088, "lr": 4.665680405822893e-05, "epoch": 4.997642621404998, "percentage": 24.99, "elapsed_time": "0:38:09", "remaining_time": "1:54:31", "throughput": 4662.22, "total_tokens": 10672032} {"current_steps": 10605, "total_steps": 42420, "loss": 0.1825, "lr": 4.6651663621763076e-05, "epoch": 5.0, "percentage": 25.0, "elapsed_time": "0:38:10", "remaining_time": "1:54:30", "throughput": 4662.07, "total_tokens": 10677088} {"current_steps": 10605, "total_steps": 42420, "eval_loss": 0.15683941543102264, "epoch": 5.0, "percentage": 25.0, "elapsed_time": "0:38:25", "remaining_time": "1:55:16", "throughput": 4631.43, "total_tokens": 10677088} {"current_steps": 10610, "total_steps": 42420, "loss": 0.0611, "lr": 4.66465195200382e-05, "epoch": 5.002357378595002, "percentage": 25.01, "elapsed_time": "0:38:28", "remaining_time": "1:55:19", "throughput": 4628.26, "total_tokens": 10682528} {"current_steps": 10615, "total_steps": 42420, "loss": 0.1325, "lr": 4.66413717539251e-05, "epoch": 5.004714757190005, "percentage": 25.02, "elapsed_time": "0:38:29", "remaining_time": "1:55:18", "throughput": 4628.36, "total_tokens": 10687872} {"current_steps": 10620, "total_steps": 42420, "loss": 0.3281, "lr": 4.6636220324295224e-05, "epoch": 5.007072135785007, "percentage": 25.04, "elapsed_time": "0:38:30", "remaining_time": "1:55:17", "throughput": 4628.31, "total_tokens": 10692224} {"current_steps": 10625, "total_steps": 42420, "loss": 0.1207, "lr": 4.663106523202059e-05, "epoch": 5.00942951438001, "percentage": 25.05, "elapsed_time": "0:38:31", "remaining_time": "1:55:16", "throughput": 4628.33, "total_tokens": 10697248} {"current_steps": 10630, "total_steps": 42420, "loss": 0.3474, "lr": 4.66259064779739e-05, "epoch": 5.011786892975012, "percentage": 25.06, "elapsed_time": "0:38:32", "remaining_time": "1:55:15", "throughput": 4628.48, "total_tokens": 10702496} {"current_steps": 10635, "total_steps": 42420, "loss": 0.1178, "lr": 4.662074406302843e-05, "epoch": 5.014144271570014, "percentage": 25.07, "elapsed_time": "0:38:33", "remaining_time": "1:55:13", "throughput": 4628.37, "total_tokens": 10706272} {"current_steps": 10640, "total_steps": 42420, "loss": 0.1943, "lr": 4.6615577988058083e-05, "epoch": 5.016501650165017, "percentage": 25.08, "elapsed_time": "0:38:34", "remaining_time": "1:55:11", "throughput": 4628.36, "total_tokens": 10710528} {"current_steps": 10645, "total_steps": 42420, "loss": 0.0978, "lr": 4.66104082539374e-05, "epoch": 5.018859028760019, "percentage": 25.09, "elapsed_time": "0:38:35", "remaining_time": "1:55:10", "throughput": 4628.45, "total_tokens": 10715488} {"current_steps": 10650, "total_steps": 42420, "loss": 0.0623, "lr": 4.660523486154152e-05, "epoch": 5.021216407355022, "percentage": 25.11, "elapsed_time": "0:38:36", "remaining_time": "1:55:09", "throughput": 4628.57, "total_tokens": 10720576} {"current_steps": 10655, "total_steps": 42420, "loss": 0.1521, "lr": 4.6600057811746216e-05, "epoch": 5.023573785950024, "percentage": 25.12, "elapsed_time": "0:38:37", "remaining_time": "1:55:08", "throughput": 4628.7, "total_tokens": 10726304} {"current_steps": 10660, "total_steps": 42420, "loss": 0.0508, "lr": 4.659487710542787e-05, "epoch": 5.0259311645450255, "percentage": 25.13, "elapsed_time": "0:38:38", "remaining_time": "1:55:07", "throughput": 4628.9, "total_tokens": 10732576} {"current_steps": 10665, "total_steps": 42420, "loss": 0.2284, "lr": 4.6589692743463495e-05, "epoch": 5.028288543140028, "percentage": 25.14, "elapsed_time": "0:38:39", "remaining_time": "1:55:06", "throughput": 4629.03, "total_tokens": 10737632} {"current_steps": 10670, "total_steps": 42420, "loss": 0.1342, "lr": 4.6584504726730706e-05, "epoch": 5.03064592173503, "percentage": 25.15, "elapsed_time": "0:38:40", "remaining_time": "1:55:05", "throughput": 4629.05, "total_tokens": 10741856} {"current_steps": 10675, "total_steps": 42420, "loss": 0.1037, "lr": 4.657931305610775e-05, "epoch": 5.033003300330033, "percentage": 25.17, "elapsed_time": "0:38:41", "remaining_time": "1:55:03", "throughput": 4628.98, "total_tokens": 10746208} {"current_steps": 10680, "total_steps": 42420, "loss": 0.3268, "lr": 4.65741177324735e-05, "epoch": 5.035360678925035, "percentage": 25.18, "elapsed_time": "0:38:42", "remaining_time": "1:55:02", "throughput": 4629.04, "total_tokens": 10750944} {"current_steps": 10685, "total_steps": 42420, "loss": 0.2841, "lr": 4.656891875670742e-05, "epoch": 5.0377180575200375, "percentage": 25.19, "elapsed_time": "0:38:43", "remaining_time": "1:55:00", "throughput": 4629.02, "total_tokens": 10755200} {"current_steps": 10690, "total_steps": 42420, "loss": 0.096, "lr": 4.656371612968961e-05, "epoch": 5.04007543611504, "percentage": 25.2, "elapsed_time": "0:38:44", "remaining_time": "1:54:59", "throughput": 4629.04, "total_tokens": 10759392} {"current_steps": 10695, "total_steps": 42420, "loss": 0.1225, "lr": 4.6558509852300784e-05, "epoch": 5.042432814710042, "percentage": 25.21, "elapsed_time": "0:38:45", "remaining_time": "1:54:58", "throughput": 4629.18, "total_tokens": 10765216} {"current_steps": 10700, "total_steps": 42420, "loss": 0.209, "lr": 4.6553299925422287e-05, "epoch": 5.044790193305045, "percentage": 25.22, "elapsed_time": "0:38:46", "remaining_time": "1:54:57", "throughput": 4629.33, "total_tokens": 10771104} {"current_steps": 10705, "total_steps": 42420, "loss": 0.1287, "lr": 4.6548086349936074e-05, "epoch": 5.047147571900047, "percentage": 25.24, "elapsed_time": "0:38:47", "remaining_time": "1:54:56", "throughput": 4629.43, "total_tokens": 10776064} {"current_steps": 10710, "total_steps": 42420, "loss": 0.0927, "lr": 4.654286912672471e-05, "epoch": 5.0495049504950495, "percentage": 25.25, "elapsed_time": "0:38:48", "remaining_time": "1:54:55", "throughput": 4629.45, "total_tokens": 10780960} {"current_steps": 10715, "total_steps": 42420, "loss": 0.1146, "lr": 4.653764825667137e-05, "epoch": 5.051862329090052, "percentage": 25.26, "elapsed_time": "0:38:49", "remaining_time": "1:54:53", "throughput": 4629.5, "total_tokens": 10785760} {"current_steps": 10720, "total_steps": 42420, "loss": 0.2415, "lr": 4.653242374065987e-05, "epoch": 5.054219707685054, "percentage": 25.27, "elapsed_time": "0:38:50", "remaining_time": "1:54:52", "throughput": 4629.55, "total_tokens": 10790400} {"current_steps": 10725, "total_steps": 42420, "loss": 0.1523, "lr": 4.6527195579574634e-05, "epoch": 5.056577086280057, "percentage": 25.28, "elapsed_time": "0:38:51", "remaining_time": "1:54:50", "throughput": 4629.6, "total_tokens": 10795200} {"current_steps": 10730, "total_steps": 42420, "loss": 0.1656, "lr": 4.65219637743007e-05, "epoch": 5.058934464875059, "percentage": 25.29, "elapsed_time": "0:38:52", "remaining_time": "1:54:49", "throughput": 4629.61, "total_tokens": 10800000} {"current_steps": 10735, "total_steps": 42420, "loss": 0.1258, "lr": 4.651672832572371e-05, "epoch": 5.061291843470062, "percentage": 25.31, "elapsed_time": "0:38:53", "remaining_time": "1:54:47", "throughput": 4629.62, "total_tokens": 10804000} {"current_steps": 10740, "total_steps": 42420, "loss": 0.1235, "lr": 4.651148923472995e-05, "epoch": 5.063649222065064, "percentage": 25.32, "elapsed_time": "0:38:54", "remaining_time": "1:54:46", "throughput": 4629.66, "total_tokens": 10808896} {"current_steps": 10745, "total_steps": 42420, "loss": 0.1118, "lr": 4.650624650220632e-05, "epoch": 5.066006600660066, "percentage": 25.33, "elapsed_time": "0:38:55", "remaining_time": "1:54:45", "throughput": 4629.73, "total_tokens": 10813664} {"current_steps": 10750, "total_steps": 42420, "loss": 0.055, "lr": 4.650100012904031e-05, "epoch": 5.068363979255069, "percentage": 25.34, "elapsed_time": "0:38:56", "remaining_time": "1:54:44", "throughput": 4629.88, "total_tokens": 10819264} {"current_steps": 10755, "total_steps": 42420, "loss": 0.0912, "lr": 4.649575011612004e-05, "epoch": 5.07072135785007, "percentage": 25.35, "elapsed_time": "0:38:57", "remaining_time": "1:54:43", "throughput": 4629.99, "total_tokens": 10824064} {"current_steps": 10760, "total_steps": 42420, "loss": 0.1165, "lr": 4.6490496464334247e-05, "epoch": 5.073078736445073, "percentage": 25.37, "elapsed_time": "0:38:58", "remaining_time": "1:54:41", "throughput": 4630.12, "total_tokens": 10829216} {"current_steps": 10765, "total_steps": 42420, "loss": 0.2117, "lr": 4.648523917457229e-05, "epoch": 5.075436115040075, "percentage": 25.38, "elapsed_time": "0:39:00", "remaining_time": "1:54:41", "throughput": 4630.29, "total_tokens": 10835264} {"current_steps": 10770, "total_steps": 42420, "loss": 0.0862, "lr": 4.6479978247724145e-05, "epoch": 5.0777934936350775, "percentage": 25.39, "elapsed_time": "0:39:01", "remaining_time": "1:54:39", "throughput": 4630.41, "total_tokens": 10840384} {"current_steps": 10775, "total_steps": 42420, "loss": 0.124, "lr": 4.6474713684680394e-05, "epoch": 5.08015087223008, "percentage": 25.4, "elapsed_time": "0:39:02", "remaining_time": "1:54:38", "throughput": 4630.49, "total_tokens": 10845632} {"current_steps": 10780, "total_steps": 42420, "loss": 0.2148, "lr": 4.646944548633223e-05, "epoch": 5.082508250825082, "percentage": 25.41, "elapsed_time": "0:39:03", "remaining_time": "1:54:37", "throughput": 4630.54, "total_tokens": 10850560} {"current_steps": 10785, "total_steps": 42420, "loss": 0.114, "lr": 4.646417365357148e-05, "epoch": 5.084865629420085, "percentage": 25.42, "elapsed_time": "0:39:04", "remaining_time": "1:54:36", "throughput": 4630.63, "total_tokens": 10855360} {"current_steps": 10790, "total_steps": 42420, "loss": 0.1399, "lr": 4.645889818729057e-05, "epoch": 5.087223008015087, "percentage": 25.44, "elapsed_time": "0:39:05", "remaining_time": "1:54:36", "throughput": 4630.84, "total_tokens": 10862336} {"current_steps": 10795, "total_steps": 42420, "loss": 0.1558, "lr": 4.645361908838255e-05, "epoch": 5.0895803866100895, "percentage": 25.45, "elapsed_time": "0:39:06", "remaining_time": "1:54:34", "throughput": 4630.95, "total_tokens": 10867264} {"current_steps": 10800, "total_steps": 42420, "loss": 0.1549, "lr": 4.644833635774107e-05, "epoch": 5.091937765205092, "percentage": 25.46, "elapsed_time": "0:39:07", "remaining_time": "1:54:33", "throughput": 4631.03, "total_tokens": 10872384} {"current_steps": 10805, "total_steps": 42420, "loss": 0.0768, "lr": 4.644304999626044e-05, "epoch": 5.094295143800094, "percentage": 25.47, "elapsed_time": "0:39:08", "remaining_time": "1:54:32", "throughput": 4631.19, "total_tokens": 10877760} {"current_steps": 10810, "total_steps": 42420, "loss": 0.0818, "lr": 4.643776000483551e-05, "epoch": 5.096652522395097, "percentage": 25.48, "elapsed_time": "0:39:09", "remaining_time": "1:54:31", "throughput": 4631.26, "total_tokens": 10882816} {"current_steps": 10815, "total_steps": 42420, "loss": 0.0421, "lr": 4.64324663843618e-05, "epoch": 5.099009900990099, "percentage": 25.5, "elapsed_time": "0:39:10", "remaining_time": "1:54:29", "throughput": 4631.31, "total_tokens": 10887488} {"current_steps": 10820, "total_steps": 42420, "loss": 0.0946, "lr": 4.642716913573544e-05, "epoch": 5.1013672795851015, "percentage": 25.51, "elapsed_time": "0:39:11", "remaining_time": "1:54:28", "throughput": 4631.37, "total_tokens": 10892096} {"current_steps": 10825, "total_steps": 42420, "loss": 0.1942, "lr": 4.6421868259853156e-05, "epoch": 5.103724658180104, "percentage": 25.52, "elapsed_time": "0:39:12", "remaining_time": "1:54:27", "throughput": 4631.53, "total_tokens": 10897952} {"current_steps": 10830, "total_steps": 42420, "loss": 0.1521, "lr": 4.64165637576123e-05, "epoch": 5.106082036775106, "percentage": 25.53, "elapsed_time": "0:39:14", "remaining_time": "1:54:26", "throughput": 4631.65, "total_tokens": 10903264} {"current_steps": 10835, "total_steps": 42420, "loss": 0.1201, "lr": 4.6411255629910835e-05, "epoch": 5.108439415370109, "percentage": 25.54, "elapsed_time": "0:39:15", "remaining_time": "1:54:25", "throughput": 4631.79, "total_tokens": 10908704} {"current_steps": 10840, "total_steps": 42420, "loss": 0.1751, "lr": 4.640594387764733e-05, "epoch": 5.110796793965111, "percentage": 25.55, "elapsed_time": "0:39:16", "remaining_time": "1:54:23", "throughput": 4631.82, "total_tokens": 10912928} {"current_steps": 10845, "total_steps": 42420, "loss": 0.0582, "lr": 4.640062850172098e-05, "epoch": 5.1131541725601135, "percentage": 25.57, "elapsed_time": "0:39:17", "remaining_time": "1:54:22", "throughput": 4631.97, "total_tokens": 10918560} {"current_steps": 10850, "total_steps": 42420, "loss": 0.1819, "lr": 4.6395309503031594e-05, "epoch": 5.115511551155116, "percentage": 25.58, "elapsed_time": "0:39:18", "remaining_time": "1:54:21", "throughput": 4632.0, "total_tokens": 10922656} {"current_steps": 10855, "total_steps": 42420, "loss": 0.056, "lr": 4.638998688247957e-05, "epoch": 5.117868929750118, "percentage": 25.59, "elapsed_time": "0:39:19", "remaining_time": "1:54:19", "throughput": 4632.08, "total_tokens": 10927232} {"current_steps": 10860, "total_steps": 42420, "loss": 0.2517, "lr": 4.6384660640965946e-05, "epoch": 5.12022630834512, "percentage": 25.6, "elapsed_time": "0:39:20", "remaining_time": "1:54:18", "throughput": 4632.14, "total_tokens": 10932832} {"current_steps": 10865, "total_steps": 42420, "loss": 0.1627, "lr": 4.637933077939238e-05, "epoch": 5.122583686940122, "percentage": 25.61, "elapsed_time": "0:39:21", "remaining_time": "1:54:17", "throughput": 4632.24, "total_tokens": 10937888} {"current_steps": 10870, "total_steps": 42420, "loss": 0.1153, "lr": 4.6373997298661105e-05, "epoch": 5.124941065535125, "percentage": 25.62, "elapsed_time": "0:39:22", "remaining_time": "1:54:16", "throughput": 4632.34, "total_tokens": 10942720} {"current_steps": 10875, "total_steps": 42420, "loss": 0.1888, "lr": 4.636866019967499e-05, "epoch": 5.127298444130127, "percentage": 25.64, "elapsed_time": "0:39:23", "remaining_time": "1:54:15", "throughput": 4632.47, "total_tokens": 10948288} {"current_steps": 10880, "total_steps": 42420, "loss": 0.1346, "lr": 4.6363319483337534e-05, "epoch": 5.129655822725129, "percentage": 25.65, "elapsed_time": "0:39:24", "remaining_time": "1:54:14", "throughput": 4632.51, "total_tokens": 10953152} {"current_steps": 10885, "total_steps": 42420, "loss": 0.1022, "lr": 4.635797515055282e-05, "epoch": 5.132013201320132, "percentage": 25.66, "elapsed_time": "0:39:25", "remaining_time": "1:54:13", "throughput": 4632.59, "total_tokens": 10958368} {"current_steps": 10890, "total_steps": 42420, "loss": 0.25, "lr": 4.635262720222554e-05, "epoch": 5.134370579915134, "percentage": 25.67, "elapsed_time": "0:39:26", "remaining_time": "1:54:12", "throughput": 4632.73, "total_tokens": 10963968} {"current_steps": 10895, "total_steps": 42420, "loss": 0.167, "lr": 4.634727563926103e-05, "epoch": 5.136727958510137, "percentage": 25.68, "elapsed_time": "0:39:27", "remaining_time": "1:54:10", "throughput": 4632.76, "total_tokens": 10968288} {"current_steps": 10900, "total_steps": 42420, "loss": 0.1596, "lr": 4.6341920462565206e-05, "epoch": 5.139085337105139, "percentage": 25.7, "elapsed_time": "0:39:28", "remaining_time": "1:54:09", "throughput": 4632.9, "total_tokens": 10973888} {"current_steps": 10905, "total_steps": 42420, "loss": 0.0548, "lr": 4.6336561673044614e-05, "epoch": 5.141442715700141, "percentage": 25.71, "elapsed_time": "0:39:30", "remaining_time": "1:54:09", "throughput": 4633.09, "total_tokens": 10981184} {"current_steps": 10910, "total_steps": 42420, "loss": 0.1813, "lr": 4.6331199271606405e-05, "epoch": 5.143800094295144, "percentage": 25.72, "elapsed_time": "0:39:31", "remaining_time": "1:54:08", "throughput": 4633.22, "total_tokens": 10986304} {"current_steps": 10915, "total_steps": 42420, "loss": 0.0719, "lr": 4.632583325915835e-05, "epoch": 5.146157472890146, "percentage": 25.73, "elapsed_time": "0:39:32", "remaining_time": "1:54:08", "throughput": 4633.4, "total_tokens": 10993312} {"current_steps": 10920, "total_steps": 42420, "loss": 0.1945, "lr": 4.6320463636608804e-05, "epoch": 5.148514851485149, "percentage": 25.74, "elapsed_time": "0:39:33", "remaining_time": "1:54:06", "throughput": 4633.36, "total_tokens": 10997120} {"current_steps": 10925, "total_steps": 42420, "loss": 0.0781, "lr": 4.6315090404866766e-05, "epoch": 5.150872230080151, "percentage": 25.75, "elapsed_time": "0:39:34", "remaining_time": "1:54:05", "throughput": 4633.44, "total_tokens": 11002592} {"current_steps": 10930, "total_steps": 42420, "loss": 0.2359, "lr": 4.630971356484184e-05, "epoch": 5.1532296086751535, "percentage": 25.77, "elapsed_time": "0:39:35", "remaining_time": "1:54:04", "throughput": 4633.53, "total_tokens": 11007040} {"current_steps": 10935, "total_steps": 42420, "loss": 0.2308, "lr": 4.630433311744422e-05, "epoch": 5.155586987270156, "percentage": 25.78, "elapsed_time": "0:39:36", "remaining_time": "1:54:02", "throughput": 4633.57, "total_tokens": 11011776} {"current_steps": 10940, "total_steps": 42420, "loss": 0.153, "lr": 4.6298949063584736e-05, "epoch": 5.157944365865158, "percentage": 25.79, "elapsed_time": "0:39:37", "remaining_time": "1:54:01", "throughput": 4633.56, "total_tokens": 11015840} {"current_steps": 10945, "total_steps": 42420, "loss": 0.1128, "lr": 4.62935614041748e-05, "epoch": 5.160301744460161, "percentage": 25.8, "elapsed_time": "0:39:38", "remaining_time": "1:53:59", "throughput": 4633.66, "total_tokens": 11021088} {"current_steps": 10950, "total_steps": 42420, "loss": 0.1626, "lr": 4.6288170140126476e-05, "epoch": 5.162659123055163, "percentage": 25.81, "elapsed_time": "0:39:39", "remaining_time": "1:53:58", "throughput": 4633.75, "total_tokens": 11026208} {"current_steps": 10955, "total_steps": 42420, "loss": 0.0525, "lr": 4.6282775272352394e-05, "epoch": 5.165016501650165, "percentage": 25.83, "elapsed_time": "0:39:40", "remaining_time": "1:53:57", "throughput": 4633.84, "total_tokens": 11031104} {"current_steps": 10960, "total_steps": 42420, "loss": 0.0547, "lr": 4.627737680176581e-05, "epoch": 5.167373880245167, "percentage": 25.84, "elapsed_time": "0:39:41", "remaining_time": "1:53:56", "throughput": 4633.95, "total_tokens": 11036032} {"current_steps": 10965, "total_steps": 42420, "loss": 0.0304, "lr": 4.627197472928062e-05, "epoch": 5.169731258840169, "percentage": 25.85, "elapsed_time": "0:39:42", "remaining_time": "1:53:54", "throughput": 4634.01, "total_tokens": 11040544} {"current_steps": 10970, "total_steps": 42420, "loss": 0.2707, "lr": 4.6266569055811276e-05, "epoch": 5.172088637435172, "percentage": 25.86, "elapsed_time": "0:39:43", "remaining_time": "1:53:53", "throughput": 4634.16, "total_tokens": 11046592} {"current_steps": 10975, "total_steps": 42420, "loss": 0.0948, "lr": 4.626115978227288e-05, "epoch": 5.174446016030174, "percentage": 25.87, "elapsed_time": "0:39:44", "remaining_time": "1:53:52", "throughput": 4634.2, "total_tokens": 11051424} {"current_steps": 10980, "total_steps": 42420, "loss": 0.121, "lr": 4.6255746909581124e-05, "epoch": 5.176803394625177, "percentage": 25.88, "elapsed_time": "0:39:45", "remaining_time": "1:53:51", "throughput": 4634.27, "total_tokens": 11056992} {"current_steps": 10985, "total_steps": 42420, "loss": 0.1895, "lr": 4.625033043865232e-05, "epoch": 5.179160773220179, "percentage": 25.9, "elapsed_time": "0:39:47", "remaining_time": "1:53:51", "throughput": 4634.44, "total_tokens": 11063520} {"current_steps": 10990, "total_steps": 42420, "loss": 0.242, "lr": 4.6244910370403383e-05, "epoch": 5.181518151815181, "percentage": 25.91, "elapsed_time": "0:39:48", "remaining_time": "1:53:50", "throughput": 4634.46, "total_tokens": 11068256} {"current_steps": 10995, "total_steps": 42420, "loss": 0.1875, "lr": 4.6239486705751834e-05, "epoch": 5.183875530410184, "percentage": 25.92, "elapsed_time": "0:39:49", "remaining_time": "1:53:49", "throughput": 4634.54, "total_tokens": 11074048} {"current_steps": 11000, "total_steps": 42420, "loss": 0.1498, "lr": 4.6234059445615813e-05, "epoch": 5.186232909005186, "percentage": 25.93, "elapsed_time": "0:39:50", "remaining_time": "1:53:47", "throughput": 4634.59, "total_tokens": 11078560} {"current_steps": 11005, "total_steps": 42420, "loss": 0.0478, "lr": 4.622862859091407e-05, "epoch": 5.188590287600189, "percentage": 25.94, "elapsed_time": "0:39:51", "remaining_time": "1:53:46", "throughput": 4634.67, "total_tokens": 11083488} {"current_steps": 11010, "total_steps": 42420, "loss": 0.0917, "lr": 4.6223194142565937e-05, "epoch": 5.190947666195191, "percentage": 25.95, "elapsed_time": "0:39:52", "remaining_time": "1:53:45", "throughput": 4634.72, "total_tokens": 11087872} {"current_steps": 11015, "total_steps": 42420, "loss": 0.0801, "lr": 4.6217756101491396e-05, "epoch": 5.193305044790193, "percentage": 25.97, "elapsed_time": "0:39:53", "remaining_time": "1:53:44", "throughput": 4634.87, "total_tokens": 11094144} {"current_steps": 11020, "total_steps": 42420, "loss": 0.137, "lr": 4.621231446861099e-05, "epoch": 5.195662423385196, "percentage": 25.98, "elapsed_time": "0:39:54", "remaining_time": "1:53:43", "throughput": 4634.94, "total_tokens": 11098976} {"current_steps": 11025, "total_steps": 42420, "loss": 0.1522, "lr": 4.620686924484592e-05, "epoch": 5.198019801980198, "percentage": 25.99, "elapsed_time": "0:39:55", "remaining_time": "1:53:42", "throughput": 4635.09, "total_tokens": 11104960} {"current_steps": 11030, "total_steps": 42420, "loss": 0.2599, "lr": 4.620142043111795e-05, "epoch": 5.200377180575201, "percentage": 26.0, "elapsed_time": "0:39:56", "remaining_time": "1:53:41", "throughput": 4635.21, "total_tokens": 11110048} {"current_steps": 11035, "total_steps": 42420, "loss": 0.2245, "lr": 4.619596802834949e-05, "epoch": 5.202734559170203, "percentage": 26.01, "elapsed_time": "0:39:58", "remaining_time": "1:53:40", "throughput": 4635.35, "total_tokens": 11115712} {"current_steps": 11040, "total_steps": 42420, "loss": 0.2114, "lr": 4.619051203746353e-05, "epoch": 5.205091937765205, "percentage": 26.03, "elapsed_time": "0:39:59", "remaining_time": "1:53:39", "throughput": 4635.44, "total_tokens": 11121344} {"current_steps": 11045, "total_steps": 42420, "loss": 0.0873, "lr": 4.618505245938367e-05, "epoch": 5.207449316360208, "percentage": 26.04, "elapsed_time": "0:40:00", "remaining_time": "1:53:38", "throughput": 4635.54, "total_tokens": 11127232} {"current_steps": 11050, "total_steps": 42420, "loss": 0.2123, "lr": 4.617958929503413e-05, "epoch": 5.20980669495521, "percentage": 26.05, "elapsed_time": "0:40:01", "remaining_time": "1:53:37", "throughput": 4635.66, "total_tokens": 11132832} {"current_steps": 11055, "total_steps": 42420, "loss": 0.2119, "lr": 4.6174122545339736e-05, "epoch": 5.212164073550213, "percentage": 26.06, "elapsed_time": "0:40:02", "remaining_time": "1:53:37", "throughput": 4635.8, "total_tokens": 11138752} {"current_steps": 11060, "total_steps": 42420, "loss": 0.1534, "lr": 4.616865221122591e-05, "epoch": 5.214521452145214, "percentage": 26.07, "elapsed_time": "0:40:03", "remaining_time": "1:53:35", "throughput": 4635.92, "total_tokens": 11143904} {"current_steps": 11065, "total_steps": 42420, "loss": 0.0826, "lr": 4.616317829361869e-05, "epoch": 5.2168788307402165, "percentage": 26.08, "elapsed_time": "0:40:04", "remaining_time": "1:53:34", "throughput": 4635.99, "total_tokens": 11148960} {"current_steps": 11070, "total_steps": 42420, "loss": 0.0768, "lr": 4.615770079344472e-05, "epoch": 5.219236209335219, "percentage": 26.1, "elapsed_time": "0:40:06", "remaining_time": "1:53:34", "throughput": 4636.06, "total_tokens": 11154816} {"current_steps": 11075, "total_steps": 42420, "loss": 0.1898, "lr": 4.615221971163123e-05, "epoch": 5.221593587930221, "percentage": 26.11, "elapsed_time": "0:40:07", "remaining_time": "1:53:32", "throughput": 4636.07, "total_tokens": 11159072} {"current_steps": 11080, "total_steps": 42420, "loss": 0.0478, "lr": 4.614673504910609e-05, "epoch": 5.223950966525224, "percentage": 26.12, "elapsed_time": "0:40:07", "remaining_time": "1:53:30", "throughput": 4635.89, "total_tokens": 11162880} {"current_steps": 11085, "total_steps": 42420, "loss": 0.0942, "lr": 4.6141246806797754e-05, "epoch": 5.226308345120226, "percentage": 26.13, "elapsed_time": "0:40:08", "remaining_time": "1:53:29", "throughput": 4635.79, "total_tokens": 11167264} {"current_steps": 11090, "total_steps": 42420, "loss": 0.0648, "lr": 4.613575498563531e-05, "epoch": 5.2286657237152285, "percentage": 26.14, "elapsed_time": "0:40:09", "remaining_time": "1:53:27", "throughput": 4635.85, "total_tokens": 11171616} {"current_steps": 11095, "total_steps": 42420, "loss": 0.1444, "lr": 4.613025958654839e-05, "epoch": 5.231023102310231, "percentage": 26.16, "elapsed_time": "0:40:10", "remaining_time": "1:53:26", "throughput": 4635.94, "total_tokens": 11176992} {"current_steps": 11100, "total_steps": 42420, "loss": 0.0926, "lr": 4.6124760610467304e-05, "epoch": 5.233380480905233, "percentage": 26.17, "elapsed_time": "0:40:11", "remaining_time": "1:53:25", "throughput": 4635.92, "total_tokens": 11181248} {"current_steps": 11105, "total_steps": 42420, "loss": 0.2565, "lr": 4.6119258058322924e-05, "epoch": 5.235737859500236, "percentage": 26.18, "elapsed_time": "0:40:13", "remaining_time": "1:53:24", "throughput": 4636.06, "total_tokens": 11187232} {"current_steps": 11110, "total_steps": 42420, "loss": 0.067, "lr": 4.611375193104674e-05, "epoch": 5.238095238095238, "percentage": 26.19, "elapsed_time": "0:40:14", "remaining_time": "1:53:23", "throughput": 4636.18, "total_tokens": 11193024} {"current_steps": 11115, "total_steps": 42420, "loss": 0.095, "lr": 4.610824222957084e-05, "epoch": 5.2404526166902405, "percentage": 26.2, "elapsed_time": "0:40:15", "remaining_time": "1:53:22", "throughput": 4636.33, "total_tokens": 11198432} {"current_steps": 11120, "total_steps": 42420, "loss": 0.1786, "lr": 4.610272895482794e-05, "epoch": 5.242809995285243, "percentage": 26.21, "elapsed_time": "0:40:16", "remaining_time": "1:53:21", "throughput": 4636.39, "total_tokens": 11202976} {"current_steps": 11125, "total_steps": 42420, "loss": 0.0897, "lr": 4.609721210775132e-05, "epoch": 5.245167373880245, "percentage": 26.23, "elapsed_time": "0:40:17", "remaining_time": "1:53:19", "throughput": 4636.45, "total_tokens": 11207488} {"current_steps": 11130, "total_steps": 42420, "loss": 0.1996, "lr": 4.609169168927491e-05, "epoch": 5.247524752475248, "percentage": 26.24, "elapsed_time": "0:40:18", "remaining_time": "1:53:18", "throughput": 4636.62, "total_tokens": 11213344} {"current_steps": 11135, "total_steps": 42420, "loss": 0.1571, "lr": 4.60861677003332e-05, "epoch": 5.24988213107025, "percentage": 26.25, "elapsed_time": "0:40:19", "remaining_time": "1:53:17", "throughput": 4636.48, "total_tokens": 11217024} {"current_steps": 11140, "total_steps": 42420, "loss": 0.0638, "lr": 4.608064014186133e-05, "epoch": 5.2522395096652525, "percentage": 26.26, "elapsed_time": "0:40:20", "remaining_time": "1:53:16", "throughput": 4636.63, "total_tokens": 11223008} {"current_steps": 11145, "total_steps": 42420, "loss": 0.0549, "lr": 4.6075109014795016e-05, "epoch": 5.254596888260255, "percentage": 26.27, "elapsed_time": "0:40:21", "remaining_time": "1:53:15", "throughput": 4636.73, "total_tokens": 11227712} {"current_steps": 11150, "total_steps": 42420, "loss": 0.0561, "lr": 4.6069574320070575e-05, "epoch": 5.256954266855257, "percentage": 26.28, "elapsed_time": "0:40:22", "remaining_time": "1:53:14", "throughput": 4636.88, "total_tokens": 11233536} {"current_steps": 11155, "total_steps": 42420, "loss": 0.289, "lr": 4.6064036058624936e-05, "epoch": 5.259311645450259, "percentage": 26.3, "elapsed_time": "0:40:23", "remaining_time": "1:53:13", "throughput": 4636.98, "total_tokens": 11239680} {"current_steps": 11160, "total_steps": 42420, "loss": 0.1295, "lr": 4.6058494231395655e-05, "epoch": 5.261669024045261, "percentage": 26.31, "elapsed_time": "0:40:24", "remaining_time": "1:53:12", "throughput": 4637.07, "total_tokens": 11244544} {"current_steps": 11165, "total_steps": 42420, "loss": 0.3552, "lr": 4.605294883932084e-05, "epoch": 5.264026402640264, "percentage": 26.32, "elapsed_time": "0:40:25", "remaining_time": "1:53:10", "throughput": 4637.15, "total_tokens": 11249120} {"current_steps": 11170, "total_steps": 42420, "loss": 0.2479, "lr": 4.604739988333925e-05, "epoch": 5.266383781235266, "percentage": 26.33, "elapsed_time": "0:40:27", "remaining_time": "1:53:10", "throughput": 4637.28, "total_tokens": 11254976} {"current_steps": 11175, "total_steps": 42420, "loss": 0.2479, "lr": 4.604184736439023e-05, "epoch": 5.2687411598302685, "percentage": 26.34, "elapsed_time": "0:40:27", "remaining_time": "1:53:08", "throughput": 4637.17, "total_tokens": 11258816} {"current_steps": 11180, "total_steps": 42420, "loss": 0.2055, "lr": 4.6036291283413714e-05, "epoch": 5.271098538425271, "percentage": 26.36, "elapsed_time": "0:40:28", "remaining_time": "1:53:07", "throughput": 4637.19, "total_tokens": 11263520} {"current_steps": 11185, "total_steps": 42420, "loss": 0.2362, "lr": 4.6030731641350265e-05, "epoch": 5.273455917020273, "percentage": 26.37, "elapsed_time": "0:40:29", "remaining_time": "1:53:05", "throughput": 4637.28, "total_tokens": 11268512} {"current_steps": 11190, "total_steps": 42420, "loss": 0.1905, "lr": 4.602516843914103e-05, "epoch": 5.275813295615276, "percentage": 26.38, "elapsed_time": "0:40:30", "remaining_time": "1:53:04", "throughput": 4637.26, "total_tokens": 11272960} {"current_steps": 11195, "total_steps": 42420, "loss": 0.0226, "lr": 4.601960167772776e-05, "epoch": 5.278170674210278, "percentage": 26.39, "elapsed_time": "0:40:31", "remaining_time": "1:53:02", "throughput": 4637.17, "total_tokens": 11276992} {"current_steps": 11200, "total_steps": 42420, "loss": 0.2681, "lr": 4.601403135805282e-05, "epoch": 5.2805280528052805, "percentage": 26.4, "elapsed_time": "0:40:32", "remaining_time": "1:53:01", "throughput": 4637.24, "total_tokens": 11281568} {"current_steps": 11205, "total_steps": 42420, "loss": 0.0947, "lr": 4.6008457481059177e-05, "epoch": 5.282885431400283, "percentage": 26.41, "elapsed_time": "0:40:33", "remaining_time": "1:52:59", "throughput": 4637.28, "total_tokens": 11285952} {"current_steps": 11210, "total_steps": 42420, "loss": 0.1465, "lr": 4.600288004769038e-05, "epoch": 5.285242809995285, "percentage": 26.43, "elapsed_time": "0:40:34", "remaining_time": "1:52:59", "throughput": 4637.4, "total_tokens": 11291552} {"current_steps": 11215, "total_steps": 42420, "loss": 0.065, "lr": 4.5997299058890594e-05, "epoch": 5.287600188590288, "percentage": 26.44, "elapsed_time": "0:40:35", "remaining_time": "1:52:57", "throughput": 4637.49, "total_tokens": 11296576} {"current_steps": 11220, "total_steps": 42420, "loss": 0.0951, "lr": 4.59917145156046e-05, "epoch": 5.28995756718529, "percentage": 26.45, "elapsed_time": "0:40:37", "remaining_time": "1:52:56", "throughput": 4637.6, "total_tokens": 11302240} {"current_steps": 11225, "total_steps": 42420, "loss": 0.136, "lr": 4.598612641877775e-05, "epoch": 5.2923149457802925, "percentage": 26.46, "elapsed_time": "0:40:38", "remaining_time": "1:52:55", "throughput": 4637.72, "total_tokens": 11307232} {"current_steps": 11230, "total_steps": 42420, "loss": 0.1246, "lr": 4.5980534769356026e-05, "epoch": 5.294672324375295, "percentage": 26.47, "elapsed_time": "0:40:39", "remaining_time": "1:52:54", "throughput": 4637.8, "total_tokens": 11312160} {"current_steps": 11235, "total_steps": 42420, "loss": 0.1154, "lr": 4.5974939568286e-05, "epoch": 5.297029702970297, "percentage": 26.49, "elapsed_time": "0:40:40", "remaining_time": "1:52:53", "throughput": 4637.81, "total_tokens": 11316960} {"current_steps": 11240, "total_steps": 42420, "loss": 0.1382, "lr": 4.596934081651483e-05, "epoch": 5.2993870815653, "percentage": 26.5, "elapsed_time": "0:40:41", "remaining_time": "1:52:52", "throughput": 4637.9, "total_tokens": 11323232} {"current_steps": 11245, "total_steps": 42420, "loss": 0.1139, "lr": 4.59637385149903e-05, "epoch": 5.301744460160302, "percentage": 26.51, "elapsed_time": "0:40:42", "remaining_time": "1:52:51", "throughput": 4637.9, "total_tokens": 11327520} {"current_steps": 11250, "total_steps": 42420, "loss": 0.0561, "lr": 4.595813266466079e-05, "epoch": 5.3041018387553045, "percentage": 26.52, "elapsed_time": "0:40:43", "remaining_time": "1:52:50", "throughput": 4638.04, "total_tokens": 11333536} {"current_steps": 11255, "total_steps": 42420, "loss": 0.0417, "lr": 4.5952523266475265e-05, "epoch": 5.306459217350307, "percentage": 26.53, "elapsed_time": "0:40:44", "remaining_time": "1:52:49", "throughput": 4638.23, "total_tokens": 11339072} {"current_steps": 11260, "total_steps": 42420, "loss": 0.1459, "lr": 4.5946910321383294e-05, "epoch": 5.308816595945308, "percentage": 26.54, "elapsed_time": "0:40:45", "remaining_time": "1:52:47", "throughput": 4638.25, "total_tokens": 11343520} {"current_steps": 11265, "total_steps": 42420, "loss": 0.1259, "lr": 4.594129383033508e-05, "epoch": 5.311173974540311, "percentage": 26.56, "elapsed_time": "0:40:46", "remaining_time": "1:52:46", "throughput": 4638.2, "total_tokens": 11348000} {"current_steps": 11270, "total_steps": 42420, "loss": 0.1222, "lr": 4.5935673794281376e-05, "epoch": 5.313531353135313, "percentage": 26.57, "elapsed_time": "0:40:47", "remaining_time": "1:52:45", "throughput": 4638.29, "total_tokens": 11352928} {"current_steps": 11275, "total_steps": 42420, "loss": 0.07, "lr": 4.593005021417357e-05, "epoch": 5.315888731730316, "percentage": 26.58, "elapsed_time": "0:40:48", "remaining_time": "1:52:44", "throughput": 4638.4, "total_tokens": 11358528} {"current_steps": 11280, "total_steps": 42420, "loss": 0.321, "lr": 4.5924423090963634e-05, "epoch": 5.318246110325318, "percentage": 26.59, "elapsed_time": "0:40:49", "remaining_time": "1:52:42", "throughput": 4638.34, "total_tokens": 11362496} {"current_steps": 11285, "total_steps": 42420, "loss": 0.1844, "lr": 4.591879242560414e-05, "epoch": 5.32060348892032, "percentage": 26.6, "elapsed_time": "0:40:50", "remaining_time": "1:52:40", "throughput": 4638.35, "total_tokens": 11366304} {"current_steps": 11290, "total_steps": 42420, "loss": 0.1584, "lr": 4.591315821904827e-05, "epoch": 5.322960867515323, "percentage": 26.61, "elapsed_time": "0:40:51", "remaining_time": "1:52:39", "throughput": 4638.39, "total_tokens": 11370848} {"current_steps": 11295, "total_steps": 42420, "loss": 0.1583, "lr": 4.5907520472249805e-05, "epoch": 5.325318246110325, "percentage": 26.63, "elapsed_time": "0:40:52", "remaining_time": "1:52:38", "throughput": 4638.48, "total_tokens": 11375584} {"current_steps": 11300, "total_steps": 42420, "loss": 0.0927, "lr": 4.590187918616311e-05, "epoch": 5.327675624705328, "percentage": 26.64, "elapsed_time": "0:40:53", "remaining_time": "1:52:36", "throughput": 4638.6, "total_tokens": 11380768} {"current_steps": 11305, "total_steps": 42420, "loss": 0.2429, "lr": 4.589623436174316e-05, "epoch": 5.33003300330033, "percentage": 26.65, "elapsed_time": "0:40:54", "remaining_time": "1:52:36", "throughput": 4638.75, "total_tokens": 11386720} {"current_steps": 11310, "total_steps": 42420, "loss": 0.0628, "lr": 4.589058599994553e-05, "epoch": 5.332390381895332, "percentage": 26.66, "elapsed_time": "0:40:56", "remaining_time": "1:52:35", "throughput": 4638.42, "total_tokens": 11392128} {"current_steps": 11315, "total_steps": 42420, "loss": 0.0651, "lr": 4.58849341017264e-05, "epoch": 5.334747760490335, "percentage": 26.67, "elapsed_time": "0:40:57", "remaining_time": "1:52:35", "throughput": 4638.56, "total_tokens": 11398144} {"current_steps": 11320, "total_steps": 42420, "loss": 0.1349, "lr": 4.5879278668042525e-05, "epoch": 5.337105139085337, "percentage": 26.69, "elapsed_time": "0:40:58", "remaining_time": "1:52:33", "throughput": 4638.6, "total_tokens": 11402656} {"current_steps": 11325, "total_steps": 42420, "loss": 0.1087, "lr": 4.587361969985128e-05, "epoch": 5.33946251768034, "percentage": 26.7, "elapsed_time": "0:40:59", "remaining_time": "1:52:32", "throughput": 4638.72, "total_tokens": 11407904} {"current_steps": 11330, "total_steps": 42420, "loss": 0.2174, "lr": 4.586795719811064e-05, "epoch": 5.341819896275342, "percentage": 26.71, "elapsed_time": "0:41:00", "remaining_time": "1:52:31", "throughput": 4638.88, "total_tokens": 11413696} {"current_steps": 11335, "total_steps": 42420, "loss": 0.0491, "lr": 4.5862291163779165e-05, "epoch": 5.344177274870344, "percentage": 26.72, "elapsed_time": "0:41:01", "remaining_time": "1:52:30", "throughput": 4639.02, "total_tokens": 11419200} {"current_steps": 11340, "total_steps": 42420, "loss": 0.1787, "lr": 4.5856621597816015e-05, "epoch": 5.346534653465347, "percentage": 26.73, "elapsed_time": "0:41:02", "remaining_time": "1:52:29", "throughput": 4639.1, "total_tokens": 11423744} {"current_steps": 11345, "total_steps": 42420, "loss": 0.1153, "lr": 4.5850948501180955e-05, "epoch": 5.348892032060349, "percentage": 26.74, "elapsed_time": "0:41:03", "remaining_time": "1:52:27", "throughput": 4639.17, "total_tokens": 11428384} {"current_steps": 11350, "total_steps": 42420, "loss": 0.0868, "lr": 4.584527187483434e-05, "epoch": 5.351249410655352, "percentage": 26.76, "elapsed_time": "0:41:04", "remaining_time": "1:52:25", "throughput": 4639.18, "total_tokens": 11432256} {"current_steps": 11355, "total_steps": 42420, "loss": 0.1607, "lr": 4.583959171973713e-05, "epoch": 5.353606789250353, "percentage": 26.77, "elapsed_time": "0:41:05", "remaining_time": "1:52:24", "throughput": 4639.22, "total_tokens": 11437024} {"current_steps": 11360, "total_steps": 42420, "loss": 0.2216, "lr": 4.583390803685088e-05, "epoch": 5.355964167845356, "percentage": 26.78, "elapsed_time": "0:41:06", "remaining_time": "1:52:24", "throughput": 4639.39, "total_tokens": 11443520} {"current_steps": 11365, "total_steps": 42420, "loss": 0.0463, "lr": 4.582822082713773e-05, "epoch": 5.358321546440358, "percentage": 26.79, "elapsed_time": "0:41:07", "remaining_time": "1:52:22", "throughput": 4639.48, "total_tokens": 11448000} {"current_steps": 11370, "total_steps": 42420, "loss": 0.0342, "lr": 4.5822530091560446e-05, "epoch": 5.36067892503536, "percentage": 26.8, "elapsed_time": "0:41:08", "remaining_time": "1:52:20", "throughput": 4639.43, "total_tokens": 11451648} {"current_steps": 11375, "total_steps": 42420, "loss": 0.1428, "lr": 4.581683583108236e-05, "epoch": 5.363036303630363, "percentage": 26.82, "elapsed_time": "0:41:09", "remaining_time": "1:52:19", "throughput": 4639.61, "total_tokens": 11457600} {"current_steps": 11380, "total_steps": 42420, "loss": 0.2321, "lr": 4.5811138046667426e-05, "epoch": 5.365393682225365, "percentage": 26.83, "elapsed_time": "0:41:10", "remaining_time": "1:52:18", "throughput": 4639.62, "total_tokens": 11461920} {"current_steps": 11385, "total_steps": 42420, "loss": 0.0471, "lr": 4.5805436739280164e-05, "epoch": 5.367751060820368, "percentage": 26.84, "elapsed_time": "0:41:11", "remaining_time": "1:52:17", "throughput": 4639.63, "total_tokens": 11466880} {"current_steps": 11390, "total_steps": 42420, "loss": 0.2042, "lr": 4.579973190988572e-05, "epoch": 5.37010843941537, "percentage": 26.85, "elapsed_time": "0:41:12", "remaining_time": "1:52:16", "throughput": 4639.76, "total_tokens": 11472512} {"current_steps": 11395, "total_steps": 42420, "loss": 0.0697, "lr": 4.5794023559449824e-05, "epoch": 5.372465818010372, "percentage": 26.86, "elapsed_time": "0:41:13", "remaining_time": "1:52:15", "throughput": 4639.84, "total_tokens": 11477920} {"current_steps": 11400, "total_steps": 42420, "loss": 0.1281, "lr": 4.57883116889388e-05, "epoch": 5.374823196605375, "percentage": 26.87, "elapsed_time": "0:41:14", "remaining_time": "1:52:13", "throughput": 4639.95, "total_tokens": 11482656} {"current_steps": 11405, "total_steps": 42420, "loss": 0.0936, "lr": 4.578259629931958e-05, "epoch": 5.377180575200377, "percentage": 26.89, "elapsed_time": "0:41:15", "remaining_time": "1:52:13", "throughput": 4640.09, "total_tokens": 11488704} {"current_steps": 11410, "total_steps": 42420, "loss": 0.2551, "lr": 4.577687739155967e-05, "epoch": 5.37953795379538, "percentage": 26.9, "elapsed_time": "0:41:16", "remaining_time": "1:52:11", "throughput": 4640.14, "total_tokens": 11493504} {"current_steps": 11415, "total_steps": 42420, "loss": 0.1474, "lr": 4.577115496662718e-05, "epoch": 5.381895332390382, "percentage": 26.91, "elapsed_time": "0:41:18", "remaining_time": "1:52:11", "throughput": 4640.22, "total_tokens": 11499296} {"current_steps": 11420, "total_steps": 42420, "loss": 0.1625, "lr": 4.576542902549084e-05, "epoch": 5.384252710985384, "percentage": 26.92, "elapsed_time": "0:41:19", "remaining_time": "1:52:09", "throughput": 4640.22, "total_tokens": 11503360} {"current_steps": 11425, "total_steps": 42420, "loss": 0.0236, "lr": 4.575969956911994e-05, "epoch": 5.386610089580387, "percentage": 26.93, "elapsed_time": "0:41:19", "remaining_time": "1:52:07", "throughput": 4640.12, "total_tokens": 11507200} {"current_steps": 11430, "total_steps": 42420, "loss": 0.1019, "lr": 4.575396659848438e-05, "epoch": 5.388967468175389, "percentage": 26.94, "elapsed_time": "0:41:20", "remaining_time": "1:52:06", "throughput": 4640.12, "total_tokens": 11511520} {"current_steps": 11435, "total_steps": 42420, "loss": 0.0761, "lr": 4.5748230114554666e-05, "epoch": 5.391324846770392, "percentage": 26.96, "elapsed_time": "0:41:21", "remaining_time": "1:52:04", "throughput": 4640.15, "total_tokens": 11516096} {"current_steps": 11440, "total_steps": 42420, "loss": 0.1303, "lr": 4.574249011830187e-05, "epoch": 5.393682225365394, "percentage": 26.97, "elapsed_time": "0:41:22", "remaining_time": "1:52:03", "throughput": 4640.26, "total_tokens": 11521632} {"current_steps": 11445, "total_steps": 42420, "loss": 0.0959, "lr": 4.573674661069768e-05, "epoch": 5.396039603960396, "percentage": 26.98, "elapsed_time": "0:41:24", "remaining_time": "1:52:03", "throughput": 4640.43, "total_tokens": 11527744} {"current_steps": 11450, "total_steps": 42420, "loss": 0.1259, "lr": 4.573099959271439e-05, "epoch": 5.398396982555399, "percentage": 26.99, "elapsed_time": "0:41:25", "remaining_time": "1:52:01", "throughput": 4640.42, "total_tokens": 11531744} {"current_steps": 11455, "total_steps": 42420, "loss": 0.1529, "lr": 4.572524906532486e-05, "epoch": 5.400754361150401, "percentage": 27.0, "elapsed_time": "0:41:25", "remaining_time": "1:52:00", "throughput": 4640.48, "total_tokens": 11536192} {"current_steps": 11460, "total_steps": 42420, "loss": 0.1478, "lr": 4.571949502950255e-05, "epoch": 5.403111739745403, "percentage": 27.02, "elapsed_time": "0:41:27", "remaining_time": "1:51:58", "throughput": 4640.55, "total_tokens": 11541152} {"current_steps": 11465, "total_steps": 42420, "loss": 0.2982, "lr": 4.5713737486221534e-05, "epoch": 5.405469118340405, "percentage": 27.03, "elapsed_time": "0:41:28", "remaining_time": "1:51:57", "throughput": 4640.67, "total_tokens": 11546560} {"current_steps": 11470, "total_steps": 42420, "loss": 0.0528, "lr": 4.570797643645646e-05, "epoch": 5.4078264969354075, "percentage": 27.04, "elapsed_time": "0:41:29", "remaining_time": "1:51:56", "throughput": 4640.79, "total_tokens": 11552000} {"current_steps": 11475, "total_steps": 42420, "loss": 0.0628, "lr": 4.570221188118258e-05, "epoch": 5.41018387553041, "percentage": 27.05, "elapsed_time": "0:41:30", "remaining_time": "1:51:55", "throughput": 4640.92, "total_tokens": 11557088} {"current_steps": 11480, "total_steps": 42420, "loss": 0.1355, "lr": 4.5696443821375726e-05, "epoch": 5.412541254125412, "percentage": 27.06, "elapsed_time": "0:41:31", "remaining_time": "1:51:54", "throughput": 4641.02, "total_tokens": 11562336} {"current_steps": 11485, "total_steps": 42420, "loss": 0.0623, "lr": 4.569067225801234e-05, "epoch": 5.414898632720415, "percentage": 27.07, "elapsed_time": "0:41:32", "remaining_time": "1:51:53", "throughput": 4641.01, "total_tokens": 11567296} {"current_steps": 11490, "total_steps": 42420, "loss": 0.0649, "lr": 4.568489719206945e-05, "epoch": 5.417256011315417, "percentage": 27.09, "elapsed_time": "0:41:33", "remaining_time": "1:51:52", "throughput": 4641.08, "total_tokens": 11572672} {"current_steps": 11495, "total_steps": 42420, "loss": 0.1322, "lr": 4.5679118624524673e-05, "epoch": 5.4196133899104195, "percentage": 27.1, "elapsed_time": "0:41:34", "remaining_time": "1:51:50", "throughput": 4641.16, "total_tokens": 11577312} {"current_steps": 11500, "total_steps": 42420, "loss": 0.0688, "lr": 4.567333655635623e-05, "epoch": 5.421970768505422, "percentage": 27.11, "elapsed_time": "0:41:35", "remaining_time": "1:51:49", "throughput": 4641.25, "total_tokens": 11582208} {"current_steps": 11505, "total_steps": 42420, "loss": 0.0776, "lr": 4.566755098854291e-05, "epoch": 5.424328147100424, "percentage": 27.12, "elapsed_time": "0:41:36", "remaining_time": "1:51:48", "throughput": 4641.37, "total_tokens": 11587424} {"current_steps": 11510, "total_steps": 42420, "loss": 0.1736, "lr": 4.5661761922064126e-05, "epoch": 5.426685525695427, "percentage": 27.13, "elapsed_time": "0:41:37", "remaining_time": "1:51:47", "throughput": 4641.37, "total_tokens": 11592000} {"current_steps": 11515, "total_steps": 42420, "loss": 0.2737, "lr": 4.5655969357899874e-05, "epoch": 5.429042904290429, "percentage": 27.15, "elapsed_time": "0:41:38", "remaining_time": "1:51:45", "throughput": 4641.48, "total_tokens": 11597088} {"current_steps": 11520, "total_steps": 42420, "loss": 0.1564, "lr": 4.565017329703072e-05, "epoch": 5.4314002828854315, "percentage": 27.16, "elapsed_time": "0:41:39", "remaining_time": "1:51:44", "throughput": 4641.52, "total_tokens": 11601568} {"current_steps": 11525, "total_steps": 42420, "loss": 0.0851, "lr": 4.5644373740437855e-05, "epoch": 5.433757661480434, "percentage": 27.17, "elapsed_time": "0:41:40", "remaining_time": "1:51:43", "throughput": 4641.64, "total_tokens": 11606752} {"current_steps": 11530, "total_steps": 42420, "loss": 0.1217, "lr": 4.5638570689103036e-05, "epoch": 5.436115040075436, "percentage": 27.18, "elapsed_time": "0:41:41", "remaining_time": "1:51:42", "throughput": 4641.7, "total_tokens": 11612288} {"current_steps": 11535, "total_steps": 42420, "loss": 0.2124, "lr": 4.563276414400861e-05, "epoch": 5.438472418670439, "percentage": 27.19, "elapsed_time": "0:41:42", "remaining_time": "1:51:41", "throughput": 4641.82, "total_tokens": 11617728} {"current_steps": 11540, "total_steps": 42420, "loss": 0.0763, "lr": 4.5626954106137554e-05, "epoch": 5.440829797265441, "percentage": 27.2, "elapsed_time": "0:41:43", "remaining_time": "1:51:40", "throughput": 4641.92, "total_tokens": 11623040} {"current_steps": 11545, "total_steps": 42420, "loss": 0.1053, "lr": 4.5621140576473384e-05, "epoch": 5.4431871758604435, "percentage": 27.22, "elapsed_time": "0:41:45", "remaining_time": "1:51:39", "throughput": 4642.03, "total_tokens": 11628416} {"current_steps": 11550, "total_steps": 42420, "loss": 0.1233, "lr": 4.5615323556000246e-05, "epoch": 5.445544554455446, "percentage": 27.23, "elapsed_time": "0:41:46", "remaining_time": "1:51:37", "throughput": 4642.12, "total_tokens": 11633312} {"current_steps": 11555, "total_steps": 42420, "loss": 0.1378, "lr": 4.560950304570285e-05, "epoch": 5.4479019330504475, "percentage": 27.24, "elapsed_time": "0:41:46", "remaining_time": "1:51:36", "throughput": 4642.22, "total_tokens": 11637920} {"current_steps": 11560, "total_steps": 42420, "loss": 0.1072, "lr": 4.5603679046566525e-05, "epoch": 5.45025931164545, "percentage": 27.25, "elapsed_time": "0:41:48", "remaining_time": "1:51:35", "throughput": 4642.33, "total_tokens": 11643392} {"current_steps": 11565, "total_steps": 42420, "loss": 0.1023, "lr": 4.559785155957717e-05, "epoch": 5.452616690240452, "percentage": 27.26, "elapsed_time": "0:41:49", "remaining_time": "1:51:34", "throughput": 4642.38, "total_tokens": 11648064} {"current_steps": 11570, "total_steps": 42420, "loss": 0.4234, "lr": 4.559202058572127e-05, "epoch": 5.454974068835455, "percentage": 27.27, "elapsed_time": "0:41:50", "remaining_time": "1:51:33", "throughput": 4642.55, "total_tokens": 11654752} {"current_steps": 11575, "total_steps": 42420, "loss": 0.0786, "lr": 4.558618612598593e-05, "epoch": 5.457331447430457, "percentage": 27.29, "elapsed_time": "0:41:51", "remaining_time": "1:51:32", "throughput": 4642.59, "total_tokens": 11659680} {"current_steps": 11580, "total_steps": 42420, "loss": 0.1033, "lr": 4.55803481813588e-05, "epoch": 5.4596888260254595, "percentage": 27.3, "elapsed_time": "0:41:52", "remaining_time": "1:51:31", "throughput": 4642.59, "total_tokens": 11664064} {"current_steps": 11585, "total_steps": 42420, "loss": 0.2388, "lr": 4.5574506752828164e-05, "epoch": 5.462046204620462, "percentage": 27.31, "elapsed_time": "0:41:53", "remaining_time": "1:51:30", "throughput": 4642.72, "total_tokens": 11669760} {"current_steps": 11590, "total_steps": 42420, "loss": 0.1797, "lr": 4.556866184138287e-05, "epoch": 5.464403583215464, "percentage": 27.32, "elapsed_time": "0:41:54", "remaining_time": "1:51:28", "throughput": 4642.77, "total_tokens": 11673952} {"current_steps": 11595, "total_steps": 42420, "loss": 0.1113, "lr": 4.5562813448012354e-05, "epoch": 5.466760961810467, "percentage": 27.33, "elapsed_time": "0:41:55", "remaining_time": "1:51:27", "throughput": 4642.85, "total_tokens": 11679040} {"current_steps": 11600, "total_steps": 42420, "loss": 0.0559, "lr": 4.555696157370667e-05, "epoch": 5.469118340405469, "percentage": 27.35, "elapsed_time": "0:41:56", "remaining_time": "1:51:26", "throughput": 4642.91, "total_tokens": 11683872} {"current_steps": 11605, "total_steps": 42420, "loss": 0.2195, "lr": 4.555110621945642e-05, "epoch": 5.4714757190004715, "percentage": 27.36, "elapsed_time": "0:41:57", "remaining_time": "1:51:24", "throughput": 4643.03, "total_tokens": 11689152} {"current_steps": 11610, "total_steps": 42420, "loss": 0.1179, "lr": 4.554524738625283e-05, "epoch": 5.473833097595474, "percentage": 27.37, "elapsed_time": "0:41:58", "remaining_time": "1:51:23", "throughput": 4643.12, "total_tokens": 11694208} {"current_steps": 11615, "total_steps": 42420, "loss": 0.2087, "lr": 4.5539385075087694e-05, "epoch": 5.476190476190476, "percentage": 27.38, "elapsed_time": "0:41:59", "remaining_time": "1:51:23", "throughput": 4643.38, "total_tokens": 11701280} {"current_steps": 11620, "total_steps": 42420, "loss": 0.1841, "lr": 4.55335192869534e-05, "epoch": 5.478547854785479, "percentage": 27.39, "elapsed_time": "0:42:01", "remaining_time": "1:51:22", "throughput": 4643.42, "total_tokens": 11706208} {"current_steps": 11625, "total_steps": 42420, "loss": 0.084, "lr": 4.552765002284294e-05, "epoch": 5.480905233380481, "percentage": 27.4, "elapsed_time": "0:42:01", "remaining_time": "1:51:20", "throughput": 4643.44, "total_tokens": 11710400} {"current_steps": 11630, "total_steps": 42420, "loss": 0.25, "lr": 4.552177728374987e-05, "epoch": 5.4832626119754835, "percentage": 27.42, "elapsed_time": "0:42:03", "remaining_time": "1:51:20", "throughput": 4643.59, "total_tokens": 11716640} {"current_steps": 11635, "total_steps": 42420, "loss": 0.1217, "lr": 4.551590107066833e-05, "epoch": 5.485619990570486, "percentage": 27.43, "elapsed_time": "0:42:04", "remaining_time": "1:51:18", "throughput": 4643.68, "total_tokens": 11721824} {"current_steps": 11640, "total_steps": 42420, "loss": 0.1324, "lr": 4.5510021384593094e-05, "epoch": 5.487977369165488, "percentage": 27.44, "elapsed_time": "0:42:05", "remaining_time": "1:51:18", "throughput": 4643.81, "total_tokens": 11727904} {"current_steps": 11645, "total_steps": 42420, "loss": 0.3763, "lr": 4.5504138226519474e-05, "epoch": 5.490334747760491, "percentage": 27.45, "elapsed_time": "0:42:06", "remaining_time": "1:51:17", "throughput": 4643.8, "total_tokens": 11733184} {"current_steps": 11650, "total_steps": 42420, "loss": 0.1878, "lr": 4.5498251597443384e-05, "epoch": 5.492692126355493, "percentage": 27.46, "elapsed_time": "0:42:07", "remaining_time": "1:51:15", "throughput": 4643.83, "total_tokens": 11737792} {"current_steps": 11655, "total_steps": 42420, "loss": 0.0728, "lr": 4.5492361498361353e-05, "epoch": 5.4950495049504955, "percentage": 27.48, "elapsed_time": "0:42:08", "remaining_time": "1:51:14", "throughput": 4643.82, "total_tokens": 11741728} {"current_steps": 11660, "total_steps": 42420, "loss": 0.0645, "lr": 4.548646793027046e-05, "epoch": 5.497406883545497, "percentage": 27.49, "elapsed_time": "0:42:09", "remaining_time": "1:51:12", "throughput": 4643.86, "total_tokens": 11746336} {"current_steps": 11665, "total_steps": 42420, "loss": 0.1758, "lr": 4.548057089416837e-05, "epoch": 5.499764262140499, "percentage": 27.5, "elapsed_time": "0:42:10", "remaining_time": "1:51:12", "throughput": 4644.03, "total_tokens": 11752480} {"current_steps": 11670, "total_steps": 42420, "loss": 0.179, "lr": 4.5474670391053385e-05, "epoch": 5.502121640735502, "percentage": 27.51, "elapsed_time": "0:42:11", "remaining_time": "1:51:10", "throughput": 4644.13, "total_tokens": 11757120} {"current_steps": 11675, "total_steps": 42420, "loss": 0.3097, "lr": 4.546876642192434e-05, "epoch": 5.504479019330504, "percentage": 27.52, "elapsed_time": "0:42:12", "remaining_time": "1:51:09", "throughput": 4644.04, "total_tokens": 11760896} {"current_steps": 11680, "total_steps": 42420, "loss": 0.0914, "lr": 4.546285898778068e-05, "epoch": 5.506836397925507, "percentage": 27.53, "elapsed_time": "0:42:13", "remaining_time": "1:51:07", "throughput": 4644.16, "total_tokens": 11765888} {"current_steps": 11685, "total_steps": 42420, "loss": 0.0951, "lr": 4.545694808962243e-05, "epoch": 5.509193776520509, "percentage": 27.55, "elapsed_time": "0:42:14", "remaining_time": "1:51:06", "throughput": 4644.21, "total_tokens": 11770432} {"current_steps": 11690, "total_steps": 42420, "loss": 0.26, "lr": 4.54510337284502e-05, "epoch": 5.511551155115511, "percentage": 27.56, "elapsed_time": "0:42:15", "remaining_time": "1:51:05", "throughput": 4644.31, "total_tokens": 11776736} {"current_steps": 11695, "total_steps": 42420, "loss": 0.0824, "lr": 4.544511590526521e-05, "epoch": 5.513908533710514, "percentage": 27.57, "elapsed_time": "0:42:16", "remaining_time": "1:51:04", "throughput": 4644.38, "total_tokens": 11781792} {"current_steps": 11700, "total_steps": 42420, "loss": 0.1828, "lr": 4.543919462106922e-05, "epoch": 5.516265912305516, "percentage": 27.58, "elapsed_time": "0:42:17", "remaining_time": "1:51:03", "throughput": 4644.48, "total_tokens": 11786912} {"current_steps": 11705, "total_steps": 42420, "loss": 0.1622, "lr": 4.5433269876864634e-05, "epoch": 5.518623290900519, "percentage": 27.59, "elapsed_time": "0:42:19", "remaining_time": "1:51:02", "throughput": 4644.55, "total_tokens": 11792960} {"current_steps": 11710, "total_steps": 42420, "loss": 0.1506, "lr": 4.54273416736544e-05, "epoch": 5.520980669495521, "percentage": 27.6, "elapsed_time": "0:42:20", "remaining_time": "1:51:01", "throughput": 4644.57, "total_tokens": 11797408} {"current_steps": 11715, "total_steps": 42420, "loss": 0.1211, "lr": 4.5421410012442046e-05, "epoch": 5.523338048090523, "percentage": 27.62, "elapsed_time": "0:42:21", "remaining_time": "1:51:00", "throughput": 4644.64, "total_tokens": 11802176} {"current_steps": 11720, "total_steps": 42420, "loss": 0.4307, "lr": 4.541547489423171e-05, "epoch": 5.525695426685526, "percentage": 27.63, "elapsed_time": "0:42:22", "remaining_time": "1:50:58", "throughput": 4644.63, "total_tokens": 11806976} {"current_steps": 11725, "total_steps": 42420, "loss": 0.0883, "lr": 4.540953632002812e-05, "epoch": 5.528052805280528, "percentage": 27.64, "elapsed_time": "0:42:22", "remaining_time": "1:50:57", "throughput": 4644.67, "total_tokens": 11811200} {"current_steps": 11730, "total_steps": 42420, "loss": 0.1915, "lr": 4.540359429083656e-05, "epoch": 5.530410183875531, "percentage": 27.65, "elapsed_time": "0:42:24", "remaining_time": "1:50:56", "throughput": 4644.79, "total_tokens": 11816480} {"current_steps": 11735, "total_steps": 42420, "loss": 0.0616, "lr": 4.5397648807662915e-05, "epoch": 5.532767562470533, "percentage": 27.66, "elapsed_time": "0:42:25", "remaining_time": "1:50:54", "throughput": 4644.92, "total_tokens": 11821696} {"current_steps": 11740, "total_steps": 42420, "loss": 0.2454, "lr": 4.539169987151367e-05, "epoch": 5.535124941065535, "percentage": 27.68, "elapsed_time": "0:42:26", "remaining_time": "1:50:53", "throughput": 4644.99, "total_tokens": 11826464} {"current_steps": 11745, "total_steps": 42420, "loss": 0.1181, "lr": 4.538574748339586e-05, "epoch": 5.537482319660538, "percentage": 27.69, "elapsed_time": "0:42:27", "remaining_time": "1:50:52", "throughput": 4645.17, "total_tokens": 11832512} {"current_steps": 11750, "total_steps": 42420, "loss": 0.0934, "lr": 4.537979164431713e-05, "epoch": 5.539839698255539, "percentage": 27.7, "elapsed_time": "0:42:28", "remaining_time": "1:50:51", "throughput": 4645.26, "total_tokens": 11837056} {"current_steps": 11755, "total_steps": 42420, "loss": 0.0944, "lr": 4.537383235528571e-05, "epoch": 5.542197076850542, "percentage": 27.71, "elapsed_time": "0:42:29", "remaining_time": "1:50:50", "throughput": 4645.36, "total_tokens": 11842240} {"current_steps": 11760, "total_steps": 42420, "loss": 0.186, "lr": 4.53678696173104e-05, "epoch": 5.544554455445544, "percentage": 27.72, "elapsed_time": "0:42:30", "remaining_time": "1:50:49", "throughput": 4645.49, "total_tokens": 11847744} {"current_steps": 11765, "total_steps": 42420, "loss": 0.0987, "lr": 4.536190343140059e-05, "epoch": 5.5469118340405466, "percentage": 27.73, "elapsed_time": "0:42:31", "remaining_time": "1:50:47", "throughput": 4645.57, "total_tokens": 11852384} {"current_steps": 11770, "total_steps": 42420, "loss": 0.2112, "lr": 4.5355933798566245e-05, "epoch": 5.549269212635549, "percentage": 27.75, "elapsed_time": "0:42:32", "remaining_time": "1:50:46", "throughput": 4645.69, "total_tokens": 11857504} {"current_steps": 11775, "total_steps": 42420, "loss": 0.0814, "lr": 4.534996071981794e-05, "epoch": 5.551626591230551, "percentage": 27.76, "elapsed_time": "0:42:33", "remaining_time": "1:50:45", "throughput": 4645.78, "total_tokens": 11862304} {"current_steps": 11780, "total_steps": 42420, "loss": 0.0841, "lr": 4.5343984196166814e-05, "epoch": 5.553983969825554, "percentage": 27.77, "elapsed_time": "0:42:34", "remaining_time": "1:50:43", "throughput": 4645.85, "total_tokens": 11866880} {"current_steps": 11785, "total_steps": 42420, "loss": 0.2915, "lr": 4.533800422862458e-05, "epoch": 5.556341348420556, "percentage": 27.78, "elapsed_time": "0:42:35", "remaining_time": "1:50:42", "throughput": 4645.97, "total_tokens": 11872064} {"current_steps": 11790, "total_steps": 42420, "loss": 0.0792, "lr": 4.5332020818203544e-05, "epoch": 5.558698727015559, "percentage": 27.79, "elapsed_time": "0:42:36", "remaining_time": "1:50:41", "throughput": 4646.08, "total_tokens": 11876864} {"current_steps": 11795, "total_steps": 42420, "loss": 0.0543, "lr": 4.5326033965916606e-05, "epoch": 5.561056105610561, "percentage": 27.81, "elapsed_time": "0:42:37", "remaining_time": "1:50:40", "throughput": 4646.21, "total_tokens": 11883136} {"current_steps": 11800, "total_steps": 42420, "loss": 0.1749, "lr": 4.532004367277723e-05, "epoch": 5.563413484205563, "percentage": 27.82, "elapsed_time": "0:42:38", "remaining_time": "1:50:39", "throughput": 4646.21, "total_tokens": 11887424} {"current_steps": 11805, "total_steps": 42420, "loss": 0.2219, "lr": 4.5314049939799475e-05, "epoch": 5.565770862800566, "percentage": 27.83, "elapsed_time": "0:42:39", "remaining_time": "1:50:37", "throughput": 4646.29, "total_tokens": 11891968} {"current_steps": 11810, "total_steps": 42420, "loss": 0.436, "lr": 4.530805276799798e-05, "epoch": 5.568128241395568, "percentage": 27.84, "elapsed_time": "0:42:40", "remaining_time": "1:50:36", "throughput": 4646.41, "total_tokens": 11897408} {"current_steps": 11815, "total_steps": 42420, "loss": 0.1224, "lr": 4.530205215838796e-05, "epoch": 5.570485619990571, "percentage": 27.85, "elapsed_time": "0:42:41", "remaining_time": "1:50:35", "throughput": 4646.46, "total_tokens": 11901696} {"current_steps": 11820, "total_steps": 42420, "loss": 0.1178, "lr": 4.529604811198523e-05, "epoch": 5.572842998585573, "percentage": 27.86, "elapsed_time": "0:42:42", "remaining_time": "1:50:34", "throughput": 4646.57, "total_tokens": 11907104} {"current_steps": 11825, "total_steps": 42420, "loss": 0.1454, "lr": 4.5290040629806155e-05, "epoch": 5.575200377180575, "percentage": 27.88, "elapsed_time": "0:42:43", "remaining_time": "1:50:33", "throughput": 4646.68, "total_tokens": 11912704} {"current_steps": 11830, "total_steps": 42420, "loss": 0.1174, "lr": 4.528402971286771e-05, "epoch": 5.577557755775578, "percentage": 27.89, "elapsed_time": "0:42:44", "remaining_time": "1:50:32", "throughput": 4646.82, "total_tokens": 11918656} {"current_steps": 11835, "total_steps": 42420, "loss": 0.1173, "lr": 4.527801536218743e-05, "epoch": 5.57991513437058, "percentage": 27.9, "elapsed_time": "0:42:45", "remaining_time": "1:50:31", "throughput": 4646.85, "total_tokens": 11923360} {"current_steps": 11840, "total_steps": 42420, "loss": 0.1191, "lr": 4.5271997578783455e-05, "epoch": 5.582272512965583, "percentage": 27.91, "elapsed_time": "0:42:46", "remaining_time": "1:50:29", "throughput": 4646.95, "total_tokens": 11928064} {"current_steps": 11845, "total_steps": 42420, "loss": 0.131, "lr": 4.526597636367449e-05, "epoch": 5.584629891560585, "percentage": 27.92, "elapsed_time": "0:42:48", "remaining_time": "1:50:29", "throughput": 4647.04, "total_tokens": 11934912} {"current_steps": 11850, "total_steps": 42420, "loss": 0.0952, "lr": 4.525995171787982e-05, "epoch": 5.586987270155587, "percentage": 27.93, "elapsed_time": "0:42:49", "remaining_time": "1:50:27", "throughput": 4647.1, "total_tokens": 11939456} {"current_steps": 11855, "total_steps": 42420, "loss": 0.2726, "lr": 4.525392364241932e-05, "epoch": 5.58934464875059, "percentage": 27.95, "elapsed_time": "0:42:50", "remaining_time": "1:50:26", "throughput": 4647.15, "total_tokens": 11943904} {"current_steps": 11860, "total_steps": 42420, "loss": 0.0483, "lr": 4.5247892138313435e-05, "epoch": 5.591702027345592, "percentage": 27.96, "elapsed_time": "0:42:51", "remaining_time": "1:50:26", "throughput": 4647.38, "total_tokens": 11951008} {"current_steps": 11865, "total_steps": 42420, "loss": 0.077, "lr": 4.5241857206583205e-05, "epoch": 5.594059405940594, "percentage": 27.97, "elapsed_time": "0:42:52", "remaining_time": "1:50:25", "throughput": 4647.5, "total_tokens": 11956352} {"current_steps": 11870, "total_steps": 42420, "loss": 0.2397, "lr": 4.5235818848250236e-05, "epoch": 5.596416784535596, "percentage": 27.98, "elapsed_time": "0:42:53", "remaining_time": "1:50:23", "throughput": 4647.61, "total_tokens": 11961024} {"current_steps": 11875, "total_steps": 42420, "loss": 0.0616, "lr": 4.522977706433672e-05, "epoch": 5.5987741631305985, "percentage": 27.99, "elapsed_time": "0:42:54", "remaining_time": "1:50:22", "throughput": 4647.7, "total_tokens": 11966496} {"current_steps": 11880, "total_steps": 42420, "loss": 0.2272, "lr": 4.522373185586544e-05, "epoch": 5.601131541725601, "percentage": 28.01, "elapsed_time": "0:42:55", "remaining_time": "1:50:21", "throughput": 4647.86, "total_tokens": 11972608} {"current_steps": 11885, "total_steps": 42420, "loss": 0.0551, "lr": 4.521768322385972e-05, "epoch": 5.603488920320603, "percentage": 28.02, "elapsed_time": "0:42:56", "remaining_time": "1:50:20", "throughput": 4647.96, "total_tokens": 11977664} {"current_steps": 11890, "total_steps": 42420, "loss": 0.3241, "lr": 4.521163116934351e-05, "epoch": 5.605846298915606, "percentage": 28.03, "elapsed_time": "0:42:57", "remaining_time": "1:50:19", "throughput": 4648.01, "total_tokens": 11982400} {"current_steps": 11895, "total_steps": 42420, "loss": 0.1546, "lr": 4.520557569334133e-05, "epoch": 5.608203677510608, "percentage": 28.04, "elapsed_time": "0:42:59", "remaining_time": "1:50:18", "throughput": 4648.12, "total_tokens": 11987968} {"current_steps": 11900, "total_steps": 42420, "loss": 0.2735, "lr": 4.5199516796878246e-05, "epoch": 5.6105610561056105, "percentage": 28.05, "elapsed_time": "0:43:00", "remaining_time": "1:50:17", "throughput": 4648.2, "total_tokens": 11993120} {"current_steps": 11905, "total_steps": 42420, "loss": 0.2493, "lr": 4.5193454480979935e-05, "epoch": 5.612918434700613, "percentage": 28.06, "elapsed_time": "0:43:01", "remaining_time": "1:50:16", "throughput": 4648.32, "total_tokens": 11998400} {"current_steps": 11910, "total_steps": 42420, "loss": 0.0739, "lr": 4.518738874667265e-05, "epoch": 5.615275813295615, "percentage": 28.08, "elapsed_time": "0:43:02", "remaining_time": "1:50:14", "throughput": 4648.33, "total_tokens": 12002592} {"current_steps": 11915, "total_steps": 42420, "loss": 0.2312, "lr": 4.518131959498321e-05, "epoch": 5.617633191890618, "percentage": 28.09, "elapsed_time": "0:43:03", "remaining_time": "1:50:13", "throughput": 4648.41, "total_tokens": 12007744} {"current_steps": 11920, "total_steps": 42420, "loss": 0.301, "lr": 4.517524702693902e-05, "epoch": 5.61999057048562, "percentage": 28.1, "elapsed_time": "0:43:04", "remaining_time": "1:50:12", "throughput": 4648.52, "total_tokens": 12013024} {"current_steps": 11925, "total_steps": 42420, "loss": 0.1224, "lr": 4.516917104356807e-05, "epoch": 5.6223479490806225, "percentage": 28.11, "elapsed_time": "0:43:05", "remaining_time": "1:50:11", "throughput": 4648.6, "total_tokens": 12018016} {"current_steps": 11930, "total_steps": 42420, "loss": 0.0551, "lr": 4.516309164589891e-05, "epoch": 5.624705327675625, "percentage": 28.12, "elapsed_time": "0:43:06", "remaining_time": "1:50:10", "throughput": 4648.6, "total_tokens": 12023008} {"current_steps": 11935, "total_steps": 42420, "loss": 0.1088, "lr": 4.515700883496069e-05, "epoch": 5.627062706270627, "percentage": 28.14, "elapsed_time": "0:43:07", "remaining_time": "1:50:08", "throughput": 4648.67, "total_tokens": 12027808} {"current_steps": 11940, "total_steps": 42420, "loss": 0.1101, "lr": 4.515092261178312e-05, "epoch": 5.62942008486563, "percentage": 28.15, "elapsed_time": "0:43:08", "remaining_time": "1:50:07", "throughput": 4648.7, "total_tokens": 12032736} {"current_steps": 11945, "total_steps": 42420, "loss": 0.2142, "lr": 4.514483297739649e-05, "epoch": 5.631777463460632, "percentage": 28.16, "elapsed_time": "0:43:09", "remaining_time": "1:50:06", "throughput": 4648.76, "total_tokens": 12037824} {"current_steps": 11950, "total_steps": 42420, "loss": 0.271, "lr": 4.5138739932831674e-05, "epoch": 5.634134842055634, "percentage": 28.17, "elapsed_time": "0:43:10", "remaining_time": "1:50:05", "throughput": 4648.82, "total_tokens": 12042368} {"current_steps": 11955, "total_steps": 42420, "loss": 0.1187, "lr": 4.513264347912013e-05, "epoch": 5.636492220650636, "percentage": 28.18, "elapsed_time": "0:43:11", "remaining_time": "1:50:03", "throughput": 4648.88, "total_tokens": 12047584} {"current_steps": 11960, "total_steps": 42420, "loss": 0.0988, "lr": 4.512654361729388e-05, "epoch": 5.6388495992456384, "percentage": 28.19, "elapsed_time": "0:43:12", "remaining_time": "1:50:02", "throughput": 4648.91, "total_tokens": 12051968} {"current_steps": 11965, "total_steps": 42420, "loss": 0.0926, "lr": 4.5120440348385524e-05, "epoch": 5.641206977840641, "percentage": 28.21, "elapsed_time": "0:43:13", "remaining_time": "1:50:01", "throughput": 4649.03, "total_tokens": 12057216} {"current_steps": 11970, "total_steps": 42420, "loss": 0.0876, "lr": 4.511433367342824e-05, "epoch": 5.643564356435643, "percentage": 28.22, "elapsed_time": "0:43:14", "remaining_time": "1:50:00", "throughput": 4649.12, "total_tokens": 12062368} {"current_steps": 11975, "total_steps": 42420, "loss": 0.1888, "lr": 4.510822359345579e-05, "epoch": 5.645921735030646, "percentage": 28.23, "elapsed_time": "0:43:15", "remaining_time": "1:49:58", "throughput": 4649.09, "total_tokens": 12066368} {"current_steps": 11980, "total_steps": 42420, "loss": 0.055, "lr": 4.510211010950249e-05, "epoch": 5.648279113625648, "percentage": 28.24, "elapsed_time": "0:43:16", "remaining_time": "1:49:57", "throughput": 4649.12, "total_tokens": 12070816} {"current_steps": 11985, "total_steps": 42420, "loss": 0.1566, "lr": 4.5095993222603285e-05, "epoch": 5.6506364922206505, "percentage": 28.25, "elapsed_time": "0:43:17", "remaining_time": "1:49:55", "throughput": 4649.18, "total_tokens": 12075744} {"current_steps": 11990, "total_steps": 42420, "loss": 0.2926, "lr": 4.508987293379362e-05, "epoch": 5.652993870815653, "percentage": 28.26, "elapsed_time": "0:43:18", "remaining_time": "1:49:54", "throughput": 4649.28, "total_tokens": 12081184} {"current_steps": 11995, "total_steps": 42420, "loss": 0.066, "lr": 4.508374924410959e-05, "epoch": 5.655351249410655, "percentage": 28.28, "elapsed_time": "0:43:19", "remaining_time": "1:49:53", "throughput": 4649.4, "total_tokens": 12086144} {"current_steps": 12000, "total_steps": 42420, "loss": 0.1806, "lr": 4.50776221545878e-05, "epoch": 5.657708628005658, "percentage": 28.29, "elapsed_time": "0:43:20", "remaining_time": "1:49:52", "throughput": 4649.44, "total_tokens": 12090528} {"current_steps": 12005, "total_steps": 42420, "loss": 0.0687, "lr": 4.5071491666265483e-05, "epoch": 5.66006600660066, "percentage": 28.3, "elapsed_time": "0:43:21", "remaining_time": "1:49:50", "throughput": 4649.43, "total_tokens": 12094688} {"current_steps": 12010, "total_steps": 42420, "loss": 0.0612, "lr": 4.5065357780180424e-05, "epoch": 5.6624233851956625, "percentage": 28.31, "elapsed_time": "0:43:22", "remaining_time": "1:49:49", "throughput": 4649.51, "total_tokens": 12100352} {"current_steps": 12015, "total_steps": 42420, "loss": 0.0912, "lr": 4.505922049737098e-05, "epoch": 5.664780763790665, "percentage": 28.32, "elapsed_time": "0:43:23", "remaining_time": "1:49:48", "throughput": 4649.51, "total_tokens": 12104768} {"current_steps": 12020, "total_steps": 42420, "loss": 0.1223, "lr": 4.50530798188761e-05, "epoch": 5.667138142385667, "percentage": 28.34, "elapsed_time": "0:43:24", "remaining_time": "1:49:46", "throughput": 4649.58, "total_tokens": 12109568} {"current_steps": 12025, "total_steps": 42420, "loss": 0.1768, "lr": 4.504693574573528e-05, "epoch": 5.66949552098067, "percentage": 28.35, "elapsed_time": "0:43:25", "remaining_time": "1:49:45", "throughput": 4649.57, "total_tokens": 12114080} {"current_steps": 12030, "total_steps": 42420, "loss": 0.0639, "lr": 4.504078827898862e-05, "epoch": 5.671852899575672, "percentage": 28.36, "elapsed_time": "0:43:26", "remaining_time": "1:49:44", "throughput": 4649.62, "total_tokens": 12118624} {"current_steps": 12035, "total_steps": 42420, "loss": 0.1652, "lr": 4.503463741967677e-05, "epoch": 5.6742102781706745, "percentage": 28.37, "elapsed_time": "0:43:27", "remaining_time": "1:49:42", "throughput": 4649.67, "total_tokens": 12123232} {"current_steps": 12040, "total_steps": 42420, "loss": 0.2648, "lr": 4.5028483168840986e-05, "epoch": 5.676567656765677, "percentage": 28.38, "elapsed_time": "0:43:28", "remaining_time": "1:49:41", "throughput": 4649.71, "total_tokens": 12128480} {"current_steps": 12045, "total_steps": 42420, "loss": 0.0751, "lr": 4.502232552752306e-05, "epoch": 5.678925035360679, "percentage": 28.39, "elapsed_time": "0:43:29", "remaining_time": "1:49:40", "throughput": 4649.81, "total_tokens": 12133600} {"current_steps": 12050, "total_steps": 42420, "loss": 0.2601, "lr": 4.501616449676538e-05, "epoch": 5.681282413955682, "percentage": 28.41, "elapsed_time": "0:43:30", "remaining_time": "1:49:39", "throughput": 4649.78, "total_tokens": 12137920} {"current_steps": 12055, "total_steps": 42420, "loss": 0.0323, "lr": 4.50100000776109e-05, "epoch": 5.683639792550684, "percentage": 28.42, "elapsed_time": "0:43:31", "remaining_time": "1:49:38", "throughput": 4649.8, "total_tokens": 12143008} {"current_steps": 12060, "total_steps": 42420, "loss": 0.1492, "lr": 4.5003832271103166e-05, "epoch": 5.6859971711456865, "percentage": 28.43, "elapsed_time": "0:43:32", "remaining_time": "1:49:36", "throughput": 4649.8, "total_tokens": 12147328} {"current_steps": 12065, "total_steps": 42420, "loss": 0.0764, "lr": 4.499766107828628e-05, "epoch": 5.688354549740688, "percentage": 28.44, "elapsed_time": "0:43:33", "remaining_time": "1:49:35", "throughput": 4649.94, "total_tokens": 12152960} {"current_steps": 12070, "total_steps": 42420, "loss": 0.1086, "lr": 4.4991486500204905e-05, "epoch": 5.69071192833569, "percentage": 28.45, "elapsed_time": "0:43:34", "remaining_time": "1:49:34", "throughput": 4649.88, "total_tokens": 12157952} {"current_steps": 12075, "total_steps": 42420, "loss": 0.2238, "lr": 4.49853085379043e-05, "epoch": 5.693069306930693, "percentage": 28.47, "elapsed_time": "0:43:35", "remaining_time": "1:49:33", "throughput": 4649.91, "total_tokens": 12163136} {"current_steps": 12080, "total_steps": 42420, "loss": 0.1214, "lr": 4.49791271924303e-05, "epoch": 5.695426685525695, "percentage": 28.48, "elapsed_time": "0:43:36", "remaining_time": "1:49:32", "throughput": 4650.03, "total_tokens": 12168512} {"current_steps": 12085, "total_steps": 42420, "loss": 0.1296, "lr": 4.4972942464829285e-05, "epoch": 5.697784064120698, "percentage": 28.49, "elapsed_time": "0:43:37", "remaining_time": "1:49:31", "throughput": 4650.14, "total_tokens": 12173984} {"current_steps": 12090, "total_steps": 42420, "loss": 0.1266, "lr": 4.4966754356148235e-05, "epoch": 5.7001414427157, "percentage": 28.5, "elapsed_time": "0:43:38", "remaining_time": "1:49:30", "throughput": 4650.2, "total_tokens": 12178656} {"current_steps": 12095, "total_steps": 42420, "loss": 0.2383, "lr": 4.4960562867434685e-05, "epoch": 5.702498821310702, "percentage": 28.51, "elapsed_time": "0:43:40", "remaining_time": "1:49:29", "throughput": 4650.29, "total_tokens": 12184224} {"current_steps": 12100, "total_steps": 42420, "loss": 0.1149, "lr": 4.495436799973676e-05, "epoch": 5.704856199905705, "percentage": 28.52, "elapsed_time": "0:43:41", "remaining_time": "1:49:28", "throughput": 4650.33, "total_tokens": 12189600} {"current_steps": 12105, "total_steps": 42420, "loss": 0.1094, "lr": 4.494816975410313e-05, "epoch": 5.707213578500707, "percentage": 28.54, "elapsed_time": "0:43:42", "remaining_time": "1:49:26", "throughput": 4650.37, "total_tokens": 12194208} {"current_steps": 12110, "total_steps": 42420, "loss": 0.0919, "lr": 4.494196813158307e-05, "epoch": 5.70957095709571, "percentage": 28.55, "elapsed_time": "0:43:43", "remaining_time": "1:49:25", "throughput": 4650.38, "total_tokens": 12198368} {"current_steps": 12115, "total_steps": 42420, "loss": 0.3229, "lr": 4.4935763133226393e-05, "epoch": 5.711928335690712, "percentage": 28.56, "elapsed_time": "0:43:44", "remaining_time": "1:49:23", "throughput": 4650.38, "total_tokens": 12202816} {"current_steps": 12120, "total_steps": 42420, "loss": 0.1405, "lr": 4.4929554760083516e-05, "epoch": 5.714285714285714, "percentage": 28.57, "elapsed_time": "0:43:45", "remaining_time": "1:49:22", "throughput": 4650.41, "total_tokens": 12207456} {"current_steps": 12125, "total_steps": 42420, "loss": 0.1398, "lr": 4.492334301320539e-05, "epoch": 5.716643092880717, "percentage": 28.58, "elapsed_time": "0:43:46", "remaining_time": "1:49:21", "throughput": 4650.47, "total_tokens": 12212224} {"current_steps": 12130, "total_steps": 42420, "loss": 0.1366, "lr": 4.491712789364358e-05, "epoch": 5.719000471475719, "percentage": 28.6, "elapsed_time": "0:43:47", "remaining_time": "1:49:20", "throughput": 4650.47, "total_tokens": 12217056} {"current_steps": 12135, "total_steps": 42420, "loss": 0.1265, "lr": 4.491090940245018e-05, "epoch": 5.721357850070722, "percentage": 28.61, "elapsed_time": "0:43:48", "remaining_time": "1:49:18", "throughput": 4650.48, "total_tokens": 12221696} {"current_steps": 12140, "total_steps": 42420, "loss": 0.1636, "lr": 4.49046875406779e-05, "epoch": 5.723715228665724, "percentage": 28.62, "elapsed_time": "0:43:49", "remaining_time": "1:49:17", "throughput": 4650.5, "total_tokens": 12227040} {"current_steps": 12145, "total_steps": 42420, "loss": 0.1397, "lr": 4.489846230937998e-05, "epoch": 5.726072607260726, "percentage": 28.63, "elapsed_time": "0:43:50", "remaining_time": "1:49:16", "throughput": 4650.48, "total_tokens": 12231360} {"current_steps": 12150, "total_steps": 42420, "loss": 0.1745, "lr": 4.489223370961025e-05, "epoch": 5.728429985855728, "percentage": 28.64, "elapsed_time": "0:43:51", "remaining_time": "1:49:15", "throughput": 4650.59, "total_tokens": 12236768} {"current_steps": 12155, "total_steps": 42420, "loss": 0.0955, "lr": 4.48860017424231e-05, "epoch": 5.73078736445073, "percentage": 28.65, "elapsed_time": "0:43:52", "remaining_time": "1:49:13", "throughput": 4650.63, "total_tokens": 12241120} {"current_steps": 12160, "total_steps": 42420, "loss": 0.1094, "lr": 4.4879766408873494e-05, "epoch": 5.733144743045733, "percentage": 28.67, "elapsed_time": "0:43:53", "remaining_time": "1:49:12", "throughput": 4650.63, "total_tokens": 12245664} {"current_steps": 12165, "total_steps": 42420, "loss": 0.2817, "lr": 4.487352771001698e-05, "epoch": 5.735502121640735, "percentage": 28.68, "elapsed_time": "0:43:54", "remaining_time": "1:49:11", "throughput": 4650.71, "total_tokens": 12250336} {"current_steps": 12170, "total_steps": 42420, "loss": 0.153, "lr": 4.486728564690966e-05, "epoch": 5.7378595002357375, "percentage": 28.69, "elapsed_time": "0:43:55", "remaining_time": "1:49:09", "throughput": 4650.73, "total_tokens": 12255168} {"current_steps": 12175, "total_steps": 42420, "loss": 0.2676, "lr": 4.48610402206082e-05, "epoch": 5.74021687883074, "percentage": 28.7, "elapsed_time": "0:43:56", "remaining_time": "1:49:08", "throughput": 4650.79, "total_tokens": 12260544} {"current_steps": 12180, "total_steps": 42420, "loss": 0.1299, "lr": 4.4854791432169855e-05, "epoch": 5.742574257425742, "percentage": 28.71, "elapsed_time": "0:43:57", "remaining_time": "1:49:07", "throughput": 4650.79, "total_tokens": 12264512} {"current_steps": 12185, "total_steps": 42420, "loss": 0.0815, "lr": 4.4848539282652444e-05, "epoch": 5.744931636020745, "percentage": 28.72, "elapsed_time": "0:43:58", "remaining_time": "1:49:06", "throughput": 4650.92, "total_tokens": 12269856} {"current_steps": 12190, "total_steps": 42420, "loss": 0.0942, "lr": 4.484228377311433e-05, "epoch": 5.747289014615747, "percentage": 28.74, "elapsed_time": "0:43:59", "remaining_time": "1:49:05", "throughput": 4651.07, "total_tokens": 12275744} {"current_steps": 12195, "total_steps": 42420, "loss": 0.0595, "lr": 4.483602490461448e-05, "epoch": 5.7496463932107496, "percentage": 28.75, "elapsed_time": "0:44:00", "remaining_time": "1:49:04", "throughput": 4651.12, "total_tokens": 12280672} {"current_steps": 12200, "total_steps": 42420, "loss": 0.3436, "lr": 4.482976267821241e-05, "epoch": 5.752003771805752, "percentage": 28.76, "elapsed_time": "0:44:01", "remaining_time": "1:49:03", "throughput": 4651.19, "total_tokens": 12286464} {"current_steps": 12205, "total_steps": 42420, "loss": 0.3628, "lr": 4.482349709496821e-05, "epoch": 5.754361150400754, "percentage": 28.77, "elapsed_time": "0:44:02", "remaining_time": "1:49:02", "throughput": 4651.3, "total_tokens": 12291712} {"current_steps": 12210, "total_steps": 42420, "loss": 0.0552, "lr": 4.481722815594254e-05, "epoch": 5.756718528995757, "percentage": 28.78, "elapsed_time": "0:44:03", "remaining_time": "1:49:00", "throughput": 4651.35, "total_tokens": 12296288} {"current_steps": 12215, "total_steps": 42420, "loss": 0.1413, "lr": 4.481095586219661e-05, "epoch": 5.759075907590759, "percentage": 28.8, "elapsed_time": "0:44:04", "remaining_time": "1:48:59", "throughput": 4651.41, "total_tokens": 12301856} {"current_steps": 12220, "total_steps": 42420, "loss": 0.3117, "lr": 4.480468021479223e-05, "epoch": 5.761433286185762, "percentage": 28.81, "elapsed_time": "0:44:05", "remaining_time": "1:48:58", "throughput": 4651.39, "total_tokens": 12306528} {"current_steps": 12225, "total_steps": 42420, "loss": 0.247, "lr": 4.479840121479175e-05, "epoch": 5.763790664780764, "percentage": 28.82, "elapsed_time": "0:44:06", "remaining_time": "1:48:57", "throughput": 4651.44, "total_tokens": 12311584} {"current_steps": 12230, "total_steps": 42420, "loss": 0.1281, "lr": 4.4792118863258104e-05, "epoch": 5.766148043375766, "percentage": 28.83, "elapsed_time": "0:44:07", "remaining_time": "1:48:56", "throughput": 4651.46, "total_tokens": 12316000} {"current_steps": 12235, "total_steps": 42420, "loss": 0.258, "lr": 4.478583316125479e-05, "epoch": 5.768505421970769, "percentage": 28.84, "elapsed_time": "0:44:08", "remaining_time": "1:48:54", "throughput": 4651.54, "total_tokens": 12321248} {"current_steps": 12240, "total_steps": 42420, "loss": 0.0435, "lr": 4.477954410984586e-05, "epoch": 5.770862800565771, "percentage": 28.85, "elapsed_time": "0:44:09", "remaining_time": "1:48:53", "throughput": 4651.58, "total_tokens": 12326272} {"current_steps": 12245, "total_steps": 42420, "loss": 0.0428, "lr": 4.4773251710095956e-05, "epoch": 5.773220179160774, "percentage": 28.87, "elapsed_time": "0:44:11", "remaining_time": "1:48:53", "throughput": 4651.72, "total_tokens": 12333472} {"current_steps": 12250, "total_steps": 42420, "loss": 0.2882, "lr": 4.4766955963070265e-05, "epoch": 5.775577557755776, "percentage": 28.88, "elapsed_time": "0:44:12", "remaining_time": "1:48:52", "throughput": 4651.84, "total_tokens": 12338848} {"current_steps": 12255, "total_steps": 42420, "loss": 0.2198, "lr": 4.476065686983455e-05, "epoch": 5.777934936350778, "percentage": 28.89, "elapsed_time": "0:44:13", "remaining_time": "1:48:51", "throughput": 4651.97, "total_tokens": 12344992} {"current_steps": 12260, "total_steps": 42420, "loss": 0.1109, "lr": 4.4754354431455145e-05, "epoch": 5.780292314945781, "percentage": 28.9, "elapsed_time": "0:44:14", "remaining_time": "1:48:51", "throughput": 4652.07, "total_tokens": 12350976} {"current_steps": 12265, "total_steps": 42420, "loss": 0.1791, "lr": 4.474804864899895e-05, "epoch": 5.782649693540782, "percentage": 28.91, "elapsed_time": "0:44:15", "remaining_time": "1:48:49", "throughput": 4652.15, "total_tokens": 12355776} {"current_steps": 12270, "total_steps": 42420, "loss": 0.0463, "lr": 4.474173952353342e-05, "epoch": 5.785007072135785, "percentage": 28.93, "elapsed_time": "0:44:16", "remaining_time": "1:48:48", "throughput": 4652.24, "total_tokens": 12360864} {"current_steps": 12275, "total_steps": 42420, "loss": 0.1661, "lr": 4.473542705612658e-05, "epoch": 5.787364450730787, "percentage": 28.94, "elapsed_time": "0:44:17", "remaining_time": "1:48:47", "throughput": 4652.27, "total_tokens": 12365472} {"current_steps": 12280, "total_steps": 42420, "loss": 0.0439, "lr": 4.4729111247847026e-05, "epoch": 5.7897218293257895, "percentage": 28.95, "elapsed_time": "0:44:18", "remaining_time": "1:48:45", "throughput": 4652.23, "total_tokens": 12369280} {"current_steps": 12285, "total_steps": 42420, "loss": 0.1447, "lr": 4.472279209976393e-05, "epoch": 5.792079207920792, "percentage": 28.96, "elapsed_time": "0:44:19", "remaining_time": "1:48:44", "throughput": 4652.24, "total_tokens": 12373600} {"current_steps": 12290, "total_steps": 42420, "loss": 0.074, "lr": 4.4716469612946996e-05, "epoch": 5.794436586515794, "percentage": 28.97, "elapsed_time": "0:44:20", "remaining_time": "1:48:42", "throughput": 4652.19, "total_tokens": 12377440} {"current_steps": 12295, "total_steps": 42420, "loss": 0.0253, "lr": 4.471014378846652e-05, "epoch": 5.796793965110797, "percentage": 28.98, "elapsed_time": "0:44:21", "remaining_time": "1:48:41", "throughput": 4652.31, "total_tokens": 12382688} {"current_steps": 12300, "total_steps": 42420, "loss": 0.1954, "lr": 4.470381462739337e-05, "epoch": 5.799151343705799, "percentage": 29.0, "elapsed_time": "0:44:22", "remaining_time": "1:48:40", "throughput": 4652.31, "total_tokens": 12387104} {"current_steps": 12305, "total_steps": 42420, "loss": 0.212, "lr": 4.469748213079895e-05, "epoch": 5.8015087223008015, "percentage": 29.01, "elapsed_time": "0:44:23", "remaining_time": "1:48:38", "throughput": 4652.38, "total_tokens": 12391968} {"current_steps": 12310, "total_steps": 42420, "loss": 0.1005, "lr": 4.469114629975525e-05, "epoch": 5.803866100895804, "percentage": 29.02, "elapsed_time": "0:44:24", "remaining_time": "1:48:38", "throughput": 4652.52, "total_tokens": 12398496} {"current_steps": 12315, "total_steps": 42420, "loss": 0.251, "lr": 4.468480713533481e-05, "epoch": 5.806223479490806, "percentage": 29.03, "elapsed_time": "0:44:26", "remaining_time": "1:48:37", "throughput": 4652.65, "total_tokens": 12404128} {"current_steps": 12320, "total_steps": 42420, "loss": 0.0742, "lr": 4.467846463861077e-05, "epoch": 5.808580858085809, "percentage": 29.04, "elapsed_time": "0:44:27", "remaining_time": "1:48:36", "throughput": 4652.75, "total_tokens": 12408960} {"current_steps": 12325, "total_steps": 42420, "loss": 0.085, "lr": 4.467211881065677e-05, "epoch": 5.810938236680811, "percentage": 29.05, "elapsed_time": "0:44:27", "remaining_time": "1:48:34", "throughput": 4652.77, "total_tokens": 12413440} {"current_steps": 12330, "total_steps": 42420, "loss": 0.1935, "lr": 4.466576965254708e-05, "epoch": 5.8132956152758135, "percentage": 29.07, "elapsed_time": "0:44:28", "remaining_time": "1:48:33", "throughput": 4652.71, "total_tokens": 12417376} {"current_steps": 12335, "total_steps": 42420, "loss": 0.1096, "lr": 4.4659417165356486e-05, "epoch": 5.815652993870816, "percentage": 29.08, "elapsed_time": "0:44:29", "remaining_time": "1:48:32", "throughput": 4652.78, "total_tokens": 12422784} {"current_steps": 12340, "total_steps": 42420, "loss": 0.0786, "lr": 4.465306135016037e-05, "epoch": 5.818010372465818, "percentage": 29.09, "elapsed_time": "0:44:31", "remaining_time": "1:48:30", "throughput": 4652.85, "total_tokens": 12427936} {"current_steps": 12345, "total_steps": 42420, "loss": 0.0804, "lr": 4.464670220803466e-05, "epoch": 5.820367751060821, "percentage": 29.1, "elapsed_time": "0:44:32", "remaining_time": "1:48:29", "throughput": 4652.93, "total_tokens": 12432928} {"current_steps": 12350, "total_steps": 42420, "loss": 0.0729, "lr": 4.464033974005584e-05, "epoch": 5.822725129655822, "percentage": 29.11, "elapsed_time": "0:44:33", "remaining_time": "1:48:28", "throughput": 4653.05, "total_tokens": 12438176} {"current_steps": 12355, "total_steps": 42420, "loss": 0.1781, "lr": 4.463397394730098e-05, "epoch": 5.825082508250825, "percentage": 29.13, "elapsed_time": "0:44:34", "remaining_time": "1:48:27", "throughput": 4653.14, "total_tokens": 12443616} {"current_steps": 12360, "total_steps": 42420, "loss": 0.3124, "lr": 4.462760483084769e-05, "epoch": 5.827439886845827, "percentage": 29.14, "elapsed_time": "0:44:35", "remaining_time": "1:48:26", "throughput": 4653.2, "total_tokens": 12448416} {"current_steps": 12365, "total_steps": 42420, "loss": 0.0538, "lr": 4.462123239177417e-05, "epoch": 5.829797265440829, "percentage": 29.15, "elapsed_time": "0:44:36", "remaining_time": "1:48:25", "throughput": 4653.3, "total_tokens": 12453856} {"current_steps": 12370, "total_steps": 42420, "loss": 0.1577, "lr": 4.461485663115915e-05, "epoch": 5.832154644035832, "percentage": 29.16, "elapsed_time": "0:44:37", "remaining_time": "1:48:23", "throughput": 4653.34, "total_tokens": 12458016} {"current_steps": 12375, "total_steps": 42420, "loss": 0.147, "lr": 4.460847755008195e-05, "epoch": 5.834512022630834, "percentage": 29.17, "elapsed_time": "0:44:38", "remaining_time": "1:48:22", "throughput": 4653.45, "total_tokens": 12463744} {"current_steps": 12380, "total_steps": 42420, "loss": 0.2012, "lr": 4.4602095149622425e-05, "epoch": 5.836869401225837, "percentage": 29.18, "elapsed_time": "0:44:39", "remaining_time": "1:48:21", "throughput": 4653.55, "total_tokens": 12468672} {"current_steps": 12385, "total_steps": 42420, "loss": 0.2239, "lr": 4.4595709430861024e-05, "epoch": 5.839226779820839, "percentage": 29.2, "elapsed_time": "0:44:40", "remaining_time": "1:48:19", "throughput": 4653.57, "total_tokens": 12472736} {"current_steps": 12390, "total_steps": 42420, "loss": 0.1129, "lr": 4.458932039487872e-05, "epoch": 5.841584158415841, "percentage": 29.21, "elapsed_time": "0:44:41", "remaining_time": "1:48:18", "throughput": 4653.56, "total_tokens": 12476768} {"current_steps": 12395, "total_steps": 42420, "loss": 0.1006, "lr": 4.458292804275709e-05, "epoch": 5.843941537010844, "percentage": 29.22, "elapsed_time": "0:44:42", "remaining_time": "1:48:17", "throughput": 4653.66, "total_tokens": 12482048} {"current_steps": 12400, "total_steps": 42420, "loss": 0.2291, "lr": 4.457653237557824e-05, "epoch": 5.846298915605846, "percentage": 29.23, "elapsed_time": "0:44:43", "remaining_time": "1:48:16", "throughput": 4653.8, "total_tokens": 12488096} {"current_steps": 12405, "total_steps": 42420, "loss": 0.1775, "lr": 4.457013339442485e-05, "epoch": 5.848656294200849, "percentage": 29.24, "elapsed_time": "0:44:44", "remaining_time": "1:48:15", "throughput": 4653.91, "total_tokens": 12493504} {"current_steps": 12410, "total_steps": 42420, "loss": 0.1385, "lr": 4.456373110038016e-05, "epoch": 5.851013672795851, "percentage": 29.26, "elapsed_time": "0:44:45", "remaining_time": "1:48:14", "throughput": 4653.95, "total_tokens": 12498208} {"current_steps": 12415, "total_steps": 42420, "loss": 0.1246, "lr": 4.455732549452797e-05, "epoch": 5.8533710513908535, "percentage": 29.27, "elapsed_time": "0:44:46", "remaining_time": "1:48:12", "throughput": 4654.01, "total_tokens": 12502656} {"current_steps": 12420, "total_steps": 42420, "loss": 0.0645, "lr": 4.455091657795263e-05, "epoch": 5.855728429985856, "percentage": 29.28, "elapsed_time": "0:44:47", "remaining_time": "1:48:11", "throughput": 4653.96, "total_tokens": 12506688} {"current_steps": 12425, "total_steps": 42420, "loss": 0.1547, "lr": 4.4544504351739076e-05, "epoch": 5.858085808580858, "percentage": 29.29, "elapsed_time": "0:44:48", "remaining_time": "1:48:09", "throughput": 4654.06, "total_tokens": 12511744} {"current_steps": 12430, "total_steps": 42420, "loss": 0.1955, "lr": 4.453808881697278e-05, "epoch": 5.860443187175861, "percentage": 29.3, "elapsed_time": "0:44:49", "remaining_time": "1:48:08", "throughput": 4654.09, "total_tokens": 12516032} {"current_steps": 12435, "total_steps": 42420, "loss": 0.1858, "lr": 4.453166997473978e-05, "epoch": 5.862800565770863, "percentage": 29.31, "elapsed_time": "0:44:50", "remaining_time": "1:48:07", "throughput": 4654.16, "total_tokens": 12520736} {"current_steps": 12440, "total_steps": 42420, "loss": 0.171, "lr": 4.452524782612669e-05, "epoch": 5.8651579443658655, "percentage": 29.33, "elapsed_time": "0:44:51", "remaining_time": "1:48:06", "throughput": 4654.18, "total_tokens": 12525920} {"current_steps": 12445, "total_steps": 42420, "loss": 0.0859, "lr": 4.451882237222066e-05, "epoch": 5.867515322960868, "percentage": 29.34, "elapsed_time": "0:44:52", "remaining_time": "1:48:04", "throughput": 4654.24, "total_tokens": 12530432} {"current_steps": 12450, "total_steps": 42420, "loss": 0.0888, "lr": 4.451239361410941e-05, "epoch": 5.86987270155587, "percentage": 29.35, "elapsed_time": "0:44:53", "remaining_time": "1:48:03", "throughput": 4654.34, "total_tokens": 12535904} {"current_steps": 12455, "total_steps": 42420, "loss": 0.0981, "lr": 4.4505961552881224e-05, "epoch": 5.872230080150873, "percentage": 29.36, "elapsed_time": "0:44:54", "remaining_time": "1:48:02", "throughput": 4654.41, "total_tokens": 12540800} {"current_steps": 12460, "total_steps": 42420, "loss": 0.2575, "lr": 4.449952618962494e-05, "epoch": 5.874587458745875, "percentage": 29.37, "elapsed_time": "0:44:55", "remaining_time": "1:48:01", "throughput": 4654.46, "total_tokens": 12546304} {"current_steps": 12465, "total_steps": 42420, "loss": 0.147, "lr": 4.4493087525429954e-05, "epoch": 5.876944837340877, "percentage": 29.38, "elapsed_time": "0:44:56", "remaining_time": "1:48:00", "throughput": 4654.56, "total_tokens": 12551680} {"current_steps": 12470, "total_steps": 42420, "loss": 0.0786, "lr": 4.448664556138623e-05, "epoch": 5.879302215935879, "percentage": 29.4, "elapsed_time": "0:44:57", "remaining_time": "1:47:58", "throughput": 4654.6, "total_tokens": 12555936} {"current_steps": 12475, "total_steps": 42420, "loss": 0.0707, "lr": 4.448020029858427e-05, "epoch": 5.881659594530881, "percentage": 29.41, "elapsed_time": "0:44:58", "remaining_time": "1:47:57", "throughput": 4654.62, "total_tokens": 12560512} {"current_steps": 12480, "total_steps": 42420, "loss": 0.1565, "lr": 4.447375173811516e-05, "epoch": 5.884016973125884, "percentage": 29.42, "elapsed_time": "0:44:59", "remaining_time": "1:47:56", "throughput": 4654.68, "total_tokens": 12565056} {"current_steps": 12485, "total_steps": 42420, "loss": 0.0963, "lr": 4.446729988107052e-05, "epoch": 5.886374351720886, "percentage": 29.43, "elapsed_time": "0:45:00", "remaining_time": "1:47:54", "throughput": 4654.73, "total_tokens": 12569344} {"current_steps": 12490, "total_steps": 42420, "loss": 0.0401, "lr": 4.446084472854255e-05, "epoch": 5.888731730315889, "percentage": 29.44, "elapsed_time": "0:45:01", "remaining_time": "1:47:53", "throughput": 4654.73, "total_tokens": 12574112} {"current_steps": 12495, "total_steps": 42420, "loss": 0.0841, "lr": 4.4454386281623995e-05, "epoch": 5.891089108910891, "percentage": 29.46, "elapsed_time": "0:45:02", "remaining_time": "1:47:51", "throughput": 4654.78, "total_tokens": 12578656} {"current_steps": 12500, "total_steps": 42420, "loss": 0.1735, "lr": 4.4447924541408156e-05, "epoch": 5.893446487505893, "percentage": 29.47, "elapsed_time": "0:45:03", "remaining_time": "1:47:52", "throughput": 4654.95, "total_tokens": 12586784} {"current_steps": 12505, "total_steps": 42420, "loss": 0.2458, "lr": 4.44414595089889e-05, "epoch": 5.895803866100896, "percentage": 29.48, "elapsed_time": "0:45:04", "remaining_time": "1:47:50", "throughput": 4654.93, "total_tokens": 12591200} {"current_steps": 12510, "total_steps": 42420, "loss": 0.1242, "lr": 4.443499118546065e-05, "epoch": 5.898161244695898, "percentage": 29.49, "elapsed_time": "0:45:05", "remaining_time": "1:47:49", "throughput": 4654.94, "total_tokens": 12595808} {"current_steps": 12515, "total_steps": 42420, "loss": 0.0953, "lr": 4.4428519571918376e-05, "epoch": 5.900518623290901, "percentage": 29.5, "elapsed_time": "0:45:06", "remaining_time": "1:47:48", "throughput": 4654.9, "total_tokens": 12600288} {"current_steps": 12520, "total_steps": 42420, "loss": 0.2164, "lr": 4.4422044669457616e-05, "epoch": 5.902876001885903, "percentage": 29.51, "elapsed_time": "0:45:07", "remaining_time": "1:47:46", "throughput": 4654.95, "total_tokens": 12605120} {"current_steps": 12525, "total_steps": 42420, "loss": 0.1288, "lr": 4.441556647917446e-05, "epoch": 5.905233380480905, "percentage": 29.53, "elapsed_time": "0:45:09", "remaining_time": "1:47:46", "throughput": 4655.01, "total_tokens": 12610624} {"current_steps": 12530, "total_steps": 42420, "loss": 0.0514, "lr": 4.4409085002165565e-05, "epoch": 5.907590759075908, "percentage": 29.54, "elapsed_time": "0:45:10", "remaining_time": "1:47:44", "throughput": 4655.07, "total_tokens": 12615392} {"current_steps": 12535, "total_steps": 42420, "loss": 0.1798, "lr": 4.440260023952811e-05, "epoch": 5.90994813767091, "percentage": 29.55, "elapsed_time": "0:45:11", "remaining_time": "1:47:43", "throughput": 4655.13, "total_tokens": 12621216} {"current_steps": 12540, "total_steps": 42420, "loss": 0.0959, "lr": 4.439611219235989e-05, "epoch": 5.912305516265913, "percentage": 29.56, "elapsed_time": "0:45:12", "remaining_time": "1:47:42", "throughput": 4655.18, "total_tokens": 12625824} {"current_steps": 12545, "total_steps": 42420, "loss": 0.2497, "lr": 4.43896208617592e-05, "epoch": 5.914662894860915, "percentage": 29.57, "elapsed_time": "0:45:13", "remaining_time": "1:47:41", "throughput": 4655.26, "total_tokens": 12630752} {"current_steps": 12550, "total_steps": 42420, "loss": 0.2289, "lr": 4.43831262488249e-05, "epoch": 5.9170202734559165, "percentage": 29.59, "elapsed_time": "0:45:14", "remaining_time": "1:47:40", "throughput": 4655.45, "total_tokens": 12636928} {"current_steps": 12555, "total_steps": 42420, "loss": 0.0815, "lr": 4.4376628354656444e-05, "epoch": 5.919377652050919, "percentage": 29.6, "elapsed_time": "0:45:15", "remaining_time": "1:47:39", "throughput": 4655.57, "total_tokens": 12642880} {"current_steps": 12560, "total_steps": 42420, "loss": 0.0692, "lr": 4.4370127180353804e-05, "epoch": 5.921735030645921, "percentage": 29.61, "elapsed_time": "0:45:16", "remaining_time": "1:47:38", "throughput": 4655.6, "total_tokens": 12647264} {"current_steps": 12565, "total_steps": 42420, "loss": 0.223, "lr": 4.4363622727017517e-05, "epoch": 5.924092409240924, "percentage": 29.62, "elapsed_time": "0:45:17", "remaining_time": "1:47:36", "throughput": 4655.61, "total_tokens": 12651776} {"current_steps": 12570, "total_steps": 42420, "loss": 0.1385, "lr": 4.435711499574867e-05, "epoch": 5.926449787835926, "percentage": 29.63, "elapsed_time": "0:45:18", "remaining_time": "1:47:35", "throughput": 4655.59, "total_tokens": 12655616} {"current_steps": 12575, "total_steps": 42420, "loss": 0.1834, "lr": 4.435060398764893e-05, "epoch": 5.9288071664309285, "percentage": 29.64, "elapsed_time": "0:45:19", "remaining_time": "1:47:33", "throughput": 4655.55, "total_tokens": 12660000} {"current_steps": 12580, "total_steps": 42420, "loss": 0.0607, "lr": 4.434408970382049e-05, "epoch": 5.931164545025931, "percentage": 29.66, "elapsed_time": "0:45:20", "remaining_time": "1:47:32", "throughput": 4655.57, "total_tokens": 12664352} {"current_steps": 12585, "total_steps": 42420, "loss": 0.1268, "lr": 4.4337572145366104e-05, "epoch": 5.933521923620933, "percentage": 29.67, "elapsed_time": "0:45:21", "remaining_time": "1:47:31", "throughput": 4655.65, "total_tokens": 12669728} {"current_steps": 12590, "total_steps": 42420, "loss": 0.1004, "lr": 4.433105131338909e-05, "epoch": 5.935879302215936, "percentage": 29.68, "elapsed_time": "0:45:22", "remaining_time": "1:47:30", "throughput": 4655.7, "total_tokens": 12674720} {"current_steps": 12595, "total_steps": 42420, "loss": 0.1385, "lr": 4.4324527208993304e-05, "epoch": 5.938236680810938, "percentage": 29.69, "elapsed_time": "0:45:23", "remaining_time": "1:47:28", "throughput": 4655.76, "total_tokens": 12679328} {"current_steps": 12600, "total_steps": 42420, "loss": 0.1142, "lr": 4.431799983328317e-05, "epoch": 5.9405940594059405, "percentage": 29.7, "elapsed_time": "0:45:24", "remaining_time": "1:47:27", "throughput": 4655.82, "total_tokens": 12684000} {"current_steps": 12605, "total_steps": 42420, "loss": 0.1173, "lr": 4.431146918736368e-05, "epoch": 5.942951438000943, "percentage": 29.71, "elapsed_time": "0:45:25", "remaining_time": "1:47:26", "throughput": 4655.9, "total_tokens": 12688896} {"current_steps": 12610, "total_steps": 42420, "loss": 0.0963, "lr": 4.430493527234034e-05, "epoch": 5.945308816595945, "percentage": 29.73, "elapsed_time": "0:45:26", "remaining_time": "1:47:25", "throughput": 4655.96, "total_tokens": 12693952} {"current_steps": 12615, "total_steps": 42420, "loss": 0.129, "lr": 4.4298398089319235e-05, "epoch": 5.947666195190948, "percentage": 29.74, "elapsed_time": "0:45:27", "remaining_time": "1:47:24", "throughput": 4656.04, "total_tokens": 12699104} {"current_steps": 12620, "total_steps": 42420, "loss": 0.3446, "lr": 4.429185763940701e-05, "epoch": 5.95002357378595, "percentage": 29.75, "elapsed_time": "0:45:28", "remaining_time": "1:47:23", "throughput": 4656.14, "total_tokens": 12704896} {"current_steps": 12625, "total_steps": 42420, "loss": 0.1462, "lr": 4.428531392371083e-05, "epoch": 5.9523809523809526, "percentage": 29.76, "elapsed_time": "0:45:29", "remaining_time": "1:47:21", "throughput": 4656.15, "total_tokens": 12709216} {"current_steps": 12630, "total_steps": 42420, "loss": 0.2191, "lr": 4.427876694333846e-05, "epoch": 5.954738330975955, "percentage": 29.77, "elapsed_time": "0:45:30", "remaining_time": "1:47:20", "throughput": 4656.19, "total_tokens": 12714016} {"current_steps": 12635, "total_steps": 42420, "loss": 0.1354, "lr": 4.427221669939817e-05, "epoch": 5.957095709570957, "percentage": 29.79, "elapsed_time": "0:45:31", "remaining_time": "1:47:19", "throughput": 4656.18, "total_tokens": 12718400} {"current_steps": 12640, "total_steps": 42420, "loss": 0.1481, "lr": 4.426566319299883e-05, "epoch": 5.95945308816596, "percentage": 29.8, "elapsed_time": "0:45:32", "remaining_time": "1:47:17", "throughput": 4656.18, "total_tokens": 12723392} {"current_steps": 12645, "total_steps": 42420, "loss": 0.136, "lr": 4.4259106425249816e-05, "epoch": 5.961810466760962, "percentage": 29.81, "elapsed_time": "0:45:33", "remaining_time": "1:47:16", "throughput": 4656.27, "total_tokens": 12728544} {"current_steps": 12650, "total_steps": 42420, "loss": 0.1844, "lr": 4.4252546397261084e-05, "epoch": 5.964167845355965, "percentage": 29.82, "elapsed_time": "0:45:34", "remaining_time": "1:47:15", "throughput": 4656.32, "total_tokens": 12733504} {"current_steps": 12655, "total_steps": 42420, "loss": 0.0644, "lr": 4.424598311014314e-05, "epoch": 5.966525223950967, "percentage": 29.83, "elapsed_time": "0:45:35", "remaining_time": "1:47:14", "throughput": 4656.41, "total_tokens": 12738240} {"current_steps": 12660, "total_steps": 42420, "loss": 0.1359, "lr": 4.423941656500704e-05, "epoch": 5.968882602545969, "percentage": 29.84, "elapsed_time": "0:45:36", "remaining_time": "1:47:13", "throughput": 4656.56, "total_tokens": 12743936} {"current_steps": 12665, "total_steps": 42420, "loss": 0.0866, "lr": 4.423284676296437e-05, "epoch": 5.971239981140971, "percentage": 29.86, "elapsed_time": "0:45:37", "remaining_time": "1:47:12", "throughput": 4656.63, "total_tokens": 12749056} {"current_steps": 12670, "total_steps": 42420, "loss": 0.175, "lr": 4.42262737051273e-05, "epoch": 5.973597359735973, "percentage": 29.87, "elapsed_time": "0:45:38", "remaining_time": "1:47:11", "throughput": 4656.71, "total_tokens": 12754080} {"current_steps": 12675, "total_steps": 42420, "loss": 0.1696, "lr": 4.421969739260854e-05, "epoch": 5.975954738330976, "percentage": 29.88, "elapsed_time": "0:45:40", "remaining_time": "1:47:10", "throughput": 4656.87, "total_tokens": 12760352} {"current_steps": 12680, "total_steps": 42420, "loss": 0.2081, "lr": 4.4213117826521345e-05, "epoch": 5.978312116925978, "percentage": 29.89, "elapsed_time": "0:45:40", "remaining_time": "1:47:08", "throughput": 4656.8, "total_tokens": 12764224} {"current_steps": 12685, "total_steps": 42420, "loss": 0.3048, "lr": 4.420653500797952e-05, "epoch": 5.9806694955209805, "percentage": 29.9, "elapsed_time": "0:45:41", "remaining_time": "1:47:07", "throughput": 4656.78, "total_tokens": 12768192} {"current_steps": 12690, "total_steps": 42420, "loss": 0.0805, "lr": 4.419994893809743e-05, "epoch": 5.983026874115983, "percentage": 29.92, "elapsed_time": "0:45:42", "remaining_time": "1:47:06", "throughput": 4656.85, "total_tokens": 12773216} {"current_steps": 12695, "total_steps": 42420, "loss": 0.114, "lr": 4.419335961798997e-05, "epoch": 5.985384252710985, "percentage": 29.93, "elapsed_time": "0:45:43", "remaining_time": "1:47:04", "throughput": 4656.96, "total_tokens": 12778432} {"current_steps": 12700, "total_steps": 42420, "loss": 0.1266, "lr": 4.4186767048772616e-05, "epoch": 5.987741631305988, "percentage": 29.94, "elapsed_time": "0:45:44", "remaining_time": "1:47:03", "throughput": 4657.02, "total_tokens": 12782976} {"current_steps": 12705, "total_steps": 42420, "loss": 0.1614, "lr": 4.4180171231561374e-05, "epoch": 5.99009900990099, "percentage": 29.95, "elapsed_time": "0:45:46", "remaining_time": "1:47:03", "throughput": 4657.14, "total_tokens": 12789728} {"current_steps": 12710, "total_steps": 42420, "loss": 0.1225, "lr": 4.417357216747281e-05, "epoch": 5.9924563884959925, "percentage": 29.96, "elapsed_time": "0:45:47", "remaining_time": "1:47:03", "throughput": 4657.18, "total_tokens": 12797312} {"current_steps": 12715, "total_steps": 42420, "loss": 0.042, "lr": 4.416696985762402e-05, "epoch": 5.994813767090995, "percentage": 29.97, "elapsed_time": "0:45:48", "remaining_time": "1:47:01", "throughput": 4657.22, "total_tokens": 12801600} {"current_steps": 12720, "total_steps": 42420, "loss": 0.1121, "lr": 4.4160364303132675e-05, "epoch": 5.997171145685997, "percentage": 29.99, "elapsed_time": "0:45:50", "remaining_time": "1:47:01", "throughput": 4657.42, "total_tokens": 12808512} {"current_steps": 12725, "total_steps": 42420, "loss": 0.1657, "lr": 4.4153755505116966e-05, "epoch": 5.999528524281, "percentage": 30.0, "elapsed_time": "0:45:51", "remaining_time": "1:46:59", "throughput": 4657.48, "total_tokens": 12812960} {"current_steps": 12726, "total_steps": 42420, "eval_loss": 0.15432102978229523, "epoch": 6.0, "percentage": 30.0, "elapsed_time": "0:46:06", "remaining_time": "1:47:35", "throughput": 4631.93, "total_tokens": 12814080} {"current_steps": 12730, "total_steps": 42420, "loss": 0.098, "lr": 4.414714346469567e-05, "epoch": 6.001885902876002, "percentage": 30.01, "elapsed_time": "0:46:08", "remaining_time": "1:47:38", "throughput": 4629.16, "total_tokens": 12818112} {"current_steps": 12735, "total_steps": 42420, "loss": 0.0913, "lr": 4.414052818298809e-05, "epoch": 6.0042432814710045, "percentage": 30.02, "elapsed_time": "0:46:10", "remaining_time": "1:47:37", "throughput": 4629.34, "total_tokens": 12824096} {"current_steps": 12740, "total_steps": 42420, "loss": 0.0273, "lr": 4.413390966111407e-05, "epoch": 6.006600660066007, "percentage": 30.03, "elapsed_time": "0:46:11", "remaining_time": "1:47:36", "throughput": 4629.38, "total_tokens": 12829024} {"current_steps": 12745, "total_steps": 42420, "loss": 0.1024, "lr": 4.412728790019403e-05, "epoch": 6.008958038661009, "percentage": 30.04, "elapsed_time": "0:46:12", "remaining_time": "1:47:34", "throughput": 4629.51, "total_tokens": 12834464} {"current_steps": 12750, "total_steps": 42420, "loss": 0.1407, "lr": 4.4120662901348896e-05, "epoch": 6.011315417256012, "percentage": 30.06, "elapsed_time": "0:46:13", "remaining_time": "1:47:33", "throughput": 4629.38, "total_tokens": 12838144} {"current_steps": 12755, "total_steps": 42420, "loss": 0.0272, "lr": 4.411403466570019e-05, "epoch": 6.013672795851014, "percentage": 30.07, "elapsed_time": "0:46:14", "remaining_time": "1:47:32", "throughput": 4629.46, "total_tokens": 12843296} {"current_steps": 12760, "total_steps": 42420, "loss": 0.1595, "lr": 4.410740319436996e-05, "epoch": 6.016030174446016, "percentage": 30.08, "elapsed_time": "0:46:15", "remaining_time": "1:47:31", "throughput": 4629.56, "total_tokens": 12848640} {"current_steps": 12765, "total_steps": 42420, "loss": 0.0854, "lr": 4.410076848848078e-05, "epoch": 6.018387553041018, "percentage": 30.09, "elapsed_time": "0:46:16", "remaining_time": "1:47:29", "throughput": 4629.56, "total_tokens": 12853184} {"current_steps": 12770, "total_steps": 42420, "loss": 0.15, "lr": 4.409413054915582e-05, "epoch": 6.02074493163602, "percentage": 30.1, "elapsed_time": "0:46:17", "remaining_time": "1:47:28", "throughput": 4629.53, "total_tokens": 12857760} {"current_steps": 12775, "total_steps": 42420, "loss": 0.2163, "lr": 4.4087489377518754e-05, "epoch": 6.023102310231023, "percentage": 30.12, "elapsed_time": "0:46:18", "remaining_time": "1:47:27", "throughput": 4629.62, "total_tokens": 12862816} {"current_steps": 12780, "total_steps": 42420, "loss": 0.1597, "lr": 4.4080844974693816e-05, "epoch": 6.025459688826025, "percentage": 30.13, "elapsed_time": "0:46:19", "remaining_time": "1:47:25", "throughput": 4629.62, "total_tokens": 12866912} {"current_steps": 12785, "total_steps": 42420, "loss": 0.0446, "lr": 4.407419734180581e-05, "epoch": 6.027817067421028, "percentage": 30.14, "elapsed_time": "0:46:20", "remaining_time": "1:47:24", "throughput": 4629.71, "total_tokens": 12872480} {"current_steps": 12790, "total_steps": 42420, "loss": 0.1838, "lr": 4.4067546479980046e-05, "epoch": 6.03017444601603, "percentage": 30.15, "elapsed_time": "0:46:21", "remaining_time": "1:47:23", "throughput": 4629.82, "total_tokens": 12878240} {"current_steps": 12795, "total_steps": 42420, "loss": 0.1158, "lr": 4.4060892390342416e-05, "epoch": 6.032531824611032, "percentage": 30.16, "elapsed_time": "0:46:22", "remaining_time": "1:47:23", "throughput": 4629.97, "total_tokens": 12885088} {"current_steps": 12800, "total_steps": 42420, "loss": 0.1024, "lr": 4.405423507401934e-05, "epoch": 6.034889203206035, "percentage": 30.17, "elapsed_time": "0:46:24", "remaining_time": "1:47:22", "throughput": 4630.02, "total_tokens": 12890080} {"current_steps": 12805, "total_steps": 42420, "loss": 0.2422, "lr": 4.4047574532137794e-05, "epoch": 6.037246581801037, "percentage": 30.19, "elapsed_time": "0:46:25", "remaining_time": "1:47:21", "throughput": 4630.11, "total_tokens": 12895616} {"current_steps": 12810, "total_steps": 42420, "loss": 0.2492, "lr": 4.4040910765825284e-05, "epoch": 6.03960396039604, "percentage": 30.2, "elapsed_time": "0:46:26", "remaining_time": "1:47:20", "throughput": 4630.22, "total_tokens": 12901152} {"current_steps": 12815, "total_steps": 42420, "loss": 0.0547, "lr": 4.403424377620987e-05, "epoch": 6.041961338991042, "percentage": 30.21, "elapsed_time": "0:46:27", "remaining_time": "1:47:19", "throughput": 4630.28, "total_tokens": 12906720} {"current_steps": 12820, "total_steps": 42420, "loss": 0.0611, "lr": 4.402757356442018e-05, "epoch": 6.044318717586044, "percentage": 30.22, "elapsed_time": "0:46:28", "remaining_time": "1:47:18", "throughput": 4630.29, "total_tokens": 12911168} {"current_steps": 12825, "total_steps": 42420, "loss": 0.1251, "lr": 4.4020900131585346e-05, "epoch": 6.046676096181047, "percentage": 30.23, "elapsed_time": "0:46:29", "remaining_time": "1:47:16", "throughput": 4630.14, "total_tokens": 12915168} {"current_steps": 12830, "total_steps": 42420, "loss": 0.0928, "lr": 4.401422347883508e-05, "epoch": 6.049033474776049, "percentage": 30.25, "elapsed_time": "0:46:30", "remaining_time": "1:47:15", "throughput": 4630.2, "total_tokens": 12920032} {"current_steps": 12835, "total_steps": 42420, "loss": 0.0503, "lr": 4.4007543607299624e-05, "epoch": 6.051390853371052, "percentage": 30.26, "elapsed_time": "0:46:31", "remaining_time": "1:47:14", "throughput": 4630.19, "total_tokens": 12924736} {"current_steps": 12840, "total_steps": 42420, "loss": 0.1641, "lr": 4.4000860518109764e-05, "epoch": 6.053748231966054, "percentage": 30.27, "elapsed_time": "0:46:32", "remaining_time": "1:47:13", "throughput": 4630.3, "total_tokens": 12930624} {"current_steps": 12845, "total_steps": 42420, "loss": 0.0121, "lr": 4.3994174212396834e-05, "epoch": 6.0561056105610565, "percentage": 30.28, "elapsed_time": "0:46:33", "remaining_time": "1:47:12", "throughput": 4630.3, "total_tokens": 12935104} {"current_steps": 12850, "total_steps": 42420, "loss": 0.2282, "lr": 4.3987484691292714e-05, "epoch": 6.058462989156059, "percentage": 30.29, "elapsed_time": "0:46:34", "remaining_time": "1:47:10", "throughput": 4630.36, "total_tokens": 12939840} {"current_steps": 12855, "total_steps": 42420, "loss": 0.0962, "lr": 4.398079195592982e-05, "epoch": 6.060820367751061, "percentage": 30.3, "elapsed_time": "0:46:35", "remaining_time": "1:47:09", "throughput": 4630.45, "total_tokens": 12945280} {"current_steps": 12860, "total_steps": 42420, "loss": 0.0321, "lr": 4.397409600744112e-05, "epoch": 6.063177746346063, "percentage": 30.32, "elapsed_time": "0:46:36", "remaining_time": "1:47:08", "throughput": 4630.48, "total_tokens": 12950208} {"current_steps": 12865, "total_steps": 42420, "loss": 0.1206, "lr": 4.396739684696014e-05, "epoch": 6.065535124941065, "percentage": 30.33, "elapsed_time": "0:46:37", "remaining_time": "1:47:07", "throughput": 4630.54, "total_tokens": 12954976} {"current_steps": 12870, "total_steps": 42420, "loss": 0.2169, "lr": 4.396069447562092e-05, "epoch": 6.067892503536068, "percentage": 30.34, "elapsed_time": "0:46:38", "remaining_time": "1:47:06", "throughput": 4630.65, "total_tokens": 12960032} {"current_steps": 12875, "total_steps": 42420, "loss": 0.0576, "lr": 4.395398889455805e-05, "epoch": 6.07024988213107, "percentage": 30.35, "elapsed_time": "0:46:39", "remaining_time": "1:47:04", "throughput": 4630.74, "total_tokens": 12965280} {"current_steps": 12880, "total_steps": 42420, "loss": 0.2139, "lr": 4.394728010490669e-05, "epoch": 6.072607260726072, "percentage": 30.36, "elapsed_time": "0:46:41", "remaining_time": "1:47:04", "throughput": 4630.89, "total_tokens": 12971552} {"current_steps": 12885, "total_steps": 42420, "loss": 0.1114, "lr": 4.394056810780251e-05, "epoch": 6.074964639321075, "percentage": 30.37, "elapsed_time": "0:46:42", "remaining_time": "1:47:03", "throughput": 4630.97, "total_tokens": 12976736} {"current_steps": 12890, "total_steps": 42420, "loss": 0.135, "lr": 4.3933852904381745e-05, "epoch": 6.077322017916077, "percentage": 30.39, "elapsed_time": "0:46:43", "remaining_time": "1:47:01", "throughput": 4631.06, "total_tokens": 12981408} {"current_steps": 12895, "total_steps": 42420, "loss": 0.0579, "lr": 4.392713449578115e-05, "epoch": 6.07967939651108, "percentage": 30.4, "elapsed_time": "0:46:44", "remaining_time": "1:47:00", "throughput": 4631.12, "total_tokens": 12985728} {"current_steps": 12900, "total_steps": 42420, "loss": 0.2383, "lr": 4.3920412883138065e-05, "epoch": 6.082036775106082, "percentage": 30.41, "elapsed_time": "0:46:45", "remaining_time": "1:46:59", "throughput": 4631.19, "total_tokens": 12991136} {"current_steps": 12905, "total_steps": 42420, "loss": 0.1067, "lr": 4.391368806759032e-05, "epoch": 6.084394153701084, "percentage": 30.42, "elapsed_time": "0:46:46", "remaining_time": "1:46:57", "throughput": 4631.19, "total_tokens": 12995424} {"current_steps": 12910, "total_steps": 42420, "loss": 0.1425, "lr": 4.390696005027633e-05, "epoch": 6.086751532296087, "percentage": 30.43, "elapsed_time": "0:46:47", "remaining_time": "1:46:56", "throughput": 4631.27, "total_tokens": 13000512} {"current_steps": 12915, "total_steps": 42420, "loss": 0.2896, "lr": 4.390022883233502e-05, "epoch": 6.089108910891089, "percentage": 30.45, "elapsed_time": "0:46:48", "remaining_time": "1:46:55", "throughput": 4631.32, "total_tokens": 13005216} {"current_steps": 12920, "total_steps": 42420, "loss": 0.2032, "lr": 4.3893494414905875e-05, "epoch": 6.091466289486092, "percentage": 30.46, "elapsed_time": "0:46:49", "remaining_time": "1:46:54", "throughput": 4631.48, "total_tokens": 13011552} {"current_steps": 12925, "total_steps": 42420, "loss": 0.207, "lr": 4.388675679912892e-05, "epoch": 6.093823668081094, "percentage": 30.47, "elapsed_time": "0:46:50", "remaining_time": "1:46:53", "throughput": 4631.59, "total_tokens": 13016960} {"current_steps": 12930, "total_steps": 42420, "loss": 0.2386, "lr": 4.388001598614472e-05, "epoch": 6.096181046676096, "percentage": 30.48, "elapsed_time": "0:46:51", "remaining_time": "1:46:52", "throughput": 4631.7, "total_tokens": 13022176} {"current_steps": 12935, "total_steps": 42420, "loss": 0.0853, "lr": 4.3873271977094375e-05, "epoch": 6.098538425271099, "percentage": 30.49, "elapsed_time": "0:46:52", "remaining_time": "1:46:51", "throughput": 4631.77, "total_tokens": 13027104} {"current_steps": 12940, "total_steps": 42420, "loss": 0.0788, "lr": 4.3866524773119534e-05, "epoch": 6.100895803866101, "percentage": 30.5, "elapsed_time": "0:46:53", "remaining_time": "1:46:49", "throughput": 4631.8, "total_tokens": 13031904} {"current_steps": 12945, "total_steps": 42420, "loss": 0.1412, "lr": 4.3859774375362385e-05, "epoch": 6.103253182461104, "percentage": 30.52, "elapsed_time": "0:46:54", "remaining_time": "1:46:48", "throughput": 4631.92, "total_tokens": 13037632} {"current_steps": 12950, "total_steps": 42420, "loss": 0.19, "lr": 4.385302078496566e-05, "epoch": 6.105610561056106, "percentage": 30.53, "elapsed_time": "0:46:55", "remaining_time": "1:46:47", "throughput": 4631.89, "total_tokens": 13042720} {"current_steps": 12955, "total_steps": 42420, "loss": 0.0755, "lr": 4.384626400307261e-05, "epoch": 6.107967939651108, "percentage": 30.54, "elapsed_time": "0:46:56", "remaining_time": "1:46:46", "throughput": 4631.87, "total_tokens": 13047136} {"current_steps": 12960, "total_steps": 42420, "loss": 0.1118, "lr": 4.383950403082707e-05, "epoch": 6.11032531824611, "percentage": 30.55, "elapsed_time": "0:46:57", "remaining_time": "1:46:45", "throughput": 4631.95, "total_tokens": 13052032} {"current_steps": 12965, "total_steps": 42420, "loss": 0.2095, "lr": 4.383274086937336e-05, "epoch": 6.112682696841112, "percentage": 30.56, "elapsed_time": "0:46:59", "remaining_time": "1:46:44", "throughput": 4632.11, "total_tokens": 13058848} {"current_steps": 12970, "total_steps": 42420, "loss": 0.2395, "lr": 4.3825974519856394e-05, "epoch": 6.115040075436115, "percentage": 30.58, "elapsed_time": "0:47:00", "remaining_time": "1:46:43", "throughput": 4632.07, "total_tokens": 13062848} {"current_steps": 12975, "total_steps": 42420, "loss": 0.1237, "lr": 4.381920498342158e-05, "epoch": 6.117397454031117, "percentage": 30.59, "elapsed_time": "0:47:01", "remaining_time": "1:46:42", "throughput": 4632.19, "total_tokens": 13068352} {"current_steps": 12980, "total_steps": 42420, "loss": 0.1405, "lr": 4.38124322612149e-05, "epoch": 6.1197548326261195, "percentage": 30.6, "elapsed_time": "0:47:02", "remaining_time": "1:46:41", "throughput": 4632.24, "total_tokens": 13073536} {"current_steps": 12985, "total_steps": 42420, "loss": 0.0775, "lr": 4.380565635438286e-05, "epoch": 6.122112211221122, "percentage": 30.61, "elapsed_time": "0:47:03", "remaining_time": "1:46:40", "throughput": 4632.38, "total_tokens": 13080352} {"current_steps": 12990, "total_steps": 42420, "loss": 0.0685, "lr": 4.379887726407249e-05, "epoch": 6.124469589816124, "percentage": 30.62, "elapsed_time": "0:47:04", "remaining_time": "1:46:39", "throughput": 4632.5, "total_tokens": 13085984} {"current_steps": 12995, "total_steps": 42420, "loss": 0.1366, "lr": 4.379209499143139e-05, "epoch": 6.126826968411127, "percentage": 30.63, "elapsed_time": "0:47:05", "remaining_time": "1:46:38", "throughput": 4632.56, "total_tokens": 13090560} {"current_steps": 13000, "total_steps": 42420, "loss": 0.0538, "lr": 4.3785309537607685e-05, "epoch": 6.129184347006129, "percentage": 30.65, "elapsed_time": "0:47:06", "remaining_time": "1:46:37", "throughput": 4632.65, "total_tokens": 13096192} {"current_steps": 13005, "total_steps": 42420, "loss": 0.0311, "lr": 4.3778520903750025e-05, "epoch": 6.1315417256011315, "percentage": 30.66, "elapsed_time": "0:47:07", "remaining_time": "1:46:36", "throughput": 4632.71, "total_tokens": 13101280} {"current_steps": 13010, "total_steps": 42420, "loss": 0.187, "lr": 4.377172909100762e-05, "epoch": 6.133899104196134, "percentage": 30.67, "elapsed_time": "0:47:09", "remaining_time": "1:46:35", "throughput": 4632.83, "total_tokens": 13108000} {"current_steps": 13015, "total_steps": 42420, "loss": 0.2459, "lr": 4.3764934100530205e-05, "epoch": 6.136256482791136, "percentage": 30.68, "elapsed_time": "0:47:10", "remaining_time": "1:46:35", "throughput": 4632.97, "total_tokens": 13113888} {"current_steps": 13020, "total_steps": 42420, "loss": 0.1027, "lr": 4.375813593346806e-05, "epoch": 6.138613861386139, "percentage": 30.69, "elapsed_time": "0:47:11", "remaining_time": "1:46:34", "throughput": 4633.04, "total_tokens": 13119552} {"current_steps": 13025, "total_steps": 42420, "loss": 0.1803, "lr": 4.3751334590971996e-05, "epoch": 6.140971239981141, "percentage": 30.7, "elapsed_time": "0:47:12", "remaining_time": "1:46:33", "throughput": 4633.13, "total_tokens": 13125280} {"current_steps": 13030, "total_steps": 42420, "loss": 0.2035, "lr": 4.374453007419336e-05, "epoch": 6.1433286185761435, "percentage": 30.72, "elapsed_time": "0:47:13", "remaining_time": "1:46:32", "throughput": 4633.17, "total_tokens": 13129856} {"current_steps": 13035, "total_steps": 42420, "loss": 0.1973, "lr": 4.373772238428405e-05, "epoch": 6.145685997171146, "percentage": 30.73, "elapsed_time": "0:47:14", "remaining_time": "1:46:30", "throughput": 4633.25, "total_tokens": 13134944} {"current_steps": 13040, "total_steps": 42420, "loss": 0.1713, "lr": 4.3730911522396486e-05, "epoch": 6.148043375766148, "percentage": 30.74, "elapsed_time": "0:47:15", "remaining_time": "1:46:29", "throughput": 4633.25, "total_tokens": 13139264} {"current_steps": 13045, "total_steps": 42420, "loss": 0.1492, "lr": 4.3724097489683634e-05, "epoch": 6.150400754361151, "percentage": 30.75, "elapsed_time": "0:47:17", "remaining_time": "1:46:28", "throughput": 4633.36, "total_tokens": 13144896} {"current_steps": 13050, "total_steps": 42420, "loss": 0.069, "lr": 4.3717280287299e-05, "epoch": 6.152758132956153, "percentage": 30.76, "elapsed_time": "0:47:18", "remaining_time": "1:46:27", "throughput": 4633.45, "total_tokens": 13150112} {"current_steps": 13055, "total_steps": 42420, "loss": 0.0492, "lr": 4.3710459916396606e-05, "epoch": 6.1551155115511555, "percentage": 30.78, "elapsed_time": "0:47:19", "remaining_time": "1:46:26", "throughput": 4633.53, "total_tokens": 13155008} {"current_steps": 13060, "total_steps": 42420, "loss": 0.1673, "lr": 4.3703636378131044e-05, "epoch": 6.157472890146157, "percentage": 30.79, "elapsed_time": "0:47:20", "remaining_time": "1:46:24", "throughput": 4633.56, "total_tokens": 13159584} {"current_steps": 13065, "total_steps": 42420, "loss": 0.2096, "lr": 4.36968096736574e-05, "epoch": 6.1598302687411595, "percentage": 30.8, "elapsed_time": "0:47:21", "remaining_time": "1:46:23", "throughput": 4633.7, "total_tokens": 13165536} {"current_steps": 13070, "total_steps": 42420, "loss": 0.0502, "lr": 4.3689979804131344e-05, "epoch": 6.162187647336162, "percentage": 30.81, "elapsed_time": "0:47:22", "remaining_time": "1:46:22", "throughput": 4633.79, "total_tokens": 13170336} {"current_steps": 13075, "total_steps": 42420, "loss": 0.0843, "lr": 4.368314677070904e-05, "epoch": 6.164545025931164, "percentage": 30.82, "elapsed_time": "0:47:23", "remaining_time": "1:46:21", "throughput": 4633.91, "total_tokens": 13175808} {"current_steps": 13080, "total_steps": 42420, "loss": 0.2368, "lr": 4.3676310574547206e-05, "epoch": 6.166902404526167, "percentage": 30.83, "elapsed_time": "0:47:24", "remaining_time": "1:46:19", "throughput": 4633.95, "total_tokens": 13180000} {"current_steps": 13085, "total_steps": 42420, "loss": 0.0844, "lr": 4.3669471216803104e-05, "epoch": 6.169259783121169, "percentage": 30.85, "elapsed_time": "0:47:25", "remaining_time": "1:46:18", "throughput": 4634.07, "total_tokens": 13185664} {"current_steps": 13090, "total_steps": 42420, "loss": 0.2274, "lr": 4.366262869863451e-05, "epoch": 6.1716171617161715, "percentage": 30.86, "elapsed_time": "0:47:26", "remaining_time": "1:46:17", "throughput": 4634.01, "total_tokens": 13189600} {"current_steps": 13095, "total_steps": 42420, "loss": 0.0676, "lr": 4.365578302119976e-05, "epoch": 6.173974540311174, "percentage": 30.87, "elapsed_time": "0:47:27", "remaining_time": "1:46:15", "throughput": 4634.02, "total_tokens": 13193824} {"current_steps": 13100, "total_steps": 42420, "loss": 0.1641, "lr": 4.3648934185657683e-05, "epoch": 6.176331918906176, "percentage": 30.88, "elapsed_time": "0:47:28", "remaining_time": "1:46:14", "throughput": 4634.13, "total_tokens": 13198432} {"current_steps": 13105, "total_steps": 42420, "loss": 0.0432, "lr": 4.364208219316771e-05, "epoch": 6.178689297501179, "percentage": 30.89, "elapsed_time": "0:47:28", "remaining_time": "1:46:12", "throughput": 4634.11, "total_tokens": 13202240} {"current_steps": 13110, "total_steps": 42420, "loss": 0.0811, "lr": 4.363522704488974e-05, "epoch": 6.181046676096181, "percentage": 30.91, "elapsed_time": "0:47:30", "remaining_time": "1:46:12", "throughput": 4634.25, "total_tokens": 13208480} {"current_steps": 13115, "total_steps": 42420, "loss": 0.1869, "lr": 4.362836874198423e-05, "epoch": 6.1834040546911835, "percentage": 30.92, "elapsed_time": "0:47:31", "remaining_time": "1:46:10", "throughput": 4634.32, "total_tokens": 13213344} {"current_steps": 13120, "total_steps": 42420, "loss": 0.1657, "lr": 4.362150728561219e-05, "epoch": 6.185761433286186, "percentage": 30.93, "elapsed_time": "0:47:32", "remaining_time": "1:46:10", "throughput": 4634.45, "total_tokens": 13219200} {"current_steps": 13125, "total_steps": 42420, "loss": 0.1473, "lr": 4.361464267693514e-05, "epoch": 6.188118811881188, "percentage": 30.94, "elapsed_time": "0:47:33", "remaining_time": "1:46:09", "throughput": 4634.55, "total_tokens": 13224832} {"current_steps": 13130, "total_steps": 42420, "loss": 0.0462, "lr": 4.360777491711515e-05, "epoch": 6.190476190476191, "percentage": 30.95, "elapsed_time": "0:47:34", "remaining_time": "1:46:08", "throughput": 4634.68, "total_tokens": 13230272} {"current_steps": 13135, "total_steps": 42420, "loss": 0.0543, "lr": 4.36009040073148e-05, "epoch": 6.192833569071193, "percentage": 30.96, "elapsed_time": "0:47:35", "remaining_time": "1:46:07", "throughput": 4634.71, "total_tokens": 13235616} {"current_steps": 13140, "total_steps": 42420, "loss": 0.1022, "lr": 4.359402994869723e-05, "epoch": 6.1951909476661955, "percentage": 30.98, "elapsed_time": "0:47:36", "remaining_time": "1:46:05", "throughput": 4634.74, "total_tokens": 13239840} {"current_steps": 13145, "total_steps": 42420, "loss": 0.0454, "lr": 4.3587152742426096e-05, "epoch": 6.197548326261198, "percentage": 30.99, "elapsed_time": "0:47:37", "remaining_time": "1:46:04", "throughput": 4634.76, "total_tokens": 13244480} {"current_steps": 13150, "total_steps": 42420, "loss": 0.0729, "lr": 4.35802723896656e-05, "epoch": 6.1999057048562, "percentage": 31.0, "elapsed_time": "0:47:38", "remaining_time": "1:46:02", "throughput": 4634.8, "total_tokens": 13248800} {"current_steps": 13155, "total_steps": 42420, "loss": 0.1516, "lr": 4.357338889158046e-05, "epoch": 6.202263083451202, "percentage": 31.01, "elapsed_time": "0:47:39", "remaining_time": "1:46:01", "throughput": 4634.77, "total_tokens": 13253056} {"current_steps": 13160, "total_steps": 42420, "loss": 0.0388, "lr": 4.356650224933594e-05, "epoch": 6.204620462046204, "percentage": 31.02, "elapsed_time": "0:47:40", "remaining_time": "1:46:00", "throughput": 4634.8, "total_tokens": 13258016} {"current_steps": 13165, "total_steps": 42420, "loss": 0.1861, "lr": 4.355961246409783e-05, "epoch": 6.206977840641207, "percentage": 31.03, "elapsed_time": "0:47:41", "remaining_time": "1:45:59", "throughput": 4634.91, "total_tokens": 13263328} {"current_steps": 13170, "total_steps": 42420, "loss": 0.2372, "lr": 4.355271953703246e-05, "epoch": 6.209335219236209, "percentage": 31.05, "elapsed_time": "0:47:42", "remaining_time": "1:45:57", "throughput": 4634.81, "total_tokens": 13267040} {"current_steps": 13175, "total_steps": 42420, "loss": 0.1847, "lr": 4.354582346930667e-05, "epoch": 6.211692597831211, "percentage": 31.06, "elapsed_time": "0:47:43", "remaining_time": "1:45:56", "throughput": 4634.86, "total_tokens": 13271648} {"current_steps": 13180, "total_steps": 42420, "loss": 0.164, "lr": 4.353892426208787e-05, "epoch": 6.214049976426214, "percentage": 31.07, "elapsed_time": "0:47:44", "remaining_time": "1:45:54", "throughput": 4634.9, "total_tokens": 13276384} {"current_steps": 13185, "total_steps": 42420, "loss": 0.0901, "lr": 4.353202191654395e-05, "epoch": 6.216407355021216, "percentage": 31.08, "elapsed_time": "0:47:45", "remaining_time": "1:45:53", "throughput": 4634.97, "total_tokens": 13281120} {"current_steps": 13190, "total_steps": 42420, "loss": 0.0439, "lr": 4.352511643384338e-05, "epoch": 6.218764733616219, "percentage": 31.09, "elapsed_time": "0:47:46", "remaining_time": "1:45:52", "throughput": 4634.96, "total_tokens": 13285504} {"current_steps": 13195, "total_steps": 42420, "loss": 0.0674, "lr": 4.351820781515514e-05, "epoch": 6.221122112211221, "percentage": 31.11, "elapsed_time": "0:47:47", "remaining_time": "1:45:50", "throughput": 4635.04, "total_tokens": 13290048} {"current_steps": 13200, "total_steps": 42420, "loss": 0.2886, "lr": 4.351129606164873e-05, "epoch": 6.223479490806223, "percentage": 31.12, "elapsed_time": "0:47:48", "remaining_time": "1:45:49", "throughput": 4635.1, "total_tokens": 13294784} {"current_steps": 13205, "total_steps": 42420, "loss": 0.1274, "lr": 4.350438117449421e-05, "epoch": 6.225836869401226, "percentage": 31.13, "elapsed_time": "0:47:49", "remaining_time": "1:45:48", "throughput": 4635.18, "total_tokens": 13300064} {"current_steps": 13210, "total_steps": 42420, "loss": 0.2172, "lr": 4.349746315486214e-05, "epoch": 6.228194247996228, "percentage": 31.14, "elapsed_time": "0:47:50", "remaining_time": "1:45:46", "throughput": 4635.18, "total_tokens": 13304000} {"current_steps": 13215, "total_steps": 42420, "loss": 0.0512, "lr": 4.349054200392363e-05, "epoch": 6.230551626591231, "percentage": 31.15, "elapsed_time": "0:47:51", "remaining_time": "1:45:45", "throughput": 4635.26, "total_tokens": 13309696} {"current_steps": 13220, "total_steps": 42420, "loss": 0.1987, "lr": 4.3483617722850305e-05, "epoch": 6.232909005186233, "percentage": 31.16, "elapsed_time": "0:47:52", "remaining_time": "1:45:44", "throughput": 4635.29, "total_tokens": 13313952} {"current_steps": 13225, "total_steps": 42420, "loss": 0.1013, "lr": 4.347669031281434e-05, "epoch": 6.235266383781235, "percentage": 31.18, "elapsed_time": "0:47:53", "remaining_time": "1:45:43", "throughput": 4635.28, "total_tokens": 13318592} {"current_steps": 13230, "total_steps": 42420, "loss": 0.2251, "lr": 4.3469759774988414e-05, "epoch": 6.237623762376238, "percentage": 31.19, "elapsed_time": "0:47:54", "remaining_time": "1:45:41", "throughput": 4635.28, "total_tokens": 13322720} {"current_steps": 13235, "total_steps": 42420, "loss": 0.0614, "lr": 4.346282611054576e-05, "epoch": 6.23998114097124, "percentage": 31.2, "elapsed_time": "0:47:55", "remaining_time": "1:45:40", "throughput": 4635.43, "total_tokens": 13329344} {"current_steps": 13240, "total_steps": 42420, "loss": 0.1025, "lr": 4.3455889320660126e-05, "epoch": 6.242338519566243, "percentage": 31.21, "elapsed_time": "0:47:56", "remaining_time": "1:45:40", "throughput": 4635.55, "total_tokens": 13335136} {"current_steps": 13245, "total_steps": 42420, "loss": 0.1194, "lr": 4.344894940650579e-05, "epoch": 6.244695898161245, "percentage": 31.22, "elapsed_time": "0:47:57", "remaining_time": "1:45:39", "throughput": 4635.61, "total_tokens": 13340736} {"current_steps": 13250, "total_steps": 42420, "loss": 0.1394, "lr": 4.3442006369257574e-05, "epoch": 6.247053276756247, "percentage": 31.24, "elapsed_time": "0:47:59", "remaining_time": "1:45:38", "throughput": 4635.79, "total_tokens": 13347072} {"current_steps": 13255, "total_steps": 42420, "loss": 0.3412, "lr": 4.3435060210090806e-05, "epoch": 6.24941065535125, "percentage": 31.25, "elapsed_time": "0:48:00", "remaining_time": "1:45:37", "throughput": 4635.9, "total_tokens": 13352480} {"current_steps": 13260, "total_steps": 42420, "loss": 0.2391, "lr": 4.342811093018134e-05, "epoch": 6.251768033946251, "percentage": 31.26, "elapsed_time": "0:48:01", "remaining_time": "1:45:35", "throughput": 4635.92, "total_tokens": 13356768} {"current_steps": 13265, "total_steps": 42420, "loss": 0.0454, "lr": 4.34211585307056e-05, "epoch": 6.254125412541254, "percentage": 31.27, "elapsed_time": "0:48:02", "remaining_time": "1:45:34", "throughput": 4635.92, "total_tokens": 13360896} {"current_steps": 13270, "total_steps": 42420, "loss": 0.1915, "lr": 4.3414203012840494e-05, "epoch": 6.256482791136256, "percentage": 31.28, "elapsed_time": "0:48:03", "remaining_time": "1:45:33", "throughput": 4636.01, "total_tokens": 13366272} {"current_steps": 13275, "total_steps": 42420, "loss": 0.0949, "lr": 4.340724437776347e-05, "epoch": 6.258840169731259, "percentage": 31.29, "elapsed_time": "0:48:04", "remaining_time": "1:45:31", "throughput": 4636.02, "total_tokens": 13370464} {"current_steps": 13280, "total_steps": 42420, "loss": 0.1384, "lr": 4.34002826266525e-05, "epoch": 6.261197548326261, "percentage": 31.31, "elapsed_time": "0:48:05", "remaining_time": "1:45:30", "throughput": 4636.1, "total_tokens": 13375424} {"current_steps": 13285, "total_steps": 42420, "loss": 0.1233, "lr": 4.3393317760686114e-05, "epoch": 6.263554926921263, "percentage": 31.32, "elapsed_time": "0:48:06", "remaining_time": "1:45:29", "throughput": 4636.2, "total_tokens": 13380736} {"current_steps": 13290, "total_steps": 42420, "loss": 0.0814, "lr": 4.338634978104332e-05, "epoch": 6.265912305516266, "percentage": 31.33, "elapsed_time": "0:48:07", "remaining_time": "1:45:28", "throughput": 4636.24, "total_tokens": 13385088} {"current_steps": 13295, "total_steps": 42420, "loss": 0.1475, "lr": 4.337937868890371e-05, "epoch": 6.268269684111268, "percentage": 31.34, "elapsed_time": "0:48:08", "remaining_time": "1:45:26", "throughput": 4636.35, "total_tokens": 13390208} {"current_steps": 13300, "total_steps": 42420, "loss": 0.276, "lr": 4.3372404485447324e-05, "epoch": 6.270627062706271, "percentage": 31.35, "elapsed_time": "0:48:09", "remaining_time": "1:45:25", "throughput": 4636.44, "total_tokens": 13395488} {"current_steps": 13305, "total_steps": 42420, "loss": 0.1008, "lr": 4.3365427171854823e-05, "epoch": 6.272984441301273, "percentage": 31.36, "elapsed_time": "0:48:10", "remaining_time": "1:45:24", "throughput": 4636.54, "total_tokens": 13400608} {"current_steps": 13310, "total_steps": 42420, "loss": 0.2154, "lr": 4.335844674930733e-05, "epoch": 6.275341819896275, "percentage": 31.38, "elapsed_time": "0:48:11", "remaining_time": "1:45:23", "throughput": 4636.62, "total_tokens": 13406784} {"current_steps": 13315, "total_steps": 42420, "loss": 0.2446, "lr": 4.335146321898651e-05, "epoch": 6.277699198491278, "percentage": 31.39, "elapsed_time": "0:48:12", "remaining_time": "1:45:22", "throughput": 4636.73, "total_tokens": 13412032} {"current_steps": 13320, "total_steps": 42420, "loss": 0.138, "lr": 4.334447658207455e-05, "epoch": 6.28005657708628, "percentage": 31.4, "elapsed_time": "0:48:14", "remaining_time": "1:45:23", "throughput": 4636.9, "total_tokens": 13420768} {"current_steps": 13325, "total_steps": 42420, "loss": 0.139, "lr": 4.333748683975418e-05, "epoch": 6.282413955681283, "percentage": 31.41, "elapsed_time": "0:48:15", "remaining_time": "1:45:21", "throughput": 4636.84, "total_tokens": 13424768} {"current_steps": 13330, "total_steps": 42420, "loss": 0.1426, "lr": 4.3330493993208644e-05, "epoch": 6.284771334276285, "percentage": 31.42, "elapsed_time": "0:48:16", "remaining_time": "1:45:20", "throughput": 4636.81, "total_tokens": 13428800} {"current_steps": 13335, "total_steps": 42420, "loss": 0.1614, "lr": 4.33234980436217e-05, "epoch": 6.287128712871287, "percentage": 31.44, "elapsed_time": "0:48:17", "remaining_time": "1:45:18", "throughput": 4636.84, "total_tokens": 13433344} {"current_steps": 13340, "total_steps": 42420, "loss": 0.1867, "lr": 4.331649899217766e-05, "epoch": 6.28948609146629, "percentage": 31.45, "elapsed_time": "0:48:18", "remaining_time": "1:45:17", "throughput": 4636.93, "total_tokens": 13438272} {"current_steps": 13345, "total_steps": 42420, "loss": 0.0294, "lr": 4.3309496840061336e-05, "epoch": 6.291843470061292, "percentage": 31.46, "elapsed_time": "0:48:19", "remaining_time": "1:45:16", "throughput": 4637.01, "total_tokens": 13443104} {"current_steps": 13350, "total_steps": 42420, "loss": 0.0952, "lr": 4.330249158845807e-05, "epoch": 6.294200848656295, "percentage": 31.47, "elapsed_time": "0:48:20", "remaining_time": "1:45:15", "throughput": 4637.17, "total_tokens": 13449152} {"current_steps": 13355, "total_steps": 42420, "loss": 0.1473, "lr": 4.3295483238553744e-05, "epoch": 6.296558227251296, "percentage": 31.48, "elapsed_time": "0:48:21", "remaining_time": "1:45:14", "throughput": 4637.22, "total_tokens": 13454112} {"current_steps": 13360, "total_steps": 42420, "loss": 0.1615, "lr": 4.3288471791534743e-05, "epoch": 6.2989156058462985, "percentage": 31.49, "elapsed_time": "0:48:22", "remaining_time": "1:45:13", "throughput": 4637.28, "total_tokens": 13459424} {"current_steps": 13365, "total_steps": 42420, "loss": 0.0686, "lr": 4.3281457248587986e-05, "epoch": 6.301272984441301, "percentage": 31.51, "elapsed_time": "0:48:23", "remaining_time": "1:45:11", "throughput": 4637.37, "total_tokens": 13464160} {"current_steps": 13370, "total_steps": 42420, "loss": 0.1156, "lr": 4.327443961090092e-05, "epoch": 6.303630363036303, "percentage": 31.52, "elapsed_time": "0:48:24", "remaining_time": "1:45:10", "throughput": 4637.4, "total_tokens": 13468704} {"current_steps": 13375, "total_steps": 42420, "loss": 0.1974, "lr": 4.3267418879661504e-05, "epoch": 6.305987741631306, "percentage": 31.53, "elapsed_time": "0:48:25", "remaining_time": "1:45:09", "throughput": 4637.44, "total_tokens": 13473184} {"current_steps": 13380, "total_steps": 42420, "loss": 0.137, "lr": 4.326039505605824e-05, "epoch": 6.308345120226308, "percentage": 31.54, "elapsed_time": "0:48:26", "remaining_time": "1:45:07", "throughput": 4637.52, "total_tokens": 13477824} {"current_steps": 13385, "total_steps": 42420, "loss": 0.2264, "lr": 4.3253368141280136e-05, "epoch": 6.3107024988213105, "percentage": 31.55, "elapsed_time": "0:48:27", "remaining_time": "1:45:07", "throughput": 4637.69, "total_tokens": 13484288} {"current_steps": 13390, "total_steps": 42420, "loss": 0.0665, "lr": 4.324633813651674e-05, "epoch": 6.313059877416313, "percentage": 31.57, "elapsed_time": "0:48:28", "remaining_time": "1:45:05", "throughput": 4637.79, "total_tokens": 13489312} {"current_steps": 13395, "total_steps": 42420, "loss": 0.2132, "lr": 4.323930504295809e-05, "epoch": 6.315417256011315, "percentage": 31.58, "elapsed_time": "0:48:29", "remaining_time": "1:45:05", "throughput": 4637.81, "total_tokens": 13495040} {"current_steps": 13400, "total_steps": 42420, "loss": 0.0999, "lr": 4.323226886179479e-05, "epoch": 6.317774634606318, "percentage": 31.59, "elapsed_time": "0:48:30", "remaining_time": "1:45:03", "throughput": 4637.86, "total_tokens": 13499616} {"current_steps": 13405, "total_steps": 42420, "loss": 0.0503, "lr": 4.322522959421793e-05, "epoch": 6.32013201320132, "percentage": 31.6, "elapsed_time": "0:48:31", "remaining_time": "1:45:02", "throughput": 4637.81, "total_tokens": 13503616} {"current_steps": 13410, "total_steps": 42420, "loss": 0.0511, "lr": 4.321818724141915e-05, "epoch": 6.3224893917963225, "percentage": 31.61, "elapsed_time": "0:48:32", "remaining_time": "1:45:01", "throughput": 4637.92, "total_tokens": 13509440} {"current_steps": 13415, "total_steps": 42420, "loss": 0.1919, "lr": 4.3211141804590595e-05, "epoch": 6.324846770391325, "percentage": 31.62, "elapsed_time": "0:48:33", "remaining_time": "1:45:00", "throughput": 4638.02, "total_tokens": 13514752} {"current_steps": 13420, "total_steps": 42420, "loss": 0.0873, "lr": 4.3204093284924946e-05, "epoch": 6.327204148986327, "percentage": 31.64, "elapsed_time": "0:48:34", "remaining_time": "1:44:58", "throughput": 4638.09, "total_tokens": 13519360} {"current_steps": 13425, "total_steps": 42420, "loss": 0.1096, "lr": 4.3197041683615394e-05, "epoch": 6.32956152758133, "percentage": 31.65, "elapsed_time": "0:48:36", "remaining_time": "1:44:57", "throughput": 4638.19, "total_tokens": 13525120} {"current_steps": 13430, "total_steps": 42420, "loss": 0.0589, "lr": 4.318998700185565e-05, "epoch": 6.331918906176332, "percentage": 31.66, "elapsed_time": "0:48:37", "remaining_time": "1:44:56", "throughput": 4638.23, "total_tokens": 13530208} {"current_steps": 13435, "total_steps": 42420, "loss": 0.2136, "lr": 4.318292924083994e-05, "epoch": 6.3342762847713345, "percentage": 31.67, "elapsed_time": "0:48:38", "remaining_time": "1:44:55", "throughput": 4638.26, "total_tokens": 13535328} {"current_steps": 13440, "total_steps": 42420, "loss": 0.1415, "lr": 4.3175868401763055e-05, "epoch": 6.336633663366337, "percentage": 31.68, "elapsed_time": "0:48:39", "remaining_time": "1:44:54", "throughput": 4638.3, "total_tokens": 13539936} {"current_steps": 13445, "total_steps": 42420, "loss": 0.1027, "lr": 4.3168804485820257e-05, "epoch": 6.338991041961339, "percentage": 31.69, "elapsed_time": "0:48:40", "remaining_time": "1:44:53", "throughput": 4638.28, "total_tokens": 13544448} {"current_steps": 13450, "total_steps": 42420, "loss": 0.072, "lr": 4.316173749420734e-05, "epoch": 6.341348420556342, "percentage": 31.71, "elapsed_time": "0:48:41", "remaining_time": "1:44:52", "throughput": 4638.38, "total_tokens": 13550336} {"current_steps": 13455, "total_steps": 42420, "loss": 0.2402, "lr": 4.3154667428120645e-05, "epoch": 6.343705799151344, "percentage": 31.72, "elapsed_time": "0:48:42", "remaining_time": "1:44:51", "throughput": 4638.53, "total_tokens": 13556480} {"current_steps": 13460, "total_steps": 42420, "loss": 0.2835, "lr": 4.3147594288757e-05, "epoch": 6.346063177746346, "percentage": 31.73, "elapsed_time": "0:48:43", "remaining_time": "1:44:50", "throughput": 4638.63, "total_tokens": 13562752} {"current_steps": 13465, "total_steps": 42420, "loss": 0.1313, "lr": 4.314051807731376e-05, "epoch": 6.348420556341348, "percentage": 31.74, "elapsed_time": "0:48:44", "remaining_time": "1:44:49", "throughput": 4638.64, "total_tokens": 13566944} {"current_steps": 13470, "total_steps": 42420, "loss": 0.1627, "lr": 4.313343879498884e-05, "epoch": 6.3507779349363505, "percentage": 31.75, "elapsed_time": "0:48:45", "remaining_time": "1:44:47", "throughput": 4638.65, "total_tokens": 13571232} {"current_steps": 13475, "total_steps": 42420, "loss": 0.3316, "lr": 4.31263564429806e-05, "epoch": 6.353135313531353, "percentage": 31.77, "elapsed_time": "0:48:46", "remaining_time": "1:44:46", "throughput": 4638.76, "total_tokens": 13576544} {"current_steps": 13480, "total_steps": 42420, "loss": 0.0615, "lr": 4.3119271022487986e-05, "epoch": 6.355492692126355, "percentage": 31.78, "elapsed_time": "0:48:47", "remaining_time": "1:44:45", "throughput": 4638.77, "total_tokens": 13580800} {"current_steps": 13485, "total_steps": 42420, "loss": 0.2381, "lr": 4.311218253471044e-05, "epoch": 6.357850070721358, "percentage": 31.79, "elapsed_time": "0:48:48", "remaining_time": "1:44:44", "throughput": 4638.89, "total_tokens": 13587040} {"current_steps": 13490, "total_steps": 42420, "loss": 0.1173, "lr": 4.310509098084791e-05, "epoch": 6.36020744931636, "percentage": 31.8, "elapsed_time": "0:48:49", "remaining_time": "1:44:43", "throughput": 4638.9, "total_tokens": 13591424} {"current_steps": 13495, "total_steps": 42420, "loss": 0.0627, "lr": 4.309799636210089e-05, "epoch": 6.3625648279113625, "percentage": 31.81, "elapsed_time": "0:48:51", "remaining_time": "1:44:42", "throughput": 4639.02, "total_tokens": 13596992} {"current_steps": 13500, "total_steps": 42420, "loss": 0.0725, "lr": 4.3090898679670376e-05, "epoch": 6.364922206506365, "percentage": 31.82, "elapsed_time": "0:48:52", "remaining_time": "1:44:41", "throughput": 4639.11, "total_tokens": 13602144} {"current_steps": 13505, "total_steps": 42420, "loss": 0.0588, "lr": 4.3083797934757874e-05, "epoch": 6.367279585101367, "percentage": 31.84, "elapsed_time": "0:48:52", "remaining_time": "1:44:39", "throughput": 4639.15, "total_tokens": 13606528} {"current_steps": 13510, "total_steps": 42420, "loss": 0.0826, "lr": 4.307669412856543e-05, "epoch": 6.36963696369637, "percentage": 31.85, "elapsed_time": "0:48:53", "remaining_time": "1:44:38", "throughput": 4639.14, "total_tokens": 13610624} {"current_steps": 13515, "total_steps": 42420, "loss": 0.0506, "lr": 4.30695872622956e-05, "epoch": 6.371994342291372, "percentage": 31.86, "elapsed_time": "0:48:54", "remaining_time": "1:44:37", "throughput": 4639.27, "total_tokens": 13616256} {"current_steps": 13520, "total_steps": 42420, "loss": 0.1254, "lr": 4.306247733715145e-05, "epoch": 6.3743517208863745, "percentage": 31.87, "elapsed_time": "0:48:55", "remaining_time": "1:44:35", "throughput": 4639.33, "total_tokens": 13620832} {"current_steps": 13525, "total_steps": 42420, "loss": 0.0796, "lr": 4.3055364354336565e-05, "epoch": 6.376709099481377, "percentage": 31.88, "elapsed_time": "0:48:56", "remaining_time": "1:44:34", "throughput": 4639.37, "total_tokens": 13625664} {"current_steps": 13530, "total_steps": 42420, "loss": 0.1228, "lr": 4.3048248315055054e-05, "epoch": 6.379066478076379, "percentage": 31.9, "elapsed_time": "0:48:57", "remaining_time": "1:44:33", "throughput": 4639.45, "total_tokens": 13630592} {"current_steps": 13535, "total_steps": 42420, "loss": 0.1004, "lr": 4.304112922051155e-05, "epoch": 6.381423856671382, "percentage": 31.91, "elapsed_time": "0:48:58", "remaining_time": "1:44:31", "throughput": 4639.28, "total_tokens": 13634336} {"current_steps": 13540, "total_steps": 42420, "loss": 0.145, "lr": 4.30340070719112e-05, "epoch": 6.383781235266384, "percentage": 31.92, "elapsed_time": "0:48:59", "remaining_time": "1:44:30", "throughput": 4639.35, "total_tokens": 13639552} {"current_steps": 13545, "total_steps": 42420, "loss": 0.0723, "lr": 4.302688187045964e-05, "epoch": 6.3861386138613865, "percentage": 31.93, "elapsed_time": "0:49:01", "remaining_time": "1:44:29", "throughput": 4639.46, "total_tokens": 13645536} {"current_steps": 13550, "total_steps": 42420, "loss": 0.1025, "lr": 4.3019753617363056e-05, "epoch": 6.388495992456389, "percentage": 31.94, "elapsed_time": "0:49:02", "remaining_time": "1:44:28", "throughput": 4639.5, "total_tokens": 13650144} {"current_steps": 13555, "total_steps": 42420, "loss": 0.0368, "lr": 4.3012622313828156e-05, "epoch": 6.39085337105139, "percentage": 31.95, "elapsed_time": "0:49:03", "remaining_time": "1:44:27", "throughput": 4639.57, "total_tokens": 13655392} {"current_steps": 13560, "total_steps": 42420, "loss": 0.1528, "lr": 4.3005487961062126e-05, "epoch": 6.393210749646393, "percentage": 31.97, "elapsed_time": "0:49:04", "remaining_time": "1:44:26", "throughput": 4639.66, "total_tokens": 13660864} {"current_steps": 13565, "total_steps": 42420, "loss": 0.2331, "lr": 4.2998350560272696e-05, "epoch": 6.395568128241395, "percentage": 31.98, "elapsed_time": "0:49:05", "remaining_time": "1:44:25", "throughput": 4639.73, "total_tokens": 13665888} {"current_steps": 13570, "total_steps": 42420, "loss": 0.0902, "lr": 4.299121011266812e-05, "epoch": 6.397925506836398, "percentage": 31.99, "elapsed_time": "0:49:06", "remaining_time": "1:44:23", "throughput": 4639.73, "total_tokens": 13670112} {"current_steps": 13575, "total_steps": 42420, "loss": 0.3347, "lr": 4.2984066619457144e-05, "epoch": 6.4002828854314, "percentage": 32.0, "elapsed_time": "0:49:07", "remaining_time": "1:44:22", "throughput": 4639.74, "total_tokens": 13674464} {"current_steps": 13580, "total_steps": 42420, "loss": 0.2435, "lr": 4.297692008184904e-05, "epoch": 6.402640264026402, "percentage": 32.01, "elapsed_time": "0:49:08", "remaining_time": "1:44:21", "throughput": 4639.82, "total_tokens": 13679648} {"current_steps": 13585, "total_steps": 42420, "loss": 0.245, "lr": 4.2969770501053586e-05, "epoch": 6.404997642621405, "percentage": 32.02, "elapsed_time": "0:49:09", "remaining_time": "1:44:20", "throughput": 4639.83, "total_tokens": 13684320} {"current_steps": 13590, "total_steps": 42420, "loss": 0.2335, "lr": 4.296261787828111e-05, "epoch": 6.407355021216407, "percentage": 32.04, "elapsed_time": "0:49:10", "remaining_time": "1:44:18", "throughput": 4639.87, "total_tokens": 13688576} {"current_steps": 13595, "total_steps": 42420, "loss": 0.0962, "lr": 4.295546221474241e-05, "epoch": 6.40971239981141, "percentage": 32.05, "elapsed_time": "0:49:11", "remaining_time": "1:44:17", "throughput": 4639.96, "total_tokens": 13693760} {"current_steps": 13600, "total_steps": 42420, "loss": 0.0594, "lr": 4.294830351164883e-05, "epoch": 6.412069778406412, "percentage": 32.06, "elapsed_time": "0:49:12", "remaining_time": "1:44:16", "throughput": 4639.97, "total_tokens": 13698112} {"current_steps": 13605, "total_steps": 42420, "loss": 0.1269, "lr": 4.2941141770212195e-05, "epoch": 6.414427157001414, "percentage": 32.07, "elapsed_time": "0:49:13", "remaining_time": "1:44:14", "throughput": 4640.02, "total_tokens": 13702528} {"current_steps": 13610, "total_steps": 42420, "loss": 0.1064, "lr": 4.293397699164489e-05, "epoch": 6.416784535596417, "percentage": 32.08, "elapsed_time": "0:49:14", "remaining_time": "1:44:13", "throughput": 4640.06, "total_tokens": 13707520} {"current_steps": 13615, "total_steps": 42420, "loss": 0.1101, "lr": 4.292680917715978e-05, "epoch": 6.419141914191419, "percentage": 32.1, "elapsed_time": "0:49:15", "remaining_time": "1:44:12", "throughput": 4640.09, "total_tokens": 13712672} {"current_steps": 13620, "total_steps": 42420, "loss": 0.0678, "lr": 4.2919638327970255e-05, "epoch": 6.421499292786422, "percentage": 32.11, "elapsed_time": "0:49:16", "remaining_time": "1:44:11", "throughput": 4640.13, "total_tokens": 13717440} {"current_steps": 13625, "total_steps": 42420, "loss": 0.153, "lr": 4.291246444529023e-05, "epoch": 6.423856671381424, "percentage": 32.12, "elapsed_time": "0:49:17", "remaining_time": "1:44:09", "throughput": 4640.21, "total_tokens": 13722272} {"current_steps": 13630, "total_steps": 42420, "loss": 0.2145, "lr": 4.2905287530334106e-05, "epoch": 6.426214049976426, "percentage": 32.13, "elapsed_time": "0:49:18", "remaining_time": "1:44:08", "throughput": 4640.25, "total_tokens": 13727040} {"current_steps": 13635, "total_steps": 42420, "loss": 0.0688, "lr": 4.289810758431681e-05, "epoch": 6.428571428571429, "percentage": 32.14, "elapsed_time": "0:49:19", "remaining_time": "1:44:07", "throughput": 4640.31, "total_tokens": 13731872} {"current_steps": 13640, "total_steps": 42420, "loss": 0.1453, "lr": 4.28909246084538e-05, "epoch": 6.430928807166431, "percentage": 32.15, "elapsed_time": "0:49:20", "remaining_time": "1:44:06", "throughput": 4640.39, "total_tokens": 13737216} {"current_steps": 13645, "total_steps": 42420, "loss": 0.1064, "lr": 4.288373860396102e-05, "epoch": 6.433286185761434, "percentage": 32.17, "elapsed_time": "0:49:21", "remaining_time": "1:44:05", "throughput": 4640.4, "total_tokens": 13741888} {"current_steps": 13650, "total_steps": 42420, "loss": 0.2703, "lr": 4.2876549572054945e-05, "epoch": 6.435643564356436, "percentage": 32.18, "elapsed_time": "0:49:22", "remaining_time": "1:44:03", "throughput": 4640.44, "total_tokens": 13746944} {"current_steps": 13655, "total_steps": 42420, "loss": 0.1859, "lr": 4.286935751395256e-05, "epoch": 6.438000942951438, "percentage": 32.19, "elapsed_time": "0:49:23", "remaining_time": "1:44:02", "throughput": 4640.49, "total_tokens": 13752256} {"current_steps": 13660, "total_steps": 42420, "loss": 0.0688, "lr": 4.286216243087134e-05, "epoch": 6.44035832154644, "percentage": 32.2, "elapsed_time": "0:49:24", "remaining_time": "1:44:01", "throughput": 4640.6, "total_tokens": 13757888} {"current_steps": 13665, "total_steps": 42420, "loss": 0.1229, "lr": 4.2854964324029314e-05, "epoch": 6.442715700141442, "percentage": 32.21, "elapsed_time": "0:49:25", "remaining_time": "1:44:00", "throughput": 4640.67, "total_tokens": 13762880} {"current_steps": 13670, "total_steps": 42420, "loss": 0.197, "lr": 4.284776319464498e-05, "epoch": 6.445073078736445, "percentage": 32.23, "elapsed_time": "0:49:26", "remaining_time": "1:43:59", "throughput": 4640.79, "total_tokens": 13768448} {"current_steps": 13675, "total_steps": 42420, "loss": 0.1819, "lr": 4.284055904393738e-05, "epoch": 6.447430457331447, "percentage": 32.24, "elapsed_time": "0:49:27", "remaining_time": "1:43:58", "throughput": 4640.78, "total_tokens": 13772448} {"current_steps": 13680, "total_steps": 42420, "loss": 0.0291, "lr": 4.283335187312604e-05, "epoch": 6.4497878359264496, "percentage": 32.25, "elapsed_time": "0:49:28", "remaining_time": "1:43:57", "throughput": 4640.86, "total_tokens": 13777632} {"current_steps": 13685, "total_steps": 42420, "loss": 0.1056, "lr": 4.282614168343103e-05, "epoch": 6.452145214521452, "percentage": 32.26, "elapsed_time": "0:49:29", "remaining_time": "1:43:56", "throughput": 4641.0, "total_tokens": 13783296} {"current_steps": 13690, "total_steps": 42420, "loss": 0.0513, "lr": 4.2818928476072904e-05, "epoch": 6.454502593116454, "percentage": 32.27, "elapsed_time": "0:49:30", "remaining_time": "1:43:54", "throughput": 4640.99, "total_tokens": 13788256} {"current_steps": 13695, "total_steps": 42420, "loss": 0.2004, "lr": 4.2811712252272726e-05, "epoch": 6.456859971711457, "percentage": 32.28, "elapsed_time": "0:49:32", "remaining_time": "1:43:54", "throughput": 4641.12, "total_tokens": 13794112} {"current_steps": 13700, "total_steps": 42420, "loss": 0.1988, "lr": 4.28044930132521e-05, "epoch": 6.459217350306459, "percentage": 32.3, "elapsed_time": "0:49:33", "remaining_time": "1:43:52", "throughput": 4641.18, "total_tokens": 13798880} {"current_steps": 13705, "total_steps": 42420, "loss": 0.1004, "lr": 4.279727076023311e-05, "epoch": 6.461574728901462, "percentage": 32.31, "elapsed_time": "0:49:33", "remaining_time": "1:43:51", "throughput": 4641.12, "total_tokens": 13802656} {"current_steps": 13710, "total_steps": 42420, "loss": 0.2552, "lr": 4.279004549443836e-05, "epoch": 6.463932107496464, "percentage": 32.32, "elapsed_time": "0:49:34", "remaining_time": "1:43:49", "throughput": 4641.21, "total_tokens": 13807328} {"current_steps": 13715, "total_steps": 42420, "loss": 0.1774, "lr": 4.278281721709096e-05, "epoch": 6.466289486091466, "percentage": 32.33, "elapsed_time": "0:49:35", "remaining_time": "1:43:48", "throughput": 4641.25, "total_tokens": 13811872} {"current_steps": 13720, "total_steps": 42420, "loss": 0.1233, "lr": 4.277558592941454e-05, "epoch": 6.468646864686469, "percentage": 32.34, "elapsed_time": "0:49:37", "remaining_time": "1:43:47", "throughput": 4641.37, "total_tokens": 13817760} {"current_steps": 13725, "total_steps": 42420, "loss": 0.1402, "lr": 4.276835163263324e-05, "epoch": 6.471004243281471, "percentage": 32.36, "elapsed_time": "0:49:38", "remaining_time": "1:43:46", "throughput": 4641.51, "total_tokens": 13823648} {"current_steps": 13730, "total_steps": 42420, "loss": 0.0521, "lr": 4.276111432797169e-05, "epoch": 6.473361621876474, "percentage": 32.37, "elapsed_time": "0:49:39", "remaining_time": "1:43:45", "throughput": 4641.63, "total_tokens": 13829696} {"current_steps": 13735, "total_steps": 42420, "loss": 0.1808, "lr": 4.275387401665506e-05, "epoch": 6.475719000471476, "percentage": 32.38, "elapsed_time": "0:49:40", "remaining_time": "1:43:44", "throughput": 4641.74, "total_tokens": 13835200} {"current_steps": 13740, "total_steps": 42420, "loss": 0.0446, "lr": 4.274663069990899e-05, "epoch": 6.478076379066478, "percentage": 32.39, "elapsed_time": "0:49:41", "remaining_time": "1:43:43", "throughput": 4641.67, "total_tokens": 13839424} {"current_steps": 13745, "total_steps": 42420, "loss": 0.1073, "lr": 4.273938437895968e-05, "epoch": 6.480433757661481, "percentage": 32.4, "elapsed_time": "0:49:42", "remaining_time": "1:43:42", "throughput": 4641.65, "total_tokens": 13843840} {"current_steps": 13750, "total_steps": 42420, "loss": 0.121, "lr": 4.273213505503378e-05, "epoch": 6.482791136256483, "percentage": 32.41, "elapsed_time": "0:49:43", "remaining_time": "1:43:40", "throughput": 4641.7, "total_tokens": 13848608} {"current_steps": 13755, "total_steps": 42420, "loss": 0.2319, "lr": 4.2724882729358494e-05, "epoch": 6.485148514851485, "percentage": 32.43, "elapsed_time": "0:49:44", "remaining_time": "1:43:39", "throughput": 4641.77, "total_tokens": 13853856} {"current_steps": 13760, "total_steps": 42420, "loss": 0.2215, "lr": 4.271762740316152e-05, "epoch": 6.487505893446487, "percentage": 32.44, "elapsed_time": "0:49:45", "remaining_time": "1:43:38", "throughput": 4641.81, "total_tokens": 13858784} {"current_steps": 13765, "total_steps": 42420, "loss": 0.071, "lr": 4.271036907767104e-05, "epoch": 6.4898632720414895, "percentage": 32.45, "elapsed_time": "0:49:46", "remaining_time": "1:43:37", "throughput": 4641.89, "total_tokens": 13863808} {"current_steps": 13770, "total_steps": 42420, "loss": 0.1346, "lr": 4.270310775411579e-05, "epoch": 6.492220650636492, "percentage": 32.46, "elapsed_time": "0:49:47", "remaining_time": "1:43:36", "throughput": 4641.98, "total_tokens": 13869312} {"current_steps": 13775, "total_steps": 42420, "loss": 0.2155, "lr": 4.269584343372498e-05, "epoch": 6.494578029231494, "percentage": 32.47, "elapsed_time": "0:49:48", "remaining_time": "1:43:35", "throughput": 4642.07, "total_tokens": 13875136} {"current_steps": 13780, "total_steps": 42420, "loss": 0.1034, "lr": 4.268857611772833e-05, "epoch": 6.496935407826497, "percentage": 32.48, "elapsed_time": "0:49:49", "remaining_time": "1:43:34", "throughput": 4642.11, "total_tokens": 13879680} {"current_steps": 13785, "total_steps": 42420, "loss": 0.0526, "lr": 4.268130580735608e-05, "epoch": 6.499292786421499, "percentage": 32.5, "elapsed_time": "0:49:50", "remaining_time": "1:43:33", "throughput": 4642.16, "total_tokens": 13884576} {"current_steps": 13790, "total_steps": 42420, "loss": 0.1368, "lr": 4.267403250383897e-05, "epoch": 6.5016501650165015, "percentage": 32.51, "elapsed_time": "0:49:51", "remaining_time": "1:43:31", "throughput": 4642.24, "total_tokens": 13889216} {"current_steps": 13795, "total_steps": 42420, "loss": 0.0429, "lr": 4.2666756208408244e-05, "epoch": 6.504007543611504, "percentage": 32.52, "elapsed_time": "0:49:52", "remaining_time": "1:43:30", "throughput": 4642.31, "total_tokens": 13894432} {"current_steps": 13800, "total_steps": 42420, "loss": 0.1714, "lr": 4.265947692229565e-05, "epoch": 6.506364922206506, "percentage": 32.53, "elapsed_time": "0:49:54", "remaining_time": "1:43:29", "throughput": 4642.43, "total_tokens": 13899936} {"current_steps": 13805, "total_steps": 42420, "loss": 0.0994, "lr": 4.265219464673346e-05, "epoch": 6.508722300801509, "percentage": 32.54, "elapsed_time": "0:49:55", "remaining_time": "1:43:28", "throughput": 4642.5, "total_tokens": 13904960} {"current_steps": 13810, "total_steps": 42420, "loss": 0.123, "lr": 4.264490938295444e-05, "epoch": 6.511079679396511, "percentage": 32.56, "elapsed_time": "0:49:56", "remaining_time": "1:43:27", "throughput": 4642.53, "total_tokens": 13909728} {"current_steps": 13815, "total_steps": 42420, "loss": 0.1508, "lr": 4.263762113219184e-05, "epoch": 6.5134370579915135, "percentage": 32.57, "elapsed_time": "0:49:57", "remaining_time": "1:43:25", "throughput": 4642.56, "total_tokens": 13914080} {"current_steps": 13820, "total_steps": 42420, "loss": 0.1122, "lr": 4.263032989567947e-05, "epoch": 6.515794436586516, "percentage": 32.58, "elapsed_time": "0:49:57", "remaining_time": "1:43:24", "throughput": 4642.57, "total_tokens": 13918272} {"current_steps": 13825, "total_steps": 42420, "loss": 0.0821, "lr": 4.262303567465158e-05, "epoch": 6.518151815181518, "percentage": 32.59, "elapsed_time": "0:49:59", "remaining_time": "1:43:23", "throughput": 4642.64, "total_tokens": 13923360} {"current_steps": 13830, "total_steps": 42420, "loss": 0.2089, "lr": 4.261573847034297e-05, "epoch": 6.520509193776521, "percentage": 32.6, "elapsed_time": "0:50:00", "remaining_time": "1:43:21", "throughput": 4642.67, "total_tokens": 13928160} {"current_steps": 13835, "total_steps": 42420, "loss": 0.2039, "lr": 4.260843828398895e-05, "epoch": 6.522866572371523, "percentage": 32.61, "elapsed_time": "0:50:01", "remaining_time": "1:43:20", "throughput": 4642.71, "total_tokens": 13933472} {"current_steps": 13840, "total_steps": 42420, "loss": 0.0785, "lr": 4.260113511682529e-05, "epoch": 6.5252239509665255, "percentage": 32.63, "elapsed_time": "0:50:02", "remaining_time": "1:43:19", "throughput": 4642.77, "total_tokens": 13938272} {"current_steps": 13845, "total_steps": 42420, "loss": 0.0958, "lr": 4.259382897008831e-05, "epoch": 6.527581329561528, "percentage": 32.64, "elapsed_time": "0:50:03", "remaining_time": "1:43:18", "throughput": 4642.89, "total_tokens": 13943584} {"current_steps": 13850, "total_steps": 42420, "loss": 0.0778, "lr": 4.2586519845014815e-05, "epoch": 6.52993870815653, "percentage": 32.65, "elapsed_time": "0:50:04", "remaining_time": "1:43:17", "throughput": 4642.99, "total_tokens": 13948992} {"current_steps": 13855, "total_steps": 42420, "loss": 0.1301, "lr": 4.257920774284211e-05, "epoch": 6.532296086751533, "percentage": 32.66, "elapsed_time": "0:50:05", "remaining_time": "1:43:15", "throughput": 4643.06, "total_tokens": 13953600} {"current_steps": 13860, "total_steps": 42420, "loss": 0.1164, "lr": 4.257189266480801e-05, "epoch": 6.534653465346535, "percentage": 32.67, "elapsed_time": "0:50:06", "remaining_time": "1:43:14", "throughput": 4643.13, "total_tokens": 13958400} {"current_steps": 13865, "total_steps": 42420, "loss": 0.1852, "lr": 4.256457461215084e-05, "epoch": 6.537010843941537, "percentage": 32.69, "elapsed_time": "0:50:07", "remaining_time": "1:43:14", "throughput": 4643.18, "total_tokens": 13964608} {"current_steps": 13870, "total_steps": 42420, "loss": 0.0602, "lr": 4.255725358610941e-05, "epoch": 6.539368222536539, "percentage": 32.7, "elapsed_time": "0:50:08", "remaining_time": "1:43:12", "throughput": 4643.24, "total_tokens": 13968896} {"current_steps": 13875, "total_steps": 42420, "loss": 0.1396, "lr": 4.254992958792306e-05, "epoch": 6.5417256011315414, "percentage": 32.71, "elapsed_time": "0:50:09", "remaining_time": "1:43:11", "throughput": 4643.32, "total_tokens": 13974272} {"current_steps": 13880, "total_steps": 42420, "loss": 0.1315, "lr": 4.2542602618831606e-05, "epoch": 6.544082979726544, "percentage": 32.72, "elapsed_time": "0:50:10", "remaining_time": "1:43:10", "throughput": 4643.33, "total_tokens": 13979424} {"current_steps": 13885, "total_steps": 42420, "loss": 0.2209, "lr": 4.253527268007539e-05, "epoch": 6.546440358321546, "percentage": 32.73, "elapsed_time": "0:50:11", "remaining_time": "1:43:09", "throughput": 4643.31, "total_tokens": 13983584} {"current_steps": 13890, "total_steps": 42420, "loss": 0.0883, "lr": 4.252793977289524e-05, "epoch": 6.548797736916549, "percentage": 32.74, "elapsed_time": "0:50:12", "remaining_time": "1:43:07", "throughput": 4643.35, "total_tokens": 13988288} {"current_steps": 13895, "total_steps": 42420, "loss": 0.2017, "lr": 4.25206038985325e-05, "epoch": 6.551155115511551, "percentage": 32.76, "elapsed_time": "0:50:13", "remaining_time": "1:43:06", "throughput": 4643.39, "total_tokens": 13992800} {"current_steps": 13900, "total_steps": 42420, "loss": 0.0683, "lr": 4.251326505822899e-05, "epoch": 6.5535124941065535, "percentage": 32.77, "elapsed_time": "0:50:14", "remaining_time": "1:43:06", "throughput": 4643.51, "total_tokens": 13999936} {"current_steps": 13905, "total_steps": 42420, "loss": 0.1017, "lr": 4.250592325322707e-05, "epoch": 6.555869872701556, "percentage": 32.78, "elapsed_time": "0:50:15", "remaining_time": "1:43:04", "throughput": 4643.52, "total_tokens": 14003968} {"current_steps": 13910, "total_steps": 42420, "loss": 0.2428, "lr": 4.249857848476958e-05, "epoch": 6.558227251296558, "percentage": 32.79, "elapsed_time": "0:50:16", "remaining_time": "1:43:03", "throughput": 4643.6, "total_tokens": 14009120} {"current_steps": 13915, "total_steps": 42420, "loss": 0.2009, "lr": 4.249123075409985e-05, "epoch": 6.560584629891561, "percentage": 32.8, "elapsed_time": "0:50:17", "remaining_time": "1:43:02", "throughput": 4643.64, "total_tokens": 14014080} {"current_steps": 13920, "total_steps": 42420, "loss": 0.1001, "lr": 4.248388006246175e-05, "epoch": 6.562942008486563, "percentage": 32.81, "elapsed_time": "0:50:19", "remaining_time": "1:43:01", "throughput": 4643.73, "total_tokens": 14020128} {"current_steps": 13925, "total_steps": 42420, "loss": 0.2345, "lr": 4.247652641109962e-05, "epoch": 6.5652993870815655, "percentage": 32.83, "elapsed_time": "0:50:20", "remaining_time": "1:43:00", "throughput": 4643.8, "total_tokens": 14024800} {"current_steps": 13930, "total_steps": 42420, "loss": 0.1527, "lr": 4.246916980125829e-05, "epoch": 6.567656765676568, "percentage": 32.84, "elapsed_time": "0:50:21", "remaining_time": "1:42:59", "throughput": 4643.93, "total_tokens": 14030496} {"current_steps": 13935, "total_steps": 42420, "loss": 0.0436, "lr": 4.246181023418312e-05, "epoch": 6.57001414427157, "percentage": 32.85, "elapsed_time": "0:50:22", "remaining_time": "1:42:58", "throughput": 4644.03, "total_tokens": 14035872} {"current_steps": 13940, "total_steps": 42420, "loss": 0.1761, "lr": 4.245444771111997e-05, "epoch": 6.572371522866573, "percentage": 32.86, "elapsed_time": "0:50:23", "remaining_time": "1:42:56", "throughput": 4644.04, "total_tokens": 14040416} {"current_steps": 13945, "total_steps": 42420, "loss": 0.0328, "lr": 4.2447082233315184e-05, "epoch": 6.574728901461575, "percentage": 32.87, "elapsed_time": "0:50:24", "remaining_time": "1:42:55", "throughput": 4644.14, "total_tokens": 14045760} {"current_steps": 13950, "total_steps": 42420, "loss": 0.0715, "lr": 4.24397138020156e-05, "epoch": 6.5770862800565775, "percentage": 32.89, "elapsed_time": "0:50:25", "remaining_time": "1:42:54", "throughput": 4644.22, "total_tokens": 14051392} {"current_steps": 13955, "total_steps": 42420, "loss": 0.0628, "lr": 4.243234241846858e-05, "epoch": 6.579443658651579, "percentage": 32.9, "elapsed_time": "0:50:26", "remaining_time": "1:42:53", "throughput": 4644.24, "total_tokens": 14055872} {"current_steps": 13960, "total_steps": 42420, "loss": 0.2508, "lr": 4.242496808392199e-05, "epoch": 6.581801037246581, "percentage": 32.91, "elapsed_time": "0:50:27", "remaining_time": "1:42:52", "throughput": 4644.3, "total_tokens": 14060608} {"current_steps": 13965, "total_steps": 42420, "loss": 0.1753, "lr": 4.241759079962415e-05, "epoch": 6.584158415841584, "percentage": 32.92, "elapsed_time": "0:50:28", "remaining_time": "1:42:50", "throughput": 4644.38, "total_tokens": 14065600} {"current_steps": 13970, "total_steps": 42420, "loss": 0.0568, "lr": 4.241021056682393e-05, "epoch": 6.586515794436586, "percentage": 32.93, "elapsed_time": "0:50:29", "remaining_time": "1:42:49", "throughput": 4644.45, "total_tokens": 14071008} {"current_steps": 13975, "total_steps": 42420, "loss": 0.1101, "lr": 4.240282738677066e-05, "epoch": 6.588873173031589, "percentage": 32.94, "elapsed_time": "0:50:30", "remaining_time": "1:42:48", "throughput": 4644.49, "total_tokens": 14075648} {"current_steps": 13980, "total_steps": 42420, "loss": 0.1578, "lr": 4.2395441260714196e-05, "epoch": 6.591230551626591, "percentage": 32.96, "elapsed_time": "0:50:31", "remaining_time": "1:42:47", "throughput": 4644.6, "total_tokens": 14080960} {"current_steps": 13985, "total_steps": 42420, "loss": 0.1027, "lr": 4.2388052189904885e-05, "epoch": 6.593587930221593, "percentage": 32.97, "elapsed_time": "0:50:32", "remaining_time": "1:42:46", "throughput": 4644.66, "total_tokens": 14085632} {"current_steps": 13990, "total_steps": 42420, "loss": 0.1665, "lr": 4.238066017559357e-05, "epoch": 6.595945308816596, "percentage": 32.98, "elapsed_time": "0:50:33", "remaining_time": "1:42:44", "throughput": 4644.72, "total_tokens": 14090400} {"current_steps": 13995, "total_steps": 42420, "loss": 0.1362, "lr": 4.23732652190316e-05, "epoch": 6.598302687411598, "percentage": 32.99, "elapsed_time": "0:50:34", "remaining_time": "1:42:43", "throughput": 4644.78, "total_tokens": 14095072} {"current_steps": 14000, "total_steps": 42420, "loss": 0.1974, "lr": 4.2365867321470806e-05, "epoch": 6.600660066006601, "percentage": 33.0, "elapsed_time": "0:50:35", "remaining_time": "1:42:42", "throughput": 4644.8, "total_tokens": 14099616} {"current_steps": 14005, "total_steps": 42420, "loss": 0.0964, "lr": 4.235846648416353e-05, "epoch": 6.603017444601603, "percentage": 33.02, "elapsed_time": "0:50:36", "remaining_time": "1:42:40", "throughput": 4644.83, "total_tokens": 14104352} {"current_steps": 14010, "total_steps": 42420, "loss": 0.0644, "lr": 4.235106270836261e-05, "epoch": 6.605374823196605, "percentage": 33.03, "elapsed_time": "0:50:37", "remaining_time": "1:42:39", "throughput": 4644.91, "total_tokens": 14109504} {"current_steps": 14015, "total_steps": 42420, "loss": 0.1716, "lr": 4.2343655995321375e-05, "epoch": 6.607732201791608, "percentage": 33.04, "elapsed_time": "0:50:38", "remaining_time": "1:42:38", "throughput": 4645.0, "total_tokens": 14114592} {"current_steps": 14020, "total_steps": 42420, "loss": 0.1485, "lr": 4.233624634629366e-05, "epoch": 6.61008958038661, "percentage": 33.05, "elapsed_time": "0:50:39", "remaining_time": "1:42:37", "throughput": 4645.0, "total_tokens": 14118592} {"current_steps": 14025, "total_steps": 42420, "loss": 0.2016, "lr": 4.232883376253379e-05, "epoch": 6.612446958981613, "percentage": 33.06, "elapsed_time": "0:50:40", "remaining_time": "1:42:35", "throughput": 4644.94, "total_tokens": 14122048} {"current_steps": 14030, "total_steps": 42420, "loss": 0.0894, "lr": 4.2321418245296595e-05, "epoch": 6.614804337576615, "percentage": 33.07, "elapsed_time": "0:50:41", "remaining_time": "1:42:34", "throughput": 4645.06, "total_tokens": 14128704} {"current_steps": 14035, "total_steps": 42420, "loss": 0.2617, "lr": 4.231399979583739e-05, "epoch": 6.617161716171617, "percentage": 33.09, "elapsed_time": "0:50:42", "remaining_time": "1:42:33", "throughput": 4645.17, "total_tokens": 14134432} {"current_steps": 14040, "total_steps": 42420, "loss": 0.2404, "lr": 4.2306578415411994e-05, "epoch": 6.61951909476662, "percentage": 33.1, "elapsed_time": "0:50:44", "remaining_time": "1:42:33", "throughput": 4645.31, "total_tokens": 14141984} {"current_steps": 14045, "total_steps": 42420, "loss": 0.2245, "lr": 4.229915410527672e-05, "epoch": 6.621876473361622, "percentage": 33.11, "elapsed_time": "0:50:45", "remaining_time": "1:42:32", "throughput": 4645.41, "total_tokens": 14147456} {"current_steps": 14050, "total_steps": 42420, "loss": 0.0572, "lr": 4.229172686668837e-05, "epoch": 6.624233851956625, "percentage": 33.12, "elapsed_time": "0:50:46", "remaining_time": "1:42:31", "throughput": 4645.47, "total_tokens": 14152640} {"current_steps": 14055, "total_steps": 42420, "loss": 0.108, "lr": 4.228429670090428e-05, "epoch": 6.626591230551627, "percentage": 33.13, "elapsed_time": "0:50:47", "remaining_time": "1:42:30", "throughput": 4645.41, "total_tokens": 14156288} {"current_steps": 14060, "total_steps": 42420, "loss": 0.0878, "lr": 4.227686360918221e-05, "epoch": 6.628948609146629, "percentage": 33.14, "elapsed_time": "0:50:48", "remaining_time": "1:42:29", "throughput": 4645.55, "total_tokens": 14162048} {"current_steps": 14065, "total_steps": 42420, "loss": 0.0856, "lr": 4.226942759278048e-05, "epoch": 6.631305987741631, "percentage": 33.16, "elapsed_time": "0:50:49", "remaining_time": "1:42:27", "throughput": 4645.58, "total_tokens": 14166432} {"current_steps": 14070, "total_steps": 42420, "loss": 0.0458, "lr": 4.226198865295789e-05, "epoch": 6.633663366336633, "percentage": 33.17, "elapsed_time": "0:50:50", "remaining_time": "1:42:26", "throughput": 4645.61, "total_tokens": 14171040} {"current_steps": 14075, "total_steps": 42420, "loss": 0.147, "lr": 4.2254546790973704e-05, "epoch": 6.636020744931636, "percentage": 33.18, "elapsed_time": "0:50:51", "remaining_time": "1:42:25", "throughput": 4645.73, "total_tokens": 14176224} {"current_steps": 14080, "total_steps": 42420, "loss": 0.0807, "lr": 4.224710200808771e-05, "epoch": 6.638378123526638, "percentage": 33.19, "elapsed_time": "0:50:52", "remaining_time": "1:42:24", "throughput": 4645.74, "total_tokens": 14181280} {"current_steps": 14085, "total_steps": 42420, "loss": 0.1424, "lr": 4.2239654305560186e-05, "epoch": 6.6407355021216405, "percentage": 33.2, "elapsed_time": "0:50:53", "remaining_time": "1:42:22", "throughput": 4645.69, "total_tokens": 14185376} {"current_steps": 14090, "total_steps": 42420, "loss": 0.0776, "lr": 4.223220368465189e-05, "epoch": 6.643092880716643, "percentage": 33.22, "elapsed_time": "0:50:54", "remaining_time": "1:42:21", "throughput": 4645.68, "total_tokens": 14189600} {"current_steps": 14095, "total_steps": 42420, "loss": 0.1573, "lr": 4.222475014662411e-05, "epoch": 6.645450259311645, "percentage": 33.23, "elapsed_time": "0:50:55", "remaining_time": "1:42:20", "throughput": 4645.77, "total_tokens": 14194656} {"current_steps": 14100, "total_steps": 42420, "loss": 0.087, "lr": 4.221729369273859e-05, "epoch": 6.647807637906648, "percentage": 33.24, "elapsed_time": "0:50:56", "remaining_time": "1:42:19", "throughput": 4645.89, "total_tokens": 14200128} {"current_steps": 14105, "total_steps": 42420, "loss": 0.1868, "lr": 4.220983432425758e-05, "epoch": 6.65016501650165, "percentage": 33.25, "elapsed_time": "0:50:57", "remaining_time": "1:42:17", "throughput": 4645.97, "total_tokens": 14205024} {"current_steps": 14110, "total_steps": 42420, "loss": 0.0569, "lr": 4.2202372042443816e-05, "epoch": 6.6525223950966526, "percentage": 33.26, "elapsed_time": "0:50:58", "remaining_time": "1:42:16", "throughput": 4645.95, "total_tokens": 14209088} {"current_steps": 14115, "total_steps": 42420, "loss": 0.1584, "lr": 4.2194906848560555e-05, "epoch": 6.654879773691655, "percentage": 33.27, "elapsed_time": "0:50:59", "remaining_time": "1:42:14", "throughput": 4645.99, "total_tokens": 14213600} {"current_steps": 14120, "total_steps": 42420, "loss": 0.2236, "lr": 4.218743874387151e-05, "epoch": 6.657237152286657, "percentage": 33.29, "elapsed_time": "0:51:00", "remaining_time": "1:42:13", "throughput": 4646.06, "total_tokens": 14218944} {"current_steps": 14125, "total_steps": 42420, "loss": 0.1766, "lr": 4.217996772964092e-05, "epoch": 6.65959453088166, "percentage": 33.3, "elapsed_time": "0:51:01", "remaining_time": "1:42:12", "throughput": 4646.13, "total_tokens": 14223552} {"current_steps": 14130, "total_steps": 42420, "loss": 0.0607, "lr": 4.2172493807133485e-05, "epoch": 6.661951909476662, "percentage": 33.31, "elapsed_time": "0:51:02", "remaining_time": "1:42:11", "throughput": 4646.22, "total_tokens": 14229152} {"current_steps": 14135, "total_steps": 42420, "loss": 0.047, "lr": 4.2165016977614424e-05, "epoch": 6.664309288071665, "percentage": 33.32, "elapsed_time": "0:51:03", "remaining_time": "1:42:10", "throughput": 4646.31, "total_tokens": 14234592} {"current_steps": 14140, "total_steps": 42420, "loss": 0.1701, "lr": 4.2157537242349433e-05, "epoch": 6.666666666666667, "percentage": 33.33, "elapsed_time": "0:51:04", "remaining_time": "1:42:09", "throughput": 4646.44, "total_tokens": 14240416} {"current_steps": 14145, "total_steps": 42420, "loss": 0.1845, "lr": 4.2150054602604706e-05, "epoch": 6.669024045261669, "percentage": 33.35, "elapsed_time": "0:51:05", "remaining_time": "1:42:08", "throughput": 4646.46, "total_tokens": 14244608} {"current_steps": 14150, "total_steps": 42420, "loss": 0.2033, "lr": 4.214256905964693e-05, "epoch": 6.671381423856672, "percentage": 33.36, "elapsed_time": "0:51:06", "remaining_time": "1:42:07", "throughput": 4646.55, "total_tokens": 14249888} {"current_steps": 14155, "total_steps": 42420, "loss": 0.0196, "lr": 4.213508061474327e-05, "epoch": 6.673738802451673, "percentage": 33.37, "elapsed_time": "0:51:07", "remaining_time": "1:42:05", "throughput": 4646.62, "total_tokens": 14254976} {"current_steps": 14160, "total_steps": 42420, "loss": 0.1411, "lr": 4.2127589269161405e-05, "epoch": 6.676096181046676, "percentage": 33.38, "elapsed_time": "0:51:08", "remaining_time": "1:42:04", "throughput": 4646.65, "total_tokens": 14259264} {"current_steps": 14165, "total_steps": 42420, "loss": 0.1729, "lr": 4.212009502416948e-05, "epoch": 6.678453559641678, "percentage": 33.39, "elapsed_time": "0:51:09", "remaining_time": "1:42:03", "throughput": 4646.68, "total_tokens": 14263872} {"current_steps": 14170, "total_steps": 42420, "loss": 0.0781, "lr": 4.2112597881036156e-05, "epoch": 6.6808109382366805, "percentage": 33.4, "elapsed_time": "0:51:10", "remaining_time": "1:42:02", "throughput": 4646.8, "total_tokens": 14269728} {"current_steps": 14175, "total_steps": 42420, "loss": 0.0431, "lr": 4.210509784103056e-05, "epoch": 6.683168316831683, "percentage": 33.42, "elapsed_time": "0:51:11", "remaining_time": "1:42:00", "throughput": 4646.84, "total_tokens": 14274336} {"current_steps": 14180, "total_steps": 42420, "loss": 0.0875, "lr": 4.2097594905422335e-05, "epoch": 6.685525695426685, "percentage": 33.43, "elapsed_time": "0:51:13", "remaining_time": "1:42:00", "throughput": 4646.4, "total_tokens": 14279136} {"current_steps": 14185, "total_steps": 42420, "loss": 0.1746, "lr": 4.209008907548159e-05, "epoch": 6.687883074021688, "percentage": 33.44, "elapsed_time": "0:51:14", "remaining_time": "1:41:59", "throughput": 4646.32, "total_tokens": 14283680} {"current_steps": 14190, "total_steps": 42420, "loss": 0.1463, "lr": 4.208258035247894e-05, "epoch": 6.69024045261669, "percentage": 33.45, "elapsed_time": "0:51:15", "remaining_time": "1:41:58", "throughput": 4646.42, "total_tokens": 14289216} {"current_steps": 14195, "total_steps": 42420, "loss": 0.1758, "lr": 4.207506873768547e-05, "epoch": 6.6925978312116925, "percentage": 33.46, "elapsed_time": "0:51:16", "remaining_time": "1:41:56", "throughput": 4646.47, "total_tokens": 14293984} {"current_steps": 14200, "total_steps": 42420, "loss": 0.0883, "lr": 4.2067554232372794e-05, "epoch": 6.694955209806695, "percentage": 33.47, "elapsed_time": "0:51:17", "remaining_time": "1:41:55", "throughput": 4646.52, "total_tokens": 14298624} {"current_steps": 14205, "total_steps": 42420, "loss": 0.1047, "lr": 4.206003683781298e-05, "epoch": 6.697312588401697, "percentage": 33.49, "elapsed_time": "0:51:18", "remaining_time": "1:41:54", "throughput": 4646.58, "total_tokens": 14304032} {"current_steps": 14210, "total_steps": 42420, "loss": 0.2166, "lr": 4.2052516555278576e-05, "epoch": 6.6996699669967, "percentage": 33.5, "elapsed_time": "0:51:19", "remaining_time": "1:41:53", "throughput": 4646.58, "total_tokens": 14308064} {"current_steps": 14215, "total_steps": 42420, "loss": 0.1337, "lr": 4.204499338604267e-05, "epoch": 6.702027345591702, "percentage": 33.51, "elapsed_time": "0:51:20", "remaining_time": "1:41:51", "throughput": 4646.54, "total_tokens": 14312064} {"current_steps": 14220, "total_steps": 42420, "loss": 0.192, "lr": 4.203746733137878e-05, "epoch": 6.7043847241867045, "percentage": 33.52, "elapsed_time": "0:51:21", "remaining_time": "1:41:50", "throughput": 4646.56, "total_tokens": 14316928} {"current_steps": 14225, "total_steps": 42420, "loss": 0.1264, "lr": 4.2029938392560956e-05, "epoch": 6.706742102781707, "percentage": 33.53, "elapsed_time": "0:51:22", "remaining_time": "1:41:49", "throughput": 4646.64, "total_tokens": 14322336} {"current_steps": 14230, "total_steps": 42420, "loss": 0.1725, "lr": 4.202240657086371e-05, "epoch": 6.709099481376709, "percentage": 33.55, "elapsed_time": "0:51:23", "remaining_time": "1:41:48", "throughput": 4646.71, "total_tokens": 14327968} {"current_steps": 14235, "total_steps": 42420, "loss": 0.3851, "lr": 4.201487186756207e-05, "epoch": 6.711456859971712, "percentage": 33.56, "elapsed_time": "0:51:24", "remaining_time": "1:41:47", "throughput": 4646.75, "total_tokens": 14332992} {"current_steps": 14240, "total_steps": 42420, "loss": 0.2909, "lr": 4.20073342839315e-05, "epoch": 6.713814238566714, "percentage": 33.57, "elapsed_time": "0:51:25", "remaining_time": "1:41:46", "throughput": 4646.82, "total_tokens": 14337792} {"current_steps": 14245, "total_steps": 42420, "loss": 0.2265, "lr": 4.1999793821248016e-05, "epoch": 6.7161716171617165, "percentage": 33.58, "elapsed_time": "0:51:26", "remaining_time": "1:41:44", "throughput": 4646.9, "total_tokens": 14342720} {"current_steps": 14250, "total_steps": 42420, "loss": 0.1139, "lr": 4.1992250480788075e-05, "epoch": 6.718528995756719, "percentage": 33.59, "elapsed_time": "0:51:27", "remaining_time": "1:41:43", "throughput": 4646.97, "total_tokens": 14348000} {"current_steps": 14255, "total_steps": 42420, "loss": 0.1385, "lr": 4.1984704263828634e-05, "epoch": 6.720886374351721, "percentage": 33.6, "elapsed_time": "0:51:29", "remaining_time": "1:41:43", "throughput": 4647.09, "total_tokens": 14355072} {"current_steps": 14260, "total_steps": 42420, "loss": 0.1054, "lr": 4.197715517164715e-05, "epoch": 6.723243752946724, "percentage": 33.62, "elapsed_time": "0:51:30", "remaining_time": "1:41:42", "throughput": 4647.16, "total_tokens": 14360512} {"current_steps": 14265, "total_steps": 42420, "loss": 0.1598, "lr": 4.1969603205521554e-05, "epoch": 6.725601131541725, "percentage": 33.63, "elapsed_time": "0:51:31", "remaining_time": "1:41:41", "throughput": 4647.1, "total_tokens": 14364864} {"current_steps": 14270, "total_steps": 42420, "loss": 0.4257, "lr": 4.1962048366730254e-05, "epoch": 6.727958510136728, "percentage": 33.64, "elapsed_time": "0:51:32", "remaining_time": "1:41:39", "throughput": 4647.12, "total_tokens": 14369312} {"current_steps": 14275, "total_steps": 42420, "loss": 0.1595, "lr": 4.195449065655217e-05, "epoch": 6.73031588873173, "percentage": 33.65, "elapsed_time": "0:51:33", "remaining_time": "1:41:38", "throughput": 4647.16, "total_tokens": 14373920} {"current_steps": 14280, "total_steps": 42420, "loss": 0.2387, "lr": 4.194693007626669e-05, "epoch": 6.732673267326732, "percentage": 33.66, "elapsed_time": "0:51:34", "remaining_time": "1:41:37", "throughput": 4647.23, "total_tokens": 14379072} {"current_steps": 14285, "total_steps": 42420, "loss": 0.1191, "lr": 4.193936662715369e-05, "epoch": 6.735030645921735, "percentage": 33.68, "elapsed_time": "0:51:35", "remaining_time": "1:41:35", "throughput": 4647.26, "total_tokens": 14383520} {"current_steps": 14290, "total_steps": 42420, "loss": 0.1049, "lr": 4.193180031049354e-05, "epoch": 6.737388024516737, "percentage": 33.69, "elapsed_time": "0:51:36", "remaining_time": "1:41:34", "throughput": 4647.31, "total_tokens": 14388160} {"current_steps": 14295, "total_steps": 42420, "loss": 0.1387, "lr": 4.192423112756708e-05, "epoch": 6.73974540311174, "percentage": 33.7, "elapsed_time": "0:51:37", "remaining_time": "1:41:33", "throughput": 4647.37, "total_tokens": 14392960} {"current_steps": 14300, "total_steps": 42420, "loss": 0.1302, "lr": 4.191665907965564e-05, "epoch": 6.742102781706742, "percentage": 33.71, "elapsed_time": "0:51:38", "remaining_time": "1:41:32", "throughput": 4647.52, "total_tokens": 14400096} {"current_steps": 14305, "total_steps": 42420, "loss": 0.212, "lr": 4.190908416804105e-05, "epoch": 6.7444601603017444, "percentage": 33.72, "elapsed_time": "0:51:39", "remaining_time": "1:41:31", "throughput": 4647.51, "total_tokens": 14404096} {"current_steps": 14310, "total_steps": 42420, "loss": 0.0586, "lr": 4.190150639400561e-05, "epoch": 6.746817538896747, "percentage": 33.73, "elapsed_time": "0:51:40", "remaining_time": "1:41:30", "throughput": 4647.59, "total_tokens": 14409184} {"current_steps": 14315, "total_steps": 42420, "loss": 0.2466, "lr": 4.189392575883211e-05, "epoch": 6.749174917491749, "percentage": 33.75, "elapsed_time": "0:51:41", "remaining_time": "1:41:29", "throughput": 4647.62, "total_tokens": 14414112} {"current_steps": 14320, "total_steps": 42420, "loss": 0.048, "lr": 4.188634226380382e-05, "epoch": 6.751532296086752, "percentage": 33.76, "elapsed_time": "0:51:42", "remaining_time": "1:41:27", "throughput": 4647.66, "total_tokens": 14418976} {"current_steps": 14325, "total_steps": 42420, "loss": 0.0671, "lr": 4.1878755910204495e-05, "epoch": 6.753889674681754, "percentage": 33.77, "elapsed_time": "0:51:43", "remaining_time": "1:41:26", "throughput": 4647.8, "total_tokens": 14424992} {"current_steps": 14330, "total_steps": 42420, "loss": 0.1964, "lr": 4.1871166699318384e-05, "epoch": 6.7562470532767565, "percentage": 33.78, "elapsed_time": "0:51:44", "remaining_time": "1:41:26", "throughput": 4647.95, "total_tokens": 14431680} {"current_steps": 14335, "total_steps": 42420, "loss": 0.1711, "lr": 4.186357463243021e-05, "epoch": 6.758604431871759, "percentage": 33.79, "elapsed_time": "0:51:45", "remaining_time": "1:41:24", "throughput": 4647.94, "total_tokens": 14435776} {"current_steps": 14340, "total_steps": 42420, "loss": 0.0789, "lr": 4.1855979710825173e-05, "epoch": 6.760961810466761, "percentage": 33.8, "elapsed_time": "0:51:46", "remaining_time": "1:41:23", "throughput": 4648.01, "total_tokens": 14440704} {"current_steps": 14345, "total_steps": 42420, "loss": 0.1469, "lr": 4.1848381935788975e-05, "epoch": 6.763319189061764, "percentage": 33.82, "elapsed_time": "0:51:47", "remaining_time": "1:41:22", "throughput": 4648.09, "total_tokens": 14445792} {"current_steps": 14350, "total_steps": 42420, "loss": 0.1052, "lr": 4.1840781308607776e-05, "epoch": 6.765676567656766, "percentage": 33.83, "elapsed_time": "0:51:48", "remaining_time": "1:41:21", "throughput": 4648.11, "total_tokens": 14450144} {"current_steps": 14355, "total_steps": 42420, "loss": 0.0849, "lr": 4.183317783056825e-05, "epoch": 6.768033946251768, "percentage": 33.84, "elapsed_time": "0:51:49", "remaining_time": "1:41:19", "throughput": 4648.1, "total_tokens": 14454592} {"current_steps": 14360, "total_steps": 42420, "loss": 0.2981, "lr": 4.1825571502957514e-05, "epoch": 6.77039132484677, "percentage": 33.85, "elapsed_time": "0:51:50", "remaining_time": "1:41:18", "throughput": 4648.16, "total_tokens": 14459360} {"current_steps": 14365, "total_steps": 42420, "loss": 0.3288, "lr": 4.181796232706322e-05, "epoch": 6.772748703441772, "percentage": 33.86, "elapsed_time": "0:51:51", "remaining_time": "1:41:17", "throughput": 4648.11, "total_tokens": 14463840} {"current_steps": 14370, "total_steps": 42420, "loss": 0.1073, "lr": 4.181035030417345e-05, "epoch": 6.775106082036775, "percentage": 33.88, "elapsed_time": "0:51:52", "remaining_time": "1:41:16", "throughput": 4648.18, "total_tokens": 14469280} {"current_steps": 14375, "total_steps": 42420, "loss": 0.1962, "lr": 4.18027354355768e-05, "epoch": 6.777463460631777, "percentage": 33.89, "elapsed_time": "0:51:53", "remaining_time": "1:41:14", "throughput": 4648.15, "total_tokens": 14473408} {"current_steps": 14380, "total_steps": 42420, "loss": 0.0829, "lr": 4.179511772256233e-05, "epoch": 6.77982083922678, "percentage": 33.9, "elapsed_time": "0:51:54", "remaining_time": "1:41:13", "throughput": 4648.13, "total_tokens": 14478144} {"current_steps": 14385, "total_steps": 42420, "loss": 0.1967, "lr": 4.17874971664196e-05, "epoch": 6.782178217821782, "percentage": 33.91, "elapsed_time": "0:51:55", "remaining_time": "1:41:12", "throughput": 4648.19, "total_tokens": 14483008} {"current_steps": 14390, "total_steps": 42420, "loss": 0.1215, "lr": 4.177987376843863e-05, "epoch": 6.784535596416784, "percentage": 33.92, "elapsed_time": "0:51:56", "remaining_time": "1:41:11", "throughput": 4648.27, "total_tokens": 14488032} {"current_steps": 14395, "total_steps": 42420, "loss": 0.1772, "lr": 4.1772247529909946e-05, "epoch": 6.786892975011787, "percentage": 33.93, "elapsed_time": "0:51:58", "remaining_time": "1:41:10", "throughput": 4648.36, "total_tokens": 14493856} {"current_steps": 14400, "total_steps": 42420, "loss": 0.1364, "lr": 4.176461845212452e-05, "epoch": 6.789250353606789, "percentage": 33.95, "elapsed_time": "0:51:59", "remaining_time": "1:41:09", "throughput": 4648.42, "total_tokens": 14498528} {"current_steps": 14405, "total_steps": 42420, "loss": 0.1775, "lr": 4.1756986536373844e-05, "epoch": 6.791607732201792, "percentage": 33.96, "elapsed_time": "0:52:00", "remaining_time": "1:41:07", "throughput": 4648.51, "total_tokens": 14503680} {"current_steps": 14410, "total_steps": 42420, "loss": 0.4332, "lr": 4.174935178394987e-05, "epoch": 6.793965110796794, "percentage": 33.97, "elapsed_time": "0:52:01", "remaining_time": "1:41:07", "throughput": 4648.62, "total_tokens": 14509440} {"current_steps": 14415, "total_steps": 42420, "loss": 0.1141, "lr": 4.174171419614502e-05, "epoch": 6.796322489391796, "percentage": 33.98, "elapsed_time": "0:52:02", "remaining_time": "1:41:05", "throughput": 4648.67, "total_tokens": 14514112} {"current_steps": 14420, "total_steps": 42420, "loss": 0.0925, "lr": 4.1734073774252214e-05, "epoch": 6.798679867986799, "percentage": 33.99, "elapsed_time": "0:52:03", "remaining_time": "1:41:04", "throughput": 4648.72, "total_tokens": 14519904} {"current_steps": 14425, "total_steps": 42420, "loss": 0.1781, "lr": 4.172643051956485e-05, "epoch": 6.801037246581801, "percentage": 34.01, "elapsed_time": "0:52:04", "remaining_time": "1:41:03", "throughput": 4648.72, "total_tokens": 14524576} {"current_steps": 14430, "total_steps": 42420, "loss": 0.0966, "lr": 4.171878443337679e-05, "epoch": 6.803394625176804, "percentage": 34.02, "elapsed_time": "0:52:05", "remaining_time": "1:41:02", "throughput": 4648.81, "total_tokens": 14530528} {"current_steps": 14435, "total_steps": 42420, "loss": 0.0956, "lr": 4.17111355169824e-05, "epoch": 6.805752003771806, "percentage": 34.03, "elapsed_time": "0:52:06", "remaining_time": "1:41:01", "throughput": 4648.88, "total_tokens": 14535552} {"current_steps": 14440, "total_steps": 42420, "loss": 0.1293, "lr": 4.170348377167651e-05, "epoch": 6.808109382366808, "percentage": 34.04, "elapsed_time": "0:52:07", "remaining_time": "1:41:00", "throughput": 4648.86, "total_tokens": 14539392} {"current_steps": 14445, "total_steps": 42420, "loss": 0.1533, "lr": 4.169582919875442e-05, "epoch": 6.810466760961811, "percentage": 34.05, "elapsed_time": "0:52:08", "remaining_time": "1:40:59", "throughput": 4648.99, "total_tokens": 14545536} {"current_steps": 14450, "total_steps": 42420, "loss": 0.0859, "lr": 4.1688171799511925e-05, "epoch": 6.812824139556813, "percentage": 34.06, "elapsed_time": "0:52:09", "remaining_time": "1:40:57", "throughput": 4648.98, "total_tokens": 14549504} {"current_steps": 14455, "total_steps": 42420, "loss": 0.2385, "lr": 4.1680511575245294e-05, "epoch": 6.815181518151816, "percentage": 34.08, "elapsed_time": "0:52:10", "remaining_time": "1:40:56", "throughput": 4649.09, "total_tokens": 14555136} {"current_steps": 14460, "total_steps": 42420, "loss": 0.2515, "lr": 4.1672848527251274e-05, "epoch": 6.817538896746818, "percentage": 34.09, "elapsed_time": "0:52:11", "remaining_time": "1:40:55", "throughput": 4649.12, "total_tokens": 14559968} {"current_steps": 14465, "total_steps": 42420, "loss": 0.2692, "lr": 4.166518265682709e-05, "epoch": 6.8198962753418195, "percentage": 34.1, "elapsed_time": "0:52:12", "remaining_time": "1:40:54", "throughput": 4649.14, "total_tokens": 14564320} {"current_steps": 14470, "total_steps": 42420, "loss": 0.2262, "lr": 4.165751396527044e-05, "epoch": 6.822253653936822, "percentage": 34.11, "elapsed_time": "0:52:13", "remaining_time": "1:40:53", "throughput": 4649.23, "total_tokens": 14569376} {"current_steps": 14475, "total_steps": 42420, "loss": 0.0457, "lr": 4.16498424538795e-05, "epoch": 6.824611032531824, "percentage": 34.12, "elapsed_time": "0:52:14", "remaining_time": "1:40:52", "throughput": 4649.34, "total_tokens": 14575328} {"current_steps": 14480, "total_steps": 42420, "loss": 0.2331, "lr": 4.1642168123952936e-05, "epoch": 6.826968411126827, "percentage": 34.13, "elapsed_time": "0:52:16", "remaining_time": "1:40:51", "throughput": 4649.4, "total_tokens": 14580960} {"current_steps": 14485, "total_steps": 42420, "loss": 0.1617, "lr": 4.163449097678987e-05, "epoch": 6.829325789721829, "percentage": 34.15, "elapsed_time": "0:52:17", "remaining_time": "1:40:50", "throughput": 4649.53, "total_tokens": 14587776} {"current_steps": 14490, "total_steps": 42420, "loss": 0.1394, "lr": 4.1626811013689925e-05, "epoch": 6.8316831683168315, "percentage": 34.16, "elapsed_time": "0:52:18", "remaining_time": "1:40:49", "throughput": 4649.62, "total_tokens": 14592992} {"current_steps": 14495, "total_steps": 42420, "loss": 0.0679, "lr": 4.1619128235953177e-05, "epoch": 6.834040546911834, "percentage": 34.17, "elapsed_time": "0:52:19", "remaining_time": "1:40:48", "throughput": 4649.65, "total_tokens": 14597536} {"current_steps": 14500, "total_steps": 42420, "loss": 0.1465, "lr": 4.161144264488021e-05, "epoch": 6.836397925506836, "percentage": 34.18, "elapsed_time": "0:52:20", "remaining_time": "1:40:47", "throughput": 4649.71, "total_tokens": 14602400} {"current_steps": 14505, "total_steps": 42420, "loss": 0.0342, "lr": 4.160375424177203e-05, "epoch": 6.838755304101839, "percentage": 34.19, "elapsed_time": "0:52:21", "remaining_time": "1:40:45", "throughput": 4649.67, "total_tokens": 14606112} {"current_steps": 14510, "total_steps": 42420, "loss": 0.1328, "lr": 4.1596063027930185e-05, "epoch": 6.841112682696841, "percentage": 34.21, "elapsed_time": "0:52:22", "remaining_time": "1:40:44", "throughput": 4649.72, "total_tokens": 14610400} {"current_steps": 14515, "total_steps": 42420, "loss": 0.207, "lr": 4.158836900465665e-05, "epoch": 6.8434700612918435, "percentage": 34.22, "elapsed_time": "0:52:23", "remaining_time": "1:40:42", "throughput": 4649.8, "total_tokens": 14615712} {"current_steps": 14520, "total_steps": 42420, "loss": 0.2916, "lr": 4.15806721732539e-05, "epoch": 6.845827439886846, "percentage": 34.23, "elapsed_time": "0:52:24", "remaining_time": "1:40:41", "throughput": 4649.85, "total_tokens": 14620768} {"current_steps": 14525, "total_steps": 42420, "loss": 0.1078, "lr": 4.1572972535024865e-05, "epoch": 6.848184818481848, "percentage": 34.24, "elapsed_time": "0:52:25", "remaining_time": "1:40:40", "throughput": 4649.9, "total_tokens": 14625408} {"current_steps": 14530, "total_steps": 42420, "loss": 0.4286, "lr": 4.156527009127298e-05, "epoch": 6.850542197076851, "percentage": 34.25, "elapsed_time": "0:52:26", "remaining_time": "1:40:39", "throughput": 4649.88, "total_tokens": 14630528} {"current_steps": 14535, "total_steps": 42420, "loss": 0.076, "lr": 4.155756484330213e-05, "epoch": 6.852899575671853, "percentage": 34.26, "elapsed_time": "0:52:27", "remaining_time": "1:40:38", "throughput": 4649.92, "total_tokens": 14635968} {"current_steps": 14540, "total_steps": 42420, "loss": 0.3006, "lr": 4.154985679241668e-05, "epoch": 6.8552569542668556, "percentage": 34.28, "elapsed_time": "0:52:28", "remaining_time": "1:40:37", "throughput": 4650.03, "total_tokens": 14642272} {"current_steps": 14545, "total_steps": 42420, "loss": 0.0456, "lr": 4.154214593992149e-05, "epoch": 6.857614332861858, "percentage": 34.29, "elapsed_time": "0:52:29", "remaining_time": "1:40:36", "throughput": 4650.09, "total_tokens": 14646976} {"current_steps": 14550, "total_steps": 42420, "loss": 0.0449, "lr": 4.153443228712185e-05, "epoch": 6.85997171145686, "percentage": 34.3, "elapsed_time": "0:52:30", "remaining_time": "1:40:35", "throughput": 4650.1, "total_tokens": 14651488} {"current_steps": 14555, "total_steps": 42420, "loss": 0.0988, "lr": 4.152671583532357e-05, "epoch": 6.862329090051862, "percentage": 34.31, "elapsed_time": "0:52:31", "remaining_time": "1:40:33", "throughput": 4650.16, "total_tokens": 14656352} {"current_steps": 14560, "total_steps": 42420, "loss": 0.1021, "lr": 4.151899658583289e-05, "epoch": 6.864686468646864, "percentage": 34.32, "elapsed_time": "0:52:32", "remaining_time": "1:40:32", "throughput": 4650.21, "total_tokens": 14661536} {"current_steps": 14565, "total_steps": 42420, "loss": 0.2142, "lr": 4.151127453995658e-05, "epoch": 6.867043847241867, "percentage": 34.34, "elapsed_time": "0:52:33", "remaining_time": "1:40:31", "throughput": 4650.29, "total_tokens": 14666592} {"current_steps": 14570, "total_steps": 42420, "loss": 0.1348, "lr": 4.150354969900183e-05, "epoch": 6.869401225836869, "percentage": 34.35, "elapsed_time": "0:52:34", "remaining_time": "1:40:30", "throughput": 4650.33, "total_tokens": 14671456} {"current_steps": 14575, "total_steps": 42420, "loss": 0.234, "lr": 4.149582206427633e-05, "epoch": 6.8717586044318715, "percentage": 34.36, "elapsed_time": "0:52:36", "remaining_time": "1:40:29", "throughput": 4650.41, "total_tokens": 14677568} {"current_steps": 14580, "total_steps": 42420, "loss": 0.0632, "lr": 4.1488091637088244e-05, "epoch": 6.874115983026874, "percentage": 34.37, "elapsed_time": "0:52:37", "remaining_time": "1:40:28", "throughput": 4650.44, "total_tokens": 14682400} {"current_steps": 14585, "total_steps": 42420, "loss": 0.1263, "lr": 4.148035841874619e-05, "epoch": 6.876473361621876, "percentage": 34.38, "elapsed_time": "0:52:38", "remaining_time": "1:40:27", "throughput": 4650.53, "total_tokens": 14688672} {"current_steps": 14590, "total_steps": 42420, "loss": 0.1827, "lr": 4.147262241055928e-05, "epoch": 6.878830740216879, "percentage": 34.39, "elapsed_time": "0:52:39", "remaining_time": "1:40:26", "throughput": 4650.57, "total_tokens": 14693312} {"current_steps": 14595, "total_steps": 42420, "loss": 0.0727, "lr": 4.146488361383708e-05, "epoch": 6.881188118811881, "percentage": 34.41, "elapsed_time": "0:52:40", "remaining_time": "1:40:25", "throughput": 4650.64, "total_tokens": 14698624} {"current_steps": 14600, "total_steps": 42420, "loss": 0.215, "lr": 4.145714202988965e-05, "epoch": 6.8835454974068835, "percentage": 34.42, "elapsed_time": "0:52:41", "remaining_time": "1:40:24", "throughput": 4650.69, "total_tokens": 14703584} {"current_steps": 14605, "total_steps": 42420, "loss": 0.1351, "lr": 4.1449397660027495e-05, "epoch": 6.885902876001886, "percentage": 34.43, "elapsed_time": "0:52:42", "remaining_time": "1:40:22", "throughput": 4650.69, "total_tokens": 14707424} {"current_steps": 14610, "total_steps": 42420, "loss": 0.0671, "lr": 4.144165050556161e-05, "epoch": 6.888260254596888, "percentage": 34.44, "elapsed_time": "0:52:43", "remaining_time": "1:40:21", "throughput": 4650.77, "total_tokens": 14712224} {"current_steps": 14615, "total_steps": 42420, "loss": 0.0758, "lr": 4.1433900567803464e-05, "epoch": 6.890617633191891, "percentage": 34.45, "elapsed_time": "0:52:44", "remaining_time": "1:40:20", "throughput": 4650.79, "total_tokens": 14717184} {"current_steps": 14620, "total_steps": 42420, "loss": 0.0915, "lr": 4.1426147848064974e-05, "epoch": 6.892975011786893, "percentage": 34.46, "elapsed_time": "0:52:45", "remaining_time": "1:40:19", "throughput": 4650.84, "total_tokens": 14721824} {"current_steps": 14625, "total_steps": 42420, "loss": 0.3243, "lr": 4.1418392347658555e-05, "epoch": 6.8953323903818955, "percentage": 34.48, "elapsed_time": "0:52:46", "remaining_time": "1:40:17", "throughput": 4650.88, "total_tokens": 14726464} {"current_steps": 14630, "total_steps": 42420, "loss": 0.3701, "lr": 4.141063406789708e-05, "epoch": 6.897689768976898, "percentage": 34.49, "elapsed_time": "0:52:47", "remaining_time": "1:40:16", "throughput": 4650.93, "total_tokens": 14731712} {"current_steps": 14635, "total_steps": 42420, "loss": 0.1976, "lr": 4.1402873010093904e-05, "epoch": 6.9000471475719, "percentage": 34.5, "elapsed_time": "0:52:48", "remaining_time": "1:40:15", "throughput": 4650.96, "total_tokens": 14736416} {"current_steps": 14640, "total_steps": 42420, "loss": 0.1535, "lr": 4.139510917556283e-05, "epoch": 6.902404526166903, "percentage": 34.51, "elapsed_time": "0:52:49", "remaining_time": "1:40:14", "throughput": 4651.05, "total_tokens": 14741888} {"current_steps": 14645, "total_steps": 42420, "loss": 0.1272, "lr": 4.1387342565618134e-05, "epoch": 6.904761904761905, "percentage": 34.52, "elapsed_time": "0:52:50", "remaining_time": "1:40:13", "throughput": 4651.12, "total_tokens": 14747488} {"current_steps": 14650, "total_steps": 42420, "loss": 0.2388, "lr": 4.1379573181574596e-05, "epoch": 6.9071192833569075, "percentage": 34.54, "elapsed_time": "0:52:51", "remaining_time": "1:40:12", "throughput": 4651.15, "total_tokens": 14751680} {"current_steps": 14655, "total_steps": 42420, "loss": 0.0622, "lr": 4.137180102474742e-05, "epoch": 6.90947666195191, "percentage": 34.55, "elapsed_time": "0:52:52", "remaining_time": "1:40:10", "throughput": 4651.2, "total_tokens": 14756320} {"current_steps": 14660, "total_steps": 42420, "loss": 0.1033, "lr": 4.1364026096452316e-05, "epoch": 6.911834040546912, "percentage": 34.56, "elapsed_time": "0:52:53", "remaining_time": "1:40:09", "throughput": 4651.24, "total_tokens": 14760544} {"current_steps": 14665, "total_steps": 42420, "loss": 0.1532, "lr": 4.135624839800543e-05, "epoch": 6.914191419141914, "percentage": 34.57, "elapsed_time": "0:52:54", "remaining_time": "1:40:08", "throughput": 4651.33, "total_tokens": 14765856} {"current_steps": 14670, "total_steps": 42420, "loss": 0.0501, "lr": 4.13484679307234e-05, "epoch": 6.916548797736916, "percentage": 34.58, "elapsed_time": "0:52:55", "remaining_time": "1:40:06", "throughput": 4651.3, "total_tokens": 14770048} {"current_steps": 14675, "total_steps": 42420, "loss": 0.3648, "lr": 4.134068469592334e-05, "epoch": 6.918906176331919, "percentage": 34.59, "elapsed_time": "0:52:56", "remaining_time": "1:40:05", "throughput": 4651.38, "total_tokens": 14774848} {"current_steps": 14680, "total_steps": 42420, "loss": 0.1889, "lr": 4.1332898694922804e-05, "epoch": 6.921263554926921, "percentage": 34.61, "elapsed_time": "0:52:57", "remaining_time": "1:40:04", "throughput": 4651.38, "total_tokens": 14779584} {"current_steps": 14685, "total_steps": 42420, "loss": 0.1167, "lr": 4.132510992903984e-05, "epoch": 6.923620933521923, "percentage": 34.62, "elapsed_time": "0:52:58", "remaining_time": "1:40:02", "throughput": 4651.32, "total_tokens": 14783616} {"current_steps": 14690, "total_steps": 42420, "loss": 0.0679, "lr": 4.131731839959295e-05, "epoch": 6.925978312116926, "percentage": 34.63, "elapsed_time": "0:52:59", "remaining_time": "1:40:01", "throughput": 4651.4, "total_tokens": 14788928} {"current_steps": 14695, "total_steps": 42420, "loss": 0.0915, "lr": 4.130952410790111e-05, "epoch": 6.928335690711928, "percentage": 34.64, "elapsed_time": "0:53:00", "remaining_time": "1:40:00", "throughput": 4651.44, "total_tokens": 14793792} {"current_steps": 14700, "total_steps": 42420, "loss": 0.1498, "lr": 4.130172705528375e-05, "epoch": 6.930693069306931, "percentage": 34.65, "elapsed_time": "0:53:01", "remaining_time": "1:39:59", "throughput": 4651.51, "total_tokens": 14799200} {"current_steps": 14705, "total_steps": 42420, "loss": 0.0888, "lr": 4.1293927243060795e-05, "epoch": 6.933050447901933, "percentage": 34.67, "elapsed_time": "0:53:02", "remaining_time": "1:39:58", "throughput": 4651.5, "total_tokens": 14804896} {"current_steps": 14710, "total_steps": 42420, "loss": 0.1529, "lr": 4.128612467255261e-05, "epoch": 6.935407826496935, "percentage": 34.68, "elapsed_time": "0:53:03", "remaining_time": "1:39:57", "throughput": 4651.47, "total_tokens": 14808864} {"current_steps": 14715, "total_steps": 42420, "loss": 0.0882, "lr": 4.1278319345080036e-05, "epoch": 6.937765205091938, "percentage": 34.69, "elapsed_time": "0:53:04", "remaining_time": "1:39:56", "throughput": 4651.52, "total_tokens": 14814688} {"current_steps": 14720, "total_steps": 42420, "loss": 0.162, "lr": 4.127051126196439e-05, "epoch": 6.94012258368694, "percentage": 34.7, "elapsed_time": "0:53:05", "remaining_time": "1:39:55", "throughput": 4651.46, "total_tokens": 14819008} {"current_steps": 14725, "total_steps": 42420, "loss": 0.2198, "lr": 4.1262700424527445e-05, "epoch": 6.942479962281943, "percentage": 34.71, "elapsed_time": "0:53:07", "remaining_time": "1:39:54", "throughput": 4651.57, "total_tokens": 14824736} {"current_steps": 14730, "total_steps": 42420, "loss": 0.1135, "lr": 4.125488683409144e-05, "epoch": 6.944837340876945, "percentage": 34.72, "elapsed_time": "0:53:08", "remaining_time": "1:39:52", "throughput": 4651.59, "total_tokens": 14829376} {"current_steps": 14735, "total_steps": 42420, "loss": 0.0768, "lr": 4.124707049197909e-05, "epoch": 6.947194719471947, "percentage": 34.74, "elapsed_time": "0:53:09", "remaining_time": "1:39:51", "throughput": 4651.6, "total_tokens": 14834080} {"current_steps": 14740, "total_steps": 42420, "loss": 0.0381, "lr": 4.123925139951357e-05, "epoch": 6.94955209806695, "percentage": 34.75, "elapsed_time": "0:53:10", "remaining_time": "1:39:50", "throughput": 4651.69, "total_tokens": 14839680} {"current_steps": 14745, "total_steps": 42420, "loss": 0.048, "lr": 4.123142955801851e-05, "epoch": 6.951909476661952, "percentage": 34.76, "elapsed_time": "0:53:11", "remaining_time": "1:39:49", "throughput": 4651.74, "total_tokens": 14844224} {"current_steps": 14750, "total_steps": 42420, "loss": 0.0583, "lr": 4.122360496881802e-05, "epoch": 6.954266855256955, "percentage": 34.77, "elapsed_time": "0:53:12", "remaining_time": "1:39:48", "throughput": 4651.8, "total_tokens": 14849216} {"current_steps": 14755, "total_steps": 42420, "loss": 0.1472, "lr": 4.121577763323667e-05, "epoch": 6.956624233851956, "percentage": 34.78, "elapsed_time": "0:53:13", "remaining_time": "1:39:47", "throughput": 4651.88, "total_tokens": 14854688} {"current_steps": 14760, "total_steps": 42420, "loss": 0.2468, "lr": 4.1207947552599495e-05, "epoch": 6.958981612446959, "percentage": 34.79, "elapsed_time": "0:53:14", "remaining_time": "1:39:45", "throughput": 4651.93, "total_tokens": 14859200} {"current_steps": 14765, "total_steps": 42420, "loss": 0.3713, "lr": 4.1200114728232e-05, "epoch": 6.961338991041961, "percentage": 34.81, "elapsed_time": "0:53:15", "remaining_time": "1:39:45", "throughput": 4652.05, "total_tokens": 14865152} {"current_steps": 14770, "total_steps": 42420, "loss": 0.0799, "lr": 4.119227916146014e-05, "epoch": 6.963696369636963, "percentage": 34.82, "elapsed_time": "0:53:16", "remaining_time": "1:39:43", "throughput": 4652.15, "total_tokens": 14870432} {"current_steps": 14775, "total_steps": 42420, "loss": 0.0785, "lr": 4.118444085361034e-05, "epoch": 6.966053748231966, "percentage": 34.83, "elapsed_time": "0:53:17", "remaining_time": "1:39:42", "throughput": 4652.25, "total_tokens": 14875808} {"current_steps": 14780, "total_steps": 42420, "loss": 0.1365, "lr": 4.11765998060095e-05, "epoch": 6.968411126826968, "percentage": 34.84, "elapsed_time": "0:53:18", "remaining_time": "1:39:41", "throughput": 4652.28, "total_tokens": 14881088} {"current_steps": 14785, "total_steps": 42420, "loss": 0.1145, "lr": 4.116875601998498e-05, "epoch": 6.970768505421971, "percentage": 34.85, "elapsed_time": "0:53:19", "remaining_time": "1:39:40", "throughput": 4652.37, "total_tokens": 14886528} {"current_steps": 14790, "total_steps": 42420, "loss": 0.0306, "lr": 4.11609094968646e-05, "epoch": 6.973125884016973, "percentage": 34.87, "elapsed_time": "0:53:20", "remaining_time": "1:39:39", "throughput": 4652.36, "total_tokens": 14891008} {"current_steps": 14795, "total_steps": 42420, "loss": 0.0238, "lr": 4.115306023797664e-05, "epoch": 6.975483262611975, "percentage": 34.88, "elapsed_time": "0:53:21", "remaining_time": "1:39:38", "throughput": 4652.44, "total_tokens": 14895712} {"current_steps": 14800, "total_steps": 42420, "loss": 0.1115, "lr": 4.1145208244649836e-05, "epoch": 6.977840641206978, "percentage": 34.89, "elapsed_time": "0:53:22", "remaining_time": "1:39:37", "throughput": 4652.56, "total_tokens": 14901728} {"current_steps": 14805, "total_steps": 42420, "loss": 0.0765, "lr": 4.113735351821341e-05, "epoch": 6.98019801980198, "percentage": 34.9, "elapsed_time": "0:53:24", "remaining_time": "1:39:36", "throughput": 4652.66, "total_tokens": 14908160} {"current_steps": 14810, "total_steps": 42420, "loss": 0.0659, "lr": 4.112949605999703e-05, "epoch": 6.982555398396983, "percentage": 34.91, "elapsed_time": "0:53:25", "remaining_time": "1:39:35", "throughput": 4652.77, "total_tokens": 14914016} {"current_steps": 14815, "total_steps": 42420, "loss": 0.1219, "lr": 4.112163587133083e-05, "epoch": 6.984912776991985, "percentage": 34.92, "elapsed_time": "0:53:26", "remaining_time": "1:39:34", "throughput": 4652.82, "total_tokens": 14918400} {"current_steps": 14820, "total_steps": 42420, "loss": 0.1934, "lr": 4.111377295354541e-05, "epoch": 6.987270155586987, "percentage": 34.94, "elapsed_time": "0:53:27", "remaining_time": "1:39:33", "throughput": 4652.9, "total_tokens": 14923168} {"current_steps": 14825, "total_steps": 42420, "loss": 0.0542, "lr": 4.110590730797182e-05, "epoch": 6.98962753418199, "percentage": 34.95, "elapsed_time": "0:53:28", "remaining_time": "1:39:31", "throughput": 4652.96, "total_tokens": 14928064} {"current_steps": 14830, "total_steps": 42420, "loss": 0.0726, "lr": 4.1098038935941594e-05, "epoch": 6.991984912776992, "percentage": 34.96, "elapsed_time": "0:53:29", "remaining_time": "1:39:30", "throughput": 4653.06, "total_tokens": 14933728} {"current_steps": 14835, "total_steps": 42420, "loss": 0.06, "lr": 4.10901678387867e-05, "epoch": 6.994342291371995, "percentage": 34.97, "elapsed_time": "0:53:30", "remaining_time": "1:39:29", "throughput": 4653.13, "total_tokens": 14938944} {"current_steps": 14840, "total_steps": 42420, "loss": 0.1174, "lr": 4.1082294017839586e-05, "epoch": 6.996699669966997, "percentage": 34.98, "elapsed_time": "0:53:31", "remaining_time": "1:39:28", "throughput": 4653.23, "total_tokens": 14944736} {"current_steps": 14845, "total_steps": 42420, "loss": 0.0268, "lr": 4.107441747443315e-05, "epoch": 6.999057048561999, "percentage": 35.0, "elapsed_time": "0:53:32", "remaining_time": "1:39:27", "throughput": 4653.19, "total_tokens": 14948800} {"current_steps": 14847, "total_steps": 42420, "eval_loss": 0.15092287957668304, "epoch": 7.0, "percentage": 35.0, "elapsed_time": "0:53:48", "remaining_time": "1:39:55", "throughput": 4631.23, "total_tokens": 14950432} {"current_steps": 14850, "total_steps": 42420, "loss": 0.2137, "lr": 4.1066538209900776e-05, "epoch": 7.001414427157002, "percentage": 35.01, "elapsed_time": "0:53:50", "remaining_time": "1:39:57", "throughput": 4628.99, "total_tokens": 14953344} {"current_steps": 14855, "total_steps": 42420, "loss": 0.0225, "lr": 4.105865622557627e-05, "epoch": 7.003771805752004, "percentage": 35.02, "elapsed_time": "0:53:51", "remaining_time": "1:39:56", "throughput": 4629.06, "total_tokens": 14958496} {"current_steps": 14860, "total_steps": 42420, "loss": 0.248, "lr": 4.105077152279393e-05, "epoch": 7.006129184347006, "percentage": 35.03, "elapsed_time": "0:53:52", "remaining_time": "1:39:55", "throughput": 4629.12, "total_tokens": 14963616} {"current_steps": 14865, "total_steps": 42420, "loss": 0.0644, "lr": 4.104288410288849e-05, "epoch": 7.008486562942008, "percentage": 35.04, "elapsed_time": "0:53:53", "remaining_time": "1:39:53", "throughput": 4629.13, "total_tokens": 14968320} {"current_steps": 14870, "total_steps": 42420, "loss": 0.1157, "lr": 4.103499396719517e-05, "epoch": 7.0108439415370105, "percentage": 35.05, "elapsed_time": "0:53:54", "remaining_time": "1:39:52", "throughput": 4629.19, "total_tokens": 14974016} {"current_steps": 14875, "total_steps": 42420, "loss": 0.1041, "lr": 4.1027101117049635e-05, "epoch": 7.013201320132013, "percentage": 35.07, "elapsed_time": "0:53:56", "remaining_time": "1:39:52", "throughput": 4629.28, "total_tokens": 14980416} {"current_steps": 14880, "total_steps": 42420, "loss": 0.0843, "lr": 4.1019205553787995e-05, "epoch": 7.015558698727015, "percentage": 35.08, "elapsed_time": "0:53:57", "remaining_time": "1:39:51", "throughput": 4629.35, "total_tokens": 14985536} {"current_steps": 14885, "total_steps": 42420, "loss": 0.1156, "lr": 4.1011307278746844e-05, "epoch": 7.017916077322018, "percentage": 35.09, "elapsed_time": "0:53:58", "remaining_time": "1:39:50", "throughput": 4629.48, "total_tokens": 14991648} {"current_steps": 14890, "total_steps": 42420, "loss": 0.1782, "lr": 4.100340629326324e-05, "epoch": 7.02027345591702, "percentage": 35.1, "elapsed_time": "0:53:59", "remaining_time": "1:39:49", "throughput": 4629.54, "total_tokens": 14996640} {"current_steps": 14895, "total_steps": 42420, "loss": 0.1741, "lr": 4.0995502598674664e-05, "epoch": 7.0226308345120225, "percentage": 35.11, "elapsed_time": "0:54:00", "remaining_time": "1:39:47", "throughput": 4629.57, "total_tokens": 15001120} {"current_steps": 14900, "total_steps": 42420, "loss": 0.0571, "lr": 4.098759619631909e-05, "epoch": 7.024988213107025, "percentage": 35.12, "elapsed_time": "0:54:01", "remaining_time": "1:39:46", "throughput": 4629.64, "total_tokens": 15006496} {"current_steps": 14905, "total_steps": 42420, "loss": 0.0605, "lr": 4.0979687087534934e-05, "epoch": 7.027345591702027, "percentage": 35.14, "elapsed_time": "0:54:02", "remaining_time": "1:39:45", "throughput": 4629.71, "total_tokens": 15011520} {"current_steps": 14910, "total_steps": 42420, "loss": 0.1391, "lr": 4.097177527366107e-05, "epoch": 7.02970297029703, "percentage": 35.15, "elapsed_time": "0:54:03", "remaining_time": "1:39:44", "throughput": 4629.83, "total_tokens": 15017152} {"current_steps": 14915, "total_steps": 42420, "loss": 0.2959, "lr": 4.096386075603684e-05, "epoch": 7.032060348892032, "percentage": 35.16, "elapsed_time": "0:54:04", "remaining_time": "1:39:43", "throughput": 4629.89, "total_tokens": 15021824} {"current_steps": 14920, "total_steps": 42420, "loss": 0.0732, "lr": 4.095594353600203e-05, "epoch": 7.0344177274870345, "percentage": 35.17, "elapsed_time": "0:54:05", "remaining_time": "1:39:42", "throughput": 4630.02, "total_tokens": 15027968} {"current_steps": 14925, "total_steps": 42420, "loss": 0.1793, "lr": 4.0948023614896905e-05, "epoch": 7.036775106082037, "percentage": 35.18, "elapsed_time": "0:54:06", "remaining_time": "1:39:41", "throughput": 4630.06, "total_tokens": 15032640} {"current_steps": 14930, "total_steps": 42420, "loss": 0.1125, "lr": 4.094010099406216e-05, "epoch": 7.039132484677039, "percentage": 35.2, "elapsed_time": "0:54:07", "remaining_time": "1:39:39", "throughput": 4630.12, "total_tokens": 15037216} {"current_steps": 14935, "total_steps": 42420, "loss": 0.1568, "lr": 4.093217567483896e-05, "epoch": 7.041489863272042, "percentage": 35.21, "elapsed_time": "0:54:08", "remaining_time": "1:39:38", "throughput": 4630.1, "total_tokens": 15041088} {"current_steps": 14940, "total_steps": 42420, "loss": 0.2211, "lr": 4.0924247658568935e-05, "epoch": 7.043847241867044, "percentage": 35.22, "elapsed_time": "0:54:09", "remaining_time": "1:39:36", "throughput": 4630.16, "total_tokens": 15045632} {"current_steps": 14945, "total_steps": 42420, "loss": 0.0786, "lr": 4.091631694659416e-05, "epoch": 7.0462046204620465, "percentage": 35.23, "elapsed_time": "0:54:10", "remaining_time": "1:39:35", "throughput": 4630.12, "total_tokens": 15049536} {"current_steps": 14950, "total_steps": 42420, "loss": 0.0665, "lr": 4.0908383540257166e-05, "epoch": 7.048561999057049, "percentage": 35.24, "elapsed_time": "0:54:11", "remaining_time": "1:39:34", "throughput": 4630.13, "total_tokens": 15053888} {"current_steps": 14955, "total_steps": 42420, "loss": 0.0195, "lr": 4.090044744090096e-05, "epoch": 7.050919377652051, "percentage": 35.25, "elapsed_time": "0:54:12", "remaining_time": "1:39:32", "throughput": 4630.2, "total_tokens": 15059040} {"current_steps": 14960, "total_steps": 42420, "loss": 0.1211, "lr": 4.089250864986896e-05, "epoch": 7.053276756247053, "percentage": 35.27, "elapsed_time": "0:54:13", "remaining_time": "1:39:31", "throughput": 4630.24, "total_tokens": 15063360} {"current_steps": 14965, "total_steps": 42420, "loss": 0.1339, "lr": 4.08845671685051e-05, "epoch": 7.055634134842055, "percentage": 35.28, "elapsed_time": "0:54:14", "remaining_time": "1:39:31", "throughput": 4630.34, "total_tokens": 15070080} {"current_steps": 14970, "total_steps": 42420, "loss": 0.2097, "lr": 4.0876622998153716e-05, "epoch": 7.057991513437058, "percentage": 35.29, "elapsed_time": "0:54:15", "remaining_time": "1:39:29", "throughput": 4630.43, "total_tokens": 15075328} {"current_steps": 14975, "total_steps": 42420, "loss": 0.1116, "lr": 4.0868676140159624e-05, "epoch": 7.06034889203206, "percentage": 35.3, "elapsed_time": "0:54:16", "remaining_time": "1:39:28", "throughput": 4630.51, "total_tokens": 15080192} {"current_steps": 14980, "total_steps": 42420, "loss": 0.0669, "lr": 4.08607265958681e-05, "epoch": 7.0627062706270625, "percentage": 35.31, "elapsed_time": "0:54:17", "remaining_time": "1:39:27", "throughput": 4630.62, "total_tokens": 15085856} {"current_steps": 14985, "total_steps": 42420, "loss": 0.0553, "lr": 4.085277436662486e-05, "epoch": 7.065063649222065, "percentage": 35.33, "elapsed_time": "0:54:18", "remaining_time": "1:39:26", "throughput": 4630.68, "total_tokens": 15090432} {"current_steps": 14990, "total_steps": 42420, "loss": 0.1604, "lr": 4.0844819453776086e-05, "epoch": 7.067421027817067, "percentage": 35.34, "elapsed_time": "0:54:19", "remaining_time": "1:39:25", "throughput": 4630.76, "total_tokens": 15095296} {"current_steps": 14995, "total_steps": 42420, "loss": 0.0808, "lr": 4.083686185866841e-05, "epoch": 7.06977840641207, "percentage": 35.35, "elapsed_time": "0:54:20", "remaining_time": "1:39:24", "throughput": 4630.8, "total_tokens": 15100640} {"current_steps": 15000, "total_steps": 42420, "loss": 0.1896, "lr": 4.082890158264891e-05, "epoch": 7.072135785007072, "percentage": 35.36, "elapsed_time": "0:54:21", "remaining_time": "1:39:22", "throughput": 4630.69, "total_tokens": 15104544} {"current_steps": 15005, "total_steps": 42420, "loss": 0.0514, "lr": 4.082093862706514e-05, "epoch": 7.0744931636020745, "percentage": 35.37, "elapsed_time": "0:54:22", "remaining_time": "1:39:21", "throughput": 4630.71, "total_tokens": 15109312} {"current_steps": 15010, "total_steps": 42420, "loss": 0.1206, "lr": 4.081297299326509e-05, "epoch": 7.076850542197077, "percentage": 35.38, "elapsed_time": "0:54:23", "remaining_time": "1:39:20", "throughput": 4630.83, "total_tokens": 15114368} {"current_steps": 15015, "total_steps": 42420, "loss": 0.1017, "lr": 4.080500468259719e-05, "epoch": 7.079207920792079, "percentage": 35.4, "elapsed_time": "0:54:25", "remaining_time": "1:39:19", "throughput": 4630.92, "total_tokens": 15120128} {"current_steps": 15020, "total_steps": 42420, "loss": 0.1012, "lr": 4.079703369641035e-05, "epoch": 7.081565299387082, "percentage": 35.41, "elapsed_time": "0:54:26", "remaining_time": "1:39:18", "throughput": 4631.03, "total_tokens": 15126208} {"current_steps": 15025, "total_steps": 42420, "loss": 0.1872, "lr": 4.0789060036053926e-05, "epoch": 7.083922677982084, "percentage": 35.42, "elapsed_time": "0:54:27", "remaining_time": "1:39:17", "throughput": 4631.1, "total_tokens": 15131552} {"current_steps": 15030, "total_steps": 42420, "loss": 0.1112, "lr": 4.078108370287772e-05, "epoch": 7.0862800565770865, "percentage": 35.43, "elapsed_time": "0:54:28", "remaining_time": "1:39:16", "throughput": 4631.21, "total_tokens": 15137312} {"current_steps": 15035, "total_steps": 42420, "loss": 0.1738, "lr": 4.0773104698232e-05, "epoch": 7.088637435172089, "percentage": 35.44, "elapsed_time": "0:54:29", "remaining_time": "1:39:15", "throughput": 4631.22, "total_tokens": 15141536} {"current_steps": 15040, "total_steps": 42420, "loss": 0.2285, "lr": 4.076512302346746e-05, "epoch": 7.090994813767091, "percentage": 35.45, "elapsed_time": "0:54:30", "remaining_time": "1:39:14", "throughput": 4631.31, "total_tokens": 15147232} {"current_steps": 15045, "total_steps": 42420, "loss": 0.1161, "lr": 4.075713867993526e-05, "epoch": 7.093352192362094, "percentage": 35.47, "elapsed_time": "0:54:31", "remaining_time": "1:39:12", "throughput": 4631.31, "total_tokens": 15151680} {"current_steps": 15050, "total_steps": 42420, "loss": 0.1263, "lr": 4.0749151668987034e-05, "epoch": 7.095709570957096, "percentage": 35.48, "elapsed_time": "0:54:32", "remaining_time": "1:39:11", "throughput": 4631.36, "total_tokens": 15156032} {"current_steps": 15055, "total_steps": 42420, "loss": 0.1409, "lr": 4.074116199197483e-05, "epoch": 7.0980669495520985, "percentage": 35.49, "elapsed_time": "0:54:33", "remaining_time": "1:39:10", "throughput": 4631.35, "total_tokens": 15160544} {"current_steps": 15060, "total_steps": 42420, "loss": 0.1248, "lr": 4.073316965025118e-05, "epoch": 7.1004243281471, "percentage": 35.5, "elapsed_time": "0:54:34", "remaining_time": "1:39:09", "throughput": 4631.47, "total_tokens": 15166432} {"current_steps": 15065, "total_steps": 42420, "loss": 0.0617, "lr": 4.072517464516903e-05, "epoch": 7.102781706742102, "percentage": 35.51, "elapsed_time": "0:54:35", "remaining_time": "1:39:07", "throughput": 4631.48, "total_tokens": 15171008} {"current_steps": 15070, "total_steps": 42420, "loss": 0.1945, "lr": 4.071717697808182e-05, "epoch": 7.105139085337105, "percentage": 35.53, "elapsed_time": "0:54:36", "remaining_time": "1:39:06", "throughput": 4631.6, "total_tokens": 15176672} {"current_steps": 15075, "total_steps": 42420, "loss": 0.267, "lr": 4.070917665034341e-05, "epoch": 7.107496463932107, "percentage": 35.54, "elapsed_time": "0:54:37", "remaining_time": "1:39:05", "throughput": 4631.62, "total_tokens": 15180928} {"current_steps": 15080, "total_steps": 42420, "loss": 0.1443, "lr": 4.0701173663308115e-05, "epoch": 7.10985384252711, "percentage": 35.55, "elapsed_time": "0:54:38", "remaining_time": "1:39:04", "throughput": 4631.69, "total_tokens": 15185824} {"current_steps": 15085, "total_steps": 42420, "loss": 0.0869, "lr": 4.0693168018330705e-05, "epoch": 7.112211221122112, "percentage": 35.56, "elapsed_time": "0:54:39", "remaining_time": "1:39:02", "throughput": 4631.68, "total_tokens": 15190080} {"current_steps": 15090, "total_steps": 42420, "loss": 0.0774, "lr": 4.068515971676641e-05, "epoch": 7.114568599717114, "percentage": 35.57, "elapsed_time": "0:54:40", "remaining_time": "1:39:01", "throughput": 4631.75, "total_tokens": 15194880} {"current_steps": 15095, "total_steps": 42420, "loss": 0.0741, "lr": 4.06771487599709e-05, "epoch": 7.116925978312117, "percentage": 35.58, "elapsed_time": "0:54:41", "remaining_time": "1:39:00", "throughput": 4631.88, "total_tokens": 15200800} {"current_steps": 15100, "total_steps": 42420, "loss": 0.0498, "lr": 4.066913514930027e-05, "epoch": 7.119283356907119, "percentage": 35.6, "elapsed_time": "0:54:42", "remaining_time": "1:38:59", "throughput": 4631.93, "total_tokens": 15205120} {"current_steps": 15105, "total_steps": 42420, "loss": 0.0925, "lr": 4.066111888611112e-05, "epoch": 7.121640735502122, "percentage": 35.61, "elapsed_time": "0:54:43", "remaining_time": "1:38:58", "throughput": 4632.02, "total_tokens": 15210304} {"current_steps": 15110, "total_steps": 42420, "loss": 0.127, "lr": 4.0653099971760456e-05, "epoch": 7.123998114097124, "percentage": 35.62, "elapsed_time": "0:54:44", "remaining_time": "1:38:56", "throughput": 4632.07, "total_tokens": 15214944} {"current_steps": 15115, "total_steps": 42420, "loss": 0.1735, "lr": 4.064507840760573e-05, "epoch": 7.126355492692126, "percentage": 35.63, "elapsed_time": "0:54:45", "remaining_time": "1:38:55", "throughput": 4632.14, "total_tokens": 15219552} {"current_steps": 15120, "total_steps": 42420, "loss": 0.1098, "lr": 4.063705419500487e-05, "epoch": 7.128712871287129, "percentage": 35.64, "elapsed_time": "0:54:46", "remaining_time": "1:38:54", "throughput": 4632.17, "total_tokens": 15224032} {"current_steps": 15125, "total_steps": 42420, "loss": 0.1292, "lr": 4.062902733531625e-05, "epoch": 7.131070249882131, "percentage": 35.66, "elapsed_time": "0:54:47", "remaining_time": "1:38:53", "throughput": 4632.27, "total_tokens": 15229888} {"current_steps": 15130, "total_steps": 42420, "loss": 0.0745, "lr": 4.062099782989866e-05, "epoch": 7.133427628477134, "percentage": 35.67, "elapsed_time": "0:54:48", "remaining_time": "1:38:52", "throughput": 4632.35, "total_tokens": 15235392} {"current_steps": 15135, "total_steps": 42420, "loss": 0.0777, "lr": 4.061296568011136e-05, "epoch": 7.135785007072136, "percentage": 35.68, "elapsed_time": "0:54:50", "remaining_time": "1:38:51", "throughput": 4632.45, "total_tokens": 15240928} {"current_steps": 15140, "total_steps": 42420, "loss": 0.1502, "lr": 4.060493088731407e-05, "epoch": 7.138142385667138, "percentage": 35.69, "elapsed_time": "0:54:51", "remaining_time": "1:38:50", "throughput": 4632.54, "total_tokens": 15246624} {"current_steps": 15145, "total_steps": 42420, "loss": 0.1193, "lr": 4.0596893452866936e-05, "epoch": 7.140499764262141, "percentage": 35.7, "elapsed_time": "0:54:52", "remaining_time": "1:38:48", "throughput": 4632.59, "total_tokens": 15251168} {"current_steps": 15150, "total_steps": 42420, "loss": 0.1396, "lr": 4.0588853378130556e-05, "epoch": 7.142857142857143, "percentage": 35.71, "elapsed_time": "0:54:53", "remaining_time": "1:38:47", "throughput": 4632.61, "total_tokens": 15255680} {"current_steps": 15155, "total_steps": 42420, "loss": 0.2917, "lr": 4.058081066446599e-05, "epoch": 7.145214521452146, "percentage": 35.73, "elapsed_time": "0:54:54", "remaining_time": "1:38:47", "throughput": 4632.74, "total_tokens": 15262656} {"current_steps": 15160, "total_steps": 42420, "loss": 0.2527, "lr": 4.057276531323473e-05, "epoch": 7.147571900047147, "percentage": 35.74, "elapsed_time": "0:54:55", "remaining_time": "1:38:45", "throughput": 4632.78, "total_tokens": 15267328} {"current_steps": 15165, "total_steps": 42420, "loss": 0.1938, "lr": 4.0564717325798695e-05, "epoch": 7.1499292786421496, "percentage": 35.75, "elapsed_time": "0:54:56", "remaining_time": "1:38:44", "throughput": 4632.86, "total_tokens": 15272992} {"current_steps": 15170, "total_steps": 42420, "loss": 0.1754, "lr": 4.055666670352031e-05, "epoch": 7.152286657237152, "percentage": 35.76, "elapsed_time": "0:54:58", "remaining_time": "1:38:44", "throughput": 4633.02, "total_tokens": 15280224} {"current_steps": 15175, "total_steps": 42420, "loss": 0.2123, "lr": 4.0548613447762374e-05, "epoch": 7.154644035832154, "percentage": 35.77, "elapsed_time": "0:54:59", "remaining_time": "1:38:43", "throughput": 4632.95, "total_tokens": 15284256} {"current_steps": 15180, "total_steps": 42420, "loss": 0.1316, "lr": 4.0540557559888194e-05, "epoch": 7.157001414427157, "percentage": 35.79, "elapsed_time": "0:54:59", "remaining_time": "1:38:41", "throughput": 4633.02, "total_tokens": 15288928} {"current_steps": 15185, "total_steps": 42420, "loss": 0.0131, "lr": 4.053249904126147e-05, "epoch": 7.159358793022159, "percentage": 35.8, "elapsed_time": "0:55:01", "remaining_time": "1:38:40", "throughput": 4633.11, "total_tokens": 15294528} {"current_steps": 15190, "total_steps": 42420, "loss": 0.2018, "lr": 4.0524437893246396e-05, "epoch": 7.161716171617162, "percentage": 35.81, "elapsed_time": "0:55:02", "remaining_time": "1:38:39", "throughput": 4633.19, "total_tokens": 15299776} {"current_steps": 15195, "total_steps": 42420, "loss": 0.2938, "lr": 4.051637411720758e-05, "epoch": 7.164073550212164, "percentage": 35.82, "elapsed_time": "0:55:03", "remaining_time": "1:38:38", "throughput": 4633.22, "total_tokens": 15304608} {"current_steps": 15200, "total_steps": 42420, "loss": 0.3108, "lr": 4.050830771451007e-05, "epoch": 7.166430928807166, "percentage": 35.83, "elapsed_time": "0:55:04", "remaining_time": "1:38:37", "throughput": 4633.21, "total_tokens": 15308864} {"current_steps": 15205, "total_steps": 42420, "loss": 0.156, "lr": 4.050023868651938e-05, "epoch": 7.168788307402169, "percentage": 35.84, "elapsed_time": "0:55:05", "remaining_time": "1:38:36", "throughput": 4633.29, "total_tokens": 15315488} {"current_steps": 15210, "total_steps": 42420, "loss": 0.1214, "lr": 4.049216703460147e-05, "epoch": 7.171145685997171, "percentage": 35.86, "elapsed_time": "0:55:06", "remaining_time": "1:38:35", "throughput": 4633.38, "total_tokens": 15320704} {"current_steps": 15215, "total_steps": 42420, "loss": 0.0649, "lr": 4.0484092760122704e-05, "epoch": 7.173503064592174, "percentage": 35.87, "elapsed_time": "0:55:07", "remaining_time": "1:38:34", "throughput": 4633.43, "total_tokens": 15325504} {"current_steps": 15220, "total_steps": 42420, "loss": 0.26, "lr": 4.0476015864449955e-05, "epoch": 7.175860443187176, "percentage": 35.88, "elapsed_time": "0:55:08", "remaining_time": "1:38:32", "throughput": 4633.44, "total_tokens": 15329536} {"current_steps": 15225, "total_steps": 42420, "loss": 0.1403, "lr": 4.046793634895048e-05, "epoch": 7.178217821782178, "percentage": 35.89, "elapsed_time": "0:55:09", "remaining_time": "1:38:31", "throughput": 4633.5, "total_tokens": 15334336} {"current_steps": 15230, "total_steps": 42420, "loss": 0.2873, "lr": 4.045985421499201e-05, "epoch": 7.180575200377181, "percentage": 35.9, "elapsed_time": "0:55:10", "remaining_time": "1:38:30", "throughput": 4633.56, "total_tokens": 15338976} {"current_steps": 15235, "total_steps": 42420, "loss": 0.1843, "lr": 4.045176946394273e-05, "epoch": 7.182932578972183, "percentage": 35.91, "elapsed_time": "0:55:11", "remaining_time": "1:38:29", "throughput": 4633.68, "total_tokens": 15344544} {"current_steps": 15240, "total_steps": 42420, "loss": 0.0807, "lr": 4.044368209717122e-05, "epoch": 7.185289957567186, "percentage": 35.93, "elapsed_time": "0:55:12", "remaining_time": "1:38:27", "throughput": 4633.76, "total_tokens": 15350016} {"current_steps": 15245, "total_steps": 42420, "loss": 0.1111, "lr": 4.043559211604655e-05, "epoch": 7.187647336162188, "percentage": 35.94, "elapsed_time": "0:55:13", "remaining_time": "1:38:26", "throughput": 4633.78, "total_tokens": 15354656} {"current_steps": 15250, "total_steps": 42420, "loss": 0.0642, "lr": 4.042749952193822e-05, "epoch": 7.19000471475719, "percentage": 35.95, "elapsed_time": "0:55:14", "remaining_time": "1:38:25", "throughput": 4633.85, "total_tokens": 15360096} {"current_steps": 15255, "total_steps": 42420, "loss": 0.2878, "lr": 4.041940431621617e-05, "epoch": 7.192362093352193, "percentage": 35.96, "elapsed_time": "0:55:15", "remaining_time": "1:38:24", "throughput": 4633.88, "total_tokens": 15365344} {"current_steps": 15260, "total_steps": 42420, "loss": 0.0628, "lr": 4.041130650025077e-05, "epoch": 7.194719471947194, "percentage": 35.97, "elapsed_time": "0:55:16", "remaining_time": "1:38:23", "throughput": 4633.95, "total_tokens": 15370208} {"current_steps": 15265, "total_steps": 42420, "loss": 0.1788, "lr": 4.040320607541285e-05, "epoch": 7.197076850542197, "percentage": 35.99, "elapsed_time": "0:55:17", "remaining_time": "1:38:22", "throughput": 4634.02, "total_tokens": 15375488} {"current_steps": 15270, "total_steps": 42420, "loss": 0.1082, "lr": 4.039510304307367e-05, "epoch": 7.199434229137199, "percentage": 36.0, "elapsed_time": "0:55:18", "remaining_time": "1:38:21", "throughput": 4633.96, "total_tokens": 15379808} {"current_steps": 15275, "total_steps": 42420, "loss": 0.1482, "lr": 4.038699740460494e-05, "epoch": 7.2017916077322015, "percentage": 36.01, "elapsed_time": "0:55:19", "remaining_time": "1:38:19", "throughput": 4633.95, "total_tokens": 15384544} {"current_steps": 15280, "total_steps": 42420, "loss": 0.0274, "lr": 4.037888916137881e-05, "epoch": 7.204148986327204, "percentage": 36.02, "elapsed_time": "0:55:21", "remaining_time": "1:38:18", "throughput": 4634.06, "total_tokens": 15390304} {"current_steps": 15285, "total_steps": 42420, "loss": 0.0968, "lr": 4.037077831476787e-05, "epoch": 7.206506364922206, "percentage": 36.03, "elapsed_time": "0:55:22", "remaining_time": "1:38:17", "throughput": 4634.11, "total_tokens": 15394848} {"current_steps": 15290, "total_steps": 42420, "loss": 0.1192, "lr": 4.036266486614513e-05, "epoch": 7.208863743517209, "percentage": 36.04, "elapsed_time": "0:55:23", "remaining_time": "1:38:16", "throughput": 4634.17, "total_tokens": 15399392} {"current_steps": 15295, "total_steps": 42420, "loss": 0.0479, "lr": 4.035454881688407e-05, "epoch": 7.211221122112211, "percentage": 36.06, "elapsed_time": "0:55:23", "remaining_time": "1:38:14", "throughput": 4634.15, "total_tokens": 15403680} {"current_steps": 15300, "total_steps": 42420, "loss": 0.1483, "lr": 4.0346430168358606e-05, "epoch": 7.2135785007072135, "percentage": 36.07, "elapsed_time": "0:55:24", "remaining_time": "1:38:13", "throughput": 4634.15, "total_tokens": 15408096} {"current_steps": 15305, "total_steps": 42420, "loss": 0.1886, "lr": 4.033830892194308e-05, "epoch": 7.215935879302216, "percentage": 36.08, "elapsed_time": "0:55:25", "remaining_time": "1:38:12", "throughput": 4634.19, "total_tokens": 15412544} {"current_steps": 15310, "total_steps": 42420, "loss": 0.0982, "lr": 4.033018507901229e-05, "epoch": 7.218293257897218, "percentage": 36.09, "elapsed_time": "0:55:26", "remaining_time": "1:38:11", "throughput": 4634.29, "total_tokens": 15418016} {"current_steps": 15315, "total_steps": 42420, "loss": 0.0925, "lr": 4.032205864094145e-05, "epoch": 7.220650636492221, "percentage": 36.1, "elapsed_time": "0:55:27", "remaining_time": "1:38:09", "throughput": 4634.35, "total_tokens": 15422880} {"current_steps": 15320, "total_steps": 42420, "loss": 0.1581, "lr": 4.031392960910624e-05, "epoch": 7.223008015087223, "percentage": 36.12, "elapsed_time": "0:55:28", "remaining_time": "1:38:08", "throughput": 4634.37, "total_tokens": 15427264} {"current_steps": 15325, "total_steps": 42420, "loss": 0.122, "lr": 4.030579798488276e-05, "epoch": 7.2253653936822255, "percentage": 36.13, "elapsed_time": "0:55:29", "remaining_time": "1:38:07", "throughput": 4634.44, "total_tokens": 15432000} {"current_steps": 15330, "total_steps": 42420, "loss": 0.225, "lr": 4.029766376964756e-05, "epoch": 7.227722772277228, "percentage": 36.14, "elapsed_time": "0:55:30", "remaining_time": "1:38:06", "throughput": 4634.52, "total_tokens": 15436896} {"current_steps": 15335, "total_steps": 42420, "loss": 0.0904, "lr": 4.028952696477763e-05, "epoch": 7.23008015087223, "percentage": 36.15, "elapsed_time": "0:55:31", "remaining_time": "1:38:04", "throughput": 4634.51, "total_tokens": 15441440} {"current_steps": 15340, "total_steps": 42420, "loss": 0.0818, "lr": 4.0281387571650374e-05, "epoch": 7.232437529467233, "percentage": 36.16, "elapsed_time": "0:55:32", "remaining_time": "1:38:03", "throughput": 4634.61, "total_tokens": 15446720} {"current_steps": 15345, "total_steps": 42420, "loss": 0.0798, "lr": 4.027324559164367e-05, "epoch": 7.234794908062235, "percentage": 36.17, "elapsed_time": "0:55:33", "remaining_time": "1:38:02", "throughput": 4634.65, "total_tokens": 15451200} {"current_steps": 15350, "total_steps": 42420, "loss": 0.1573, "lr": 4.026510102613581e-05, "epoch": 7.2371522866572375, "percentage": 36.19, "elapsed_time": "0:55:35", "remaining_time": "1:38:01", "throughput": 4634.75, "total_tokens": 15456992} {"current_steps": 15355, "total_steps": 42420, "loss": 0.1597, "lr": 4.025695387650554e-05, "epoch": 7.23950966525224, "percentage": 36.2, "elapsed_time": "0:55:35", "remaining_time": "1:37:59", "throughput": 4634.77, "total_tokens": 15461056} {"current_steps": 15360, "total_steps": 42420, "loss": 0.116, "lr": 4.0248804144132025e-05, "epoch": 7.2418670438472414, "percentage": 36.21, "elapsed_time": "0:55:36", "remaining_time": "1:37:58", "throughput": 4634.85, "total_tokens": 15466208} {"current_steps": 15365, "total_steps": 42420, "loss": 0.1462, "lr": 4.024065183039487e-05, "epoch": 7.244224422442244, "percentage": 36.22, "elapsed_time": "0:55:37", "remaining_time": "1:37:57", "throughput": 4634.85, "total_tokens": 15470400} {"current_steps": 15370, "total_steps": 42420, "loss": 0.1292, "lr": 4.023249693667414e-05, "epoch": 7.246581801037246, "percentage": 36.23, "elapsed_time": "0:55:38", "remaining_time": "1:37:56", "throughput": 4634.93, "total_tokens": 15475168} {"current_steps": 15375, "total_steps": 42420, "loss": 0.0743, "lr": 4.022433946435031e-05, "epoch": 7.248939179632249, "percentage": 36.24, "elapsed_time": "0:55:39", "remaining_time": "1:37:54", "throughput": 4634.97, "total_tokens": 15479872} {"current_steps": 15380, "total_steps": 42420, "loss": 0.1084, "lr": 4.0216179414804305e-05, "epoch": 7.251296558227251, "percentage": 36.26, "elapsed_time": "0:55:40", "remaining_time": "1:37:53", "throughput": 4635.05, "total_tokens": 15485088} {"current_steps": 15385, "total_steps": 42420, "loss": 0.2372, "lr": 4.020801678941748e-05, "epoch": 7.2536539368222535, "percentage": 36.27, "elapsed_time": "0:55:41", "remaining_time": "1:37:52", "throughput": 4635.13, "total_tokens": 15490080} {"current_steps": 15390, "total_steps": 42420, "loss": 0.2452, "lr": 4.0199851589571625e-05, "epoch": 7.256011315417256, "percentage": 36.28, "elapsed_time": "0:55:42", "remaining_time": "1:37:51", "throughput": 4635.22, "total_tokens": 15495360} {"current_steps": 15395, "total_steps": 42420, "loss": 0.224, "lr": 4.0191683816648985e-05, "epoch": 7.258368694012258, "percentage": 36.29, "elapsed_time": "0:55:43", "remaining_time": "1:37:50", "throughput": 4635.26, "total_tokens": 15499840} {"current_steps": 15400, "total_steps": 42420, "loss": 0.1918, "lr": 4.018351347203221e-05, "epoch": 7.260726072607261, "percentage": 36.3, "elapsed_time": "0:55:44", "remaining_time": "1:37:48", "throughput": 4635.23, "total_tokens": 15504352} {"current_steps": 15405, "total_steps": 42420, "loss": 0.1376, "lr": 4.01753405571044e-05, "epoch": 7.263083451202263, "percentage": 36.32, "elapsed_time": "0:55:45", "remaining_time": "1:37:47", "throughput": 4635.29, "total_tokens": 15509504} {"current_steps": 15410, "total_steps": 42420, "loss": 0.1133, "lr": 4.01671650732491e-05, "epoch": 7.2654408297972655, "percentage": 36.33, "elapsed_time": "0:55:47", "remaining_time": "1:37:46", "throughput": 4635.41, "total_tokens": 15515296} {"current_steps": 15415, "total_steps": 42420, "loss": 0.1389, "lr": 4.015898702185028e-05, "epoch": 7.267798208392268, "percentage": 36.34, "elapsed_time": "0:55:48", "remaining_time": "1:37:45", "throughput": 4635.5, "total_tokens": 15520384} {"current_steps": 15420, "total_steps": 42420, "loss": 0.1256, "lr": 4.015080640429234e-05, "epoch": 7.27015558698727, "percentage": 36.35, "elapsed_time": "0:55:49", "remaining_time": "1:37:44", "throughput": 4635.55, "total_tokens": 15524960} {"current_steps": 15425, "total_steps": 42420, "loss": 0.1924, "lr": 4.0142623221960126e-05, "epoch": 7.272512965582273, "percentage": 36.36, "elapsed_time": "0:55:50", "remaining_time": "1:37:43", "throughput": 4635.63, "total_tokens": 15530720} {"current_steps": 15430, "total_steps": 42420, "loss": 0.3297, "lr": 4.01344374762389e-05, "epoch": 7.274870344177275, "percentage": 36.37, "elapsed_time": "0:55:51", "remaining_time": "1:37:41", "throughput": 4635.66, "total_tokens": 15534976} {"current_steps": 15435, "total_steps": 42420, "loss": 0.0801, "lr": 4.012624916851438e-05, "epoch": 7.2772277227722775, "percentage": 36.39, "elapsed_time": "0:55:52", "remaining_time": "1:37:41", "throughput": 4635.79, "total_tokens": 15541376} {"current_steps": 15440, "total_steps": 42420, "loss": 0.1214, "lr": 4.0118058300172705e-05, "epoch": 7.27958510136728, "percentage": 36.4, "elapsed_time": "0:55:53", "remaining_time": "1:37:40", "throughput": 4635.84, "total_tokens": 15546720} {"current_steps": 15445, "total_steps": 42420, "loss": 0.2079, "lr": 4.0109864872600456e-05, "epoch": 7.281942479962282, "percentage": 36.41, "elapsed_time": "0:55:54", "remaining_time": "1:37:39", "throughput": 4635.93, "total_tokens": 15552320} {"current_steps": 15450, "total_steps": 42420, "loss": 0.127, "lr": 4.010166888718463e-05, "epoch": 7.284299858557285, "percentage": 36.42, "elapsed_time": "0:55:55", "remaining_time": "1:37:37", "throughput": 4635.9, "total_tokens": 15556128} {"current_steps": 15455, "total_steps": 42420, "loss": 0.1153, "lr": 4.009347034531267e-05, "epoch": 7.286657237152287, "percentage": 36.43, "elapsed_time": "0:55:56", "remaining_time": "1:37:36", "throughput": 4635.89, "total_tokens": 15560096} {"current_steps": 15460, "total_steps": 42420, "loss": 0.0882, "lr": 4.008526924837245e-05, "epoch": 7.2890146157472895, "percentage": 36.45, "elapsed_time": "0:55:57", "remaining_time": "1:37:35", "throughput": 4635.99, "total_tokens": 15565824} {"current_steps": 15465, "total_steps": 42420, "loss": 0.0995, "lr": 4.007706559775228e-05, "epoch": 7.291371994342291, "percentage": 36.46, "elapsed_time": "0:55:58", "remaining_time": "1:37:34", "throughput": 4636.06, "total_tokens": 15570944} {"current_steps": 15470, "total_steps": 42420, "loss": 0.1556, "lr": 4.006885939484091e-05, "epoch": 7.293729372937293, "percentage": 36.47, "elapsed_time": "0:55:59", "remaining_time": "1:37:32", "throughput": 4636.1, "total_tokens": 15575968} {"current_steps": 15475, "total_steps": 42420, "loss": 0.1866, "lr": 4.006065064102749e-05, "epoch": 7.296086751532296, "percentage": 36.48, "elapsed_time": "0:56:00", "remaining_time": "1:37:31", "throughput": 4636.15, "total_tokens": 15580832} {"current_steps": 15480, "total_steps": 42420, "loss": 0.0836, "lr": 4.0052439337701644e-05, "epoch": 7.298444130127298, "percentage": 36.49, "elapsed_time": "0:56:01", "remaining_time": "1:37:30", "throughput": 4636.13, "total_tokens": 15585152} {"current_steps": 15485, "total_steps": 42420, "loss": 0.293, "lr": 4.004422548625338e-05, "epoch": 7.300801508722301, "percentage": 36.5, "elapsed_time": "0:56:02", "remaining_time": "1:37:29", "throughput": 4636.21, "total_tokens": 15589952} {"current_steps": 15490, "total_steps": 42420, "loss": 0.0618, "lr": 4.003600908807318e-05, "epoch": 7.303158887317303, "percentage": 36.52, "elapsed_time": "0:56:03", "remaining_time": "1:37:28", "throughput": 4636.32, "total_tokens": 15595968} {"current_steps": 15495, "total_steps": 42420, "loss": 0.0607, "lr": 4.0027790144551935e-05, "epoch": 7.305516265912305, "percentage": 36.53, "elapsed_time": "0:56:04", "remaining_time": "1:37:27", "throughput": 4636.41, "total_tokens": 15601152} {"current_steps": 15500, "total_steps": 42420, "loss": 0.11, "lr": 4.001956865708099e-05, "epoch": 7.307873644507308, "percentage": 36.54, "elapsed_time": "0:56:05", "remaining_time": "1:37:25", "throughput": 4636.44, "total_tokens": 15605440} {"current_steps": 15505, "total_steps": 42420, "loss": 0.1285, "lr": 4.0011344627052075e-05, "epoch": 7.31023102310231, "percentage": 36.55, "elapsed_time": "0:56:06", "remaining_time": "1:37:24", "throughput": 4636.45, "total_tokens": 15610496} {"current_steps": 15510, "total_steps": 42420, "loss": 0.2575, "lr": 4.0003118055857404e-05, "epoch": 7.312588401697313, "percentage": 36.56, "elapsed_time": "0:56:08", "remaining_time": "1:37:23", "throughput": 4636.53, "total_tokens": 15616160} {"current_steps": 15515, "total_steps": 42420, "loss": 0.0724, "lr": 3.999488894488957e-05, "epoch": 7.314945780292315, "percentage": 36.57, "elapsed_time": "0:56:09", "remaining_time": "1:37:22", "throughput": 4636.54, "total_tokens": 15620960} {"current_steps": 15520, "total_steps": 42420, "loss": 0.173, "lr": 3.998665729554165e-05, "epoch": 7.317303158887317, "percentage": 36.59, "elapsed_time": "0:56:10", "remaining_time": "1:37:21", "throughput": 4636.58, "total_tokens": 15625600} {"current_steps": 15525, "total_steps": 42420, "loss": 0.0473, "lr": 3.99784231092071e-05, "epoch": 7.31966053748232, "percentage": 36.6, "elapsed_time": "0:56:11", "remaining_time": "1:37:19", "throughput": 4636.64, "total_tokens": 15630304} {"current_steps": 15530, "total_steps": 42420, "loss": 0.2229, "lr": 3.997018638727984e-05, "epoch": 7.322017916077322, "percentage": 36.61, "elapsed_time": "0:56:12", "remaining_time": "1:37:18", "throughput": 4636.71, "total_tokens": 15635232} {"current_steps": 15535, "total_steps": 42420, "loss": 0.1378, "lr": 3.996194713115421e-05, "epoch": 7.324375294672325, "percentage": 36.62, "elapsed_time": "0:56:13", "remaining_time": "1:37:17", "throughput": 4636.76, "total_tokens": 15640576} {"current_steps": 15540, "total_steps": 42420, "loss": 0.0279, "lr": 3.9953705342224964e-05, "epoch": 7.326732673267327, "percentage": 36.63, "elapsed_time": "0:56:14", "remaining_time": "1:37:16", "throughput": 4636.78, "total_tokens": 15644640} {"current_steps": 15545, "total_steps": 42420, "loss": 0.1876, "lr": 3.99454610218873e-05, "epoch": 7.329090051862329, "percentage": 36.65, "elapsed_time": "0:56:15", "remaining_time": "1:37:15", "throughput": 4636.77, "total_tokens": 15651296} {"current_steps": 15550, "total_steps": 42420, "loss": 0.1651, "lr": 3.993721417153685e-05, "epoch": 7.331447430457332, "percentage": 36.66, "elapsed_time": "0:56:16", "remaining_time": "1:37:14", "throughput": 4636.84, "total_tokens": 15656160} {"current_steps": 15555, "total_steps": 42420, "loss": 0.1749, "lr": 3.9928964792569655e-05, "epoch": 7.333804809052333, "percentage": 36.67, "elapsed_time": "0:56:17", "remaining_time": "1:37:13", "throughput": 4636.9, "total_tokens": 15661216} {"current_steps": 15560, "total_steps": 42420, "loss": 0.1413, "lr": 3.992071288638221e-05, "epoch": 7.336162187647336, "percentage": 36.68, "elapsed_time": "0:56:18", "remaining_time": "1:37:12", "throughput": 4637.01, "total_tokens": 15667360} {"current_steps": 15565, "total_steps": 42420, "loss": 0.2865, "lr": 3.99124584543714e-05, "epoch": 7.338519566242338, "percentage": 36.69, "elapsed_time": "0:56:19", "remaining_time": "1:37:11", "throughput": 4637.01, "total_tokens": 15671840} {"current_steps": 15570, "total_steps": 42420, "loss": 0.2956, "lr": 3.990420149793458e-05, "epoch": 7.3408769448373405, "percentage": 36.7, "elapsed_time": "0:56:20", "remaining_time": "1:37:10", "throughput": 4637.13, "total_tokens": 15677312} {"current_steps": 15575, "total_steps": 42420, "loss": 0.0663, "lr": 3.98959420184695e-05, "epoch": 7.343234323432343, "percentage": 36.72, "elapsed_time": "0:56:21", "remaining_time": "1:37:08", "throughput": 4637.12, "total_tokens": 15681408} {"current_steps": 15580, "total_steps": 42420, "loss": 0.2608, "lr": 3.988768001737436e-05, "epoch": 7.345591702027345, "percentage": 36.73, "elapsed_time": "0:56:22", "remaining_time": "1:37:07", "throughput": 4637.16, "total_tokens": 15685984} {"current_steps": 15585, "total_steps": 42420, "loss": 0.088, "lr": 3.9879415496047774e-05, "epoch": 7.347949080622348, "percentage": 36.74, "elapsed_time": "0:56:23", "remaining_time": "1:37:06", "throughput": 4637.19, "total_tokens": 15690400} {"current_steps": 15590, "total_steps": 42420, "loss": 0.1083, "lr": 3.9871148455888775e-05, "epoch": 7.35030645921735, "percentage": 36.75, "elapsed_time": "0:56:24", "remaining_time": "1:37:05", "throughput": 4637.25, "total_tokens": 15695936} {"current_steps": 15595, "total_steps": 42420, "loss": 0.1259, "lr": 3.986287889829685e-05, "epoch": 7.3526638378123526, "percentage": 36.76, "elapsed_time": "0:56:25", "remaining_time": "1:37:03", "throughput": 4637.31, "total_tokens": 15701184} {"current_steps": 15600, "total_steps": 42420, "loss": 0.1399, "lr": 3.985460682467187e-05, "epoch": 7.355021216407355, "percentage": 36.78, "elapsed_time": "0:56:26", "remaining_time": "1:37:02", "throughput": 4637.36, "total_tokens": 15705760} {"current_steps": 15605, "total_steps": 42420, "loss": 0.1596, "lr": 3.9846332236414186e-05, "epoch": 7.357378595002357, "percentage": 36.79, "elapsed_time": "0:56:27", "remaining_time": "1:37:01", "throughput": 4637.42, "total_tokens": 15710592} {"current_steps": 15610, "total_steps": 42420, "loss": 0.0991, "lr": 3.9838055134924526e-05, "epoch": 7.35973597359736, "percentage": 36.8, "elapsed_time": "0:56:28", "remaining_time": "1:37:00", "throughput": 4637.47, "total_tokens": 15714912} {"current_steps": 15615, "total_steps": 42420, "loss": 0.1805, "lr": 3.982977552160406e-05, "epoch": 7.362093352192362, "percentage": 36.81, "elapsed_time": "0:56:29", "remaining_time": "1:36:58", "throughput": 4637.52, "total_tokens": 15720032} {"current_steps": 15620, "total_steps": 42420, "loss": 0.1608, "lr": 3.98214933978544e-05, "epoch": 7.364450730787365, "percentage": 36.82, "elapsed_time": "0:56:30", "remaining_time": "1:36:57", "throughput": 4637.57, "total_tokens": 15725184} {"current_steps": 15625, "total_steps": 42420, "loss": 0.1788, "lr": 3.981320876507757e-05, "epoch": 7.366808109382367, "percentage": 36.83, "elapsed_time": "0:56:31", "remaining_time": "1:36:56", "throughput": 4637.6, "total_tokens": 15730208} {"current_steps": 15630, "total_steps": 42420, "loss": 0.1576, "lr": 3.9804921624676e-05, "epoch": 7.369165487977369, "percentage": 36.85, "elapsed_time": "0:56:32", "remaining_time": "1:36:55", "throughput": 4637.65, "total_tokens": 15734944} {"current_steps": 15635, "total_steps": 42420, "loss": 0.1038, "lr": 3.9796631978052575e-05, "epoch": 7.371522866572372, "percentage": 36.86, "elapsed_time": "0:56:33", "remaining_time": "1:36:54", "throughput": 4637.69, "total_tokens": 15739648} {"current_steps": 15640, "total_steps": 42420, "loss": 0.2457, "lr": 3.978833982661059e-05, "epoch": 7.373880245167374, "percentage": 36.87, "elapsed_time": "0:56:34", "remaining_time": "1:36:53", "throughput": 4637.66, "total_tokens": 15744544} {"current_steps": 15645, "total_steps": 42420, "loss": 0.097, "lr": 3.9780045171753764e-05, "epoch": 7.376237623762377, "percentage": 36.88, "elapsed_time": "0:56:35", "remaining_time": "1:36:51", "throughput": 4637.69, "total_tokens": 15749344} {"current_steps": 15650, "total_steps": 42420, "loss": 0.3234, "lr": 3.977174801488624e-05, "epoch": 7.378595002357379, "percentage": 36.89, "elapsed_time": "0:56:37", "remaining_time": "1:36:51", "throughput": 4637.82, "total_tokens": 15755488} {"current_steps": 15655, "total_steps": 42420, "loss": 0.1286, "lr": 3.976344835741258e-05, "epoch": 7.380952380952381, "percentage": 36.9, "elapsed_time": "0:56:38", "remaining_time": "1:36:49", "throughput": 4637.89, "total_tokens": 15760224} {"current_steps": 15660, "total_steps": 42420, "loss": 0.0586, "lr": 3.975514620073779e-05, "epoch": 7.383309759547384, "percentage": 36.92, "elapsed_time": "0:56:39", "remaining_time": "1:36:48", "throughput": 4637.89, "total_tokens": 15764512} {"current_steps": 15665, "total_steps": 42420, "loss": 0.2617, "lr": 3.974684154626728e-05, "epoch": 7.385667138142385, "percentage": 36.93, "elapsed_time": "0:56:40", "remaining_time": "1:36:47", "throughput": 4637.99, "total_tokens": 15769760} {"current_steps": 15670, "total_steps": 42420, "loss": 0.0945, "lr": 3.973853439540688e-05, "epoch": 7.388024516737388, "percentage": 36.94, "elapsed_time": "0:56:41", "remaining_time": "1:36:46", "throughput": 4638.07, "total_tokens": 15774656} {"current_steps": 15675, "total_steps": 42420, "loss": 0.1161, "lr": 3.973022474956285e-05, "epoch": 7.39038189533239, "percentage": 36.95, "elapsed_time": "0:56:42", "remaining_time": "1:36:44", "throughput": 4638.1, "total_tokens": 15779008} {"current_steps": 15680, "total_steps": 42420, "loss": 0.0939, "lr": 3.972191261014188e-05, "epoch": 7.3927392739273925, "percentage": 36.96, "elapsed_time": "0:56:43", "remaining_time": "1:36:43", "throughput": 4638.17, "total_tokens": 15784032} {"current_steps": 15685, "total_steps": 42420, "loss": 0.0357, "lr": 3.9713597978551066e-05, "epoch": 7.395096652522395, "percentage": 36.98, "elapsed_time": "0:56:44", "remaining_time": "1:36:42", "throughput": 4638.25, "total_tokens": 15789952} {"current_steps": 15690, "total_steps": 42420, "loss": 0.1526, "lr": 3.970528085619794e-05, "epoch": 7.397454031117397, "percentage": 36.99, "elapsed_time": "0:56:45", "remaining_time": "1:36:41", "throughput": 4638.15, "total_tokens": 15794048} {"current_steps": 15695, "total_steps": 42420, "loss": 0.0934, "lr": 3.969696124449044e-05, "epoch": 7.3998114097124, "percentage": 37.0, "elapsed_time": "0:56:46", "remaining_time": "1:36:40", "throughput": 4638.22, "total_tokens": 15799456} {"current_steps": 15700, "total_steps": 42420, "loss": 0.1602, "lr": 3.968863914483693e-05, "epoch": 7.402168788307402, "percentage": 37.01, "elapsed_time": "0:56:47", "remaining_time": "1:36:39", "throughput": 4638.3, "total_tokens": 15804576} {"current_steps": 15705, "total_steps": 42420, "loss": 0.0469, "lr": 3.9680314558646233e-05, "epoch": 7.4045261669024045, "percentage": 37.02, "elapsed_time": "0:56:48", "remaining_time": "1:36:38", "throughput": 4638.38, "total_tokens": 15809952} {"current_steps": 15710, "total_steps": 42420, "loss": 0.1553, "lr": 3.967198748732753e-05, "epoch": 7.406883545497407, "percentage": 37.03, "elapsed_time": "0:56:49", "remaining_time": "1:36:36", "throughput": 4638.43, "total_tokens": 15814528} {"current_steps": 15715, "total_steps": 42420, "loss": 0.1492, "lr": 3.9663657932290466e-05, "epoch": 7.409240924092409, "percentage": 37.05, "elapsed_time": "0:56:50", "remaining_time": "1:36:35", "throughput": 4638.51, "total_tokens": 15819488} {"current_steps": 15720, "total_steps": 42420, "loss": 0.1072, "lr": 3.965532589494508e-05, "epoch": 7.411598302687412, "percentage": 37.06, "elapsed_time": "0:56:51", "remaining_time": "1:36:34", "throughput": 4638.54, "total_tokens": 15824160} {"current_steps": 15725, "total_steps": 42420, "loss": 0.1172, "lr": 3.964699137670186e-05, "epoch": 7.413955681282414, "percentage": 37.07, "elapsed_time": "0:56:52", "remaining_time": "1:36:32", "throughput": 4638.55, "total_tokens": 15828384} {"current_steps": 15730, "total_steps": 42420, "loss": 0.1499, "lr": 3.963865437897169e-05, "epoch": 7.4163130598774165, "percentage": 37.08, "elapsed_time": "0:56:53", "remaining_time": "1:36:31", "throughput": 4638.65, "total_tokens": 15833920} {"current_steps": 15735, "total_steps": 42420, "loss": 0.1464, "lr": 3.9630314903165886e-05, "epoch": 7.418670438472419, "percentage": 37.09, "elapsed_time": "0:56:54", "remaining_time": "1:36:30", "throughput": 4638.71, "total_tokens": 15838496} {"current_steps": 15740, "total_steps": 42420, "loss": 0.0288, "lr": 3.9621972950696185e-05, "epoch": 7.421027817067421, "percentage": 37.11, "elapsed_time": "0:56:55", "remaining_time": "1:36:29", "throughput": 4638.8, "total_tokens": 15844096} {"current_steps": 15745, "total_steps": 42420, "loss": 0.1333, "lr": 3.961362852297472e-05, "epoch": 7.423385195662424, "percentage": 37.12, "elapsed_time": "0:56:56", "remaining_time": "1:36:28", "throughput": 4638.85, "total_tokens": 15848704} {"current_steps": 15750, "total_steps": 42420, "loss": 0.1358, "lr": 3.960528162141407e-05, "epoch": 7.425742574257426, "percentage": 37.13, "elapsed_time": "0:56:57", "remaining_time": "1:36:27", "throughput": 4638.95, "total_tokens": 15853792} {"current_steps": 15755, "total_steps": 42420, "loss": 0.1404, "lr": 3.959693224742723e-05, "epoch": 7.428099952852428, "percentage": 37.14, "elapsed_time": "0:56:58", "remaining_time": "1:36:25", "throughput": 4639.02, "total_tokens": 15858848} {"current_steps": 15760, "total_steps": 42420, "loss": 0.1876, "lr": 3.95885804024276e-05, "epoch": 7.43045733144743, "percentage": 37.15, "elapsed_time": "0:56:59", "remaining_time": "1:36:24", "throughput": 4639.11, "total_tokens": 15864032} {"current_steps": 15765, "total_steps": 42420, "loss": 0.165, "lr": 3.958022608782901e-05, "epoch": 7.432814710042432, "percentage": 37.16, "elapsed_time": "0:57:00", "remaining_time": "1:36:23", "throughput": 4639.16, "total_tokens": 15868832} {"current_steps": 15770, "total_steps": 42420, "loss": 0.0957, "lr": 3.95718693050457e-05, "epoch": 7.435172088637435, "percentage": 37.18, "elapsed_time": "0:57:01", "remaining_time": "1:36:22", "throughput": 4639.18, "total_tokens": 15873344} {"current_steps": 15775, "total_steps": 42420, "loss": 0.0764, "lr": 3.9563510055492336e-05, "epoch": 7.437529467232437, "percentage": 37.19, "elapsed_time": "0:57:02", "remaining_time": "1:36:21", "throughput": 4639.22, "total_tokens": 15878368} {"current_steps": 15780, "total_steps": 42420, "loss": 0.0591, "lr": 3.9555148340583994e-05, "epoch": 7.43988684582744, "percentage": 37.2, "elapsed_time": "0:57:03", "remaining_time": "1:36:20", "throughput": 4639.31, "total_tokens": 15884064} {"current_steps": 15785, "total_steps": 42420, "loss": 0.1305, "lr": 3.954678416173616e-05, "epoch": 7.442244224422442, "percentage": 37.21, "elapsed_time": "0:57:05", "remaining_time": "1:36:19", "throughput": 4639.42, "total_tokens": 15891200} {"current_steps": 15790, "total_steps": 42420, "loss": 0.2691, "lr": 3.9538417520364765e-05, "epoch": 7.4446016030174444, "percentage": 37.22, "elapsed_time": "0:57:06", "remaining_time": "1:36:18", "throughput": 4639.47, "total_tokens": 15895584} {"current_steps": 15795, "total_steps": 42420, "loss": 0.138, "lr": 3.953004841788613e-05, "epoch": 7.446958981612447, "percentage": 37.23, "elapsed_time": "0:57:07", "remaining_time": "1:36:17", "throughput": 4639.54, "total_tokens": 15900544} {"current_steps": 15800, "total_steps": 42420, "loss": 0.2289, "lr": 3.9521676855717006e-05, "epoch": 7.449316360207449, "percentage": 37.25, "elapsed_time": "0:57:08", "remaining_time": "1:36:15", "throughput": 4639.48, "total_tokens": 15904640} {"current_steps": 15805, "total_steps": 42420, "loss": 0.2135, "lr": 3.9513302835274557e-05, "epoch": 7.451673738802452, "percentage": 37.26, "elapsed_time": "0:57:09", "remaining_time": "1:36:14", "throughput": 4639.58, "total_tokens": 15910656} {"current_steps": 15810, "total_steps": 42420, "loss": 0.0574, "lr": 3.950492635797636e-05, "epoch": 7.454031117397454, "percentage": 37.27, "elapsed_time": "0:57:10", "remaining_time": "1:36:13", "throughput": 4639.6, "total_tokens": 15914912} {"current_steps": 15815, "total_steps": 42420, "loss": 0.0768, "lr": 3.94965474252404e-05, "epoch": 7.4563884959924565, "percentage": 37.28, "elapsed_time": "0:57:11", "remaining_time": "1:36:12", "throughput": 4639.69, "total_tokens": 15920256} {"current_steps": 15820, "total_steps": 42420, "loss": 0.1448, "lr": 3.948816603848511e-05, "epoch": 7.458745874587459, "percentage": 37.29, "elapsed_time": "0:57:12", "remaining_time": "1:36:11", "throughput": 4639.74, "total_tokens": 15924928} {"current_steps": 15825, "total_steps": 42420, "loss": 0.1566, "lr": 3.94797821991293e-05, "epoch": 7.461103253182461, "percentage": 37.31, "elapsed_time": "0:57:13", "remaining_time": "1:36:09", "throughput": 4639.8, "total_tokens": 15929792} {"current_steps": 15830, "total_steps": 42420, "loss": 0.0911, "lr": 3.9471395908592214e-05, "epoch": 7.463460631777464, "percentage": 37.32, "elapsed_time": "0:57:14", "remaining_time": "1:36:08", "throughput": 4639.86, "total_tokens": 15934976} {"current_steps": 15835, "total_steps": 42420, "loss": 0.0864, "lr": 3.946300716829352e-05, "epoch": 7.465818010372466, "percentage": 37.33, "elapsed_time": "0:57:15", "remaining_time": "1:36:07", "throughput": 4639.91, "total_tokens": 15939936} {"current_steps": 15840, "total_steps": 42420, "loss": 0.0277, "lr": 3.945461597965327e-05, "epoch": 7.4681753889674685, "percentage": 37.34, "elapsed_time": "0:57:16", "remaining_time": "1:36:06", "throughput": 4639.87, "total_tokens": 15943840} {"current_steps": 15845, "total_steps": 42420, "loss": 0.1222, "lr": 3.9446222344091965e-05, "epoch": 7.470532767562471, "percentage": 37.35, "elapsed_time": "0:57:17", "remaining_time": "1:36:04", "throughput": 4639.92, "total_tokens": 15948800} {"current_steps": 15850, "total_steps": 42420, "loss": 0.1243, "lr": 3.94378262630305e-05, "epoch": 7.472890146157473, "percentage": 37.36, "elapsed_time": "0:57:18", "remaining_time": "1:36:03", "throughput": 4639.89, "total_tokens": 15952800} {"current_steps": 15855, "total_steps": 42420, "loss": 0.091, "lr": 3.942942773789019e-05, "epoch": 7.475247524752476, "percentage": 37.38, "elapsed_time": "0:57:19", "remaining_time": "1:36:02", "throughput": 4639.93, "total_tokens": 15957472} {"current_steps": 15860, "total_steps": 42420, "loss": 0.1419, "lr": 3.9421026770092756e-05, "epoch": 7.477604903347478, "percentage": 37.39, "elapsed_time": "0:57:20", "remaining_time": "1:36:01", "throughput": 4640.0, "total_tokens": 15963424} {"current_steps": 15865, "total_steps": 42420, "loss": 0.2388, "lr": 3.941262336106035e-05, "epoch": 7.47996228194248, "percentage": 37.4, "elapsed_time": "0:57:21", "remaining_time": "1:36:00", "throughput": 4640.06, "total_tokens": 15968288} {"current_steps": 15870, "total_steps": 42420, "loss": 0.0816, "lr": 3.9404217512215525e-05, "epoch": 7.482319660537482, "percentage": 37.41, "elapsed_time": "0:57:22", "remaining_time": "1:35:58", "throughput": 4640.06, "total_tokens": 15972416} {"current_steps": 15875, "total_steps": 42420, "loss": 0.0451, "lr": 3.939580922498124e-05, "epoch": 7.484677039132484, "percentage": 37.42, "elapsed_time": "0:57:23", "remaining_time": "1:35:57", "throughput": 4640.15, "total_tokens": 15977600} {"current_steps": 15880, "total_steps": 42420, "loss": 0.3321, "lr": 3.9387398500780884e-05, "epoch": 7.487034417727487, "percentage": 37.44, "elapsed_time": "0:57:24", "remaining_time": "1:35:56", "throughput": 4640.25, "total_tokens": 15983744} {"current_steps": 15885, "total_steps": 42420, "loss": 0.0432, "lr": 3.9378985341038235e-05, "epoch": 7.489391796322489, "percentage": 37.45, "elapsed_time": "0:57:25", "remaining_time": "1:35:55", "throughput": 4640.3, "total_tokens": 15988800} {"current_steps": 15890, "total_steps": 42420, "loss": 0.1854, "lr": 3.9370569747177514e-05, "epoch": 7.491749174917492, "percentage": 37.46, "elapsed_time": "0:57:26", "remaining_time": "1:35:54", "throughput": 4640.39, "total_tokens": 15994080} {"current_steps": 15895, "total_steps": 42420, "loss": 0.2173, "lr": 3.9362151720623336e-05, "epoch": 7.494106553512494, "percentage": 37.47, "elapsed_time": "0:57:27", "remaining_time": "1:35:53", "throughput": 4640.46, "total_tokens": 15999328} {"current_steps": 15900, "total_steps": 42420, "loss": 0.1905, "lr": 3.935373126280073e-05, "epoch": 7.496463932107496, "percentage": 37.48, "elapsed_time": "0:57:29", "remaining_time": "1:35:52", "throughput": 4640.59, "total_tokens": 16005408} {"current_steps": 15905, "total_steps": 42420, "loss": 0.1595, "lr": 3.934530837513512e-05, "epoch": 7.498821310702499, "percentage": 37.49, "elapsed_time": "0:57:30", "remaining_time": "1:35:51", "throughput": 4640.68, "total_tokens": 16010592} {"current_steps": 15910, "total_steps": 42420, "loss": 0.0857, "lr": 3.9336883059052385e-05, "epoch": 7.501178689297501, "percentage": 37.51, "elapsed_time": "0:57:31", "remaining_time": "1:35:50", "throughput": 4640.68, "total_tokens": 16015296} {"current_steps": 15915, "total_steps": 42420, "loss": 0.1869, "lr": 3.9328455315978775e-05, "epoch": 7.503536067892504, "percentage": 37.52, "elapsed_time": "0:57:32", "remaining_time": "1:35:49", "throughput": 4640.78, "total_tokens": 16020704} {"current_steps": 15920, "total_steps": 42420, "loss": 0.0514, "lr": 3.932002514734096e-05, "epoch": 7.505893446487506, "percentage": 37.53, "elapsed_time": "0:57:33", "remaining_time": "1:35:48", "throughput": 4640.84, "total_tokens": 16025728} {"current_steps": 15925, "total_steps": 42420, "loss": 0.0984, "lr": 3.9311592554566026e-05, "epoch": 7.508250825082508, "percentage": 37.54, "elapsed_time": "0:57:34", "remaining_time": "1:35:47", "throughput": 4640.93, "total_tokens": 16031072} {"current_steps": 15930, "total_steps": 42420, "loss": 0.0573, "lr": 3.930315753908147e-05, "epoch": 7.510608203677511, "percentage": 37.55, "elapsed_time": "0:57:35", "remaining_time": "1:35:45", "throughput": 4640.93, "total_tokens": 16035040} {"current_steps": 15935, "total_steps": 42420, "loss": 0.1264, "lr": 3.92947201023152e-05, "epoch": 7.512965582272513, "percentage": 37.56, "elapsed_time": "0:57:36", "remaining_time": "1:35:44", "throughput": 4641.04, "total_tokens": 16041760} {"current_steps": 15940, "total_steps": 42420, "loss": 0.1933, "lr": 3.928628024569552e-05, "epoch": 7.515322960867516, "percentage": 37.58, "elapsed_time": "0:57:37", "remaining_time": "1:35:43", "throughput": 4641.13, "total_tokens": 16046560} {"current_steps": 15945, "total_steps": 42420, "loss": 0.1998, "lr": 3.9277837970651165e-05, "epoch": 7.517680339462518, "percentage": 37.59, "elapsed_time": "0:57:38", "remaining_time": "1:35:42", "throughput": 4641.26, "total_tokens": 16052704} {"current_steps": 15950, "total_steps": 42420, "loss": 0.1095, "lr": 3.926939327861127e-05, "epoch": 7.52003771805752, "percentage": 37.6, "elapsed_time": "0:57:39", "remaining_time": "1:35:41", "throughput": 4641.28, "total_tokens": 16057312} {"current_steps": 15955, "total_steps": 42420, "loss": 0.314, "lr": 3.926094617100537e-05, "epoch": 7.522395096652522, "percentage": 37.61, "elapsed_time": "0:57:40", "remaining_time": "1:35:40", "throughput": 4641.27, "total_tokens": 16062048} {"current_steps": 15960, "total_steps": 42420, "loss": 0.1201, "lr": 3.925249664926342e-05, "epoch": 7.524752475247524, "percentage": 37.62, "elapsed_time": "0:57:41", "remaining_time": "1:35:39", "throughput": 4641.31, "total_tokens": 16066656} {"current_steps": 15965, "total_steps": 42420, "loss": 0.1327, "lr": 3.924404471481578e-05, "epoch": 7.527109853842527, "percentage": 37.64, "elapsed_time": "0:57:42", "remaining_time": "1:35:37", "throughput": 4641.34, "total_tokens": 16071264} {"current_steps": 15970, "total_steps": 42420, "loss": 0.0728, "lr": 3.9235590369093225e-05, "epoch": 7.529467232437529, "percentage": 37.65, "elapsed_time": "0:57:43", "remaining_time": "1:35:37", "throughput": 4641.48, "total_tokens": 16077632} {"current_steps": 15975, "total_steps": 42420, "loss": 0.1127, "lr": 3.922713361352692e-05, "epoch": 7.5318246110325315, "percentage": 37.66, "elapsed_time": "0:57:44", "remaining_time": "1:35:35", "throughput": 4641.47, "total_tokens": 16082208} {"current_steps": 15980, "total_steps": 42420, "loss": 0.0583, "lr": 3.9218674449548466e-05, "epoch": 7.534181989627534, "percentage": 37.67, "elapsed_time": "0:57:45", "remaining_time": "1:35:34", "throughput": 4641.47, "total_tokens": 16086464} {"current_steps": 15985, "total_steps": 42420, "loss": 0.0912, "lr": 3.921021287858984e-05, "epoch": 7.536539368222536, "percentage": 37.68, "elapsed_time": "0:57:46", "remaining_time": "1:35:33", "throughput": 4641.58, "total_tokens": 16092000} {"current_steps": 15990, "total_steps": 42420, "loss": 0.2073, "lr": 3.920174890208345e-05, "epoch": 7.538896746817539, "percentage": 37.69, "elapsed_time": "0:57:47", "remaining_time": "1:35:32", "throughput": 4641.6, "total_tokens": 16096352} {"current_steps": 15995, "total_steps": 42420, "loss": 0.1266, "lr": 3.9193282521462106e-05, "epoch": 7.541254125412541, "percentage": 37.71, "elapsed_time": "0:57:48", "remaining_time": "1:35:30", "throughput": 4641.66, "total_tokens": 16101664} {"current_steps": 16000, "total_steps": 42420, "loss": 0.1457, "lr": 3.918481373815901e-05, "epoch": 7.5436115040075435, "percentage": 37.72, "elapsed_time": "0:57:50", "remaining_time": "1:35:29", "throughput": 4641.76, "total_tokens": 16107040} {"current_steps": 16005, "total_steps": 42420, "loss": 0.0835, "lr": 3.9176342553607806e-05, "epoch": 7.545968882602546, "percentage": 37.73, "elapsed_time": "0:57:51", "remaining_time": "1:35:28", "throughput": 4641.76, "total_tokens": 16111744} {"current_steps": 16010, "total_steps": 42420, "loss": 0.2402, "lr": 3.91678689692425e-05, "epoch": 7.548326261197548, "percentage": 37.74, "elapsed_time": "0:57:52", "remaining_time": "1:35:27", "throughput": 4641.73, "total_tokens": 16116512} {"current_steps": 16015, "total_steps": 42420, "loss": 0.0548, "lr": 3.915939298649753e-05, "epoch": 7.550683639792551, "percentage": 37.75, "elapsed_time": "0:57:53", "remaining_time": "1:35:26", "throughput": 4641.81, "total_tokens": 16121792} {"current_steps": 16020, "total_steps": 42420, "loss": 0.1599, "lr": 3.915091460680775e-05, "epoch": 7.553041018387553, "percentage": 37.77, "elapsed_time": "0:57:54", "remaining_time": "1:35:25", "throughput": 4641.88, "total_tokens": 16126816} {"current_steps": 16025, "total_steps": 42420, "loss": 0.1632, "lr": 3.914243383160839e-05, "epoch": 7.5553983969825556, "percentage": 37.78, "elapsed_time": "0:57:55", "remaining_time": "1:35:24", "throughput": 4641.93, "total_tokens": 16131744} {"current_steps": 16030, "total_steps": 42420, "loss": 0.101, "lr": 3.9133950662335114e-05, "epoch": 7.557755775577558, "percentage": 37.79, "elapsed_time": "0:57:56", "remaining_time": "1:35:22", "throughput": 4641.95, "total_tokens": 16136544} {"current_steps": 16035, "total_steps": 42420, "loss": 0.0664, "lr": 3.912546510042396e-05, "epoch": 7.56011315417256, "percentage": 37.8, "elapsed_time": "0:57:57", "remaining_time": "1:35:21", "throughput": 4642.02, "total_tokens": 16141888} {"current_steps": 16040, "total_steps": 42420, "loss": 0.0982, "lr": 3.911697714731141e-05, "epoch": 7.562470532767563, "percentage": 37.81, "elapsed_time": "0:57:58", "remaining_time": "1:35:20", "throughput": 4642.06, "total_tokens": 16146688} {"current_steps": 16045, "total_steps": 42420, "loss": 0.2252, "lr": 3.910848680443433e-05, "epoch": 7.564827911362565, "percentage": 37.82, "elapsed_time": "0:57:59", "remaining_time": "1:35:19", "throughput": 4642.09, "total_tokens": 16151424} {"current_steps": 16050, "total_steps": 42420, "loss": 0.0476, "lr": 3.909999407322996e-05, "epoch": 7.567185289957568, "percentage": 37.84, "elapsed_time": "0:58:00", "remaining_time": "1:35:18", "throughput": 4642.12, "total_tokens": 16156192} {"current_steps": 16055, "total_steps": 42420, "loss": 0.0594, "lr": 3.909149895513602e-05, "epoch": 7.56954266855257, "percentage": 37.85, "elapsed_time": "0:58:01", "remaining_time": "1:35:17", "throughput": 4642.17, "total_tokens": 16161120} {"current_steps": 16060, "total_steps": 42420, "loss": 0.0728, "lr": 3.908300145159055e-05, "epoch": 7.571900047147572, "percentage": 37.86, "elapsed_time": "0:58:02", "remaining_time": "1:35:15", "throughput": 4642.22, "total_tokens": 16166080} {"current_steps": 16065, "total_steps": 42420, "loss": 0.1246, "lr": 3.907450156403206e-05, "epoch": 7.574257425742574, "percentage": 37.87, "elapsed_time": "0:58:03", "remaining_time": "1:35:14", "throughput": 4642.22, "total_tokens": 16170912} {"current_steps": 16070, "total_steps": 42420, "loss": 0.1532, "lr": 3.9065999293899425e-05, "epoch": 7.576614804337576, "percentage": 37.88, "elapsed_time": "0:58:04", "remaining_time": "1:35:13", "throughput": 4642.3, "total_tokens": 16176160} {"current_steps": 16075, "total_steps": 42420, "loss": 0.0748, "lr": 3.905749464263193e-05, "epoch": 7.578972182932579, "percentage": 37.89, "elapsed_time": "0:58:05", "remaining_time": "1:35:12", "throughput": 4642.39, "total_tokens": 16181728} {"current_steps": 16080, "total_steps": 42420, "loss": 0.047, "lr": 3.904898761166929e-05, "epoch": 7.581329561527581, "percentage": 37.91, "elapsed_time": "0:58:06", "remaining_time": "1:35:11", "throughput": 4642.44, "total_tokens": 16186752} {"current_steps": 16085, "total_steps": 42420, "loss": 0.1347, "lr": 3.904047820245157e-05, "epoch": 7.5836869401225835, "percentage": 37.92, "elapsed_time": "0:58:07", "remaining_time": "1:35:10", "throughput": 4642.45, "total_tokens": 16191296} {"current_steps": 16090, "total_steps": 42420, "loss": 0.1184, "lr": 3.903196641641929e-05, "epoch": 7.586044318717586, "percentage": 37.93, "elapsed_time": "0:58:08", "remaining_time": "1:35:08", "throughput": 4642.49, "total_tokens": 16195680} {"current_steps": 16095, "total_steps": 42420, "loss": 0.1459, "lr": 3.902345225501334e-05, "epoch": 7.588401697312588, "percentage": 37.94, "elapsed_time": "0:58:09", "remaining_time": "1:35:07", "throughput": 4642.59, "total_tokens": 16201664} {"current_steps": 16100, "total_steps": 42420, "loss": 0.1589, "lr": 3.901493571967504e-05, "epoch": 7.590759075907591, "percentage": 37.95, "elapsed_time": "0:58:10", "remaining_time": "1:35:06", "throughput": 4642.61, "total_tokens": 16206496} {"current_steps": 16105, "total_steps": 42420, "loss": 0.0567, "lr": 3.900641681184607e-05, "epoch": 7.593116454502593, "percentage": 37.97, "elapsed_time": "0:58:11", "remaining_time": "1:35:05", "throughput": 4642.72, "total_tokens": 16212288} {"current_steps": 16110, "total_steps": 42420, "loss": 0.0862, "lr": 3.8997895532968554e-05, "epoch": 7.5954738330975955, "percentage": 37.98, "elapsed_time": "0:58:13", "remaining_time": "1:35:04", "throughput": 4642.83, "total_tokens": 16217952} {"current_steps": 16115, "total_steps": 42420, "loss": 0.226, "lr": 3.8989371884484994e-05, "epoch": 7.597831211692598, "percentage": 37.99, "elapsed_time": "0:58:14", "remaining_time": "1:35:03", "throughput": 4642.88, "total_tokens": 16222560} {"current_steps": 16120, "total_steps": 42420, "loss": 0.129, "lr": 3.898084586783831e-05, "epoch": 7.6001885902876, "percentage": 38.0, "elapsed_time": "0:58:15", "remaining_time": "1:35:02", "throughput": 4642.89, "total_tokens": 16227232} {"current_steps": 16125, "total_steps": 42420, "loss": 0.0339, "lr": 3.897231748447179e-05, "epoch": 7.602545968882603, "percentage": 38.01, "elapsed_time": "0:58:16", "remaining_time": "1:35:01", "throughput": 4642.94, "total_tokens": 16232128} {"current_steps": 16130, "total_steps": 42420, "loss": 0.0666, "lr": 3.896378673582915e-05, "epoch": 7.604903347477605, "percentage": 38.02, "elapsed_time": "0:58:17", "remaining_time": "1:34:59", "throughput": 4643.0, "total_tokens": 16237120} {"current_steps": 16135, "total_steps": 42420, "loss": 0.1786, "lr": 3.895525362335452e-05, "epoch": 7.6072607260726075, "percentage": 38.04, "elapsed_time": "0:58:18", "remaining_time": "1:34:58", "throughput": 4643.06, "total_tokens": 16242080} {"current_steps": 16140, "total_steps": 42420, "loss": 0.1475, "lr": 3.89467181484924e-05, "epoch": 7.60961810466761, "percentage": 38.05, "elapsed_time": "0:58:19", "remaining_time": "1:34:57", "throughput": 4643.06, "total_tokens": 16246368} {"current_steps": 16145, "total_steps": 42420, "loss": 0.1224, "lr": 3.8938180312687686e-05, "epoch": 7.611975483262612, "percentage": 38.06, "elapsed_time": "0:58:20", "remaining_time": "1:34:56", "throughput": 4643.13, "total_tokens": 16251584} {"current_steps": 16150, "total_steps": 42420, "loss": 0.2192, "lr": 3.892964011738571e-05, "epoch": 7.614332861857615, "percentage": 38.07, "elapsed_time": "0:58:20", "remaining_time": "1:34:54", "throughput": 4643.13, "total_tokens": 16255552} {"current_steps": 16155, "total_steps": 42420, "loss": 0.2286, "lr": 3.892109756403218e-05, "epoch": 7.616690240452616, "percentage": 38.08, "elapsed_time": "0:58:22", "remaining_time": "1:34:53", "throughput": 4643.21, "total_tokens": 16260960} {"current_steps": 16160, "total_steps": 42420, "loss": 0.0739, "lr": 3.891255265407319e-05, "epoch": 7.619047619047619, "percentage": 38.1, "elapsed_time": "0:58:23", "remaining_time": "1:34:52", "throughput": 4643.27, "total_tokens": 16265728} {"current_steps": 16165, "total_steps": 42420, "loss": 0.0848, "lr": 3.890400538895526e-05, "epoch": 7.621404997642621, "percentage": 38.11, "elapsed_time": "0:58:23", "remaining_time": "1:34:51", "throughput": 4643.19, "total_tokens": 16269312} {"current_steps": 16170, "total_steps": 42420, "loss": 0.1851, "lr": 3.88954557701253e-05, "epoch": 7.623762376237623, "percentage": 38.12, "elapsed_time": "0:58:24", "remaining_time": "1:34:49", "throughput": 4643.13, "total_tokens": 16273152} {"current_steps": 16175, "total_steps": 42420, "loss": 0.0351, "lr": 3.88869037990306e-05, "epoch": 7.626119754832626, "percentage": 38.13, "elapsed_time": "0:58:25", "remaining_time": "1:34:48", "throughput": 4643.2, "total_tokens": 16278112} {"current_steps": 16180, "total_steps": 42420, "loss": 0.1095, "lr": 3.887834947711888e-05, "epoch": 7.628477133427628, "percentage": 38.14, "elapsed_time": "0:58:26", "remaining_time": "1:34:47", "throughput": 4643.24, "total_tokens": 16282688} {"current_steps": 16185, "total_steps": 42420, "loss": 0.1023, "lr": 3.886979280583823e-05, "epoch": 7.630834512022631, "percentage": 38.15, "elapsed_time": "0:58:27", "remaining_time": "1:34:45", "throughput": 4643.27, "total_tokens": 16287136} {"current_steps": 16190, "total_steps": 42420, "loss": 0.1471, "lr": 3.886123378663715e-05, "epoch": 7.633191890617633, "percentage": 38.17, "elapsed_time": "0:58:28", "remaining_time": "1:34:44", "throughput": 4643.35, "total_tokens": 16292480} {"current_steps": 16195, "total_steps": 42420, "loss": 0.0491, "lr": 3.885267242096455e-05, "epoch": 7.635549269212635, "percentage": 38.18, "elapsed_time": "0:58:29", "remaining_time": "1:34:43", "throughput": 4643.42, "total_tokens": 16297728} {"current_steps": 16200, "total_steps": 42420, "loss": 0.096, "lr": 3.884410871026971e-05, "epoch": 7.637906647807638, "percentage": 38.19, "elapsed_time": "0:58:30", "remaining_time": "1:34:42", "throughput": 4643.41, "total_tokens": 16301728} {"current_steps": 16205, "total_steps": 42420, "loss": 0.2611, "lr": 3.8835542656002324e-05, "epoch": 7.64026402640264, "percentage": 38.2, "elapsed_time": "0:58:31", "remaining_time": "1:34:41", "throughput": 4643.51, "total_tokens": 16307616} {"current_steps": 16210, "total_steps": 42420, "loss": 0.0886, "lr": 3.882697425961248e-05, "epoch": 7.642621404997643, "percentage": 38.21, "elapsed_time": "0:58:33", "remaining_time": "1:34:40", "throughput": 4643.57, "total_tokens": 16313056} {"current_steps": 16215, "total_steps": 42420, "loss": 0.1556, "lr": 3.8818403522550674e-05, "epoch": 7.644978783592645, "percentage": 38.22, "elapsed_time": "0:58:34", "remaining_time": "1:34:39", "throughput": 4643.64, "total_tokens": 16317920} {"current_steps": 16220, "total_steps": 42420, "loss": 0.1539, "lr": 3.8809830446267756e-05, "epoch": 7.6473361621876474, "percentage": 38.24, "elapsed_time": "0:58:35", "remaining_time": "1:34:37", "throughput": 4643.67, "total_tokens": 16322592} {"current_steps": 16225, "total_steps": 42420, "loss": 0.1537, "lr": 3.8801255032215036e-05, "epoch": 7.64969354078265, "percentage": 38.25, "elapsed_time": "0:58:36", "remaining_time": "1:34:36", "throughput": 4643.74, "total_tokens": 16327648} {"current_steps": 16230, "total_steps": 42420, "loss": 0.0469, "lr": 3.879267728184416e-05, "epoch": 7.652050919377652, "percentage": 38.26, "elapsed_time": "0:58:37", "remaining_time": "1:34:35", "throughput": 4643.81, "total_tokens": 16332768} {"current_steps": 16235, "total_steps": 42420, "loss": 0.1446, "lr": 3.8784097196607215e-05, "epoch": 7.654408297972655, "percentage": 38.27, "elapsed_time": "0:58:37", "remaining_time": "1:34:33", "throughput": 4643.79, "total_tokens": 16336576} {"current_steps": 16240, "total_steps": 42420, "loss": 0.0321, "lr": 3.8775514777956645e-05, "epoch": 7.656765676567657, "percentage": 38.28, "elapsed_time": "0:58:38", "remaining_time": "1:34:32", "throughput": 4643.86, "total_tokens": 16341472} {"current_steps": 16245, "total_steps": 42420, "loss": 0.2432, "lr": 3.8766930027345326e-05, "epoch": 7.6591230551626595, "percentage": 38.3, "elapsed_time": "0:58:40", "remaining_time": "1:34:31", "throughput": 4643.93, "total_tokens": 16347264} {"current_steps": 16250, "total_steps": 42420, "loss": 0.104, "lr": 3.87583429462265e-05, "epoch": 7.661480433757662, "percentage": 38.31, "elapsed_time": "0:58:41", "remaining_time": "1:34:30", "throughput": 4643.92, "total_tokens": 16351712} {"current_steps": 16255, "total_steps": 42420, "loss": 0.0912, "lr": 3.8749753536053824e-05, "epoch": 7.663837812352664, "percentage": 38.32, "elapsed_time": "0:58:42", "remaining_time": "1:34:29", "throughput": 4643.93, "total_tokens": 16356512} {"current_steps": 16260, "total_steps": 42420, "loss": 0.1071, "lr": 3.874116179828132e-05, "epoch": 7.666195190947667, "percentage": 38.33, "elapsed_time": "0:58:43", "remaining_time": "1:34:28", "throughput": 4644.04, "total_tokens": 16362560} {"current_steps": 16265, "total_steps": 42420, "loss": 0.1191, "lr": 3.873256773436344e-05, "epoch": 7.668552569542668, "percentage": 38.34, "elapsed_time": "0:58:44", "remaining_time": "1:34:27", "throughput": 4644.09, "total_tokens": 16367520} {"current_steps": 16270, "total_steps": 42420, "loss": 0.1967, "lr": 3.8723971345755005e-05, "epoch": 7.670909948137671, "percentage": 38.35, "elapsed_time": "0:58:45", "remaining_time": "1:34:26", "throughput": 4644.16, "total_tokens": 16372800} {"current_steps": 16275, "total_steps": 42420, "loss": 0.1319, "lr": 3.8715372633911254e-05, "epoch": 7.673267326732673, "percentage": 38.37, "elapsed_time": "0:58:46", "remaining_time": "1:34:25", "throughput": 4644.25, "total_tokens": 16378272} {"current_steps": 16280, "total_steps": 42420, "loss": 0.0782, "lr": 3.870677160028777e-05, "epoch": 7.675624705327675, "percentage": 38.38, "elapsed_time": "0:58:47", "remaining_time": "1:34:24", "throughput": 4644.3, "total_tokens": 16382944} {"current_steps": 16285, "total_steps": 42420, "loss": 0.1908, "lr": 3.86981682463406e-05, "epoch": 7.677982083922678, "percentage": 38.39, "elapsed_time": "0:58:48", "remaining_time": "1:34:22", "throughput": 4644.36, "total_tokens": 16387936} {"current_steps": 16290, "total_steps": 42420, "loss": 0.0919, "lr": 3.8689562573526116e-05, "epoch": 7.68033946251768, "percentage": 38.4, "elapsed_time": "0:58:49", "remaining_time": "1:34:21", "throughput": 4644.43, "total_tokens": 16392896} {"current_steps": 16295, "total_steps": 42420, "loss": 0.2033, "lr": 3.868095458330113e-05, "epoch": 7.682696841112683, "percentage": 38.41, "elapsed_time": "0:58:50", "remaining_time": "1:34:20", "throughput": 4644.5, "total_tokens": 16398688} {"current_steps": 16300, "total_steps": 42420, "loss": 0.1452, "lr": 3.867234427712282e-05, "epoch": 7.685054219707685, "percentage": 38.43, "elapsed_time": "0:58:51", "remaining_time": "1:34:19", "throughput": 4644.6, "total_tokens": 16404032} {"current_steps": 16305, "total_steps": 42420, "loss": 0.1178, "lr": 3.8663731656448764e-05, "epoch": 7.687411598302687, "percentage": 38.44, "elapsed_time": "0:58:52", "remaining_time": "1:34:18", "throughput": 4644.64, "total_tokens": 16408992} {"current_steps": 16310, "total_steps": 42420, "loss": 0.0321, "lr": 3.865511672273694e-05, "epoch": 7.68976897689769, "percentage": 38.45, "elapsed_time": "0:58:54", "remaining_time": "1:34:17", "throughput": 4644.74, "total_tokens": 16414688} {"current_steps": 16315, "total_steps": 42420, "loss": 0.1934, "lr": 3.864649947744571e-05, "epoch": 7.692126355492692, "percentage": 38.46, "elapsed_time": "0:58:55", "remaining_time": "1:34:16", "throughput": 4644.81, "total_tokens": 16419456} {"current_steps": 16320, "total_steps": 42420, "loss": 0.1363, "lr": 3.863787992203381e-05, "epoch": 7.694483734087695, "percentage": 38.47, "elapsed_time": "0:58:56", "remaining_time": "1:34:15", "throughput": 4644.84, "total_tokens": 16424160} {"current_steps": 16325, "total_steps": 42420, "loss": 0.1531, "lr": 3.8629258057960416e-05, "epoch": 7.696841112682697, "percentage": 38.48, "elapsed_time": "0:58:57", "remaining_time": "1:34:14", "throughput": 4644.9, "total_tokens": 16429792} {"current_steps": 16330, "total_steps": 42420, "loss": 0.0933, "lr": 3.862063388668503e-05, "epoch": 7.699198491277699, "percentage": 38.5, "elapsed_time": "0:58:58", "remaining_time": "1:34:12", "throughput": 4644.98, "total_tokens": 16434976} {"current_steps": 16335, "total_steps": 42420, "loss": 0.2653, "lr": 3.8612007409667595e-05, "epoch": 7.701555869872702, "percentage": 38.51, "elapsed_time": "0:58:59", "remaining_time": "1:34:11", "throughput": 4645.08, "total_tokens": 16440640} {"current_steps": 16340, "total_steps": 42420, "loss": 0.1044, "lr": 3.860337862836843e-05, "epoch": 7.703913248467704, "percentage": 38.52, "elapsed_time": "0:59:00", "remaining_time": "1:34:10", "throughput": 4645.17, "total_tokens": 16446144} {"current_steps": 16345, "total_steps": 42420, "loss": 0.2023, "lr": 3.859474754424822e-05, "epoch": 7.706270627062707, "percentage": 38.53, "elapsed_time": "0:59:01", "remaining_time": "1:34:09", "throughput": 4645.21, "total_tokens": 16450720} {"current_steps": 16350, "total_steps": 42420, "loss": 0.176, "lr": 3.858611415876809e-05, "epoch": 7.708628005657709, "percentage": 38.54, "elapsed_time": "0:59:02", "remaining_time": "1:34:08", "throughput": 4645.25, "total_tokens": 16455904} {"current_steps": 16355, "total_steps": 42420, "loss": 0.1995, "lr": 3.8577478473389504e-05, "epoch": 7.7109853842527105, "percentage": 38.55, "elapsed_time": "0:59:03", "remaining_time": "1:34:07", "throughput": 4645.3, "total_tokens": 16460832} {"current_steps": 16360, "total_steps": 42420, "loss": 0.2152, "lr": 3.8568840489574356e-05, "epoch": 7.713342762847713, "percentage": 38.57, "elapsed_time": "0:59:04", "remaining_time": "1:34:06", "throughput": 4645.36, "total_tokens": 16465920} {"current_steps": 16365, "total_steps": 42420, "loss": 0.3332, "lr": 3.856020020878489e-05, "epoch": 7.715700141442715, "percentage": 38.58, "elapsed_time": "0:59:05", "remaining_time": "1:34:04", "throughput": 4645.37, "total_tokens": 16470432} {"current_steps": 16370, "total_steps": 42420, "loss": 0.0749, "lr": 3.855155763248377e-05, "epoch": 7.718057520037718, "percentage": 38.59, "elapsed_time": "0:59:06", "remaining_time": "1:34:03", "throughput": 4645.33, "total_tokens": 16474464} {"current_steps": 16375, "total_steps": 42420, "loss": 0.0666, "lr": 3.8542912762134035e-05, "epoch": 7.72041489863272, "percentage": 38.6, "elapsed_time": "0:59:07", "remaining_time": "1:34:02", "throughput": 4645.36, "total_tokens": 16478848} {"current_steps": 16380, "total_steps": 42420, "loss": 0.1661, "lr": 3.853426559919911e-05, "epoch": 7.7227722772277225, "percentage": 38.61, "elapsed_time": "0:59:08", "remaining_time": "1:34:01", "throughput": 4645.43, "total_tokens": 16483840} {"current_steps": 16385, "total_steps": 42420, "loss": 0.0191, "lr": 3.852561614514282e-05, "epoch": 7.725129655822725, "percentage": 38.63, "elapsed_time": "0:59:09", "remaining_time": "1:33:59", "throughput": 4645.52, "total_tokens": 16489248} {"current_steps": 16390, "total_steps": 42420, "loss": 0.1026, "lr": 3.851696440142937e-05, "epoch": 7.727487034417727, "percentage": 38.64, "elapsed_time": "0:59:10", "remaining_time": "1:33:58", "throughput": 4645.63, "total_tokens": 16494912} {"current_steps": 16395, "total_steps": 42420, "loss": 0.0329, "lr": 3.850831036952336e-05, "epoch": 7.72984441301273, "percentage": 38.65, "elapsed_time": "0:59:11", "remaining_time": "1:33:57", "throughput": 4645.67, "total_tokens": 16499520} {"current_steps": 16400, "total_steps": 42420, "loss": 0.1571, "lr": 3.8499654050889754e-05, "epoch": 7.732201791607732, "percentage": 38.66, "elapsed_time": "0:59:12", "remaining_time": "1:33:56", "throughput": 4645.64, "total_tokens": 16503552} {"current_steps": 16405, "total_steps": 42420, "loss": 0.0558, "lr": 3.8490995446993924e-05, "epoch": 7.7345591702027345, "percentage": 38.67, "elapsed_time": "0:59:13", "remaining_time": "1:33:55", "throughput": 4645.66, "total_tokens": 16508320} {"current_steps": 16410, "total_steps": 42420, "loss": 0.0274, "lr": 3.848233455930164e-05, "epoch": 7.736916548797737, "percentage": 38.68, "elapsed_time": "0:59:14", "remaining_time": "1:33:54", "throughput": 4645.73, "total_tokens": 16513632} {"current_steps": 16415, "total_steps": 42420, "loss": 0.1234, "lr": 3.847367138927902e-05, "epoch": 7.739273927392739, "percentage": 38.7, "elapsed_time": "0:59:15", "remaining_time": "1:33:53", "throughput": 4645.83, "total_tokens": 16519200} {"current_steps": 16420, "total_steps": 42420, "loss": 0.2398, "lr": 3.846500593839262e-05, "epoch": 7.741631305987742, "percentage": 38.71, "elapsed_time": "0:59:16", "remaining_time": "1:33:51", "throughput": 4645.91, "total_tokens": 16524352} {"current_steps": 16425, "total_steps": 42420, "loss": 0.0428, "lr": 3.8456338208109324e-05, "epoch": 7.743988684582744, "percentage": 38.72, "elapsed_time": "0:59:17", "remaining_time": "1:33:50", "throughput": 4645.93, "total_tokens": 16529344} {"current_steps": 16430, "total_steps": 42420, "loss": 0.0497, "lr": 3.844766819989645e-05, "epoch": 7.7463460631777465, "percentage": 38.73, "elapsed_time": "0:59:19", "remaining_time": "1:33:49", "throughput": 4646.01, "total_tokens": 16535392} {"current_steps": 16435, "total_steps": 42420, "loss": 0.0844, "lr": 3.8438995915221677e-05, "epoch": 7.748703441772749, "percentage": 38.74, "elapsed_time": "0:59:20", "remaining_time": "1:33:48", "throughput": 4645.99, "total_tokens": 16540192} {"current_steps": 16440, "total_steps": 42420, "loss": 0.0861, "lr": 3.843032135555308e-05, "epoch": 7.751060820367751, "percentage": 38.76, "elapsed_time": "0:59:21", "remaining_time": "1:33:47", "throughput": 4646.06, "total_tokens": 16546208} {"current_steps": 16445, "total_steps": 42420, "loss": 0.1858, "lr": 3.8421644522359105e-05, "epoch": 7.753418198962754, "percentage": 38.77, "elapsed_time": "0:59:22", "remaining_time": "1:33:46", "throughput": 4646.1, "total_tokens": 16550848} {"current_steps": 16450, "total_steps": 42420, "loss": 0.0948, "lr": 3.8412965417108606e-05, "epoch": 7.755775577557756, "percentage": 38.78, "elapsed_time": "0:59:23", "remaining_time": "1:33:45", "throughput": 4646.13, "total_tokens": 16555104} {"current_steps": 16455, "total_steps": 42420, "loss": 0.089, "lr": 3.8404284041270797e-05, "epoch": 7.7581329561527586, "percentage": 38.79, "elapsed_time": "0:59:24", "remaining_time": "1:33:43", "throughput": 4646.15, "total_tokens": 16559488} {"current_steps": 16460, "total_steps": 42420, "loss": 0.0943, "lr": 3.839560039631529e-05, "epoch": 7.760490334747761, "percentage": 38.8, "elapsed_time": "0:59:25", "remaining_time": "1:33:42", "throughput": 4646.15, "total_tokens": 16564256} {"current_steps": 16465, "total_steps": 42420, "loss": 0.1629, "lr": 3.8386914483712085e-05, "epoch": 7.7628477133427625, "percentage": 38.81, "elapsed_time": "0:59:26", "remaining_time": "1:33:41", "throughput": 4646.22, "total_tokens": 16568832} {"current_steps": 16470, "total_steps": 42420, "loss": 0.1746, "lr": 3.8378226304931545e-05, "epoch": 7.765205091937765, "percentage": 38.83, "elapsed_time": "0:59:27", "remaining_time": "1:33:40", "throughput": 4646.31, "total_tokens": 16573888} {"current_steps": 16475, "total_steps": 42420, "loss": 0.2049, "lr": 3.836953586144445e-05, "epoch": 7.767562470532767, "percentage": 38.84, "elapsed_time": "0:59:28", "remaining_time": "1:33:39", "throughput": 4646.3, "total_tokens": 16578336} {"current_steps": 16480, "total_steps": 42420, "loss": 0.11, "lr": 3.836084315472193e-05, "epoch": 7.76991984912777, "percentage": 38.85, "elapsed_time": "0:59:28", "remaining_time": "1:33:37", "throughput": 4646.26, "total_tokens": 16582400} {"current_steps": 16485, "total_steps": 42420, "loss": 0.1954, "lr": 3.835214818623553e-05, "epoch": 7.772277227722772, "percentage": 38.86, "elapsed_time": "0:59:30", "remaining_time": "1:33:36", "throughput": 4646.33, "total_tokens": 16587712} {"current_steps": 16490, "total_steps": 42420, "loss": 0.1615, "lr": 3.8343450957457136e-05, "epoch": 7.7746346063177745, "percentage": 38.87, "elapsed_time": "0:59:31", "remaining_time": "1:33:35", "throughput": 4646.37, "total_tokens": 16592576} {"current_steps": 16495, "total_steps": 42420, "loss": 0.1854, "lr": 3.833475146985905e-05, "epoch": 7.776991984912777, "percentage": 38.88, "elapsed_time": "0:59:32", "remaining_time": "1:33:34", "throughput": 4646.39, "total_tokens": 16597344} {"current_steps": 16500, "total_steps": 42420, "loss": 0.0392, "lr": 3.832604972491396e-05, "epoch": 7.779349363507779, "percentage": 38.9, "elapsed_time": "0:59:33", "remaining_time": "1:33:32", "throughput": 4646.41, "total_tokens": 16601856} {"current_steps": 16505, "total_steps": 42420, "loss": 0.2827, "lr": 3.831734572409492e-05, "epoch": 7.781706742102782, "percentage": 38.91, "elapsed_time": "0:59:34", "remaining_time": "1:33:31", "throughput": 4646.37, "total_tokens": 16606304} {"current_steps": 16510, "total_steps": 42420, "loss": 0.1058, "lr": 3.830863946887536e-05, "epoch": 7.784064120697784, "percentage": 38.92, "elapsed_time": "0:59:35", "remaining_time": "1:33:30", "throughput": 4646.42, "total_tokens": 16611264} {"current_steps": 16515, "total_steps": 42420, "loss": 0.1349, "lr": 3.82999309607291e-05, "epoch": 7.7864214992927865, "percentage": 38.93, "elapsed_time": "0:59:36", "remaining_time": "1:33:29", "throughput": 4646.47, "total_tokens": 16616256} {"current_steps": 16520, "total_steps": 42420, "loss": 0.074, "lr": 3.829122020113035e-05, "epoch": 7.788778877887789, "percentage": 38.94, "elapsed_time": "0:59:37", "remaining_time": "1:33:28", "throughput": 4646.55, "total_tokens": 16621920} {"current_steps": 16525, "total_steps": 42420, "loss": 0.1071, "lr": 3.82825071915537e-05, "epoch": 7.791136256482791, "percentage": 38.96, "elapsed_time": "0:59:38", "remaining_time": "1:33:27", "throughput": 4646.67, "total_tokens": 16628448} {"current_steps": 16530, "total_steps": 42420, "loss": 0.1032, "lr": 3.8273791933474104e-05, "epoch": 7.793493635077794, "percentage": 38.97, "elapsed_time": "0:59:39", "remaining_time": "1:33:26", "throughput": 4646.78, "total_tokens": 16634624} {"current_steps": 16535, "total_steps": 42420, "loss": 0.1841, "lr": 3.82650744283669e-05, "epoch": 7.795851013672796, "percentage": 38.98, "elapsed_time": "0:59:40", "remaining_time": "1:33:25", "throughput": 4646.83, "total_tokens": 16639712} {"current_steps": 16540, "total_steps": 42420, "loss": 0.167, "lr": 3.825635467770783e-05, "epoch": 7.7982083922677985, "percentage": 38.99, "elapsed_time": "0:59:41", "remaining_time": "1:33:24", "throughput": 4646.88, "total_tokens": 16644800} {"current_steps": 16545, "total_steps": 42420, "loss": 0.0382, "lr": 3.8247632682973e-05, "epoch": 7.800565770862801, "percentage": 39.0, "elapsed_time": "0:59:43", "remaining_time": "1:33:23", "throughput": 4646.96, "total_tokens": 16650240} {"current_steps": 16550, "total_steps": 42420, "loss": 0.2372, "lr": 3.8238908445638886e-05, "epoch": 7.802923149457803, "percentage": 39.01, "elapsed_time": "0:59:44", "remaining_time": "1:33:22", "throughput": 4647.01, "total_tokens": 16655552} {"current_steps": 16555, "total_steps": 42420, "loss": 0.2275, "lr": 3.823018196718235e-05, "epoch": 7.805280528052805, "percentage": 39.03, "elapsed_time": "0:59:45", "remaining_time": "1:33:21", "throughput": 4647.01, "total_tokens": 16660096} {"current_steps": 16560, "total_steps": 42420, "loss": 0.0983, "lr": 3.822145324908064e-05, "epoch": 7.807637906647807, "percentage": 39.04, "elapsed_time": "0:59:46", "remaining_time": "1:33:20", "throughput": 4647.05, "total_tokens": 16665056} {"current_steps": 16565, "total_steps": 42420, "loss": 0.1059, "lr": 3.821272229281139e-05, "epoch": 7.80999528524281, "percentage": 39.05, "elapsed_time": "0:59:47", "remaining_time": "1:33:19", "throughput": 4647.12, "total_tokens": 16671072} {"current_steps": 16570, "total_steps": 42420, "loss": 0.1204, "lr": 3.82039890998526e-05, "epoch": 7.812352663837812, "percentage": 39.06, "elapsed_time": "0:59:48", "remaining_time": "1:33:18", "throughput": 4647.16, "total_tokens": 16676672} {"current_steps": 16575, "total_steps": 42420, "loss": 0.1558, "lr": 3.8195253671682634e-05, "epoch": 7.814710042432814, "percentage": 39.07, "elapsed_time": "0:59:49", "remaining_time": "1:33:17", "throughput": 4647.07, "total_tokens": 16680608} {"current_steps": 16580, "total_steps": 42420, "loss": 0.0451, "lr": 3.818651600978027e-05, "epoch": 7.817067421027817, "percentage": 39.09, "elapsed_time": "0:59:50", "remaining_time": "1:33:15", "throughput": 4647.09, "total_tokens": 16685664} {"current_steps": 16585, "total_steps": 42420, "loss": 0.0546, "lr": 3.817777611562464e-05, "epoch": 7.819424799622819, "percentage": 39.1, "elapsed_time": "0:59:51", "remaining_time": "1:33:14", "throughput": 4647.13, "total_tokens": 16690560} {"current_steps": 16590, "total_steps": 42420, "loss": 0.043, "lr": 3.8169033990695255e-05, "epoch": 7.821782178217822, "percentage": 39.11, "elapsed_time": "0:59:52", "remaining_time": "1:33:13", "throughput": 4647.12, "total_tokens": 16695648} {"current_steps": 16595, "total_steps": 42420, "loss": 0.21, "lr": 3.816028963647201e-05, "epoch": 7.824139556812824, "percentage": 39.12, "elapsed_time": "0:59:53", "remaining_time": "1:33:12", "throughput": 4647.15, "total_tokens": 16700672} {"current_steps": 16600, "total_steps": 42420, "loss": 0.0918, "lr": 3.815154305443519e-05, "epoch": 7.826496935407826, "percentage": 39.13, "elapsed_time": "0:59:54", "remaining_time": "1:33:11", "throughput": 4647.21, "total_tokens": 16705792} {"current_steps": 16605, "total_steps": 42420, "loss": 0.1612, "lr": 3.814279424606543e-05, "epoch": 7.828854314002829, "percentage": 39.14, "elapsed_time": "0:59:55", "remaining_time": "1:33:10", "throughput": 4647.31, "total_tokens": 16711424} {"current_steps": 16610, "total_steps": 42420, "loss": 0.406, "lr": 3.813404321284375e-05, "epoch": 7.831211692597831, "percentage": 39.16, "elapsed_time": "0:59:56", "remaining_time": "1:33:09", "throughput": 4647.34, "total_tokens": 16715968} {"current_steps": 16615, "total_steps": 42420, "loss": 0.1018, "lr": 3.812528995625156e-05, "epoch": 7.833569071192834, "percentage": 39.17, "elapsed_time": "0:59:57", "remaining_time": "1:33:07", "throughput": 4647.37, "total_tokens": 16720160} {"current_steps": 16620, "total_steps": 42420, "loss": 0.158, "lr": 3.8116534477770634e-05, "epoch": 7.835926449787836, "percentage": 39.18, "elapsed_time": "0:59:59", "remaining_time": "1:33:06", "throughput": 4647.48, "total_tokens": 16726496} {"current_steps": 16625, "total_steps": 42420, "loss": 0.122, "lr": 3.8107776778883125e-05, "epoch": 7.838283828382838, "percentage": 39.19, "elapsed_time": "1:00:00", "remaining_time": "1:33:06", "throughput": 4647.5, "total_tokens": 16732352} {"current_steps": 16630, "total_steps": 42420, "loss": 0.0543, "lr": 3.809901686107157e-05, "epoch": 7.840641206977841, "percentage": 39.2, "elapsed_time": "1:00:01", "remaining_time": "1:33:05", "throughput": 4647.59, "total_tokens": 16738080} {"current_steps": 16635, "total_steps": 42420, "loss": 0.0638, "lr": 3.8090254725818864e-05, "epoch": 7.842998585572843, "percentage": 39.21, "elapsed_time": "1:00:02", "remaining_time": "1:33:04", "throughput": 4647.66, "total_tokens": 16743328} {"current_steps": 16640, "total_steps": 42420, "loss": 0.1474, "lr": 3.80814903746083e-05, "epoch": 7.845355964167846, "percentage": 39.23, "elapsed_time": "1:00:03", "remaining_time": "1:33:03", "throughput": 4647.75, "total_tokens": 16748992} {"current_steps": 16645, "total_steps": 42420, "loss": 0.0464, "lr": 3.8072723808923514e-05, "epoch": 7.847713342762848, "percentage": 39.24, "elapsed_time": "1:00:04", "remaining_time": "1:33:02", "throughput": 4647.79, "total_tokens": 16754112} {"current_steps": 16650, "total_steps": 42420, "loss": 0.227, "lr": 3.806395503024857e-05, "epoch": 7.8500707213578504, "percentage": 39.25, "elapsed_time": "1:00:05", "remaining_time": "1:33:00", "throughput": 4647.88, "total_tokens": 16759616} {"current_steps": 16655, "total_steps": 42420, "loss": 0.2335, "lr": 3.805518404006784e-05, "epoch": 7.852428099952853, "percentage": 39.26, "elapsed_time": "1:00:06", "remaining_time": "1:32:59", "throughput": 4647.93, "total_tokens": 16764064} {"current_steps": 16660, "total_steps": 42420, "loss": 0.0347, "lr": 3.8046410839866116e-05, "epoch": 7.854785478547855, "percentage": 39.27, "elapsed_time": "1:00:07", "remaining_time": "1:32:58", "throughput": 4647.99, "total_tokens": 16769760} {"current_steps": 16665, "total_steps": 42420, "loss": 0.0435, "lr": 3.803763543112855e-05, "epoch": 7.857142857142857, "percentage": 39.29, "elapsed_time": "1:00:08", "remaining_time": "1:32:57", "throughput": 4648.0, "total_tokens": 16773984} {"current_steps": 16670, "total_steps": 42420, "loss": 0.0673, "lr": 3.8028857815340674e-05, "epoch": 7.859500235737859, "percentage": 39.3, "elapsed_time": "1:00:10", "remaining_time": "1:32:56", "throughput": 4648.11, "total_tokens": 16780256} {"current_steps": 16675, "total_steps": 42420, "loss": 0.0736, "lr": 3.802007799398839e-05, "epoch": 7.861857614332862, "percentage": 39.31, "elapsed_time": "1:00:11", "remaining_time": "1:32:55", "throughput": 4648.13, "total_tokens": 16784736} {"current_steps": 16680, "total_steps": 42420, "loss": 0.1521, "lr": 3.801129596855797e-05, "epoch": 7.864214992927864, "percentage": 39.32, "elapsed_time": "1:00:12", "remaining_time": "1:32:54", "throughput": 4648.17, "total_tokens": 16789504} {"current_steps": 16685, "total_steps": 42420, "loss": 0.1447, "lr": 3.8002511740536055e-05, "epoch": 7.866572371522866, "percentage": 39.33, "elapsed_time": "1:00:13", "remaining_time": "1:32:52", "throughput": 4648.21, "total_tokens": 16794208} {"current_steps": 16690, "total_steps": 42420, "loss": 0.2111, "lr": 3.799372531140968e-05, "epoch": 7.868929750117869, "percentage": 39.34, "elapsed_time": "1:00:14", "remaining_time": "1:32:51", "throughput": 4648.3, "total_tokens": 16799680} {"current_steps": 16695, "total_steps": 42420, "loss": 0.0613, "lr": 3.7984936682666225e-05, "epoch": 7.871287128712871, "percentage": 39.36, "elapsed_time": "1:00:15", "remaining_time": "1:32:50", "throughput": 4648.32, "total_tokens": 16804320} {"current_steps": 16700, "total_steps": 42420, "loss": 0.2264, "lr": 3.7976145855793464e-05, "epoch": 7.873644507307874, "percentage": 39.37, "elapsed_time": "1:00:16", "remaining_time": "1:32:49", "throughput": 4648.43, "total_tokens": 16810240} {"current_steps": 16705, "total_steps": 42420, "loss": 0.064, "lr": 3.796735283227954e-05, "epoch": 7.876001885902876, "percentage": 39.38, "elapsed_time": "1:00:17", "remaining_time": "1:32:48", "throughput": 4648.5, "total_tokens": 16814880} {"current_steps": 16710, "total_steps": 42420, "loss": 0.1444, "lr": 3.7958557613612936e-05, "epoch": 7.878359264497878, "percentage": 39.39, "elapsed_time": "1:00:18", "remaining_time": "1:32:46", "throughput": 4648.56, "total_tokens": 16819328} {"current_steps": 16715, "total_steps": 42420, "loss": 0.1309, "lr": 3.794976020128257e-05, "epoch": 7.880716643092881, "percentage": 39.4, "elapsed_time": "1:00:19", "remaining_time": "1:32:45", "throughput": 4648.58, "total_tokens": 16824064} {"current_steps": 16720, "total_steps": 42420, "loss": 0.0423, "lr": 3.7940960596777665e-05, "epoch": 7.883074021687883, "percentage": 39.42, "elapsed_time": "1:00:20", "remaining_time": "1:32:44", "throughput": 4648.66, "total_tokens": 16828832} {"current_steps": 16725, "total_steps": 42420, "loss": 0.076, "lr": 3.7932158801587855e-05, "epoch": 7.885431400282886, "percentage": 39.43, "elapsed_time": "1:00:21", "remaining_time": "1:32:43", "throughput": 4648.66, "total_tokens": 16833216} {"current_steps": 16730, "total_steps": 42420, "loss": 0.0881, "lr": 3.792335481720314e-05, "epoch": 7.887788778877888, "percentage": 39.44, "elapsed_time": "1:00:22", "remaining_time": "1:32:41", "throughput": 4648.68, "total_tokens": 16837856} {"current_steps": 16735, "total_steps": 42420, "loss": 0.3584, "lr": 3.791454864511389e-05, "epoch": 7.89014615747289, "percentage": 39.45, "elapsed_time": "1:00:23", "remaining_time": "1:32:41", "throughput": 4648.78, "total_tokens": 16843872} {"current_steps": 16740, "total_steps": 42420, "loss": 0.1589, "lr": 3.790574028681082e-05, "epoch": 7.892503536067893, "percentage": 39.46, "elapsed_time": "1:00:24", "remaining_time": "1:32:40", "throughput": 4648.88, "total_tokens": 16849728} {"current_steps": 16745, "total_steps": 42420, "loss": 0.1429, "lr": 3.789692974378505e-05, "epoch": 7.894860914662895, "percentage": 39.47, "elapsed_time": "1:00:25", "remaining_time": "1:32:38", "throughput": 4648.93, "total_tokens": 16854592} {"current_steps": 16750, "total_steps": 42420, "loss": 0.0876, "lr": 3.7888117017528046e-05, "epoch": 7.897218293257898, "percentage": 39.49, "elapsed_time": "1:00:26", "remaining_time": "1:32:37", "throughput": 4648.99, "total_tokens": 16859808} {"current_steps": 16755, "total_steps": 42420, "loss": 0.1622, "lr": 3.787930210953167e-05, "epoch": 7.899575671852899, "percentage": 39.5, "elapsed_time": "1:00:27", "remaining_time": "1:32:36", "throughput": 4649.01, "total_tokens": 16864192} {"current_steps": 16760, "total_steps": 42420, "loss": 0.2264, "lr": 3.787048502128811e-05, "epoch": 7.9019330504479015, "percentage": 39.51, "elapsed_time": "1:00:28", "remaining_time": "1:32:35", "throughput": 4649.08, "total_tokens": 16869056} {"current_steps": 16765, "total_steps": 42420, "loss": 0.1088, "lr": 3.786166575428997e-05, "epoch": 7.904290429042904, "percentage": 39.52, "elapsed_time": "1:00:29", "remaining_time": "1:32:33", "throughput": 4648.99, "total_tokens": 16872672} {"current_steps": 16770, "total_steps": 42420, "loss": 0.0888, "lr": 3.78528443100302e-05, "epoch": 7.906647807637906, "percentage": 39.53, "elapsed_time": "1:00:30", "remaining_time": "1:32:32", "throughput": 4649.03, "total_tokens": 16877888} {"current_steps": 16775, "total_steps": 42420, "loss": 0.0583, "lr": 3.784402069000211e-05, "epoch": 7.909005186232909, "percentage": 39.55, "elapsed_time": "1:00:31", "remaining_time": "1:32:31", "throughput": 4648.99, "total_tokens": 16881984} {"current_steps": 16780, "total_steps": 42420, "loss": 0.1668, "lr": 3.783519489569941e-05, "epoch": 7.911362564827911, "percentage": 39.56, "elapsed_time": "1:00:32", "remaining_time": "1:32:30", "throughput": 4649.01, "total_tokens": 16886624} {"current_steps": 16785, "total_steps": 42420, "loss": 0.1722, "lr": 3.782636692861613e-05, "epoch": 7.9137199434229135, "percentage": 39.57, "elapsed_time": "1:00:33", "remaining_time": "1:32:29", "throughput": 4649.09, "total_tokens": 16892096} {"current_steps": 16790, "total_steps": 42420, "loss": 0.0855, "lr": 3.781753679024672e-05, "epoch": 7.916077322017916, "percentage": 39.58, "elapsed_time": "1:00:34", "remaining_time": "1:32:27", "throughput": 4649.15, "total_tokens": 16896960} {"current_steps": 16795, "total_steps": 42420, "loss": 0.0396, "lr": 3.7808704482085956e-05, "epoch": 7.918434700612918, "percentage": 39.59, "elapsed_time": "1:00:35", "remaining_time": "1:32:26", "throughput": 4649.25, "total_tokens": 16902272} {"current_steps": 16800, "total_steps": 42420, "loss": 0.1813, "lr": 3.7799870005629e-05, "epoch": 7.920792079207921, "percentage": 39.6, "elapsed_time": "1:00:36", "remaining_time": "1:32:25", "throughput": 4649.33, "total_tokens": 16907136} {"current_steps": 16805, "total_steps": 42420, "loss": 0.1426, "lr": 3.779103336237138e-05, "epoch": 7.923149457802923, "percentage": 39.62, "elapsed_time": "1:00:37", "remaining_time": "1:32:24", "throughput": 4649.4, "total_tokens": 16911680} {"current_steps": 16810, "total_steps": 42420, "loss": 0.1607, "lr": 3.7782194553808995e-05, "epoch": 7.9255068363979255, "percentage": 39.63, "elapsed_time": "1:00:38", "remaining_time": "1:32:23", "throughput": 4649.49, "total_tokens": 16916640} {"current_steps": 16815, "total_steps": 42420, "loss": 0.0711, "lr": 3.77733535814381e-05, "epoch": 7.927864214992928, "percentage": 39.64, "elapsed_time": "1:00:39", "remaining_time": "1:32:21", "throughput": 4649.38, "total_tokens": 16920672} {"current_steps": 16820, "total_steps": 42420, "loss": 0.0887, "lr": 3.776451044675532e-05, "epoch": 7.93022159358793, "percentage": 39.65, "elapsed_time": "1:00:40", "remaining_time": "1:32:20", "throughput": 4649.41, "total_tokens": 16925472} {"current_steps": 16825, "total_steps": 42420, "loss": 0.0637, "lr": 3.7755665151257654e-05, "epoch": 7.932578972182933, "percentage": 39.66, "elapsed_time": "1:00:41", "remaining_time": "1:32:19", "throughput": 4649.46, "total_tokens": 16930240} {"current_steps": 16830, "total_steps": 42420, "loss": 0.1304, "lr": 3.774681769644245e-05, "epoch": 7.934936350777935, "percentage": 39.67, "elapsed_time": "1:00:42", "remaining_time": "1:32:18", "throughput": 4649.5, "total_tokens": 16935200} {"current_steps": 16835, "total_steps": 42420, "loss": 0.0914, "lr": 3.773796808380745e-05, "epoch": 7.9372937293729375, "percentage": 39.69, "elapsed_time": "1:00:43", "remaining_time": "1:32:17", "throughput": 4649.62, "total_tokens": 16941248} {"current_steps": 16840, "total_steps": 42420, "loss": 0.1464, "lr": 3.7729116314850733e-05, "epoch": 7.93965110796794, "percentage": 39.7, "elapsed_time": "1:00:44", "remaining_time": "1:32:16", "throughput": 4649.68, "total_tokens": 16946976} {"current_steps": 16845, "total_steps": 42420, "loss": 0.0923, "lr": 3.7720262391070736e-05, "epoch": 7.942008486562942, "percentage": 39.71, "elapsed_time": "1:00:45", "remaining_time": "1:32:15", "throughput": 4649.72, "total_tokens": 16951360} {"current_steps": 16850, "total_steps": 42420, "loss": 0.0977, "lr": 3.7711406313966303e-05, "epoch": 7.944365865157945, "percentage": 39.72, "elapsed_time": "1:00:46", "remaining_time": "1:32:13", "throughput": 4649.79, "total_tokens": 16956512} {"current_steps": 16855, "total_steps": 42420, "loss": 0.1233, "lr": 3.770254808503661e-05, "epoch": 7.946723243752947, "percentage": 39.73, "elapsed_time": "1:00:47", "remaining_time": "1:32:12", "throughput": 4649.83, "total_tokens": 16961536} {"current_steps": 16860, "total_steps": 42420, "loss": 0.1786, "lr": 3.7693687705781203e-05, "epoch": 7.9490806223479495, "percentage": 39.75, "elapsed_time": "1:00:48", "remaining_time": "1:32:11", "throughput": 4649.95, "total_tokens": 16967360} {"current_steps": 16865, "total_steps": 42420, "loss": 0.1263, "lr": 3.7684825177699995e-05, "epoch": 7.951438000942951, "percentage": 39.76, "elapsed_time": "1:00:50", "remaining_time": "1:32:10", "throughput": 4650.04, "total_tokens": 16972704} {"current_steps": 16870, "total_steps": 42420, "loss": 0.1422, "lr": 3.7675960502293255e-05, "epoch": 7.9537953795379535, "percentage": 39.77, "elapsed_time": "1:00:51", "remaining_time": "1:32:09", "throughput": 4650.07, "total_tokens": 16977760} {"current_steps": 16875, "total_steps": 42420, "loss": 0.0544, "lr": 3.766709368106163e-05, "epoch": 7.956152758132956, "percentage": 39.78, "elapsed_time": "1:00:52", "remaining_time": "1:32:08", "throughput": 4650.15, "total_tokens": 16983552} {"current_steps": 16880, "total_steps": 42420, "loss": 0.2577, "lr": 3.765822471550612e-05, "epoch": 7.958510136727958, "percentage": 39.79, "elapsed_time": "1:00:53", "remaining_time": "1:32:07", "throughput": 4650.2, "total_tokens": 16988480} {"current_steps": 16885, "total_steps": 42420, "loss": 0.1363, "lr": 3.76493536071281e-05, "epoch": 7.960867515322961, "percentage": 39.8, "elapsed_time": "1:00:54", "remaining_time": "1:32:06", "throughput": 4650.21, "total_tokens": 16992928} {"current_steps": 16890, "total_steps": 42420, "loss": 0.1031, "lr": 3.7640480357429274e-05, "epoch": 7.963224893917963, "percentage": 39.82, "elapsed_time": "1:00:55", "remaining_time": "1:32:04", "throughput": 4650.26, "total_tokens": 16997472} {"current_steps": 16895, "total_steps": 42420, "loss": 0.0754, "lr": 3.763160496791175e-05, "epoch": 7.9655822725129655, "percentage": 39.83, "elapsed_time": "1:00:56", "remaining_time": "1:32:03", "throughput": 4650.34, "total_tokens": 17002528} {"current_steps": 16900, "total_steps": 42420, "loss": 0.2309, "lr": 3.762272744007798e-05, "epoch": 7.967939651107968, "percentage": 39.84, "elapsed_time": "1:00:57", "remaining_time": "1:32:02", "throughput": 4650.4, "total_tokens": 17007648} {"current_steps": 16905, "total_steps": 42420, "loss": 0.2064, "lr": 3.7613847775430776e-05, "epoch": 7.97029702970297, "percentage": 39.85, "elapsed_time": "1:00:58", "remaining_time": "1:32:01", "throughput": 4650.49, "total_tokens": 17013440} {"current_steps": 16910, "total_steps": 42420, "loss": 0.0785, "lr": 3.760496597547332e-05, "epoch": 7.972654408297973, "percentage": 39.86, "elapsed_time": "1:00:59", "remaining_time": "1:32:00", "throughput": 4650.51, "total_tokens": 17018048} {"current_steps": 16915, "total_steps": 42420, "loss": 0.0543, "lr": 3.759608204170914e-05, "epoch": 7.975011786892975, "percentage": 39.88, "elapsed_time": "1:01:00", "remaining_time": "1:31:59", "throughput": 4650.64, "total_tokens": 17024960} {"current_steps": 16920, "total_steps": 42420, "loss": 0.0217, "lr": 3.758719597564213e-05, "epoch": 7.9773691654879775, "percentage": 39.89, "elapsed_time": "1:01:02", "remaining_time": "1:31:59", "throughput": 4650.75, "total_tokens": 17031232} {"current_steps": 16925, "total_steps": 42420, "loss": 0.047, "lr": 3.7578307778776564e-05, "epoch": 7.97972654408298, "percentage": 39.9, "elapsed_time": "1:01:03", "remaining_time": "1:31:57", "throughput": 4650.8, "total_tokens": 17036512} {"current_steps": 16930, "total_steps": 42420, "loss": 0.06, "lr": 3.756941745261707e-05, "epoch": 7.982083922677982, "percentage": 39.91, "elapsed_time": "1:01:04", "remaining_time": "1:31:56", "throughput": 4650.91, "total_tokens": 17042112} {"current_steps": 16935, "total_steps": 42420, "loss": 0.2452, "lr": 3.75605249986686e-05, "epoch": 7.984441301272985, "percentage": 39.92, "elapsed_time": "1:01:05", "remaining_time": "1:31:56", "throughput": 4651.0, "total_tokens": 17048000} {"current_steps": 16940, "total_steps": 42420, "loss": 0.1119, "lr": 3.755163041843652e-05, "epoch": 7.986798679867987, "percentage": 39.93, "elapsed_time": "1:01:06", "remaining_time": "1:31:54", "throughput": 4651.07, "total_tokens": 17053280} {"current_steps": 16945, "total_steps": 42420, "loss": 0.1418, "lr": 3.7542733713426536e-05, "epoch": 7.9891560584629895, "percentage": 39.95, "elapsed_time": "1:01:07", "remaining_time": "1:31:53", "throughput": 4651.16, "total_tokens": 17058784} {"current_steps": 16950, "total_steps": 42420, "loss": 0.2862, "lr": 3.753383488514469e-05, "epoch": 7.991513437057992, "percentage": 39.96, "elapsed_time": "1:01:08", "remaining_time": "1:31:52", "throughput": 4651.22, "total_tokens": 17063136} {"current_steps": 16955, "total_steps": 42420, "loss": 0.1414, "lr": 3.7524933935097405e-05, "epoch": 7.993870815652993, "percentage": 39.97, "elapsed_time": "1:01:09", "remaining_time": "1:31:51", "throughput": 4651.31, "total_tokens": 17069600} {"current_steps": 16960, "total_steps": 42420, "loss": 0.0459, "lr": 3.7516030864791474e-05, "epoch": 7.996228194247996, "percentage": 39.98, "elapsed_time": "1:01:10", "remaining_time": "1:31:50", "throughput": 4651.35, "total_tokens": 17074400} {"current_steps": 16965, "total_steps": 42420, "loss": 0.0805, "lr": 3.7507125675734026e-05, "epoch": 7.998585572842998, "percentage": 39.99, "elapsed_time": "1:01:11", "remaining_time": "1:31:49", "throughput": 4651.36, "total_tokens": 17079296} {"current_steps": 16968, "total_steps": 42420, "eval_loss": 0.15088850259780884, "epoch": 8.0, "percentage": 40.0, "elapsed_time": "1:01:27", "remaining_time": "1:32:11", "throughput": 4632.24, "total_tokens": 17082336} {"current_steps": 16970, "total_steps": 42420, "loss": 0.4733, "lr": 3.749821836943256e-05, "epoch": 8.000942951438, "percentage": 40.0, "elapsed_time": "1:01:29", "remaining_time": "1:32:13", "throughput": 4630.29, "total_tokens": 17085120} {"current_steps": 16975, "total_steps": 42420, "loss": 0.0358, "lr": 3.748930894739493e-05, "epoch": 8.003300330033003, "percentage": 40.02, "elapsed_time": "1:01:30", "remaining_time": "1:32:12", "throughput": 4630.33, "total_tokens": 17089824} {"current_steps": 16980, "total_steps": 42420, "loss": 0.0941, "lr": 3.748039741112935e-05, "epoch": 8.005657708628005, "percentage": 40.03, "elapsed_time": "1:01:31", "remaining_time": "1:32:11", "throughput": 4630.38, "total_tokens": 17094624} {"current_steps": 16985, "total_steps": 42420, "loss": 0.0555, "lr": 3.74714837621444e-05, "epoch": 8.008015087223008, "percentage": 40.04, "elapsed_time": "1:01:32", "remaining_time": "1:32:10", "throughput": 4630.43, "total_tokens": 17099520} {"current_steps": 16990, "total_steps": 42420, "loss": 0.0504, "lr": 3.7462568001949e-05, "epoch": 8.01037246581801, "percentage": 40.05, "elapsed_time": "1:01:34", "remaining_time": "1:32:09", "throughput": 4630.05, "total_tokens": 17104416} {"current_steps": 16995, "total_steps": 42420, "loss": 0.0798, "lr": 3.745365013205243e-05, "epoch": 8.012729844413013, "percentage": 40.06, "elapsed_time": "1:01:35", "remaining_time": "1:32:08", "throughput": 4630.11, "total_tokens": 17109440} {"current_steps": 17000, "total_steps": 42420, "loss": 0.0564, "lr": 3.744473015396436e-05, "epoch": 8.015087223008015, "percentage": 40.08, "elapsed_time": "1:01:36", "remaining_time": "1:32:07", "throughput": 4630.19, "total_tokens": 17115104} {"current_steps": 17005, "total_steps": 42420, "loss": 0.1551, "lr": 3.743580806919476e-05, "epoch": 8.017444601603017, "percentage": 40.09, "elapsed_time": "1:01:37", "remaining_time": "1:32:06", "throughput": 4630.22, "total_tokens": 17120000} {"current_steps": 17010, "total_steps": 42420, "loss": 0.3367, "lr": 3.742688387925402e-05, "epoch": 8.01980198019802, "percentage": 40.1, "elapsed_time": "1:01:38", "remaining_time": "1:32:04", "throughput": 4630.26, "total_tokens": 17124864} {"current_steps": 17015, "total_steps": 42420, "loss": 0.096, "lr": 3.741795758565281e-05, "epoch": 8.022159358793022, "percentage": 40.11, "elapsed_time": "1:01:39", "remaining_time": "1:32:03", "throughput": 4630.31, "total_tokens": 17129760} {"current_steps": 17020, "total_steps": 42420, "loss": 0.106, "lr": 3.7409029189902245e-05, "epoch": 8.024516737388025, "percentage": 40.12, "elapsed_time": "1:01:40", "remaining_time": "1:32:02", "throughput": 4630.36, "total_tokens": 17134752} {"current_steps": 17025, "total_steps": 42420, "loss": 0.1633, "lr": 3.740009869351372e-05, "epoch": 8.026874115983027, "percentage": 40.13, "elapsed_time": "1:01:41", "remaining_time": "1:32:01", "throughput": 4630.42, "total_tokens": 17139872} {"current_steps": 17030, "total_steps": 42420, "loss": 0.078, "lr": 3.7391166097999045e-05, "epoch": 8.02923149457803, "percentage": 40.15, "elapsed_time": "1:01:42", "remaining_time": "1:32:00", "throughput": 4630.5, "total_tokens": 17145344} {"current_steps": 17035, "total_steps": 42420, "loss": 0.106, "lr": 3.7382231404870325e-05, "epoch": 8.031588873173032, "percentage": 40.16, "elapsed_time": "1:01:43", "remaining_time": "1:31:59", "throughput": 4630.56, "total_tokens": 17150336} {"current_steps": 17040, "total_steps": 42420, "loss": 0.1836, "lr": 3.737329461564007e-05, "epoch": 8.033946251768034, "percentage": 40.17, "elapsed_time": "1:01:44", "remaining_time": "1:31:58", "throughput": 4630.62, "total_tokens": 17155328} {"current_steps": 17045, "total_steps": 42420, "loss": 0.0936, "lr": 3.736435573182111e-05, "epoch": 8.036303630363037, "percentage": 40.18, "elapsed_time": "1:01:45", "remaining_time": "1:31:56", "throughput": 4630.67, "total_tokens": 17160128} {"current_steps": 17050, "total_steps": 42420, "loss": 0.101, "lr": 3.735541475492668e-05, "epoch": 8.038661008958039, "percentage": 40.19, "elapsed_time": "1:01:46", "remaining_time": "1:31:55", "throughput": 4630.76, "total_tokens": 17165728} {"current_steps": 17055, "total_steps": 42420, "loss": 0.0579, "lr": 3.734647168647031e-05, "epoch": 8.041018387553041, "percentage": 40.21, "elapsed_time": "1:01:47", "remaining_time": "1:31:54", "throughput": 4630.74, "total_tokens": 17169952} {"current_steps": 17060, "total_steps": 42420, "loss": 0.1636, "lr": 3.7337526527965906e-05, "epoch": 8.043375766148044, "percentage": 40.22, "elapsed_time": "1:01:48", "remaining_time": "1:31:53", "throughput": 4630.8, "total_tokens": 17175008} {"current_steps": 17065, "total_steps": 42420, "loss": 0.1047, "lr": 3.732857928092774e-05, "epoch": 8.045733144743046, "percentage": 40.23, "elapsed_time": "1:01:49", "remaining_time": "1:31:52", "throughput": 4630.79, "total_tokens": 17179552} {"current_steps": 17070, "total_steps": 42420, "loss": 0.1286, "lr": 3.7319629946870444e-05, "epoch": 8.048090523338049, "percentage": 40.24, "elapsed_time": "1:01:50", "remaining_time": "1:31:50", "throughput": 4630.85, "total_tokens": 17184608} {"current_steps": 17075, "total_steps": 42420, "loss": 0.1314, "lr": 3.7310678527308965e-05, "epoch": 8.050447901933051, "percentage": 40.25, "elapsed_time": "1:01:52", "remaining_time": "1:31:49", "throughput": 4630.94, "total_tokens": 17190080} {"current_steps": 17080, "total_steps": 42420, "loss": 0.0885, "lr": 3.7301725023758635e-05, "epoch": 8.052805280528053, "percentage": 40.26, "elapsed_time": "1:01:53", "remaining_time": "1:31:48", "throughput": 4631.01, "total_tokens": 17195136} {"current_steps": 17085, "total_steps": 42420, "loss": 0.1736, "lr": 3.7292769437735126e-05, "epoch": 8.055162659123056, "percentage": 40.28, "elapsed_time": "1:01:54", "remaining_time": "1:31:47", "throughput": 4631.15, "total_tokens": 17201344} {"current_steps": 17090, "total_steps": 42420, "loss": 0.2111, "lr": 3.728381177075447e-05, "epoch": 8.057520037718058, "percentage": 40.29, "elapsed_time": "1:01:55", "remaining_time": "1:31:46", "throughput": 4631.17, "total_tokens": 17206016} {"current_steps": 17095, "total_steps": 42420, "loss": 0.0955, "lr": 3.7274852024333054e-05, "epoch": 8.05987741631306, "percentage": 40.3, "elapsed_time": "1:01:56", "remaining_time": "1:31:45", "throughput": 4631.19, "total_tokens": 17211040} {"current_steps": 17100, "total_steps": 42420, "loss": 0.1463, "lr": 3.726589019998761e-05, "epoch": 8.062234794908063, "percentage": 40.31, "elapsed_time": "1:01:57", "remaining_time": "1:31:44", "throughput": 4631.28, "total_tokens": 17216288} {"current_steps": 17105, "total_steps": 42420, "loss": 0.2897, "lr": 3.725692629923521e-05, "epoch": 8.064592173503065, "percentage": 40.32, "elapsed_time": "1:01:58", "remaining_time": "1:31:43", "throughput": 4631.38, "total_tokens": 17222880} {"current_steps": 17110, "total_steps": 42420, "loss": 0.2187, "lr": 3.72479603235933e-05, "epoch": 8.066949552098066, "percentage": 40.33, "elapsed_time": "1:01:59", "remaining_time": "1:31:42", "throughput": 4631.42, "total_tokens": 17227392} {"current_steps": 17115, "total_steps": 42420, "loss": 0.0373, "lr": 3.723899227457967e-05, "epoch": 8.069306930693068, "percentage": 40.35, "elapsed_time": "1:02:00", "remaining_time": "1:31:41", "throughput": 4631.49, "total_tokens": 17232512} {"current_steps": 17120, "total_steps": 42420, "loss": 0.2, "lr": 3.7230022153712446e-05, "epoch": 8.07166430928807, "percentage": 40.36, "elapsed_time": "1:02:01", "remaining_time": "1:31:40", "throughput": 4631.58, "total_tokens": 17237568} {"current_steps": 17125, "total_steps": 42420, "loss": 0.4364, "lr": 3.722104996251013e-05, "epoch": 8.074021687883073, "percentage": 40.37, "elapsed_time": "1:02:03", "remaining_time": "1:31:39", "throughput": 4631.63, "total_tokens": 17243808} {"current_steps": 17130, "total_steps": 42420, "loss": 0.2482, "lr": 3.721207570249155e-05, "epoch": 8.076379066478076, "percentage": 40.38, "elapsed_time": "1:02:03", "remaining_time": "1:31:37", "throughput": 4631.69, "total_tokens": 17248256} {"current_steps": 17135, "total_steps": 42420, "loss": 0.2209, "lr": 3.720309937517592e-05, "epoch": 8.078736445073078, "percentage": 40.39, "elapsed_time": "1:02:04", "remaining_time": "1:31:36", "throughput": 4631.71, "total_tokens": 17252832} {"current_steps": 17140, "total_steps": 42420, "loss": 0.138, "lr": 3.719412098208275e-05, "epoch": 8.08109382366808, "percentage": 40.41, "elapsed_time": "1:02:06", "remaining_time": "1:31:35", "throughput": 4631.79, "total_tokens": 17258560} {"current_steps": 17145, "total_steps": 42420, "loss": 0.0388, "lr": 3.718514052473194e-05, "epoch": 8.083451202263083, "percentage": 40.42, "elapsed_time": "1:02:06", "remaining_time": "1:31:34", "throughput": 4631.7, "total_tokens": 17262272} {"current_steps": 17150, "total_steps": 42420, "loss": 0.2718, "lr": 3.717615800464373e-05, "epoch": 8.085808580858085, "percentage": 40.43, "elapsed_time": "1:02:08", "remaining_time": "1:31:33", "throughput": 4631.72, "total_tokens": 17267360} {"current_steps": 17155, "total_steps": 42420, "loss": 0.1106, "lr": 3.716717342333872e-05, "epoch": 8.088165959453088, "percentage": 40.44, "elapsed_time": "1:02:08", "remaining_time": "1:31:31", "throughput": 4631.71, "total_tokens": 17271360} {"current_steps": 17160, "total_steps": 42420, "loss": 0.0634, "lr": 3.7158186782337825e-05, "epoch": 8.09052333804809, "percentage": 40.45, "elapsed_time": "1:02:10", "remaining_time": "1:31:30", "throughput": 4631.76, "total_tokens": 17276640} {"current_steps": 17165, "total_steps": 42420, "loss": 0.1897, "lr": 3.714919808316235e-05, "epoch": 8.092880716643092, "percentage": 40.46, "elapsed_time": "1:02:11", "remaining_time": "1:31:29", "throughput": 4631.78, "total_tokens": 17281216} {"current_steps": 17170, "total_steps": 42420, "loss": 0.1158, "lr": 3.714020732733392e-05, "epoch": 8.095238095238095, "percentage": 40.48, "elapsed_time": "1:02:12", "remaining_time": "1:31:28", "throughput": 4631.87, "total_tokens": 17286624} {"current_steps": 17175, "total_steps": 42420, "loss": 0.216, "lr": 3.713121451637451e-05, "epoch": 8.097595473833097, "percentage": 40.49, "elapsed_time": "1:02:13", "remaining_time": "1:31:27", "throughput": 4631.94, "total_tokens": 17291744} {"current_steps": 17180, "total_steps": 42420, "loss": 0.2238, "lr": 3.712221965180647e-05, "epoch": 8.0999528524281, "percentage": 40.5, "elapsed_time": "1:02:14", "remaining_time": "1:31:26", "throughput": 4632.05, "total_tokens": 17297280} {"current_steps": 17185, "total_steps": 42420, "loss": 0.1584, "lr": 3.711322273515247e-05, "epoch": 8.102310231023102, "percentage": 40.51, "elapsed_time": "1:02:15", "remaining_time": "1:31:24", "throughput": 4632.01, "total_tokens": 17301760} {"current_steps": 17190, "total_steps": 42420, "loss": 0.2124, "lr": 3.710422376793551e-05, "epoch": 8.104667609618105, "percentage": 40.52, "elapsed_time": "1:02:16", "remaining_time": "1:31:23", "throughput": 4632.04, "total_tokens": 17306976} {"current_steps": 17195, "total_steps": 42420, "loss": 0.0353, "lr": 3.7095222751679e-05, "epoch": 8.107024988213107, "percentage": 40.54, "elapsed_time": "1:02:17", "remaining_time": "1:31:22", "throughput": 4632.05, "total_tokens": 17311680} {"current_steps": 17200, "total_steps": 42420, "loss": 0.1342, "lr": 3.7086219687906644e-05, "epoch": 8.10938236680811, "percentage": 40.55, "elapsed_time": "1:02:18", "remaining_time": "1:31:21", "throughput": 4632.1, "total_tokens": 17316704} {"current_steps": 17205, "total_steps": 42420, "loss": 0.0929, "lr": 3.7077214578142504e-05, "epoch": 8.111739745403112, "percentage": 40.56, "elapsed_time": "1:02:19", "remaining_time": "1:31:20", "throughput": 4632.14, "total_tokens": 17321408} {"current_steps": 17210, "total_steps": 42420, "loss": 0.1065, "lr": 3.706820742391099e-05, "epoch": 8.114097123998114, "percentage": 40.57, "elapsed_time": "1:02:20", "remaining_time": "1:31:19", "throughput": 4632.18, "total_tokens": 17326464} {"current_steps": 17215, "total_steps": 42420, "loss": 0.1835, "lr": 3.7059198226736876e-05, "epoch": 8.116454502593117, "percentage": 40.58, "elapsed_time": "1:02:21", "remaining_time": "1:31:18", "throughput": 4632.26, "total_tokens": 17332736} {"current_steps": 17220, "total_steps": 42420, "loss": 0.1729, "lr": 3.705018698814525e-05, "epoch": 8.118811881188119, "percentage": 40.59, "elapsed_time": "1:02:22", "remaining_time": "1:31:17", "throughput": 4632.28, "total_tokens": 17337216} {"current_steps": 17225, "total_steps": 42420, "loss": 0.2506, "lr": 3.704117370966158e-05, "epoch": 8.121169259783121, "percentage": 40.61, "elapsed_time": "1:02:23", "remaining_time": "1:31:15", "throughput": 4632.28, "total_tokens": 17341664} {"current_steps": 17230, "total_steps": 42420, "loss": 0.057, "lr": 3.703215839281163e-05, "epoch": 8.123526638378124, "percentage": 40.62, "elapsed_time": "1:02:24", "remaining_time": "1:31:14", "throughput": 4632.32, "total_tokens": 17346048} {"current_steps": 17235, "total_steps": 42420, "loss": 0.0728, "lr": 3.7023141039121565e-05, "epoch": 8.125884016973126, "percentage": 40.63, "elapsed_time": "1:02:25", "remaining_time": "1:31:13", "throughput": 4632.36, "total_tokens": 17350624} {"current_steps": 17240, "total_steps": 42420, "loss": 0.112, "lr": 3.7014121650117864e-05, "epoch": 8.128241395568129, "percentage": 40.64, "elapsed_time": "1:02:26", "remaining_time": "1:31:12", "throughput": 4632.42, "total_tokens": 17357088} {"current_steps": 17245, "total_steps": 42420, "loss": 0.014, "lr": 3.700510022732736e-05, "epoch": 8.130598774163131, "percentage": 40.65, "elapsed_time": "1:02:27", "remaining_time": "1:31:11", "throughput": 4632.49, "total_tokens": 17361696} {"current_steps": 17250, "total_steps": 42420, "loss": 0.0361, "lr": 3.699607677227722e-05, "epoch": 8.132956152758133, "percentage": 40.66, "elapsed_time": "1:02:29", "remaining_time": "1:31:10", "throughput": 4632.54, "total_tokens": 17368320} {"current_steps": 17255, "total_steps": 42420, "loss": 0.1406, "lr": 3.698705128649496e-05, "epoch": 8.135313531353136, "percentage": 40.68, "elapsed_time": "1:02:30", "remaining_time": "1:31:09", "throughput": 4632.64, "total_tokens": 17374624} {"current_steps": 17260, "total_steps": 42420, "loss": 0.2459, "lr": 3.697802377150845e-05, "epoch": 8.137670909948138, "percentage": 40.69, "elapsed_time": "1:02:31", "remaining_time": "1:31:08", "throughput": 4632.68, "total_tokens": 17379360} {"current_steps": 17265, "total_steps": 42420, "loss": 0.2148, "lr": 3.696899422884589e-05, "epoch": 8.14002828854314, "percentage": 40.7, "elapsed_time": "1:02:32", "remaining_time": "1:31:07", "throughput": 4632.73, "total_tokens": 17384128} {"current_steps": 17270, "total_steps": 42420, "loss": 0.0895, "lr": 3.695996266003582e-05, "epoch": 8.142385667138143, "percentage": 40.71, "elapsed_time": "1:02:33", "remaining_time": "1:31:06", "throughput": 4632.73, "total_tokens": 17388576} {"current_steps": 17275, "total_steps": 42420, "loss": 0.1656, "lr": 3.6950929066607146e-05, "epoch": 8.144743045733145, "percentage": 40.72, "elapsed_time": "1:02:34", "remaining_time": "1:31:05", "throughput": 4632.83, "total_tokens": 17394432} {"current_steps": 17280, "total_steps": 42420, "loss": 0.1328, "lr": 3.6941893450089104e-05, "epoch": 8.147100424328148, "percentage": 40.74, "elapsed_time": "1:02:35", "remaining_time": "1:31:04", "throughput": 4632.96, "total_tokens": 17401024} {"current_steps": 17285, "total_steps": 42420, "loss": 0.1061, "lr": 3.6932855812011256e-05, "epoch": 8.14945780292315, "percentage": 40.75, "elapsed_time": "1:02:36", "remaining_time": "1:31:03", "throughput": 4633.01, "total_tokens": 17406112} {"current_steps": 17290, "total_steps": 42420, "loss": 0.0489, "lr": 3.6923816153903526e-05, "epoch": 8.151815181518153, "percentage": 40.76, "elapsed_time": "1:02:38", "remaining_time": "1:31:02", "throughput": 4633.1, "total_tokens": 17411616} {"current_steps": 17295, "total_steps": 42420, "loss": 0.093, "lr": 3.691477447729618e-05, "epoch": 8.154172560113155, "percentage": 40.77, "elapsed_time": "1:02:39", "remaining_time": "1:31:01", "throughput": 4633.19, "total_tokens": 17416832} {"current_steps": 17300, "total_steps": 42420, "loss": 0.0543, "lr": 3.690573078371981e-05, "epoch": 8.156529938708157, "percentage": 40.78, "elapsed_time": "1:02:40", "remaining_time": "1:30:59", "throughput": 4633.21, "total_tokens": 17422080} {"current_steps": 17305, "total_steps": 42420, "loss": 0.176, "lr": 3.689668507470538e-05, "epoch": 8.15888731730316, "percentage": 40.79, "elapsed_time": "1:02:41", "remaining_time": "1:30:58", "throughput": 4633.28, "total_tokens": 17426912} {"current_steps": 17310, "total_steps": 42420, "loss": 0.1872, "lr": 3.688763735178415e-05, "epoch": 8.16124469589816, "percentage": 40.81, "elapsed_time": "1:02:42", "remaining_time": "1:30:57", "throughput": 4633.41, "total_tokens": 17433152} {"current_steps": 17315, "total_steps": 42420, "loss": 0.184, "lr": 3.687858761648776e-05, "epoch": 8.163602074493163, "percentage": 40.82, "elapsed_time": "1:02:43", "remaining_time": "1:30:56", "throughput": 4633.47, "total_tokens": 17438208} {"current_steps": 17320, "total_steps": 42420, "loss": 0.076, "lr": 3.686953587034817e-05, "epoch": 8.165959453088165, "percentage": 40.83, "elapsed_time": "1:02:44", "remaining_time": "1:30:55", "throughput": 4633.53, "total_tokens": 17443328} {"current_steps": 17325, "total_steps": 42420, "loss": 0.1784, "lr": 3.6860482114897696e-05, "epoch": 8.168316831683168, "percentage": 40.84, "elapsed_time": "1:02:45", "remaining_time": "1:30:54", "throughput": 4633.55, "total_tokens": 17447840} {"current_steps": 17330, "total_steps": 42420, "loss": 0.1642, "lr": 3.685142635166897e-05, "epoch": 8.17067421027817, "percentage": 40.85, "elapsed_time": "1:02:46", "remaining_time": "1:30:53", "throughput": 4633.58, "total_tokens": 17452544} {"current_steps": 17335, "total_steps": 42420, "loss": 0.2077, "lr": 3.6842368582195e-05, "epoch": 8.173031588873172, "percentage": 40.87, "elapsed_time": "1:02:47", "remaining_time": "1:30:52", "throughput": 4633.64, "total_tokens": 17457824} {"current_steps": 17340, "total_steps": 42420, "loss": 0.0303, "lr": 3.68333088080091e-05, "epoch": 8.175388967468175, "percentage": 40.88, "elapsed_time": "1:02:48", "remaining_time": "1:30:50", "throughput": 4633.64, "total_tokens": 17462496} {"current_steps": 17345, "total_steps": 42420, "loss": 0.1419, "lr": 3.6824247030644935e-05, "epoch": 8.177746346063177, "percentage": 40.89, "elapsed_time": "1:02:49", "remaining_time": "1:30:49", "throughput": 4633.68, "total_tokens": 17467200} {"current_steps": 17350, "total_steps": 42420, "loss": 0.0752, "lr": 3.681518325163651e-05, "epoch": 8.18010372465818, "percentage": 40.9, "elapsed_time": "1:02:50", "remaining_time": "1:30:48", "throughput": 4633.64, "total_tokens": 17471296} {"current_steps": 17355, "total_steps": 42420, "loss": 0.0809, "lr": 3.680611747251816e-05, "epoch": 8.182461103253182, "percentage": 40.91, "elapsed_time": "1:02:51", "remaining_time": "1:30:47", "throughput": 4633.67, "total_tokens": 17475904} {"current_steps": 17360, "total_steps": 42420, "loss": 0.2744, "lr": 3.67970496948246e-05, "epoch": 8.184818481848184, "percentage": 40.92, "elapsed_time": "1:02:52", "remaining_time": "1:30:45", "throughput": 4633.66, "total_tokens": 17480192} {"current_steps": 17365, "total_steps": 42420, "loss": 0.0572, "lr": 3.6787979920090816e-05, "epoch": 8.187175860443187, "percentage": 40.94, "elapsed_time": "1:02:53", "remaining_time": "1:30:44", "throughput": 4633.66, "total_tokens": 17484288} {"current_steps": 17370, "total_steps": 42420, "loss": 0.2616, "lr": 3.677890814985218e-05, "epoch": 8.18953323903819, "percentage": 40.95, "elapsed_time": "1:02:54", "remaining_time": "1:30:42", "throughput": 4633.7, "total_tokens": 17488608} {"current_steps": 17375, "total_steps": 42420, "loss": 0.2157, "lr": 3.6769834385644385e-05, "epoch": 8.191890617633192, "percentage": 40.96, "elapsed_time": "1:02:55", "remaining_time": "1:30:41", "throughput": 4633.69, "total_tokens": 17493120} {"current_steps": 17380, "total_steps": 42420, "loss": 0.0877, "lr": 3.676075862900348e-05, "epoch": 8.194247996228194, "percentage": 40.97, "elapsed_time": "1:02:56", "remaining_time": "1:30:40", "throughput": 4633.71, "total_tokens": 17497376} {"current_steps": 17385, "total_steps": 42420, "loss": 0.1672, "lr": 3.675168088146582e-05, "epoch": 8.196605374823196, "percentage": 40.98, "elapsed_time": "1:02:57", "remaining_time": "1:30:39", "throughput": 4633.8, "total_tokens": 17503008} {"current_steps": 17390, "total_steps": 42420, "loss": 0.0155, "lr": 3.674260114456812e-05, "epoch": 8.198962753418199, "percentage": 40.99, "elapsed_time": "1:02:58", "remaining_time": "1:30:38", "throughput": 4633.91, "total_tokens": 17508992} {"current_steps": 17395, "total_steps": 42420, "loss": 0.1648, "lr": 3.673351941984742e-05, "epoch": 8.201320132013201, "percentage": 41.01, "elapsed_time": "1:02:59", "remaining_time": "1:30:37", "throughput": 4634.0, "total_tokens": 17514880} {"current_steps": 17400, "total_steps": 42420, "loss": 0.0887, "lr": 3.6724435708841114e-05, "epoch": 8.203677510608204, "percentage": 41.02, "elapsed_time": "1:03:00", "remaining_time": "1:30:36", "throughput": 4634.05, "total_tokens": 17519936} {"current_steps": 17405, "total_steps": 42420, "loss": 0.1173, "lr": 3.671535001308691e-05, "epoch": 8.206034889203206, "percentage": 41.03, "elapsed_time": "1:03:01", "remaining_time": "1:30:35", "throughput": 4634.14, "total_tokens": 17525408} {"current_steps": 17410, "total_steps": 42420, "loss": 0.1605, "lr": 3.670626233412286e-05, "epoch": 8.208392267798208, "percentage": 41.04, "elapsed_time": "1:03:03", "remaining_time": "1:30:34", "throughput": 4634.25, "total_tokens": 17531744} {"current_steps": 17415, "total_steps": 42420, "loss": 0.0644, "lr": 3.669717267348736e-05, "epoch": 8.21074964639321, "percentage": 41.05, "elapsed_time": "1:03:03", "remaining_time": "1:30:33", "throughput": 4634.25, "total_tokens": 17535936} {"current_steps": 17420, "total_steps": 42420, "loss": 0.0345, "lr": 3.6688081032719134e-05, "epoch": 8.213107024988213, "percentage": 41.07, "elapsed_time": "1:03:04", "remaining_time": "1:30:31", "throughput": 4634.27, "total_tokens": 17540032} {"current_steps": 17425, "total_steps": 42420, "loss": 0.0444, "lr": 3.667898741335724e-05, "epoch": 8.215464403583216, "percentage": 41.08, "elapsed_time": "1:03:05", "remaining_time": "1:30:30", "throughput": 4634.28, "total_tokens": 17544672} {"current_steps": 17430, "total_steps": 42420, "loss": 0.0954, "lr": 3.666989181694107e-05, "epoch": 8.217821782178218, "percentage": 41.09, "elapsed_time": "1:03:06", "remaining_time": "1:30:29", "throughput": 4634.33, "total_tokens": 17549920} {"current_steps": 17435, "total_steps": 42420, "loss": 0.1944, "lr": 3.666079424501037e-05, "epoch": 8.22017916077322, "percentage": 41.1, "elapsed_time": "1:03:07", "remaining_time": "1:30:28", "throughput": 4634.35, "total_tokens": 17554560} {"current_steps": 17440, "total_steps": 42420, "loss": 0.065, "lr": 3.665169469910518e-05, "epoch": 8.222536539368223, "percentage": 41.11, "elapsed_time": "1:03:08", "remaining_time": "1:30:26", "throughput": 4634.38, "total_tokens": 17559072} {"current_steps": 17445, "total_steps": 42420, "loss": 0.1394, "lr": 3.664259318076592e-05, "epoch": 8.224893917963225, "percentage": 41.12, "elapsed_time": "1:03:09", "remaining_time": "1:30:25", "throughput": 4634.4, "total_tokens": 17563456} {"current_steps": 17450, "total_steps": 42420, "loss": 0.2816, "lr": 3.6633489691533315e-05, "epoch": 8.227251296558228, "percentage": 41.14, "elapsed_time": "1:03:10", "remaining_time": "1:30:24", "throughput": 4634.37, "total_tokens": 17567456} {"current_steps": 17455, "total_steps": 42420, "loss": 0.4686, "lr": 3.662438423294843e-05, "epoch": 8.22960867515323, "percentage": 41.15, "elapsed_time": "1:03:11", "remaining_time": "1:30:23", "throughput": 4634.4, "total_tokens": 17572864} {"current_steps": 17460, "total_steps": 42420, "loss": 0.091, "lr": 3.661527680655267e-05, "epoch": 8.231966053748232, "percentage": 41.16, "elapsed_time": "1:03:13", "remaining_time": "1:30:22", "throughput": 4634.46, "total_tokens": 17578528} {"current_steps": 17465, "total_steps": 42420, "loss": 0.0882, "lr": 3.6606167413887754e-05, "epoch": 8.234323432343235, "percentage": 41.17, "elapsed_time": "1:03:14", "remaining_time": "1:30:21", "throughput": 4634.52, "total_tokens": 17583744} {"current_steps": 17470, "total_steps": 42420, "loss": 0.0692, "lr": 3.659705605649576e-05, "epoch": 8.236680810938237, "percentage": 41.18, "elapsed_time": "1:03:15", "remaining_time": "1:30:20", "throughput": 4634.52, "total_tokens": 17588416} {"current_steps": 17475, "total_steps": 42420, "loss": 0.1346, "lr": 3.658794273591908e-05, "epoch": 8.23903818953324, "percentage": 41.2, "elapsed_time": "1:03:16", "remaining_time": "1:30:19", "throughput": 4634.6, "total_tokens": 17594336} {"current_steps": 17480, "total_steps": 42420, "loss": 0.1136, "lr": 3.657882745370045e-05, "epoch": 8.241395568128242, "percentage": 41.21, "elapsed_time": "1:03:17", "remaining_time": "1:30:17", "throughput": 4634.61, "total_tokens": 17598880} {"current_steps": 17485, "total_steps": 42420, "loss": 0.1409, "lr": 3.656971021138293e-05, "epoch": 8.243752946723244, "percentage": 41.22, "elapsed_time": "1:03:18", "remaining_time": "1:30:16", "throughput": 4634.62, "total_tokens": 17603488} {"current_steps": 17490, "total_steps": 42420, "loss": 0.0388, "lr": 3.656059101050991e-05, "epoch": 8.246110325318247, "percentage": 41.23, "elapsed_time": "1:03:19", "remaining_time": "1:30:15", "throughput": 4634.65, "total_tokens": 17609536} {"current_steps": 17495, "total_steps": 42420, "loss": 0.2091, "lr": 3.655146985262512e-05, "epoch": 8.24846770391325, "percentage": 41.24, "elapsed_time": "1:03:20", "remaining_time": "1:30:14", "throughput": 4634.62, "total_tokens": 17613952} {"current_steps": 17500, "total_steps": 42420, "loss": 0.1117, "lr": 3.654234673927261e-05, "epoch": 8.250825082508252, "percentage": 41.25, "elapsed_time": "1:03:21", "remaining_time": "1:30:13", "throughput": 4634.57, "total_tokens": 17618144} {"current_steps": 17505, "total_steps": 42420, "loss": 0.0808, "lr": 3.6533221671996796e-05, "epoch": 8.253182461103254, "percentage": 41.27, "elapsed_time": "1:03:22", "remaining_time": "1:30:12", "throughput": 4634.6, "total_tokens": 17622880} {"current_steps": 17510, "total_steps": 42420, "loss": 0.2825, "lr": 3.652409465234236e-05, "epoch": 8.255539839698255, "percentage": 41.28, "elapsed_time": "1:03:23", "remaining_time": "1:30:10", "throughput": 4634.52, "total_tokens": 17627200} {"current_steps": 17515, "total_steps": 42420, "loss": 0.1057, "lr": 3.651496568185437e-05, "epoch": 8.257897218293257, "percentage": 41.29, "elapsed_time": "1:03:25", "remaining_time": "1:30:10", "throughput": 4634.64, "total_tokens": 17636096} {"current_steps": 17520, "total_steps": 42420, "loss": 0.2172, "lr": 3.65058347620782e-05, "epoch": 8.26025459688826, "percentage": 41.3, "elapsed_time": "1:03:26", "remaining_time": "1:30:09", "throughput": 4634.74, "total_tokens": 17641792} {"current_steps": 17525, "total_steps": 42420, "loss": 0.0888, "lr": 3.649670189455957e-05, "epoch": 8.262611975483262, "percentage": 41.31, "elapsed_time": "1:03:27", "remaining_time": "1:30:08", "throughput": 4634.76, "total_tokens": 17645920} {"current_steps": 17530, "total_steps": 42420, "loss": 0.0931, "lr": 3.6487567080844507e-05, "epoch": 8.264969354078264, "percentage": 41.32, "elapsed_time": "1:03:28", "remaining_time": "1:30:07", "throughput": 4634.86, "total_tokens": 17651968} {"current_steps": 17535, "total_steps": 42420, "loss": 0.0991, "lr": 3.6478430322479383e-05, "epoch": 8.267326732673267, "percentage": 41.34, "elapsed_time": "1:03:29", "remaining_time": "1:30:06", "throughput": 4634.9, "total_tokens": 17657408} {"current_steps": 17540, "total_steps": 42420, "loss": 0.0786, "lr": 3.64692916210109e-05, "epoch": 8.269684111268269, "percentage": 41.35, "elapsed_time": "1:03:30", "remaining_time": "1:30:05", "throughput": 4634.98, "total_tokens": 17662752} {"current_steps": 17545, "total_steps": 42420, "loss": 0.1244, "lr": 3.646015097798609e-05, "epoch": 8.272041489863271, "percentage": 41.36, "elapsed_time": "1:03:31", "remaining_time": "1:30:04", "throughput": 4635.04, "total_tokens": 17667648} {"current_steps": 17550, "total_steps": 42420, "loss": 0.0589, "lr": 3.6451008394952296e-05, "epoch": 8.274398868458274, "percentage": 41.37, "elapsed_time": "1:03:32", "remaining_time": "1:30:02", "throughput": 4635.03, "total_tokens": 17672096} {"current_steps": 17555, "total_steps": 42420, "loss": 0.0551, "lr": 3.6441863873457204e-05, "epoch": 8.276756247053276, "percentage": 41.38, "elapsed_time": "1:03:34", "remaining_time": "1:30:02", "throughput": 4635.12, "total_tokens": 17678400} {"current_steps": 17560, "total_steps": 42420, "loss": 0.1498, "lr": 3.643271741504884e-05, "epoch": 8.279113625648279, "percentage": 41.4, "elapsed_time": "1:03:34", "remaining_time": "1:30:00", "throughput": 4635.1, "total_tokens": 17682752} {"current_steps": 17565, "total_steps": 42420, "loss": 0.1208, "lr": 3.6423569021275526e-05, "epoch": 8.281471004243281, "percentage": 41.41, "elapsed_time": "1:03:35", "remaining_time": "1:29:59", "throughput": 4635.03, "total_tokens": 17686720} {"current_steps": 17570, "total_steps": 42420, "loss": 0.133, "lr": 3.641441869368595e-05, "epoch": 8.283828382838283, "percentage": 41.42, "elapsed_time": "1:03:36", "remaining_time": "1:29:58", "throughput": 4635.08, "total_tokens": 17691904} {"current_steps": 17575, "total_steps": 42420, "loss": 0.0575, "lr": 3.6405266433829075e-05, "epoch": 8.286185761433286, "percentage": 41.43, "elapsed_time": "1:03:38", "remaining_time": "1:29:57", "throughput": 4635.15, "total_tokens": 17697088} {"current_steps": 17580, "total_steps": 42420, "loss": 0.2267, "lr": 3.639611224325426e-05, "epoch": 8.288543140028288, "percentage": 41.44, "elapsed_time": "1:03:39", "remaining_time": "1:29:56", "throughput": 4635.28, "total_tokens": 17704480} {"current_steps": 17585, "total_steps": 42420, "loss": 0.2092, "lr": 3.638695612351112e-05, "epoch": 8.29090051862329, "percentage": 41.45, "elapsed_time": "1:03:40", "remaining_time": "1:29:55", "throughput": 4635.36, "total_tokens": 17709984} {"current_steps": 17590, "total_steps": 42420, "loss": 0.1443, "lr": 3.637779807614967e-05, "epoch": 8.293257897218293, "percentage": 41.47, "elapsed_time": "1:03:41", "remaining_time": "1:29:54", "throughput": 4635.46, "total_tokens": 17715328} {"current_steps": 17595, "total_steps": 42420, "loss": 0.2866, "lr": 3.6368638102720173e-05, "epoch": 8.295615275813295, "percentage": 41.48, "elapsed_time": "1:03:42", "remaining_time": "1:29:53", "throughput": 4635.47, "total_tokens": 17719776} {"current_steps": 17600, "total_steps": 42420, "loss": 0.2662, "lr": 3.635947620477328e-05, "epoch": 8.297972654408298, "percentage": 41.49, "elapsed_time": "1:03:43", "remaining_time": "1:29:52", "throughput": 4635.54, "total_tokens": 17725376} {"current_steps": 17605, "total_steps": 42420, "loss": 0.1599, "lr": 3.635031238385993e-05, "epoch": 8.3003300330033, "percentage": 41.5, "elapsed_time": "1:03:44", "remaining_time": "1:29:51", "throughput": 4635.56, "total_tokens": 17729600} {"current_steps": 17610, "total_steps": 42420, "loss": 0.1091, "lr": 3.634114664153143e-05, "epoch": 8.302687411598303, "percentage": 41.51, "elapsed_time": "1:03:45", "remaining_time": "1:29:49", "throughput": 4635.51, "total_tokens": 17733984} {"current_steps": 17615, "total_steps": 42420, "loss": 0.1778, "lr": 3.633197897933934e-05, "epoch": 8.305044790193305, "percentage": 41.53, "elapsed_time": "1:03:46", "remaining_time": "1:29:48", "throughput": 4635.55, "total_tokens": 17738912} {"current_steps": 17620, "total_steps": 42420, "loss": 0.1613, "lr": 3.6322809398835636e-05, "epoch": 8.307402168788308, "percentage": 41.54, "elapsed_time": "1:03:47", "remaining_time": "1:29:47", "throughput": 4635.52, "total_tokens": 17743136} {"current_steps": 17625, "total_steps": 42420, "loss": 0.0598, "lr": 3.631363790157254e-05, "epoch": 8.30975954738331, "percentage": 41.55, "elapsed_time": "1:03:48", "remaining_time": "1:29:46", "throughput": 4635.58, "total_tokens": 17748608} {"current_steps": 17630, "total_steps": 42420, "loss": 0.0455, "lr": 3.630446448910265e-05, "epoch": 8.312116925978312, "percentage": 41.56, "elapsed_time": "1:03:49", "remaining_time": "1:29:44", "throughput": 4635.56, "total_tokens": 17752576} {"current_steps": 17635, "total_steps": 42420, "loss": 0.0619, "lr": 3.629528916297885e-05, "epoch": 8.314474304573315, "percentage": 41.57, "elapsed_time": "1:03:50", "remaining_time": "1:29:43", "throughput": 4635.55, "total_tokens": 17756864} {"current_steps": 17640, "total_steps": 42420, "loss": 0.153, "lr": 3.628611192475438e-05, "epoch": 8.316831683168317, "percentage": 41.58, "elapsed_time": "1:03:51", "remaining_time": "1:29:42", "throughput": 4635.54, "total_tokens": 17761952} {"current_steps": 17645, "total_steps": 42420, "loss": 0.0636, "lr": 3.62769327759828e-05, "epoch": 8.31918906176332, "percentage": 41.6, "elapsed_time": "1:03:52", "remaining_time": "1:29:41", "throughput": 4635.51, "total_tokens": 17765920} {"current_steps": 17650, "total_steps": 42420, "loss": 0.0813, "lr": 3.6267751718217963e-05, "epoch": 8.321546440358322, "percentage": 41.61, "elapsed_time": "1:03:53", "remaining_time": "1:29:40", "throughput": 4635.58, "total_tokens": 17771744} {"current_steps": 17655, "total_steps": 42420, "loss": 0.0617, "lr": 3.625856875301408e-05, "epoch": 8.323903818953324, "percentage": 41.62, "elapsed_time": "1:03:54", "remaining_time": "1:29:39", "throughput": 4635.56, "total_tokens": 17776032} {"current_steps": 17660, "total_steps": 42420, "loss": 0.0633, "lr": 3.6249383881925655e-05, "epoch": 8.326261197548327, "percentage": 41.63, "elapsed_time": "1:03:55", "remaining_time": "1:29:38", "throughput": 4635.63, "total_tokens": 17781696} {"current_steps": 17665, "total_steps": 42420, "loss": 0.0624, "lr": 3.624019710650755e-05, "epoch": 8.32861857614333, "percentage": 41.64, "elapsed_time": "1:03:56", "remaining_time": "1:29:36", "throughput": 4635.68, "total_tokens": 17786688} {"current_steps": 17670, "total_steps": 42420, "loss": 0.1178, "lr": 3.623100842831493e-05, "epoch": 8.330975954738332, "percentage": 41.65, "elapsed_time": "1:03:57", "remaining_time": "1:29:35", "throughput": 4635.67, "total_tokens": 17790912} {"current_steps": 17675, "total_steps": 42420, "loss": 0.0963, "lr": 3.622181784890327e-05, "epoch": 8.333333333333334, "percentage": 41.67, "elapsed_time": "1:03:59", "remaining_time": "1:29:34", "throughput": 4635.76, "total_tokens": 17796832} {"current_steps": 17680, "total_steps": 42420, "loss": 0.1215, "lr": 3.621262536982838e-05, "epoch": 8.335690711928336, "percentage": 41.68, "elapsed_time": "1:04:00", "remaining_time": "1:29:33", "throughput": 4635.69, "total_tokens": 17801280} {"current_steps": 17685, "total_steps": 42420, "loss": 0.1412, "lr": 3.6203430992646397e-05, "epoch": 8.338048090523339, "percentage": 41.69, "elapsed_time": "1:04:00", "remaining_time": "1:29:32", "throughput": 4635.73, "total_tokens": 17805824} {"current_steps": 17690, "total_steps": 42420, "loss": 0.2347, "lr": 3.619423471891377e-05, "epoch": 8.340405469118341, "percentage": 41.7, "elapsed_time": "1:04:02", "remaining_time": "1:29:31", "throughput": 4635.81, "total_tokens": 17811840} {"current_steps": 17695, "total_steps": 42420, "loss": 0.0689, "lr": 3.618503655018728e-05, "epoch": 8.342762847713344, "percentage": 41.71, "elapsed_time": "1:04:03", "remaining_time": "1:29:30", "throughput": 4635.84, "total_tokens": 17816768} {"current_steps": 17700, "total_steps": 42420, "loss": 0.2184, "lr": 3.6175836488024e-05, "epoch": 8.345120226308346, "percentage": 41.73, "elapsed_time": "1:04:04", "remaining_time": "1:29:29", "throughput": 4635.88, "total_tokens": 17821824} {"current_steps": 17705, "total_steps": 42420, "loss": 0.1823, "lr": 3.616663453398136e-05, "epoch": 8.347477604903348, "percentage": 41.74, "elapsed_time": "1:04:05", "remaining_time": "1:29:27", "throughput": 4635.85, "total_tokens": 17826400} {"current_steps": 17710, "total_steps": 42420, "loss": 0.24, "lr": 3.6157430689617094e-05, "epoch": 8.34983498349835, "percentage": 41.75, "elapsed_time": "1:04:06", "remaining_time": "1:29:26", "throughput": 4635.93, "total_tokens": 17831264} {"current_steps": 17715, "total_steps": 42420, "loss": 0.2114, "lr": 3.614822495648926e-05, "epoch": 8.352192362093351, "percentage": 41.76, "elapsed_time": "1:04:07", "remaining_time": "1:29:25", "throughput": 4635.95, "total_tokens": 17835840} {"current_steps": 17720, "total_steps": 42420, "loss": 0.084, "lr": 3.613901733615622e-05, "epoch": 8.354549740688354, "percentage": 41.77, "elapsed_time": "1:04:08", "remaining_time": "1:29:23", "throughput": 4635.9, "total_tokens": 17839776} {"current_steps": 17725, "total_steps": 42420, "loss": 0.0482, "lr": 3.612980783017667e-05, "epoch": 8.356907119283356, "percentage": 41.78, "elapsed_time": "1:04:09", "remaining_time": "1:29:22", "throughput": 4635.92, "total_tokens": 17844416} {"current_steps": 17730, "total_steps": 42420, "loss": 0.1103, "lr": 3.612059644010964e-05, "epoch": 8.359264497878359, "percentage": 41.8, "elapsed_time": "1:04:10", "remaining_time": "1:29:21", "throughput": 4635.97, "total_tokens": 17849024} {"current_steps": 17735, "total_steps": 42420, "loss": 0.0851, "lr": 3.611138316751445e-05, "epoch": 8.361621876473361, "percentage": 41.81, "elapsed_time": "1:04:11", "remaining_time": "1:29:20", "throughput": 4636.01, "total_tokens": 17853440} {"current_steps": 17740, "total_steps": 42420, "loss": 0.0609, "lr": 3.610216801395074e-05, "epoch": 8.363979255068363, "percentage": 41.82, "elapsed_time": "1:04:12", "remaining_time": "1:29:19", "throughput": 4636.08, "total_tokens": 17858432} {"current_steps": 17745, "total_steps": 42420, "loss": 0.1874, "lr": 3.60929509809785e-05, "epoch": 8.366336633663366, "percentage": 41.83, "elapsed_time": "1:04:13", "remaining_time": "1:29:18", "throughput": 4636.18, "total_tokens": 17864352} {"current_steps": 17750, "total_steps": 42420, "loss": 0.1618, "lr": 3.6083732070158e-05, "epoch": 8.368694012258368, "percentage": 41.84, "elapsed_time": "1:04:14", "remaining_time": "1:29:16", "throughput": 4636.17, "total_tokens": 17869024} {"current_steps": 17755, "total_steps": 42420, "loss": 0.1328, "lr": 3.6074511283049854e-05, "epoch": 8.37105139085337, "percentage": 41.86, "elapsed_time": "1:04:15", "remaining_time": "1:29:15", "throughput": 4636.23, "total_tokens": 17874944} {"current_steps": 17760, "total_steps": 42420, "loss": 0.3567, "lr": 3.606528862121498e-05, "epoch": 8.373408769448373, "percentage": 41.87, "elapsed_time": "1:04:16", "remaining_time": "1:29:14", "throughput": 4636.24, "total_tokens": 17879264} {"current_steps": 17765, "total_steps": 42420, "loss": 0.0923, "lr": 3.605606408621462e-05, "epoch": 8.375766148043375, "percentage": 41.88, "elapsed_time": "1:04:17", "remaining_time": "1:29:13", "throughput": 4636.33, "total_tokens": 17884960} {"current_steps": 17770, "total_steps": 42420, "loss": 0.1031, "lr": 3.6046837679610336e-05, "epoch": 8.378123526638378, "percentage": 41.89, "elapsed_time": "1:04:18", "remaining_time": "1:29:12", "throughput": 4636.37, "total_tokens": 17889856} {"current_steps": 17775, "total_steps": 42420, "loss": 0.0554, "lr": 3.6037609402964e-05, "epoch": 8.38048090523338, "percentage": 41.9, "elapsed_time": "1:04:19", "remaining_time": "1:29:11", "throughput": 4636.39, "total_tokens": 17894240} {"current_steps": 17780, "total_steps": 42420, "loss": 0.1388, "lr": 3.602837925783778e-05, "epoch": 8.382838283828383, "percentage": 41.91, "elapsed_time": "1:04:20", "remaining_time": "1:29:10", "throughput": 4636.46, "total_tokens": 17899552} {"current_steps": 17785, "total_steps": 42420, "loss": 0.1881, "lr": 3.601914724579423e-05, "epoch": 8.385195662423385, "percentage": 41.93, "elapsed_time": "1:04:21", "remaining_time": "1:29:08", "throughput": 4636.51, "total_tokens": 17904512} {"current_steps": 17790, "total_steps": 42420, "loss": 0.0917, "lr": 3.600991336839613e-05, "epoch": 8.387553041018387, "percentage": 41.94, "elapsed_time": "1:04:22", "remaining_time": "1:29:07", "throughput": 4636.58, "total_tokens": 17910016} {"current_steps": 17795, "total_steps": 42420, "loss": 0.083, "lr": 3.600067762720663e-05, "epoch": 8.38991041961339, "percentage": 41.95, "elapsed_time": "1:04:23", "remaining_time": "1:29:06", "throughput": 4636.57, "total_tokens": 17914560} {"current_steps": 17800, "total_steps": 42420, "loss": 0.1636, "lr": 3.59914400237892e-05, "epoch": 8.392267798208392, "percentage": 41.96, "elapsed_time": "1:04:24", "remaining_time": "1:29:05", "throughput": 4636.62, "total_tokens": 17919456} {"current_steps": 17805, "total_steps": 42420, "loss": 0.1512, "lr": 3.59822005597076e-05, "epoch": 8.394625176803395, "percentage": 41.97, "elapsed_time": "1:04:25", "remaining_time": "1:29:04", "throughput": 4636.67, "total_tokens": 17924352} {"current_steps": 17810, "total_steps": 42420, "loss": 0.1906, "lr": 3.5972959236525904e-05, "epoch": 8.396982555398397, "percentage": 41.98, "elapsed_time": "1:04:26", "remaining_time": "1:29:03", "throughput": 4636.69, "total_tokens": 17929024} {"current_steps": 17815, "total_steps": 42420, "loss": 0.0486, "lr": 3.5963716055808514e-05, "epoch": 8.3993399339934, "percentage": 42.0, "elapsed_time": "1:04:27", "remaining_time": "1:29:01", "throughput": 4636.72, "total_tokens": 17933568} {"current_steps": 17820, "total_steps": 42420, "loss": 0.1695, "lr": 3.5954471019120166e-05, "epoch": 8.401697312588402, "percentage": 42.01, "elapsed_time": "1:04:28", "remaining_time": "1:29:00", "throughput": 4636.77, "total_tokens": 17938336} {"current_steps": 17825, "total_steps": 42420, "loss": 0.1429, "lr": 3.594522412802586e-05, "epoch": 8.404054691183404, "percentage": 42.02, "elapsed_time": "1:04:29", "remaining_time": "1:28:59", "throughput": 4636.81, "total_tokens": 17943808} {"current_steps": 17830, "total_steps": 42420, "loss": 0.1245, "lr": 3.593597538409095e-05, "epoch": 8.406412069778407, "percentage": 42.03, "elapsed_time": "1:04:31", "remaining_time": "1:28:58", "throughput": 4636.88, "total_tokens": 17949536} {"current_steps": 17835, "total_steps": 42420, "loss": 0.0773, "lr": 3.592672478888109e-05, "epoch": 8.408769448373409, "percentage": 42.04, "elapsed_time": "1:04:32", "remaining_time": "1:28:57", "throughput": 4636.94, "total_tokens": 17954560} {"current_steps": 17840, "total_steps": 42420, "loss": 0.1706, "lr": 3.591747234396225e-05, "epoch": 8.411126826968411, "percentage": 42.06, "elapsed_time": "1:04:33", "remaining_time": "1:28:56", "throughput": 4637.03, "total_tokens": 17960288} {"current_steps": 17845, "total_steps": 42420, "loss": 0.1296, "lr": 3.59082180509007e-05, "epoch": 8.413484205563414, "percentage": 42.07, "elapsed_time": "1:04:34", "remaining_time": "1:28:55", "throughput": 4637.06, "total_tokens": 17965056} {"current_steps": 17850, "total_steps": 42420, "loss": 0.047, "lr": 3.589896191126306e-05, "epoch": 8.415841584158416, "percentage": 42.08, "elapsed_time": "1:04:35", "remaining_time": "1:28:54", "throughput": 4637.09, "total_tokens": 17969728} {"current_steps": 17855, "total_steps": 42420, "loss": 0.33, "lr": 3.588970392661622e-05, "epoch": 8.418198962753419, "percentage": 42.09, "elapsed_time": "1:04:36", "remaining_time": "1:28:53", "throughput": 4637.16, "total_tokens": 17975072} {"current_steps": 17860, "total_steps": 42420, "loss": 0.2056, "lr": 3.588044409852739e-05, "epoch": 8.420556341348421, "percentage": 42.1, "elapsed_time": "1:04:37", "remaining_time": "1:28:51", "throughput": 4637.24, "total_tokens": 17980480} {"current_steps": 17865, "total_steps": 42420, "loss": 0.1559, "lr": 3.5871182428564126e-05, "epoch": 8.422913719943423, "percentage": 42.11, "elapsed_time": "1:04:38", "remaining_time": "1:28:50", "throughput": 4637.28, "total_tokens": 17985152} {"current_steps": 17870, "total_steps": 42420, "loss": 0.0718, "lr": 3.5861918918294255e-05, "epoch": 8.425271098538426, "percentage": 42.13, "elapsed_time": "1:04:39", "remaining_time": "1:28:49", "throughput": 4637.35, "total_tokens": 17991264} {"current_steps": 17875, "total_steps": 42420, "loss": 0.0755, "lr": 3.585265356928593e-05, "epoch": 8.427628477133428, "percentage": 42.14, "elapsed_time": "1:04:40", "remaining_time": "1:28:48", "throughput": 4637.35, "total_tokens": 17995712} {"current_steps": 17880, "total_steps": 42420, "loss": 0.0614, "lr": 3.584338638310763e-05, "epoch": 8.42998585572843, "percentage": 42.15, "elapsed_time": "1:04:41", "remaining_time": "1:28:47", "throughput": 4637.43, "total_tokens": 18001088} {"current_steps": 17885, "total_steps": 42420, "loss": 0.0266, "lr": 3.5834117361328124e-05, "epoch": 8.432343234323433, "percentage": 42.16, "elapsed_time": "1:04:42", "remaining_time": "1:28:46", "throughput": 4637.51, "total_tokens": 18006368} {"current_steps": 17890, "total_steps": 42420, "loss": 0.0745, "lr": 3.58248465055165e-05, "epoch": 8.434700612918435, "percentage": 42.17, "elapsed_time": "1:04:43", "remaining_time": "1:28:45", "throughput": 4637.6, "total_tokens": 18012128} {"current_steps": 17895, "total_steps": 42420, "loss": 0.1597, "lr": 3.581557381724216e-05, "epoch": 8.437057991513438, "percentage": 42.19, "elapsed_time": "1:04:44", "remaining_time": "1:28:44", "throughput": 4637.6, "total_tokens": 18016384} {"current_steps": 17900, "total_steps": 42420, "loss": 0.1166, "lr": 3.580629929807481e-05, "epoch": 8.43941537010844, "percentage": 42.2, "elapsed_time": "1:04:45", "remaining_time": "1:28:43", "throughput": 4637.68, "total_tokens": 18021696} {"current_steps": 17905, "total_steps": 42420, "loss": 0.1696, "lr": 3.579702294958448e-05, "epoch": 8.441772748703443, "percentage": 42.21, "elapsed_time": "1:04:46", "remaining_time": "1:28:41", "throughput": 4637.69, "total_tokens": 18026592} {"current_steps": 17910, "total_steps": 42420, "loss": 0.0371, "lr": 3.578774477334148e-05, "epoch": 8.444130127298443, "percentage": 42.22, "elapsed_time": "1:04:48", "remaining_time": "1:28:40", "throughput": 4637.76, "total_tokens": 18032160} {"current_steps": 17915, "total_steps": 42420, "loss": 0.0938, "lr": 3.5778464770916444e-05, "epoch": 8.446487505893446, "percentage": 42.23, "elapsed_time": "1:04:48", "remaining_time": "1:28:39", "throughput": 4637.74, "total_tokens": 18036128} {"current_steps": 17920, "total_steps": 42420, "loss": 0.1998, "lr": 3.5769182943880344e-05, "epoch": 8.448844884488448, "percentage": 42.24, "elapsed_time": "1:04:50", "remaining_time": "1:28:38", "throughput": 4637.74, "total_tokens": 18041152} {"current_steps": 17925, "total_steps": 42420, "loss": 0.0356, "lr": 3.5759899293804416e-05, "epoch": 8.45120226308345, "percentage": 42.26, "elapsed_time": "1:04:51", "remaining_time": "1:28:37", "throughput": 4637.77, "total_tokens": 18046144} {"current_steps": 17930, "total_steps": 42420, "loss": 0.0318, "lr": 3.5750613822260234e-05, "epoch": 8.453559641678453, "percentage": 42.27, "elapsed_time": "1:04:52", "remaining_time": "1:28:36", "throughput": 4637.81, "total_tokens": 18051200} {"current_steps": 17935, "total_steps": 42420, "loss": 0.0408, "lr": 3.574132653081966e-05, "epoch": 8.455917020273455, "percentage": 42.28, "elapsed_time": "1:04:53", "remaining_time": "1:28:35", "throughput": 4637.92, "total_tokens": 18057344} {"current_steps": 17940, "total_steps": 42420, "loss": 0.1748, "lr": 3.5732037421054885e-05, "epoch": 8.458274398868458, "percentage": 42.29, "elapsed_time": "1:04:54", "remaining_time": "1:28:33", "throughput": 4637.88, "total_tokens": 18061216} {"current_steps": 17945, "total_steps": 42420, "loss": 0.0485, "lr": 3.572274649453839e-05, "epoch": 8.46063177746346, "percentage": 42.3, "elapsed_time": "1:04:55", "remaining_time": "1:28:32", "throughput": 4637.94, "total_tokens": 18066432} {"current_steps": 17950, "total_steps": 42420, "loss": 0.0362, "lr": 3.5713453752842986e-05, "epoch": 8.462989156058462, "percentage": 42.31, "elapsed_time": "1:04:56", "remaining_time": "1:28:31", "throughput": 4638.01, "total_tokens": 18072512} {"current_steps": 17955, "total_steps": 42420, "loss": 0.1217, "lr": 3.570415919754176e-05, "epoch": 8.465346534653465, "percentage": 42.33, "elapsed_time": "1:04:57", "remaining_time": "1:28:30", "throughput": 4638.07, "total_tokens": 18077120} {"current_steps": 17960, "total_steps": 42420, "loss": 0.0704, "lr": 3.569486283020813e-05, "epoch": 8.467703913248467, "percentage": 42.34, "elapsed_time": "1:04:58", "remaining_time": "1:28:29", "throughput": 4638.13, "total_tokens": 18082720} {"current_steps": 17965, "total_steps": 42420, "loss": 0.1393, "lr": 3.568556465241581e-05, "epoch": 8.47006129184347, "percentage": 42.35, "elapsed_time": "1:04:59", "remaining_time": "1:28:28", "throughput": 4638.11, "total_tokens": 18086848} {"current_steps": 17970, "total_steps": 42420, "loss": 0.1248, "lr": 3.5676264665738824e-05, "epoch": 8.472418670438472, "percentage": 42.36, "elapsed_time": "1:05:01", "remaining_time": "1:28:27", "throughput": 4638.18, "total_tokens": 18094144} {"current_steps": 17975, "total_steps": 42420, "loss": 0.1912, "lr": 3.5666962871751495e-05, "epoch": 8.474776049033474, "percentage": 42.37, "elapsed_time": "1:05:02", "remaining_time": "1:28:26", "throughput": 4638.25, "total_tokens": 18099104} {"current_steps": 17980, "total_steps": 42420, "loss": 0.0493, "lr": 3.565765927202848e-05, "epoch": 8.477133427628477, "percentage": 42.39, "elapsed_time": "1:05:03", "remaining_time": "1:28:25", "throughput": 4638.24, "total_tokens": 18103200} {"current_steps": 17985, "total_steps": 42420, "loss": 0.0654, "lr": 3.56483538681447e-05, "epoch": 8.47949080622348, "percentage": 42.4, "elapsed_time": "1:05:04", "remaining_time": "1:28:24", "throughput": 4638.31, "total_tokens": 18108384} {"current_steps": 17990, "total_steps": 42420, "loss": 0.1507, "lr": 3.5639046661675414e-05, "epoch": 8.481848184818482, "percentage": 42.41, "elapsed_time": "1:05:05", "remaining_time": "1:28:23", "throughput": 4638.32, "total_tokens": 18113184} {"current_steps": 17995, "total_steps": 42420, "loss": 0.0488, "lr": 3.562973765419616e-05, "epoch": 8.484205563413484, "percentage": 42.42, "elapsed_time": "1:05:05", "remaining_time": "1:28:21", "throughput": 4638.31, "total_tokens": 18116992} {"current_steps": 18000, "total_steps": 42420, "loss": 0.0506, "lr": 3.5620426847282815e-05, "epoch": 8.486562942008486, "percentage": 42.43, "elapsed_time": "1:05:06", "remaining_time": "1:28:20", "throughput": 4638.4, "total_tokens": 18122176} {"current_steps": 18005, "total_steps": 42420, "loss": 0.2296, "lr": 3.561111424251152e-05, "epoch": 8.488920320603489, "percentage": 42.44, "elapsed_time": "1:05:08", "remaining_time": "1:28:19", "throughput": 4638.46, "total_tokens": 18127264} {"current_steps": 18010, "total_steps": 42420, "loss": 0.1819, "lr": 3.560179984145876e-05, "epoch": 8.491277699198491, "percentage": 42.46, "elapsed_time": "1:05:09", "remaining_time": "1:28:18", "throughput": 4638.51, "total_tokens": 18132288} {"current_steps": 18015, "total_steps": 42420, "loss": 0.1761, "lr": 3.559248364570129e-05, "epoch": 8.493635077793494, "percentage": 42.47, "elapsed_time": "1:05:10", "remaining_time": "1:28:17", "throughput": 4638.57, "total_tokens": 18137440} {"current_steps": 18020, "total_steps": 42420, "loss": 0.0349, "lr": 3.558316565681619e-05, "epoch": 8.495992456388496, "percentage": 42.48, "elapsed_time": "1:05:11", "remaining_time": "1:28:15", "throughput": 4638.64, "total_tokens": 18142400} {"current_steps": 18025, "total_steps": 42420, "loss": 0.137, "lr": 3.557384587638083e-05, "epoch": 8.498349834983498, "percentage": 42.49, "elapsed_time": "1:05:12", "remaining_time": "1:28:14", "throughput": 4638.66, "total_tokens": 18146720} {"current_steps": 18030, "total_steps": 42420, "loss": 0.2201, "lr": 3.55645243059729e-05, "epoch": 8.500707213578501, "percentage": 42.5, "elapsed_time": "1:05:12", "remaining_time": "1:28:13", "throughput": 4638.68, "total_tokens": 18151040} {"current_steps": 18035, "total_steps": 42420, "loss": 0.2598, "lr": 3.555520094717038e-05, "epoch": 8.503064592173503, "percentage": 42.52, "elapsed_time": "1:05:13", "remaining_time": "1:28:12", "throughput": 4638.66, "total_tokens": 18155456} {"current_steps": 18040, "total_steps": 42420, "loss": 0.2028, "lr": 3.554587580155156e-05, "epoch": 8.505421970768506, "percentage": 42.53, "elapsed_time": "1:05:15", "remaining_time": "1:28:10", "throughput": 4638.69, "total_tokens": 18160640} {"current_steps": 18045, "total_steps": 42420, "loss": 0.134, "lr": 3.553654887069502e-05, "epoch": 8.507779349363508, "percentage": 42.54, "elapsed_time": "1:05:16", "remaining_time": "1:28:10", "throughput": 4638.77, "total_tokens": 18166784} {"current_steps": 18050, "total_steps": 42420, "loss": 0.182, "lr": 3.5527220156179664e-05, "epoch": 8.51013672795851, "percentage": 42.55, "elapsed_time": "1:05:17", "remaining_time": "1:28:08", "throughput": 4638.8, "total_tokens": 18171648} {"current_steps": 18055, "total_steps": 42420, "loss": 0.1535, "lr": 3.5517889659584675e-05, "epoch": 8.512494106553513, "percentage": 42.56, "elapsed_time": "1:05:18", "remaining_time": "1:28:07", "throughput": 4638.84, "total_tokens": 18176384} {"current_steps": 18060, "total_steps": 42420, "loss": 0.1017, "lr": 3.550855738248955e-05, "epoch": 8.514851485148515, "percentage": 42.57, "elapsed_time": "1:05:19", "remaining_time": "1:28:06", "throughput": 4638.93, "total_tokens": 18182272} {"current_steps": 18065, "total_steps": 42420, "loss": 0.2218, "lr": 3.549922332647408e-05, "epoch": 8.517208863743518, "percentage": 42.59, "elapsed_time": "1:05:20", "remaining_time": "1:28:05", "throughput": 4638.97, "total_tokens": 18186848} {"current_steps": 18070, "total_steps": 42420, "loss": 0.2262, "lr": 3.548988749311838e-05, "epoch": 8.51956624233852, "percentage": 42.6, "elapsed_time": "1:05:21", "remaining_time": "1:28:04", "throughput": 4639.0, "total_tokens": 18191104} {"current_steps": 18075, "total_steps": 42420, "loss": 0.0861, "lr": 3.5480549884002826e-05, "epoch": 8.521923620933523, "percentage": 42.61, "elapsed_time": "1:05:22", "remaining_time": "1:28:02", "throughput": 4639.04, "total_tokens": 18195936} {"current_steps": 18080, "total_steps": 42420, "loss": 0.0368, "lr": 3.5471210500708125e-05, "epoch": 8.524280999528525, "percentage": 42.62, "elapsed_time": "1:05:23", "remaining_time": "1:28:01", "throughput": 4639.12, "total_tokens": 18200960} {"current_steps": 18085, "total_steps": 42420, "loss": 0.1426, "lr": 3.546186934481528e-05, "epoch": 8.526638378123527, "percentage": 42.63, "elapsed_time": "1:05:24", "remaining_time": "1:28:00", "throughput": 4639.22, "total_tokens": 18206880} {"current_steps": 18090, "total_steps": 42420, "loss": 0.164, "lr": 3.545252641790558e-05, "epoch": 8.52899575671853, "percentage": 42.64, "elapsed_time": "1:05:25", "remaining_time": "1:27:59", "throughput": 4639.24, "total_tokens": 18211072} {"current_steps": 18095, "total_steps": 42420, "loss": 0.1881, "lr": 3.544318172156065e-05, "epoch": 8.531353135313532, "percentage": 42.66, "elapsed_time": "1:05:26", "remaining_time": "1:27:58", "throughput": 4639.25, "total_tokens": 18215392} {"current_steps": 18100, "total_steps": 42420, "loss": 0.0527, "lr": 3.543383525736235e-05, "epoch": 8.533710513908535, "percentage": 42.67, "elapsed_time": "1:05:27", "remaining_time": "1:27:57", "throughput": 4639.33, "total_tokens": 18221248} {"current_steps": 18105, "total_steps": 42420, "loss": 0.178, "lr": 3.542448702689291e-05, "epoch": 8.536067892503535, "percentage": 42.68, "elapsed_time": "1:05:28", "remaining_time": "1:27:56", "throughput": 4639.39, "total_tokens": 18226816} {"current_steps": 18110, "total_steps": 42420, "loss": 0.1212, "lr": 3.5415137031734815e-05, "epoch": 8.53842527109854, "percentage": 42.69, "elapsed_time": "1:05:29", "remaining_time": "1:27:55", "throughput": 4639.43, "total_tokens": 18231488} {"current_steps": 18115, "total_steps": 42420, "loss": 0.05, "lr": 3.5405785273470846e-05, "epoch": 8.54078264969354, "percentage": 42.7, "elapsed_time": "1:05:30", "remaining_time": "1:27:53", "throughput": 4639.44, "total_tokens": 18236032} {"current_steps": 18120, "total_steps": 42420, "loss": 0.0478, "lr": 3.539643175368412e-05, "epoch": 8.543140028288542, "percentage": 42.72, "elapsed_time": "1:05:31", "remaining_time": "1:27:52", "throughput": 4639.48, "total_tokens": 18240640} {"current_steps": 18125, "total_steps": 42420, "loss": 0.1519, "lr": 3.538707647395802e-05, "epoch": 8.545497406883545, "percentage": 42.73, "elapsed_time": "1:05:32", "remaining_time": "1:27:51", "throughput": 4639.56, "total_tokens": 18246848} {"current_steps": 18130, "total_steps": 42420, "loss": 0.0435, "lr": 3.537771943587623e-05, "epoch": 8.547854785478547, "percentage": 42.74, "elapsed_time": "1:05:34", "remaining_time": "1:27:50", "throughput": 4639.64, "total_tokens": 18252768} {"current_steps": 18135, "total_steps": 42420, "loss": 0.1155, "lr": 3.536836064102275e-05, "epoch": 8.55021216407355, "percentage": 42.75, "elapsed_time": "1:05:35", "remaining_time": "1:27:49", "throughput": 4639.67, "total_tokens": 18257312} {"current_steps": 18140, "total_steps": 42420, "loss": 0.0906, "lr": 3.535900009098185e-05, "epoch": 8.552569542668552, "percentage": 42.76, "elapsed_time": "1:05:36", "remaining_time": "1:27:48", "throughput": 4639.73, "total_tokens": 18263456} {"current_steps": 18145, "total_steps": 42420, "loss": 0.049, "lr": 3.534963778733813e-05, "epoch": 8.554926921263554, "percentage": 42.77, "elapsed_time": "1:05:37", "remaining_time": "1:27:47", "throughput": 4639.74, "total_tokens": 18268320} {"current_steps": 18150, "total_steps": 42420, "loss": 0.275, "lr": 3.5340273731676456e-05, "epoch": 8.557284299858557, "percentage": 42.79, "elapsed_time": "1:05:38", "remaining_time": "1:27:46", "throughput": 4639.67, "total_tokens": 18272256} {"current_steps": 18155, "total_steps": 42420, "loss": 0.2328, "lr": 3.533090792558201e-05, "epoch": 8.55964167845356, "percentage": 42.8, "elapsed_time": "1:05:39", "remaining_time": "1:27:44", "throughput": 4639.65, "total_tokens": 18276512} {"current_steps": 18160, "total_steps": 42420, "loss": 0.0741, "lr": 3.532154037064025e-05, "epoch": 8.561999057048562, "percentage": 42.81, "elapsed_time": "1:05:40", "remaining_time": "1:27:44", "throughput": 4639.75, "total_tokens": 18282688} {"current_steps": 18165, "total_steps": 42420, "loss": 0.1447, "lr": 3.531217106843696e-05, "epoch": 8.564356435643564, "percentage": 42.82, "elapsed_time": "1:05:41", "remaining_time": "1:27:42", "throughput": 4639.8, "total_tokens": 18287584} {"current_steps": 18170, "total_steps": 42420, "loss": 0.1496, "lr": 3.5302800020558205e-05, "epoch": 8.566713814238566, "percentage": 42.83, "elapsed_time": "1:05:42", "remaining_time": "1:27:41", "throughput": 4639.87, "total_tokens": 18292768} {"current_steps": 18175, "total_steps": 42420, "loss": 0.1955, "lr": 3.529342722859034e-05, "epoch": 8.569071192833569, "percentage": 42.85, "elapsed_time": "1:05:43", "remaining_time": "1:27:40", "throughput": 4639.93, "total_tokens": 18297920} {"current_steps": 18180, "total_steps": 42420, "loss": 0.1051, "lr": 3.5284052694120005e-05, "epoch": 8.571428571428571, "percentage": 42.86, "elapsed_time": "1:05:44", "remaining_time": "1:27:39", "throughput": 4639.94, "total_tokens": 18302304} {"current_steps": 18185, "total_steps": 42420, "loss": 0.0782, "lr": 3.5274676418734163e-05, "epoch": 8.573785950023574, "percentage": 42.87, "elapsed_time": "1:05:45", "remaining_time": "1:27:38", "throughput": 4640.02, "total_tokens": 18307264} {"current_steps": 18190, "total_steps": 42420, "loss": 0.1298, "lr": 3.526529840402006e-05, "epoch": 8.576143328618576, "percentage": 42.88, "elapsed_time": "1:05:46", "remaining_time": "1:27:37", "throughput": 4640.12, "total_tokens": 18312640} {"current_steps": 18195, "total_steps": 42420, "loss": 0.1589, "lr": 3.5255918651565246e-05, "epoch": 8.578500707213578, "percentage": 42.89, "elapsed_time": "1:05:47", "remaining_time": "1:27:35", "throughput": 4640.14, "total_tokens": 18316928} {"current_steps": 18200, "total_steps": 42420, "loss": 0.2473, "lr": 3.524653716295753e-05, "epoch": 8.58085808580858, "percentage": 42.9, "elapsed_time": "1:05:48", "remaining_time": "1:27:34", "throughput": 4640.2, "total_tokens": 18323072} {"current_steps": 18205, "total_steps": 42420, "loss": 0.0977, "lr": 3.523715393978505e-05, "epoch": 8.583215464403583, "percentage": 42.92, "elapsed_time": "1:05:49", "remaining_time": "1:27:33", "throughput": 4640.2, "total_tokens": 18327296} {"current_steps": 18210, "total_steps": 42420, "loss": 0.0982, "lr": 3.522776898363621e-05, "epoch": 8.585572842998586, "percentage": 42.93, "elapsed_time": "1:05:50", "remaining_time": "1:27:32", "throughput": 4640.19, "total_tokens": 18331168} {"current_steps": 18215, "total_steps": 42420, "loss": 0.092, "lr": 3.521838229609976e-05, "epoch": 8.587930221593588, "percentage": 42.94, "elapsed_time": "1:05:51", "remaining_time": "1:27:31", "throughput": 4640.28, "total_tokens": 18337248} {"current_steps": 18220, "total_steps": 42420, "loss": 0.0719, "lr": 3.5208993878764674e-05, "epoch": 8.59028760018859, "percentage": 42.95, "elapsed_time": "1:05:52", "remaining_time": "1:27:30", "throughput": 4640.32, "total_tokens": 18342240} {"current_steps": 18225, "total_steps": 42420, "loss": 0.063, "lr": 3.519960373322026e-05, "epoch": 8.592644978783593, "percentage": 42.96, "elapsed_time": "1:05:53", "remaining_time": "1:27:28", "throughput": 4640.39, "total_tokens": 18347040} {"current_steps": 18230, "total_steps": 42420, "loss": 0.2234, "lr": 3.5190211861056124e-05, "epoch": 8.595002357378595, "percentage": 42.98, "elapsed_time": "1:05:54", "remaining_time": "1:27:27", "throughput": 4640.49, "total_tokens": 18352320} {"current_steps": 18235, "total_steps": 42420, "loss": 0.2042, "lr": 3.5180818263862137e-05, "epoch": 8.597359735973598, "percentage": 42.99, "elapsed_time": "1:05:55", "remaining_time": "1:27:26", "throughput": 4640.54, "total_tokens": 18357280} {"current_steps": 18240, "total_steps": 42420, "loss": 0.1148, "lr": 3.517142294322848e-05, "epoch": 8.5997171145686, "percentage": 43.0, "elapsed_time": "1:05:56", "remaining_time": "1:27:25", "throughput": 4640.58, "total_tokens": 18361920} {"current_steps": 18245, "total_steps": 42420, "loss": 0.1532, "lr": 3.516202590074562e-05, "epoch": 8.602074493163602, "percentage": 43.01, "elapsed_time": "1:05:57", "remaining_time": "1:27:24", "throughput": 4640.63, "total_tokens": 18366720} {"current_steps": 18250, "total_steps": 42420, "loss": 0.0955, "lr": 3.515262713800431e-05, "epoch": 8.604431871758605, "percentage": 43.02, "elapsed_time": "1:05:58", "remaining_time": "1:27:23", "throughput": 4640.69, "total_tokens": 18371776} {"current_steps": 18255, "total_steps": 42420, "loss": 0.0759, "lr": 3.5143226656595604e-05, "epoch": 8.606789250353607, "percentage": 43.03, "elapsed_time": "1:05:59", "remaining_time": "1:27:21", "throughput": 4640.68, "total_tokens": 18376544} {"current_steps": 18260, "total_steps": 42420, "loss": 0.1676, "lr": 3.5133824458110856e-05, "epoch": 8.60914662894861, "percentage": 43.05, "elapsed_time": "1:06:00", "remaining_time": "1:27:20", "throughput": 4640.63, "total_tokens": 18380704} {"current_steps": 18265, "total_steps": 42420, "loss": 0.0673, "lr": 3.512442054414169e-05, "epoch": 8.611504007543612, "percentage": 43.06, "elapsed_time": "1:06:01", "remaining_time": "1:27:19", "throughput": 4640.61, "total_tokens": 18384800} {"current_steps": 18270, "total_steps": 42420, "loss": 0.1202, "lr": 3.511501491628002e-05, "epoch": 8.613861386138614, "percentage": 43.07, "elapsed_time": "1:06:02", "remaining_time": "1:27:18", "throughput": 4640.71, "total_tokens": 18390848} {"current_steps": 18275, "total_steps": 42420, "loss": 0.1822, "lr": 3.510560757611807e-05, "epoch": 8.616218764733617, "percentage": 43.08, "elapsed_time": "1:06:04", "remaining_time": "1:27:17", "throughput": 4640.71, "total_tokens": 18396064} {"current_steps": 18280, "total_steps": 42420, "loss": 0.3791, "lr": 3.5096198525248355e-05, "epoch": 8.61857614332862, "percentage": 43.09, "elapsed_time": "1:06:05", "remaining_time": "1:27:16", "throughput": 4640.8, "total_tokens": 18401696} {"current_steps": 18285, "total_steps": 42420, "loss": 0.0985, "lr": 3.508678776526364e-05, "epoch": 8.620933521923622, "percentage": 43.1, "elapsed_time": "1:06:06", "remaining_time": "1:27:15", "throughput": 4640.87, "total_tokens": 18406752} {"current_steps": 18290, "total_steps": 42420, "loss": 0.0627, "lr": 3.507737529775702e-05, "epoch": 8.623290900518624, "percentage": 43.12, "elapsed_time": "1:06:07", "remaining_time": "1:27:13", "throughput": 4640.92, "total_tokens": 18411552} {"current_steps": 18295, "total_steps": 42420, "loss": 0.1923, "lr": 3.506796112432187e-05, "epoch": 8.625648279113626, "percentage": 43.13, "elapsed_time": "1:06:08", "remaining_time": "1:27:12", "throughput": 4640.96, "total_tokens": 18416256} {"current_steps": 18300, "total_steps": 42420, "loss": 0.0434, "lr": 3.505854524655184e-05, "epoch": 8.628005657708629, "percentage": 43.14, "elapsed_time": "1:06:09", "remaining_time": "1:27:11", "throughput": 4641.01, "total_tokens": 18421440} {"current_steps": 18305, "total_steps": 42420, "loss": 0.2011, "lr": 3.5049127666040895e-05, "epoch": 8.630363036303631, "percentage": 43.15, "elapsed_time": "1:06:10", "remaining_time": "1:27:10", "throughput": 4641.1, "total_tokens": 18426912} {"current_steps": 18310, "total_steps": 42420, "loss": 0.1422, "lr": 3.503970838438325e-05, "epoch": 8.632720414898632, "percentage": 43.16, "elapsed_time": "1:06:11", "remaining_time": "1:27:09", "throughput": 4641.09, "total_tokens": 18430624} {"current_steps": 18315, "total_steps": 42420, "loss": 0.2197, "lr": 3.5030287403173446e-05, "epoch": 8.635077793493634, "percentage": 43.18, "elapsed_time": "1:06:12", "remaining_time": "1:27:08", "throughput": 4641.19, "total_tokens": 18436576} {"current_steps": 18320, "total_steps": 42420, "loss": 0.1287, "lr": 3.5020864724006294e-05, "epoch": 8.637435172088637, "percentage": 43.19, "elapsed_time": "1:06:13", "remaining_time": "1:27:06", "throughput": 4641.24, "total_tokens": 18441280} {"current_steps": 18325, "total_steps": 42420, "loss": 0.0478, "lr": 3.501144034847688e-05, "epoch": 8.639792550683639, "percentage": 43.2, "elapsed_time": "1:06:14", "remaining_time": "1:27:05", "throughput": 4641.3, "total_tokens": 18446464} {"current_steps": 18330, "total_steps": 42420, "loss": 0.082, "lr": 3.50020142781806e-05, "epoch": 8.642149929278641, "percentage": 43.21, "elapsed_time": "1:06:15", "remaining_time": "1:27:04", "throughput": 4641.38, "total_tokens": 18451840} {"current_steps": 18335, "total_steps": 42420, "loss": 0.1319, "lr": 3.499258651471313e-05, "epoch": 8.644507307873644, "percentage": 43.22, "elapsed_time": "1:06:16", "remaining_time": "1:27:03", "throughput": 4641.4, "total_tokens": 18456416} {"current_steps": 18340, "total_steps": 42420, "loss": 0.1047, "lr": 3.498315705967043e-05, "epoch": 8.646864686468646, "percentage": 43.23, "elapsed_time": "1:06:17", "remaining_time": "1:27:02", "throughput": 4641.42, "total_tokens": 18461312} {"current_steps": 18345, "total_steps": 42420, "loss": 0.1747, "lr": 3.4973725914648743e-05, "epoch": 8.649222065063649, "percentage": 43.25, "elapsed_time": "1:06:18", "remaining_time": "1:27:01", "throughput": 4641.42, "total_tokens": 18465664} {"current_steps": 18350, "total_steps": 42420, "loss": 0.0531, "lr": 3.49642930812446e-05, "epoch": 8.651579443658651, "percentage": 43.26, "elapsed_time": "1:06:19", "remaining_time": "1:27:00", "throughput": 4641.46, "total_tokens": 18471168} {"current_steps": 18355, "total_steps": 42420, "loss": 0.2008, "lr": 3.495485856105483e-05, "epoch": 8.653936822253653, "percentage": 43.27, "elapsed_time": "1:06:20", "remaining_time": "1:26:58", "throughput": 4641.48, "total_tokens": 18475552} {"current_steps": 18360, "total_steps": 42420, "loss": 0.045, "lr": 3.494542235567652e-05, "epoch": 8.656294200848656, "percentage": 43.28, "elapsed_time": "1:06:21", "remaining_time": "1:26:57", "throughput": 4641.55, "total_tokens": 18481120} {"current_steps": 18365, "total_steps": 42420, "loss": 0.0971, "lr": 3.493598446670707e-05, "epoch": 8.658651579443658, "percentage": 43.29, "elapsed_time": "1:06:22", "remaining_time": "1:26:56", "throughput": 4641.57, "total_tokens": 18485632} {"current_steps": 18370, "total_steps": 42420, "loss": 0.0626, "lr": 3.492654489574416e-05, "epoch": 8.66100895803866, "percentage": 43.31, "elapsed_time": "1:06:23", "remaining_time": "1:26:55", "throughput": 4641.59, "total_tokens": 18490304} {"current_steps": 18375, "total_steps": 42420, "loss": 0.2569, "lr": 3.491710364438573e-05, "epoch": 8.663366336633663, "percentage": 43.32, "elapsed_time": "1:06:24", "remaining_time": "1:26:54", "throughput": 4641.61, "total_tokens": 18496416} {"current_steps": 18380, "total_steps": 42420, "loss": 0.1205, "lr": 3.490766071423005e-05, "epoch": 8.665723715228665, "percentage": 43.33, "elapsed_time": "1:06:26", "remaining_time": "1:26:53", "throughput": 4641.71, "total_tokens": 18503072} {"current_steps": 18385, "total_steps": 42420, "loss": 0.1031, "lr": 3.489821610687562e-05, "epoch": 8.668081093823668, "percentage": 43.34, "elapsed_time": "1:06:27", "remaining_time": "1:26:52", "throughput": 4641.79, "total_tokens": 18508352} {"current_steps": 18390, "total_steps": 42420, "loss": 0.0509, "lr": 3.488876982392127e-05, "epoch": 8.67043847241867, "percentage": 43.35, "elapsed_time": "1:06:28", "remaining_time": "1:26:51", "throughput": 4641.81, "total_tokens": 18512448} {"current_steps": 18395, "total_steps": 42420, "loss": 0.0639, "lr": 3.48793218669661e-05, "epoch": 8.672795851013673, "percentage": 43.36, "elapsed_time": "1:06:29", "remaining_time": "1:26:50", "throughput": 4641.9, "total_tokens": 18517856} {"current_steps": 18400, "total_steps": 42420, "loss": 0.0845, "lr": 3.486987223760947e-05, "epoch": 8.675153229608675, "percentage": 43.38, "elapsed_time": "1:06:30", "remaining_time": "1:26:49", "throughput": 4641.94, "total_tokens": 18522560} {"current_steps": 18405, "total_steps": 42420, "loss": 0.1104, "lr": 3.4860420937451055e-05, "epoch": 8.677510608203677, "percentage": 43.39, "elapsed_time": "1:06:31", "remaining_time": "1:26:47", "throughput": 4641.95, "total_tokens": 18526784} {"current_steps": 18410, "total_steps": 42420, "loss": 0.1824, "lr": 3.485096796809079e-05, "epoch": 8.67986798679868, "percentage": 43.4, "elapsed_time": "1:06:32", "remaining_time": "1:26:46", "throughput": 4641.97, "total_tokens": 18531104} {"current_steps": 18415, "total_steps": 42420, "loss": 0.1684, "lr": 3.4841513331128914e-05, "epoch": 8.682225365393682, "percentage": 43.41, "elapsed_time": "1:06:32", "remaining_time": "1:26:45", "throughput": 4642.01, "total_tokens": 18535520} {"current_steps": 18420, "total_steps": 42420, "loss": 0.0705, "lr": 3.483205702816593e-05, "epoch": 8.684582743988685, "percentage": 43.42, "elapsed_time": "1:06:34", "remaining_time": "1:26:44", "throughput": 4642.1, "total_tokens": 18541056} {"current_steps": 18425, "total_steps": 42420, "loss": 0.0442, "lr": 3.482259906080263e-05, "epoch": 8.686940122583687, "percentage": 43.43, "elapsed_time": "1:06:35", "remaining_time": "1:26:42", "throughput": 4642.18, "total_tokens": 18546336} {"current_steps": 18430, "total_steps": 42420, "loss": 0.0592, "lr": 3.481313943064008e-05, "epoch": 8.68929750117869, "percentage": 43.45, "elapsed_time": "1:06:36", "remaining_time": "1:26:42", "throughput": 4642.28, "total_tokens": 18552544} {"current_steps": 18435, "total_steps": 42420, "loss": 0.1747, "lr": 3.480367813927965e-05, "epoch": 8.691654879773692, "percentage": 43.46, "elapsed_time": "1:06:37", "remaining_time": "1:26:41", "throughput": 4642.35, "total_tokens": 18558016} {"current_steps": 18440, "total_steps": 42420, "loss": 0.0829, "lr": 3.4794215188322964e-05, "epoch": 8.694012258368694, "percentage": 43.47, "elapsed_time": "1:06:38", "remaining_time": "1:26:39", "throughput": 4642.37, "total_tokens": 18563040} {"current_steps": 18445, "total_steps": 42420, "loss": 0.2105, "lr": 3.478475057937194e-05, "epoch": 8.696369636963697, "percentage": 43.48, "elapsed_time": "1:06:39", "remaining_time": "1:26:38", "throughput": 4642.41, "total_tokens": 18567584} {"current_steps": 18450, "total_steps": 42420, "loss": 0.2731, "lr": 3.477528431402879e-05, "epoch": 8.698727015558699, "percentage": 43.49, "elapsed_time": "1:06:40", "remaining_time": "1:26:37", "throughput": 4642.49, "total_tokens": 18573888} {"current_steps": 18455, "total_steps": 42420, "loss": 0.0953, "lr": 3.4765816393895964e-05, "epoch": 8.701084394153701, "percentage": 43.51, "elapsed_time": "1:06:41", "remaining_time": "1:26:36", "throughput": 4642.49, "total_tokens": 18577952} {"current_steps": 18460, "total_steps": 42420, "loss": 0.0781, "lr": 3.475634682057625e-05, "epoch": 8.703441772748704, "percentage": 43.52, "elapsed_time": "1:06:42", "remaining_time": "1:26:35", "throughput": 4642.46, "total_tokens": 18582048} {"current_steps": 18465, "total_steps": 42420, "loss": 0.0425, "lr": 3.474687559567268e-05, "epoch": 8.705799151343706, "percentage": 43.53, "elapsed_time": "1:06:43", "remaining_time": "1:26:34", "throughput": 4642.49, "total_tokens": 18586912} {"current_steps": 18470, "total_steps": 42420, "loss": 0.034, "lr": 3.473740272078855e-05, "epoch": 8.708156529938709, "percentage": 43.54, "elapsed_time": "1:06:44", "remaining_time": "1:26:32", "throughput": 4642.55, "total_tokens": 18591904} {"current_steps": 18475, "total_steps": 42420, "loss": 0.0671, "lr": 3.472792819752747e-05, "epoch": 8.710513908533711, "percentage": 43.55, "elapsed_time": "1:06:45", "remaining_time": "1:26:31", "throughput": 4642.62, "total_tokens": 18597056} {"current_steps": 18480, "total_steps": 42420, "loss": 0.1088, "lr": 3.471845202749332e-05, "epoch": 8.712871287128714, "percentage": 43.56, "elapsed_time": "1:06:46", "remaining_time": "1:26:30", "throughput": 4642.68, "total_tokens": 18602240} {"current_steps": 18485, "total_steps": 42420, "loss": 0.1453, "lr": 3.470897421229026e-05, "epoch": 8.715228665723716, "percentage": 43.58, "elapsed_time": "1:06:48", "remaining_time": "1:26:29", "throughput": 4642.8, "total_tokens": 18608800} {"current_steps": 18490, "total_steps": 42420, "loss": 0.0513, "lr": 3.46994947535227e-05, "epoch": 8.717586044318718, "percentage": 43.59, "elapsed_time": "1:06:49", "remaining_time": "1:26:28", "throughput": 4642.77, "total_tokens": 18613184} {"current_steps": 18495, "total_steps": 42420, "loss": 0.2321, "lr": 3.4690013652795374e-05, "epoch": 8.71994342291372, "percentage": 43.6, "elapsed_time": "1:06:50", "remaining_time": "1:26:27", "throughput": 4642.81, "total_tokens": 18617728} {"current_steps": 18500, "total_steps": 42420, "loss": 0.203, "lr": 3.468053091171326e-05, "epoch": 8.722300801508723, "percentage": 43.61, "elapsed_time": "1:06:51", "remaining_time": "1:26:26", "throughput": 4642.87, "total_tokens": 18622624} {"current_steps": 18505, "total_steps": 42420, "loss": 0.1017, "lr": 3.4671046531881633e-05, "epoch": 8.724658180103724, "percentage": 43.62, "elapsed_time": "1:06:52", "remaining_time": "1:26:25", "throughput": 4642.92, "total_tokens": 18627712} {"current_steps": 18510, "total_steps": 42420, "loss": 0.1638, "lr": 3.4661560514906034e-05, "epoch": 8.727015558698728, "percentage": 43.64, "elapsed_time": "1:06:53", "remaining_time": "1:26:23", "throughput": 4642.98, "total_tokens": 18632928} {"current_steps": 18515, "total_steps": 42420, "loss": 0.0945, "lr": 3.465207286239228e-05, "epoch": 8.729372937293729, "percentage": 43.65, "elapsed_time": "1:06:54", "remaining_time": "1:26:23", "throughput": 4643.08, "total_tokens": 18639264} {"current_steps": 18520, "total_steps": 42420, "loss": 0.0544, "lr": 3.4642583575946476e-05, "epoch": 8.731730315888731, "percentage": 43.66, "elapsed_time": "1:06:55", "remaining_time": "1:26:21", "throughput": 4643.14, "total_tokens": 18643776} {"current_steps": 18525, "total_steps": 42420, "loss": 0.1805, "lr": 3.4633092657174995e-05, "epoch": 8.734087694483733, "percentage": 43.67, "elapsed_time": "1:06:56", "remaining_time": "1:26:20", "throughput": 4643.16, "total_tokens": 18648192} {"current_steps": 18530, "total_steps": 42420, "loss": 0.0713, "lr": 3.462360010768448e-05, "epoch": 8.736445073078736, "percentage": 43.68, "elapsed_time": "1:06:57", "remaining_time": "1:26:19", "throughput": 4643.22, "total_tokens": 18653120} {"current_steps": 18535, "total_steps": 42420, "loss": 0.2582, "lr": 3.4614105929081876e-05, "epoch": 8.738802451673738, "percentage": 43.69, "elapsed_time": "1:06:58", "remaining_time": "1:26:18", "throughput": 4643.3, "total_tokens": 18658208} {"current_steps": 18540, "total_steps": 42420, "loss": 0.1146, "lr": 3.4604610122974376e-05, "epoch": 8.74115983026874, "percentage": 43.71, "elapsed_time": "1:06:59", "remaining_time": "1:26:16", "throughput": 4643.31, "total_tokens": 18662944} {"current_steps": 18545, "total_steps": 42420, "loss": 0.1617, "lr": 3.4595112690969454e-05, "epoch": 8.743517208863743, "percentage": 43.72, "elapsed_time": "1:07:00", "remaining_time": "1:26:15", "throughput": 4643.39, "total_tokens": 18668608} {"current_steps": 18550, "total_steps": 42420, "loss": 0.0993, "lr": 3.4585613634674874e-05, "epoch": 8.745874587458745, "percentage": 43.73, "elapsed_time": "1:07:01", "remaining_time": "1:26:14", "throughput": 4643.44, "total_tokens": 18673792} {"current_steps": 18555, "total_steps": 42420, "loss": 0.0984, "lr": 3.457611295569865e-05, "epoch": 8.748231966053748, "percentage": 43.74, "elapsed_time": "1:07:02", "remaining_time": "1:26:13", "throughput": 4643.5, "total_tokens": 18678848} {"current_steps": 18560, "total_steps": 42420, "loss": 0.2667, "lr": 3.456661065564911e-05, "epoch": 8.75058934464875, "percentage": 43.75, "elapsed_time": "1:07:03", "remaining_time": "1:26:12", "throughput": 4643.51, "total_tokens": 18682944} {"current_steps": 18565, "total_steps": 42420, "loss": 0.1882, "lr": 3.455710673613481e-05, "epoch": 8.752946723243753, "percentage": 43.76, "elapsed_time": "1:07:04", "remaining_time": "1:26:11", "throughput": 4643.55, "total_tokens": 18688032} {"current_steps": 18570, "total_steps": 42420, "loss": 0.1257, "lr": 3.454760119876461e-05, "epoch": 8.755304101838755, "percentage": 43.78, "elapsed_time": "1:07:05", "remaining_time": "1:26:10", "throughput": 4643.63, "total_tokens": 18693760} {"current_steps": 18575, "total_steps": 42420, "loss": 0.0325, "lr": 3.453809404514764e-05, "epoch": 8.757661480433757, "percentage": 43.79, "elapsed_time": "1:07:06", "remaining_time": "1:26:09", "throughput": 4643.68, "total_tokens": 18698464} {"current_steps": 18580, "total_steps": 42420, "loss": 0.1045, "lr": 3.4528585276893294e-05, "epoch": 8.76001885902876, "percentage": 43.8, "elapsed_time": "1:07:07", "remaining_time": "1:26:08", "throughput": 4643.74, "total_tokens": 18704096} {"current_steps": 18585, "total_steps": 42420, "loss": 0.1154, "lr": 3.4519074895611244e-05, "epoch": 8.762376237623762, "percentage": 43.81, "elapsed_time": "1:07:08", "remaining_time": "1:26:06", "throughput": 4643.81, "total_tokens": 18709408} {"current_steps": 18590, "total_steps": 42420, "loss": 0.1484, "lr": 3.450956290291144e-05, "epoch": 8.764733616218765, "percentage": 43.82, "elapsed_time": "1:07:09", "remaining_time": "1:26:05", "throughput": 4643.83, "total_tokens": 18713920} {"current_steps": 18595, "total_steps": 42420, "loss": 0.0957, "lr": 3.45000493004041e-05, "epoch": 8.767090994813767, "percentage": 43.84, "elapsed_time": "1:07:10", "remaining_time": "1:26:04", "throughput": 4643.84, "total_tokens": 18717952} {"current_steps": 18600, "total_steps": 42420, "loss": 0.1871, "lr": 3.4490534089699716e-05, "epoch": 8.76944837340877, "percentage": 43.85, "elapsed_time": "1:07:11", "remaining_time": "1:26:03", "throughput": 4643.87, "total_tokens": 18722208} {"current_steps": 18605, "total_steps": 42420, "loss": 0.0258, "lr": 3.448101727240905e-05, "epoch": 8.771805752003772, "percentage": 43.86, "elapsed_time": "1:07:12", "remaining_time": "1:26:01", "throughput": 4643.86, "total_tokens": 18726848} {"current_steps": 18610, "total_steps": 42420, "loss": 0.244, "lr": 3.447149885014314e-05, "epoch": 8.774163130598774, "percentage": 43.87, "elapsed_time": "1:07:13", "remaining_time": "1:26:00", "throughput": 4643.93, "total_tokens": 18731808} {"current_steps": 18615, "total_steps": 42420, "loss": 0.1282, "lr": 3.4461978824513285e-05, "epoch": 8.776520509193777, "percentage": 43.88, "elapsed_time": "1:07:14", "remaining_time": "1:25:59", "throughput": 4643.95, "total_tokens": 18736128} {"current_steps": 18620, "total_steps": 42420, "loss": 0.1135, "lr": 3.445245719713108e-05, "epoch": 8.778877887788779, "percentage": 43.89, "elapsed_time": "1:07:15", "remaining_time": "1:25:58", "throughput": 4644.02, "total_tokens": 18741024} {"current_steps": 18625, "total_steps": 42420, "loss": 0.1502, "lr": 3.444293396960835e-05, "epoch": 8.781235266383781, "percentage": 43.91, "elapsed_time": "1:07:16", "remaining_time": "1:25:57", "throughput": 4644.13, "total_tokens": 18747968} {"current_steps": 18630, "total_steps": 42420, "loss": 0.0265, "lr": 3.443340914355725e-05, "epoch": 8.783592644978784, "percentage": 43.92, "elapsed_time": "1:07:17", "remaining_time": "1:25:56", "throughput": 4644.19, "total_tokens": 18752672} {"current_steps": 18635, "total_steps": 42420, "loss": 0.0381, "lr": 3.442388272059014e-05, "epoch": 8.785950023573786, "percentage": 43.93, "elapsed_time": "1:07:18", "remaining_time": "1:25:54", "throughput": 4644.21, "total_tokens": 18756928} {"current_steps": 18640, "total_steps": 42420, "loss": 0.0445, "lr": 3.4414354702319694e-05, "epoch": 8.788307402168789, "percentage": 43.94, "elapsed_time": "1:07:19", "remaining_time": "1:25:53", "throughput": 4644.19, "total_tokens": 18760864} {"current_steps": 18645, "total_steps": 42420, "loss": 0.0765, "lr": 3.440482509035885e-05, "epoch": 8.790664780763791, "percentage": 43.95, "elapsed_time": "1:07:20", "remaining_time": "1:25:52", "throughput": 4644.22, "total_tokens": 18765664} {"current_steps": 18650, "total_steps": 42420, "loss": 0.1795, "lr": 3.43952938863208e-05, "epoch": 8.793022159358793, "percentage": 43.97, "elapsed_time": "1:07:21", "remaining_time": "1:25:51", "throughput": 4644.32, "total_tokens": 18771456} {"current_steps": 18655, "total_steps": 42420, "loss": 0.1398, "lr": 3.438576109181902e-05, "epoch": 8.795379537953796, "percentage": 43.98, "elapsed_time": "1:07:22", "remaining_time": "1:25:50", "throughput": 4644.37, "total_tokens": 18776000} {"current_steps": 18660, "total_steps": 42420, "loss": 0.1018, "lr": 3.437622670846724e-05, "epoch": 8.797736916548798, "percentage": 43.99, "elapsed_time": "1:07:23", "remaining_time": "1:25:48", "throughput": 4644.41, "total_tokens": 18780704} {"current_steps": 18665, "total_steps": 42420, "loss": 0.1416, "lr": 3.436669073787949e-05, "epoch": 8.8000942951438, "percentage": 44.0, "elapsed_time": "1:07:24", "remaining_time": "1:25:47", "throughput": 4644.46, "total_tokens": 18786176} {"current_steps": 18670, "total_steps": 42420, "loss": 0.0476, "lr": 3.435715318167003e-05, "epoch": 8.802451673738803, "percentage": 44.01, "elapsed_time": "1:07:25", "remaining_time": "1:25:46", "throughput": 4644.48, "total_tokens": 18790400} {"current_steps": 18675, "total_steps": 42420, "loss": 0.1089, "lr": 3.434761404145341e-05, "epoch": 8.804809052333805, "percentage": 44.02, "elapsed_time": "1:07:26", "remaining_time": "1:25:45", "throughput": 4644.54, "total_tokens": 18795968} {"current_steps": 18680, "total_steps": 42420, "loss": 0.1764, "lr": 3.433807331884445e-05, "epoch": 8.807166430928808, "percentage": 44.04, "elapsed_time": "1:07:27", "remaining_time": "1:25:44", "throughput": 4644.6, "total_tokens": 18800960} {"current_steps": 18685, "total_steps": 42420, "loss": 0.067, "lr": 3.432853101545822e-05, "epoch": 8.80952380952381, "percentage": 44.05, "elapsed_time": "1:07:28", "remaining_time": "1:25:43", "throughput": 4644.63, "total_tokens": 18805696} {"current_steps": 18690, "total_steps": 42420, "loss": 0.0312, "lr": 3.431898713291009e-05, "epoch": 8.811881188118813, "percentage": 44.06, "elapsed_time": "1:07:29", "remaining_time": "1:25:42", "throughput": 4644.67, "total_tokens": 18810784} {"current_steps": 18695, "total_steps": 42420, "loss": 0.1546, "lr": 3.430944167281566e-05, "epoch": 8.814238566713815, "percentage": 44.07, "elapsed_time": "1:07:31", "remaining_time": "1:25:41", "throughput": 4644.76, "total_tokens": 18816288} {"current_steps": 18700, "total_steps": 42420, "loss": 0.0749, "lr": 3.429989463679082e-05, "epoch": 8.816595945308817, "percentage": 44.08, "elapsed_time": "1:07:32", "remaining_time": "1:25:39", "throughput": 4644.79, "total_tokens": 18820928} {"current_steps": 18705, "total_steps": 42420, "loss": 0.0832, "lr": 3.429034602645171e-05, "epoch": 8.81895332390382, "percentage": 44.09, "elapsed_time": "1:07:32", "remaining_time": "1:25:38", "throughput": 4644.73, "total_tokens": 18824352} {"current_steps": 18710, "total_steps": 42420, "loss": 0.1121, "lr": 3.428079584341477e-05, "epoch": 8.82131070249882, "percentage": 44.11, "elapsed_time": "1:07:33", "remaining_time": "1:25:37", "throughput": 4644.79, "total_tokens": 18828992} {"current_steps": 18715, "total_steps": 42420, "loss": 0.1384, "lr": 3.4271244089296685e-05, "epoch": 8.823668081093825, "percentage": 44.12, "elapsed_time": "1:07:34", "remaining_time": "1:25:36", "throughput": 4644.86, "total_tokens": 18834656} {"current_steps": 18720, "total_steps": 42420, "loss": 0.0863, "lr": 3.426169076571437e-05, "epoch": 8.826025459688825, "percentage": 44.13, "elapsed_time": "1:07:36", "remaining_time": "1:25:35", "throughput": 4644.94, "total_tokens": 18840096} {"current_steps": 18725, "total_steps": 42420, "loss": 0.1548, "lr": 3.425213587428507e-05, "epoch": 8.828382838283828, "percentage": 44.14, "elapsed_time": "1:07:37", "remaining_time": "1:25:33", "throughput": 4645.01, "total_tokens": 18845472} {"current_steps": 18730, "total_steps": 42420, "loss": 0.066, "lr": 3.4242579416626266e-05, "epoch": 8.83074021687883, "percentage": 44.15, "elapsed_time": "1:07:38", "remaining_time": "1:25:32", "throughput": 4645.01, "total_tokens": 18849792} {"current_steps": 18735, "total_steps": 42420, "loss": 0.0313, "lr": 3.42330213943557e-05, "epoch": 8.833097595473832, "percentage": 44.17, "elapsed_time": "1:07:39", "remaining_time": "1:25:31", "throughput": 4645.06, "total_tokens": 18854624} {"current_steps": 18740, "total_steps": 42420, "loss": 0.1741, "lr": 3.422346180909137e-05, "epoch": 8.835454974068835, "percentage": 44.18, "elapsed_time": "1:07:40", "remaining_time": "1:25:30", "throughput": 4645.07, "total_tokens": 18859328} {"current_steps": 18745, "total_steps": 42420, "loss": 0.0705, "lr": 3.421390066245156e-05, "epoch": 8.837812352663837, "percentage": 44.19, "elapsed_time": "1:07:41", "remaining_time": "1:25:29", "throughput": 4645.14, "total_tokens": 18864640} {"current_steps": 18750, "total_steps": 42420, "loss": 0.2898, "lr": 3.420433795605481e-05, "epoch": 8.84016973125884, "percentage": 44.2, "elapsed_time": "1:07:42", "remaining_time": "1:25:28", "throughput": 4645.21, "total_tokens": 18869376} {"current_steps": 18755, "total_steps": 42420, "loss": 0.1117, "lr": 3.4194773691519934e-05, "epoch": 8.842527109853842, "percentage": 44.21, "elapsed_time": "1:07:43", "remaining_time": "1:25:26", "throughput": 4645.23, "total_tokens": 18873920} {"current_steps": 18760, "total_steps": 42420, "loss": 0.1165, "lr": 3.418520787046598e-05, "epoch": 8.844884488448844, "percentage": 44.22, "elapsed_time": "1:07:44", "remaining_time": "1:25:25", "throughput": 4645.32, "total_tokens": 18879488} {"current_steps": 18765, "total_steps": 42420, "loss": 0.0742, "lr": 3.41756404945123e-05, "epoch": 8.847241867043847, "percentage": 44.24, "elapsed_time": "1:07:45", "remaining_time": "1:25:24", "throughput": 4645.38, "total_tokens": 18884768} {"current_steps": 18770, "total_steps": 42420, "loss": 0.1545, "lr": 3.416607156527847e-05, "epoch": 8.84959924563885, "percentage": 44.25, "elapsed_time": "1:07:46", "remaining_time": "1:25:23", "throughput": 4645.39, "total_tokens": 18888992} {"current_steps": 18775, "total_steps": 42420, "loss": 0.0189, "lr": 3.415650108438436e-05, "epoch": 8.851956624233852, "percentage": 44.26, "elapsed_time": "1:07:47", "remaining_time": "1:25:22", "throughput": 4645.45, "total_tokens": 18893664} {"current_steps": 18780, "total_steps": 42420, "loss": 0.3648, "lr": 3.4146929053450086e-05, "epoch": 8.854314002828854, "percentage": 44.27, "elapsed_time": "1:07:48", "remaining_time": "1:25:21", "throughput": 4645.53, "total_tokens": 18899328} {"current_steps": 18785, "total_steps": 42420, "loss": 0.1617, "lr": 3.413735547409602e-05, "epoch": 8.856671381423856, "percentage": 44.28, "elapsed_time": "1:07:49", "remaining_time": "1:25:19", "throughput": 4645.58, "total_tokens": 18904320} {"current_steps": 18790, "total_steps": 42420, "loss": 0.201, "lr": 3.4127780347942826e-05, "epoch": 8.859028760018859, "percentage": 44.3, "elapsed_time": "1:07:50", "remaining_time": "1:25:18", "throughput": 4645.63, "total_tokens": 18909056} {"current_steps": 18795, "total_steps": 42420, "loss": 0.1293, "lr": 3.41182036766114e-05, "epoch": 8.861386138613861, "percentage": 44.31, "elapsed_time": "1:07:51", "remaining_time": "1:25:17", "throughput": 4645.63, "total_tokens": 18913536} {"current_steps": 18800, "total_steps": 42420, "loss": 0.2077, "lr": 3.410862546172291e-05, "epoch": 8.863743517208864, "percentage": 44.32, "elapsed_time": "1:07:52", "remaining_time": "1:25:16", "throughput": 4645.7, "total_tokens": 18919456} {"current_steps": 18805, "total_steps": 42420, "loss": 0.1453, "lr": 3.4099045704898775e-05, "epoch": 8.866100895803866, "percentage": 44.33, "elapsed_time": "1:07:53", "remaining_time": "1:25:15", "throughput": 4645.74, "total_tokens": 18924512} {"current_steps": 18810, "total_steps": 42420, "loss": 0.0468, "lr": 3.40894644077607e-05, "epoch": 8.868458274398868, "percentage": 44.34, "elapsed_time": "1:07:54", "remaining_time": "1:25:14", "throughput": 4645.78, "total_tokens": 18929344} {"current_steps": 18815, "total_steps": 42420, "loss": 0.114, "lr": 3.407988157193063e-05, "epoch": 8.87081565299387, "percentage": 44.35, "elapsed_time": "1:07:55", "remaining_time": "1:25:13", "throughput": 4645.83, "total_tokens": 18934560} {"current_steps": 18820, "total_steps": 42420, "loss": 0.0555, "lr": 3.4070297199030784e-05, "epoch": 8.873173031588873, "percentage": 44.37, "elapsed_time": "1:07:56", "remaining_time": "1:25:12", "throughput": 4645.91, "total_tokens": 18940256} {"current_steps": 18825, "total_steps": 42420, "loss": 0.21, "lr": 3.406071129068362e-05, "epoch": 8.875530410183876, "percentage": 44.38, "elapsed_time": "1:07:57", "remaining_time": "1:25:11", "throughput": 4645.97, "total_tokens": 18946272} {"current_steps": 18830, "total_steps": 42420, "loss": 0.19, "lr": 3.405112384851188e-05, "epoch": 8.877887788778878, "percentage": 44.39, "elapsed_time": "1:07:59", "remaining_time": "1:25:10", "throughput": 4646.09, "total_tokens": 18952576} {"current_steps": 18835, "total_steps": 42420, "loss": 0.0501, "lr": 3.4041534874138546e-05, "epoch": 8.88024516737388, "percentage": 44.4, "elapsed_time": "1:08:00", "remaining_time": "1:25:09", "throughput": 4646.14, "total_tokens": 18957344} {"current_steps": 18840, "total_steps": 42420, "loss": 0.0393, "lr": 3.403194436918689e-05, "epoch": 8.882602545968883, "percentage": 44.41, "elapsed_time": "1:08:01", "remaining_time": "1:25:08", "throughput": 4646.19, "total_tokens": 18962144} {"current_steps": 18845, "total_steps": 42420, "loss": 0.1864, "lr": 3.402235233528039e-05, "epoch": 8.884959924563885, "percentage": 44.42, "elapsed_time": "1:08:02", "remaining_time": "1:25:06", "throughput": 4646.23, "total_tokens": 18966816} {"current_steps": 18850, "total_steps": 42420, "loss": 0.1062, "lr": 3.4012758774042837e-05, "epoch": 8.887317303158888, "percentage": 44.44, "elapsed_time": "1:08:03", "remaining_time": "1:25:05", "throughput": 4646.19, "total_tokens": 18970496} {"current_steps": 18855, "total_steps": 42420, "loss": 0.1105, "lr": 3.4003163687098245e-05, "epoch": 8.88967468175389, "percentage": 44.45, "elapsed_time": "1:08:03", "remaining_time": "1:25:04", "throughput": 4646.25, "total_tokens": 18975264} {"current_steps": 18860, "total_steps": 42420, "loss": 0.1281, "lr": 3.399356707607091e-05, "epoch": 8.892032060348892, "percentage": 44.46, "elapsed_time": "1:08:04", "remaining_time": "1:25:02", "throughput": 4646.28, "total_tokens": 18979808} {"current_steps": 18865, "total_steps": 42420, "loss": 0.0702, "lr": 3.3983968942585376e-05, "epoch": 8.894389438943895, "percentage": 44.47, "elapsed_time": "1:08:05", "remaining_time": "1:25:01", "throughput": 4646.33, "total_tokens": 18984832} {"current_steps": 18870, "total_steps": 42420, "loss": 0.0555, "lr": 3.397436928826643e-05, "epoch": 8.896746817538897, "percentage": 44.48, "elapsed_time": "1:08:07", "remaining_time": "1:25:00", "throughput": 4646.42, "total_tokens": 18990752} {"current_steps": 18875, "total_steps": 42420, "loss": 0.2359, "lr": 3.396476811473915e-05, "epoch": 8.8991041961339, "percentage": 44.5, "elapsed_time": "1:08:08", "remaining_time": "1:24:59", "throughput": 4646.49, "total_tokens": 18995616} {"current_steps": 18880, "total_steps": 42420, "loss": 0.0442, "lr": 3.395516542362884e-05, "epoch": 8.901461574728902, "percentage": 44.51, "elapsed_time": "1:08:09", "remaining_time": "1:24:58", "throughput": 4646.53, "total_tokens": 19000320} {"current_steps": 18885, "total_steps": 42420, "loss": 0.037, "lr": 3.3945561216561065e-05, "epoch": 8.903818953323904, "percentage": 44.52, "elapsed_time": "1:08:10", "remaining_time": "1:24:57", "throughput": 4646.62, "total_tokens": 19007360} {"current_steps": 18890, "total_steps": 42420, "loss": 0.0833, "lr": 3.393595549516166e-05, "epoch": 8.906176331918907, "percentage": 44.53, "elapsed_time": "1:08:11", "remaining_time": "1:24:56", "throughput": 4646.64, "total_tokens": 19012576} {"current_steps": 18895, "total_steps": 42420, "loss": 0.1114, "lr": 3.3926348261056725e-05, "epoch": 8.90853371051391, "percentage": 44.54, "elapsed_time": "1:08:12", "remaining_time": "1:24:55", "throughput": 4646.68, "total_tokens": 19017344} {"current_steps": 18900, "total_steps": 42420, "loss": 0.0805, "lr": 3.391673951587259e-05, "epoch": 8.910891089108912, "percentage": 44.55, "elapsed_time": "1:08:13", "remaining_time": "1:24:54", "throughput": 4646.73, "total_tokens": 19022016} {"current_steps": 18905, "total_steps": 42420, "loss": 0.2116, "lr": 3.390712926123585e-05, "epoch": 8.913248467703912, "percentage": 44.57, "elapsed_time": "1:08:14", "remaining_time": "1:24:53", "throughput": 4646.77, "total_tokens": 19026912} {"current_steps": 18910, "total_steps": 42420, "loss": 0.071, "lr": 3.3897517498773364e-05, "epoch": 8.915605846298917, "percentage": 44.58, "elapsed_time": "1:08:15", "remaining_time": "1:24:52", "throughput": 4646.9, "total_tokens": 19033184} {"current_steps": 18915, "total_steps": 42420, "loss": 0.1264, "lr": 3.388790423011223e-05, "epoch": 8.917963224893917, "percentage": 44.59, "elapsed_time": "1:08:16", "remaining_time": "1:24:51", "throughput": 4646.91, "total_tokens": 19037664} {"current_steps": 18920, "total_steps": 42420, "loss": 0.1656, "lr": 3.387828945687982e-05, "epoch": 8.92032060348892, "percentage": 44.6, "elapsed_time": "1:08:17", "remaining_time": "1:24:49", "throughput": 4646.97, "total_tokens": 19042784} {"current_steps": 18925, "total_steps": 42420, "loss": 0.1128, "lr": 3.3868673180703755e-05, "epoch": 8.922677982083922, "percentage": 44.61, "elapsed_time": "1:08:18", "remaining_time": "1:24:48", "throughput": 4646.99, "total_tokens": 19047424} {"current_steps": 18930, "total_steps": 42420, "loss": 0.151, "lr": 3.3859055403211894e-05, "epoch": 8.925035360678924, "percentage": 44.63, "elapsed_time": "1:08:19", "remaining_time": "1:24:47", "throughput": 4647.01, "total_tokens": 19052512} {"current_steps": 18935, "total_steps": 42420, "loss": 0.2638, "lr": 3.384943612603238e-05, "epoch": 8.927392739273927, "percentage": 44.64, "elapsed_time": "1:08:20", "remaining_time": "1:24:46", "throughput": 4647.03, "total_tokens": 19056992} {"current_steps": 18940, "total_steps": 42420, "loss": 0.0534, "lr": 3.383981535079357e-05, "epoch": 8.92975011786893, "percentage": 44.65, "elapsed_time": "1:08:21", "remaining_time": "1:24:45", "throughput": 4647.09, "total_tokens": 19061984} {"current_steps": 18945, "total_steps": 42420, "loss": 0.1585, "lr": 3.383019307912413e-05, "epoch": 8.932107496463932, "percentage": 44.66, "elapsed_time": "1:08:22", "remaining_time": "1:24:43", "throughput": 4647.15, "total_tokens": 19066592} {"current_steps": 18950, "total_steps": 42420, "loss": 0.1463, "lr": 3.382056931265292e-05, "epoch": 8.934464875058934, "percentage": 44.67, "elapsed_time": "1:08:23", "remaining_time": "1:24:42", "throughput": 4647.25, "total_tokens": 19072128} {"current_steps": 18955, "total_steps": 42420, "loss": 0.1262, "lr": 3.381094405300909e-05, "epoch": 8.936822253653936, "percentage": 44.68, "elapsed_time": "1:08:25", "remaining_time": "1:24:41", "throughput": 4647.26, "total_tokens": 19077056} {"current_steps": 18960, "total_steps": 42420, "loss": 0.059, "lr": 3.3801317301822035e-05, "epoch": 8.939179632248939, "percentage": 44.7, "elapsed_time": "1:08:26", "remaining_time": "1:24:40", "throughput": 4647.24, "total_tokens": 19082048} {"current_steps": 18965, "total_steps": 42420, "loss": 0.0792, "lr": 3.37916890607214e-05, "epoch": 8.941537010843941, "percentage": 44.71, "elapsed_time": "1:08:27", "remaining_time": "1:24:39", "throughput": 4647.29, "total_tokens": 19086912} {"current_steps": 18970, "total_steps": 42420, "loss": 0.1016, "lr": 3.378205933133708e-05, "epoch": 8.943894389438944, "percentage": 44.72, "elapsed_time": "1:08:27", "remaining_time": "1:24:38", "throughput": 4647.3, "total_tokens": 19090816} {"current_steps": 18975, "total_steps": 42420, "loss": 0.0484, "lr": 3.377242811529922e-05, "epoch": 8.946251768033946, "percentage": 44.73, "elapsed_time": "1:08:29", "remaining_time": "1:24:37", "throughput": 4647.39, "total_tokens": 19096224} {"current_steps": 18980, "total_steps": 42420, "loss": 0.1091, "lr": 3.376279541423824e-05, "epoch": 8.948609146628948, "percentage": 44.74, "elapsed_time": "1:08:29", "remaining_time": "1:24:35", "throughput": 4647.39, "total_tokens": 19100352} {"current_steps": 18985, "total_steps": 42420, "loss": 0.0761, "lr": 3.3753161229784766e-05, "epoch": 8.95096652522395, "percentage": 44.75, "elapsed_time": "1:08:30", "remaining_time": "1:24:34", "throughput": 4647.32, "total_tokens": 19104480} {"current_steps": 18990, "total_steps": 42420, "loss": 0.058, "lr": 3.374352556356973e-05, "epoch": 8.953323903818953, "percentage": 44.77, "elapsed_time": "1:08:31", "remaining_time": "1:24:33", "throughput": 4647.33, "total_tokens": 19109152} {"current_steps": 18995, "total_steps": 42420, "loss": 0.1219, "lr": 3.3733888417224265e-05, "epoch": 8.955681282413956, "percentage": 44.78, "elapsed_time": "1:08:33", "remaining_time": "1:24:32", "throughput": 4647.43, "total_tokens": 19116512} {"current_steps": 19000, "total_steps": 42420, "loss": 0.0814, "lr": 3.372424979237978e-05, "epoch": 8.958038661008958, "percentage": 44.79, "elapsed_time": "1:08:34", "remaining_time": "1:24:31", "throughput": 4647.49, "total_tokens": 19121920} {"current_steps": 19005, "total_steps": 42420, "loss": 0.0902, "lr": 3.371460969066794e-05, "epoch": 8.96039603960396, "percentage": 44.8, "elapsed_time": "1:08:35", "remaining_time": "1:24:30", "throughput": 4647.47, "total_tokens": 19126144} {"current_steps": 19010, "total_steps": 42420, "loss": 0.1744, "lr": 3.370496811372065e-05, "epoch": 8.962753418198963, "percentage": 44.81, "elapsed_time": "1:08:36", "remaining_time": "1:24:29", "throughput": 4647.52, "total_tokens": 19131648} {"current_steps": 19015, "total_steps": 42420, "loss": 0.1578, "lr": 3.3695325063170054e-05, "epoch": 8.965110796793965, "percentage": 44.83, "elapsed_time": "1:08:37", "remaining_time": "1:24:28", "throughput": 4647.54, "total_tokens": 19136768} {"current_steps": 19020, "total_steps": 42420, "loss": 0.2551, "lr": 3.368568054064856e-05, "epoch": 8.967468175388968, "percentage": 44.84, "elapsed_time": "1:08:38", "remaining_time": "1:24:27", "throughput": 4647.59, "total_tokens": 19141792} {"current_steps": 19025, "total_steps": 42420, "loss": 0.0477, "lr": 3.367603454778884e-05, "epoch": 8.96982555398397, "percentage": 44.85, "elapsed_time": "1:08:39", "remaining_time": "1:24:26", "throughput": 4647.58, "total_tokens": 19146720} {"current_steps": 19030, "total_steps": 42420, "loss": 0.2125, "lr": 3.366638708622377e-05, "epoch": 8.972182932578972, "percentage": 44.86, "elapsed_time": "1:08:40", "remaining_time": "1:24:24", "throughput": 4647.61, "total_tokens": 19151776} {"current_steps": 19035, "total_steps": 42420, "loss": 0.0225, "lr": 3.365673815758651e-05, "epoch": 8.974540311173975, "percentage": 44.87, "elapsed_time": "1:08:42", "remaining_time": "1:24:24", "throughput": 4647.67, "total_tokens": 19157856} {"current_steps": 19040, "total_steps": 42420, "loss": 0.1521, "lr": 3.364708776351047e-05, "epoch": 8.976897689768977, "percentage": 44.88, "elapsed_time": "1:08:43", "remaining_time": "1:24:22", "throughput": 4647.72, "total_tokens": 19162752} {"current_steps": 19045, "total_steps": 42420, "loss": 0.1502, "lr": 3.3637435905629284e-05, "epoch": 8.97925506836398, "percentage": 44.9, "elapsed_time": "1:08:43", "remaining_time": "1:24:21", "throughput": 4647.73, "total_tokens": 19166944} {"current_steps": 19050, "total_steps": 42420, "loss": 0.1948, "lr": 3.362778258557686e-05, "epoch": 8.981612446958982, "percentage": 44.91, "elapsed_time": "1:08:45", "remaining_time": "1:24:20", "throughput": 4647.76, "total_tokens": 19172064} {"current_steps": 19055, "total_steps": 42420, "loss": 0.1272, "lr": 3.361812780498733e-05, "epoch": 8.983969825553984, "percentage": 44.92, "elapsed_time": "1:08:46", "remaining_time": "1:24:19", "throughput": 4647.81, "total_tokens": 19177216} {"current_steps": 19060, "total_steps": 42420, "loss": 0.1482, "lr": 3.3608471565495095e-05, "epoch": 8.986327204148987, "percentage": 44.93, "elapsed_time": "1:08:47", "remaining_time": "1:24:18", "throughput": 4647.87, "total_tokens": 19182560} {"current_steps": 19065, "total_steps": 42420, "loss": 0.1537, "lr": 3.359881386873479e-05, "epoch": 8.98868458274399, "percentage": 44.94, "elapsed_time": "1:08:48", "remaining_time": "1:24:17", "throughput": 4647.92, "total_tokens": 19187520} {"current_steps": 19070, "total_steps": 42420, "loss": 0.1157, "lr": 3.3589154716341294e-05, "epoch": 8.991041961338992, "percentage": 44.96, "elapsed_time": "1:08:49", "remaining_time": "1:24:15", "throughput": 4647.9, "total_tokens": 19192160} {"current_steps": 19075, "total_steps": 42420, "loss": 0.0819, "lr": 3.357949410994974e-05, "epoch": 8.993399339933994, "percentage": 44.97, "elapsed_time": "1:08:50", "remaining_time": "1:24:14", "throughput": 4647.93, "total_tokens": 19196832} {"current_steps": 19080, "total_steps": 42420, "loss": 0.0982, "lr": 3.35698320511955e-05, "epoch": 8.995756718528996, "percentage": 44.98, "elapsed_time": "1:08:51", "remaining_time": "1:24:13", "throughput": 4647.97, "total_tokens": 19202272} {"current_steps": 19085, "total_steps": 42420, "loss": 0.3383, "lr": 3.3560168541714206e-05, "epoch": 8.998114097123999, "percentage": 44.99, "elapsed_time": "1:08:52", "remaining_time": "1:24:12", "throughput": 4648.04, "total_tokens": 19207616} {"current_steps": 19089, "total_steps": 42420, "eval_loss": 0.15185481309890747, "epoch": 9.0, "percentage": 45.0, "elapsed_time": "1:09:08", "remaining_time": "1:24:30", "throughput": 4631.05, "total_tokens": 19211360} {"current_steps": 19090, "total_steps": 42420, "loss": 0.1032, "lr": 3.355050358314172e-05, "epoch": 9.000471475719001, "percentage": 45.0, "elapsed_time": "1:09:10", "remaining_time": "1:24:31", "throughput": 4629.43, "total_tokens": 19212512} {"current_steps": 19095, "total_steps": 42420, "loss": 0.0446, "lr": 3.354083717711416e-05, "epoch": 9.002828854314004, "percentage": 45.01, "elapsed_time": "1:09:11", "remaining_time": "1:24:31", "throughput": 4629.53, "total_tokens": 19219552} {"current_steps": 19100, "total_steps": 42420, "loss": 0.102, "lr": 3.353116932526787e-05, "epoch": 9.005186232909006, "percentage": 45.03, "elapsed_time": "1:09:12", "remaining_time": "1:24:29", "throughput": 4629.56, "total_tokens": 19224320} {"current_steps": 19105, "total_steps": 42420, "loss": 0.0545, "lr": 3.352150002923947e-05, "epoch": 9.007543611504008, "percentage": 45.04, "elapsed_time": "1:09:13", "remaining_time": "1:24:28", "throughput": 4629.62, "total_tokens": 19229536} {"current_steps": 19110, "total_steps": 42420, "loss": 0.2174, "lr": 3.351182929066581e-05, "epoch": 9.009900990099009, "percentage": 45.05, "elapsed_time": "1:09:14", "remaining_time": "1:24:27", "throughput": 4629.64, "total_tokens": 19233920} {"current_steps": 19115, "total_steps": 42420, "loss": 0.1436, "lr": 3.3502157111183965e-05, "epoch": 9.012258368694011, "percentage": 45.06, "elapsed_time": "1:09:15", "remaining_time": "1:24:26", "throughput": 4629.66, "total_tokens": 19238944} {"current_steps": 19120, "total_steps": 42420, "loss": 0.1677, "lr": 3.349248349243129e-05, "epoch": 9.014615747289014, "percentage": 45.07, "elapsed_time": "1:09:16", "remaining_time": "1:24:25", "throughput": 4629.67, "total_tokens": 19243744} {"current_steps": 19125, "total_steps": 42420, "loss": 0.1553, "lr": 3.3482808436045344e-05, "epoch": 9.016973125884016, "percentage": 45.08, "elapsed_time": "1:09:17", "remaining_time": "1:24:24", "throughput": 4629.71, "total_tokens": 19248608} {"current_steps": 19130, "total_steps": 42420, "loss": 0.0829, "lr": 3.347313194366396e-05, "epoch": 9.019330504479019, "percentage": 45.1, "elapsed_time": "1:09:18", "remaining_time": "1:24:22", "throughput": 4629.75, "total_tokens": 19253152} {"current_steps": 19135, "total_steps": 42420, "loss": 0.2017, "lr": 3.346345401692521e-05, "epoch": 9.021687883074021, "percentage": 45.11, "elapsed_time": "1:09:19", "remaining_time": "1:24:21", "throughput": 4629.8, "total_tokens": 19258112} {"current_steps": 19140, "total_steps": 42420, "loss": 0.0674, "lr": 3.34537746574674e-05, "epoch": 9.024045261669023, "percentage": 45.12, "elapsed_time": "1:09:20", "remaining_time": "1:24:20", "throughput": 4629.82, "total_tokens": 19262624} {"current_steps": 19145, "total_steps": 42420, "loss": 0.1199, "lr": 3.344409386692906e-05, "epoch": 9.026402640264026, "percentage": 45.13, "elapsed_time": "1:09:21", "remaining_time": "1:24:19", "throughput": 4629.83, "total_tokens": 19267360} {"current_steps": 19150, "total_steps": 42420, "loss": 0.2416, "lr": 3.343441164694901e-05, "epoch": 9.028760018859028, "percentage": 45.14, "elapsed_time": "1:09:22", "remaining_time": "1:24:18", "throughput": 4629.89, "total_tokens": 19272608} {"current_steps": 19155, "total_steps": 42420, "loss": 0.0867, "lr": 3.342472799916628e-05, "epoch": 9.03111739745403, "percentage": 45.16, "elapsed_time": "1:09:23", "remaining_time": "1:24:16", "throughput": 4629.84, "total_tokens": 19276448} {"current_steps": 19160, "total_steps": 42420, "loss": 0.165, "lr": 3.341504292522014e-05, "epoch": 9.033474776049033, "percentage": 45.17, "elapsed_time": "1:09:24", "remaining_time": "1:24:15", "throughput": 4629.86, "total_tokens": 19280832} {"current_steps": 19165, "total_steps": 42420, "loss": 0.1047, "lr": 3.34053564267501e-05, "epoch": 9.035832154644035, "percentage": 45.18, "elapsed_time": "1:09:25", "remaining_time": "1:24:14", "throughput": 4629.9, "total_tokens": 19285824} {"current_steps": 19170, "total_steps": 42420, "loss": 0.0832, "lr": 3.339566850539595e-05, "epoch": 9.038189533239038, "percentage": 45.19, "elapsed_time": "1:09:26", "remaining_time": "1:24:13", "throughput": 4629.97, "total_tokens": 19291424} {"current_steps": 19175, "total_steps": 42420, "loss": 0.0689, "lr": 3.338597916279767e-05, "epoch": 9.04054691183404, "percentage": 45.2, "elapsed_time": "1:09:27", "remaining_time": "1:24:12", "throughput": 4630.04, "total_tokens": 19297024} {"current_steps": 19180, "total_steps": 42420, "loss": 0.0536, "lr": 3.33762884005955e-05, "epoch": 9.042904290429043, "percentage": 45.21, "elapsed_time": "1:09:28", "remaining_time": "1:24:11", "throughput": 4630.04, "total_tokens": 19301440} {"current_steps": 19185, "total_steps": 42420, "loss": 0.1484, "lr": 3.3366596220429925e-05, "epoch": 9.045261669024045, "percentage": 45.23, "elapsed_time": "1:09:29", "remaining_time": "1:24:10", "throughput": 4630.06, "total_tokens": 19306848} {"current_steps": 19190, "total_steps": 42420, "loss": 0.0974, "lr": 3.335690262394166e-05, "epoch": 9.047619047619047, "percentage": 45.24, "elapsed_time": "1:09:31", "remaining_time": "1:24:09", "throughput": 4630.14, "total_tokens": 19312992} {"current_steps": 19195, "total_steps": 42420, "loss": 0.4488, "lr": 3.3347207612771685e-05, "epoch": 9.04997642621405, "percentage": 45.25, "elapsed_time": "1:09:32", "remaining_time": "1:24:08", "throughput": 4630.17, "total_tokens": 19320544} {"current_steps": 19200, "total_steps": 42420, "loss": 0.1104, "lr": 3.333751118856118e-05, "epoch": 9.052333804809052, "percentage": 45.26, "elapsed_time": "1:09:33", "remaining_time": "1:24:07", "throughput": 4630.14, "total_tokens": 19325088} {"current_steps": 19205, "total_steps": 42420, "loss": 0.0901, "lr": 3.33278133529516e-05, "epoch": 9.054691183404055, "percentage": 45.27, "elapsed_time": "1:09:34", "remaining_time": "1:24:06", "throughput": 4629.98, "total_tokens": 19328768} {"current_steps": 19210, "total_steps": 42420, "loss": 0.1215, "lr": 3.331811410758461e-05, "epoch": 9.057048561999057, "percentage": 45.29, "elapsed_time": "1:09:35", "remaining_time": "1:24:05", "throughput": 4629.99, "total_tokens": 19334144} {"current_steps": 19215, "total_steps": 42420, "loss": 0.1003, "lr": 3.330841345410214e-05, "epoch": 9.05940594059406, "percentage": 45.3, "elapsed_time": "1:09:36", "remaining_time": "1:24:04", "throughput": 4630.07, "total_tokens": 19339552} {"current_steps": 19220, "total_steps": 42420, "loss": 0.0361, "lr": 3.329871139414634e-05, "epoch": 9.061763319189062, "percentage": 45.31, "elapsed_time": "1:09:38", "remaining_time": "1:24:03", "throughput": 4630.11, "total_tokens": 19344928} {"current_steps": 19225, "total_steps": 42420, "loss": 0.1945, "lr": 3.328900792935961e-05, "epoch": 9.064120697784064, "percentage": 45.32, "elapsed_time": "1:09:39", "remaining_time": "1:24:02", "throughput": 4630.15, "total_tokens": 19349856} {"current_steps": 19230, "total_steps": 42420, "loss": 0.1124, "lr": 3.3279303061384566e-05, "epoch": 9.066478076379067, "percentage": 45.33, "elapsed_time": "1:09:40", "remaining_time": "1:24:00", "throughput": 4630.11, "total_tokens": 19354368} {"current_steps": 19235, "total_steps": 42420, "loss": 0.0614, "lr": 3.32695967918641e-05, "epoch": 9.068835454974069, "percentage": 45.34, "elapsed_time": "1:09:41", "remaining_time": "1:23:59", "throughput": 4630.2, "total_tokens": 19360096} {"current_steps": 19240, "total_steps": 42420, "loss": 0.0564, "lr": 3.32598891224413e-05, "epoch": 9.071192833569071, "percentage": 45.36, "elapsed_time": "1:09:42", "remaining_time": "1:23:58", "throughput": 4630.23, "total_tokens": 19364544} {"current_steps": 19245, "total_steps": 42420, "loss": 0.1846, "lr": 3.3250180054759515e-05, "epoch": 9.073550212164074, "percentage": 45.37, "elapsed_time": "1:09:43", "remaining_time": "1:23:57", "throughput": 4630.27, "total_tokens": 19369728} {"current_steps": 19250, "total_steps": 42420, "loss": 0.1145, "lr": 3.3240469590462334e-05, "epoch": 9.075907590759076, "percentage": 45.38, "elapsed_time": "1:09:44", "remaining_time": "1:23:56", "throughput": 4630.34, "total_tokens": 19375392} {"current_steps": 19255, "total_steps": 42420, "loss": 0.0828, "lr": 3.3230757731193564e-05, "epoch": 9.078264969354079, "percentage": 45.39, "elapsed_time": "1:09:45", "remaining_time": "1:23:55", "throughput": 4630.4, "total_tokens": 19380704} {"current_steps": 19260, "total_steps": 42420, "loss": 0.035, "lr": 3.322104447859726e-05, "epoch": 9.080622347949081, "percentage": 45.4, "elapsed_time": "1:09:46", "remaining_time": "1:23:54", "throughput": 4630.42, "total_tokens": 19384992} {"current_steps": 19265, "total_steps": 42420, "loss": 0.125, "lr": 3.3211329834317706e-05, "epoch": 9.082979726544083, "percentage": 45.41, "elapsed_time": "1:09:47", "remaining_time": "1:23:53", "throughput": 4630.46, "total_tokens": 19390112} {"current_steps": 19270, "total_steps": 42420, "loss": 0.1095, "lr": 3.320161379999943e-05, "epoch": 9.085337105139086, "percentage": 45.43, "elapsed_time": "1:09:48", "remaining_time": "1:23:51", "throughput": 4630.49, "total_tokens": 19395360} {"current_steps": 19275, "total_steps": 42420, "loss": 0.1161, "lr": 3.31918963772872e-05, "epoch": 9.087694483734088, "percentage": 45.44, "elapsed_time": "1:09:49", "remaining_time": "1:23:50", "throughput": 4630.52, "total_tokens": 19399712} {"current_steps": 19280, "total_steps": 42420, "loss": 0.1051, "lr": 3.3182177567826005e-05, "epoch": 9.09005186232909, "percentage": 45.45, "elapsed_time": "1:09:50", "remaining_time": "1:23:49", "throughput": 4630.57, "total_tokens": 19404960} {"current_steps": 19285, "total_steps": 42420, "loss": 0.1708, "lr": 3.317245737326107e-05, "epoch": 9.092409240924093, "percentage": 45.46, "elapsed_time": "1:09:51", "remaining_time": "1:23:48", "throughput": 4630.66, "total_tokens": 19410944} {"current_steps": 19290, "total_steps": 42420, "loss": 0.0444, "lr": 3.316273579523787e-05, "epoch": 9.094766619519095, "percentage": 45.47, "elapsed_time": "1:09:52", "remaining_time": "1:23:47", "throughput": 4630.71, "total_tokens": 19416480} {"current_steps": 19295, "total_steps": 42420, "loss": 0.2501, "lr": 3.315301283540208e-05, "epoch": 9.097123998114098, "percentage": 45.49, "elapsed_time": "1:09:53", "remaining_time": "1:23:46", "throughput": 4630.73, "total_tokens": 19420960} {"current_steps": 19300, "total_steps": 42420, "loss": 0.329, "lr": 3.314328849539966e-05, "epoch": 9.0994813767091, "percentage": 45.5, "elapsed_time": "1:09:55", "remaining_time": "1:23:45", "throughput": 4630.76, "total_tokens": 19426112} {"current_steps": 19305, "total_steps": 42420, "loss": 0.1617, "lr": 3.313356277687675e-05, "epoch": 9.101838755304103, "percentage": 45.51, "elapsed_time": "1:09:55", "remaining_time": "1:23:44", "throughput": 4630.77, "total_tokens": 19430592} {"current_steps": 19310, "total_steps": 42420, "loss": 0.1385, "lr": 3.3123835681479774e-05, "epoch": 9.104196133899103, "percentage": 45.52, "elapsed_time": "1:09:56", "remaining_time": "1:23:42", "throughput": 4630.8, "total_tokens": 19435168} {"current_steps": 19315, "total_steps": 42420, "loss": 0.0435, "lr": 3.311410721085534e-05, "epoch": 9.106553512494106, "percentage": 45.53, "elapsed_time": "1:09:58", "remaining_time": "1:23:41", "throughput": 4630.87, "total_tokens": 19440672} {"current_steps": 19320, "total_steps": 42420, "loss": 0.081, "lr": 3.310437736665034e-05, "epoch": 9.108910891089108, "percentage": 45.54, "elapsed_time": "1:09:58", "remaining_time": "1:23:40", "throughput": 4630.9, "total_tokens": 19444992} {"current_steps": 19325, "total_steps": 42420, "loss": 0.092, "lr": 3.309464615051185e-05, "epoch": 9.11126826968411, "percentage": 45.56, "elapsed_time": "1:10:00", "remaining_time": "1:23:39", "throughput": 4630.99, "total_tokens": 19451040} {"current_steps": 19330, "total_steps": 42420, "loss": 0.2135, "lr": 3.30849135640872e-05, "epoch": 9.113625648279113, "percentage": 45.57, "elapsed_time": "1:10:01", "remaining_time": "1:23:38", "throughput": 4631.01, "total_tokens": 19455328} {"current_steps": 19335, "total_steps": 42420, "loss": 0.0354, "lr": 3.307517960902397e-05, "epoch": 9.115983026874115, "percentage": 45.58, "elapsed_time": "1:10:02", "remaining_time": "1:23:37", "throughput": 4631.15, "total_tokens": 19462176} {"current_steps": 19340, "total_steps": 42420, "loss": 0.0327, "lr": 3.3065444286969935e-05, "epoch": 9.118340405469118, "percentage": 45.59, "elapsed_time": "1:10:03", "remaining_time": "1:23:36", "throughput": 4631.2, "total_tokens": 19467360} {"current_steps": 19345, "total_steps": 42420, "loss": 0.0959, "lr": 3.305570759957312e-05, "epoch": 9.12069778406412, "percentage": 45.6, "elapsed_time": "1:10:04", "remaining_time": "1:23:35", "throughput": 4631.3, "total_tokens": 19473376} {"current_steps": 19350, "total_steps": 42420, "loss": 0.0319, "lr": 3.304596954848179e-05, "epoch": 9.123055162659123, "percentage": 45.62, "elapsed_time": "1:10:05", "remaining_time": "1:23:34", "throughput": 4631.32, "total_tokens": 19477408} {"current_steps": 19355, "total_steps": 42420, "loss": 0.3211, "lr": 3.303623013534442e-05, "epoch": 9.125412541254125, "percentage": 45.63, "elapsed_time": "1:10:06", "remaining_time": "1:23:32", "throughput": 4631.41, "total_tokens": 19482656} {"current_steps": 19360, "total_steps": 42420, "loss": 0.2037, "lr": 3.302648936180977e-05, "epoch": 9.127769919849127, "percentage": 45.64, "elapsed_time": "1:10:07", "remaining_time": "1:23:31", "throughput": 4631.5, "total_tokens": 19488416} {"current_steps": 19365, "total_steps": 42420, "loss": 0.0531, "lr": 3.301674722952672e-05, "epoch": 9.13012729844413, "percentage": 45.65, "elapsed_time": "1:10:08", "remaining_time": "1:23:30", "throughput": 4631.57, "total_tokens": 19494144} {"current_steps": 19370, "total_steps": 42420, "loss": 0.0729, "lr": 3.300700374014448e-05, "epoch": 9.132484677039132, "percentage": 45.66, "elapsed_time": "1:10:09", "remaining_time": "1:23:29", "throughput": 4631.62, "total_tokens": 19498944} {"current_steps": 19375, "total_steps": 42420, "loss": 0.0355, "lr": 3.299725889531247e-05, "epoch": 9.134842055634135, "percentage": 45.67, "elapsed_time": "1:10:11", "remaining_time": "1:23:28", "throughput": 4631.7, "total_tokens": 19504448} {"current_steps": 19380, "total_steps": 42420, "loss": 0.0922, "lr": 3.298751269668031e-05, "epoch": 9.137199434229137, "percentage": 45.69, "elapsed_time": "1:10:12", "remaining_time": "1:23:27", "throughput": 4631.78, "total_tokens": 19510176} {"current_steps": 19385, "total_steps": 42420, "loss": 0.1096, "lr": 3.297776514589787e-05, "epoch": 9.13955681282414, "percentage": 45.7, "elapsed_time": "1:10:13", "remaining_time": "1:23:26", "throughput": 4631.82, "total_tokens": 19514688} {"current_steps": 19390, "total_steps": 42420, "loss": 0.074, "lr": 3.296801624461525e-05, "epoch": 9.141914191419142, "percentage": 45.71, "elapsed_time": "1:10:14", "remaining_time": "1:23:25", "throughput": 4631.88, "total_tokens": 19519328} {"current_steps": 19395, "total_steps": 42420, "loss": 0.0489, "lr": 3.2958265994482766e-05, "epoch": 9.144271570014144, "percentage": 45.72, "elapsed_time": "1:10:15", "remaining_time": "1:23:24", "throughput": 4631.96, "total_tokens": 19524992} {"current_steps": 19400, "total_steps": 42420, "loss": 0.0381, "lr": 3.294851439715098e-05, "epoch": 9.146628948609147, "percentage": 45.73, "elapsed_time": "1:10:16", "remaining_time": "1:23:23", "throughput": 4632.05, "total_tokens": 19530752} {"current_steps": 19405, "total_steps": 42420, "loss": 0.0952, "lr": 3.293876145427065e-05, "epoch": 9.148986327204149, "percentage": 45.74, "elapsed_time": "1:10:17", "remaining_time": "1:23:22", "throughput": 4632.12, "total_tokens": 19536704} {"current_steps": 19410, "total_steps": 42420, "loss": 0.0243, "lr": 3.292900716749281e-05, "epoch": 9.151343705799151, "percentage": 45.76, "elapsed_time": "1:10:18", "remaining_time": "1:23:20", "throughput": 4632.1, "total_tokens": 19540352} {"current_steps": 19415, "total_steps": 42420, "loss": 0.2405, "lr": 3.291925153846868e-05, "epoch": 9.153701084394154, "percentage": 45.77, "elapsed_time": "1:10:19", "remaining_time": "1:23:19", "throughput": 4632.11, "total_tokens": 19544640} {"current_steps": 19420, "total_steps": 42420, "loss": 0.1397, "lr": 3.290949456884973e-05, "epoch": 9.156058462989156, "percentage": 45.78, "elapsed_time": "1:10:20", "remaining_time": "1:23:18", "throughput": 4632.12, "total_tokens": 19549216} {"current_steps": 19425, "total_steps": 42420, "loss": 0.1709, "lr": 3.289973626028763e-05, "epoch": 9.158415841584159, "percentage": 45.79, "elapsed_time": "1:10:21", "remaining_time": "1:23:17", "throughput": 4632.12, "total_tokens": 19553408} {"current_steps": 19430, "total_steps": 42420, "loss": 0.2005, "lr": 3.2889976614434325e-05, "epoch": 9.160773220179161, "percentage": 45.8, "elapsed_time": "1:10:22", "remaining_time": "1:23:15", "throughput": 4632.2, "total_tokens": 19558752} {"current_steps": 19435, "total_steps": 42420, "loss": 0.2622, "lr": 3.288021563294193e-05, "epoch": 9.163130598774163, "percentage": 45.82, "elapsed_time": "1:10:23", "remaining_time": "1:23:14", "throughput": 4632.25, "total_tokens": 19563840} {"current_steps": 19440, "total_steps": 42420, "loss": 0.2158, "lr": 3.287045331746285e-05, "epoch": 9.165487977369166, "percentage": 45.83, "elapsed_time": "1:10:24", "remaining_time": "1:23:13", "throughput": 4632.28, "total_tokens": 19568576} {"current_steps": 19445, "total_steps": 42420, "loss": 0.175, "lr": 3.286068966964964e-05, "epoch": 9.167845355964168, "percentage": 45.84, "elapsed_time": "1:10:25", "remaining_time": "1:23:12", "throughput": 4632.31, "total_tokens": 19573504} {"current_steps": 19450, "total_steps": 42420, "loss": 0.1807, "lr": 3.285092469115514e-05, "epoch": 9.17020273455917, "percentage": 45.85, "elapsed_time": "1:10:26", "remaining_time": "1:23:11", "throughput": 4632.34, "total_tokens": 19578176} {"current_steps": 19455, "total_steps": 42420, "loss": 0.1412, "lr": 3.284115838363239e-05, "epoch": 9.172560113154173, "percentage": 45.86, "elapsed_time": "1:10:27", "remaining_time": "1:23:09", "throughput": 4632.38, "total_tokens": 19582432} {"current_steps": 19460, "total_steps": 42420, "loss": 0.1362, "lr": 3.2831390748734657e-05, "epoch": 9.174917491749175, "percentage": 45.87, "elapsed_time": "1:10:28", "remaining_time": "1:23:08", "throughput": 4632.46, "total_tokens": 19587936} {"current_steps": 19465, "total_steps": 42420, "loss": 0.2161, "lr": 3.2821621788115445e-05, "epoch": 9.177274870344178, "percentage": 45.89, "elapsed_time": "1:10:29", "remaining_time": "1:23:07", "throughput": 4632.52, "total_tokens": 19592704} {"current_steps": 19470, "total_steps": 42420, "loss": 0.2406, "lr": 3.281185150342846e-05, "epoch": 9.17963224893918, "percentage": 45.9, "elapsed_time": "1:10:30", "remaining_time": "1:23:06", "throughput": 4632.57, "total_tokens": 19597440} {"current_steps": 19475, "total_steps": 42420, "loss": 0.2278, "lr": 3.280207989632767e-05, "epoch": 9.181989627534183, "percentage": 45.91, "elapsed_time": "1:10:31", "remaining_time": "1:23:05", "throughput": 4632.62, "total_tokens": 19603488} {"current_steps": 19480, "total_steps": 42420, "loss": 0.1422, "lr": 3.2792306968467207e-05, "epoch": 9.184347006129185, "percentage": 45.92, "elapsed_time": "1:10:32", "remaining_time": "1:23:04", "throughput": 4632.69, "total_tokens": 19609088} {"current_steps": 19485, "total_steps": 42420, "loss": 0.0462, "lr": 3.278253272150149e-05, "epoch": 9.186704384724187, "percentage": 45.93, "elapsed_time": "1:10:33", "remaining_time": "1:23:03", "throughput": 4632.73, "total_tokens": 19613856} {"current_steps": 19490, "total_steps": 42420, "loss": 0.102, "lr": 3.277275715708512e-05, "epoch": 9.18906176331919, "percentage": 45.95, "elapsed_time": "1:10:34", "remaining_time": "1:23:02", "throughput": 4632.83, "total_tokens": 19619648} {"current_steps": 19495, "total_steps": 42420, "loss": 0.0789, "lr": 3.2762980276872936e-05, "epoch": 9.191419141914192, "percentage": 45.96, "elapsed_time": "1:10:35", "remaining_time": "1:23:01", "throughput": 4632.86, "total_tokens": 19624320} {"current_steps": 19500, "total_steps": 42420, "loss": 0.0431, "lr": 3.275320208252e-05, "epoch": 9.193776520509195, "percentage": 45.97, "elapsed_time": "1:10:36", "remaining_time": "1:22:59", "throughput": 4632.9, "total_tokens": 19628832} {"current_steps": 19505, "total_steps": 42420, "loss": 0.0907, "lr": 3.27434225756816e-05, "epoch": 9.196133899104197, "percentage": 45.98, "elapsed_time": "1:10:37", "remaining_time": "1:22:58", "throughput": 4632.98, "total_tokens": 19634464} {"current_steps": 19510, "total_steps": 42420, "loss": 0.0229, "lr": 3.273364175801322e-05, "epoch": 9.198491277699198, "percentage": 45.99, "elapsed_time": "1:10:39", "remaining_time": "1:22:57", "throughput": 4633.06, "total_tokens": 19640384} {"current_steps": 19515, "total_steps": 42420, "loss": 0.041, "lr": 3.2723859631170614e-05, "epoch": 9.2008486562942, "percentage": 46.0, "elapsed_time": "1:10:40", "remaining_time": "1:22:56", "throughput": 4633.08, "total_tokens": 19644864} {"current_steps": 19520, "total_steps": 42420, "loss": 0.1109, "lr": 3.2714076196809705e-05, "epoch": 9.203206034889202, "percentage": 46.02, "elapsed_time": "1:10:41", "remaining_time": "1:22:55", "throughput": 4633.16, "total_tokens": 19650784} {"current_steps": 19525, "total_steps": 42420, "loss": 0.05, "lr": 3.2704291456586686e-05, "epoch": 9.205563413484205, "percentage": 46.03, "elapsed_time": "1:10:42", "remaining_time": "1:22:54", "throughput": 4633.24, "total_tokens": 19656032} {"current_steps": 19530, "total_steps": 42420, "loss": 0.0723, "lr": 3.269450541215792e-05, "epoch": 9.207920792079207, "percentage": 46.04, "elapsed_time": "1:10:43", "remaining_time": "1:22:53", "throughput": 4633.3, "total_tokens": 19661120} {"current_steps": 19535, "total_steps": 42420, "loss": 0.0669, "lr": 3.2684718065180044e-05, "epoch": 9.21027817067421, "percentage": 46.05, "elapsed_time": "1:10:44", "remaining_time": "1:22:52", "throughput": 4633.36, "total_tokens": 19665792} {"current_steps": 19540, "total_steps": 42420, "loss": 0.0779, "lr": 3.267492941730988e-05, "epoch": 9.212635549269212, "percentage": 46.06, "elapsed_time": "1:10:45", "remaining_time": "1:22:51", "throughput": 4633.46, "total_tokens": 19671712} {"current_steps": 19545, "total_steps": 42420, "loss": 0.1058, "lr": 3.266513947020447e-05, "epoch": 9.214992927864214, "percentage": 46.07, "elapsed_time": "1:10:46", "remaining_time": "1:22:50", "throughput": 4633.53, "total_tokens": 19677120} {"current_steps": 19550, "total_steps": 42420, "loss": 0.1505, "lr": 3.2655348225521096e-05, "epoch": 9.217350306459217, "percentage": 46.09, "elapsed_time": "1:10:47", "remaining_time": "1:22:49", "throughput": 4633.59, "total_tokens": 19682112} {"current_steps": 19555, "total_steps": 42420, "loss": 0.1224, "lr": 3.2645555684917246e-05, "epoch": 9.21970768505422, "percentage": 46.1, "elapsed_time": "1:10:48", "remaining_time": "1:22:48", "throughput": 4633.7, "total_tokens": 19688288} {"current_steps": 19560, "total_steps": 42420, "loss": 0.1248, "lr": 3.263576185005063e-05, "epoch": 9.222065063649222, "percentage": 46.11, "elapsed_time": "1:10:49", "remaining_time": "1:22:46", "throughput": 4633.75, "total_tokens": 19693216} {"current_steps": 19565, "total_steps": 42420, "loss": 0.0444, "lr": 3.262596672257919e-05, "epoch": 9.224422442244224, "percentage": 46.12, "elapsed_time": "1:10:50", "remaining_time": "1:22:45", "throughput": 4633.76, "total_tokens": 19697504} {"current_steps": 19570, "total_steps": 42420, "loss": 0.0973, "lr": 3.261617030416107e-05, "epoch": 9.226779820839226, "percentage": 46.13, "elapsed_time": "1:10:51", "remaining_time": "1:22:44", "throughput": 4633.81, "total_tokens": 19702560} {"current_steps": 19575, "total_steps": 42420, "loss": 0.0192, "lr": 3.260637259645462e-05, "epoch": 9.229137199434229, "percentage": 46.15, "elapsed_time": "1:10:52", "remaining_time": "1:22:43", "throughput": 4633.79, "total_tokens": 19706304} {"current_steps": 19580, "total_steps": 42420, "loss": 0.1414, "lr": 3.2596573601118444e-05, "epoch": 9.231494578029231, "percentage": 46.16, "elapsed_time": "1:10:54", "remaining_time": "1:22:42", "throughput": 4633.91, "total_tokens": 19713216} {"current_steps": 19585, "total_steps": 42420, "loss": 0.1357, "lr": 3.258677331981134e-05, "epoch": 9.233851956624234, "percentage": 46.17, "elapsed_time": "1:10:55", "remaining_time": "1:22:41", "throughput": 4634.0, "total_tokens": 19718592} {"current_steps": 19590, "total_steps": 42420, "loss": 0.3251, "lr": 3.257697175419233e-05, "epoch": 9.236209335219236, "percentage": 46.18, "elapsed_time": "1:10:56", "remaining_time": "1:22:40", "throughput": 4634.08, "total_tokens": 19725472} {"current_steps": 19595, "total_steps": 42420, "loss": 0.071, "lr": 3.256716890592065e-05, "epoch": 9.238566713814238, "percentage": 46.19, "elapsed_time": "1:10:57", "remaining_time": "1:22:39", "throughput": 4633.99, "total_tokens": 19729056} {"current_steps": 19600, "total_steps": 42420, "loss": 0.083, "lr": 3.255736477665576e-05, "epoch": 9.24092409240924, "percentage": 46.2, "elapsed_time": "1:10:58", "remaining_time": "1:22:38", "throughput": 4634.08, "total_tokens": 19734816} {"current_steps": 19605, "total_steps": 42420, "loss": 0.2715, "lr": 3.2547559368057325e-05, "epoch": 9.243281471004243, "percentage": 46.22, "elapsed_time": "1:10:59", "remaining_time": "1:22:37", "throughput": 4634.14, "total_tokens": 19739584} {"current_steps": 19610, "total_steps": 42420, "loss": 0.0609, "lr": 3.253775268178524e-05, "epoch": 9.245638849599246, "percentage": 46.23, "elapsed_time": "1:11:00", "remaining_time": "1:22:35", "throughput": 4634.2, "total_tokens": 19744416} {"current_steps": 19615, "total_steps": 42420, "loss": 0.1477, "lr": 3.252794471949961e-05, "epoch": 9.247996228194248, "percentage": 46.24, "elapsed_time": "1:11:01", "remaining_time": "1:22:34", "throughput": 4634.24, "total_tokens": 19749184} {"current_steps": 19620, "total_steps": 42420, "loss": 0.1388, "lr": 3.251813548286076e-05, "epoch": 9.25035360678925, "percentage": 46.25, "elapsed_time": "1:11:02", "remaining_time": "1:22:33", "throughput": 4634.26, "total_tokens": 19753888} {"current_steps": 19625, "total_steps": 42420, "loss": 0.2659, "lr": 3.250832497352922e-05, "epoch": 9.252710985384253, "percentage": 46.26, "elapsed_time": "1:11:03", "remaining_time": "1:22:32", "throughput": 4634.24, "total_tokens": 19758368} {"current_steps": 19630, "total_steps": 42420, "loss": 0.1459, "lr": 3.249851319316575e-05, "epoch": 9.255068363979255, "percentage": 46.28, "elapsed_time": "1:11:04", "remaining_time": "1:22:30", "throughput": 4634.23, "total_tokens": 19762432} {"current_steps": 19635, "total_steps": 42420, "loss": 0.0538, "lr": 3.2488700143431314e-05, "epoch": 9.257425742574258, "percentage": 46.29, "elapsed_time": "1:11:05", "remaining_time": "1:22:29", "throughput": 4634.26, "total_tokens": 19766784} {"current_steps": 19640, "total_steps": 42420, "loss": 0.0824, "lr": 3.247888582598709e-05, "epoch": 9.25978312116926, "percentage": 46.3, "elapsed_time": "1:11:06", "remaining_time": "1:22:28", "throughput": 4634.29, "total_tokens": 19771264} {"current_steps": 19645, "total_steps": 42420, "loss": 0.2229, "lr": 3.2469070242494476e-05, "epoch": 9.262140499764262, "percentage": 46.31, "elapsed_time": "1:11:07", "remaining_time": "1:22:27", "throughput": 4634.35, "total_tokens": 19776320} {"current_steps": 19650, "total_steps": 42420, "loss": 0.2367, "lr": 3.2459253394615094e-05, "epoch": 9.264497878359265, "percentage": 46.32, "elapsed_time": "1:11:08", "remaining_time": "1:22:26", "throughput": 4634.41, "total_tokens": 19781696} {"current_steps": 19655, "total_steps": 42420, "loss": 0.0838, "lr": 3.244943528401077e-05, "epoch": 9.266855256954267, "percentage": 46.33, "elapsed_time": "1:11:09", "remaining_time": "1:22:24", "throughput": 4634.47, "total_tokens": 19786400} {"current_steps": 19660, "total_steps": 42420, "loss": 0.1309, "lr": 3.2439615912343526e-05, "epoch": 9.26921263554927, "percentage": 46.35, "elapsed_time": "1:11:10", "remaining_time": "1:22:23", "throughput": 4634.52, "total_tokens": 19791072} {"current_steps": 19665, "total_steps": 42420, "loss": 0.0628, "lr": 3.242979528127562e-05, "epoch": 9.271570014144272, "percentage": 46.36, "elapsed_time": "1:11:11", "remaining_time": "1:22:22", "throughput": 4634.53, "total_tokens": 19796032} {"current_steps": 19670, "total_steps": 42420, "loss": 0.0525, "lr": 3.2419973392469535e-05, "epoch": 9.273927392739274, "percentage": 46.37, "elapsed_time": "1:11:12", "remaining_time": "1:22:21", "throughput": 4634.6, "total_tokens": 19801024} {"current_steps": 19675, "total_steps": 42420, "loss": 0.1603, "lr": 3.241015024758794e-05, "epoch": 9.276284771334277, "percentage": 46.38, "elapsed_time": "1:11:13", "remaining_time": "1:22:20", "throughput": 4634.63, "total_tokens": 19805696} {"current_steps": 19680, "total_steps": 42420, "loss": 0.0715, "lr": 3.2400325848293716e-05, "epoch": 9.27864214992928, "percentage": 46.39, "elapsed_time": "1:11:14", "remaining_time": "1:22:18", "throughput": 4634.66, "total_tokens": 19810144} {"current_steps": 19685, "total_steps": 42420, "loss": 0.0319, "lr": 3.2390500196249986e-05, "epoch": 9.280999528524282, "percentage": 46.4, "elapsed_time": "1:11:15", "remaining_time": "1:22:17", "throughput": 4634.72, "total_tokens": 19814848} {"current_steps": 19690, "total_steps": 42420, "loss": 0.0584, "lr": 3.2380673293120054e-05, "epoch": 9.283356907119284, "percentage": 46.42, "elapsed_time": "1:11:16", "remaining_time": "1:22:16", "throughput": 4634.79, "total_tokens": 19820384} {"current_steps": 19695, "total_steps": 42420, "loss": 0.1157, "lr": 3.2370845140567443e-05, "epoch": 9.285714285714286, "percentage": 46.43, "elapsed_time": "1:11:17", "remaining_time": "1:22:15", "throughput": 4634.83, "total_tokens": 19824960} {"current_steps": 19700, "total_steps": 42420, "loss": 0.2238, "lr": 3.2361015740255905e-05, "epoch": 9.288071664309289, "percentage": 46.44, "elapsed_time": "1:11:18", "remaining_time": "1:22:14", "throughput": 4634.9, "total_tokens": 19830720} {"current_steps": 19705, "total_steps": 42420, "loss": 0.125, "lr": 3.235118509384939e-05, "epoch": 9.290429042904291, "percentage": 46.45, "elapsed_time": "1:11:19", "remaining_time": "1:22:13", "throughput": 4634.98, "total_tokens": 19836480} {"current_steps": 19710, "total_steps": 42420, "loss": 0.085, "lr": 3.2341353203012045e-05, "epoch": 9.292786421499294, "percentage": 46.46, "elapsed_time": "1:11:20", "remaining_time": "1:22:12", "throughput": 4635.04, "total_tokens": 19841184} {"current_steps": 19715, "total_steps": 42420, "loss": 0.1747, "lr": 3.233152006940826e-05, "epoch": 9.295143800094294, "percentage": 46.48, "elapsed_time": "1:11:21", "remaining_time": "1:22:11", "throughput": 4635.08, "total_tokens": 19845984} {"current_steps": 19720, "total_steps": 42420, "loss": 0.2419, "lr": 3.23216856947026e-05, "epoch": 9.297501178689297, "percentage": 46.49, "elapsed_time": "1:11:22", "remaining_time": "1:22:09", "throughput": 4635.1, "total_tokens": 19850304} {"current_steps": 19725, "total_steps": 42420, "loss": 0.2432, "lr": 3.2311850080559875e-05, "epoch": 9.299858557284299, "percentage": 46.5, "elapsed_time": "1:11:23", "remaining_time": "1:22:08", "throughput": 4635.16, "total_tokens": 19855552} {"current_steps": 19730, "total_steps": 42420, "loss": 0.2157, "lr": 3.230201322864507e-05, "epoch": 9.302215935879302, "percentage": 46.51, "elapsed_time": "1:11:25", "remaining_time": "1:22:07", "throughput": 4635.21, "total_tokens": 19862176} {"current_steps": 19735, "total_steps": 42420, "loss": 0.0555, "lr": 3.229217514062342e-05, "epoch": 9.304573314474304, "percentage": 46.52, "elapsed_time": "1:11:26", "remaining_time": "1:22:06", "throughput": 4635.21, "total_tokens": 19867008} {"current_steps": 19740, "total_steps": 42420, "loss": 0.1923, "lr": 3.228233581816033e-05, "epoch": 9.306930693069306, "percentage": 46.53, "elapsed_time": "1:11:27", "remaining_time": "1:22:05", "throughput": 4635.29, "total_tokens": 19872640} {"current_steps": 19745, "total_steps": 42420, "loss": 0.2343, "lr": 3.227249526292142e-05, "epoch": 9.309288071664309, "percentage": 46.55, "elapsed_time": "1:11:28", "remaining_time": "1:22:04", "throughput": 4635.39, "total_tokens": 19878656} {"current_steps": 19750, "total_steps": 42420, "loss": 0.093, "lr": 3.2262653476572554e-05, "epoch": 9.311645450259311, "percentage": 46.56, "elapsed_time": "1:11:29", "remaining_time": "1:22:03", "throughput": 4635.38, "total_tokens": 19882624} {"current_steps": 19755, "total_steps": 42420, "loss": 0.2056, "lr": 3.225281046077976e-05, "epoch": 9.314002828854314, "percentage": 46.57, "elapsed_time": "1:11:30", "remaining_time": "1:22:02", "throughput": 4635.46, "total_tokens": 19888096} {"current_steps": 19760, "total_steps": 42420, "loss": 0.0617, "lr": 3.224296621720931e-05, "epoch": 9.316360207449316, "percentage": 46.58, "elapsed_time": "1:11:31", "remaining_time": "1:22:01", "throughput": 4635.47, "total_tokens": 19892480} {"current_steps": 19765, "total_steps": 42420, "loss": 0.1072, "lr": 3.223312074752765e-05, "epoch": 9.318717586044318, "percentage": 46.59, "elapsed_time": "1:11:32", "remaining_time": "1:22:00", "throughput": 4635.55, "total_tokens": 19898272} {"current_steps": 19770, "total_steps": 42420, "loss": 0.1086, "lr": 3.2223274053401466e-05, "epoch": 9.32107496463932, "percentage": 46.61, "elapsed_time": "1:11:33", "remaining_time": "1:21:59", "throughput": 4635.6, "total_tokens": 19903168} {"current_steps": 19775, "total_steps": 42420, "loss": 0.2417, "lr": 3.221342613649763e-05, "epoch": 9.323432343234323, "percentage": 46.62, "elapsed_time": "1:11:34", "remaining_time": "1:21:57", "throughput": 4635.66, "total_tokens": 19908032} {"current_steps": 19780, "total_steps": 42420, "loss": 0.1627, "lr": 3.2203576998483216e-05, "epoch": 9.325789721829326, "percentage": 46.63, "elapsed_time": "1:11:35", "remaining_time": "1:21:56", "throughput": 4635.67, "total_tokens": 19912160} {"current_steps": 19785, "total_steps": 42420, "loss": 0.1085, "lr": 3.219372664102552e-05, "epoch": 9.328147100424328, "percentage": 46.64, "elapsed_time": "1:11:36", "remaining_time": "1:21:55", "throughput": 4635.7, "total_tokens": 19916640} {"current_steps": 19790, "total_steps": 42420, "loss": 0.1413, "lr": 3.2183875065792065e-05, "epoch": 9.33050447901933, "percentage": 46.65, "elapsed_time": "1:11:37", "remaining_time": "1:21:54", "throughput": 4635.74, "total_tokens": 19921824} {"current_steps": 19795, "total_steps": 42420, "loss": 0.0806, "lr": 3.2174022274450534e-05, "epoch": 9.332861857614333, "percentage": 46.66, "elapsed_time": "1:11:38", "remaining_time": "1:21:53", "throughput": 4635.79, "total_tokens": 19927104} {"current_steps": 19800, "total_steps": 42420, "loss": 0.1001, "lr": 3.216416826866883e-05, "epoch": 9.335219236209335, "percentage": 46.68, "elapsed_time": "1:11:39", "remaining_time": "1:21:52", "throughput": 4635.86, "total_tokens": 19932800} {"current_steps": 19805, "total_steps": 42420, "loss": 0.1531, "lr": 3.2154313050115084e-05, "epoch": 9.337576614804338, "percentage": 46.69, "elapsed_time": "1:11:40", "remaining_time": "1:21:50", "throughput": 4635.9, "total_tokens": 19937696} {"current_steps": 19810, "total_steps": 42420, "loss": 0.1684, "lr": 3.214445662045761e-05, "epoch": 9.33993399339934, "percentage": 46.7, "elapsed_time": "1:11:41", "remaining_time": "1:21:49", "throughput": 4635.87, "total_tokens": 19941472} {"current_steps": 19815, "total_steps": 42420, "loss": 0.0946, "lr": 3.2134598981364936e-05, "epoch": 9.342291371994342, "percentage": 46.71, "elapsed_time": "1:11:42", "remaining_time": "1:21:48", "throughput": 4635.89, "total_tokens": 19946336} {"current_steps": 19820, "total_steps": 42420, "loss": 0.1554, "lr": 3.21247401345058e-05, "epoch": 9.344648750589345, "percentage": 46.72, "elapsed_time": "1:11:43", "remaining_time": "1:21:47", "throughput": 4635.93, "total_tokens": 19951584} {"current_steps": 19825, "total_steps": 42420, "loss": 0.0778, "lr": 3.2114880081549125e-05, "epoch": 9.347006129184347, "percentage": 46.74, "elapsed_time": "1:11:44", "remaining_time": "1:21:46", "throughput": 4635.98, "total_tokens": 19956192} {"current_steps": 19830, "total_steps": 42420, "loss": 0.0936, "lr": 3.2105018824164055e-05, "epoch": 9.34936350777935, "percentage": 46.75, "elapsed_time": "1:11:45", "remaining_time": "1:21:44", "throughput": 4636.04, "total_tokens": 19961472} {"current_steps": 19835, "total_steps": 42420, "loss": 0.2639, "lr": 3.209515636401993e-05, "epoch": 9.351720886374352, "percentage": 46.76, "elapsed_time": "1:11:46", "remaining_time": "1:21:43", "throughput": 4636.1, "total_tokens": 19966016} {"current_steps": 19840, "total_steps": 42420, "loss": 0.1984, "lr": 3.2085292702786313e-05, "epoch": 9.354078264969354, "percentage": 46.77, "elapsed_time": "1:11:47", "remaining_time": "1:21:42", "throughput": 4635.84, "total_tokens": 19970560} {"current_steps": 19845, "total_steps": 42420, "loss": 0.1441, "lr": 3.207542784213293e-05, "epoch": 9.356435643564357, "percentage": 46.78, "elapsed_time": "1:11:48", "remaining_time": "1:21:41", "throughput": 4635.84, "total_tokens": 19974592} {"current_steps": 19850, "total_steps": 42420, "loss": 0.193, "lr": 3.206556178372976e-05, "epoch": 9.35879302215936, "percentage": 46.79, "elapsed_time": "1:11:49", "remaining_time": "1:21:40", "throughput": 4635.91, "total_tokens": 19979712} {"current_steps": 19855, "total_steps": 42420, "loss": 0.2008, "lr": 3.205569452924693e-05, "epoch": 9.361150400754362, "percentage": 46.81, "elapsed_time": "1:11:50", "remaining_time": "1:21:39", "throughput": 4635.95, "total_tokens": 19984416} {"current_steps": 19860, "total_steps": 42420, "loss": 0.1592, "lr": 3.204582608035483e-05, "epoch": 9.363507779349364, "percentage": 46.82, "elapsed_time": "1:11:51", "remaining_time": "1:21:37", "throughput": 4635.97, "total_tokens": 19988576} {"current_steps": 19865, "total_steps": 42420, "loss": 0.0446, "lr": 3.2035956438724004e-05, "epoch": 9.365865157944366, "percentage": 46.83, "elapsed_time": "1:11:52", "remaining_time": "1:21:36", "throughput": 4636.04, "total_tokens": 19993696} {"current_steps": 19870, "total_steps": 42420, "loss": 0.0288, "lr": 3.202608560602521e-05, "epoch": 9.368222536539369, "percentage": 46.84, "elapsed_time": "1:11:53", "remaining_time": "1:21:35", "throughput": 4636.16, "total_tokens": 19999872} {"current_steps": 19875, "total_steps": 42420, "loss": 0.1252, "lr": 3.201621358392942e-05, "epoch": 9.370579915134371, "percentage": 46.85, "elapsed_time": "1:11:54", "remaining_time": "1:21:34", "throughput": 4636.22, "total_tokens": 20004896} {"current_steps": 19880, "total_steps": 42420, "loss": 0.0631, "lr": 3.200634037410781e-05, "epoch": 9.372937293729374, "percentage": 46.86, "elapsed_time": "1:11:55", "remaining_time": "1:21:33", "throughput": 4636.26, "total_tokens": 20009088} {"current_steps": 19885, "total_steps": 42420, "loss": 0.2882, "lr": 3.1996465978231726e-05, "epoch": 9.375294672324376, "percentage": 46.88, "elapsed_time": "1:11:56", "remaining_time": "1:21:32", "throughput": 4636.32, "total_tokens": 20013856} {"current_steps": 19890, "total_steps": 42420, "loss": 0.0885, "lr": 3.198659039797274e-05, "epoch": 9.377652050919378, "percentage": 46.89, "elapsed_time": "1:11:57", "remaining_time": "1:21:30", "throughput": 4636.3, "total_tokens": 20018400} {"current_steps": 19895, "total_steps": 42420, "loss": 0.1097, "lr": 3.1976713635002634e-05, "epoch": 9.38000942951438, "percentage": 46.9, "elapsed_time": "1:11:58", "remaining_time": "1:21:29", "throughput": 4636.36, "total_tokens": 20023264} {"current_steps": 19900, "total_steps": 42420, "loss": 0.0321, "lr": 3.196683569099337e-05, "epoch": 9.382366808109383, "percentage": 46.91, "elapsed_time": "1:12:00", "remaining_time": "1:21:28", "throughput": 4636.44, "total_tokens": 20029696} {"current_steps": 19905, "total_steps": 42420, "loss": 0.1352, "lr": 3.1956956567617106e-05, "epoch": 9.384724186704386, "percentage": 46.92, "elapsed_time": "1:12:00", "remaining_time": "1:21:27", "throughput": 4636.46, "total_tokens": 20033952} {"current_steps": 19910, "total_steps": 42420, "loss": 0.1029, "lr": 3.194707626654622e-05, "epoch": 9.387081565299386, "percentage": 46.94, "elapsed_time": "1:12:02", "remaining_time": "1:21:26", "throughput": 4636.5, "total_tokens": 20039104} {"current_steps": 19915, "total_steps": 42420, "loss": 0.132, "lr": 3.1937194789453274e-05, "epoch": 9.389438943894389, "percentage": 46.95, "elapsed_time": "1:12:02", "remaining_time": "1:21:25", "throughput": 4636.52, "total_tokens": 20043296} {"current_steps": 19920, "total_steps": 42420, "loss": 0.1738, "lr": 3.1927312138011043e-05, "epoch": 9.391796322489391, "percentage": 46.96, "elapsed_time": "1:12:03", "remaining_time": "1:21:23", "throughput": 4636.55, "total_tokens": 20048128} {"current_steps": 19925, "total_steps": 42420, "loss": 0.1569, "lr": 3.1917428313892484e-05, "epoch": 9.394153701084393, "percentage": 46.97, "elapsed_time": "1:12:05", "remaining_time": "1:21:22", "throughput": 4636.64, "total_tokens": 20053664} {"current_steps": 19930, "total_steps": 42420, "loss": 0.1544, "lr": 3.190754331877076e-05, "epoch": 9.396511079679396, "percentage": 46.98, "elapsed_time": "1:12:06", "remaining_time": "1:21:22", "throughput": 4636.73, "total_tokens": 20060064} {"current_steps": 19935, "total_steps": 42420, "loss": 0.0682, "lr": 3.189765715431924e-05, "epoch": 9.398868458274398, "percentage": 46.99, "elapsed_time": "1:12:07", "remaining_time": "1:21:20", "throughput": 4636.77, "total_tokens": 20064800} {"current_steps": 19940, "total_steps": 42420, "loss": 0.1742, "lr": 3.188776982221147e-05, "epoch": 9.4012258368694, "percentage": 47.01, "elapsed_time": "1:12:08", "remaining_time": "1:21:19", "throughput": 4636.85, "total_tokens": 20070496} {"current_steps": 19945, "total_steps": 42420, "loss": 0.059, "lr": 3.1877881324121226e-05, "epoch": 9.403583215464403, "percentage": 47.02, "elapsed_time": "1:12:09", "remaining_time": "1:21:18", "throughput": 4636.92, "total_tokens": 20075840} {"current_steps": 19950, "total_steps": 42420, "loss": 0.1739, "lr": 3.186799166172245e-05, "epoch": 9.405940594059405, "percentage": 47.03, "elapsed_time": "1:12:10", "remaining_time": "1:21:18", "throughput": 4637.01, "total_tokens": 20082816} {"current_steps": 19955, "total_steps": 42420, "loss": 0.1067, "lr": 3.18581008366893e-05, "epoch": 9.408297972654408, "percentage": 47.04, "elapsed_time": "1:12:12", "remaining_time": "1:21:16", "throughput": 4637.05, "total_tokens": 20087712} {"current_steps": 19960, "total_steps": 42420, "loss": 0.1164, "lr": 3.184820885069612e-05, "epoch": 9.41065535124941, "percentage": 47.05, "elapsed_time": "1:12:12", "remaining_time": "1:21:15", "throughput": 4637.08, "total_tokens": 20092256} {"current_steps": 19965, "total_steps": 42420, "loss": 0.0614, "lr": 3.183831570541746e-05, "epoch": 9.413012729844413, "percentage": 47.07, "elapsed_time": "1:12:14", "remaining_time": "1:21:14", "throughput": 4637.14, "total_tokens": 20097408} {"current_steps": 19970, "total_steps": 42420, "loss": 0.2195, "lr": 3.182842140252806e-05, "epoch": 9.415370108439415, "percentage": 47.08, "elapsed_time": "1:12:14", "remaining_time": "1:21:13", "throughput": 4637.16, "total_tokens": 20102048} {"current_steps": 19975, "total_steps": 42420, "loss": 0.0828, "lr": 3.181852594370285e-05, "epoch": 9.417727487034417, "percentage": 47.09, "elapsed_time": "1:12:16", "remaining_time": "1:21:12", "throughput": 4637.19, "total_tokens": 20107200} {"current_steps": 19980, "total_steps": 42420, "loss": 0.1436, "lr": 3.1808629330616975e-05, "epoch": 9.42008486562942, "percentage": 47.1, "elapsed_time": "1:12:16", "remaining_time": "1:21:10", "throughput": 4637.17, "total_tokens": 20111392} {"current_steps": 19985, "total_steps": 42420, "loss": 0.1003, "lr": 3.1798731564945764e-05, "epoch": 9.422442244224422, "percentage": 47.11, "elapsed_time": "1:12:17", "remaining_time": "1:21:09", "throughput": 4637.22, "total_tokens": 20116000} {"current_steps": 19990, "total_steps": 42420, "loss": 0.0256, "lr": 3.178883264836472e-05, "epoch": 9.424799622819425, "percentage": 47.12, "elapsed_time": "1:12:19", "remaining_time": "1:21:08", "throughput": 4637.29, "total_tokens": 20122432} {"current_steps": 19995, "total_steps": 42420, "loss": 0.1223, "lr": 3.177893258254958e-05, "epoch": 9.427157001414427, "percentage": 47.14, "elapsed_time": "1:12:20", "remaining_time": "1:21:07", "throughput": 4637.28, "total_tokens": 20126432} {"current_steps": 20000, "total_steps": 42420, "loss": 0.2625, "lr": 3.176903136917626e-05, "epoch": 9.42951438000943, "percentage": 47.15, "elapsed_time": "1:12:21", "remaining_time": "1:21:06", "throughput": 4637.34, "total_tokens": 20131648} {"current_steps": 20005, "total_steps": 42420, "loss": 0.208, "lr": 3.175912900992086e-05, "epoch": 9.431871758604432, "percentage": 47.16, "elapsed_time": "1:12:22", "remaining_time": "1:21:05", "throughput": 4637.35, "total_tokens": 20135968} {"current_steps": 20010, "total_steps": 42420, "loss": 0.2599, "lr": 3.174922550645968e-05, "epoch": 9.434229137199434, "percentage": 47.17, "elapsed_time": "1:12:23", "remaining_time": "1:21:04", "throughput": 4637.38, "total_tokens": 20140896} {"current_steps": 20015, "total_steps": 42420, "loss": 0.0745, "lr": 3.173932086046922e-05, "epoch": 9.436586515794437, "percentage": 47.18, "elapsed_time": "1:12:24", "remaining_time": "1:21:02", "throughput": 4637.44, "total_tokens": 20145952} {"current_steps": 20020, "total_steps": 42420, "loss": 0.0934, "lr": 3.172941507362616e-05, "epoch": 9.438943894389439, "percentage": 47.19, "elapsed_time": "1:12:25", "remaining_time": "1:21:01", "throughput": 4637.5, "total_tokens": 20151712} {"current_steps": 20025, "total_steps": 42420, "loss": 0.0553, "lr": 3.171950814760739e-05, "epoch": 9.441301272984441, "percentage": 47.21, "elapsed_time": "1:12:26", "remaining_time": "1:21:00", "throughput": 4637.5, "total_tokens": 20156320} {"current_steps": 20030, "total_steps": 42420, "loss": 0.155, "lr": 3.170960008408999e-05, "epoch": 9.443658651579444, "percentage": 47.22, "elapsed_time": "1:12:27", "remaining_time": "1:20:59", "throughput": 4637.57, "total_tokens": 20161408} {"current_steps": 20035, "total_steps": 42420, "loss": 0.1055, "lr": 3.1699690884751206e-05, "epoch": 9.446016030174446, "percentage": 47.23, "elapsed_time": "1:12:28", "remaining_time": "1:20:58", "throughput": 4637.63, "total_tokens": 20166976} {"current_steps": 20040, "total_steps": 42420, "loss": 0.0226, "lr": 3.168978055126851e-05, "epoch": 9.448373408769449, "percentage": 47.24, "elapsed_time": "1:12:29", "remaining_time": "1:20:57", "throughput": 4637.63, "total_tokens": 20171328} {"current_steps": 20045, "total_steps": 42420, "loss": 0.0712, "lr": 3.167986908531956e-05, "epoch": 9.450730787364451, "percentage": 47.25, "elapsed_time": "1:12:30", "remaining_time": "1:20:56", "throughput": 4637.68, "total_tokens": 20176256} {"current_steps": 20050, "total_steps": 42420, "loss": 0.062, "lr": 3.166995648858218e-05, "epoch": 9.453088165959453, "percentage": 47.27, "elapsed_time": "1:12:31", "remaining_time": "1:20:55", "throughput": 4637.77, "total_tokens": 20182080} {"current_steps": 20055, "total_steps": 42420, "loss": 0.0425, "lr": 3.166004276273443e-05, "epoch": 9.455445544554456, "percentage": 47.28, "elapsed_time": "1:12:32", "remaining_time": "1:20:54", "throughput": 4637.8, "total_tokens": 20187168} {"current_steps": 20060, "total_steps": 42420, "loss": 0.066, "lr": 3.1650127909454516e-05, "epoch": 9.457802923149458, "percentage": 47.29, "elapsed_time": "1:12:33", "remaining_time": "1:20:53", "throughput": 4637.87, "total_tokens": 20192480} {"current_steps": 20065, "total_steps": 42420, "loss": 0.1607, "lr": 3.164021193042085e-05, "epoch": 9.46016030174446, "percentage": 47.3, "elapsed_time": "1:12:34", "remaining_time": "1:20:51", "throughput": 4637.9, "total_tokens": 20197920} {"current_steps": 20070, "total_steps": 42420, "loss": 0.1525, "lr": 3.1630294827312067e-05, "epoch": 9.462517680339463, "percentage": 47.31, "elapsed_time": "1:12:36", "remaining_time": "1:20:50", "throughput": 4637.94, "total_tokens": 20203008} {"current_steps": 20075, "total_steps": 42420, "loss": 0.0537, "lr": 3.1620376601806935e-05, "epoch": 9.464875058934465, "percentage": 47.32, "elapsed_time": "1:12:36", "remaining_time": "1:20:49", "throughput": 4637.98, "total_tokens": 20207680} {"current_steps": 20080, "total_steps": 42420, "loss": 0.1362, "lr": 3.161045725558445e-05, "epoch": 9.467232437529468, "percentage": 47.34, "elapsed_time": "1:12:38", "remaining_time": "1:20:48", "throughput": 4638.03, "total_tokens": 20212544} {"current_steps": 20085, "total_steps": 42420, "loss": 0.1659, "lr": 3.160053679032379e-05, "epoch": 9.46958981612447, "percentage": 47.35, "elapsed_time": "1:12:38", "remaining_time": "1:20:47", "throughput": 4638.03, "total_tokens": 20216608} {"current_steps": 20090, "total_steps": 42420, "loss": 0.2875, "lr": 3.1590615207704334e-05, "epoch": 9.471947194719473, "percentage": 47.36, "elapsed_time": "1:12:39", "remaining_time": "1:20:45", "throughput": 4638.04, "total_tokens": 20220768} {"current_steps": 20095, "total_steps": 42420, "loss": 0.1401, "lr": 3.158069250940561e-05, "epoch": 9.474304573314475, "percentage": 47.37, "elapsed_time": "1:12:40", "remaining_time": "1:20:44", "throughput": 4638.04, "total_tokens": 20225728} {"current_steps": 20100, "total_steps": 42420, "loss": 0.1374, "lr": 3.157076869710738e-05, "epoch": 9.476661951909477, "percentage": 47.38, "elapsed_time": "1:12:41", "remaining_time": "1:20:43", "throughput": 4638.07, "total_tokens": 20230304} {"current_steps": 20105, "total_steps": 42420, "loss": 0.0361, "lr": 3.1560843772489584e-05, "epoch": 9.47901933050448, "percentage": 47.4, "elapsed_time": "1:12:42", "remaining_time": "1:20:42", "throughput": 4638.1, "total_tokens": 20235360} {"current_steps": 20110, "total_steps": 42420, "loss": 0.0457, "lr": 3.1550917737232334e-05, "epoch": 9.481376709099482, "percentage": 47.41, "elapsed_time": "1:12:43", "remaining_time": "1:20:41", "throughput": 4638.14, "total_tokens": 20240608} {"current_steps": 20115, "total_steps": 42420, "loss": 0.2025, "lr": 3.154099059301593e-05, "epoch": 9.483734087694483, "percentage": 47.42, "elapsed_time": "1:12:45", "remaining_time": "1:20:40", "throughput": 4638.18, "total_tokens": 20246112} {"current_steps": 20120, "total_steps": 42420, "loss": 0.133, "lr": 3.153106234152089e-05, "epoch": 9.486091466289485, "percentage": 47.43, "elapsed_time": "1:12:46", "remaining_time": "1:20:39", "throughput": 4638.24, "total_tokens": 20251104} {"current_steps": 20125, "total_steps": 42420, "loss": 0.0475, "lr": 3.152113298442788e-05, "epoch": 9.488448844884488, "percentage": 47.44, "elapsed_time": "1:12:47", "remaining_time": "1:20:38", "throughput": 4638.3, "total_tokens": 20256288} {"current_steps": 20130, "total_steps": 42420, "loss": 0.0613, "lr": 3.151120252341778e-05, "epoch": 9.49080622347949, "percentage": 47.45, "elapsed_time": "1:12:48", "remaining_time": "1:20:37", "throughput": 4638.35, "total_tokens": 20262048} {"current_steps": 20135, "total_steps": 42420, "loss": 0.1553, "lr": 3.150127096017164e-05, "epoch": 9.493163602074493, "percentage": 47.47, "elapsed_time": "1:12:49", "remaining_time": "1:20:35", "throughput": 4638.4, "total_tokens": 20266912} {"current_steps": 20140, "total_steps": 42420, "loss": 0.1855, "lr": 3.149133829637072e-05, "epoch": 9.495520980669495, "percentage": 47.48, "elapsed_time": "1:12:50", "remaining_time": "1:20:34", "throughput": 4638.48, "total_tokens": 20272800} {"current_steps": 20145, "total_steps": 42420, "loss": 0.0199, "lr": 3.1481404533696436e-05, "epoch": 9.497878359264497, "percentage": 47.49, "elapsed_time": "1:12:51", "remaining_time": "1:20:33", "throughput": 4638.51, "total_tokens": 20277440} {"current_steps": 20150, "total_steps": 42420, "loss": 0.0812, "lr": 3.1471469673830424e-05, "epoch": 9.5002357378595, "percentage": 47.5, "elapsed_time": "1:12:52", "remaining_time": "1:20:32", "throughput": 4638.53, "total_tokens": 20282624} {"current_steps": 20155, "total_steps": 42420, "loss": 0.1565, "lr": 3.146153371845447e-05, "epoch": 9.502593116454502, "percentage": 47.51, "elapsed_time": "1:12:53", "remaining_time": "1:20:31", "throughput": 4638.51, "total_tokens": 20286848} {"current_steps": 20160, "total_steps": 42420, "loss": 0.0808, "lr": 3.145159666925057e-05, "epoch": 9.504950495049505, "percentage": 47.52, "elapsed_time": "1:12:54", "remaining_time": "1:20:30", "throughput": 4638.54, "total_tokens": 20291104} {"current_steps": 20165, "total_steps": 42420, "loss": 0.0992, "lr": 3.144165852790088e-05, "epoch": 9.507307873644507, "percentage": 47.54, "elapsed_time": "1:12:55", "remaining_time": "1:20:28", "throughput": 4638.55, "total_tokens": 20295392} {"current_steps": 20170, "total_steps": 42420, "loss": 0.0896, "lr": 3.143171929608779e-05, "epoch": 9.50966525223951, "percentage": 47.55, "elapsed_time": "1:12:56", "remaining_time": "1:20:27", "throughput": 4638.61, "total_tokens": 20300192} {"current_steps": 20175, "total_steps": 42420, "loss": 0.1648, "lr": 3.1421778975493826e-05, "epoch": 9.512022630834512, "percentage": 47.56, "elapsed_time": "1:12:57", "remaining_time": "1:20:26", "throughput": 4638.59, "total_tokens": 20304672} {"current_steps": 20180, "total_steps": 42420, "loss": 0.0854, "lr": 3.141183756780172e-05, "epoch": 9.514380009429514, "percentage": 47.57, "elapsed_time": "1:12:58", "remaining_time": "1:20:25", "throughput": 4638.63, "total_tokens": 20309408} {"current_steps": 20185, "total_steps": 42420, "loss": 0.155, "lr": 3.140189507469437e-05, "epoch": 9.516737388024517, "percentage": 47.58, "elapsed_time": "1:12:59", "remaining_time": "1:20:24", "throughput": 4638.69, "total_tokens": 20316320} {"current_steps": 20190, "total_steps": 42420, "loss": 0.1578, "lr": 3.139195149785489e-05, "epoch": 9.519094766619519, "percentage": 47.6, "elapsed_time": "1:13:00", "remaining_time": "1:20:23", "throughput": 4638.71, "total_tokens": 20321248} {"current_steps": 20195, "total_steps": 42420, "loss": 0.0879, "lr": 3.1382006838966546e-05, "epoch": 9.521452145214521, "percentage": 47.61, "elapsed_time": "1:13:01", "remaining_time": "1:20:22", "throughput": 4638.79, "total_tokens": 20326944} {"current_steps": 20200, "total_steps": 42420, "loss": 0.0948, "lr": 3.1372061099712804e-05, "epoch": 9.523809523809524, "percentage": 47.62, "elapsed_time": "1:13:03", "remaining_time": "1:20:21", "throughput": 4638.82, "total_tokens": 20332096} {"current_steps": 20205, "total_steps": 42420, "loss": 0.2, "lr": 3.136211428177731e-05, "epoch": 9.526166902404526, "percentage": 47.63, "elapsed_time": "1:13:04", "remaining_time": "1:20:20", "throughput": 4638.89, "total_tokens": 20337216} {"current_steps": 20210, "total_steps": 42420, "loss": 0.231, "lr": 3.135216638684389e-05, "epoch": 9.528524280999529, "percentage": 47.64, "elapsed_time": "1:13:05", "remaining_time": "1:20:19", "throughput": 4638.93, "total_tokens": 20342336} {"current_steps": 20215, "total_steps": 42420, "loss": 0.2855, "lr": 3.1342217416596566e-05, "epoch": 9.530881659594531, "percentage": 47.65, "elapsed_time": "1:13:06", "remaining_time": "1:20:17", "throughput": 4638.99, "total_tokens": 20347616} {"current_steps": 20220, "total_steps": 42420, "loss": 0.0508, "lr": 3.13322673727195e-05, "epoch": 9.533239038189533, "percentage": 47.67, "elapsed_time": "1:13:07", "remaining_time": "1:20:16", "throughput": 4639.03, "total_tokens": 20352096} {"current_steps": 20225, "total_steps": 42420, "loss": 0.055, "lr": 3.13223162568971e-05, "epoch": 9.535596416784536, "percentage": 47.68, "elapsed_time": "1:13:08", "remaining_time": "1:20:15", "throughput": 4639.08, "total_tokens": 20357376} {"current_steps": 20230, "total_steps": 42420, "loss": 0.0507, "lr": 3.1312364070813896e-05, "epoch": 9.537953795379538, "percentage": 47.69, "elapsed_time": "1:13:09", "remaining_time": "1:20:14", "throughput": 4639.06, "total_tokens": 20361824} {"current_steps": 20235, "total_steps": 42420, "loss": 0.0614, "lr": 3.130241081615464e-05, "epoch": 9.54031117397454, "percentage": 47.7, "elapsed_time": "1:13:10", "remaining_time": "1:20:13", "throughput": 4639.05, "total_tokens": 20366176} {"current_steps": 20240, "total_steps": 42420, "loss": 0.0514, "lr": 3.129245649460423e-05, "epoch": 9.542668552569543, "percentage": 47.71, "elapsed_time": "1:13:11", "remaining_time": "1:20:12", "throughput": 4639.13, "total_tokens": 20372352} {"current_steps": 20245, "total_steps": 42420, "loss": 0.076, "lr": 3.128250110784778e-05, "epoch": 9.545025931164545, "percentage": 47.73, "elapsed_time": "1:13:12", "remaining_time": "1:20:11", "throughput": 4639.17, "total_tokens": 20377216} {"current_steps": 20250, "total_steps": 42420, "loss": 0.0382, "lr": 3.127254465757056e-05, "epoch": 9.547383309759548, "percentage": 47.74, "elapsed_time": "1:13:13", "remaining_time": "1:20:10", "throughput": 4639.23, "total_tokens": 20382368} {"current_steps": 20255, "total_steps": 42420, "loss": 0.098, "lr": 3.126258714545804e-05, "epoch": 9.54974068835455, "percentage": 47.75, "elapsed_time": "1:13:14", "remaining_time": "1:20:08", "throughput": 4639.24, "total_tokens": 20387072} {"current_steps": 20260, "total_steps": 42420, "loss": 0.1154, "lr": 3.1252628573195845e-05, "epoch": 9.552098066949553, "percentage": 47.76, "elapsed_time": "1:13:15", "remaining_time": "1:20:07", "throughput": 4639.26, "total_tokens": 20392256} {"current_steps": 20265, "total_steps": 42420, "loss": 0.0238, "lr": 3.124266894246979e-05, "epoch": 9.554455445544555, "percentage": 47.77, "elapsed_time": "1:13:16", "remaining_time": "1:20:06", "throughput": 4639.27, "total_tokens": 20396960} {"current_steps": 20270, "total_steps": 42420, "loss": 0.0883, "lr": 3.123270825496589e-05, "epoch": 9.556812824139557, "percentage": 47.78, "elapsed_time": "1:13:17", "remaining_time": "1:20:05", "throughput": 4639.29, "total_tokens": 20401472} {"current_steps": 20275, "total_steps": 42420, "loss": 0.092, "lr": 3.12227465123703e-05, "epoch": 9.55917020273456, "percentage": 47.8, "elapsed_time": "1:13:18", "remaining_time": "1:20:04", "throughput": 4639.31, "total_tokens": 20406144} {"current_steps": 20280, "total_steps": 42420, "loss": 0.1539, "lr": 3.121278371636938e-05, "epoch": 9.561527581329562, "percentage": 47.81, "elapsed_time": "1:13:19", "remaining_time": "1:20:02", "throughput": 4639.36, "total_tokens": 20410816} {"current_steps": 20285, "total_steps": 42420, "loss": 0.137, "lr": 3.1202819868649666e-05, "epoch": 9.563884959924565, "percentage": 47.82, "elapsed_time": "1:13:20", "remaining_time": "1:20:01", "throughput": 4639.36, "total_tokens": 20415712} {"current_steps": 20290, "total_steps": 42420, "loss": 0.0429, "lr": 3.119285497089787e-05, "epoch": 9.566242338519567, "percentage": 47.83, "elapsed_time": "1:13:21", "remaining_time": "1:20:00", "throughput": 4639.41, "total_tokens": 20420704} {"current_steps": 20295, "total_steps": 42420, "loss": 0.1227, "lr": 3.118288902480087e-05, "epoch": 9.56859971711457, "percentage": 47.84, "elapsed_time": "1:13:22", "remaining_time": "1:19:59", "throughput": 4639.48, "total_tokens": 20425504} {"current_steps": 20300, "total_steps": 42420, "loss": 0.105, "lr": 3.117292203204574e-05, "epoch": 9.570957095709572, "percentage": 47.85, "elapsed_time": "1:13:23", "remaining_time": "1:19:58", "throughput": 4639.52, "total_tokens": 20430656} {"current_steps": 20305, "total_steps": 42420, "loss": 0.0181, "lr": 3.1162953994319716e-05, "epoch": 9.573314474304574, "percentage": 47.87, "elapsed_time": "1:13:24", "remaining_time": "1:19:57", "throughput": 4639.57, "total_tokens": 20435680} {"current_steps": 20310, "total_steps": 42420, "loss": 0.1292, "lr": 3.115298491331022e-05, "epoch": 9.575671852899575, "percentage": 47.88, "elapsed_time": "1:13:25", "remaining_time": "1:19:56", "throughput": 4639.58, "total_tokens": 20440512} {"current_steps": 20315, "total_steps": 42420, "loss": 0.0512, "lr": 3.114301479070486e-05, "epoch": 9.578029231494579, "percentage": 47.89, "elapsed_time": "1:13:26", "remaining_time": "1:19:54", "throughput": 4639.65, "total_tokens": 20445472} {"current_steps": 20320, "total_steps": 42420, "loss": 0.0505, "lr": 3.11330436281914e-05, "epoch": 9.58038661008958, "percentage": 47.9, "elapsed_time": "1:13:27", "remaining_time": "1:19:53", "throughput": 4639.72, "total_tokens": 20451232} {"current_steps": 20325, "total_steps": 42420, "loss": 0.2404, "lr": 3.112307142745778e-05, "epoch": 9.582743988684582, "percentage": 47.91, "elapsed_time": "1:13:28", "remaining_time": "1:19:52", "throughput": 4639.77, "total_tokens": 20456032} {"current_steps": 20330, "total_steps": 42420, "loss": 0.0882, "lr": 3.111309819019213e-05, "epoch": 9.585101367279584, "percentage": 47.93, "elapsed_time": "1:13:29", "remaining_time": "1:19:51", "throughput": 4639.83, "total_tokens": 20461056} {"current_steps": 20335, "total_steps": 42420, "loss": 0.164, "lr": 3.110312391808275e-05, "epoch": 9.587458745874587, "percentage": 47.94, "elapsed_time": "1:13:30", "remaining_time": "1:19:50", "throughput": 4639.87, "total_tokens": 20466144} {"current_steps": 20340, "total_steps": 42420, "loss": 0.1881, "lr": 3.1093148612818126e-05, "epoch": 9.58981612446959, "percentage": 47.95, "elapsed_time": "1:13:32", "remaining_time": "1:19:49", "throughput": 4639.96, "total_tokens": 20472192} {"current_steps": 20345, "total_steps": 42420, "loss": 0.2007, "lr": 3.108317227608688e-05, "epoch": 9.592173503064592, "percentage": 47.96, "elapsed_time": "1:13:33", "remaining_time": "1:19:48", "throughput": 4640.01, "total_tokens": 20476992} {"current_steps": 20350, "total_steps": 42420, "loss": 0.0565, "lr": 3.107319490957787e-05, "epoch": 9.594530881659594, "percentage": 47.97, "elapsed_time": "1:13:34", "remaining_time": "1:19:47", "throughput": 4640.1, "total_tokens": 20482848} {"current_steps": 20355, "total_steps": 42420, "loss": 0.1515, "lr": 3.106321651498007e-05, "epoch": 9.596888260254596, "percentage": 47.98, "elapsed_time": "1:13:35", "remaining_time": "1:19:46", "throughput": 4640.17, "total_tokens": 20488000} {"current_steps": 20360, "total_steps": 42420, "loss": 0.2603, "lr": 3.105323709398267e-05, "epoch": 9.599245638849599, "percentage": 48.0, "elapsed_time": "1:13:36", "remaining_time": "1:19:45", "throughput": 4640.2, "total_tokens": 20492864} {"current_steps": 20365, "total_steps": 42420, "loss": 0.0667, "lr": 3.1043256648275e-05, "epoch": 9.601603017444601, "percentage": 48.01, "elapsed_time": "1:13:37", "remaining_time": "1:19:43", "throughput": 4640.19, "total_tokens": 20497216} {"current_steps": 20370, "total_steps": 42420, "loss": 0.1184, "lr": 3.103327517954659e-05, "epoch": 9.603960396039604, "percentage": 48.02, "elapsed_time": "1:13:38", "remaining_time": "1:19:42", "throughput": 4640.24, "total_tokens": 20502560} {"current_steps": 20375, "total_steps": 42420, "loss": 0.0719, "lr": 3.102329268948714e-05, "epoch": 9.606317774634606, "percentage": 48.03, "elapsed_time": "1:13:39", "remaining_time": "1:19:41", "throughput": 4640.31, "total_tokens": 20508000} {"current_steps": 20380, "total_steps": 42420, "loss": 0.1512, "lr": 3.10133091797865e-05, "epoch": 9.608675153229608, "percentage": 48.04, "elapsed_time": "1:13:40", "remaining_time": "1:19:40", "throughput": 4640.43, "total_tokens": 20514432} {"current_steps": 20385, "total_steps": 42420, "loss": 0.1079, "lr": 3.100332465213471e-05, "epoch": 9.61103253182461, "percentage": 48.06, "elapsed_time": "1:13:41", "remaining_time": "1:19:39", "throughput": 4640.51, "total_tokens": 20519872} {"current_steps": 20390, "total_steps": 42420, "loss": 0.0744, "lr": 3.0993339108222e-05, "epoch": 9.613389910419613, "percentage": 48.07, "elapsed_time": "1:13:42", "remaining_time": "1:19:38", "throughput": 4640.46, "total_tokens": 20523872} {"current_steps": 20395, "total_steps": 42420, "loss": 0.1662, "lr": 3.098335254973872e-05, "epoch": 9.615747289014616, "percentage": 48.08, "elapsed_time": "1:13:43", "remaining_time": "1:19:37", "throughput": 4640.49, "total_tokens": 20528320} {"current_steps": 20400, "total_steps": 42420, "loss": 0.1484, "lr": 3.097336497837547e-05, "epoch": 9.618104667609618, "percentage": 48.09, "elapsed_time": "1:13:44", "remaining_time": "1:19:36", "throughput": 4640.57, "total_tokens": 20534016} {"current_steps": 20405, "total_steps": 42420, "loss": 0.0165, "lr": 3.096337639582294e-05, "epoch": 9.62046204620462, "percentage": 48.1, "elapsed_time": "1:13:45", "remaining_time": "1:19:35", "throughput": 4640.6, "total_tokens": 20539008} {"current_steps": 20410, "total_steps": 42420, "loss": 0.3449, "lr": 3.0953386803772036e-05, "epoch": 9.622819424799623, "percentage": 48.11, "elapsed_time": "1:13:47", "remaining_time": "1:19:34", "throughput": 4640.67, "total_tokens": 20544416} {"current_steps": 20415, "total_steps": 42420, "loss": 0.0798, "lr": 3.0943396203913826e-05, "epoch": 9.625176803394625, "percentage": 48.13, "elapsed_time": "1:13:48", "remaining_time": "1:19:32", "throughput": 4640.73, "total_tokens": 20549664} {"current_steps": 20420, "total_steps": 42420, "loss": 0.0242, "lr": 3.093340459793956e-05, "epoch": 9.627534181989628, "percentage": 48.14, "elapsed_time": "1:13:49", "remaining_time": "1:19:31", "throughput": 4640.79, "total_tokens": 20554848} {"current_steps": 20425, "total_steps": 42420, "loss": 0.0258, "lr": 3.0923411987540636e-05, "epoch": 9.62989156058463, "percentage": 48.15, "elapsed_time": "1:13:50", "remaining_time": "1:19:30", "throughput": 4640.84, "total_tokens": 20559840} {"current_steps": 20430, "total_steps": 42420, "loss": 0.1581, "lr": 3.091341837440863e-05, "epoch": 9.632248939179632, "percentage": 48.16, "elapsed_time": "1:13:51", "remaining_time": "1:19:29", "throughput": 4640.78, "total_tokens": 20563840} {"current_steps": 20435, "total_steps": 42420, "loss": 0.0375, "lr": 3.090342376023531e-05, "epoch": 9.634606317774635, "percentage": 48.17, "elapsed_time": "1:13:52", "remaining_time": "1:19:28", "throughput": 4640.82, "total_tokens": 20568448} {"current_steps": 20440, "total_steps": 42420, "loss": 0.1926, "lr": 3.089342814671257e-05, "epoch": 9.636963696369637, "percentage": 48.18, "elapsed_time": "1:13:53", "remaining_time": "1:19:27", "throughput": 4640.85, "total_tokens": 20573824} {"current_steps": 20445, "total_steps": 42420, "loss": 0.0522, "lr": 3.0883431535532516e-05, "epoch": 9.63932107496464, "percentage": 48.2, "elapsed_time": "1:13:54", "remaining_time": "1:19:25", "throughput": 4640.86, "total_tokens": 20577984} {"current_steps": 20450, "total_steps": 42420, "loss": 0.2802, "lr": 3.08734339283874e-05, "epoch": 9.641678453559642, "percentage": 48.21, "elapsed_time": "1:13:55", "remaining_time": "1:19:24", "throughput": 4640.95, "total_tokens": 20583520} {"current_steps": 20455, "total_steps": 42420, "loss": 0.2941, "lr": 3.0863435326969635e-05, "epoch": 9.644035832154644, "percentage": 48.22, "elapsed_time": "1:13:56", "remaining_time": "1:19:23", "throughput": 4640.92, "total_tokens": 20587840} {"current_steps": 20460, "total_steps": 42420, "loss": 0.0828, "lr": 3.085343573297184e-05, "epoch": 9.646393210749647, "percentage": 48.23, "elapsed_time": "1:13:57", "remaining_time": "1:19:22", "throughput": 4640.93, "total_tokens": 20592480} {"current_steps": 20465, "total_steps": 42420, "loss": 0.3211, "lr": 3.084343514808674e-05, "epoch": 9.64875058934465, "percentage": 48.24, "elapsed_time": "1:13:58", "remaining_time": "1:19:21", "throughput": 4640.84, "total_tokens": 20596096} {"current_steps": 20470, "total_steps": 42420, "loss": 0.1785, "lr": 3.08334335740073e-05, "epoch": 9.651107967939652, "percentage": 48.26, "elapsed_time": "1:13:58", "remaining_time": "1:19:19", "throughput": 4640.9, "total_tokens": 20600928} {"current_steps": 20475, "total_steps": 42420, "loss": 0.1228, "lr": 3.0823431012426595e-05, "epoch": 9.653465346534654, "percentage": 48.27, "elapsed_time": "1:13:59", "remaining_time": "1:19:18", "throughput": 4640.91, "total_tokens": 20605024} {"current_steps": 20480, "total_steps": 42420, "loss": 0.1692, "lr": 3.0813427465037906e-05, "epoch": 9.655822725129656, "percentage": 48.28, "elapsed_time": "1:14:00", "remaining_time": "1:19:17", "throughput": 4640.99, "total_tokens": 20610560} {"current_steps": 20485, "total_steps": 42420, "loss": 0.1178, "lr": 3.080342293353465e-05, "epoch": 9.658180103724659, "percentage": 48.29, "elapsed_time": "1:14:02", "remaining_time": "1:19:16", "throughput": 4641.06, "total_tokens": 20616608} {"current_steps": 20490, "total_steps": 42420, "loss": 0.0766, "lr": 3.079341741961043e-05, "epoch": 9.660537482319661, "percentage": 48.3, "elapsed_time": "1:14:03", "remaining_time": "1:19:15", "throughput": 4641.14, "total_tokens": 20622240} {"current_steps": 20495, "total_steps": 42420, "loss": 0.1106, "lr": 3.0783410924959e-05, "epoch": 9.662894860914664, "percentage": 48.31, "elapsed_time": "1:14:04", "remaining_time": "1:19:14", "throughput": 4641.21, "total_tokens": 20627584} {"current_steps": 20500, "total_steps": 42420, "loss": 0.0729, "lr": 3.07734034512743e-05, "epoch": 9.665252239509666, "percentage": 48.33, "elapsed_time": "1:14:05", "remaining_time": "1:19:13", "throughput": 4641.28, "total_tokens": 20632480} {"current_steps": 20505, "total_steps": 42420, "loss": 0.1441, "lr": 3.076339500025042e-05, "epoch": 9.667609618104667, "percentage": 48.34, "elapsed_time": "1:14:06", "remaining_time": "1:19:12", "throughput": 4641.32, "total_tokens": 20637408} {"current_steps": 20510, "total_steps": 42420, "loss": 0.2678, "lr": 3.075338557358163e-05, "epoch": 9.66996699669967, "percentage": 48.35, "elapsed_time": "1:14:07", "remaining_time": "1:19:11", "throughput": 4641.39, "total_tokens": 20643456} {"current_steps": 20515, "total_steps": 42420, "loss": 0.0894, "lr": 3.074337517296234e-05, "epoch": 9.672324375294671, "percentage": 48.36, "elapsed_time": "1:14:08", "remaining_time": "1:19:10", "throughput": 4641.42, "total_tokens": 20648224} {"current_steps": 20520, "total_steps": 42420, "loss": 0.2162, "lr": 3.0733363800087154e-05, "epoch": 9.674681753889674, "percentage": 48.37, "elapsed_time": "1:14:09", "remaining_time": "1:19:09", "throughput": 4641.49, "total_tokens": 20653824} {"current_steps": 20525, "total_steps": 42420, "loss": 0.1529, "lr": 3.072335145665083e-05, "epoch": 9.677039132484676, "percentage": 48.39, "elapsed_time": "1:14:10", "remaining_time": "1:19:07", "throughput": 4641.47, "total_tokens": 20658048} {"current_steps": 20530, "total_steps": 42420, "loss": 0.2537, "lr": 3.071333814434827e-05, "epoch": 9.679396511079679, "percentage": 48.4, "elapsed_time": "1:14:11", "remaining_time": "1:19:06", "throughput": 4641.52, "total_tokens": 20663744} {"current_steps": 20535, "total_steps": 42420, "loss": 0.0557, "lr": 3.0703323864874576e-05, "epoch": 9.681753889674681, "percentage": 48.41, "elapsed_time": "1:14:13", "remaining_time": "1:19:05", "throughput": 4641.58, "total_tokens": 20668992} {"current_steps": 20540, "total_steps": 42420, "loss": 0.1298, "lr": 3.069330861992499e-05, "epoch": 9.684111268269683, "percentage": 48.42, "elapsed_time": "1:14:13", "remaining_time": "1:19:04", "throughput": 4641.59, "total_tokens": 20673632} {"current_steps": 20545, "total_steps": 42420, "loss": 0.0817, "lr": 3.0683292411194925e-05, "epoch": 9.686468646864686, "percentage": 48.43, "elapsed_time": "1:14:15", "remaining_time": "1:19:03", "throughput": 4641.65, "total_tokens": 20678912} {"current_steps": 20550, "total_steps": 42420, "loss": 0.1251, "lr": 3.067327524037994e-05, "epoch": 9.688826025459688, "percentage": 48.44, "elapsed_time": "1:14:16", "remaining_time": "1:19:02", "throughput": 4641.72, "total_tokens": 20683680} {"current_steps": 20555, "total_steps": 42420, "loss": 0.0521, "lr": 3.066325710917579e-05, "epoch": 9.69118340405469, "percentage": 48.46, "elapsed_time": "1:14:16", "remaining_time": "1:19:01", "throughput": 4641.75, "total_tokens": 20688128} {"current_steps": 20560, "total_steps": 42420, "loss": 0.1589, "lr": 3.0653238019278365e-05, "epoch": 9.693540782649693, "percentage": 48.47, "elapsed_time": "1:14:18", "remaining_time": "1:19:00", "throughput": 4641.81, "total_tokens": 20693856} {"current_steps": 20565, "total_steps": 42420, "loss": 0.1956, "lr": 3.0643217972383745e-05, "epoch": 9.695898161244696, "percentage": 48.48, "elapsed_time": "1:14:19", "remaining_time": "1:18:58", "throughput": 4641.86, "total_tokens": 20698688} {"current_steps": 20570, "total_steps": 42420, "loss": 0.0518, "lr": 3.063319697018812e-05, "epoch": 9.698255539839698, "percentage": 48.49, "elapsed_time": "1:14:20", "remaining_time": "1:18:57", "throughput": 4641.91, "total_tokens": 20703840} {"current_steps": 20575, "total_steps": 42420, "loss": 0.1183, "lr": 3.06231750143879e-05, "epoch": 9.7006129184347, "percentage": 48.5, "elapsed_time": "1:14:21", "remaining_time": "1:18:56", "throughput": 4641.96, "total_tokens": 20708576} {"current_steps": 20580, "total_steps": 42420, "loss": 0.0782, "lr": 3.061315210667963e-05, "epoch": 9.702970297029703, "percentage": 48.51, "elapsed_time": "1:14:22", "remaining_time": "1:18:55", "throughput": 4641.95, "total_tokens": 20713120} {"current_steps": 20585, "total_steps": 42420, "loss": 0.1282, "lr": 3.060312824876001e-05, "epoch": 9.705327675624705, "percentage": 48.53, "elapsed_time": "1:14:23", "remaining_time": "1:18:54", "throughput": 4641.99, "total_tokens": 20717984} {"current_steps": 20590, "total_steps": 42420, "loss": 0.0607, "lr": 3.0593103442325916e-05, "epoch": 9.707685054219708, "percentage": 48.54, "elapsed_time": "1:14:24", "remaining_time": "1:18:53", "throughput": 4642.06, "total_tokens": 20723648} {"current_steps": 20595, "total_steps": 42420, "loss": 0.2808, "lr": 3.0583077689074366e-05, "epoch": 9.71004243281471, "percentage": 48.55, "elapsed_time": "1:14:25", "remaining_time": "1:18:51", "throughput": 4642.08, "total_tokens": 20728000} {"current_steps": 20600, "total_steps": 42420, "loss": 0.1403, "lr": 3.057305099070257e-05, "epoch": 9.712399811409712, "percentage": 48.56, "elapsed_time": "1:14:26", "remaining_time": "1:18:50", "throughput": 4642.15, "total_tokens": 20733152} {"current_steps": 20605, "total_steps": 42420, "loss": 0.1342, "lr": 3.056302334890786e-05, "epoch": 9.714757190004715, "percentage": 48.57, "elapsed_time": "1:14:27", "remaining_time": "1:18:49", "throughput": 4642.23, "total_tokens": 20738944} {"current_steps": 20610, "total_steps": 42420, "loss": 0.2181, "lr": 3.055299476538776e-05, "epoch": 9.717114568599717, "percentage": 48.59, "elapsed_time": "1:14:28", "remaining_time": "1:18:48", "throughput": 4642.28, "total_tokens": 20744192} {"current_steps": 20615, "total_steps": 42420, "loss": 0.0847, "lr": 3.054296524183992e-05, "epoch": 9.71947194719472, "percentage": 48.6, "elapsed_time": "1:14:29", "remaining_time": "1:18:47", "throughput": 4642.29, "total_tokens": 20748864} {"current_steps": 20620, "total_steps": 42420, "loss": 0.2352, "lr": 3.053293477996219e-05, "epoch": 9.721829325789722, "percentage": 48.61, "elapsed_time": "1:14:30", "remaining_time": "1:18:46", "throughput": 4642.32, "total_tokens": 20754144} {"current_steps": 20625, "total_steps": 42420, "loss": 0.0879, "lr": 3.052290338145253e-05, "epoch": 9.724186704384724, "percentage": 48.62, "elapsed_time": "1:14:31", "remaining_time": "1:18:45", "throughput": 4642.35, "total_tokens": 20758592} {"current_steps": 20630, "total_steps": 42420, "loss": 0.1359, "lr": 3.0512871048009117e-05, "epoch": 9.726544082979727, "percentage": 48.63, "elapsed_time": "1:14:32", "remaining_time": "1:18:44", "throughput": 4642.41, "total_tokens": 20763520} {"current_steps": 20635, "total_steps": 42420, "loss": 0.2109, "lr": 3.0502837781330228e-05, "epoch": 9.72890146157473, "percentage": 48.64, "elapsed_time": "1:14:33", "remaining_time": "1:18:42", "throughput": 4642.46, "total_tokens": 20768480} {"current_steps": 20640, "total_steps": 42420, "loss": 0.0872, "lr": 3.049280358311434e-05, "epoch": 9.731258840169732, "percentage": 48.66, "elapsed_time": "1:14:34", "remaining_time": "1:18:41", "throughput": 4642.53, "total_tokens": 20773760} {"current_steps": 20645, "total_steps": 42420, "loss": 0.2955, "lr": 3.0482768455060063e-05, "epoch": 9.733616218764734, "percentage": 48.67, "elapsed_time": "1:14:35", "remaining_time": "1:18:40", "throughput": 4642.52, "total_tokens": 20777696} {"current_steps": 20650, "total_steps": 42420, "loss": 0.0886, "lr": 3.047273239886619e-05, "epoch": 9.735973597359736, "percentage": 48.68, "elapsed_time": "1:14:36", "remaining_time": "1:18:39", "throughput": 4642.5, "total_tokens": 20781728} {"current_steps": 20655, "total_steps": 42420, "loss": 0.2982, "lr": 3.046269541623163e-05, "epoch": 9.738330975954739, "percentage": 48.69, "elapsed_time": "1:14:37", "remaining_time": "1:18:38", "throughput": 4642.5, "total_tokens": 20787200} {"current_steps": 20660, "total_steps": 42420, "loss": 0.2494, "lr": 3.0452657508855493e-05, "epoch": 9.740688354549741, "percentage": 48.7, "elapsed_time": "1:14:38", "remaining_time": "1:18:36", "throughput": 4642.5, "total_tokens": 20791296} {"current_steps": 20665, "total_steps": 42420, "loss": 0.1077, "lr": 3.0442618678437017e-05, "epoch": 9.743045733144744, "percentage": 48.72, "elapsed_time": "1:14:39", "remaining_time": "1:18:35", "throughput": 4642.49, "total_tokens": 20795456} {"current_steps": 20670, "total_steps": 42420, "loss": 0.2269, "lr": 3.043257892667562e-05, "epoch": 9.745403111739746, "percentage": 48.73, "elapsed_time": "1:14:40", "remaining_time": "1:18:34", "throughput": 4642.49, "total_tokens": 20799648} {"current_steps": 20675, "total_steps": 42420, "loss": 0.0412, "lr": 3.0422538255270844e-05, "epoch": 9.747760490334748, "percentage": 48.74, "elapsed_time": "1:14:41", "remaining_time": "1:18:33", "throughput": 4642.52, "total_tokens": 20804480} {"current_steps": 20680, "total_steps": 42420, "loss": 0.136, "lr": 3.041249666592241e-05, "epoch": 9.75011786892975, "percentage": 48.75, "elapsed_time": "1:14:42", "remaining_time": "1:18:32", "throughput": 4642.61, "total_tokens": 20810016} {"current_steps": 20685, "total_steps": 42420, "loss": 0.1742, "lr": 3.0402454160330184e-05, "epoch": 9.752475247524753, "percentage": 48.76, "elapsed_time": "1:14:43", "remaining_time": "1:18:31", "throughput": 4642.65, "total_tokens": 20814976} {"current_steps": 20690, "total_steps": 42420, "loss": 0.1559, "lr": 3.039241074019421e-05, "epoch": 9.754832626119756, "percentage": 48.77, "elapsed_time": "1:14:44", "remaining_time": "1:18:29", "throughput": 4642.62, "total_tokens": 20819104} {"current_steps": 20695, "total_steps": 42420, "loss": 0.1193, "lr": 3.0382366407214646e-05, "epoch": 9.757190004714758, "percentage": 48.79, "elapsed_time": "1:14:45", "remaining_time": "1:18:28", "throughput": 4642.63, "total_tokens": 20823904} {"current_steps": 20700, "total_steps": 42420, "loss": 0.1631, "lr": 3.0372321163091838e-05, "epoch": 9.75954738330976, "percentage": 48.8, "elapsed_time": "1:14:46", "remaining_time": "1:18:27", "throughput": 4642.7, "total_tokens": 20830048} {"current_steps": 20705, "total_steps": 42420, "loss": 0.2431, "lr": 3.0362275009526275e-05, "epoch": 9.761904761904763, "percentage": 48.81, "elapsed_time": "1:14:47", "remaining_time": "1:18:26", "throughput": 4642.69, "total_tokens": 20834688} {"current_steps": 20710, "total_steps": 42420, "loss": 0.0483, "lr": 3.0352227948218603e-05, "epoch": 9.764262140499763, "percentage": 48.82, "elapsed_time": "1:14:48", "remaining_time": "1:18:25", "throughput": 4642.71, "total_tokens": 20839040} {"current_steps": 20715, "total_steps": 42420, "loss": 0.1085, "lr": 3.0342179980869616e-05, "epoch": 9.766619519094768, "percentage": 48.83, "elapsed_time": "1:14:49", "remaining_time": "1:18:24", "throughput": 4642.75, "total_tokens": 20843840} {"current_steps": 20720, "total_steps": 42420, "loss": 0.1137, "lr": 3.0332131109180255e-05, "epoch": 9.768976897689768, "percentage": 48.84, "elapsed_time": "1:14:50", "remaining_time": "1:18:22", "throughput": 4642.78, "total_tokens": 20848512} {"current_steps": 20725, "total_steps": 42420, "loss": 0.1653, "lr": 3.0322081334851637e-05, "epoch": 9.77133427628477, "percentage": 48.86, "elapsed_time": "1:14:51", "remaining_time": "1:18:21", "throughput": 4642.76, "total_tokens": 20853120} {"current_steps": 20730, "total_steps": 42420, "loss": 0.1254, "lr": 3.0312030659585013e-05, "epoch": 9.773691654879773, "percentage": 48.87, "elapsed_time": "1:14:52", "remaining_time": "1:18:20", "throughput": 4642.72, "total_tokens": 20857536} {"current_steps": 20735, "total_steps": 42420, "loss": 0.1776, "lr": 3.0301979085081788e-05, "epoch": 9.776049033474775, "percentage": 48.88, "elapsed_time": "1:14:53", "remaining_time": "1:18:19", "throughput": 4642.71, "total_tokens": 20862688} {"current_steps": 20740, "total_steps": 42420, "loss": 0.2376, "lr": 3.0291926613043526e-05, "epoch": 9.778406412069778, "percentage": 48.89, "elapsed_time": "1:14:54", "remaining_time": "1:18:18", "throughput": 4642.73, "total_tokens": 20867712} {"current_steps": 20745, "total_steps": 42420, "loss": 0.0436, "lr": 3.0281873245171943e-05, "epoch": 9.78076379066478, "percentage": 48.9, "elapsed_time": "1:14:55", "remaining_time": "1:18:17", "throughput": 4642.78, "total_tokens": 20872544} {"current_steps": 20750, "total_steps": 42420, "loss": 0.2089, "lr": 3.02718189831689e-05, "epoch": 9.783121169259783, "percentage": 48.92, "elapsed_time": "1:14:56", "remaining_time": "1:18:16", "throughput": 4642.82, "total_tokens": 20877504} {"current_steps": 20755, "total_steps": 42420, "loss": 0.0488, "lr": 3.0261763828736417e-05, "epoch": 9.785478547854785, "percentage": 48.93, "elapsed_time": "1:14:57", "remaining_time": "1:18:15", "throughput": 4642.86, "total_tokens": 20882656} {"current_steps": 20760, "total_steps": 42420, "loss": 0.1431, "lr": 3.025170778357665e-05, "epoch": 9.787835926449787, "percentage": 48.94, "elapsed_time": "1:14:58", "remaining_time": "1:18:13", "throughput": 4642.87, "total_tokens": 20887136} {"current_steps": 20765, "total_steps": 42420, "loss": 0.0704, "lr": 3.024165084939193e-05, "epoch": 9.79019330504479, "percentage": 48.95, "elapsed_time": "1:14:59", "remaining_time": "1:18:12", "throughput": 4642.89, "total_tokens": 20891488} {"current_steps": 20770, "total_steps": 42420, "loss": 0.0512, "lr": 3.0231593027884712e-05, "epoch": 9.792550683639792, "percentage": 48.96, "elapsed_time": "1:15:00", "remaining_time": "1:18:11", "throughput": 4642.94, "total_tokens": 20896992} {"current_steps": 20775, "total_steps": 42420, "loss": 0.3546, "lr": 3.0221534320757633e-05, "epoch": 9.794908062234795, "percentage": 48.97, "elapsed_time": "1:15:01", "remaining_time": "1:18:10", "throughput": 4642.96, "total_tokens": 20901504} {"current_steps": 20780, "total_steps": 42420, "loss": 0.1012, "lr": 3.0211474729713442e-05, "epoch": 9.797265440829797, "percentage": 48.99, "elapsed_time": "1:15:02", "remaining_time": "1:18:09", "throughput": 4642.99, "total_tokens": 20906880} {"current_steps": 20785, "total_steps": 42420, "loss": 0.1235, "lr": 3.0201414256455068e-05, "epoch": 9.7996228194248, "percentage": 49.0, "elapsed_time": "1:15:03", "remaining_time": "1:18:08", "throughput": 4643.01, "total_tokens": 20911776} {"current_steps": 20790, "total_steps": 42420, "loss": 0.0774, "lr": 3.0191352902685572e-05, "epoch": 9.801980198019802, "percentage": 49.01, "elapsed_time": "1:15:05", "remaining_time": "1:18:07", "throughput": 4643.09, "total_tokens": 20917376} {"current_steps": 20795, "total_steps": 42420, "loss": 0.1283, "lr": 3.0181290670108183e-05, "epoch": 9.804337576614804, "percentage": 49.02, "elapsed_time": "1:15:06", "remaining_time": "1:18:05", "throughput": 4643.14, "total_tokens": 20922048} {"current_steps": 20800, "total_steps": 42420, "loss": 0.1757, "lr": 3.0171227560426245e-05, "epoch": 9.806694955209807, "percentage": 49.03, "elapsed_time": "1:15:07", "remaining_time": "1:18:04", "throughput": 4643.17, "total_tokens": 20927008} {"current_steps": 20805, "total_steps": 42420, "loss": 0.0764, "lr": 3.0161163575343288e-05, "epoch": 9.809052333804809, "percentage": 49.05, "elapsed_time": "1:15:07", "remaining_time": "1:18:03", "throughput": 4643.1, "total_tokens": 20930944} {"current_steps": 20810, "total_steps": 42420, "loss": 0.0697, "lr": 3.015109871656297e-05, "epoch": 9.811409712399811, "percentage": 49.06, "elapsed_time": "1:15:08", "remaining_time": "1:18:02", "throughput": 4643.12, "total_tokens": 20935296} {"current_steps": 20815, "total_steps": 42420, "loss": 0.2282, "lr": 3.0141032985789103e-05, "epoch": 9.813767090994814, "percentage": 49.07, "elapsed_time": "1:15:09", "remaining_time": "1:18:01", "throughput": 4643.15, "total_tokens": 20940064} {"current_steps": 20820, "total_steps": 42420, "loss": 0.0474, "lr": 3.0130966384725638e-05, "epoch": 9.816124469589816, "percentage": 49.08, "elapsed_time": "1:15:10", "remaining_time": "1:17:59", "throughput": 4643.14, "total_tokens": 20944064} {"current_steps": 20825, "total_steps": 42420, "loss": 0.0622, "lr": 3.012089891507669e-05, "epoch": 9.818481848184819, "percentage": 49.09, "elapsed_time": "1:15:11", "remaining_time": "1:17:58", "throughput": 4643.14, "total_tokens": 20948672} {"current_steps": 20830, "total_steps": 42420, "loss": 0.1287, "lr": 3.0110830578546497e-05, "epoch": 9.820839226779821, "percentage": 49.1, "elapsed_time": "1:15:12", "remaining_time": "1:17:57", "throughput": 4643.17, "total_tokens": 20953696} {"current_steps": 20835, "total_steps": 42420, "loss": 0.1902, "lr": 3.010076137683946e-05, "epoch": 9.823196605374823, "percentage": 49.12, "elapsed_time": "1:15:13", "remaining_time": "1:17:56", "throughput": 4643.24, "total_tokens": 20959296} {"current_steps": 20840, "total_steps": 42420, "loss": 0.0555, "lr": 3.0090691311660137e-05, "epoch": 9.825553983969826, "percentage": 49.13, "elapsed_time": "1:15:15", "remaining_time": "1:17:55", "throughput": 4643.29, "total_tokens": 20964480} {"current_steps": 20845, "total_steps": 42420, "loss": 0.0835, "lr": 3.00806203847132e-05, "epoch": 9.827911362564828, "percentage": 49.14, "elapsed_time": "1:15:15", "remaining_time": "1:17:54", "throughput": 4643.35, "total_tokens": 20969376} {"current_steps": 20850, "total_steps": 42420, "loss": 0.1277, "lr": 3.00705485977035e-05, "epoch": 9.83026874115983, "percentage": 49.15, "elapsed_time": "1:15:17", "remaining_time": "1:17:53", "throughput": 4643.43, "total_tokens": 20975648} {"current_steps": 20855, "total_steps": 42420, "loss": 0.0547, "lr": 3.0060475952336015e-05, "epoch": 9.832626119754833, "percentage": 49.16, "elapsed_time": "1:15:18", "remaining_time": "1:17:52", "throughput": 4643.54, "total_tokens": 20981632} {"current_steps": 20860, "total_steps": 42420, "loss": 0.078, "lr": 3.005040245031588e-05, "epoch": 9.834983498349835, "percentage": 49.17, "elapsed_time": "1:15:19", "remaining_time": "1:17:51", "throughput": 4643.62, "total_tokens": 20987584} {"current_steps": 20865, "total_steps": 42420, "loss": 0.0386, "lr": 3.004032809334835e-05, "epoch": 9.837340876944838, "percentage": 49.19, "elapsed_time": "1:15:20", "remaining_time": "1:17:50", "throughput": 4643.66, "total_tokens": 20992256} {"current_steps": 20870, "total_steps": 42420, "loss": 0.2037, "lr": 3.003025288313886e-05, "epoch": 9.83969825553984, "percentage": 49.2, "elapsed_time": "1:15:21", "remaining_time": "1:17:49", "throughput": 4643.69, "total_tokens": 20997504} {"current_steps": 20875, "total_steps": 42420, "loss": 0.1763, "lr": 3.0020176821392964e-05, "epoch": 9.842055634134843, "percentage": 49.21, "elapsed_time": "1:15:22", "remaining_time": "1:17:47", "throughput": 4643.75, "total_tokens": 21002752} {"current_steps": 20880, "total_steps": 42420, "loss": 0.0867, "lr": 3.0010099909816374e-05, "epoch": 9.844413012729845, "percentage": 49.22, "elapsed_time": "1:15:23", "remaining_time": "1:17:46", "throughput": 4643.82, "total_tokens": 21008608} {"current_steps": 20885, "total_steps": 42420, "loss": 0.1509, "lr": 3.000002215011493e-05, "epoch": 9.846770391324847, "percentage": 49.23, "elapsed_time": "1:15:24", "remaining_time": "1:17:45", "throughput": 4643.82, "total_tokens": 21012928} {"current_steps": 20890, "total_steps": 42420, "loss": 0.1756, "lr": 2.9989943543994635e-05, "epoch": 9.84912776991985, "percentage": 49.25, "elapsed_time": "1:15:25", "remaining_time": "1:17:44", "throughput": 4643.88, "total_tokens": 21018080} {"current_steps": 20895, "total_steps": 42420, "loss": 0.0921, "lr": 2.997986409316162e-05, "epoch": 9.851485148514852, "percentage": 49.26, "elapsed_time": "1:15:26", "remaining_time": "1:17:43", "throughput": 4643.9, "total_tokens": 21022112} {"current_steps": 20900, "total_steps": 42420, "loss": 0.0953, "lr": 2.9969783799322172e-05, "epoch": 9.853842527109855, "percentage": 49.27, "elapsed_time": "1:15:27", "remaining_time": "1:17:42", "throughput": 4643.93, "total_tokens": 21027712} {"current_steps": 20905, "total_steps": 42420, "loss": 0.0569, "lr": 2.9959702664182704e-05, "epoch": 9.856199905704855, "percentage": 49.28, "elapsed_time": "1:15:28", "remaining_time": "1:17:41", "throughput": 4643.94, "total_tokens": 21032384} {"current_steps": 20910, "total_steps": 42420, "loss": 0.0835, "lr": 2.9949620689449786e-05, "epoch": 9.85855728429986, "percentage": 49.29, "elapsed_time": "1:15:30", "remaining_time": "1:17:40", "throughput": 4644.01, "total_tokens": 21037824} {"current_steps": 20915, "total_steps": 42420, "loss": 0.144, "lr": 2.9939537876830124e-05, "epoch": 9.86091466289486, "percentage": 49.3, "elapsed_time": "1:15:31", "remaining_time": "1:17:38", "throughput": 4644.07, "total_tokens": 21042816} {"current_steps": 20920, "total_steps": 42420, "loss": 0.1557, "lr": 2.9929454228030573e-05, "epoch": 9.863272041489862, "percentage": 49.32, "elapsed_time": "1:15:32", "remaining_time": "1:17:37", "throughput": 4644.11, "total_tokens": 21047520} {"current_steps": 20925, "total_steps": 42420, "loss": 0.0372, "lr": 2.991936974475812e-05, "epoch": 9.865629420084865, "percentage": 49.33, "elapsed_time": "1:15:33", "remaining_time": "1:17:36", "throughput": 4644.13, "total_tokens": 21052512} {"current_steps": 20930, "total_steps": 42420, "loss": 0.0721, "lr": 2.9909284428719886e-05, "epoch": 9.867986798679867, "percentage": 49.34, "elapsed_time": "1:15:34", "remaining_time": "1:17:35", "throughput": 4644.18, "total_tokens": 21057952} {"current_steps": 20935, "total_steps": 42420, "loss": 0.0422, "lr": 2.9899198281623166e-05, "epoch": 9.87034417727487, "percentage": 49.35, "elapsed_time": "1:15:35", "remaining_time": "1:17:34", "throughput": 4644.25, "total_tokens": 21063200} {"current_steps": 20940, "total_steps": 42420, "loss": 0.1933, "lr": 2.988911130517535e-05, "epoch": 9.872701555869872, "percentage": 49.36, "elapsed_time": "1:15:36", "remaining_time": "1:17:33", "throughput": 4644.32, "total_tokens": 21069024} {"current_steps": 20945, "total_steps": 42420, "loss": 0.064, "lr": 2.9879023501084013e-05, "epoch": 9.875058934464874, "percentage": 49.38, "elapsed_time": "1:15:37", "remaining_time": "1:17:32", "throughput": 4644.34, "total_tokens": 21073408} {"current_steps": 20950, "total_steps": 42420, "loss": 0.0818, "lr": 2.9868934871056832e-05, "epoch": 9.877416313059877, "percentage": 49.39, "elapsed_time": "1:15:38", "remaining_time": "1:17:31", "throughput": 4644.4, "total_tokens": 21078688} {"current_steps": 20955, "total_steps": 42420, "loss": 0.1675, "lr": 2.985884541680164e-05, "epoch": 9.87977369165488, "percentage": 49.4, "elapsed_time": "1:15:39", "remaining_time": "1:17:29", "throughput": 4644.42, "total_tokens": 21082912} {"current_steps": 20960, "total_steps": 42420, "loss": 0.1823, "lr": 2.9848755140026423e-05, "epoch": 9.882131070249882, "percentage": 49.41, "elapsed_time": "1:15:40", "remaining_time": "1:17:28", "throughput": 4644.47, "total_tokens": 21088192} {"current_steps": 20965, "total_steps": 42420, "loss": 0.2171, "lr": 2.983866404243929e-05, "epoch": 9.884488448844884, "percentage": 49.42, "elapsed_time": "1:15:41", "remaining_time": "1:17:27", "throughput": 4644.5, "total_tokens": 21092768} {"current_steps": 20970, "total_steps": 42420, "loss": 0.1868, "lr": 2.982857212574849e-05, "epoch": 9.886845827439886, "percentage": 49.43, "elapsed_time": "1:15:42", "remaining_time": "1:17:26", "throughput": 4644.55, "total_tokens": 21097888} {"current_steps": 20975, "total_steps": 42420, "loss": 0.0864, "lr": 2.9818479391662412e-05, "epoch": 9.889203206034889, "percentage": 49.45, "elapsed_time": "1:15:43", "remaining_time": "1:17:25", "throughput": 4644.55, "total_tokens": 21102400} {"current_steps": 20980, "total_steps": 42420, "loss": 0.0867, "lr": 2.9808385841889587e-05, "epoch": 9.891560584629891, "percentage": 49.46, "elapsed_time": "1:15:44", "remaining_time": "1:17:24", "throughput": 4644.64, "total_tokens": 21108160} {"current_steps": 20985, "total_steps": 42420, "loss": 0.0405, "lr": 2.9798291478138685e-05, "epoch": 9.893917963224894, "percentage": 49.47, "elapsed_time": "1:15:45", "remaining_time": "1:17:23", "throughput": 4644.66, "total_tokens": 21113184} {"current_steps": 20990, "total_steps": 42420, "loss": 0.1871, "lr": 2.9788196302118498e-05, "epoch": 9.896275341819896, "percentage": 49.48, "elapsed_time": "1:15:46", "remaining_time": "1:17:22", "throughput": 4644.71, "total_tokens": 21118208} {"current_steps": 20995, "total_steps": 42420, "loss": 0.1184, "lr": 2.9778100315537976e-05, "epoch": 9.898632720414899, "percentage": 49.49, "elapsed_time": "1:15:47", "remaining_time": "1:17:20", "throughput": 4644.76, "total_tokens": 21123488} {"current_steps": 21000, "total_steps": 42420, "loss": 0.093, "lr": 2.9768003520106204e-05, "epoch": 9.900990099009901, "percentage": 49.5, "elapsed_time": "1:15:48", "remaining_time": "1:17:19", "throughput": 4644.82, "total_tokens": 21128800} {"current_steps": 21005, "total_steps": 42420, "loss": 0.1258, "lr": 2.9757905917532393e-05, "epoch": 9.903347477604903, "percentage": 49.52, "elapsed_time": "1:15:49", "remaining_time": "1:17:18", "throughput": 4644.79, "total_tokens": 21132352} {"current_steps": 21010, "total_steps": 42420, "loss": 0.1062, "lr": 2.9747807509525892e-05, "epoch": 9.905704856199906, "percentage": 49.53, "elapsed_time": "1:15:51", "remaining_time": "1:17:17", "throughput": 4644.89, "total_tokens": 21139040} {"current_steps": 21015, "total_steps": 42420, "loss": 0.1406, "lr": 2.973770829779619e-05, "epoch": 9.908062234794908, "percentage": 49.54, "elapsed_time": "1:15:52", "remaining_time": "1:17:16", "throughput": 4644.95, "total_tokens": 21143840} {"current_steps": 21020, "total_steps": 42420, "loss": 0.1104, "lr": 2.9727608284052917e-05, "epoch": 9.91041961338991, "percentage": 49.55, "elapsed_time": "1:15:53", "remaining_time": "1:17:15", "throughput": 4645.03, "total_tokens": 21149664} {"current_steps": 21025, "total_steps": 42420, "loss": 0.0649, "lr": 2.9717507470005833e-05, "epoch": 9.912776991984913, "percentage": 49.56, "elapsed_time": "1:15:54", "remaining_time": "1:17:14", "throughput": 4645.13, "total_tokens": 21156064} {"current_steps": 21030, "total_steps": 42420, "loss": 0.2231, "lr": 2.9707405857364835e-05, "epoch": 9.915134370579915, "percentage": 49.58, "elapsed_time": "1:15:55", "remaining_time": "1:17:13", "throughput": 4645.19, "total_tokens": 21160928} {"current_steps": 21035, "total_steps": 42420, "loss": 0.1484, "lr": 2.9697303447839946e-05, "epoch": 9.917491749174918, "percentage": 49.59, "elapsed_time": "1:15:56", "remaining_time": "1:17:12", "throughput": 4645.21, "total_tokens": 21165248} {"current_steps": 21040, "total_steps": 42420, "loss": 0.1992, "lr": 2.9687200243141346e-05, "epoch": 9.91984912776992, "percentage": 49.6, "elapsed_time": "1:15:57", "remaining_time": "1:17:10", "throughput": 4645.27, "total_tokens": 21170112} {"current_steps": 21045, "total_steps": 42420, "loss": 0.1284, "lr": 2.9677096244979323e-05, "epoch": 9.922206506364923, "percentage": 49.61, "elapsed_time": "1:15:58", "remaining_time": "1:17:09", "throughput": 4645.35, "total_tokens": 21175584} {"current_steps": 21050, "total_steps": 42420, "loss": 0.0747, "lr": 2.966699145506433e-05, "epoch": 9.924563884959925, "percentage": 49.62, "elapsed_time": "1:15:59", "remaining_time": "1:17:08", "throughput": 4645.36, "total_tokens": 21179744} {"current_steps": 21055, "total_steps": 42420, "loss": 0.2991, "lr": 2.965688587510691e-05, "epoch": 9.926921263554927, "percentage": 49.63, "elapsed_time": "1:16:00", "remaining_time": "1:17:07", "throughput": 4645.41, "total_tokens": 21184704} {"current_steps": 21060, "total_steps": 42420, "loss": 0.0972, "lr": 2.9646779506817785e-05, "epoch": 9.92927864214993, "percentage": 49.65, "elapsed_time": "1:16:01", "remaining_time": "1:17:06", "throughput": 4645.47, "total_tokens": 21189664} {"current_steps": 21065, "total_steps": 42420, "loss": 0.1119, "lr": 2.963667235190779e-05, "epoch": 9.931636020744932, "percentage": 49.66, "elapsed_time": "1:16:02", "remaining_time": "1:17:05", "throughput": 4645.47, "total_tokens": 21194240} {"current_steps": 21070, "total_steps": 42420, "loss": 0.078, "lr": 2.9626564412087892e-05, "epoch": 9.933993399339935, "percentage": 49.67, "elapsed_time": "1:16:03", "remaining_time": "1:17:04", "throughput": 4645.52, "total_tokens": 21199552} {"current_steps": 21075, "total_steps": 42420, "loss": 0.1068, "lr": 2.9616455689069194e-05, "epoch": 9.936350777934937, "percentage": 49.68, "elapsed_time": "1:16:04", "remaining_time": "1:17:02", "throughput": 4645.47, "total_tokens": 21203232} {"current_steps": 21080, "total_steps": 42420, "loss": 0.0492, "lr": 2.9606346184562927e-05, "epoch": 9.93870815652994, "percentage": 49.69, "elapsed_time": "1:16:05", "remaining_time": "1:17:01", "throughput": 4645.53, "total_tokens": 21209696} {"current_steps": 21085, "total_steps": 42420, "loss": 0.0232, "lr": 2.9596235900280463e-05, "epoch": 9.941065535124942, "percentage": 49.71, "elapsed_time": "1:16:06", "remaining_time": "1:17:00", "throughput": 4645.57, "total_tokens": 21214688} {"current_steps": 21090, "total_steps": 42420, "loss": 0.1123, "lr": 2.9586124837933303e-05, "epoch": 9.943422913719944, "percentage": 49.72, "elapsed_time": "1:16:07", "remaining_time": "1:16:59", "throughput": 4645.67, "total_tokens": 21221184} {"current_steps": 21095, "total_steps": 42420, "loss": 0.1217, "lr": 2.9576012999233078e-05, "epoch": 9.945780292314947, "percentage": 49.73, "elapsed_time": "1:16:08", "remaining_time": "1:16:58", "throughput": 4645.68, "total_tokens": 21225408} {"current_steps": 21100, "total_steps": 42420, "loss": 0.1691, "lr": 2.9565900385891542e-05, "epoch": 9.948137670909949, "percentage": 49.74, "elapsed_time": "1:16:09", "remaining_time": "1:16:57", "throughput": 4645.71, "total_tokens": 21230400} {"current_steps": 21105, "total_steps": 42420, "loss": 0.1524, "lr": 2.95557869996206e-05, "epoch": 9.950495049504951, "percentage": 49.75, "elapsed_time": "1:16:10", "remaining_time": "1:16:56", "throughput": 4645.75, "total_tokens": 21234752} {"current_steps": 21110, "total_steps": 42420, "loss": 0.1367, "lr": 2.9545672842132273e-05, "epoch": 9.952852428099952, "percentage": 49.76, "elapsed_time": "1:16:11", "remaining_time": "1:16:55", "throughput": 4645.8, "total_tokens": 21240192} {"current_steps": 21115, "total_steps": 42420, "loss": 0.1459, "lr": 2.953555791513871e-05, "epoch": 9.955209806694956, "percentage": 49.78, "elapsed_time": "1:16:12", "remaining_time": "1:16:54", "throughput": 4645.8, "total_tokens": 21244608} {"current_steps": 21120, "total_steps": 42420, "loss": 0.0826, "lr": 2.9525442220352208e-05, "epoch": 9.957567185289957, "percentage": 49.79, "elapsed_time": "1:16:14", "remaining_time": "1:16:53", "throughput": 4645.9, "total_tokens": 21251680} {"current_steps": 21125, "total_steps": 42420, "loss": 0.024, "lr": 2.9515325759485167e-05, "epoch": 9.95992456388496, "percentage": 49.8, "elapsed_time": "1:16:15", "remaining_time": "1:16:52", "throughput": 4645.93, "total_tokens": 21257600} {"current_steps": 21130, "total_steps": 42420, "loss": 0.0902, "lr": 2.950520853425015e-05, "epoch": 9.962281942479962, "percentage": 49.81, "elapsed_time": "1:16:16", "remaining_time": "1:16:51", "throughput": 4645.97, "total_tokens": 21262336} {"current_steps": 21135, "total_steps": 42420, "loss": 0.0567, "lr": 2.9495090546359816e-05, "epoch": 9.964639321074964, "percentage": 49.82, "elapsed_time": "1:16:17", "remaining_time": "1:16:50", "throughput": 4645.98, "total_tokens": 21267136} {"current_steps": 21140, "total_steps": 42420, "loss": 0.0401, "lr": 2.9484971797526972e-05, "epoch": 9.966996699669966, "percentage": 49.83, "elapsed_time": "1:16:18", "remaining_time": "1:16:48", "throughput": 4646.03, "total_tokens": 21271872} {"current_steps": 21145, "total_steps": 42420, "loss": 0.0665, "lr": 2.947485228946456e-05, "epoch": 9.969354078264969, "percentage": 49.85, "elapsed_time": "1:16:19", "remaining_time": "1:16:47", "throughput": 4646.08, "total_tokens": 21277056} {"current_steps": 21150, "total_steps": 42420, "loss": 0.106, "lr": 2.946473202388563e-05, "epoch": 9.971711456859971, "percentage": 49.86, "elapsed_time": "1:16:20", "remaining_time": "1:16:46", "throughput": 4646.15, "total_tokens": 21281888} {"current_steps": 21155, "total_steps": 42420, "loss": 0.0906, "lr": 2.945461100250338e-05, "epoch": 9.974068835454974, "percentage": 49.87, "elapsed_time": "1:16:21", "remaining_time": "1:16:45", "throughput": 4646.24, "total_tokens": 21288128} {"current_steps": 21160, "total_steps": 42420, "loss": 0.1743, "lr": 2.9444489227031124e-05, "epoch": 9.976426214049976, "percentage": 49.88, "elapsed_time": "1:16:22", "remaining_time": "1:16:44", "throughput": 4646.28, "total_tokens": 21293280} {"current_steps": 21165, "total_steps": 42420, "loss": 0.0838, "lr": 2.9434366699182297e-05, "epoch": 9.978783592644978, "percentage": 49.89, "elapsed_time": "1:16:23", "remaining_time": "1:16:43", "throughput": 4646.35, "total_tokens": 21298880} {"current_steps": 21170, "total_steps": 42420, "loss": 0.0944, "lr": 2.9424243420670483e-05, "epoch": 9.98114097123998, "percentage": 49.91, "elapsed_time": "1:16:25", "remaining_time": "1:16:42", "throughput": 4646.43, "total_tokens": 21304480} {"current_steps": 21175, "total_steps": 42420, "loss": 0.0871, "lr": 2.9414119393209376e-05, "epoch": 9.983498349834983, "percentage": 49.92, "elapsed_time": "1:16:26", "remaining_time": "1:16:41", "throughput": 4646.42, "total_tokens": 21309120} {"current_steps": 21180, "total_steps": 42420, "loss": 0.0589, "lr": 2.9403994618512805e-05, "epoch": 9.985855728429986, "percentage": 49.93, "elapsed_time": "1:16:27", "remaining_time": "1:16:40", "throughput": 4646.46, "total_tokens": 21314048} {"current_steps": 21185, "total_steps": 42420, "loss": 0.1725, "lr": 2.939386909829472e-05, "epoch": 9.988213107024988, "percentage": 49.94, "elapsed_time": "1:16:28", "remaining_time": "1:16:39", "throughput": 4646.49, "total_tokens": 21319552} {"current_steps": 21190, "total_steps": 42420, "loss": 0.0354, "lr": 2.9383742834269197e-05, "epoch": 9.99057048561999, "percentage": 49.95, "elapsed_time": "1:16:29", "remaining_time": "1:16:37", "throughput": 4646.49, "total_tokens": 21323808} {"current_steps": 21195, "total_steps": 42420, "loss": 0.0907, "lr": 2.9373615828150452e-05, "epoch": 9.992927864214993, "percentage": 49.96, "elapsed_time": "1:16:30", "remaining_time": "1:16:36", "throughput": 4646.54, "total_tokens": 21329056} {"current_steps": 21200, "total_steps": 42420, "loss": 0.0586, "lr": 2.9363488081652802e-05, "epoch": 9.995285242809995, "percentage": 49.98, "elapsed_time": "1:16:31", "remaining_time": "1:16:35", "throughput": 4646.52, "total_tokens": 21333280} {"current_steps": 21205, "total_steps": 42420, "loss": 0.2289, "lr": 2.9353359596490705e-05, "epoch": 9.997642621404998, "percentage": 49.99, "elapsed_time": "1:16:32", "remaining_time": "1:16:34", "throughput": 4646.53, "total_tokens": 21337632} {"current_steps": 21210, "total_steps": 42420, "loss": 0.0432, "lr": 2.9343230374378743e-05, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "1:16:33", "remaining_time": "1:16:33", "throughput": 4646.41, "total_tokens": 21342336} {"current_steps": 21210, "total_steps": 42420, "eval_loss": 0.15169008076190948, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "1:16:48", "remaining_time": "1:16:48", "throughput": 4631.15, "total_tokens": 21342336} {"current_steps": 21215, "total_steps": 42420, "loss": 0.2246, "lr": 2.933310041703163e-05, "epoch": 10.002357378595002, "percentage": 50.01, "elapsed_time": "1:16:51", "remaining_time": "1:16:49", "throughput": 4629.57, "total_tokens": 21348032} {"current_steps": 21220, "total_steps": 42420, "loss": 0.1716, "lr": 2.9322969726164184e-05, "epoch": 10.004714757190005, "percentage": 50.02, "elapsed_time": "1:16:52", "remaining_time": "1:16:48", "throughput": 4629.63, "total_tokens": 21353856} {"current_steps": 21225, "total_steps": 42420, "loss": 0.1227, "lr": 2.931283830349136e-05, "epoch": 10.007072135785007, "percentage": 50.04, "elapsed_time": "1:16:53", "remaining_time": "1:16:47", "throughput": 4629.68, "total_tokens": 21360096} {"current_steps": 21230, "total_steps": 42420, "loss": 0.2034, "lr": 2.9302706150728242e-05, "epoch": 10.00942951438001, "percentage": 50.05, "elapsed_time": "1:16:54", "remaining_time": "1:16:46", "throughput": 4629.74, "total_tokens": 21365952} {"current_steps": 21235, "total_steps": 42420, "loss": 0.1473, "lr": 2.929257326959003e-05, "epoch": 10.011786892975012, "percentage": 50.06, "elapsed_time": "1:16:55", "remaining_time": "1:16:45", "throughput": 4629.74, "total_tokens": 21370528} {"current_steps": 21240, "total_steps": 42420, "loss": 0.0987, "lr": 2.928243966179205e-05, "epoch": 10.014144271570014, "percentage": 50.07, "elapsed_time": "1:16:57", "remaining_time": "1:16:44", "throughput": 4629.81, "total_tokens": 21376384} {"current_steps": 21245, "total_steps": 42420, "loss": 0.1006, "lr": 2.9272305329049736e-05, "epoch": 10.016501650165017, "percentage": 50.08, "elapsed_time": "1:16:58", "remaining_time": "1:16:42", "throughput": 4629.85, "total_tokens": 21381056} {"current_steps": 21250, "total_steps": 42420, "loss": 0.0829, "lr": 2.9262170273078676e-05, "epoch": 10.01885902876002, "percentage": 50.09, "elapsed_time": "1:16:59", "remaining_time": "1:16:41", "throughput": 4629.86, "total_tokens": 21385344} {"current_steps": 21255, "total_steps": 42420, "loss": 0.031, "lr": 2.925203449559456e-05, "epoch": 10.021216407355022, "percentage": 50.11, "elapsed_time": "1:17:00", "remaining_time": "1:16:40", "throughput": 4629.91, "total_tokens": 21390784} {"current_steps": 21260, "total_steps": 42420, "loss": 0.1632, "lr": 2.9241897998313195e-05, "epoch": 10.023573785950024, "percentage": 50.12, "elapsed_time": "1:17:01", "remaining_time": "1:16:39", "throughput": 4629.9, "total_tokens": 21395200} {"current_steps": 21265, "total_steps": 42420, "loss": 0.0696, "lr": 2.9231760782950525e-05, "epoch": 10.025931164545026, "percentage": 50.13, "elapsed_time": "1:17:02", "remaining_time": "1:16:38", "throughput": 4629.94, "total_tokens": 21400512} {"current_steps": 21270, "total_steps": 42420, "loss": 0.2323, "lr": 2.92216228512226e-05, "epoch": 10.028288543140029, "percentage": 50.14, "elapsed_time": "1:17:03", "remaining_time": "1:16:37", "throughput": 4630.0, "total_tokens": 21405792} {"current_steps": 21275, "total_steps": 42420, "loss": 0.1555, "lr": 2.9211484204845617e-05, "epoch": 10.030645921735031, "percentage": 50.15, "elapsed_time": "1:17:04", "remaining_time": "1:16:36", "throughput": 4630.09, "total_tokens": 21413696} {"current_steps": 21280, "total_steps": 42420, "loss": 0.2099, "lr": 2.9201344845535862e-05, "epoch": 10.033003300330034, "percentage": 50.17, "elapsed_time": "1:17:05", "remaining_time": "1:16:35", "throughput": 4630.12, "total_tokens": 21418400} {"current_steps": 21285, "total_steps": 42420, "loss": 0.1004, "lr": 2.919120477500975e-05, "epoch": 10.035360678925036, "percentage": 50.18, "elapsed_time": "1:17:06", "remaining_time": "1:16:34", "throughput": 4630.17, "total_tokens": 21423520} {"current_steps": 21290, "total_steps": 42420, "loss": 0.1882, "lr": 2.9181063994983836e-05, "epoch": 10.037718057520038, "percentage": 50.19, "elapsed_time": "1:17:07", "remaining_time": "1:16:33", "throughput": 4630.22, "total_tokens": 21428512} {"current_steps": 21295, "total_steps": 42420, "loss": 0.0786, "lr": 2.917092250717478e-05, "epoch": 10.04007543611504, "percentage": 50.2, "elapsed_time": "1:17:09", "remaining_time": "1:16:32", "throughput": 4630.25, "total_tokens": 21433664} {"current_steps": 21300, "total_steps": 42420, "loss": 0.0376, "lr": 2.9160780313299363e-05, "epoch": 10.042432814710043, "percentage": 50.21, "elapsed_time": "1:17:10", "remaining_time": "1:16:30", "throughput": 4630.3, "total_tokens": 21438624} {"current_steps": 21305, "total_steps": 42420, "loss": 0.0651, "lr": 2.915063741507448e-05, "epoch": 10.044790193305046, "percentage": 50.22, "elapsed_time": "1:17:11", "remaining_time": "1:16:29", "throughput": 4630.34, "total_tokens": 21443872} {"current_steps": 21310, "total_steps": 42420, "loss": 0.0269, "lr": 2.9140493814217157e-05, "epoch": 10.047147571900048, "percentage": 50.24, "elapsed_time": "1:17:12", "remaining_time": "1:16:28", "throughput": 4630.38, "total_tokens": 21448704} {"current_steps": 21315, "total_steps": 42420, "loss": 0.1096, "lr": 2.9130349512444544e-05, "epoch": 10.049504950495049, "percentage": 50.25, "elapsed_time": "1:17:13", "remaining_time": "1:16:27", "throughput": 4630.43, "total_tokens": 21453664} {"current_steps": 21320, "total_steps": 42420, "loss": 0.1962, "lr": 2.9120204511473876e-05, "epoch": 10.051862329090051, "percentage": 50.26, "elapsed_time": "1:17:14", "remaining_time": "1:16:26", "throughput": 4630.45, "total_tokens": 21458400} {"current_steps": 21325, "total_steps": 42420, "loss": 0.1231, "lr": 2.911005881302254e-05, "epoch": 10.054219707685053, "percentage": 50.27, "elapsed_time": "1:17:15", "remaining_time": "1:16:25", "throughput": 4630.48, "total_tokens": 21464032} {"current_steps": 21330, "total_steps": 42420, "loss": 0.0313, "lr": 2.9099912418808033e-05, "epoch": 10.056577086280056, "percentage": 50.28, "elapsed_time": "1:17:16", "remaining_time": "1:16:24", "throughput": 4630.53, "total_tokens": 21468992} {"current_steps": 21335, "total_steps": 42420, "loss": 0.1632, "lr": 2.9089765330547975e-05, "epoch": 10.058934464875058, "percentage": 50.29, "elapsed_time": "1:17:17", "remaining_time": "1:16:23", "throughput": 4630.57, "total_tokens": 21473856} {"current_steps": 21340, "total_steps": 42420, "loss": 0.1128, "lr": 2.907961754996008e-05, "epoch": 10.06129184347006, "percentage": 50.31, "elapsed_time": "1:17:18", "remaining_time": "1:16:22", "throughput": 4630.65, "total_tokens": 21479808} {"current_steps": 21345, "total_steps": 42420, "loss": 0.0482, "lr": 2.90694690787622e-05, "epoch": 10.063649222065063, "percentage": 50.32, "elapsed_time": "1:17:19", "remaining_time": "1:16:21", "throughput": 4630.67, "total_tokens": 21485440} {"current_steps": 21350, "total_steps": 42420, "loss": 0.0351, "lr": 2.90593199186723e-05, "epoch": 10.066006600660065, "percentage": 50.33, "elapsed_time": "1:17:20", "remaining_time": "1:16:20", "throughput": 4630.7, "total_tokens": 21490624} {"current_steps": 21355, "total_steps": 42420, "loss": 0.0949, "lr": 2.9049170071408466e-05, "epoch": 10.068363979255068, "percentage": 50.34, "elapsed_time": "1:17:21", "remaining_time": "1:16:18", "throughput": 4630.71, "total_tokens": 21495424} {"current_steps": 21360, "total_steps": 42420, "loss": 0.0871, "lr": 2.9039019538688895e-05, "epoch": 10.07072135785007, "percentage": 50.35, "elapsed_time": "1:17:22", "remaining_time": "1:16:17", "throughput": 4630.75, "total_tokens": 21500160} {"current_steps": 21365, "total_steps": 42420, "loss": 0.0567, "lr": 2.9028868322231884e-05, "epoch": 10.073078736445073, "percentage": 50.37, "elapsed_time": "1:17:24", "remaining_time": "1:16:16", "throughput": 4630.82, "total_tokens": 21505696} {"current_steps": 21370, "total_steps": 42420, "loss": 0.2149, "lr": 2.9018716423755877e-05, "epoch": 10.075436115040075, "percentage": 50.38, "elapsed_time": "1:17:25", "remaining_time": "1:16:15", "throughput": 4630.87, "total_tokens": 21511232} {"current_steps": 21375, "total_steps": 42420, "loss": 0.1439, "lr": 2.9008563844979408e-05, "epoch": 10.077793493635077, "percentage": 50.39, "elapsed_time": "1:17:26", "remaining_time": "1:16:14", "throughput": 4630.92, "total_tokens": 21516256} {"current_steps": 21380, "total_steps": 42420, "loss": 0.2781, "lr": 2.899841058762115e-05, "epoch": 10.08015087223008, "percentage": 50.4, "elapsed_time": "1:17:27", "remaining_time": "1:16:13", "throughput": 4630.97, "total_tokens": 21521568} {"current_steps": 21385, "total_steps": 42420, "loss": 0.2595, "lr": 2.898825665339987e-05, "epoch": 10.082508250825082, "percentage": 50.41, "elapsed_time": "1:17:28", "remaining_time": "1:16:12", "throughput": 4631.08, "total_tokens": 21528320} {"current_steps": 21390, "total_steps": 42420, "loss": 0.1523, "lr": 2.897810204403445e-05, "epoch": 10.084865629420085, "percentage": 50.42, "elapsed_time": "1:17:29", "remaining_time": "1:16:11", "throughput": 4631.12, "total_tokens": 21533216} {"current_steps": 21395, "total_steps": 42420, "loss": 0.1324, "lr": 2.89679467612439e-05, "epoch": 10.087223008015087, "percentage": 50.44, "elapsed_time": "1:17:30", "remaining_time": "1:16:10", "throughput": 4631.21, "total_tokens": 21539552} {"current_steps": 21400, "total_steps": 42420, "loss": 0.1056, "lr": 2.8957790806747337e-05, "epoch": 10.08958038661009, "percentage": 50.45, "elapsed_time": "1:17:31", "remaining_time": "1:16:09", "throughput": 4631.2, "total_tokens": 21544128} {"current_steps": 21405, "total_steps": 42420, "loss": 0.1545, "lr": 2.8947634182263984e-05, "epoch": 10.091937765205092, "percentage": 50.46, "elapsed_time": "1:17:33", "remaining_time": "1:16:08", "throughput": 4631.33, "total_tokens": 21551232} {"current_steps": 21410, "total_steps": 42420, "loss": 0.293, "lr": 2.8937476889513194e-05, "epoch": 10.094295143800094, "percentage": 50.47, "elapsed_time": "1:17:34", "remaining_time": "1:16:07", "throughput": 4631.33, "total_tokens": 21556256} {"current_steps": 21415, "total_steps": 42420, "loss": 0.0999, "lr": 2.8927318930214414e-05, "epoch": 10.096652522395097, "percentage": 50.48, "elapsed_time": "1:17:35", "remaining_time": "1:16:06", "throughput": 4631.38, "total_tokens": 21561184} {"current_steps": 21420, "total_steps": 42420, "loss": 0.1105, "lr": 2.8917160306087233e-05, "epoch": 10.099009900990099, "percentage": 50.5, "elapsed_time": "1:17:36", "remaining_time": "1:16:05", "throughput": 4631.4, "total_tokens": 21565888} {"current_steps": 21425, "total_steps": 42420, "loss": 0.1682, "lr": 2.8907001018851317e-05, "epoch": 10.101367279585101, "percentage": 50.51, "elapsed_time": "1:17:37", "remaining_time": "1:16:04", "throughput": 4631.49, "total_tokens": 21571712} {"current_steps": 21430, "total_steps": 42420, "loss": 0.1516, "lr": 2.8896841070226465e-05, "epoch": 10.103724658180104, "percentage": 50.52, "elapsed_time": "1:17:38", "remaining_time": "1:16:03", "throughput": 4631.54, "total_tokens": 21577120} {"current_steps": 21435, "total_steps": 42420, "loss": 0.3188, "lr": 2.888668046193258e-05, "epoch": 10.106082036775106, "percentage": 50.53, "elapsed_time": "1:17:39", "remaining_time": "1:16:02", "throughput": 4631.6, "total_tokens": 21582496} {"current_steps": 21440, "total_steps": 42420, "loss": 0.1468, "lr": 2.8876519195689696e-05, "epoch": 10.108439415370109, "percentage": 50.54, "elapsed_time": "1:17:40", "remaining_time": "1:16:00", "throughput": 4631.64, "total_tokens": 21587200} {"current_steps": 21445, "total_steps": 42420, "loss": 0.0438, "lr": 2.8866357273217925e-05, "epoch": 10.110796793965111, "percentage": 50.55, "elapsed_time": "1:17:41", "remaining_time": "1:15:59", "throughput": 4631.66, "total_tokens": 21592160} {"current_steps": 21450, "total_steps": 42420, "loss": 0.0476, "lr": 2.8856194696237515e-05, "epoch": 10.113154172560114, "percentage": 50.57, "elapsed_time": "1:17:42", "remaining_time": "1:15:58", "throughput": 4631.72, "total_tokens": 21597344} {"current_steps": 21455, "total_steps": 42420, "loss": 0.091, "lr": 2.8846031466468816e-05, "epoch": 10.115511551155116, "percentage": 50.58, "elapsed_time": "1:17:43", "remaining_time": "1:15:57", "throughput": 4631.76, "total_tokens": 21602176} {"current_steps": 21460, "total_steps": 42420, "loss": 0.096, "lr": 2.8835867585632294e-05, "epoch": 10.117868929750118, "percentage": 50.59, "elapsed_time": "1:17:44", "remaining_time": "1:15:56", "throughput": 4631.75, "total_tokens": 21605984} {"current_steps": 21465, "total_steps": 42420, "loss": 0.1575, "lr": 2.8825703055448517e-05, "epoch": 10.12022630834512, "percentage": 50.6, "elapsed_time": "1:17:46", "remaining_time": "1:15:55", "throughput": 4631.82, "total_tokens": 21612096} {"current_steps": 21470, "total_steps": 42420, "loss": 0.1231, "lr": 2.8815537877638172e-05, "epoch": 10.122583686940123, "percentage": 50.61, "elapsed_time": "1:17:47", "remaining_time": "1:15:54", "throughput": 4631.89, "total_tokens": 21617600} {"current_steps": 21475, "total_steps": 42420, "loss": 0.109, "lr": 2.8805372053922043e-05, "epoch": 10.124941065535126, "percentage": 50.62, "elapsed_time": "1:17:48", "remaining_time": "1:15:53", "throughput": 4632.01, "total_tokens": 21624576} {"current_steps": 21480, "total_steps": 42420, "loss": 0.0656, "lr": 2.8795205586021044e-05, "epoch": 10.127298444130128, "percentage": 50.64, "elapsed_time": "1:17:49", "remaining_time": "1:15:52", "throughput": 4632.07, "total_tokens": 21630048} {"current_steps": 21485, "total_steps": 42420, "loss": 0.0469, "lr": 2.8785038475656173e-05, "epoch": 10.12965582272513, "percentage": 50.65, "elapsed_time": "1:17:50", "remaining_time": "1:15:51", "throughput": 4632.13, "total_tokens": 21634752} {"current_steps": 21490, "total_steps": 42420, "loss": 0.1039, "lr": 2.8774870724548557e-05, "epoch": 10.132013201320133, "percentage": 50.66, "elapsed_time": "1:17:51", "remaining_time": "1:15:49", "throughput": 4632.19, "total_tokens": 21639840} {"current_steps": 21495, "total_steps": 42420, "loss": 0.0216, "lr": 2.876470233441942e-05, "epoch": 10.134370579915135, "percentage": 50.67, "elapsed_time": "1:17:52", "remaining_time": "1:15:48", "throughput": 4632.24, "total_tokens": 21644352} {"current_steps": 21500, "total_steps": 42420, "loss": 0.16, "lr": 2.87545333069901e-05, "epoch": 10.136727958510138, "percentage": 50.68, "elapsed_time": "1:17:53", "remaining_time": "1:15:47", "throughput": 4632.29, "total_tokens": 21649184} {"current_steps": 21505, "total_steps": 42420, "loss": 0.1049, "lr": 2.874436364398204e-05, "epoch": 10.13908533710514, "percentage": 50.7, "elapsed_time": "1:17:54", "remaining_time": "1:15:46", "throughput": 4632.3, "total_tokens": 21653632} {"current_steps": 21510, "total_steps": 42420, "loss": 0.0801, "lr": 2.8734193347116793e-05, "epoch": 10.14144271570014, "percentage": 50.71, "elapsed_time": "1:17:55", "remaining_time": "1:15:45", "throughput": 4632.36, "total_tokens": 21659264} {"current_steps": 21515, "total_steps": 42420, "loss": 0.1449, "lr": 2.872402241811601e-05, "epoch": 10.143800094295143, "percentage": 50.72, "elapsed_time": "1:17:56", "remaining_time": "1:15:44", "throughput": 4632.41, "total_tokens": 21664224} {"current_steps": 21520, "total_steps": 42420, "loss": 0.1851, "lr": 2.8713850858701463e-05, "epoch": 10.146157472890145, "percentage": 50.73, "elapsed_time": "1:17:57", "remaining_time": "1:15:43", "throughput": 4632.48, "total_tokens": 21669952} {"current_steps": 21525, "total_steps": 42420, "loss": 0.1505, "lr": 2.8703678670595023e-05, "epoch": 10.148514851485148, "percentage": 50.74, "elapsed_time": "1:17:58", "remaining_time": "1:15:41", "throughput": 4632.51, "total_tokens": 21674432} {"current_steps": 21530, "total_steps": 42420, "loss": 0.2027, "lr": 2.8693505855518672e-05, "epoch": 10.15087223008015, "percentage": 50.75, "elapsed_time": "1:17:59", "remaining_time": "1:15:40", "throughput": 4632.61, "total_tokens": 21680352} {"current_steps": 21535, "total_steps": 42420, "loss": 0.0889, "lr": 2.8683332415194485e-05, "epoch": 10.153229608675153, "percentage": 50.77, "elapsed_time": "1:18:01", "remaining_time": "1:15:39", "throughput": 4632.67, "total_tokens": 21685600} {"current_steps": 21540, "total_steps": 42420, "loss": 0.1461, "lr": 2.8673158351344666e-05, "epoch": 10.155586987270155, "percentage": 50.78, "elapsed_time": "1:18:02", "remaining_time": "1:15:38", "throughput": 4632.74, "total_tokens": 21690912} {"current_steps": 21545, "total_steps": 42420, "loss": 0.1025, "lr": 2.8662983665691508e-05, "epoch": 10.157944365865157, "percentage": 50.79, "elapsed_time": "1:18:03", "remaining_time": "1:15:37", "throughput": 4632.74, "total_tokens": 21695488} {"current_steps": 21550, "total_steps": 42420, "loss": 0.0394, "lr": 2.86528083599574e-05, "epoch": 10.16030174446016, "percentage": 50.8, "elapsed_time": "1:18:04", "remaining_time": "1:15:36", "throughput": 4632.81, "total_tokens": 21700352} {"current_steps": 21555, "total_steps": 42420, "loss": 0.2241, "lr": 2.8642632435864862e-05, "epoch": 10.162659123055162, "percentage": 50.81, "elapsed_time": "1:18:05", "remaining_time": "1:15:35", "throughput": 4632.91, "total_tokens": 21708160} {"current_steps": 21560, "total_steps": 42420, "loss": 0.0339, "lr": 2.86324558951365e-05, "epoch": 10.165016501650165, "percentage": 50.83, "elapsed_time": "1:18:06", "remaining_time": "1:15:34", "throughput": 4632.93, "total_tokens": 21712448} {"current_steps": 21565, "total_steps": 42420, "loss": 0.0705, "lr": 2.8622278739495035e-05, "epoch": 10.167373880245167, "percentage": 50.84, "elapsed_time": "1:18:07", "remaining_time": "1:15:33", "throughput": 4632.96, "total_tokens": 21717184} {"current_steps": 21570, "total_steps": 42420, "loss": 0.073, "lr": 2.861210097066328e-05, "epoch": 10.16973125884017, "percentage": 50.85, "elapsed_time": "1:18:08", "remaining_time": "1:15:32", "throughput": 4633.01, "total_tokens": 21723456} {"current_steps": 21575, "total_steps": 42420, "loss": 0.1005, "lr": 2.8601922590364154e-05, "epoch": 10.172088637435172, "percentage": 50.86, "elapsed_time": "1:18:10", "remaining_time": "1:15:31", "throughput": 4633.1, "total_tokens": 21730048} {"current_steps": 21580, "total_steps": 42420, "loss": 0.1536, "lr": 2.8591743600320697e-05, "epoch": 10.174446016030174, "percentage": 50.87, "elapsed_time": "1:18:11", "remaining_time": "1:15:30", "throughput": 4633.18, "total_tokens": 21734848} {"current_steps": 21585, "total_steps": 42420, "loss": 0.0877, "lr": 2.8581564002256034e-05, "epoch": 10.176803394625177, "percentage": 50.88, "elapsed_time": "1:18:12", "remaining_time": "1:15:29", "throughput": 4633.22, "total_tokens": 21739584} {"current_steps": 21590, "total_steps": 42420, "loss": 0.0617, "lr": 2.8571383797893397e-05, "epoch": 10.179160773220179, "percentage": 50.9, "elapsed_time": "1:18:13", "remaining_time": "1:15:27", "throughput": 4633.29, "total_tokens": 21744384} {"current_steps": 21595, "total_steps": 42420, "loss": 0.111, "lr": 2.8561202988956115e-05, "epoch": 10.181518151815181, "percentage": 50.91, "elapsed_time": "1:18:14", "remaining_time": "1:15:26", "throughput": 4633.33, "total_tokens": 21749920} {"current_steps": 21600, "total_steps": 42420, "loss": 0.0765, "lr": 2.8551021577167636e-05, "epoch": 10.183875530410184, "percentage": 50.92, "elapsed_time": "1:18:15", "remaining_time": "1:15:25", "throughput": 4633.34, "total_tokens": 21754176} {"current_steps": 21605, "total_steps": 42420, "loss": 0.1733, "lr": 2.8540839564251502e-05, "epoch": 10.186232909005186, "percentage": 50.93, "elapsed_time": "1:18:16", "remaining_time": "1:15:24", "throughput": 4633.41, "total_tokens": 21759712} {"current_steps": 21610, "total_steps": 42420, "loss": 0.1566, "lr": 2.853065695193135e-05, "epoch": 10.188590287600189, "percentage": 50.94, "elapsed_time": "1:18:17", "remaining_time": "1:15:23", "throughput": 4633.44, "total_tokens": 21764256} {"current_steps": 21615, "total_steps": 42420, "loss": 0.0759, "lr": 2.852047374193092e-05, "epoch": 10.190947666195191, "percentage": 50.95, "elapsed_time": "1:18:18", "remaining_time": "1:15:22", "throughput": 4633.49, "total_tokens": 21768704} {"current_steps": 21620, "total_steps": 42420, "loss": 0.0609, "lr": 2.8510289935974057e-05, "epoch": 10.193305044790193, "percentage": 50.97, "elapsed_time": "1:18:19", "remaining_time": "1:15:20", "throughput": 4633.54, "total_tokens": 21773728} {"current_steps": 21625, "total_steps": 42420, "loss": 0.134, "lr": 2.850010553578471e-05, "epoch": 10.195662423385196, "percentage": 50.98, "elapsed_time": "1:18:20", "remaining_time": "1:15:19", "throughput": 4633.61, "total_tokens": 21778784} {"current_steps": 21630, "total_steps": 42420, "loss": 0.1385, "lr": 2.848992054308693e-05, "epoch": 10.198019801980198, "percentage": 50.99, "elapsed_time": "1:18:21", "remaining_time": "1:15:18", "throughput": 4633.66, "total_tokens": 21784704} {"current_steps": 21635, "total_steps": 42420, "loss": 0.0463, "lr": 2.8479734959604846e-05, "epoch": 10.2003771805752, "percentage": 51.0, "elapsed_time": "1:18:22", "remaining_time": "1:15:17", "throughput": 4633.71, "total_tokens": 21789280} {"current_steps": 21640, "total_steps": 42420, "loss": 0.1056, "lr": 2.8469548787062727e-05, "epoch": 10.202734559170203, "percentage": 51.01, "elapsed_time": "1:18:23", "remaining_time": "1:15:16", "throughput": 4633.65, "total_tokens": 21792992} {"current_steps": 21645, "total_steps": 42420, "loss": 0.095, "lr": 2.84593620271849e-05, "epoch": 10.205091937765205, "percentage": 51.03, "elapsed_time": "1:18:24", "remaining_time": "1:15:15", "throughput": 4633.64, "total_tokens": 21797696} {"current_steps": 21650, "total_steps": 42420, "loss": 0.1014, "lr": 2.8449174681695827e-05, "epoch": 10.207449316360208, "percentage": 51.04, "elapsed_time": "1:18:25", "remaining_time": "1:15:13", "throughput": 4633.68, "total_tokens": 21802208} {"current_steps": 21655, "total_steps": 42420, "loss": 0.0417, "lr": 2.8438986752320035e-05, "epoch": 10.20980669495521, "percentage": 51.05, "elapsed_time": "1:18:26", "remaining_time": "1:15:12", "throughput": 4633.74, "total_tokens": 21807168} {"current_steps": 21660, "total_steps": 42420, "loss": 0.1046, "lr": 2.8428798240782182e-05, "epoch": 10.212164073550213, "percentage": 51.06, "elapsed_time": "1:18:27", "remaining_time": "1:15:11", "throughput": 4633.79, "total_tokens": 21812512} {"current_steps": 21665, "total_steps": 42420, "loss": 0.173, "lr": 2.8418609148807003e-05, "epoch": 10.214521452145215, "percentage": 51.07, "elapsed_time": "1:18:28", "remaining_time": "1:15:10", "throughput": 4633.86, "total_tokens": 21817728} {"current_steps": 21670, "total_steps": 42420, "loss": 0.0603, "lr": 2.840841947811934e-05, "epoch": 10.216878830740217, "percentage": 51.08, "elapsed_time": "1:18:29", "remaining_time": "1:15:09", "throughput": 4633.87, "total_tokens": 21822464} {"current_steps": 21675, "total_steps": 42420, "loss": 0.049, "lr": 2.839822923044413e-05, "epoch": 10.21923620933522, "percentage": 51.1, "elapsed_time": "1:18:30", "remaining_time": "1:15:08", "throughput": 4633.91, "total_tokens": 21827296} {"current_steps": 21680, "total_steps": 42420, "loss": 0.0974, "lr": 2.8388038407506413e-05, "epoch": 10.221593587930222, "percentage": 51.11, "elapsed_time": "1:18:31", "remaining_time": "1:15:06", "throughput": 4633.89, "total_tokens": 21831456} {"current_steps": 21685, "total_steps": 42420, "loss": 0.0657, "lr": 2.837784701103131e-05, "epoch": 10.223950966525225, "percentage": 51.12, "elapsed_time": "1:18:32", "remaining_time": "1:15:05", "throughput": 4633.96, "total_tokens": 21836640} {"current_steps": 21690, "total_steps": 42420, "loss": 0.0236, "lr": 2.8367655042744074e-05, "epoch": 10.226308345120227, "percentage": 51.13, "elapsed_time": "1:18:33", "remaining_time": "1:15:04", "throughput": 4634.02, "total_tokens": 21841696} {"current_steps": 21695, "total_steps": 42420, "loss": 0.075, "lr": 2.8357462504370014e-05, "epoch": 10.22866572371523, "percentage": 51.14, "elapsed_time": "1:18:34", "remaining_time": "1:15:03", "throughput": 4634.05, "total_tokens": 21846176} {"current_steps": 21700, "total_steps": 42420, "loss": 0.1099, "lr": 2.8347269397634553e-05, "epoch": 10.231023102310232, "percentage": 51.16, "elapsed_time": "1:18:35", "remaining_time": "1:15:02", "throughput": 4634.13, "total_tokens": 21851872} {"current_steps": 21705, "total_steps": 42420, "loss": 0.1254, "lr": 2.8337075724263218e-05, "epoch": 10.233380480905234, "percentage": 51.17, "elapsed_time": "1:18:36", "remaining_time": "1:15:01", "throughput": 4634.16, "total_tokens": 21856896} {"current_steps": 21710, "total_steps": 42420, "loss": 0.0704, "lr": 2.8326881485981633e-05, "epoch": 10.235737859500237, "percentage": 51.18, "elapsed_time": "1:18:37", "remaining_time": "1:15:00", "throughput": 4634.27, "total_tokens": 21864064} {"current_steps": 21715, "total_steps": 42420, "loss": 0.0336, "lr": 2.8316686684515488e-05, "epoch": 10.238095238095237, "percentage": 51.19, "elapsed_time": "1:18:38", "remaining_time": "1:14:59", "throughput": 4634.29, "total_tokens": 21868608} {"current_steps": 21720, "total_steps": 42420, "loss": 0.1785, "lr": 2.8306491321590607e-05, "epoch": 10.24045261669024, "percentage": 51.2, "elapsed_time": "1:18:39", "remaining_time": "1:14:58", "throughput": 4634.34, "total_tokens": 21873856} {"current_steps": 21725, "total_steps": 42420, "loss": 0.1683, "lr": 2.8296295398932886e-05, "epoch": 10.242809995285242, "percentage": 51.21, "elapsed_time": "1:18:41", "remaining_time": "1:14:57", "throughput": 4634.4, "total_tokens": 21879424} {"current_steps": 21730, "total_steps": 42420, "loss": 0.0196, "lr": 2.828609891826832e-05, "epoch": 10.245167373880244, "percentage": 51.23, "elapsed_time": "1:18:42", "remaining_time": "1:14:56", "throughput": 4634.46, "total_tokens": 21883968} {"current_steps": 21735, "total_steps": 42420, "loss": 0.0456, "lr": 2.8275901881323007e-05, "epoch": 10.247524752475247, "percentage": 51.24, "elapsed_time": "1:18:43", "remaining_time": "1:14:54", "throughput": 4634.49, "total_tokens": 21888768} {"current_steps": 21740, "total_steps": 42420, "loss": 0.1209, "lr": 2.8265704289823118e-05, "epoch": 10.24988213107025, "percentage": 51.25, "elapsed_time": "1:18:43", "remaining_time": "1:14:53", "throughput": 4634.52, "total_tokens": 21893056} {"current_steps": 21745, "total_steps": 42420, "loss": 0.0679, "lr": 2.8255506145494948e-05, "epoch": 10.252239509665252, "percentage": 51.26, "elapsed_time": "1:18:44", "remaining_time": "1:14:52", "throughput": 4634.58, "total_tokens": 21898208} {"current_steps": 21750, "total_steps": 42420, "loss": 0.1035, "lr": 2.8245307450064863e-05, "epoch": 10.254596888260254, "percentage": 51.27, "elapsed_time": "1:18:45", "remaining_time": "1:14:51", "throughput": 4634.58, "total_tokens": 21902368} {"current_steps": 21755, "total_steps": 42420, "loss": 0.088, "lr": 2.8235108205259324e-05, "epoch": 10.256954266855256, "percentage": 51.28, "elapsed_time": "1:18:46", "remaining_time": "1:14:49", "throughput": 4634.63, "total_tokens": 21906816} {"current_steps": 21760, "total_steps": 42420, "loss": 0.187, "lr": 2.8224908412804895e-05, "epoch": 10.259311645450259, "percentage": 51.3, "elapsed_time": "1:18:47", "remaining_time": "1:14:48", "throughput": 4634.69, "total_tokens": 21911616} {"current_steps": 21765, "total_steps": 42420, "loss": 0.1301, "lr": 2.821470807442823e-05, "epoch": 10.261669024045261, "percentage": 51.31, "elapsed_time": "1:18:48", "remaining_time": "1:14:47", "throughput": 4634.7, "total_tokens": 21916192} {"current_steps": 21770, "total_steps": 42420, "loss": 0.2156, "lr": 2.8204507191856073e-05, "epoch": 10.264026402640264, "percentage": 51.32, "elapsed_time": "1:18:49", "remaining_time": "1:14:46", "throughput": 4634.68, "total_tokens": 21920256} {"current_steps": 21775, "total_steps": 42420, "loss": 0.1895, "lr": 2.819430576681526e-05, "epoch": 10.266383781235266, "percentage": 51.33, "elapsed_time": "1:18:50", "remaining_time": "1:14:45", "throughput": 4634.64, "total_tokens": 21924864} {"current_steps": 21780, "total_steps": 42420, "loss": 0.0935, "lr": 2.8184103801032714e-05, "epoch": 10.268741159830268, "percentage": 51.34, "elapsed_time": "1:18:51", "remaining_time": "1:14:44", "throughput": 4634.69, "total_tokens": 21930464} {"current_steps": 21785, "total_steps": 42420, "loss": 0.0818, "lr": 2.817390129623545e-05, "epoch": 10.27109853842527, "percentage": 51.36, "elapsed_time": "1:18:52", "remaining_time": "1:14:43", "throughput": 4634.76, "total_tokens": 21936160} {"current_steps": 21790, "total_steps": 42420, "loss": 0.0897, "lr": 2.8163698254150593e-05, "epoch": 10.273455917020273, "percentage": 51.37, "elapsed_time": "1:18:54", "remaining_time": "1:14:42", "throughput": 4634.78, "total_tokens": 21941184} {"current_steps": 21795, "total_steps": 42420, "loss": 0.0583, "lr": 2.8153494676505345e-05, "epoch": 10.275813295615276, "percentage": 51.38, "elapsed_time": "1:18:55", "remaining_time": "1:14:40", "throughput": 4634.73, "total_tokens": 21945472} {"current_steps": 21800, "total_steps": 42420, "loss": 0.1135, "lr": 2.814329056502698e-05, "epoch": 10.278170674210278, "percentage": 51.39, "elapsed_time": "1:18:56", "remaining_time": "1:14:39", "throughput": 4634.77, "total_tokens": 21950496} {"current_steps": 21805, "total_steps": 42420, "loss": 0.0635, "lr": 2.8133085921442893e-05, "epoch": 10.28052805280528, "percentage": 51.4, "elapsed_time": "1:18:57", "remaining_time": "1:14:38", "throughput": 4634.79, "total_tokens": 21956000} {"current_steps": 21810, "total_steps": 42420, "loss": 0.0851, "lr": 2.8122880747480555e-05, "epoch": 10.282885431400283, "percentage": 51.41, "elapsed_time": "1:18:58", "remaining_time": "1:14:37", "throughput": 4634.85, "total_tokens": 21962624} {"current_steps": 21815, "total_steps": 42420, "loss": 0.2442, "lr": 2.8112675044867543e-05, "epoch": 10.285242809995285, "percentage": 51.43, "elapsed_time": "1:18:59", "remaining_time": "1:14:36", "throughput": 4634.91, "total_tokens": 21967680} {"current_steps": 21820, "total_steps": 42420, "loss": 0.0798, "lr": 2.8102468815331485e-05, "epoch": 10.287600188590288, "percentage": 51.44, "elapsed_time": "1:19:00", "remaining_time": "1:14:35", "throughput": 4634.94, "total_tokens": 21972608} {"current_steps": 21825, "total_steps": 42420, "loss": 0.0347, "lr": 2.8092262060600133e-05, "epoch": 10.28995756718529, "percentage": 51.45, "elapsed_time": "1:19:01", "remaining_time": "1:14:34", "throughput": 4635.01, "total_tokens": 21978624} {"current_steps": 21830, "total_steps": 42420, "loss": 0.0207, "lr": 2.8082054782401322e-05, "epoch": 10.292314945780292, "percentage": 51.46, "elapsed_time": "1:19:03", "remaining_time": "1:14:33", "throughput": 4635.06, "total_tokens": 21984256} {"current_steps": 21835, "total_steps": 42420, "loss": 0.0528, "lr": 2.807184698246297e-05, "epoch": 10.294672324375295, "percentage": 51.47, "elapsed_time": "1:19:04", "remaining_time": "1:14:32", "throughput": 4635.11, "total_tokens": 21989760} {"current_steps": 21840, "total_steps": 42420, "loss": 0.0196, "lr": 2.8061638662513077e-05, "epoch": 10.297029702970297, "percentage": 51.49, "elapsed_time": "1:19:05", "remaining_time": "1:14:31", "throughput": 4635.13, "total_tokens": 21994144} {"current_steps": 21845, "total_steps": 42420, "loss": 0.0345, "lr": 2.8051429824279745e-05, "epoch": 10.2993870815653, "percentage": 51.5, "elapsed_time": "1:19:06", "remaining_time": "1:14:30", "throughput": 4635.19, "total_tokens": 22000512} {"current_steps": 21850, "total_steps": 42420, "loss": 0.1514, "lr": 2.804122046949115e-05, "epoch": 10.301744460160302, "percentage": 51.51, "elapsed_time": "1:19:07", "remaining_time": "1:14:29", "throughput": 4635.26, "total_tokens": 22005952} {"current_steps": 21855, "total_steps": 42420, "loss": 0.0484, "lr": 2.803101059987556e-05, "epoch": 10.304101838755304, "percentage": 51.52, "elapsed_time": "1:19:08", "remaining_time": "1:14:28", "throughput": 4635.29, "total_tokens": 22010560} {"current_steps": 21860, "total_steps": 42420, "loss": 0.0801, "lr": 2.8020800217161353e-05, "epoch": 10.306459217350307, "percentage": 51.53, "elapsed_time": "1:19:09", "remaining_time": "1:14:27", "throughput": 4635.34, "total_tokens": 22015648} {"current_steps": 21865, "total_steps": 42420, "loss": 0.3151, "lr": 2.8010589323076952e-05, "epoch": 10.30881659594531, "percentage": 51.54, "elapsed_time": "1:19:10", "remaining_time": "1:14:25", "throughput": 4635.35, "total_tokens": 22020320} {"current_steps": 21870, "total_steps": 42420, "loss": 0.1504, "lr": 2.8000377919350897e-05, "epoch": 10.311173974540312, "percentage": 51.56, "elapsed_time": "1:19:11", "remaining_time": "1:14:24", "throughput": 4635.4, "total_tokens": 22025280} {"current_steps": 21875, "total_steps": 42420, "loss": 0.1017, "lr": 2.79901660077118e-05, "epoch": 10.313531353135314, "percentage": 51.57, "elapsed_time": "1:19:12", "remaining_time": "1:14:23", "throughput": 4635.48, "total_tokens": 22031744} {"current_steps": 21880, "total_steps": 42420, "loss": 0.0563, "lr": 2.7979953589888376e-05, "epoch": 10.315888731730317, "percentage": 51.58, "elapsed_time": "1:19:13", "remaining_time": "1:14:22", "throughput": 4635.5, "total_tokens": 22036832} {"current_steps": 21885, "total_steps": 42420, "loss": 0.1075, "lr": 2.79697406676094e-05, "epoch": 10.318246110325319, "percentage": 51.59, "elapsed_time": "1:19:15", "remaining_time": "1:14:21", "throughput": 4635.55, "total_tokens": 22042144} {"current_steps": 21890, "total_steps": 42420, "loss": 0.136, "lr": 2.795952724260375e-05, "epoch": 10.320603488920321, "percentage": 51.6, "elapsed_time": "1:19:15", "remaining_time": "1:14:20", "throughput": 4635.6, "total_tokens": 22046720} {"current_steps": 21895, "total_steps": 42420, "loss": 0.2172, "lr": 2.794931331660039e-05, "epoch": 10.322960867515324, "percentage": 51.61, "elapsed_time": "1:19:17", "remaining_time": "1:14:19", "throughput": 4635.66, "total_tokens": 22052992} {"current_steps": 21900, "total_steps": 42420, "loss": 0.1307, "lr": 2.793909889132837e-05, "epoch": 10.325318246110326, "percentage": 51.63, "elapsed_time": "1:19:18", "remaining_time": "1:14:18", "throughput": 4635.65, "total_tokens": 22057088} {"current_steps": 21905, "total_steps": 42420, "loss": 0.0502, "lr": 2.79288839685168e-05, "epoch": 10.327675624705329, "percentage": 51.64, "elapsed_time": "1:19:19", "remaining_time": "1:14:17", "throughput": 4635.63, "total_tokens": 22061120} {"current_steps": 21910, "total_steps": 42420, "loss": 0.0955, "lr": 2.7918668549894904e-05, "epoch": 10.33003300330033, "percentage": 51.65, "elapsed_time": "1:19:20", "remaining_time": "1:14:15", "throughput": 4635.67, "total_tokens": 22066048} {"current_steps": 21915, "total_steps": 42420, "loss": 0.0253, "lr": 2.7908452637191984e-05, "epoch": 10.332390381895332, "percentage": 51.66, "elapsed_time": "1:19:20", "remaining_time": "1:14:14", "throughput": 4635.7, "total_tokens": 22070560} {"current_steps": 21920, "total_steps": 42420, "loss": 0.0944, "lr": 2.7898236232137414e-05, "epoch": 10.334747760490334, "percentage": 51.67, "elapsed_time": "1:19:21", "remaining_time": "1:14:13", "throughput": 4635.72, "total_tokens": 22075232} {"current_steps": 21925, "total_steps": 42420, "loss": 0.1121, "lr": 2.7888019336460657e-05, "epoch": 10.337105139085336, "percentage": 51.69, "elapsed_time": "1:19:23", "remaining_time": "1:14:12", "throughput": 4635.8, "total_tokens": 22081696} {"current_steps": 21930, "total_steps": 42420, "loss": 0.1441, "lr": 2.7877801951891264e-05, "epoch": 10.339462517680339, "percentage": 51.7, "elapsed_time": "1:19:24", "remaining_time": "1:14:11", "throughput": 4635.81, "total_tokens": 22086432} {"current_steps": 21935, "total_steps": 42420, "loss": 0.0758, "lr": 2.7867584080158865e-05, "epoch": 10.341819896275341, "percentage": 51.71, "elapsed_time": "1:19:25", "remaining_time": "1:14:10", "throughput": 4635.88, "total_tokens": 22092320} {"current_steps": 21940, "total_steps": 42420, "loss": 0.1616, "lr": 2.7857365722993168e-05, "epoch": 10.344177274870344, "percentage": 51.72, "elapsed_time": "1:19:26", "remaining_time": "1:14:09", "throughput": 4635.87, "total_tokens": 22096192} {"current_steps": 21945, "total_steps": 42420, "loss": 0.4166, "lr": 2.784714688212397e-05, "epoch": 10.346534653465346, "percentage": 51.73, "elapsed_time": "1:19:27", "remaining_time": "1:14:08", "throughput": 4635.92, "total_tokens": 22101120} {"current_steps": 21950, "total_steps": 42420, "loss": 0.1213, "lr": 2.7836927559281152e-05, "epoch": 10.348892032060348, "percentage": 51.74, "elapsed_time": "1:19:28", "remaining_time": "1:14:06", "throughput": 4635.89, "total_tokens": 22105152} {"current_steps": 21955, "total_steps": 42420, "loss": 0.065, "lr": 2.782670775619466e-05, "epoch": 10.35124941065535, "percentage": 51.76, "elapsed_time": "1:19:29", "remaining_time": "1:14:05", "throughput": 4635.94, "total_tokens": 22110048} {"current_steps": 21960, "total_steps": 42420, "loss": 0.1021, "lr": 2.7816487474594534e-05, "epoch": 10.353606789250353, "percentage": 51.77, "elapsed_time": "1:19:30", "remaining_time": "1:14:04", "throughput": 4635.89, "total_tokens": 22113568} {"current_steps": 21965, "total_steps": 42420, "loss": 0.0519, "lr": 2.780626671621091e-05, "epoch": 10.355964167845356, "percentage": 51.78, "elapsed_time": "1:19:31", "remaining_time": "1:14:03", "throughput": 4635.95, "total_tokens": 22118976} {"current_steps": 21970, "total_steps": 42420, "loss": 0.0859, "lr": 2.7796045482773976e-05, "epoch": 10.358321546440358, "percentage": 51.79, "elapsed_time": "1:19:32", "remaining_time": "1:14:02", "throughput": 4636.0, "total_tokens": 22126240} {"current_steps": 21975, "total_steps": 42420, "loss": 0.129, "lr": 2.778582377601401e-05, "epoch": 10.36067892503536, "percentage": 51.8, "elapsed_time": "1:19:33", "remaining_time": "1:14:01", "throughput": 4636.07, "total_tokens": 22131936} {"current_steps": 21980, "total_steps": 42420, "loss": 0.1455, "lr": 2.7775601597661384e-05, "epoch": 10.363036303630363, "percentage": 51.82, "elapsed_time": "1:19:34", "remaining_time": "1:14:00", "throughput": 4636.06, "total_tokens": 22136704} {"current_steps": 21985, "total_steps": 42420, "loss": 0.1654, "lr": 2.7765378949446535e-05, "epoch": 10.365393682225365, "percentage": 51.83, "elapsed_time": "1:19:35", "remaining_time": "1:13:59", "throughput": 4636.06, "total_tokens": 22141024} {"current_steps": 21990, "total_steps": 42420, "loss": 0.3227, "lr": 2.7755155833099982e-05, "epoch": 10.367751060820368, "percentage": 51.84, "elapsed_time": "1:19:36", "remaining_time": "1:13:58", "throughput": 4636.1, "total_tokens": 22146592} {"current_steps": 21995, "total_steps": 42420, "loss": 0.0497, "lr": 2.7744932250352324e-05, "epoch": 10.37010843941537, "percentage": 51.85, "elapsed_time": "1:19:38", "remaining_time": "1:13:57", "throughput": 4636.15, "total_tokens": 22151904} {"current_steps": 22000, "total_steps": 42420, "loss": 0.0252, "lr": 2.7734708202934247e-05, "epoch": 10.372465818010372, "percentage": 51.86, "elapsed_time": "1:19:38", "remaining_time": "1:13:55", "throughput": 4636.13, "total_tokens": 22155840} {"current_steps": 22005, "total_steps": 42420, "loss": 0.1912, "lr": 2.77244836925765e-05, "epoch": 10.374823196605375, "percentage": 51.87, "elapsed_time": "1:19:39", "remaining_time": "1:13:54", "throughput": 4636.15, "total_tokens": 22160544} {"current_steps": 22010, "total_steps": 42420, "loss": 0.3668, "lr": 2.7714258721009927e-05, "epoch": 10.377180575200377, "percentage": 51.89, "elapsed_time": "1:19:40", "remaining_time": "1:13:53", "throughput": 4636.17, "total_tokens": 22165152} {"current_steps": 22015, "total_steps": 42420, "loss": 0.2036, "lr": 2.7704033289965437e-05, "epoch": 10.37953795379538, "percentage": 51.9, "elapsed_time": "1:19:41", "remaining_time": "1:13:52", "throughput": 4636.21, "total_tokens": 22169728} {"current_steps": 22020, "total_steps": 42420, "loss": 0.1491, "lr": 2.7693807401174023e-05, "epoch": 10.381895332390382, "percentage": 51.91, "elapsed_time": "1:19:42", "remaining_time": "1:13:50", "throughput": 4636.2, "total_tokens": 22173984} {"current_steps": 22025, "total_steps": 42420, "loss": 0.2411, "lr": 2.7683581056366755e-05, "epoch": 10.384252710985384, "percentage": 51.92, "elapsed_time": "1:19:43", "remaining_time": "1:13:49", "throughput": 4636.27, "total_tokens": 22179776} {"current_steps": 22030, "total_steps": 42420, "loss": 0.2832, "lr": 2.7673354257274775e-05, "epoch": 10.386610089580387, "percentage": 51.93, "elapsed_time": "1:19:45", "remaining_time": "1:13:48", "throughput": 4636.3, "total_tokens": 22185664} {"current_steps": 22035, "total_steps": 42420, "loss": 0.1411, "lr": 2.7663127005629306e-05, "epoch": 10.38896746817539, "percentage": 51.94, "elapsed_time": "1:19:46", "remaining_time": "1:13:48", "throughput": 4636.36, "total_tokens": 22191648} {"current_steps": 22040, "total_steps": 42420, "loss": 0.2098, "lr": 2.7652899303161662e-05, "epoch": 10.391324846770392, "percentage": 51.96, "elapsed_time": "1:19:47", "remaining_time": "1:13:47", "throughput": 4636.43, "total_tokens": 22197824} {"current_steps": 22045, "total_steps": 42420, "loss": 0.0303, "lr": 2.7642671151603207e-05, "epoch": 10.393682225365394, "percentage": 51.97, "elapsed_time": "1:19:48", "remaining_time": "1:13:45", "throughput": 4636.47, "total_tokens": 22202688} {"current_steps": 22050, "total_steps": 42420, "loss": 0.0819, "lr": 2.7632442552685395e-05, "epoch": 10.396039603960396, "percentage": 51.98, "elapsed_time": "1:19:49", "remaining_time": "1:13:44", "throughput": 4636.52, "total_tokens": 22207808} {"current_steps": 22055, "total_steps": 42420, "loss": 0.0984, "lr": 2.7622213508139754e-05, "epoch": 10.398396982555399, "percentage": 51.99, "elapsed_time": "1:19:50", "remaining_time": "1:13:43", "throughput": 4636.52, "total_tokens": 22212320} {"current_steps": 22060, "total_steps": 42420, "loss": 0.0171, "lr": 2.761198401969789e-05, "epoch": 10.400754361150401, "percentage": 52.0, "elapsed_time": "1:19:51", "remaining_time": "1:13:42", "throughput": 4636.56, "total_tokens": 22217536} {"current_steps": 22065, "total_steps": 42420, "loss": 0.1167, "lr": 2.760175408909148e-05, "epoch": 10.403111739745404, "percentage": 52.02, "elapsed_time": "1:19:52", "remaining_time": "1:13:41", "throughput": 4636.55, "total_tokens": 22221472} {"current_steps": 22070, "total_steps": 42420, "loss": 0.0839, "lr": 2.7591523718052287e-05, "epoch": 10.405469118340406, "percentage": 52.03, "elapsed_time": "1:19:53", "remaining_time": "1:13:40", "throughput": 4636.66, "total_tokens": 22228064} {"current_steps": 22075, "total_steps": 42420, "loss": 0.0874, "lr": 2.7581292908312116e-05, "epoch": 10.407826496935408, "percentage": 52.04, "elapsed_time": "1:19:54", "remaining_time": "1:13:39", "throughput": 4636.64, "total_tokens": 22232544} {"current_steps": 22080, "total_steps": 42420, "loss": 0.3829, "lr": 2.7571061661602887e-05, "epoch": 10.41018387553041, "percentage": 52.05, "elapsed_time": "1:19:56", "remaining_time": "1:13:38", "throughput": 4636.67, "total_tokens": 22238016} {"current_steps": 22085, "total_steps": 42420, "loss": 0.0717, "lr": 2.7560829979656577e-05, "epoch": 10.412541254125413, "percentage": 52.06, "elapsed_time": "1:19:57", "remaining_time": "1:13:37", "throughput": 4636.72, "total_tokens": 22242976} {"current_steps": 22090, "total_steps": 42420, "loss": 0.2507, "lr": 2.755059786420523e-05, "epoch": 10.414898632720416, "percentage": 52.07, "elapsed_time": "1:19:58", "remaining_time": "1:13:35", "throughput": 4636.77, "total_tokens": 22248416} {"current_steps": 22095, "total_steps": 42420, "loss": 0.0675, "lr": 2.754036531698097e-05, "epoch": 10.417256011315418, "percentage": 52.09, "elapsed_time": "1:19:59", "remaining_time": "1:13:34", "throughput": 4636.82, "total_tokens": 22253984} {"current_steps": 22100, "total_steps": 42420, "loss": 0.21, "lr": 2.7530132339715998e-05, "epoch": 10.41961338991042, "percentage": 52.1, "elapsed_time": "1:20:00", "remaining_time": "1:13:34", "throughput": 4636.89, "total_tokens": 22260640} {"current_steps": 22105, "total_steps": 42420, "loss": 0.0613, "lr": 2.7519898934142573e-05, "epoch": 10.421970768505423, "percentage": 52.11, "elapsed_time": "1:20:01", "remaining_time": "1:13:33", "throughput": 4636.95, "total_tokens": 22265952} {"current_steps": 22110, "total_steps": 42420, "loss": 0.0864, "lr": 2.7509665101993053e-05, "epoch": 10.424328147100425, "percentage": 52.12, "elapsed_time": "1:20:02", "remaining_time": "1:13:31", "throughput": 4636.99, "total_tokens": 22270848} {"current_steps": 22115, "total_steps": 42420, "loss": 0.0542, "lr": 2.749943084499984e-05, "epoch": 10.426685525695426, "percentage": 52.13, "elapsed_time": "1:20:03", "remaining_time": "1:13:30", "throughput": 4637.01, "total_tokens": 22275552} {"current_steps": 22120, "total_steps": 42420, "loss": 0.0592, "lr": 2.748919616489542e-05, "epoch": 10.429042904290428, "percentage": 52.15, "elapsed_time": "1:20:04", "remaining_time": "1:13:29", "throughput": 4637.03, "total_tokens": 22280512} {"current_steps": 22125, "total_steps": 42420, "loss": 0.0732, "lr": 2.747896106341235e-05, "epoch": 10.43140028288543, "percentage": 52.16, "elapsed_time": "1:20:05", "remaining_time": "1:13:28", "throughput": 4637.03, "total_tokens": 22285184} {"current_steps": 22130, "total_steps": 42420, "loss": 0.1081, "lr": 2.7468725542283275e-05, "epoch": 10.433757661480433, "percentage": 52.17, "elapsed_time": "1:20:06", "remaining_time": "1:13:27", "throughput": 4637.06, "total_tokens": 22289856} {"current_steps": 22135, "total_steps": 42420, "loss": 0.0731, "lr": 2.745848960324087e-05, "epoch": 10.436115040075435, "percentage": 52.18, "elapsed_time": "1:20:07", "remaining_time": "1:13:26", "throughput": 4637.08, "total_tokens": 22294720} {"current_steps": 22140, "total_steps": 42420, "loss": 0.0999, "lr": 2.744825324801792e-05, "epoch": 10.438472418670438, "percentage": 52.19, "elapsed_time": "1:20:08", "remaining_time": "1:13:24", "throughput": 4637.11, "total_tokens": 22299328} {"current_steps": 22145, "total_steps": 42420, "loss": 0.1196, "lr": 2.743801647834727e-05, "epoch": 10.44082979726544, "percentage": 52.2, "elapsed_time": "1:20:09", "remaining_time": "1:13:23", "throughput": 4637.17, "total_tokens": 22304416} {"current_steps": 22150, "total_steps": 42420, "loss": 0.2945, "lr": 2.7427779295961824e-05, "epoch": 10.443187175860443, "percentage": 52.22, "elapsed_time": "1:20:10", "remaining_time": "1:13:22", "throughput": 4637.21, "total_tokens": 22309376} {"current_steps": 22155, "total_steps": 42420, "loss": 0.2133, "lr": 2.7417541702594563e-05, "epoch": 10.445544554455445, "percentage": 52.23, "elapsed_time": "1:20:11", "remaining_time": "1:13:21", "throughput": 4637.23, "total_tokens": 22314208} {"current_steps": 22160, "total_steps": 42420, "loss": 0.0516, "lr": 2.740730369997853e-05, "epoch": 10.447901933050447, "percentage": 52.24, "elapsed_time": "1:20:12", "remaining_time": "1:13:20", "throughput": 4637.26, "total_tokens": 22319136} {"current_steps": 22165, "total_steps": 42420, "loss": 0.3372, "lr": 2.7397065289846868e-05, "epoch": 10.45025931164545, "percentage": 52.25, "elapsed_time": "1:20:14", "remaining_time": "1:13:19", "throughput": 4637.28, "total_tokens": 22323872} {"current_steps": 22170, "total_steps": 42420, "loss": 0.1851, "lr": 2.7386826473932747e-05, "epoch": 10.452616690240452, "percentage": 52.26, "elapsed_time": "1:20:15", "remaining_time": "1:13:18", "throughput": 4637.32, "total_tokens": 22328896} {"current_steps": 22175, "total_steps": 42420, "loss": 0.0628, "lr": 2.737658725396944e-05, "epoch": 10.454974068835455, "percentage": 52.27, "elapsed_time": "1:20:16", "remaining_time": "1:13:16", "throughput": 4637.35, "total_tokens": 22333760} {"current_steps": 22180, "total_steps": 42420, "loss": 0.0543, "lr": 2.7366347631690248e-05, "epoch": 10.457331447430457, "percentage": 52.29, "elapsed_time": "1:20:17", "remaining_time": "1:13:15", "throughput": 4637.4, "total_tokens": 22338848} {"current_steps": 22185, "total_steps": 42420, "loss": 0.0261, "lr": 2.7356107608828586e-05, "epoch": 10.45968882602546, "percentage": 52.3, "elapsed_time": "1:20:18", "remaining_time": "1:13:14", "throughput": 4637.46, "total_tokens": 22344448} {"current_steps": 22190, "total_steps": 42420, "loss": 0.0327, "lr": 2.7345867187117908e-05, "epoch": 10.462046204620462, "percentage": 52.31, "elapsed_time": "1:20:19", "remaining_time": "1:13:13", "throughput": 4637.47, "total_tokens": 22349216} {"current_steps": 22195, "total_steps": 42420, "loss": 0.1413, "lr": 2.733562636829175e-05, "epoch": 10.464403583215464, "percentage": 52.32, "elapsed_time": "1:20:20", "remaining_time": "1:13:12", "throughput": 4637.45, "total_tokens": 22353600} {"current_steps": 22200, "total_steps": 42420, "loss": 0.1303, "lr": 2.73253851540837e-05, "epoch": 10.466760961810467, "percentage": 52.33, "elapsed_time": "1:20:21", "remaining_time": "1:13:11", "throughput": 4637.52, "total_tokens": 22359808} {"current_steps": 22205, "total_steps": 42420, "loss": 0.1506, "lr": 2.7315143546227427e-05, "epoch": 10.469118340405469, "percentage": 52.35, "elapsed_time": "1:20:22", "remaining_time": "1:13:10", "throughput": 4637.52, "total_tokens": 22363872} {"current_steps": 22210, "total_steps": 42420, "loss": 0.206, "lr": 2.730490154645666e-05, "epoch": 10.471475719000471, "percentage": 52.36, "elapsed_time": "1:20:23", "remaining_time": "1:13:09", "throughput": 4637.53, "total_tokens": 22368512} {"current_steps": 22215, "total_steps": 42420, "loss": 0.2259, "lr": 2.7294659156505203e-05, "epoch": 10.473833097595474, "percentage": 52.37, "elapsed_time": "1:20:24", "remaining_time": "1:13:07", "throughput": 4637.52, "total_tokens": 22372704} {"current_steps": 22220, "total_steps": 42420, "loss": 0.1567, "lr": 2.72844163781069e-05, "epoch": 10.476190476190476, "percentage": 52.38, "elapsed_time": "1:20:25", "remaining_time": "1:13:06", "throughput": 4637.52, "total_tokens": 22377024} {"current_steps": 22225, "total_steps": 42420, "loss": 0.1986, "lr": 2.72741732129957e-05, "epoch": 10.478547854785479, "percentage": 52.39, "elapsed_time": "1:20:26", "remaining_time": "1:13:05", "throughput": 4637.59, "total_tokens": 22382560} {"current_steps": 22230, "total_steps": 42420, "loss": 0.1503, "lr": 2.7263929662905583e-05, "epoch": 10.480905233380481, "percentage": 52.4, "elapsed_time": "1:20:27", "remaining_time": "1:13:04", "throughput": 4637.64, "total_tokens": 22387616} {"current_steps": 22235, "total_steps": 42420, "loss": 0.2191, "lr": 2.7253685729570628e-05, "epoch": 10.483262611975483, "percentage": 52.42, "elapsed_time": "1:20:28", "remaining_time": "1:13:03", "throughput": 4637.68, "total_tokens": 22392160} {"current_steps": 22240, "total_steps": 42420, "loss": 0.1178, "lr": 2.724344141472493e-05, "epoch": 10.485619990570486, "percentage": 52.43, "elapsed_time": "1:20:29", "remaining_time": "1:13:02", "throughput": 4637.72, "total_tokens": 22397152} {"current_steps": 22245, "total_steps": 42420, "loss": 0.1542, "lr": 2.7233196720102693e-05, "epoch": 10.487977369165488, "percentage": 52.44, "elapsed_time": "1:20:30", "remaining_time": "1:13:00", "throughput": 4637.75, "total_tokens": 22402112} {"current_steps": 22250, "total_steps": 42420, "loss": 0.2039, "lr": 2.722295164743817e-05, "epoch": 10.49033474776049, "percentage": 52.45, "elapsed_time": "1:20:31", "remaining_time": "1:12:59", "throughput": 4637.74, "total_tokens": 22407328} {"current_steps": 22255, "total_steps": 42420, "loss": 0.0252, "lr": 2.7212706198465682e-05, "epoch": 10.492692126355493, "percentage": 52.46, "elapsed_time": "1:20:32", "remaining_time": "1:12:58", "throughput": 4637.78, "total_tokens": 22412480} {"current_steps": 22260, "total_steps": 42420, "loss": 0.0489, "lr": 2.7202460374919598e-05, "epoch": 10.495049504950495, "percentage": 52.48, "elapsed_time": "1:20:33", "remaining_time": "1:12:57", "throughput": 4637.87, "total_tokens": 22418816} {"current_steps": 22265, "total_steps": 42420, "loss": 0.082, "lr": 2.719221417853437e-05, "epoch": 10.497406883545498, "percentage": 52.49, "elapsed_time": "1:20:34", "remaining_time": "1:12:56", "throughput": 4637.92, "total_tokens": 22423296} {"current_steps": 22270, "total_steps": 42420, "loss": 0.0622, "lr": 2.71819676110445e-05, "epoch": 10.4997642621405, "percentage": 52.5, "elapsed_time": "1:20:35", "remaining_time": "1:12:55", "throughput": 4637.95, "total_tokens": 22428064} {"current_steps": 22275, "total_steps": 42420, "loss": 0.0411, "lr": 2.717172067418457e-05, "epoch": 10.502121640735503, "percentage": 52.51, "elapsed_time": "1:20:36", "remaining_time": "1:12:54", "throughput": 4637.99, "total_tokens": 22432928} {"current_steps": 22280, "total_steps": 42420, "loss": 0.119, "lr": 2.7161473369689194e-05, "epoch": 10.504479019330505, "percentage": 52.52, "elapsed_time": "1:20:37", "remaining_time": "1:12:53", "throughput": 4637.92, "total_tokens": 22436736} {"current_steps": 22285, "total_steps": 42420, "loss": 0.1373, "lr": 2.715122569929308e-05, "epoch": 10.506836397925507, "percentage": 52.53, "elapsed_time": "1:20:38", "remaining_time": "1:12:51", "throughput": 4637.98, "total_tokens": 22442208} {"current_steps": 22290, "total_steps": 42420, "loss": 0.2584, "lr": 2.7140977664730986e-05, "epoch": 10.50919377652051, "percentage": 52.55, "elapsed_time": "1:20:39", "remaining_time": "1:12:50", "throughput": 4637.99, "total_tokens": 22447168} {"current_steps": 22295, "total_steps": 42420, "loss": 0.0923, "lr": 2.7130729267737726e-05, "epoch": 10.511551155115512, "percentage": 52.56, "elapsed_time": "1:20:40", "remaining_time": "1:12:49", "throughput": 4638.01, "total_tokens": 22452096} {"current_steps": 22300, "total_steps": 42420, "loss": 0.0709, "lr": 2.7120480510048168e-05, "epoch": 10.513908533710515, "percentage": 52.57, "elapsed_time": "1:20:41", "remaining_time": "1:12:48", "throughput": 4638.02, "total_tokens": 22456384} {"current_steps": 22305, "total_steps": 42420, "loss": 0.039, "lr": 2.7110231393397268e-05, "epoch": 10.516265912305517, "percentage": 52.58, "elapsed_time": "1:20:42", "remaining_time": "1:12:47", "throughput": 4638.03, "total_tokens": 22460896} {"current_steps": 22310, "total_steps": 42420, "loss": 0.2541, "lr": 2.7099981919520024e-05, "epoch": 10.518623290900518, "percentage": 52.59, "elapsed_time": "1:20:43", "remaining_time": "1:12:46", "throughput": 4638.11, "total_tokens": 22466464} {"current_steps": 22315, "total_steps": 42420, "loss": 0.3366, "lr": 2.70897320901515e-05, "epoch": 10.520980669495522, "percentage": 52.6, "elapsed_time": "1:20:44", "remaining_time": "1:12:44", "throughput": 4638.13, "total_tokens": 22470688} {"current_steps": 22320, "total_steps": 42420, "loss": 0.1078, "lr": 2.707948190702681e-05, "epoch": 10.523338048090523, "percentage": 52.62, "elapsed_time": "1:20:45", "remaining_time": "1:12:43", "throughput": 4638.17, "total_tokens": 22475840} {"current_steps": 22325, "total_steps": 42420, "loss": 0.1015, "lr": 2.7069231371881138e-05, "epoch": 10.525695426685525, "percentage": 52.63, "elapsed_time": "1:20:46", "remaining_time": "1:12:42", "throughput": 4638.15, "total_tokens": 22480032} {"current_steps": 22330, "total_steps": 42420, "loss": 0.1097, "lr": 2.7058980486449732e-05, "epoch": 10.528052805280527, "percentage": 52.64, "elapsed_time": "1:20:47", "remaining_time": "1:12:41", "throughput": 4638.19, "total_tokens": 22484576} {"current_steps": 22335, "total_steps": 42420, "loss": 0.0182, "lr": 2.704872925246789e-05, "epoch": 10.53041018387553, "percentage": 52.65, "elapsed_time": "1:20:48", "remaining_time": "1:12:40", "throughput": 4638.23, "total_tokens": 22489056} {"current_steps": 22340, "total_steps": 42420, "loss": 0.1323, "lr": 2.703847767167097e-05, "epoch": 10.532767562470532, "percentage": 52.66, "elapsed_time": "1:20:49", "remaining_time": "1:12:38", "throughput": 4638.18, "total_tokens": 22492992} {"current_steps": 22345, "total_steps": 42420, "loss": 0.0909, "lr": 2.702822574579439e-05, "epoch": 10.535124941065535, "percentage": 52.68, "elapsed_time": "1:20:50", "remaining_time": "1:12:37", "throughput": 4638.21, "total_tokens": 22498144} {"current_steps": 22350, "total_steps": 42420, "loss": 0.0647, "lr": 2.7017973476573625e-05, "epoch": 10.537482319660537, "percentage": 52.69, "elapsed_time": "1:20:51", "remaining_time": "1:12:36", "throughput": 4638.21, "total_tokens": 22502400} {"current_steps": 22355, "total_steps": 42420, "loss": 0.0955, "lr": 2.7007720865744224e-05, "epoch": 10.53983969825554, "percentage": 52.7, "elapsed_time": "1:20:52", "remaining_time": "1:12:35", "throughput": 4638.25, "total_tokens": 22507360} {"current_steps": 22360, "total_steps": 42420, "loss": 0.0733, "lr": 2.6997467915041765e-05, "epoch": 10.542197076850542, "percentage": 52.71, "elapsed_time": "1:20:53", "remaining_time": "1:12:34", "throughput": 4638.22, "total_tokens": 22512608} {"current_steps": 22365, "total_steps": 42420, "loss": 0.0525, "lr": 2.69872146262019e-05, "epoch": 10.544554455445544, "percentage": 52.72, "elapsed_time": "1:20:54", "remaining_time": "1:12:33", "throughput": 4638.15, "total_tokens": 22516896} {"current_steps": 22370, "total_steps": 42420, "loss": 0.1544, "lr": 2.6976961000960345e-05, "epoch": 10.546911834040547, "percentage": 52.73, "elapsed_time": "1:20:55", "remaining_time": "1:12:32", "throughput": 4638.17, "total_tokens": 22522112} {"current_steps": 22375, "total_steps": 42420, "loss": 0.0792, "lr": 2.6966707041052858e-05, "epoch": 10.549269212635549, "percentage": 52.75, "elapsed_time": "1:20:57", "remaining_time": "1:12:31", "throughput": 4638.25, "total_tokens": 22528672} {"current_steps": 22380, "total_steps": 42420, "loss": 0.1408, "lr": 2.6956452748215255e-05, "epoch": 10.551626591230551, "percentage": 52.76, "elapsed_time": "1:20:58", "remaining_time": "1:12:30", "throughput": 4638.32, "total_tokens": 22534592} {"current_steps": 22385, "total_steps": 42420, "loss": 0.0675, "lr": 2.6946198124183423e-05, "epoch": 10.553983969825554, "percentage": 52.77, "elapsed_time": "1:20:59", "remaining_time": "1:12:29", "throughput": 4638.39, "total_tokens": 22539808} {"current_steps": 22390, "total_steps": 42420, "loss": 0.065, "lr": 2.6935943170693295e-05, "epoch": 10.556341348420556, "percentage": 52.78, "elapsed_time": "1:21:00", "remaining_time": "1:12:28", "throughput": 4638.44, "total_tokens": 22544832} {"current_steps": 22395, "total_steps": 42420, "loss": 0.0894, "lr": 2.6925687889480865e-05, "epoch": 10.558698727015559, "percentage": 52.79, "elapsed_time": "1:21:01", "remaining_time": "1:12:26", "throughput": 4638.39, "total_tokens": 22548864} {"current_steps": 22400, "total_steps": 42420, "loss": 0.063, "lr": 2.691543228228217e-05, "epoch": 10.561056105610561, "percentage": 52.81, "elapsed_time": "1:21:02", "remaining_time": "1:12:25", "throughput": 4638.4, "total_tokens": 22552864} {"current_steps": 22405, "total_steps": 42420, "loss": 0.0338, "lr": 2.6905176350833307e-05, "epoch": 10.563413484205563, "percentage": 52.82, "elapsed_time": "1:21:03", "remaining_time": "1:12:24", "throughput": 4638.35, "total_tokens": 22556512} {"current_steps": 22410, "total_steps": 42420, "loss": 0.0753, "lr": 2.6894920096870435e-05, "epoch": 10.565770862800566, "percentage": 52.83, "elapsed_time": "1:21:04", "remaining_time": "1:12:23", "throughput": 4638.38, "total_tokens": 22561280} {"current_steps": 22415, "total_steps": 42420, "loss": 0.0634, "lr": 2.6884663522129766e-05, "epoch": 10.568128241395568, "percentage": 52.84, "elapsed_time": "1:21:05", "remaining_time": "1:12:21", "throughput": 4638.38, "total_tokens": 22565792} {"current_steps": 22420, "total_steps": 42420, "loss": 0.0909, "lr": 2.6874406628347564e-05, "epoch": 10.57048561999057, "percentage": 52.85, "elapsed_time": "1:21:06", "remaining_time": "1:12:20", "throughput": 4638.44, "total_tokens": 22570784} {"current_steps": 22425, "total_steps": 42420, "loss": 0.1066, "lr": 2.6864149417260142e-05, "epoch": 10.572842998585573, "percentage": 52.86, "elapsed_time": "1:21:07", "remaining_time": "1:12:19", "throughput": 4638.44, "total_tokens": 22575776} {"current_steps": 22430, "total_steps": 42420, "loss": 0.202, "lr": 2.6853891890603877e-05, "epoch": 10.575200377180575, "percentage": 52.88, "elapsed_time": "1:21:08", "remaining_time": "1:12:18", "throughput": 4638.48, "total_tokens": 22580864} {"current_steps": 22435, "total_steps": 42420, "loss": 0.0976, "lr": 2.684363405011519e-05, "epoch": 10.577557755775578, "percentage": 52.89, "elapsed_time": "1:21:09", "remaining_time": "1:12:17", "throughput": 4638.51, "total_tokens": 22585440} {"current_steps": 22440, "total_steps": 42420, "loss": 0.1796, "lr": 2.6833375897530573e-05, "epoch": 10.57991513437058, "percentage": 52.9, "elapsed_time": "1:21:10", "remaining_time": "1:12:16", "throughput": 4638.59, "total_tokens": 22591744} {"current_steps": 22445, "total_steps": 42420, "loss": 0.1456, "lr": 2.682311743458653e-05, "epoch": 10.582272512965583, "percentage": 52.91, "elapsed_time": "1:21:11", "remaining_time": "1:12:15", "throughput": 4638.64, "total_tokens": 22597056} {"current_steps": 22450, "total_steps": 42420, "loss": 0.1631, "lr": 2.6812858663019668e-05, "epoch": 10.584629891560585, "percentage": 52.92, "elapsed_time": "1:21:12", "remaining_time": "1:12:14", "throughput": 4638.69, "total_tokens": 22601824} {"current_steps": 22455, "total_steps": 42420, "loss": 0.0482, "lr": 2.6802599584566613e-05, "epoch": 10.586987270155587, "percentage": 52.93, "elapsed_time": "1:21:13", "remaining_time": "1:12:13", "throughput": 4638.73, "total_tokens": 22607008} {"current_steps": 22460, "total_steps": 42420, "loss": 0.1033, "lr": 2.6792340200964056e-05, "epoch": 10.58934464875059, "percentage": 52.95, "elapsed_time": "1:21:14", "remaining_time": "1:12:11", "throughput": 4638.77, "total_tokens": 22611968} {"current_steps": 22465, "total_steps": 42420, "loss": 0.0933, "lr": 2.678208051394873e-05, "epoch": 10.591702027345592, "percentage": 52.96, "elapsed_time": "1:21:15", "remaining_time": "1:12:10", "throughput": 4638.8, "total_tokens": 22617536} {"current_steps": 22470, "total_steps": 42420, "loss": 0.1555, "lr": 2.6771820525257434e-05, "epoch": 10.594059405940595, "percentage": 52.97, "elapsed_time": "1:21:16", "remaining_time": "1:12:09", "throughput": 4638.84, "total_tokens": 22622464} {"current_steps": 22475, "total_steps": 42420, "loss": 0.0143, "lr": 2.6761560236627008e-05, "epoch": 10.596416784535597, "percentage": 52.98, "elapsed_time": "1:21:17", "remaining_time": "1:12:08", "throughput": 4638.86, "total_tokens": 22627168} {"current_steps": 22480, "total_steps": 42420, "loss": 0.1453, "lr": 2.675129964979435e-05, "epoch": 10.5987741631306, "percentage": 52.99, "elapsed_time": "1:21:18", "remaining_time": "1:12:07", "throughput": 4638.9, "total_tokens": 22631904} {"current_steps": 22485, "total_steps": 42420, "loss": 0.2278, "lr": 2.674103876649639e-05, "epoch": 10.601131541725602, "percentage": 53.01, "elapsed_time": "1:21:19", "remaining_time": "1:12:06", "throughput": 4638.94, "total_tokens": 22636704} {"current_steps": 22490, "total_steps": 42420, "loss": 0.0465, "lr": 2.6730777588470125e-05, "epoch": 10.603488920320604, "percentage": 53.02, "elapsed_time": "1:21:20", "remaining_time": "1:12:05", "throughput": 4638.95, "total_tokens": 22641440} {"current_steps": 22495, "total_steps": 42420, "loss": 0.2015, "lr": 2.6720516117452604e-05, "epoch": 10.605846298915607, "percentage": 53.03, "elapsed_time": "1:21:21", "remaining_time": "1:12:03", "throughput": 4638.97, "total_tokens": 22645952} {"current_steps": 22500, "total_steps": 42420, "loss": 0.1917, "lr": 2.671025435518092e-05, "epoch": 10.608203677510609, "percentage": 53.04, "elapsed_time": "1:21:22", "remaining_time": "1:12:02", "throughput": 4639.0, "total_tokens": 22650912} {"current_steps": 22505, "total_steps": 42420, "loss": 0.0448, "lr": 2.6699992303392206e-05, "epoch": 10.61056105610561, "percentage": 53.05, "elapsed_time": "1:21:23", "remaining_time": "1:12:01", "throughput": 4638.95, "total_tokens": 22654880} {"current_steps": 22510, "total_steps": 42420, "loss": 0.0454, "lr": 2.668972996382366e-05, "epoch": 10.612918434700614, "percentage": 53.06, "elapsed_time": "1:21:24", "remaining_time": "1:12:00", "throughput": 4638.93, "total_tokens": 22659104} {"current_steps": 22515, "total_steps": 42420, "loss": 0.0663, "lr": 2.667946733821253e-05, "epoch": 10.615275813295614, "percentage": 53.08, "elapsed_time": "1:21:25", "remaining_time": "1:11:59", "throughput": 4638.99, "total_tokens": 22664608} {"current_steps": 22520, "total_steps": 42420, "loss": 0.2022, "lr": 2.666920442829609e-05, "epoch": 10.617633191890617, "percentage": 53.09, "elapsed_time": "1:21:26", "remaining_time": "1:11:58", "throughput": 4639.04, "total_tokens": 22669632} {"current_steps": 22525, "total_steps": 42420, "loss": 0.1735, "lr": 2.6658941235811684e-05, "epoch": 10.61999057048562, "percentage": 53.1, "elapsed_time": "1:21:27", "remaining_time": "1:11:57", "throughput": 4639.08, "total_tokens": 22674368} {"current_steps": 22530, "total_steps": 42420, "loss": 0.2019, "lr": 2.6648677762496692e-05, "epoch": 10.622347949080622, "percentage": 53.11, "elapsed_time": "1:21:28", "remaining_time": "1:11:55", "throughput": 4639.12, "total_tokens": 22679328} {"current_steps": 22535, "total_steps": 42420, "loss": 0.1788, "lr": 2.6638414010088546e-05, "epoch": 10.624705327675624, "percentage": 53.12, "elapsed_time": "1:21:29", "remaining_time": "1:11:54", "throughput": 4639.06, "total_tokens": 22683520} {"current_steps": 22540, "total_steps": 42420, "loss": 0.2394, "lr": 2.6628149980324722e-05, "epoch": 10.627062706270626, "percentage": 53.14, "elapsed_time": "1:21:30", "remaining_time": "1:11:53", "throughput": 4639.08, "total_tokens": 22688000} {"current_steps": 22545, "total_steps": 42420, "loss": 0.1466, "lr": 2.6617885674942765e-05, "epoch": 10.629420084865629, "percentage": 53.15, "elapsed_time": "1:21:31", "remaining_time": "1:11:52", "throughput": 4639.15, "total_tokens": 22693248} {"current_steps": 22550, "total_steps": 42420, "loss": 0.0683, "lr": 2.6607621095680225e-05, "epoch": 10.631777463460631, "percentage": 53.16, "elapsed_time": "1:21:32", "remaining_time": "1:11:51", "throughput": 4639.18, "total_tokens": 22697856} {"current_steps": 22555, "total_steps": 42420, "loss": 0.0762, "lr": 2.6597356244274724e-05, "epoch": 10.634134842055634, "percentage": 53.17, "elapsed_time": "1:21:33", "remaining_time": "1:11:50", "throughput": 4639.24, "total_tokens": 22703616} {"current_steps": 22560, "total_steps": 42420, "loss": 0.0759, "lr": 2.6587091122463936e-05, "epoch": 10.636492220650636, "percentage": 53.18, "elapsed_time": "1:21:34", "remaining_time": "1:11:49", "throughput": 4639.21, "total_tokens": 22708416} {"current_steps": 22565, "total_steps": 42420, "loss": 0.2111, "lr": 2.6576825731985576e-05, "epoch": 10.638849599245638, "percentage": 53.19, "elapsed_time": "1:21:35", "remaining_time": "1:11:47", "throughput": 4639.21, "total_tokens": 22712512} {"current_steps": 22570, "total_steps": 42420, "loss": 0.1708, "lr": 2.6566560074577383e-05, "epoch": 10.64120697784064, "percentage": 53.21, "elapsed_time": "1:21:36", "remaining_time": "1:11:46", "throughput": 4639.19, "total_tokens": 22716768} {"current_steps": 22575, "total_steps": 42420, "loss": 0.0572, "lr": 2.6556294151977168e-05, "epoch": 10.643564356435643, "percentage": 53.22, "elapsed_time": "1:21:37", "remaining_time": "1:11:45", "throughput": 4639.19, "total_tokens": 22721664} {"current_steps": 22580, "total_steps": 42420, "loss": 0.0906, "lr": 2.6546027965922783e-05, "epoch": 10.645921735030646, "percentage": 53.23, "elapsed_time": "1:21:38", "remaining_time": "1:11:44", "throughput": 4639.25, "total_tokens": 22727040} {"current_steps": 22585, "total_steps": 42420, "loss": 0.1157, "lr": 2.6535761518152115e-05, "epoch": 10.648279113625648, "percentage": 53.24, "elapsed_time": "1:21:39", "remaining_time": "1:11:43", "throughput": 4639.29, "total_tokens": 22731936} {"current_steps": 22590, "total_steps": 42420, "loss": 0.2467, "lr": 2.652549481040309e-05, "epoch": 10.65063649222065, "percentage": 53.25, "elapsed_time": "1:21:40", "remaining_time": "1:11:42", "throughput": 4639.31, "total_tokens": 22736352} {"current_steps": 22595, "total_steps": 42420, "loss": 0.102, "lr": 2.6515227844413698e-05, "epoch": 10.652993870815653, "percentage": 53.26, "elapsed_time": "1:21:41", "remaining_time": "1:11:40", "throughput": 4639.34, "total_tokens": 22740576} {"current_steps": 22600, "total_steps": 42420, "loss": 0.173, "lr": 2.650496062192196e-05, "epoch": 10.655351249410655, "percentage": 53.28, "elapsed_time": "1:21:42", "remaining_time": "1:11:39", "throughput": 4639.39, "total_tokens": 22745792} {"current_steps": 22605, "total_steps": 42420, "loss": 0.2231, "lr": 2.6494693144665943e-05, "epoch": 10.657708628005658, "percentage": 53.29, "elapsed_time": "1:21:43", "remaining_time": "1:11:38", "throughput": 4639.38, "total_tokens": 22749952} {"current_steps": 22610, "total_steps": 42420, "loss": 0.0502, "lr": 2.6484425414383756e-05, "epoch": 10.66006600660066, "percentage": 53.3, "elapsed_time": "1:21:44", "remaining_time": "1:11:37", "throughput": 4639.38, "total_tokens": 22753952} {"current_steps": 22615, "total_steps": 42420, "loss": 0.0663, "lr": 2.6474157432813545e-05, "epoch": 10.662423385195662, "percentage": 53.31, "elapsed_time": "1:21:45", "remaining_time": "1:11:35", "throughput": 4639.4, "total_tokens": 22758240} {"current_steps": 22620, "total_steps": 42420, "loss": 0.2497, "lr": 2.6463889201693516e-05, "epoch": 10.664780763790665, "percentage": 53.32, "elapsed_time": "1:21:46", "remaining_time": "1:11:34", "throughput": 4639.45, "total_tokens": 22763328} {"current_steps": 22625, "total_steps": 42420, "loss": 0.0946, "lr": 2.6453620722761896e-05, "epoch": 10.667138142385667, "percentage": 53.34, "elapsed_time": "1:21:47", "remaining_time": "1:11:33", "throughput": 4639.46, "total_tokens": 22767648} {"current_steps": 22630, "total_steps": 42420, "loss": 0.2562, "lr": 2.6443351997756976e-05, "epoch": 10.66949552098067, "percentage": 53.35, "elapsed_time": "1:21:48", "remaining_time": "1:11:32", "throughput": 4639.48, "total_tokens": 22772512} {"current_steps": 22635, "total_steps": 42420, "loss": 0.1875, "lr": 2.6433083028417067e-05, "epoch": 10.671852899575672, "percentage": 53.36, "elapsed_time": "1:21:49", "remaining_time": "1:11:31", "throughput": 4639.54, "total_tokens": 22777312} {"current_steps": 22640, "total_steps": 42420, "loss": 0.1334, "lr": 2.642281381648053e-05, "epoch": 10.674210278170674, "percentage": 53.37, "elapsed_time": "1:21:50", "remaining_time": "1:11:30", "throughput": 4639.58, "total_tokens": 22781696} {"current_steps": 22645, "total_steps": 42420, "loss": 0.0865, "lr": 2.641254436368577e-05, "epoch": 10.676567656765677, "percentage": 53.38, "elapsed_time": "1:21:51", "remaining_time": "1:11:28", "throughput": 4639.57, "total_tokens": 22786592} {"current_steps": 22650, "total_steps": 42420, "loss": 0.1755, "lr": 2.6402274671771238e-05, "epoch": 10.67892503536068, "percentage": 53.39, "elapsed_time": "1:21:52", "remaining_time": "1:11:27", "throughput": 4639.68, "total_tokens": 22792928} {"current_steps": 22655, "total_steps": 42420, "loss": 0.0814, "lr": 2.6392004742475405e-05, "epoch": 10.681282413955682, "percentage": 53.41, "elapsed_time": "1:21:53", "remaining_time": "1:11:26", "throughput": 4639.72, "total_tokens": 22797568} {"current_steps": 22660, "total_steps": 42420, "loss": 0.1532, "lr": 2.6381734577536816e-05, "epoch": 10.683639792550684, "percentage": 53.42, "elapsed_time": "1:21:54", "remaining_time": "1:11:25", "throughput": 4639.72, "total_tokens": 22801792} {"current_steps": 22665, "total_steps": 42420, "loss": 0.1156, "lr": 2.6371464178694012e-05, "epoch": 10.685997171145686, "percentage": 53.43, "elapsed_time": "1:21:55", "remaining_time": "1:11:24", "throughput": 4639.75, "total_tokens": 22806848} {"current_steps": 22670, "total_steps": 42420, "loss": 0.1597, "lr": 2.636119354768562e-05, "epoch": 10.688354549740689, "percentage": 53.44, "elapsed_time": "1:21:56", "remaining_time": "1:11:23", "throughput": 4639.77, "total_tokens": 22810944} {"current_steps": 22675, "total_steps": 42420, "loss": 0.1027, "lr": 2.6350922686250263e-05, "epoch": 10.690711928335691, "percentage": 53.45, "elapsed_time": "1:21:57", "remaining_time": "1:11:22", "throughput": 4639.82, "total_tokens": 22816096} {"current_steps": 22680, "total_steps": 42420, "loss": 0.0436, "lr": 2.6340651596126636e-05, "epoch": 10.693069306930694, "percentage": 53.47, "elapsed_time": "1:21:58", "remaining_time": "1:11:20", "throughput": 4639.88, "total_tokens": 22821408} {"current_steps": 22685, "total_steps": 42420, "loss": 0.1192, "lr": 2.6330380279053456e-05, "epoch": 10.695426685525696, "percentage": 53.48, "elapsed_time": "1:21:59", "remaining_time": "1:11:19", "throughput": 4639.83, "total_tokens": 22825632} {"current_steps": 22690, "total_steps": 42420, "loss": 0.2843, "lr": 2.632010873676949e-05, "epoch": 10.697784064120698, "percentage": 53.49, "elapsed_time": "1:22:00", "remaining_time": "1:11:18", "throughput": 4639.88, "total_tokens": 22830272} {"current_steps": 22695, "total_steps": 42420, "loss": 0.1409, "lr": 2.6309836971013517e-05, "epoch": 10.700141442715701, "percentage": 53.5, "elapsed_time": "1:22:01", "remaining_time": "1:11:17", "throughput": 4639.88, "total_tokens": 22835008} {"current_steps": 22700, "total_steps": 42420, "loss": 0.2197, "lr": 2.6299564983524388e-05, "epoch": 10.702498821310703, "percentage": 53.51, "elapsed_time": "1:22:02", "remaining_time": "1:11:16", "throughput": 4639.92, "total_tokens": 22840512} {"current_steps": 22705, "total_steps": 42420, "loss": 0.0903, "lr": 2.6289292776040975e-05, "epoch": 10.704856199905706, "percentage": 53.52, "elapsed_time": "1:22:03", "remaining_time": "1:11:15", "throughput": 4639.93, "total_tokens": 22845376} {"current_steps": 22710, "total_steps": 42420, "loss": 0.1508, "lr": 2.627902035030219e-05, "epoch": 10.707213578500706, "percentage": 53.54, "elapsed_time": "1:22:04", "remaining_time": "1:11:14", "throughput": 4639.67, "total_tokens": 22850144} {"current_steps": 22715, "total_steps": 42420, "loss": 0.1221, "lr": 2.626874770804697e-05, "epoch": 10.70957095709571, "percentage": 53.55, "elapsed_time": "1:22:05", "remaining_time": "1:11:13", "throughput": 4639.74, "total_tokens": 22855264} {"current_steps": 22720, "total_steps": 42420, "loss": 0.118, "lr": 2.625847485101431e-05, "epoch": 10.711928335690711, "percentage": 53.56, "elapsed_time": "1:22:06", "remaining_time": "1:11:12", "throughput": 4639.77, "total_tokens": 22860064} {"current_steps": 22725, "total_steps": 42420, "loss": 0.0988, "lr": 2.6248201780943222e-05, "epoch": 10.714285714285714, "percentage": 53.57, "elapsed_time": "1:22:08", "remaining_time": "1:11:11", "throughput": 4639.82, "total_tokens": 22865920} {"current_steps": 22730, "total_steps": 42420, "loss": 0.0448, "lr": 2.6237928499572766e-05, "epoch": 10.716643092880716, "percentage": 53.58, "elapsed_time": "1:22:09", "remaining_time": "1:11:09", "throughput": 4639.83, "total_tokens": 22870016} {"current_steps": 22735, "total_steps": 42420, "loss": 0.1552, "lr": 2.6227655008642036e-05, "epoch": 10.719000471475718, "percentage": 53.6, "elapsed_time": "1:22:10", "remaining_time": "1:11:08", "throughput": 4639.91, "total_tokens": 22876800} {"current_steps": 22740, "total_steps": 42420, "loss": 0.2183, "lr": 2.621738130989016e-05, "epoch": 10.72135785007072, "percentage": 53.61, "elapsed_time": "1:22:11", "remaining_time": "1:11:07", "throughput": 4639.94, "total_tokens": 22881376} {"current_steps": 22745, "total_steps": 42420, "loss": 0.1229, "lr": 2.6207107405056293e-05, "epoch": 10.723715228665723, "percentage": 53.62, "elapsed_time": "1:22:12", "remaining_time": "1:11:06", "throughput": 4640.01, "total_tokens": 22886208} {"current_steps": 22750, "total_steps": 42420, "loss": 0.2207, "lr": 2.6196833295879637e-05, "epoch": 10.726072607260726, "percentage": 53.63, "elapsed_time": "1:22:13", "remaining_time": "1:11:05", "throughput": 4640.08, "total_tokens": 22891808} {"current_steps": 22755, "total_steps": 42420, "loss": 0.1377, "lr": 2.618655898409943e-05, "epoch": 10.728429985855728, "percentage": 53.64, "elapsed_time": "1:22:14", "remaining_time": "1:11:04", "throughput": 4640.09, "total_tokens": 22896544} {"current_steps": 22760, "total_steps": 42420, "loss": 0.0315, "lr": 2.6176284471454932e-05, "epoch": 10.73078736445073, "percentage": 53.65, "elapsed_time": "1:22:15", "remaining_time": "1:11:03", "throughput": 4640.11, "total_tokens": 22901504} {"current_steps": 22765, "total_steps": 42420, "loss": 0.023, "lr": 2.616600975968544e-05, "epoch": 10.733144743045733, "percentage": 53.67, "elapsed_time": "1:22:16", "remaining_time": "1:11:02", "throughput": 4640.15, "total_tokens": 22906432} {"current_steps": 22770, "total_steps": 42420, "loss": 0.1859, "lr": 2.6155734850530296e-05, "epoch": 10.735502121640735, "percentage": 53.68, "elapsed_time": "1:22:17", "remaining_time": "1:11:00", "throughput": 4640.16, "total_tokens": 22910656} {"current_steps": 22775, "total_steps": 42420, "loss": 0.0804, "lr": 2.6145459745728874e-05, "epoch": 10.737859500235738, "percentage": 53.69, "elapsed_time": "1:22:18", "remaining_time": "1:10:59", "throughput": 4640.18, "total_tokens": 22914976} {"current_steps": 22780, "total_steps": 42420, "loss": 0.0638, "lr": 2.6135184447020557e-05, "epoch": 10.74021687883074, "percentage": 53.7, "elapsed_time": "1:22:19", "remaining_time": "1:10:58", "throughput": 4640.24, "total_tokens": 22920768} {"current_steps": 22785, "total_steps": 42420, "loss": 0.0836, "lr": 2.6124908956144784e-05, "epoch": 10.742574257425742, "percentage": 53.71, "elapsed_time": "1:22:20", "remaining_time": "1:10:57", "throughput": 4640.32, "total_tokens": 22926528} {"current_steps": 22790, "total_steps": 42420, "loss": 0.0828, "lr": 2.611463327484103e-05, "epoch": 10.744931636020745, "percentage": 53.72, "elapsed_time": "1:22:21", "remaining_time": "1:10:56", "throughput": 4640.31, "total_tokens": 22931040} {"current_steps": 22795, "total_steps": 42420, "loss": 0.1132, "lr": 2.610435740484879e-05, "epoch": 10.747289014615747, "percentage": 53.74, "elapsed_time": "1:22:22", "remaining_time": "1:10:55", "throughput": 4640.37, "total_tokens": 22936736} {"current_steps": 22800, "total_steps": 42420, "loss": 0.0292, "lr": 2.6094081347907588e-05, "epoch": 10.74964639321075, "percentage": 53.75, "elapsed_time": "1:22:23", "remaining_time": "1:10:54", "throughput": 4640.39, "total_tokens": 22941408} {"current_steps": 22805, "total_steps": 42420, "loss": 0.0742, "lr": 2.6083805105756993e-05, "epoch": 10.752003771805752, "percentage": 53.76, "elapsed_time": "1:22:24", "remaining_time": "1:10:53", "throughput": 4640.45, "total_tokens": 22946528} {"current_steps": 22810, "total_steps": 42420, "loss": 0.041, "lr": 2.6073528680136588e-05, "epoch": 10.754361150400754, "percentage": 53.77, "elapsed_time": "1:22:25", "remaining_time": "1:10:51", "throughput": 4640.48, "total_tokens": 22950880} {"current_steps": 22815, "total_steps": 42420, "loss": 0.1808, "lr": 2.6063252072786016e-05, "epoch": 10.756718528995757, "percentage": 53.78, "elapsed_time": "1:22:26", "remaining_time": "1:10:50", "throughput": 4640.5, "total_tokens": 22955232} {"current_steps": 22820, "total_steps": 42420, "loss": 0.2133, "lr": 2.6052975285444914e-05, "epoch": 10.75907590759076, "percentage": 53.8, "elapsed_time": "1:22:27", "remaining_time": "1:10:49", "throughput": 4640.55, "total_tokens": 22960384} {"current_steps": 22825, "total_steps": 42420, "loss": 0.033, "lr": 2.6042698319852975e-05, "epoch": 10.761433286185762, "percentage": 53.81, "elapsed_time": "1:22:28", "remaining_time": "1:10:48", "throughput": 4640.55, "total_tokens": 22964544} {"current_steps": 22830, "total_steps": 42420, "loss": 0.0368, "lr": 2.6032421177749917e-05, "epoch": 10.763790664780764, "percentage": 53.82, "elapsed_time": "1:22:29", "remaining_time": "1:10:47", "throughput": 4640.58, "total_tokens": 22969376} {"current_steps": 22835, "total_steps": 42420, "loss": 0.064, "lr": 2.6022143860875485e-05, "epoch": 10.766148043375766, "percentage": 53.83, "elapsed_time": "1:22:30", "remaining_time": "1:10:46", "throughput": 4640.64, "total_tokens": 22974784} {"current_steps": 22840, "total_steps": 42420, "loss": 0.1169, "lr": 2.601186637096945e-05, "epoch": 10.768505421970769, "percentage": 53.84, "elapsed_time": "1:22:31", "remaining_time": "1:10:44", "throughput": 4640.68, "total_tokens": 22979168} {"current_steps": 22845, "total_steps": 42420, "loss": 0.1356, "lr": 2.600158870977162e-05, "epoch": 10.770862800565771, "percentage": 53.85, "elapsed_time": "1:22:32", "remaining_time": "1:10:43", "throughput": 4640.73, "total_tokens": 22984096} {"current_steps": 22850, "total_steps": 42420, "loss": 0.0985, "lr": 2.599131087902183e-05, "epoch": 10.773220179160774, "percentage": 53.87, "elapsed_time": "1:22:33", "remaining_time": "1:10:42", "throughput": 4640.73, "total_tokens": 22988832} {"current_steps": 22855, "total_steps": 42420, "loss": 0.2404, "lr": 2.5981032880459932e-05, "epoch": 10.775577557755776, "percentage": 53.88, "elapsed_time": "1:22:34", "remaining_time": "1:10:41", "throughput": 4640.77, "total_tokens": 22993952} {"current_steps": 22860, "total_steps": 42420, "loss": 0.0992, "lr": 2.5970754715825836e-05, "epoch": 10.777934936350778, "percentage": 53.89, "elapsed_time": "1:22:35", "remaining_time": "1:10:40", "throughput": 4640.79, "total_tokens": 22998688} {"current_steps": 22865, "total_steps": 42420, "loss": 0.0624, "lr": 2.596047638685944e-05, "epoch": 10.78029231494578, "percentage": 53.9, "elapsed_time": "1:22:36", "remaining_time": "1:10:39", "throughput": 4640.8, "total_tokens": 23003200} {"current_steps": 22870, "total_steps": 42420, "loss": 0.1886, "lr": 2.59501978953007e-05, "epoch": 10.782649693540783, "percentage": 53.91, "elapsed_time": "1:22:37", "remaining_time": "1:10:38", "throughput": 4640.85, "total_tokens": 23008288} {"current_steps": 22875, "total_steps": 42420, "loss": 0.2403, "lr": 2.593991924288959e-05, "epoch": 10.785007072135786, "percentage": 53.93, "elapsed_time": "1:22:38", "remaining_time": "1:10:36", "throughput": 4640.87, "total_tokens": 23012704} {"current_steps": 22880, "total_steps": 42420, "loss": 0.0671, "lr": 2.5929640431366114e-05, "epoch": 10.787364450730788, "percentage": 53.94, "elapsed_time": "1:22:39", "remaining_time": "1:10:35", "throughput": 4640.92, "total_tokens": 23018208} {"current_steps": 22885, "total_steps": 42420, "loss": 0.0873, "lr": 2.5919361462470294e-05, "epoch": 10.78972182932579, "percentage": 53.95, "elapsed_time": "1:22:40", "remaining_time": "1:10:34", "throughput": 4640.97, "total_tokens": 23022880} {"current_steps": 22890, "total_steps": 42420, "loss": 0.0717, "lr": 2.5909082337942185e-05, "epoch": 10.792079207920793, "percentage": 53.96, "elapsed_time": "1:22:41", "remaining_time": "1:10:33", "throughput": 4641.0, "total_tokens": 23028000} {"current_steps": 22895, "total_steps": 42420, "loss": 0.0694, "lr": 2.5898803059521874e-05, "epoch": 10.794436586515795, "percentage": 53.97, "elapsed_time": "1:22:42", "remaining_time": "1:10:32", "throughput": 4641.06, "total_tokens": 23033216} {"current_steps": 22900, "total_steps": 42420, "loss": 0.1306, "lr": 2.5888523628949472e-05, "epoch": 10.796793965110798, "percentage": 53.98, "elapsed_time": "1:22:43", "remaining_time": "1:10:31", "throughput": 4641.1, "total_tokens": 23038240} {"current_steps": 22905, "total_steps": 42420, "loss": 0.1024, "lr": 2.58782440479651e-05, "epoch": 10.799151343705798, "percentage": 54.0, "elapsed_time": "1:22:44", "remaining_time": "1:10:30", "throughput": 4641.1, "total_tokens": 23042848} {"current_steps": 22910, "total_steps": 42420, "loss": 0.1615, "lr": 2.5867964318308922e-05, "epoch": 10.801508722300802, "percentage": 54.01, "elapsed_time": "1:22:45", "remaining_time": "1:10:28", "throughput": 4641.1, "total_tokens": 23047136} {"current_steps": 22915, "total_steps": 42420, "loss": 0.1165, "lr": 2.5857684441721124e-05, "epoch": 10.803866100895803, "percentage": 54.02, "elapsed_time": "1:22:46", "remaining_time": "1:10:27", "throughput": 4641.13, "total_tokens": 23051968} {"current_steps": 22920, "total_steps": 42420, "loss": 0.1349, "lr": 2.5847404419941917e-05, "epoch": 10.806223479490805, "percentage": 54.03, "elapsed_time": "1:22:47", "remaining_time": "1:10:26", "throughput": 4641.19, "total_tokens": 23056992} {"current_steps": 22925, "total_steps": 42420, "loss": 0.1763, "lr": 2.5837124254711524e-05, "epoch": 10.808580858085808, "percentage": 54.04, "elapsed_time": "1:22:49", "remaining_time": "1:10:25", "throughput": 4641.29, "total_tokens": 23063072} {"current_steps": 22930, "total_steps": 42420, "loss": 0.2828, "lr": 2.5826843947770212e-05, "epoch": 10.81093823668081, "percentage": 54.05, "elapsed_time": "1:22:50", "remaining_time": "1:10:24", "throughput": 4641.38, "total_tokens": 23070944} {"current_steps": 22935, "total_steps": 42420, "loss": 0.065, "lr": 2.5816563500858254e-05, "epoch": 10.813295615275813, "percentage": 54.07, "elapsed_time": "1:22:51", "remaining_time": "1:10:23", "throughput": 4641.35, "total_tokens": 23074912} {"current_steps": 22940, "total_steps": 42420, "loss": 0.0845, "lr": 2.5806282915715967e-05, "epoch": 10.815652993870815, "percentage": 54.08, "elapsed_time": "1:22:52", "remaining_time": "1:10:22", "throughput": 4641.42, "total_tokens": 23080512} {"current_steps": 22945, "total_steps": 42420, "loss": 0.1842, "lr": 2.579600219408367e-05, "epoch": 10.818010372465817, "percentage": 54.09, "elapsed_time": "1:22:53", "remaining_time": "1:10:21", "throughput": 4641.44, "total_tokens": 23085792} {"current_steps": 22950, "total_steps": 42420, "loss": 0.0399, "lr": 2.5785721337701706e-05, "epoch": 10.82036775106082, "percentage": 54.1, "elapsed_time": "1:22:54", "remaining_time": "1:10:20", "throughput": 4641.5, "total_tokens": 23090784} {"current_steps": 22955, "total_steps": 42420, "loss": 0.2223, "lr": 2.577544034831047e-05, "epoch": 10.822725129655822, "percentage": 54.11, "elapsed_time": "1:22:55", "remaining_time": "1:10:19", "throughput": 4641.48, "total_tokens": 23094880} {"current_steps": 22960, "total_steps": 42420, "loss": 0.1388, "lr": 2.5765159227650353e-05, "epoch": 10.825082508250825, "percentage": 54.13, "elapsed_time": "1:22:56", "remaining_time": "1:10:18", "throughput": 4641.47, "total_tokens": 23099136} {"current_steps": 22965, "total_steps": 42420, "loss": 0.1606, "lr": 2.5754877977461767e-05, "epoch": 10.827439886845827, "percentage": 54.14, "elapsed_time": "1:22:57", "remaining_time": "1:10:16", "throughput": 4641.48, "total_tokens": 23103904} {"current_steps": 22970, "total_steps": 42420, "loss": 0.0912, "lr": 2.5744596599485156e-05, "epoch": 10.82979726544083, "percentage": 54.15, "elapsed_time": "1:22:58", "remaining_time": "1:10:15", "throughput": 4641.5, "total_tokens": 23108064} {"current_steps": 22975, "total_steps": 42420, "loss": 0.0493, "lr": 2.5734315095460982e-05, "epoch": 10.832154644035832, "percentage": 54.16, "elapsed_time": "1:22:59", "remaining_time": "1:10:14", "throughput": 4641.54, "total_tokens": 23112704} {"current_steps": 22980, "total_steps": 42420, "loss": 0.153, "lr": 2.5724033467129726e-05, "epoch": 10.834512022630834, "percentage": 54.17, "elapsed_time": "1:23:00", "remaining_time": "1:10:13", "throughput": 4641.6, "total_tokens": 23118080} {"current_steps": 22985, "total_steps": 42420, "loss": 0.1273, "lr": 2.571375171623191e-05, "epoch": 10.836869401225837, "percentage": 54.18, "elapsed_time": "1:23:01", "remaining_time": "1:10:12", "throughput": 4641.66, "total_tokens": 23123072} {"current_steps": 22990, "total_steps": 42420, "loss": 0.0993, "lr": 2.5703469844508038e-05, "epoch": 10.839226779820839, "percentage": 54.2, "elapsed_time": "1:23:02", "remaining_time": "1:10:11", "throughput": 4641.74, "total_tokens": 23128768} {"current_steps": 22995, "total_steps": 42420, "loss": 0.2889, "lr": 2.5693187853698664e-05, "epoch": 10.841584158415841, "percentage": 54.21, "elapsed_time": "1:23:03", "remaining_time": "1:10:10", "throughput": 4641.8, "total_tokens": 23134400} {"current_steps": 23000, "total_steps": 42420, "loss": 0.2165, "lr": 2.5682905745544354e-05, "epoch": 10.843941537010844, "percentage": 54.22, "elapsed_time": "1:23:04", "remaining_time": "1:10:09", "throughput": 4641.83, "total_tokens": 23139232} {"current_steps": 23005, "total_steps": 42420, "loss": 0.1153, "lr": 2.567262352178571e-05, "epoch": 10.846298915605846, "percentage": 54.23, "elapsed_time": "1:23:05", "remaining_time": "1:10:07", "throughput": 4641.83, "total_tokens": 23144032} {"current_steps": 23010, "total_steps": 42420, "loss": 0.0674, "lr": 2.566234118416331e-05, "epoch": 10.848656294200849, "percentage": 54.24, "elapsed_time": "1:23:07", "remaining_time": "1:10:06", "throughput": 4641.9, "total_tokens": 23150080} {"current_steps": 23015, "total_steps": 42420, "loss": 0.3021, "lr": 2.56520587344178e-05, "epoch": 10.851013672795851, "percentage": 54.26, "elapsed_time": "1:23:08", "remaining_time": "1:10:05", "throughput": 4641.95, "total_tokens": 23155328} {"current_steps": 23020, "total_steps": 42420, "loss": 0.1907, "lr": 2.5641776174289816e-05, "epoch": 10.853371051390853, "percentage": 54.27, "elapsed_time": "1:23:09", "remaining_time": "1:10:04", "throughput": 4642.0, "total_tokens": 23160544} {"current_steps": 23025, "total_steps": 42420, "loss": 0.0661, "lr": 2.5631493505520028e-05, "epoch": 10.855728429985856, "percentage": 54.28, "elapsed_time": "1:23:10", "remaining_time": "1:10:03", "throughput": 4642.03, "total_tokens": 23164960} {"current_steps": 23030, "total_steps": 42420, "loss": 0.159, "lr": 2.5621210729849105e-05, "epoch": 10.858085808580858, "percentage": 54.29, "elapsed_time": "1:23:11", "remaining_time": "1:10:02", "throughput": 4642.07, "total_tokens": 23170016} {"current_steps": 23035, "total_steps": 42420, "loss": 0.0577, "lr": 2.561092784901775e-05, "epoch": 10.86044318717586, "percentage": 54.3, "elapsed_time": "1:23:12", "remaining_time": "1:10:01", "throughput": 4642.13, "total_tokens": 23174912} {"current_steps": 23040, "total_steps": 42420, "loss": 0.2291, "lr": 2.5600644864766687e-05, "epoch": 10.862800565770863, "percentage": 54.31, "elapsed_time": "1:23:13", "remaining_time": "1:10:00", "throughput": 4642.14, "total_tokens": 23179232} {"current_steps": 23045, "total_steps": 42420, "loss": 0.0623, "lr": 2.5590361778836652e-05, "epoch": 10.865157944365865, "percentage": 54.33, "elapsed_time": "1:23:14", "remaining_time": "1:09:59", "throughput": 4642.2, "total_tokens": 23184960} {"current_steps": 23050, "total_steps": 42420, "loss": 0.101, "lr": 2.558007859296839e-05, "epoch": 10.867515322960868, "percentage": 54.34, "elapsed_time": "1:23:15", "remaining_time": "1:09:57", "throughput": 4642.22, "total_tokens": 23189312} {"current_steps": 23055, "total_steps": 42420, "loss": 0.0476, "lr": 2.556979530890266e-05, "epoch": 10.86987270155587, "percentage": 54.35, "elapsed_time": "1:23:16", "remaining_time": "1:09:56", "throughput": 4642.26, "total_tokens": 23193824} {"current_steps": 23060, "total_steps": 42420, "loss": 0.2348, "lr": 2.555951192838027e-05, "epoch": 10.872230080150873, "percentage": 54.36, "elapsed_time": "1:23:17", "remaining_time": "1:09:55", "throughput": 4642.3, "total_tokens": 23198464} {"current_steps": 23065, "total_steps": 42420, "loss": 0.0999, "lr": 2.554922845314201e-05, "epoch": 10.874587458745875, "percentage": 54.37, "elapsed_time": "1:23:18", "remaining_time": "1:09:54", "throughput": 4642.38, "total_tokens": 23204416} {"current_steps": 23070, "total_steps": 42420, "loss": 0.1312, "lr": 2.5538944884928694e-05, "epoch": 10.876944837340877, "percentage": 54.38, "elapsed_time": "1:23:19", "remaining_time": "1:09:53", "throughput": 4642.46, "total_tokens": 23210400} {"current_steps": 23075, "total_steps": 42420, "loss": 0.0371, "lr": 2.5528661225481165e-05, "epoch": 10.87930221593588, "percentage": 54.4, "elapsed_time": "1:23:20", "remaining_time": "1:09:52", "throughput": 4642.52, "total_tokens": 23215840} {"current_steps": 23080, "total_steps": 42420, "loss": 0.2309, "lr": 2.551837747654027e-05, "epoch": 10.881659594530882, "percentage": 54.41, "elapsed_time": "1:23:21", "remaining_time": "1:09:51", "throughput": 4642.58, "total_tokens": 23221632} {"current_steps": 23085, "total_steps": 42420, "loss": 0.0874, "lr": 2.5508093639846857e-05, "epoch": 10.884016973125885, "percentage": 54.42, "elapsed_time": "1:23:22", "remaining_time": "1:09:50", "throughput": 4642.6, "total_tokens": 23226176} {"current_steps": 23090, "total_steps": 42420, "loss": 0.0806, "lr": 2.549780971714183e-05, "epoch": 10.886374351720887, "percentage": 54.43, "elapsed_time": "1:23:23", "remaining_time": "1:09:49", "throughput": 4642.62, "total_tokens": 23231040} {"current_steps": 23095, "total_steps": 42420, "loss": 0.1059, "lr": 2.548752571016606e-05, "epoch": 10.88873173031589, "percentage": 54.44, "elapsed_time": "1:23:24", "remaining_time": "1:09:47", "throughput": 4642.65, "total_tokens": 23236192} {"current_steps": 23100, "total_steps": 42420, "loss": 0.0889, "lr": 2.5477241620660468e-05, "epoch": 10.891089108910892, "percentage": 54.46, "elapsed_time": "1:23:25", "remaining_time": "1:09:46", "throughput": 4642.66, "total_tokens": 23240640} {"current_steps": 23105, "total_steps": 42420, "loss": 0.1297, "lr": 2.5466957450365976e-05, "epoch": 10.893446487505894, "percentage": 54.47, "elapsed_time": "1:23:27", "remaining_time": "1:09:45", "throughput": 4642.7, "total_tokens": 23246752} {"current_steps": 23110, "total_steps": 42420, "loss": 0.0739, "lr": 2.5456673201023513e-05, "epoch": 10.895803866100895, "percentage": 54.48, "elapsed_time": "1:23:28", "remaining_time": "1:09:44", "throughput": 4642.74, "total_tokens": 23251904} {"current_steps": 23115, "total_steps": 42420, "loss": 0.1292, "lr": 2.5446388874374034e-05, "epoch": 10.898161244695899, "percentage": 54.49, "elapsed_time": "1:23:29", "remaining_time": "1:09:43", "throughput": 4642.73, "total_tokens": 23256128} {"current_steps": 23120, "total_steps": 42420, "loss": 0.1867, "lr": 2.543610447215849e-05, "epoch": 10.9005186232909, "percentage": 54.5, "elapsed_time": "1:23:30", "remaining_time": "1:09:42", "throughput": 4642.77, "total_tokens": 23260864} {"current_steps": 23125, "total_steps": 42420, "loss": 0.1968, "lr": 2.5425819996117873e-05, "epoch": 10.902876001885902, "percentage": 54.51, "elapsed_time": "1:23:31", "remaining_time": "1:09:41", "throughput": 4642.81, "total_tokens": 23266176} {"current_steps": 23130, "total_steps": 42420, "loss": 0.1471, "lr": 2.541553544799316e-05, "epoch": 10.905233380480905, "percentage": 54.53, "elapsed_time": "1:23:32", "remaining_time": "1:09:40", "throughput": 4642.84, "total_tokens": 23271072} {"current_steps": 23135, "total_steps": 42420, "loss": 0.0426, "lr": 2.5405250829525344e-05, "epoch": 10.907590759075907, "percentage": 54.54, "elapsed_time": "1:23:33", "remaining_time": "1:09:39", "throughput": 4642.92, "total_tokens": 23276448} {"current_steps": 23140, "total_steps": 42420, "loss": 0.0732, "lr": 2.5394966142455445e-05, "epoch": 10.90994813767091, "percentage": 54.55, "elapsed_time": "1:23:34", "remaining_time": "1:09:37", "throughput": 4642.93, "total_tokens": 23281536} {"current_steps": 23145, "total_steps": 42420, "loss": 0.0725, "lr": 2.5384681388524488e-05, "epoch": 10.912305516265912, "percentage": 54.56, "elapsed_time": "1:23:35", "remaining_time": "1:09:37", "throughput": 4643.03, "total_tokens": 23289408} {"current_steps": 23150, "total_steps": 42420, "loss": 0.0909, "lr": 2.5374396569473506e-05, "epoch": 10.914662894860914, "percentage": 54.57, "elapsed_time": "1:23:36", "remaining_time": "1:09:36", "throughput": 4643.07, "total_tokens": 23294112} {"current_steps": 23155, "total_steps": 42420, "loss": 0.1161, "lr": 2.5364111687043535e-05, "epoch": 10.917020273455917, "percentage": 54.59, "elapsed_time": "1:23:37", "remaining_time": "1:09:34", "throughput": 4643.11, "total_tokens": 23298944} {"current_steps": 23160, "total_steps": 42420, "loss": 0.0351, "lr": 2.535382674297564e-05, "epoch": 10.919377652050919, "percentage": 54.6, "elapsed_time": "1:23:38", "remaining_time": "1:09:33", "throughput": 4643.11, "total_tokens": 23303616} {"current_steps": 23165, "total_steps": 42420, "loss": 0.0956, "lr": 2.5343541739010884e-05, "epoch": 10.921735030645921, "percentage": 54.61, "elapsed_time": "1:23:39", "remaining_time": "1:09:32", "throughput": 4643.14, "total_tokens": 23308512} {"current_steps": 23170, "total_steps": 42420, "loss": 0.0582, "lr": 2.533325667689035e-05, "epoch": 10.924092409240924, "percentage": 54.62, "elapsed_time": "1:23:40", "remaining_time": "1:09:31", "throughput": 4643.16, "total_tokens": 23312832} {"current_steps": 23175, "total_steps": 42420, "loss": 0.0558, "lr": 2.5322971558355112e-05, "epoch": 10.926449787835926, "percentage": 54.63, "elapsed_time": "1:23:41", "remaining_time": "1:09:30", "throughput": 4643.21, "total_tokens": 23317888} {"current_steps": 23180, "total_steps": 42420, "loss": 0.1752, "lr": 2.531268638514627e-05, "epoch": 10.928807166430929, "percentage": 54.64, "elapsed_time": "1:23:42", "remaining_time": "1:09:29", "throughput": 4643.24, "total_tokens": 23322432} {"current_steps": 23185, "total_steps": 42420, "loss": 0.1246, "lr": 2.530240115900494e-05, "epoch": 10.931164545025931, "percentage": 54.66, "elapsed_time": "1:23:43", "remaining_time": "1:09:27", "throughput": 4643.23, "total_tokens": 23326784} {"current_steps": 23190, "total_steps": 42420, "loss": 0.0452, "lr": 2.529211588167223e-05, "epoch": 10.933521923620933, "percentage": 54.67, "elapsed_time": "1:23:45", "remaining_time": "1:09:26", "throughput": 4643.31, "total_tokens": 23332928} {"current_steps": 23195, "total_steps": 42420, "loss": 0.0901, "lr": 2.5281830554889262e-05, "epoch": 10.935879302215936, "percentage": 54.68, "elapsed_time": "1:23:46", "remaining_time": "1:09:25", "throughput": 4643.35, "total_tokens": 23337824} {"current_steps": 23200, "total_steps": 42420, "loss": 0.1581, "lr": 2.527154518039716e-05, "epoch": 10.938236680810938, "percentage": 54.69, "elapsed_time": "1:23:47", "remaining_time": "1:09:24", "throughput": 4643.35, "total_tokens": 23343136} {"current_steps": 23205, "total_steps": 42420, "loss": 0.0647, "lr": 2.5261259759937072e-05, "epoch": 10.94059405940594, "percentage": 54.7, "elapsed_time": "1:23:48", "remaining_time": "1:09:23", "throughput": 4643.43, "total_tokens": 23349056} {"current_steps": 23210, "total_steps": 42420, "loss": 0.1095, "lr": 2.525097429525014e-05, "epoch": 10.942951438000943, "percentage": 54.71, "elapsed_time": "1:23:49", "remaining_time": "1:09:22", "throughput": 4643.48, "total_tokens": 23354368} {"current_steps": 23215, "total_steps": 42420, "loss": 0.1518, "lr": 2.5240688788077527e-05, "epoch": 10.945308816595945, "percentage": 54.73, "elapsed_time": "1:23:50", "remaining_time": "1:09:21", "throughput": 4643.53, "total_tokens": 23359552} {"current_steps": 23220, "total_steps": 42420, "loss": 0.0584, "lr": 2.5230403240160383e-05, "epoch": 10.947666195190948, "percentage": 54.74, "elapsed_time": "1:23:51", "remaining_time": "1:09:20", "throughput": 4643.57, "total_tokens": 23364608} {"current_steps": 23225, "total_steps": 42420, "loss": 0.0813, "lr": 2.5220117653239882e-05, "epoch": 10.95002357378595, "percentage": 54.75, "elapsed_time": "1:23:52", "remaining_time": "1:09:19", "throughput": 4643.58, "total_tokens": 23368992} {"current_steps": 23230, "total_steps": 42420, "loss": 0.0643, "lr": 2.5209832029057202e-05, "epoch": 10.952380952380953, "percentage": 54.76, "elapsed_time": "1:23:53", "remaining_time": "1:09:18", "throughput": 4643.64, "total_tokens": 23374368} {"current_steps": 23235, "total_steps": 42420, "loss": 0.0944, "lr": 2.5199546369353522e-05, "epoch": 10.954738330975955, "percentage": 54.77, "elapsed_time": "1:23:54", "remaining_time": "1:09:17", "throughput": 4643.65, "total_tokens": 23379392} {"current_steps": 23240, "total_steps": 42420, "loss": 0.1685, "lr": 2.518926067587003e-05, "epoch": 10.957095709570957, "percentage": 54.79, "elapsed_time": "1:23:55", "remaining_time": "1:09:15", "throughput": 4643.64, "total_tokens": 23383232} {"current_steps": 23245, "total_steps": 42420, "loss": 0.1221, "lr": 2.5178974950347917e-05, "epoch": 10.95945308816596, "percentage": 54.8, "elapsed_time": "1:23:56", "remaining_time": "1:09:14", "throughput": 4643.69, "total_tokens": 23388384} {"current_steps": 23250, "total_steps": 42420, "loss": 0.1313, "lr": 2.5168689194528382e-05, "epoch": 10.961810466760962, "percentage": 54.81, "elapsed_time": "1:23:57", "remaining_time": "1:09:13", "throughput": 4643.72, "total_tokens": 23393312} {"current_steps": 23255, "total_steps": 42420, "loss": 0.0635, "lr": 2.5158403410152643e-05, "epoch": 10.964167845355965, "percentage": 54.82, "elapsed_time": "1:23:58", "remaining_time": "1:09:12", "throughput": 4643.78, "total_tokens": 23398880} {"current_steps": 23260, "total_steps": 42420, "loss": 0.105, "lr": 2.5148117598961883e-05, "epoch": 10.966525223950967, "percentage": 54.83, "elapsed_time": "1:23:59", "remaining_time": "1:09:11", "throughput": 4643.78, "total_tokens": 23403136} {"current_steps": 23265, "total_steps": 42420, "loss": 0.1783, "lr": 2.5137831762697333e-05, "epoch": 10.96888260254597, "percentage": 54.84, "elapsed_time": "1:24:00", "remaining_time": "1:09:10", "throughput": 4643.76, "total_tokens": 23408288} {"current_steps": 23270, "total_steps": 42420, "loss": 0.0729, "lr": 2.5127545903100202e-05, "epoch": 10.971239981140972, "percentage": 54.86, "elapsed_time": "1:24:01", "remaining_time": "1:09:09", "throughput": 4643.75, "total_tokens": 23412608} {"current_steps": 23275, "total_steps": 42420, "loss": 0.2157, "lr": 2.5117260021911727e-05, "epoch": 10.973597359735974, "percentage": 54.87, "elapsed_time": "1:24:02", "remaining_time": "1:09:07", "throughput": 4643.72, "total_tokens": 23416704} {"current_steps": 23280, "total_steps": 42420, "loss": 0.0446, "lr": 2.510697412087311e-05, "epoch": 10.975954738330977, "percentage": 54.88, "elapsed_time": "1:24:03", "remaining_time": "1:09:06", "throughput": 4643.75, "total_tokens": 23421216} {"current_steps": 23285, "total_steps": 42420, "loss": 0.0446, "lr": 2.5096688201725593e-05, "epoch": 10.978312116925979, "percentage": 54.89, "elapsed_time": "1:24:04", "remaining_time": "1:09:05", "throughput": 4643.79, "total_tokens": 23426304} {"current_steps": 23290, "total_steps": 42420, "loss": 0.1145, "lr": 2.50864022662104e-05, "epoch": 10.980669495520981, "percentage": 54.9, "elapsed_time": "1:24:05", "remaining_time": "1:09:04", "throughput": 4643.83, "total_tokens": 23431424} {"current_steps": 23295, "total_steps": 42420, "loss": 0.0745, "lr": 2.507611631606878e-05, "epoch": 10.983026874115984, "percentage": 54.92, "elapsed_time": "1:24:06", "remaining_time": "1:09:03", "throughput": 4643.9, "total_tokens": 23436992} {"current_steps": 23300, "total_steps": 42420, "loss": 0.2269, "lr": 2.5065830353041962e-05, "epoch": 10.985384252710986, "percentage": 54.93, "elapsed_time": "1:24:07", "remaining_time": "1:09:02", "throughput": 4643.9, "total_tokens": 23441408} {"current_steps": 23305, "total_steps": 42420, "loss": 0.0821, "lr": 2.5055544378871178e-05, "epoch": 10.987741631305987, "percentage": 54.94, "elapsed_time": "1:24:08", "remaining_time": "1:09:01", "throughput": 4643.94, "total_tokens": 23446720} {"current_steps": 23310, "total_steps": 42420, "loss": 0.1738, "lr": 2.504525839529767e-05, "epoch": 10.990099009900991, "percentage": 54.95, "elapsed_time": "1:24:09", "remaining_time": "1:08:59", "throughput": 4643.95, "total_tokens": 23450976} {"current_steps": 23315, "total_steps": 42420, "loss": 0.1434, "lr": 2.503497240406269e-05, "epoch": 10.992456388495992, "percentage": 54.96, "elapsed_time": "1:24:11", "remaining_time": "1:08:59", "throughput": 4644.04, "total_tokens": 23457440} {"current_steps": 23320, "total_steps": 42420, "loss": 0.0916, "lr": 2.502468640690747e-05, "epoch": 10.994813767090994, "percentage": 54.97, "elapsed_time": "1:24:12", "remaining_time": "1:08:57", "throughput": 4644.04, "total_tokens": 23462112} {"current_steps": 23325, "total_steps": 42420, "loss": 0.0439, "lr": 2.5014400405573262e-05, "epoch": 10.997171145685996, "percentage": 54.99, "elapsed_time": "1:24:13", "remaining_time": "1:08:56", "throughput": 4644.04, "total_tokens": 23466912} {"current_steps": 23330, "total_steps": 42420, "loss": 0.14, "lr": 2.500411440180131e-05, "epoch": 10.999528524280999, "percentage": 55.0, "elapsed_time": "1:24:14", "remaining_time": "1:08:55", "throughput": 4644.09, "total_tokens": 23471712} {"current_steps": 23331, "total_steps": 42420, "eval_loss": 0.15143364667892456, "epoch": 11.0, "percentage": 55.0, "elapsed_time": "1:24:29", "remaining_time": "1:09:07", "throughput": 4630.0, "total_tokens": 23472352} {"current_steps": 23335, "total_steps": 42420, "loss": 0.1103, "lr": 2.499382839733286e-05, "epoch": 11.001885902876001, "percentage": 55.01, "elapsed_time": "1:24:31", "remaining_time": "1:09:08", "throughput": 4628.66, "total_tokens": 23476192} {"current_steps": 23340, "total_steps": 42420, "loss": 0.1692, "lr": 2.4983542393909156e-05, "epoch": 11.004243281471004, "percentage": 55.02, "elapsed_time": "1:24:33", "remaining_time": "1:09:07", "throughput": 4628.73, "total_tokens": 23481728} {"current_steps": 23345, "total_steps": 42420, "loss": 0.0745, "lr": 2.4973256393271448e-05, "epoch": 11.006600660066006, "percentage": 55.03, "elapsed_time": "1:24:34", "remaining_time": "1:09:06", "throughput": 4628.78, "total_tokens": 23487552} {"current_steps": 23350, "total_steps": 42420, "loss": 0.1607, "lr": 2.4962970397160975e-05, "epoch": 11.008958038661008, "percentage": 55.04, "elapsed_time": "1:24:35", "remaining_time": "1:09:04", "throughput": 4628.78, "total_tokens": 23491744} {"current_steps": 23355, "total_steps": 42420, "loss": 0.1732, "lr": 2.4952684407319e-05, "epoch": 11.01131541725601, "percentage": 55.06, "elapsed_time": "1:24:36", "remaining_time": "1:09:03", "throughput": 4628.84, "total_tokens": 23497888} {"current_steps": 23360, "total_steps": 42420, "loss": 0.2163, "lr": 2.4942398425486745e-05, "epoch": 11.013672795851013, "percentage": 55.07, "elapsed_time": "1:24:37", "remaining_time": "1:09:03", "throughput": 4628.9, "total_tokens": 23504512} {"current_steps": 23365, "total_steps": 42420, "loss": 0.1341, "lr": 2.493211245340545e-05, "epoch": 11.016030174446016, "percentage": 55.08, "elapsed_time": "1:24:38", "remaining_time": "1:09:01", "throughput": 4628.88, "total_tokens": 23508704} {"current_steps": 23370, "total_steps": 42420, "loss": 0.0744, "lr": 2.4921826492816366e-05, "epoch": 11.018387553041018, "percentage": 55.09, "elapsed_time": "1:24:39", "remaining_time": "1:09:00", "throughput": 4628.87, "total_tokens": 23513632} {"current_steps": 23375, "total_steps": 42420, "loss": 0.1195, "lr": 2.491154054546073e-05, "epoch": 11.02074493163602, "percentage": 55.1, "elapsed_time": "1:24:40", "remaining_time": "1:08:59", "throughput": 4628.9, "total_tokens": 23518560} {"current_steps": 23380, "total_steps": 42420, "loss": 0.0397, "lr": 2.490125461307978e-05, "epoch": 11.023102310231023, "percentage": 55.12, "elapsed_time": "1:24:41", "remaining_time": "1:08:58", "throughput": 4628.96, "total_tokens": 23523520} {"current_steps": 23385, "total_steps": 42420, "loss": 0.0441, "lr": 2.4890968697414747e-05, "epoch": 11.025459688826025, "percentage": 55.13, "elapsed_time": "1:24:42", "remaining_time": "1:08:57", "throughput": 4628.99, "total_tokens": 23528192} {"current_steps": 23390, "total_steps": 42420, "loss": 0.1262, "lr": 2.488068280020686e-05, "epoch": 11.027817067421028, "percentage": 55.14, "elapsed_time": "1:24:43", "remaining_time": "1:08:56", "throughput": 4629.04, "total_tokens": 23533856} {"current_steps": 23395, "total_steps": 42420, "loss": 0.1675, "lr": 2.4870396923197348e-05, "epoch": 11.03017444601603, "percentage": 55.15, "elapsed_time": "1:24:44", "remaining_time": "1:08:55", "throughput": 4629.04, "total_tokens": 23538016} {"current_steps": 23400, "total_steps": 42420, "loss": 0.0304, "lr": 2.486011106812744e-05, "epoch": 11.032531824611032, "percentage": 55.16, "elapsed_time": "1:24:46", "remaining_time": "1:08:54", "throughput": 4629.11, "total_tokens": 23543776} {"current_steps": 23405, "total_steps": 42420, "loss": 0.1218, "lr": 2.484982523673835e-05, "epoch": 11.034889203206035, "percentage": 55.17, "elapsed_time": "1:24:46", "remaining_time": "1:08:52", "throughput": 4629.15, "total_tokens": 23548256} {"current_steps": 23410, "total_steps": 42420, "loss": 0.2219, "lr": 2.4839539430771296e-05, "epoch": 11.037246581801037, "percentage": 55.19, "elapsed_time": "1:24:48", "remaining_time": "1:08:51", "throughput": 4629.21, "total_tokens": 23553472} {"current_steps": 23415, "total_steps": 42420, "loss": 0.0901, "lr": 2.4829253651967495e-05, "epoch": 11.03960396039604, "percentage": 55.2, "elapsed_time": "1:24:48", "remaining_time": "1:08:50", "throughput": 4629.23, "total_tokens": 23557856} {"current_steps": 23420, "total_steps": 42420, "loss": 0.1353, "lr": 2.4818967902068158e-05, "epoch": 11.041961338991042, "percentage": 55.21, "elapsed_time": "1:24:50", "remaining_time": "1:08:49", "throughput": 4629.25, "total_tokens": 23563232} {"current_steps": 23425, "total_steps": 42420, "loss": 0.1445, "lr": 2.4808682182814473e-05, "epoch": 11.044318717586044, "percentage": 55.22, "elapsed_time": "1:24:51", "remaining_time": "1:08:48", "throughput": 4629.3, "total_tokens": 23568768} {"current_steps": 23430, "total_steps": 42420, "loss": 0.0605, "lr": 2.4798396495947645e-05, "epoch": 11.046676096181047, "percentage": 55.23, "elapsed_time": "1:24:52", "remaining_time": "1:08:47", "throughput": 4629.28, "total_tokens": 23573024} {"current_steps": 23435, "total_steps": 42420, "loss": 0.0974, "lr": 2.478811084320887e-05, "epoch": 11.04903347477605, "percentage": 55.25, "elapsed_time": "1:24:53", "remaining_time": "1:08:45", "throughput": 4629.31, "total_tokens": 23577568} {"current_steps": 23440, "total_steps": 42420, "loss": 0.1642, "lr": 2.4777825226339337e-05, "epoch": 11.051390853371052, "percentage": 55.26, "elapsed_time": "1:24:54", "remaining_time": "1:08:44", "throughput": 4629.37, "total_tokens": 23582528} {"current_steps": 23445, "total_steps": 42420, "loss": 0.1626, "lr": 2.476753964708021e-05, "epoch": 11.053748231966054, "percentage": 55.27, "elapsed_time": "1:24:55", "remaining_time": "1:08:43", "throughput": 4629.38, "total_tokens": 23587072} {"current_steps": 23450, "total_steps": 42420, "loss": 0.16, "lr": 2.4757254107172682e-05, "epoch": 11.056105610561056, "percentage": 55.28, "elapsed_time": "1:24:56", "remaining_time": "1:08:42", "throughput": 4629.44, "total_tokens": 23592320} {"current_steps": 23455, "total_steps": 42420, "loss": 0.1165, "lr": 2.4746968608357905e-05, "epoch": 11.058462989156059, "percentage": 55.29, "elapsed_time": "1:24:57", "remaining_time": "1:08:41", "throughput": 4629.47, "total_tokens": 23597088} {"current_steps": 23460, "total_steps": 42420, "loss": 0.0492, "lr": 2.4736683152377056e-05, "epoch": 11.060820367751061, "percentage": 55.3, "elapsed_time": "1:24:58", "remaining_time": "1:08:40", "throughput": 4629.55, "total_tokens": 23602944} {"current_steps": 23465, "total_steps": 42420, "loss": 0.0684, "lr": 2.4726397740971272e-05, "epoch": 11.063177746346064, "percentage": 55.32, "elapsed_time": "1:24:59", "remaining_time": "1:08:39", "throughput": 4629.58, "total_tokens": 23607424} {"current_steps": 23470, "total_steps": 42420, "loss": 0.062, "lr": 2.4716112375881704e-05, "epoch": 11.065535124941066, "percentage": 55.33, "elapsed_time": "1:25:00", "remaining_time": "1:08:38", "throughput": 4629.62, "total_tokens": 23612448} {"current_steps": 23475, "total_steps": 42420, "loss": 0.1008, "lr": 2.470582705884949e-05, "epoch": 11.067892503536068, "percentage": 55.34, "elapsed_time": "1:25:01", "remaining_time": "1:08:36", "throughput": 4629.7, "total_tokens": 23617888} {"current_steps": 23480, "total_steps": 42420, "loss": 0.0613, "lr": 2.469554179161577e-05, "epoch": 11.07024988213107, "percentage": 55.35, "elapsed_time": "1:25:02", "remaining_time": "1:08:35", "throughput": 4629.78, "total_tokens": 23623744} {"current_steps": 23485, "total_steps": 42420, "loss": 0.075, "lr": 2.4685256575921643e-05, "epoch": 11.072607260726073, "percentage": 55.36, "elapsed_time": "1:25:03", "remaining_time": "1:08:34", "throughput": 4629.83, "total_tokens": 23628256} {"current_steps": 23490, "total_steps": 42420, "loss": 0.0728, "lr": 2.467497141350824e-05, "epoch": 11.074964639321076, "percentage": 55.37, "elapsed_time": "1:25:04", "remaining_time": "1:08:33", "throughput": 4629.87, "total_tokens": 23633024} {"current_steps": 23495, "total_steps": 42420, "loss": 0.1193, "lr": 2.4664686306116656e-05, "epoch": 11.077322017916078, "percentage": 55.39, "elapsed_time": "1:25:05", "remaining_time": "1:08:32", "throughput": 4629.91, "total_tokens": 23637792} {"current_steps": 23500, "total_steps": 42420, "loss": 0.123, "lr": 2.465440125548799e-05, "epoch": 11.07967939651108, "percentage": 55.4, "elapsed_time": "1:25:06", "remaining_time": "1:08:31", "throughput": 4629.94, "total_tokens": 23643232} {"current_steps": 23505, "total_steps": 42420, "loss": 0.0784, "lr": 2.4644116263363323e-05, "epoch": 11.082036775106083, "percentage": 55.41, "elapsed_time": "1:25:07", "remaining_time": "1:08:30", "throughput": 4629.92, "total_tokens": 23647360} {"current_steps": 23510, "total_steps": 42420, "loss": 0.2101, "lr": 2.4633831331483724e-05, "epoch": 11.084394153701085, "percentage": 55.42, "elapsed_time": "1:25:08", "remaining_time": "1:08:28", "throughput": 4629.95, "total_tokens": 23652192} {"current_steps": 23515, "total_steps": 42420, "loss": 0.2448, "lr": 2.4623546461590267e-05, "epoch": 11.086751532296086, "percentage": 55.43, "elapsed_time": "1:25:09", "remaining_time": "1:08:27", "throughput": 4630.01, "total_tokens": 23657792} {"current_steps": 23520, "total_steps": 42420, "loss": 0.0485, "lr": 2.461326165542401e-05, "epoch": 11.089108910891088, "percentage": 55.45, "elapsed_time": "1:25:10", "remaining_time": "1:08:26", "throughput": 4630.06, "total_tokens": 23663328} {"current_steps": 23525, "total_steps": 42420, "loss": 0.0344, "lr": 2.460297691472598e-05, "epoch": 11.09146628948609, "percentage": 55.46, "elapsed_time": "1:25:11", "remaining_time": "1:08:25", "throughput": 4630.08, "total_tokens": 23667616} {"current_steps": 23530, "total_steps": 42420, "loss": 0.0406, "lr": 2.4592692241237217e-05, "epoch": 11.093823668081093, "percentage": 55.47, "elapsed_time": "1:25:12", "remaining_time": "1:08:24", "throughput": 4630.13, "total_tokens": 23672576} {"current_steps": 23535, "total_steps": 42420, "loss": 0.1864, "lr": 2.458240763669874e-05, "epoch": 11.096181046676096, "percentage": 55.48, "elapsed_time": "1:25:13", "remaining_time": "1:08:23", "throughput": 4630.16, "total_tokens": 23677280} {"current_steps": 23540, "total_steps": 42420, "loss": 0.1288, "lr": 2.457212310285157e-05, "epoch": 11.098538425271098, "percentage": 55.49, "elapsed_time": "1:25:14", "remaining_time": "1:08:22", "throughput": 4630.2, "total_tokens": 23681728} {"current_steps": 23545, "total_steps": 42420, "loss": 0.0464, "lr": 2.4561838641436685e-05, "epoch": 11.1008958038661, "percentage": 55.5, "elapsed_time": "1:25:15", "remaining_time": "1:08:21", "throughput": 4630.22, "total_tokens": 23687584} {"current_steps": 23550, "total_steps": 42420, "loss": 0.0261, "lr": 2.455155425419508e-05, "epoch": 11.103253182461103, "percentage": 55.52, "elapsed_time": "1:25:16", "remaining_time": "1:08:20", "throughput": 4630.27, "total_tokens": 23692480} {"current_steps": 23555, "total_steps": 42420, "loss": 0.0756, "lr": 2.4541269942867722e-05, "epoch": 11.105610561056105, "percentage": 55.53, "elapsed_time": "1:25:18", "remaining_time": "1:08:19", "throughput": 4630.34, "total_tokens": 23699040} {"current_steps": 23560, "total_steps": 42420, "loss": 0.2345, "lr": 2.4530985709195582e-05, "epoch": 11.107967939651108, "percentage": 55.54, "elapsed_time": "1:25:19", "remaining_time": "1:08:18", "throughput": 4630.41, "total_tokens": 23705408} {"current_steps": 23565, "total_steps": 42420, "loss": 0.0407, "lr": 2.4520701554919595e-05, "epoch": 11.11032531824611, "percentage": 55.55, "elapsed_time": "1:25:20", "remaining_time": "1:08:17", "throughput": 4630.48, "total_tokens": 23710688} {"current_steps": 23570, "total_steps": 42420, "loss": 0.2394, "lr": 2.4510417481780697e-05, "epoch": 11.112682696841112, "percentage": 55.56, "elapsed_time": "1:25:21", "remaining_time": "1:08:15", "throughput": 4630.52, "total_tokens": 23715648} {"current_steps": 23575, "total_steps": 42420, "loss": 0.1251, "lr": 2.4500133491519802e-05, "epoch": 11.115040075436115, "percentage": 55.58, "elapsed_time": "1:25:22", "remaining_time": "1:08:14", "throughput": 4630.56, "total_tokens": 23720064} {"current_steps": 23580, "total_steps": 42420, "loss": 0.2226, "lr": 2.4489849585877834e-05, "epoch": 11.117397454031117, "percentage": 55.59, "elapsed_time": "1:25:23", "remaining_time": "1:08:13", "throughput": 4630.62, "total_tokens": 23725280} {"current_steps": 23585, "total_steps": 42420, "loss": 0.2203, "lr": 2.4479565766595656e-05, "epoch": 11.11975483262612, "percentage": 55.6, "elapsed_time": "1:25:24", "remaining_time": "1:08:12", "throughput": 4630.64, "total_tokens": 23729408} {"current_steps": 23590, "total_steps": 42420, "loss": 0.124, "lr": 2.4469282035414163e-05, "epoch": 11.122112211221122, "percentage": 55.61, "elapsed_time": "1:25:25", "remaining_time": "1:08:11", "throughput": 4630.69, "total_tokens": 23734368} {"current_steps": 23595, "total_steps": 42420, "loss": 0.2403, "lr": 2.4458998394074207e-05, "epoch": 11.124469589816124, "percentage": 55.62, "elapsed_time": "1:25:26", "remaining_time": "1:08:09", "throughput": 4630.72, "total_tokens": 23738656} {"current_steps": 23600, "total_steps": 42420, "loss": 0.1577, "lr": 2.4448714844316635e-05, "epoch": 11.126826968411127, "percentage": 55.63, "elapsed_time": "1:25:27", "remaining_time": "1:08:08", "throughput": 4630.78, "total_tokens": 23744192} {"current_steps": 23605, "total_steps": 42420, "loss": 0.0662, "lr": 2.443843138788228e-05, "epoch": 11.12918434700613, "percentage": 55.65, "elapsed_time": "1:25:28", "remaining_time": "1:08:07", "throughput": 4630.86, "total_tokens": 23749760} {"current_steps": 23610, "total_steps": 42420, "loss": 0.0864, "lr": 2.4428148026511964e-05, "epoch": 11.131541725601132, "percentage": 55.66, "elapsed_time": "1:25:29", "remaining_time": "1:08:06", "throughput": 4630.89, "total_tokens": 23754592} {"current_steps": 23615, "total_steps": 42420, "loss": 0.1282, "lr": 2.441786476194647e-05, "epoch": 11.133899104196134, "percentage": 55.67, "elapsed_time": "1:25:30", "remaining_time": "1:08:05", "throughput": 4630.91, "total_tokens": 23759104} {"current_steps": 23620, "total_steps": 42420, "loss": 0.0395, "lr": 2.4407581595926586e-05, "epoch": 11.136256482791136, "percentage": 55.68, "elapsed_time": "1:25:31", "remaining_time": "1:08:04", "throughput": 4630.98, "total_tokens": 23764064} {"current_steps": 23625, "total_steps": 42420, "loss": 0.0928, "lr": 2.439729853019308e-05, "epoch": 11.138613861386139, "percentage": 55.69, "elapsed_time": "1:25:32", "remaining_time": "1:08:03", "throughput": 4631.03, "total_tokens": 23768992} {"current_steps": 23630, "total_steps": 42420, "loss": 0.0789, "lr": 2.4387015566486707e-05, "epoch": 11.140971239981141, "percentage": 55.7, "elapsed_time": "1:25:33", "remaining_time": "1:08:02", "throughput": 4631.09, "total_tokens": 23773984} {"current_steps": 23635, "total_steps": 42420, "loss": 0.0746, "lr": 2.4376732706548183e-05, "epoch": 11.143328618576144, "percentage": 55.72, "elapsed_time": "1:25:34", "remaining_time": "1:08:00", "throughput": 4631.1, "total_tokens": 23778848} {"current_steps": 23640, "total_steps": 42420, "loss": 0.1991, "lr": 2.436644995211823e-05, "epoch": 11.145685997171146, "percentage": 55.73, "elapsed_time": "1:25:35", "remaining_time": "1:08:00", "throughput": 4631.21, "total_tokens": 23785440} {"current_steps": 23645, "total_steps": 42420, "loss": 0.1213, "lr": 2.4356167304937545e-05, "epoch": 11.148043375766148, "percentage": 55.74, "elapsed_time": "1:25:36", "remaining_time": "1:07:58", "throughput": 4631.22, "total_tokens": 23789696} {"current_steps": 23650, "total_steps": 42420, "loss": 0.0507, "lr": 2.4345884766746807e-05, "epoch": 11.15040075436115, "percentage": 55.75, "elapsed_time": "1:25:37", "remaining_time": "1:07:57", "throughput": 4631.2, "total_tokens": 23793888} {"current_steps": 23655, "total_steps": 42420, "loss": 0.0928, "lr": 2.4335602339286667e-05, "epoch": 11.152758132956153, "percentage": 55.76, "elapsed_time": "1:25:38", "remaining_time": "1:07:56", "throughput": 4631.28, "total_tokens": 23799328} {"current_steps": 23660, "total_steps": 42420, "loss": 0.2056, "lr": 2.432532002429777e-05, "epoch": 11.155115511551156, "percentage": 55.78, "elapsed_time": "1:25:40", "remaining_time": "1:07:55", "throughput": 4631.35, "total_tokens": 23805152} {"current_steps": 23665, "total_steps": 42420, "loss": 0.0917, "lr": 2.431503782352074e-05, "epoch": 11.157472890146158, "percentage": 55.79, "elapsed_time": "1:25:40", "remaining_time": "1:07:54", "throughput": 4631.38, "total_tokens": 23809568} {"current_steps": 23670, "total_steps": 42420, "loss": 0.1245, "lr": 2.4304755738696178e-05, "epoch": 11.15983026874116, "percentage": 55.8, "elapsed_time": "1:25:41", "remaining_time": "1:07:53", "throughput": 4631.41, "total_tokens": 23814016} {"current_steps": 23675, "total_steps": 42420, "loss": 0.2122, "lr": 2.4294473771564662e-05, "epoch": 11.162187647336163, "percentage": 55.81, "elapsed_time": "1:25:42", "remaining_time": "1:07:51", "throughput": 4631.42, "total_tokens": 23818368} {"current_steps": 23680, "total_steps": 42420, "loss": 0.0663, "lr": 2.4284191923866756e-05, "epoch": 11.164545025931165, "percentage": 55.82, "elapsed_time": "1:25:43", "remaining_time": "1:07:50", "throughput": 4631.49, "total_tokens": 23823424} {"current_steps": 23685, "total_steps": 42420, "loss": 0.0457, "lr": 2.4273910197343002e-05, "epoch": 11.166902404526168, "percentage": 55.83, "elapsed_time": "1:25:44", "remaining_time": "1:07:49", "throughput": 4631.51, "total_tokens": 23827936} {"current_steps": 23690, "total_steps": 42420, "loss": 0.2383, "lr": 2.426362859373393e-05, "epoch": 11.16925978312117, "percentage": 55.85, "elapsed_time": "1:25:45", "remaining_time": "1:07:48", "throughput": 4631.51, "total_tokens": 23832736} {"current_steps": 23695, "total_steps": 42420, "loss": 0.1229, "lr": 2.425334711478003e-05, "epoch": 11.171617161716172, "percentage": 55.86, "elapsed_time": "1:25:46", "remaining_time": "1:07:47", "throughput": 4631.55, "total_tokens": 23837920} {"current_steps": 23700, "total_steps": 42420, "loss": 0.1197, "lr": 2.4243065762221787e-05, "epoch": 11.173974540311175, "percentage": 55.87, "elapsed_time": "1:25:47", "remaining_time": "1:07:46", "throughput": 4631.59, "total_tokens": 23842560} {"current_steps": 23705, "total_steps": 42420, "loss": 0.035, "lr": 2.4232784537799655e-05, "epoch": 11.176331918906177, "percentage": 55.88, "elapsed_time": "1:25:48", "remaining_time": "1:07:44", "throughput": 4631.62, "total_tokens": 23847200} {"current_steps": 23710, "total_steps": 42420, "loss": 0.0793, "lr": 2.422250344325408e-05, "epoch": 11.17868929750118, "percentage": 55.89, "elapsed_time": "1:25:49", "remaining_time": "1:07:43", "throughput": 4631.62, "total_tokens": 23851456} {"current_steps": 23715, "total_steps": 42420, "loss": 0.1634, "lr": 2.421222248032547e-05, "epoch": 11.18104667609618, "percentage": 55.91, "elapsed_time": "1:25:50", "remaining_time": "1:07:42", "throughput": 4631.7, "total_tokens": 23857056} {"current_steps": 23720, "total_steps": 42420, "loss": 0.0651, "lr": 2.4201941650754215e-05, "epoch": 11.183404054691183, "percentage": 55.92, "elapsed_time": "1:25:52", "remaining_time": "1:07:41", "throughput": 4631.78, "total_tokens": 23863456} {"current_steps": 23725, "total_steps": 42420, "loss": 0.0419, "lr": 2.4191660956280687e-05, "epoch": 11.185761433286185, "percentage": 55.93, "elapsed_time": "1:25:52", "remaining_time": "1:07:40", "throughput": 4631.76, "total_tokens": 23867392} {"current_steps": 23730, "total_steps": 42420, "loss": 0.0253, "lr": 2.418138039864524e-05, "epoch": 11.188118811881187, "percentage": 55.94, "elapsed_time": "1:25:53", "remaining_time": "1:07:39", "throughput": 4631.79, "total_tokens": 23872128} {"current_steps": 23735, "total_steps": 42420, "loss": 0.0284, "lr": 2.417109997958819e-05, "epoch": 11.19047619047619, "percentage": 55.95, "elapsed_time": "1:25:54", "remaining_time": "1:07:38", "throughput": 4631.79, "total_tokens": 23876448} {"current_steps": 23740, "total_steps": 42420, "loss": 0.3254, "lr": 2.4160819700849836e-05, "epoch": 11.192833569071192, "percentage": 55.96, "elapsed_time": "1:25:55", "remaining_time": "1:07:36", "throughput": 4631.84, "total_tokens": 23881536} {"current_steps": 23745, "total_steps": 42420, "loss": 0.2391, "lr": 2.415053956417046e-05, "epoch": 11.195190947666195, "percentage": 55.98, "elapsed_time": "1:25:57", "remaining_time": "1:07:35", "throughput": 4631.91, "total_tokens": 23886816} {"current_steps": 23750, "total_steps": 42420, "loss": 0.2549, "lr": 2.414025957129032e-05, "epoch": 11.197548326261197, "percentage": 55.99, "elapsed_time": "1:25:57", "remaining_time": "1:07:34", "throughput": 4631.94, "total_tokens": 23891360} {"current_steps": 23755, "total_steps": 42420, "loss": 0.0553, "lr": 2.4129979723949628e-05, "epoch": 11.1999057048562, "percentage": 56.0, "elapsed_time": "1:25:59", "remaining_time": "1:07:33", "throughput": 4632.0, "total_tokens": 23896864} {"current_steps": 23760, "total_steps": 42420, "loss": 0.2131, "lr": 2.4119700023888598e-05, "epoch": 11.202263083451202, "percentage": 56.01, "elapsed_time": "1:26:00", "remaining_time": "1:07:32", "throughput": 4632.1, "total_tokens": 23903616} {"current_steps": 23765, "total_steps": 42420, "loss": 0.2682, "lr": 2.4109420472847406e-05, "epoch": 11.204620462046204, "percentage": 56.02, "elapsed_time": "1:26:01", "remaining_time": "1:07:31", "throughput": 4632.12, "total_tokens": 23908064} {"current_steps": 23770, "total_steps": 42420, "loss": 0.0607, "lr": 2.4099141072566214e-05, "epoch": 11.206977840641207, "percentage": 56.03, "elapsed_time": "1:26:02", "remaining_time": "1:07:30", "throughput": 4632.19, "total_tokens": 23913472} {"current_steps": 23775, "total_steps": 42420, "loss": 0.1411, "lr": 2.4088861824785135e-05, "epoch": 11.209335219236209, "percentage": 56.05, "elapsed_time": "1:26:03", "remaining_time": "1:07:29", "throughput": 4632.19, "total_tokens": 23917760} {"current_steps": 23780, "total_steps": 42420, "loss": 0.0481, "lr": 2.4078582731244283e-05, "epoch": 11.211692597831211, "percentage": 56.06, "elapsed_time": "1:26:04", "remaining_time": "1:07:28", "throughput": 4632.26, "total_tokens": 23923744} {"current_steps": 23785, "total_steps": 42420, "loss": 0.1102, "lr": 2.406830379368373e-05, "epoch": 11.214049976426214, "percentage": 56.07, "elapsed_time": "1:26:05", "remaining_time": "1:07:27", "throughput": 4632.31, "total_tokens": 23928896} {"current_steps": 23790, "total_steps": 42420, "loss": 0.2966, "lr": 2.4058025013843524e-05, "epoch": 11.216407355021216, "percentage": 56.08, "elapsed_time": "1:26:06", "remaining_time": "1:07:26", "throughput": 4632.38, "total_tokens": 23935168} {"current_steps": 23795, "total_steps": 42420, "loss": 0.0764, "lr": 2.404774639346369e-05, "epoch": 11.218764733616219, "percentage": 56.09, "elapsed_time": "1:26:07", "remaining_time": "1:07:25", "throughput": 4632.42, "total_tokens": 23939904} {"current_steps": 23800, "total_steps": 42420, "loss": 0.1044, "lr": 2.403746793428422e-05, "epoch": 11.221122112211221, "percentage": 56.11, "elapsed_time": "1:26:08", "remaining_time": "1:07:23", "throughput": 4632.41, "total_tokens": 23943808} {"current_steps": 23805, "total_steps": 42420, "loss": 0.2186, "lr": 2.40271896380451e-05, "epoch": 11.223479490806223, "percentage": 56.12, "elapsed_time": "1:26:09", "remaining_time": "1:07:22", "throughput": 4632.42, "total_tokens": 23948096} {"current_steps": 23810, "total_steps": 42420, "loss": 0.1357, "lr": 2.401691150648624e-05, "epoch": 11.225836869401226, "percentage": 56.13, "elapsed_time": "1:26:10", "remaining_time": "1:07:21", "throughput": 4632.47, "total_tokens": 23953536} {"current_steps": 23815, "total_steps": 42420, "loss": 0.0539, "lr": 2.4006633541347578e-05, "epoch": 11.228194247996228, "percentage": 56.14, "elapsed_time": "1:26:11", "remaining_time": "1:07:20", "throughput": 4632.52, "total_tokens": 23958528} {"current_steps": 23820, "total_steps": 42420, "loss": 0.0991, "lr": 2.3996355744368993e-05, "epoch": 11.23055162659123, "percentage": 56.15, "elapsed_time": "1:26:13", "remaining_time": "1:07:19", "throughput": 4632.59, "total_tokens": 23964640} {"current_steps": 23825, "total_steps": 42420, "loss": 0.0607, "lr": 2.3986078117290333e-05, "epoch": 11.232909005186233, "percentage": 56.16, "elapsed_time": "1:26:14", "remaining_time": "1:07:18", "throughput": 4632.65, "total_tokens": 23969920} {"current_steps": 23830, "total_steps": 42420, "loss": 0.1431, "lr": 2.397580066185143e-05, "epoch": 11.235266383781235, "percentage": 56.18, "elapsed_time": "1:26:15", "remaining_time": "1:07:17", "throughput": 4632.69, "total_tokens": 23974944} {"current_steps": 23835, "total_steps": 42420, "loss": 0.1077, "lr": 2.396552337979209e-05, "epoch": 11.237623762376238, "percentage": 56.19, "elapsed_time": "1:26:16", "remaining_time": "1:07:16", "throughput": 4632.75, "total_tokens": 23980032} {"current_steps": 23840, "total_steps": 42420, "loss": 0.1, "lr": 2.3955246272852084e-05, "epoch": 11.23998114097124, "percentage": 56.2, "elapsed_time": "1:26:17", "remaining_time": "1:07:14", "throughput": 4632.8, "total_tokens": 23985248} {"current_steps": 23845, "total_steps": 42420, "loss": 0.1243, "lr": 2.3944969342771134e-05, "epoch": 11.242338519566243, "percentage": 56.21, "elapsed_time": "1:26:18", "remaining_time": "1:07:13", "throughput": 4632.82, "total_tokens": 23990592} {"current_steps": 23850, "total_steps": 42420, "loss": 0.0748, "lr": 2.3934692591288965e-05, "epoch": 11.244695898161245, "percentage": 56.22, "elapsed_time": "1:26:19", "remaining_time": "1:07:12", "throughput": 4632.87, "total_tokens": 23995584} {"current_steps": 23855, "total_steps": 42420, "loss": 0.2186, "lr": 2.392441602014525e-05, "epoch": 11.247053276756247, "percentage": 56.24, "elapsed_time": "1:26:20", "remaining_time": "1:07:11", "throughput": 4632.94, "total_tokens": 24001248} {"current_steps": 23860, "total_steps": 42420, "loss": 0.1385, "lr": 2.3914139631079646e-05, "epoch": 11.24941065535125, "percentage": 56.25, "elapsed_time": "1:26:21", "remaining_time": "1:07:10", "throughput": 4632.97, "total_tokens": 24006336} {"current_steps": 23865, "total_steps": 42420, "loss": 0.0941, "lr": 2.3903863425831762e-05, "epoch": 11.251768033946252, "percentage": 56.26, "elapsed_time": "1:26:22", "remaining_time": "1:07:09", "throughput": 4632.99, "total_tokens": 24010656} {"current_steps": 23870, "total_steps": 42420, "loss": 0.2133, "lr": 2.3893587406141187e-05, "epoch": 11.254125412541255, "percentage": 56.27, "elapsed_time": "1:26:23", "remaining_time": "1:07:08", "throughput": 4633.02, "total_tokens": 24016480} {"current_steps": 23875, "total_steps": 42420, "loss": 0.1844, "lr": 2.388331157374748e-05, "epoch": 11.256482791136257, "percentage": 56.28, "elapsed_time": "1:26:24", "remaining_time": "1:07:07", "throughput": 4633.06, "total_tokens": 24020864} {"current_steps": 23880, "total_steps": 42420, "loss": 0.067, "lr": 2.3873035930390167e-05, "epoch": 11.25884016973126, "percentage": 56.29, "elapsed_time": "1:26:25", "remaining_time": "1:07:06", "throughput": 4633.11, "total_tokens": 24025600} {"current_steps": 23885, "total_steps": 42420, "loss": 0.1973, "lr": 2.3862760477808733e-05, "epoch": 11.261197548326262, "percentage": 56.31, "elapsed_time": "1:26:27", "remaining_time": "1:07:05", "throughput": 4633.18, "total_tokens": 24033440} {"current_steps": 23890, "total_steps": 42420, "loss": 0.1272, "lr": 2.3852485217742638e-05, "epoch": 11.263554926921264, "percentage": 56.32, "elapsed_time": "1:26:28", "remaining_time": "1:07:04", "throughput": 4633.27, "total_tokens": 24040992} {"current_steps": 23895, "total_steps": 42420, "loss": 0.1983, "lr": 2.384221015193131e-05, "epoch": 11.265912305516267, "percentage": 56.33, "elapsed_time": "1:26:30", "remaining_time": "1:07:03", "throughput": 4633.35, "total_tokens": 24047136} {"current_steps": 23900, "total_steps": 42420, "loss": 0.018, "lr": 2.3831935282114156e-05, "epoch": 11.268269684111269, "percentage": 56.34, "elapsed_time": "1:26:30", "remaining_time": "1:07:02", "throughput": 4633.37, "total_tokens": 24051584} {"current_steps": 23905, "total_steps": 42420, "loss": 0.0343, "lr": 2.3821660610030523e-05, "epoch": 11.270627062706271, "percentage": 56.35, "elapsed_time": "1:26:31", "remaining_time": "1:07:01", "throughput": 4633.42, "total_tokens": 24056000} {"current_steps": 23910, "total_steps": 42420, "loss": 0.2219, "lr": 2.3811386137419734e-05, "epoch": 11.272984441301272, "percentage": 56.36, "elapsed_time": "1:26:32", "remaining_time": "1:07:00", "throughput": 4633.49, "total_tokens": 24061664} {"current_steps": 23915, "total_steps": 42420, "loss": 0.1241, "lr": 2.3801111866021093e-05, "epoch": 11.275341819896274, "percentage": 56.38, "elapsed_time": "1:26:34", "remaining_time": "1:06:59", "throughput": 4633.51, "total_tokens": 24067392} {"current_steps": 23920, "total_steps": 42420, "loss": 0.0997, "lr": 2.3790837797573864e-05, "epoch": 11.277699198491277, "percentage": 56.39, "elapsed_time": "1:26:35", "remaining_time": "1:06:58", "throughput": 4633.59, "total_tokens": 24073184} {"current_steps": 23925, "total_steps": 42420, "loss": 0.1209, "lr": 2.378056393381726e-05, "epoch": 11.28005657708628, "percentage": 56.4, "elapsed_time": "1:26:36", "remaining_time": "1:06:56", "throughput": 4633.6, "total_tokens": 24077504} {"current_steps": 23930, "total_steps": 42420, "loss": 0.0718, "lr": 2.3770290276490474e-05, "epoch": 11.282413955681282, "percentage": 56.41, "elapsed_time": "1:26:37", "remaining_time": "1:06:55", "throughput": 4633.64, "total_tokens": 24082784} {"current_steps": 23935, "total_steps": 42420, "loss": 0.1603, "lr": 2.3760016827332672e-05, "epoch": 11.284771334276284, "percentage": 56.42, "elapsed_time": "1:26:38", "remaining_time": "1:06:54", "throughput": 4633.64, "total_tokens": 24087136} {"current_steps": 23940, "total_steps": 42420, "loss": 0.1812, "lr": 2.3749743588082966e-05, "epoch": 11.287128712871286, "percentage": 56.44, "elapsed_time": "1:26:39", "remaining_time": "1:06:53", "throughput": 4633.71, "total_tokens": 24092832} {"current_steps": 23945, "total_steps": 42420, "loss": 0.0545, "lr": 2.373947056048044e-05, "epoch": 11.289486091466289, "percentage": 56.45, "elapsed_time": "1:26:40", "remaining_time": "1:06:52", "throughput": 4633.76, "total_tokens": 24097952} {"current_steps": 23950, "total_steps": 42420, "loss": 0.1133, "lr": 2.3729197746264143e-05, "epoch": 11.291843470061291, "percentage": 56.46, "elapsed_time": "1:26:41", "remaining_time": "1:06:51", "throughput": 4633.82, "total_tokens": 24102880} {"current_steps": 23955, "total_steps": 42420, "loss": 0.0368, "lr": 2.3718925147173092e-05, "epoch": 11.294200848656294, "percentage": 56.47, "elapsed_time": "1:26:42", "remaining_time": "1:06:50", "throughput": 4633.89, "total_tokens": 24108128} {"current_steps": 23960, "total_steps": 42420, "loss": 0.1608, "lr": 2.3708652764946267e-05, "epoch": 11.296558227251296, "percentage": 56.48, "elapsed_time": "1:26:43", "remaining_time": "1:06:49", "throughput": 4633.96, "total_tokens": 24113568} {"current_steps": 23965, "total_steps": 42420, "loss": 0.2007, "lr": 2.36983806013226e-05, "epoch": 11.298915605846299, "percentage": 56.49, "elapsed_time": "1:26:44", "remaining_time": "1:06:48", "throughput": 4634.01, "total_tokens": 24118560} {"current_steps": 23970, "total_steps": 42420, "loss": 0.0636, "lr": 2.3688108658040994e-05, "epoch": 11.301272984441301, "percentage": 56.51, "elapsed_time": "1:26:45", "remaining_time": "1:06:46", "throughput": 4634.03, "total_tokens": 24123584} {"current_steps": 23975, "total_steps": 42420, "loss": 0.1158, "lr": 2.367783693684032e-05, "epoch": 11.303630363036303, "percentage": 56.52, "elapsed_time": "1:26:46", "remaining_time": "1:06:45", "throughput": 4634.06, "total_tokens": 24128192} {"current_steps": 23980, "total_steps": 42420, "loss": 0.0478, "lr": 2.3667565439459407e-05, "epoch": 11.305987741631306, "percentage": 56.53, "elapsed_time": "1:26:47", "remaining_time": "1:06:44", "throughput": 4634.03, "total_tokens": 24132384} {"current_steps": 23985, "total_steps": 42420, "loss": 0.062, "lr": 2.3657294167637038e-05, "epoch": 11.308345120226308, "percentage": 56.54, "elapsed_time": "1:26:48", "remaining_time": "1:06:43", "throughput": 4634.09, "total_tokens": 24138240} {"current_steps": 23990, "total_steps": 42420, "loss": 0.0296, "lr": 2.3647023123111965e-05, "epoch": 11.31070249882131, "percentage": 56.55, "elapsed_time": "1:26:49", "remaining_time": "1:06:42", "throughput": 4634.12, "total_tokens": 24143200} {"current_steps": 23995, "total_steps": 42420, "loss": 0.1698, "lr": 2.363675230762291e-05, "epoch": 11.313059877416313, "percentage": 56.57, "elapsed_time": "1:26:50", "remaining_time": "1:06:41", "throughput": 4634.15, "total_tokens": 24148256} {"current_steps": 24000, "total_steps": 42420, "loss": 0.068, "lr": 2.3626481722908546e-05, "epoch": 11.315417256011315, "percentage": 56.58, "elapsed_time": "1:26:51", "remaining_time": "1:06:40", "throughput": 4634.13, "total_tokens": 24152608} {"current_steps": 24005, "total_steps": 42420, "loss": 0.1743, "lr": 2.36162113707075e-05, "epoch": 11.317774634606318, "percentage": 56.59, "elapsed_time": "1:26:52", "remaining_time": "1:06:38", "throughput": 4634.13, "total_tokens": 24156800} {"current_steps": 24010, "total_steps": 42420, "loss": 0.0697, "lr": 2.3605941252758375e-05, "epoch": 11.32013201320132, "percentage": 56.6, "elapsed_time": "1:26:53", "remaining_time": "1:06:37", "throughput": 4634.16, "total_tokens": 24161984} {"current_steps": 24015, "total_steps": 42420, "loss": 0.1099, "lr": 2.3595671370799724e-05, "epoch": 11.322489391796323, "percentage": 56.61, "elapsed_time": "1:26:54", "remaining_time": "1:06:36", "throughput": 4634.17, "total_tokens": 24166048} {"current_steps": 24020, "total_steps": 42420, "loss": 0.1317, "lr": 2.358540172657007e-05, "epoch": 11.324846770391325, "percentage": 56.62, "elapsed_time": "1:26:55", "remaining_time": "1:06:35", "throughput": 4634.22, "total_tokens": 24171232} {"current_steps": 24025, "total_steps": 42420, "loss": 0.2057, "lr": 2.3575132321807883e-05, "epoch": 11.327204148986327, "percentage": 56.64, "elapsed_time": "1:26:56", "remaining_time": "1:06:34", "throughput": 4634.23, "total_tokens": 24175168} {"current_steps": 24030, "total_steps": 42420, "loss": 0.1312, "lr": 2.356486315825161e-05, "epoch": 11.32956152758133, "percentage": 56.65, "elapsed_time": "1:26:57", "remaining_time": "1:06:33", "throughput": 4634.26, "total_tokens": 24180224} {"current_steps": 24035, "total_steps": 42420, "loss": 0.1268, "lr": 2.3554594237639627e-05, "epoch": 11.331918906176332, "percentage": 56.66, "elapsed_time": "1:26:58", "remaining_time": "1:06:32", "throughput": 4634.32, "total_tokens": 24185600} {"current_steps": 24040, "total_steps": 42420, "loss": 0.2121, "lr": 2.3544325561710295e-05, "epoch": 11.334276284771335, "percentage": 56.67, "elapsed_time": "1:26:59", "remaining_time": "1:06:30", "throughput": 4634.37, "total_tokens": 24190656} {"current_steps": 24045, "total_steps": 42420, "loss": 0.0879, "lr": 2.3534057132201932e-05, "epoch": 11.336633663366337, "percentage": 56.68, "elapsed_time": "1:27:00", "remaining_time": "1:06:29", "throughput": 4634.36, "total_tokens": 24194688} {"current_steps": 24050, "total_steps": 42420, "loss": 0.2109, "lr": 2.3523788950852814e-05, "epoch": 11.33899104196134, "percentage": 56.69, "elapsed_time": "1:27:01", "remaining_time": "1:06:28", "throughput": 4634.43, "total_tokens": 24200928} {"current_steps": 24055, "total_steps": 42420, "loss": 0.1955, "lr": 2.3513521019401153e-05, "epoch": 11.341348420556342, "percentage": 56.71, "elapsed_time": "1:27:02", "remaining_time": "1:06:27", "throughput": 4634.44, "total_tokens": 24204896} {"current_steps": 24060, "total_steps": 42420, "loss": 0.0246, "lr": 2.3503253339585145e-05, "epoch": 11.343705799151344, "percentage": 56.72, "elapsed_time": "1:27:03", "remaining_time": "1:06:26", "throughput": 4634.48, "total_tokens": 24209856} {"current_steps": 24065, "total_steps": 42420, "loss": 0.1479, "lr": 2.3492985913142933e-05, "epoch": 11.346063177746347, "percentage": 56.73, "elapsed_time": "1:27:05", "remaining_time": "1:06:25", "throughput": 4634.55, "total_tokens": 24216640} {"current_steps": 24070, "total_steps": 42420, "loss": 0.0315, "lr": 2.3482718741812625e-05, "epoch": 11.348420556341349, "percentage": 56.74, "elapsed_time": "1:27:06", "remaining_time": "1:06:24", "throughput": 4634.52, "total_tokens": 24221088} {"current_steps": 24075, "total_steps": 42420, "loss": 0.145, "lr": 2.3472451827332267e-05, "epoch": 11.350777934936351, "percentage": 56.75, "elapsed_time": "1:27:07", "remaining_time": "1:06:23", "throughput": 4634.55, "total_tokens": 24225728} {"current_steps": 24080, "total_steps": 42420, "loss": 0.0407, "lr": 2.3462185171439878e-05, "epoch": 11.353135313531354, "percentage": 56.77, "elapsed_time": "1:27:08", "remaining_time": "1:06:22", "throughput": 4634.61, "total_tokens": 24231008} {"current_steps": 24085, "total_steps": 42420, "loss": 0.0713, "lr": 2.3451918775873426e-05, "epoch": 11.355492692126356, "percentage": 56.78, "elapsed_time": "1:27:09", "remaining_time": "1:06:20", "throughput": 4634.67, "total_tokens": 24236608} {"current_steps": 24090, "total_steps": 42420, "loss": 0.0662, "lr": 2.3441652642370853e-05, "epoch": 11.357850070721359, "percentage": 56.79, "elapsed_time": "1:27:10", "remaining_time": "1:06:19", "throughput": 4634.72, "total_tokens": 24242240} {"current_steps": 24095, "total_steps": 42420, "loss": 0.1972, "lr": 2.3431386772670013e-05, "epoch": 11.360207449316361, "percentage": 56.8, "elapsed_time": "1:27:11", "remaining_time": "1:06:19", "throughput": 4634.82, "total_tokens": 24249024} {"current_steps": 24100, "total_steps": 42420, "loss": 0.0816, "lr": 2.3421121168508768e-05, "epoch": 11.362564827911363, "percentage": 56.81, "elapsed_time": "1:27:13", "remaining_time": "1:06:17", "throughput": 4634.88, "total_tokens": 24254400} {"current_steps": 24105, "total_steps": 42420, "loss": 0.0485, "lr": 2.3410855831624896e-05, "epoch": 11.364922206506366, "percentage": 56.82, "elapsed_time": "1:27:13", "remaining_time": "1:06:16", "throughput": 4634.88, "total_tokens": 24258752} {"current_steps": 24110, "total_steps": 42420, "loss": 0.1364, "lr": 2.3400590763756154e-05, "epoch": 11.367279585101368, "percentage": 56.84, "elapsed_time": "1:27:14", "remaining_time": "1:06:15", "throughput": 4634.91, "total_tokens": 24263616} {"current_steps": 24115, "total_steps": 42420, "loss": 0.1211, "lr": 2.3390325966640237e-05, "epoch": 11.369636963696369, "percentage": 56.85, "elapsed_time": "1:27:16", "remaining_time": "1:06:14", "throughput": 4635.01, "total_tokens": 24269792} {"current_steps": 24120, "total_steps": 42420, "loss": 0.1762, "lr": 2.3380061442014802e-05, "epoch": 11.371994342291371, "percentage": 56.86, "elapsed_time": "1:27:17", "remaining_time": "1:06:13", "throughput": 4635.05, "total_tokens": 24275360} {"current_steps": 24125, "total_steps": 42420, "loss": 0.0766, "lr": 2.336979719161746e-05, "epoch": 11.374351720886374, "percentage": 56.87, "elapsed_time": "1:27:18", "remaining_time": "1:06:12", "throughput": 4635.09, "total_tokens": 24280096} {"current_steps": 24130, "total_steps": 42420, "loss": 0.0304, "lr": 2.335953321718578e-05, "epoch": 11.376709099481376, "percentage": 56.88, "elapsed_time": "1:27:19", "remaining_time": "1:06:11", "throughput": 4635.11, "total_tokens": 24284608} {"current_steps": 24135, "total_steps": 42420, "loss": 0.077, "lr": 2.334926952045727e-05, "epoch": 11.379066478076378, "percentage": 56.9, "elapsed_time": "1:27:20", "remaining_time": "1:06:10", "throughput": 4635.1, "total_tokens": 24288704} {"current_steps": 24140, "total_steps": 42420, "loss": 0.1272, "lr": 2.3339006103169397e-05, "epoch": 11.38142385667138, "percentage": 56.91, "elapsed_time": "1:27:21", "remaining_time": "1:06:08", "throughput": 4635.12, "total_tokens": 24292960} {"current_steps": 24145, "total_steps": 42420, "loss": 0.1616, "lr": 2.332874296705959e-05, "epoch": 11.383781235266383, "percentage": 56.92, "elapsed_time": "1:27:22", "remaining_time": "1:06:07", "throughput": 4635.17, "total_tokens": 24298176} {"current_steps": 24150, "total_steps": 42420, "loss": 0.0894, "lr": 2.3318480113865232e-05, "epoch": 11.386138613861386, "percentage": 56.93, "elapsed_time": "1:27:23", "remaining_time": "1:06:06", "throughput": 4635.19, "total_tokens": 24302848} {"current_steps": 24155, "total_steps": 42420, "loss": 0.1239, "lr": 2.3308217545323628e-05, "epoch": 11.388495992456388, "percentage": 56.94, "elapsed_time": "1:27:24", "remaining_time": "1:06:05", "throughput": 4635.21, "total_tokens": 24307296} {"current_steps": 24160, "total_steps": 42420, "loss": 0.0676, "lr": 2.3297955263172076e-05, "epoch": 11.39085337105139, "percentage": 56.95, "elapsed_time": "1:27:25", "remaining_time": "1:06:04", "throughput": 4635.26, "total_tokens": 24312608} {"current_steps": 24165, "total_steps": 42420, "loss": 0.0595, "lr": 2.3287693269147794e-05, "epoch": 11.393210749646393, "percentage": 56.97, "elapsed_time": "1:27:26", "remaining_time": "1:06:03", "throughput": 4635.29, "total_tokens": 24317024} {"current_steps": 24170, "total_steps": 42420, "loss": 0.1237, "lr": 2.3277431564987974e-05, "epoch": 11.395568128241395, "percentage": 56.98, "elapsed_time": "1:27:27", "remaining_time": "1:06:01", "throughput": 4635.32, "total_tokens": 24321536} {"current_steps": 24175, "total_steps": 42420, "loss": 0.0973, "lr": 2.3267170152429736e-05, "epoch": 11.397925506836398, "percentage": 56.99, "elapsed_time": "1:27:27", "remaining_time": "1:06:00", "throughput": 4635.28, "total_tokens": 24325536} {"current_steps": 24180, "total_steps": 42420, "loss": 0.1596, "lr": 2.3256909033210175e-05, "epoch": 11.4002828854314, "percentage": 57.0, "elapsed_time": "1:27:28", "remaining_time": "1:05:59", "throughput": 4635.27, "total_tokens": 24330144} {"current_steps": 24185, "total_steps": 42420, "loss": 0.2101, "lr": 2.3246648209066312e-05, "epoch": 11.402640264026402, "percentage": 57.01, "elapsed_time": "1:27:29", "remaining_time": "1:05:58", "throughput": 4635.29, "total_tokens": 24334752} {"current_steps": 24190, "total_steps": 42420, "loss": 0.0178, "lr": 2.3236387681735146e-05, "epoch": 11.404997642621405, "percentage": 57.02, "elapsed_time": "1:27:30", "remaining_time": "1:05:57", "throughput": 4635.28, "total_tokens": 24339712} {"current_steps": 24195, "total_steps": 42420, "loss": 0.1003, "lr": 2.3226127452953598e-05, "epoch": 11.407355021216407, "percentage": 57.04, "elapsed_time": "1:27:32", "remaining_time": "1:05:56", "throughput": 4635.32, "total_tokens": 24344704} {"current_steps": 24200, "total_steps": 42420, "loss": 0.0352, "lr": 2.321586752445855e-05, "epoch": 11.40971239981141, "percentage": 57.05, "elapsed_time": "1:27:33", "remaining_time": "1:05:55", "throughput": 4635.4, "total_tokens": 24351040} {"current_steps": 24205, "total_steps": 42420, "loss": 0.1186, "lr": 2.3205607897986837e-05, "epoch": 11.412069778406412, "percentage": 57.06, "elapsed_time": "1:27:34", "remaining_time": "1:05:54", "throughput": 4635.44, "total_tokens": 24356224} {"current_steps": 24210, "total_steps": 42420, "loss": 0.0367, "lr": 2.3195348575275246e-05, "epoch": 11.414427157001414, "percentage": 57.07, "elapsed_time": "1:27:35", "remaining_time": "1:05:52", "throughput": 4635.5, "total_tokens": 24361216} {"current_steps": 24215, "total_steps": 42420, "loss": 0.0255, "lr": 2.3185089558060497e-05, "epoch": 11.416784535596417, "percentage": 57.08, "elapsed_time": "1:27:36", "remaining_time": "1:05:51", "throughput": 4635.56, "total_tokens": 24366880} {"current_steps": 24220, "total_steps": 42420, "loss": 0.1074, "lr": 2.3174830848079266e-05, "epoch": 11.41914191419142, "percentage": 57.1, "elapsed_time": "1:27:37", "remaining_time": "1:05:50", "throughput": 4635.61, "total_tokens": 24372000} {"current_steps": 24225, "total_steps": 42420, "loss": 0.0389, "lr": 2.3164572447068186e-05, "epoch": 11.421499292786422, "percentage": 57.11, "elapsed_time": "1:27:38", "remaining_time": "1:05:49", "throughput": 4635.62, "total_tokens": 24376160} {"current_steps": 24230, "total_steps": 42420, "loss": 0.2016, "lr": 2.315431435676383e-05, "epoch": 11.423856671381424, "percentage": 57.12, "elapsed_time": "1:27:39", "remaining_time": "1:05:48", "throughput": 4635.67, "total_tokens": 24381088} {"current_steps": 24235, "total_steps": 42420, "loss": 0.0156, "lr": 2.3144056578902713e-05, "epoch": 11.426214049976426, "percentage": 57.13, "elapsed_time": "1:27:40", "remaining_time": "1:05:47", "throughput": 4635.75, "total_tokens": 24387136} {"current_steps": 24240, "total_steps": 42420, "loss": 0.0588, "lr": 2.31337991152213e-05, "epoch": 11.428571428571429, "percentage": 57.14, "elapsed_time": "1:27:42", "remaining_time": "1:05:46", "throughput": 4635.83, "total_tokens": 24394016} {"current_steps": 24245, "total_steps": 42420, "loss": 0.0523, "lr": 2.3123541967456016e-05, "epoch": 11.430928807166431, "percentage": 57.15, "elapsed_time": "1:27:43", "remaining_time": "1:05:45", "throughput": 4635.9, "total_tokens": 24399872} {"current_steps": 24250, "total_steps": 42420, "loss": 0.0799, "lr": 2.311328513734322e-05, "epoch": 11.433286185761434, "percentage": 57.17, "elapsed_time": "1:27:44", "remaining_time": "1:05:44", "throughput": 4635.94, "total_tokens": 24404864} {"current_steps": 24255, "total_steps": 42420, "loss": 0.1161, "lr": 2.3103028626619222e-05, "epoch": 11.435643564356436, "percentage": 57.18, "elapsed_time": "1:27:45", "remaining_time": "1:05:43", "throughput": 4635.94, "total_tokens": 24409280} {"current_steps": 24260, "total_steps": 42420, "loss": 0.0427, "lr": 2.3092772437020256e-05, "epoch": 11.438000942951438, "percentage": 57.19, "elapsed_time": "1:27:46", "remaining_time": "1:05:42", "throughput": 4635.98, "total_tokens": 24413792} {"current_steps": 24265, "total_steps": 42420, "loss": 0.1381, "lr": 2.3082516570282535e-05, "epoch": 11.44035832154644, "percentage": 57.2, "elapsed_time": "1:27:47", "remaining_time": "1:05:40", "throughput": 4636.02, "total_tokens": 24418592} {"current_steps": 24270, "total_steps": 42420, "loss": 0.1086, "lr": 2.30722610281422e-05, "epoch": 11.442715700141443, "percentage": 57.21, "elapsed_time": "1:27:48", "remaining_time": "1:05:39", "throughput": 4636.05, "total_tokens": 24423296} {"current_steps": 24275, "total_steps": 42420, "loss": 0.3978, "lr": 2.3062005812335348e-05, "epoch": 11.445073078736446, "percentage": 57.23, "elapsed_time": "1:27:49", "remaining_time": "1:05:38", "throughput": 4636.1, "total_tokens": 24428032} {"current_steps": 24280, "total_steps": 42420, "loss": 0.1738, "lr": 2.3051750924598002e-05, "epoch": 11.447430457331448, "percentage": 57.24, "elapsed_time": "1:27:50", "remaining_time": "1:05:37", "throughput": 4636.15, "total_tokens": 24433792} {"current_steps": 24285, "total_steps": 42420, "loss": 0.036, "lr": 2.304149636666614e-05, "epoch": 11.44978783592645, "percentage": 57.25, "elapsed_time": "1:27:51", "remaining_time": "1:05:36", "throughput": 4636.21, "total_tokens": 24439520} {"current_steps": 24290, "total_steps": 42420, "loss": 0.2354, "lr": 2.30312421402757e-05, "epoch": 11.452145214521453, "percentage": 57.26, "elapsed_time": "1:27:52", "remaining_time": "1:05:35", "throughput": 4636.16, "total_tokens": 24443232} {"current_steps": 24295, "total_steps": 42420, "loss": 0.0356, "lr": 2.3020988247162536e-05, "epoch": 11.454502593116455, "percentage": 57.27, "elapsed_time": "1:27:53", "remaining_time": "1:05:34", "throughput": 4636.19, "total_tokens": 24447744} {"current_steps": 24300, "total_steps": 42420, "loss": 0.1489, "lr": 2.3010734689062457e-05, "epoch": 11.456859971711458, "percentage": 57.28, "elapsed_time": "1:27:54", "remaining_time": "1:05:32", "throughput": 4636.21, "total_tokens": 24451872} {"current_steps": 24305, "total_steps": 42420, "loss": 0.2179, "lr": 2.300048146771122e-05, "epoch": 11.45921735030646, "percentage": 57.3, "elapsed_time": "1:27:55", "remaining_time": "1:05:31", "throughput": 4636.27, "total_tokens": 24457472} {"current_steps": 24310, "total_steps": 42420, "loss": 0.0726, "lr": 2.2990228584844516e-05, "epoch": 11.46157472890146, "percentage": 57.31, "elapsed_time": "1:27:56", "remaining_time": "1:05:30", "throughput": 4636.34, "total_tokens": 24463296} {"current_steps": 24315, "total_steps": 42420, "loss": 0.0551, "lr": 2.2979976042197997e-05, "epoch": 11.463932107496463, "percentage": 57.32, "elapsed_time": "1:27:57", "remaining_time": "1:05:29", "throughput": 4636.38, "total_tokens": 24468704} {"current_steps": 24320, "total_steps": 42420, "loss": 0.1777, "lr": 2.296972384150723e-05, "epoch": 11.466289486091465, "percentage": 57.33, "elapsed_time": "1:27:58", "remaining_time": "1:05:28", "throughput": 4636.43, "total_tokens": 24474496} {"current_steps": 24325, "total_steps": 42420, "loss": 0.1685, "lr": 2.2959471984507746e-05, "epoch": 11.468646864686468, "percentage": 57.34, "elapsed_time": "1:27:59", "remaining_time": "1:05:27", "throughput": 4636.4, "total_tokens": 24478944} {"current_steps": 24330, "total_steps": 42420, "loss": 0.3608, "lr": 2.294922047293501e-05, "epoch": 11.47100424328147, "percentage": 57.36, "elapsed_time": "1:28:00", "remaining_time": "1:05:26", "throughput": 4636.45, "total_tokens": 24484672} {"current_steps": 24335, "total_steps": 42420, "loss": 0.1256, "lr": 2.2938969308524433e-05, "epoch": 11.473361621876473, "percentage": 57.37, "elapsed_time": "1:28:01", "remaining_time": "1:05:25", "throughput": 4636.47, "total_tokens": 24489184} {"current_steps": 24340, "total_steps": 42420, "loss": 0.0305, "lr": 2.2928718493011348e-05, "epoch": 11.475719000471475, "percentage": 57.38, "elapsed_time": "1:28:02", "remaining_time": "1:05:24", "throughput": 4636.5, "total_tokens": 24493632} {"current_steps": 24345, "total_steps": 42420, "loss": 0.2899, "lr": 2.291846802813106e-05, "epoch": 11.478076379066477, "percentage": 57.39, "elapsed_time": "1:28:04", "remaining_time": "1:05:23", "throughput": 4636.55, "total_tokens": 24499552} {"current_steps": 24350, "total_steps": 42420, "loss": 0.0606, "lr": 2.2908217915618786e-05, "epoch": 11.48043375766148, "percentage": 57.4, "elapsed_time": "1:28:05", "remaining_time": "1:05:21", "throughput": 4636.56, "total_tokens": 24504256} {"current_steps": 24355, "total_steps": 42420, "loss": 0.1472, "lr": 2.289796815720971e-05, "epoch": 11.482791136256482, "percentage": 57.41, "elapsed_time": "1:28:05", "remaining_time": "1:05:20", "throughput": 4636.58, "total_tokens": 24508480} {"current_steps": 24360, "total_steps": 42420, "loss": 0.0462, "lr": 2.2887718754638933e-05, "epoch": 11.485148514851485, "percentage": 57.43, "elapsed_time": "1:28:06", "remaining_time": "1:05:19", "throughput": 4636.62, "total_tokens": 24512992} {"current_steps": 24365, "total_steps": 42420, "loss": 0.0932, "lr": 2.28774697096415e-05, "epoch": 11.487505893446487, "percentage": 57.44, "elapsed_time": "1:28:08", "remaining_time": "1:05:18", "throughput": 4636.66, "total_tokens": 24519872} {"current_steps": 24370, "total_steps": 42420, "loss": 0.1369, "lr": 2.286722102395241e-05, "epoch": 11.48986327204149, "percentage": 57.45, "elapsed_time": "1:28:09", "remaining_time": "1:05:17", "throughput": 4636.69, "total_tokens": 24524544} {"current_steps": 24375, "total_steps": 42420, "loss": 0.1323, "lr": 2.2856972699306595e-05, "epoch": 11.492220650636492, "percentage": 57.46, "elapsed_time": "1:28:10", "remaining_time": "1:05:16", "throughput": 4636.74, "total_tokens": 24530368} {"current_steps": 24380, "total_steps": 42420, "loss": 0.052, "lr": 2.2846724737438907e-05, "epoch": 11.494578029231494, "percentage": 57.47, "elapsed_time": "1:28:11", "remaining_time": "1:05:15", "throughput": 4636.76, "total_tokens": 24534784} {"current_steps": 24385, "total_steps": 42420, "loss": 0.2704, "lr": 2.283647714008416e-05, "epoch": 11.496935407826497, "percentage": 57.48, "elapsed_time": "1:28:12", "remaining_time": "1:05:14", "throughput": 4636.8, "total_tokens": 24539712} {"current_steps": 24390, "total_steps": 42420, "loss": 0.0331, "lr": 2.2826229908977105e-05, "epoch": 11.499292786421499, "percentage": 57.5, "elapsed_time": "1:28:13", "remaining_time": "1:05:13", "throughput": 4636.85, "total_tokens": 24544512} {"current_steps": 24395, "total_steps": 42420, "loss": 0.0829, "lr": 2.2815983045852414e-05, "epoch": 11.501650165016502, "percentage": 57.51, "elapsed_time": "1:28:14", "remaining_time": "1:05:12", "throughput": 4636.93, "total_tokens": 24550464} {"current_steps": 24400, "total_steps": 42420, "loss": 0.1987, "lr": 2.2805736552444713e-05, "epoch": 11.504007543611504, "percentage": 57.52, "elapsed_time": "1:28:15", "remaining_time": "1:05:10", "throughput": 4636.95, "total_tokens": 24555200} {"current_steps": 24405, "total_steps": 42420, "loss": 0.1517, "lr": 2.2795490430488552e-05, "epoch": 11.506364922206506, "percentage": 57.53, "elapsed_time": "1:28:16", "remaining_time": "1:05:09", "throughput": 4637.01, "total_tokens": 24560416} {"current_steps": 24410, "total_steps": 42420, "loss": 0.2632, "lr": 2.2785244681718435e-05, "epoch": 11.508722300801509, "percentage": 57.54, "elapsed_time": "1:28:17", "remaining_time": "1:05:08", "throughput": 4637.02, "total_tokens": 24564544} {"current_steps": 24415, "total_steps": 42420, "loss": 0.0887, "lr": 2.277499930786879e-05, "epoch": 11.511079679396511, "percentage": 57.56, "elapsed_time": "1:28:18", "remaining_time": "1:05:07", "throughput": 4637.1, "total_tokens": 24570784} {"current_steps": 24420, "total_steps": 42420, "loss": 0.0589, "lr": 2.2764754310673982e-05, "epoch": 11.513437057991514, "percentage": 57.57, "elapsed_time": "1:28:19", "remaining_time": "1:05:06", "throughput": 4637.13, "total_tokens": 24575392} {"current_steps": 24425, "total_steps": 42420, "loss": 0.1879, "lr": 2.2754509691868317e-05, "epoch": 11.515794436586516, "percentage": 57.58, "elapsed_time": "1:28:20", "remaining_time": "1:05:05", "throughput": 4637.15, "total_tokens": 24580064} {"current_steps": 24430, "total_steps": 42420, "loss": 0.1006, "lr": 2.2744265453186035e-05, "epoch": 11.518151815181518, "percentage": 57.59, "elapsed_time": "1:28:21", "remaining_time": "1:05:04", "throughput": 4637.2, "total_tokens": 24585632} {"current_steps": 24435, "total_steps": 42420, "loss": 0.0462, "lr": 2.2734021596361312e-05, "epoch": 11.52050919377652, "percentage": 57.6, "elapsed_time": "1:28:22", "remaining_time": "1:05:03", "throughput": 4637.22, "total_tokens": 24590048} {"current_steps": 24440, "total_steps": 42420, "loss": 0.0573, "lr": 2.2723778123128257e-05, "epoch": 11.522866572371523, "percentage": 57.61, "elapsed_time": "1:28:23", "remaining_time": "1:05:01", "throughput": 4637.28, "total_tokens": 24595040} {"current_steps": 24445, "total_steps": 42420, "loss": 0.1907, "lr": 2.2713535035220922e-05, "epoch": 11.525223950966526, "percentage": 57.63, "elapsed_time": "1:28:25", "remaining_time": "1:05:00", "throughput": 4637.33, "total_tokens": 24601184} {"current_steps": 24450, "total_steps": 42420, "loss": 0.0603, "lr": 2.2703292334373278e-05, "epoch": 11.527581329561528, "percentage": 57.64, "elapsed_time": "1:28:25", "remaining_time": "1:04:59", "throughput": 4637.35, "total_tokens": 24605536} {"current_steps": 24455, "total_steps": 42420, "loss": 0.031, "lr": 2.269305002231925e-05, "epoch": 11.52993870815653, "percentage": 57.65, "elapsed_time": "1:28:27", "remaining_time": "1:04:58", "throughput": 4637.39, "total_tokens": 24610784} {"current_steps": 24460, "total_steps": 42420, "loss": 0.1234, "lr": 2.2682808100792683e-05, "epoch": 11.532296086751533, "percentage": 57.66, "elapsed_time": "1:28:27", "remaining_time": "1:04:57", "throughput": 4637.42, "total_tokens": 24615360} {"current_steps": 24465, "total_steps": 42420, "loss": 0.274, "lr": 2.2672566571527357e-05, "epoch": 11.534653465346535, "percentage": 57.67, "elapsed_time": "1:28:29", "remaining_time": "1:04:56", "throughput": 4637.48, "total_tokens": 24620992} {"current_steps": 24470, "total_steps": 42420, "loss": 0.009, "lr": 2.2662325436256994e-05, "epoch": 11.537010843941538, "percentage": 57.69, "elapsed_time": "1:28:30", "remaining_time": "1:04:55", "throughput": 4637.53, "total_tokens": 24626368} {"current_steps": 24475, "total_steps": 42420, "loss": 0.1456, "lr": 2.2652084696715247e-05, "epoch": 11.53936822253654, "percentage": 57.7, "elapsed_time": "1:28:31", "remaining_time": "1:04:54", "throughput": 4637.6, "total_tokens": 24632000} {"current_steps": 24480, "total_steps": 42420, "loss": 0.129, "lr": 2.2641844354635694e-05, "epoch": 11.541725601131542, "percentage": 57.71, "elapsed_time": "1:28:32", "remaining_time": "1:04:53", "throughput": 4637.59, "total_tokens": 24636480} {"current_steps": 24485, "total_steps": 42420, "loss": 0.0394, "lr": 2.263160441175186e-05, "epoch": 11.544082979726545, "percentage": 57.72, "elapsed_time": "1:28:33", "remaining_time": "1:04:51", "throughput": 4637.6, "total_tokens": 24641024} {"current_steps": 24490, "total_steps": 42420, "loss": 0.1456, "lr": 2.262136486979718e-05, "epoch": 11.546440358321547, "percentage": 57.73, "elapsed_time": "1:28:34", "remaining_time": "1:04:50", "throughput": 4637.66, "total_tokens": 24646080} {"current_steps": 24495, "total_steps": 42420, "loss": 0.0603, "lr": 2.2611125730505035e-05, "epoch": 11.54879773691655, "percentage": 57.74, "elapsed_time": "1:28:35", "remaining_time": "1:04:49", "throughput": 4637.64, "total_tokens": 24650304} {"current_steps": 24500, "total_steps": 42420, "loss": 0.1125, "lr": 2.2600886995608744e-05, "epoch": 11.551155115511552, "percentage": 57.76, "elapsed_time": "1:28:36", "remaining_time": "1:04:48", "throughput": 4637.67, "total_tokens": 24655168} {"current_steps": 24505, "total_steps": 42420, "loss": 0.1674, "lr": 2.2590648666841556e-05, "epoch": 11.553512494106554, "percentage": 57.77, "elapsed_time": "1:28:37", "remaining_time": "1:04:47", "throughput": 4637.67, "total_tokens": 24660576} {"current_steps": 24510, "total_steps": 42420, "loss": 0.0425, "lr": 2.2580410745936636e-05, "epoch": 11.555869872701557, "percentage": 57.78, "elapsed_time": "1:28:38", "remaining_time": "1:04:46", "throughput": 4637.68, "total_tokens": 24665184} {"current_steps": 24515, "total_steps": 42420, "loss": 0.1158, "lr": 2.2570173234627095e-05, "epoch": 11.558227251296557, "percentage": 57.79, "elapsed_time": "1:28:39", "remaining_time": "1:04:45", "throughput": 4637.67, "total_tokens": 24669408} {"current_steps": 24520, "total_steps": 42420, "loss": 0.2407, "lr": 2.255993613464597e-05, "epoch": 11.56058462989156, "percentage": 57.8, "elapsed_time": "1:28:40", "remaining_time": "1:04:43", "throughput": 4637.71, "total_tokens": 24674240} {"current_steps": 24525, "total_steps": 42420, "loss": 0.1446, "lr": 2.254969944772623e-05, "epoch": 11.562942008486562, "percentage": 57.81, "elapsed_time": "1:28:41", "remaining_time": "1:04:42", "throughput": 4637.73, "total_tokens": 24679616} {"current_steps": 24530, "total_steps": 42420, "loss": 0.1452, "lr": 2.2539463175600764e-05, "epoch": 11.565299387081565, "percentage": 57.83, "elapsed_time": "1:28:42", "remaining_time": "1:04:41", "throughput": 4637.77, "total_tokens": 24684128} {"current_steps": 24535, "total_steps": 42420, "loss": 0.1432, "lr": 2.2529227320002405e-05, "epoch": 11.567656765676567, "percentage": 57.84, "elapsed_time": "1:28:43", "remaining_time": "1:04:40", "throughput": 4637.78, "total_tokens": 24688320} {"current_steps": 24540, "total_steps": 42420, "loss": 0.1094, "lr": 2.251899188266391e-05, "epoch": 11.57001414427157, "percentage": 57.85, "elapsed_time": "1:28:44", "remaining_time": "1:04:39", "throughput": 4637.85, "total_tokens": 24694272} {"current_steps": 24545, "total_steps": 42420, "loss": 0.1162, "lr": 2.2508756865317973e-05, "epoch": 11.572371522866572, "percentage": 57.86, "elapsed_time": "1:28:45", "remaining_time": "1:04:38", "throughput": 4637.89, "total_tokens": 24699520} {"current_steps": 24550, "total_steps": 42420, "loss": 0.0874, "lr": 2.2498522269697193e-05, "epoch": 11.574728901461574, "percentage": 57.87, "elapsed_time": "1:28:46", "remaining_time": "1:04:37", "throughput": 4637.93, "total_tokens": 24704256} {"current_steps": 24555, "total_steps": 42420, "loss": 0.1004, "lr": 2.2488288097534116e-05, "epoch": 11.577086280056577, "percentage": 57.89, "elapsed_time": "1:28:47", "remaining_time": "1:04:36", "throughput": 4638.0, "total_tokens": 24709888} {"current_steps": 24560, "total_steps": 42420, "loss": 0.0516, "lr": 2.247805435056122e-05, "epoch": 11.579443658651579, "percentage": 57.9, "elapsed_time": "1:28:48", "remaining_time": "1:04:34", "throughput": 4638.01, "total_tokens": 24714272} {"current_steps": 24565, "total_steps": 42420, "loss": 0.0484, "lr": 2.246782103051091e-05, "epoch": 11.581801037246581, "percentage": 57.91, "elapsed_time": "1:28:49", "remaining_time": "1:04:33", "throughput": 4638.05, "total_tokens": 24718976} {"current_steps": 24570, "total_steps": 42420, "loss": 0.2398, "lr": 2.2457588139115496e-05, "epoch": 11.584158415841584, "percentage": 57.92, "elapsed_time": "1:28:50", "remaining_time": "1:04:32", "throughput": 4638.08, "total_tokens": 24724096} {"current_steps": 24575, "total_steps": 42420, "loss": 0.0229, "lr": 2.2447355678107247e-05, "epoch": 11.586515794436586, "percentage": 57.93, "elapsed_time": "1:28:51", "remaining_time": "1:04:31", "throughput": 4638.11, "total_tokens": 24729408} {"current_steps": 24580, "total_steps": 42420, "loss": 0.1776, "lr": 2.2437123649218335e-05, "epoch": 11.588873173031589, "percentage": 57.94, "elapsed_time": "1:28:52", "remaining_time": "1:04:30", "throughput": 4638.16, "total_tokens": 24734336} {"current_steps": 24585, "total_steps": 42420, "loss": 0.0607, "lr": 2.242689205418088e-05, "epoch": 11.591230551626591, "percentage": 57.96, "elapsed_time": "1:28:53", "remaining_time": "1:04:29", "throughput": 4638.09, "total_tokens": 24738432} {"current_steps": 24590, "total_steps": 42420, "loss": 0.0599, "lr": 2.2416660894726908e-05, "epoch": 11.593587930221593, "percentage": 57.97, "elapsed_time": "1:28:54", "remaining_time": "1:04:28", "throughput": 4638.14, "total_tokens": 24743904} {"current_steps": 24595, "total_steps": 42420, "loss": 0.0074, "lr": 2.2406430172588386e-05, "epoch": 11.595945308816596, "percentage": 57.98, "elapsed_time": "1:28:55", "remaining_time": "1:04:27", "throughput": 4638.19, "total_tokens": 24749088} {"current_steps": 24600, "total_steps": 42420, "loss": 0.0574, "lr": 2.23961998894972e-05, "epoch": 11.598302687411598, "percentage": 57.99, "elapsed_time": "1:28:56", "remaining_time": "1:04:25", "throughput": 4638.23, "total_tokens": 24753728} {"current_steps": 24605, "total_steps": 42420, "loss": 0.061, "lr": 2.2385970047185163e-05, "epoch": 11.6006600660066, "percentage": 58.0, "elapsed_time": "1:28:57", "remaining_time": "1:04:24", "throughput": 4638.29, "total_tokens": 24759072} {"current_steps": 24610, "total_steps": 42420, "loss": 0.2886, "lr": 2.237574064738401e-05, "epoch": 11.603017444601603, "percentage": 58.02, "elapsed_time": "1:28:58", "remaining_time": "1:04:23", "throughput": 4638.31, "total_tokens": 24763744} {"current_steps": 24615, "total_steps": 42420, "loss": 0.1427, "lr": 2.236551169182541e-05, "epoch": 11.605374823196605, "percentage": 58.03, "elapsed_time": "1:29:00", "remaining_time": "1:04:22", "throughput": 4638.33, "total_tokens": 24768704} {"current_steps": 24620, "total_steps": 42420, "loss": 0.165, "lr": 2.235528318224095e-05, "epoch": 11.607732201791608, "percentage": 58.04, "elapsed_time": "1:29:00", "remaining_time": "1:04:21", "throughput": 4638.34, "total_tokens": 24773056} {"current_steps": 24625, "total_steps": 42420, "loss": 0.0909, "lr": 2.2345055120362143e-05, "epoch": 11.61008958038661, "percentage": 58.05, "elapsed_time": "1:29:02", "remaining_time": "1:04:20", "throughput": 4638.37, "total_tokens": 24778272} {"current_steps": 24630, "total_steps": 42420, "loss": 0.0843, "lr": 2.2334827507920426e-05, "epoch": 11.612446958981613, "percentage": 58.06, "elapsed_time": "1:29:03", "remaining_time": "1:04:19", "throughput": 4638.41, "total_tokens": 24783296} {"current_steps": 24635, "total_steps": 42420, "loss": 0.0875, "lr": 2.2324600346647153e-05, "epoch": 11.614804337576615, "percentage": 58.07, "elapsed_time": "1:29:04", "remaining_time": "1:04:18", "throughput": 4638.49, "total_tokens": 24789376} {"current_steps": 24640, "total_steps": 42420, "loss": 0.1388, "lr": 2.231437363827362e-05, "epoch": 11.617161716171617, "percentage": 58.09, "elapsed_time": "1:29:05", "remaining_time": "1:04:17", "throughput": 4638.51, "total_tokens": 24793824} {"current_steps": 24645, "total_steps": 42420, "loss": 0.0995, "lr": 2.2304147384531038e-05, "epoch": 11.61951909476662, "percentage": 58.1, "elapsed_time": "1:29:06", "remaining_time": "1:04:15", "throughput": 4638.56, "total_tokens": 24798976} {"current_steps": 24650, "total_steps": 42420, "loss": 0.1239, "lr": 2.2293921587150524e-05, "epoch": 11.621876473361622, "percentage": 58.11, "elapsed_time": "1:29:07", "remaining_time": "1:04:14", "throughput": 4638.56, "total_tokens": 24802912} {"current_steps": 24655, "total_steps": 42420, "loss": 0.2277, "lr": 2.2283696247863135e-05, "epoch": 11.624233851956625, "percentage": 58.12, "elapsed_time": "1:29:08", "remaining_time": "1:04:13", "throughput": 4638.6, "total_tokens": 24808480} {"current_steps": 24660, "total_steps": 42420, "loss": 0.1573, "lr": 2.2273471368399857e-05, "epoch": 11.626591230551627, "percentage": 58.13, "elapsed_time": "1:29:09", "remaining_time": "1:04:12", "throughput": 4638.62, "total_tokens": 24813600} {"current_steps": 24665, "total_steps": 42420, "loss": 0.1155, "lr": 2.2263246950491584e-05, "epoch": 11.62894860914663, "percentage": 58.14, "elapsed_time": "1:29:10", "remaining_time": "1:04:11", "throughput": 4638.67, "total_tokens": 24818560} {"current_steps": 24670, "total_steps": 42420, "loss": 0.1292, "lr": 2.225302299586913e-05, "epoch": 11.631305987741632, "percentage": 58.16, "elapsed_time": "1:29:11", "remaining_time": "1:04:10", "throughput": 4638.65, "total_tokens": 24822400} {"current_steps": 24675, "total_steps": 42420, "loss": 0.0993, "lr": 2.224279950626324e-05, "epoch": 11.633663366336634, "percentage": 58.17, "elapsed_time": "1:29:12", "remaining_time": "1:04:09", "throughput": 4638.69, "total_tokens": 24827232} {"current_steps": 24680, "total_steps": 42420, "loss": 0.0978, "lr": 2.2232576483404582e-05, "epoch": 11.636020744931637, "percentage": 58.18, "elapsed_time": "1:29:13", "remaining_time": "1:04:07", "throughput": 4638.74, "total_tokens": 24832096} {"current_steps": 24685, "total_steps": 42420, "loss": 0.0566, "lr": 2.222235392902374e-05, "epoch": 11.638378123526639, "percentage": 58.19, "elapsed_time": "1:29:14", "remaining_time": "1:04:06", "throughput": 4638.73, "total_tokens": 24836512} {"current_steps": 24690, "total_steps": 42420, "loss": 0.1573, "lr": 2.2212131844851212e-05, "epoch": 11.640735502121641, "percentage": 58.2, "elapsed_time": "1:29:15", "remaining_time": "1:04:05", "throughput": 4638.77, "total_tokens": 24841536} {"current_steps": 24695, "total_steps": 42420, "loss": 0.1072, "lr": 2.220191023261743e-05, "epoch": 11.643092880716644, "percentage": 58.22, "elapsed_time": "1:29:16", "remaining_time": "1:04:04", "throughput": 4638.79, "total_tokens": 24846176} {"current_steps": 24700, "total_steps": 42420, "loss": 0.1517, "lr": 2.2191689094052736e-05, "epoch": 11.645450259311646, "percentage": 58.23, "elapsed_time": "1:29:17", "remaining_time": "1:04:03", "throughput": 4638.74, "total_tokens": 24850144} {"current_steps": 24705, "total_steps": 42420, "loss": 0.1321, "lr": 2.21814684308874e-05, "epoch": 11.647807637906649, "percentage": 58.24, "elapsed_time": "1:29:18", "remaining_time": "1:04:02", "throughput": 4638.78, "total_tokens": 24855008} {"current_steps": 24710, "total_steps": 42420, "loss": 0.0585, "lr": 2.21712482448516e-05, "epoch": 11.65016501650165, "percentage": 58.25, "elapsed_time": "1:29:19", "remaining_time": "1:04:01", "throughput": 4638.83, "total_tokens": 24861184} {"current_steps": 24715, "total_steps": 42420, "loss": 0.0481, "lr": 2.2161028537675448e-05, "epoch": 11.652522395096653, "percentage": 58.26, "elapsed_time": "1:29:20", "remaining_time": "1:04:00", "throughput": 4638.91, "total_tokens": 24866496} {"current_steps": 24720, "total_steps": 42420, "loss": 0.1199, "lr": 2.2150809311088953e-05, "epoch": 11.654879773691654, "percentage": 58.27, "elapsed_time": "1:29:21", "remaining_time": "1:03:59", "throughput": 4638.97, "total_tokens": 24872608} {"current_steps": 24725, "total_steps": 42420, "loss": 0.0917, "lr": 2.2140590566822063e-05, "epoch": 11.657237152286656, "percentage": 58.29, "elapsed_time": "1:29:22", "remaining_time": "1:03:58", "throughput": 4639.04, "total_tokens": 24878752} {"current_steps": 24730, "total_steps": 42420, "loss": 0.0515, "lr": 2.2130372306604643e-05, "epoch": 11.659594530881659, "percentage": 58.3, "elapsed_time": "1:29:23", "remaining_time": "1:03:56", "throughput": 4639.07, "total_tokens": 24883648} {"current_steps": 24735, "total_steps": 42420, "loss": 0.0954, "lr": 2.2120154532166474e-05, "epoch": 11.661951909476661, "percentage": 58.31, "elapsed_time": "1:29:24", "remaining_time": "1:03:55", "throughput": 4639.1, "total_tokens": 24888416} {"current_steps": 24740, "total_steps": 42420, "loss": 0.0472, "lr": 2.210993724523724e-05, "epoch": 11.664309288071664, "percentage": 58.32, "elapsed_time": "1:29:26", "remaining_time": "1:03:54", "throughput": 4639.18, "total_tokens": 24894208} {"current_steps": 24745, "total_steps": 42420, "loss": 0.058, "lr": 2.2099720447546557e-05, "epoch": 11.666666666666666, "percentage": 58.33, "elapsed_time": "1:29:27", "remaining_time": "1:03:53", "throughput": 4639.25, "total_tokens": 24899936} {"current_steps": 24750, "total_steps": 42420, "loss": 0.1445, "lr": 2.208950414082396e-05, "epoch": 11.669024045261668, "percentage": 58.35, "elapsed_time": "1:29:28", "remaining_time": "1:03:52", "throughput": 4639.29, "total_tokens": 24904928} {"current_steps": 24755, "total_steps": 42420, "loss": 0.3727, "lr": 2.2079288326798902e-05, "epoch": 11.67138142385667, "percentage": 58.36, "elapsed_time": "1:29:29", "remaining_time": "1:03:51", "throughput": 4639.3, "total_tokens": 24909408} {"current_steps": 24760, "total_steps": 42420, "loss": 0.1505, "lr": 2.2069073007200733e-05, "epoch": 11.673738802451673, "percentage": 58.37, "elapsed_time": "1:29:30", "remaining_time": "1:03:50", "throughput": 4639.27, "total_tokens": 24913088} {"current_steps": 24765, "total_steps": 42420, "loss": 0.1626, "lr": 2.2058858183758738e-05, "epoch": 11.676096181046676, "percentage": 58.38, "elapsed_time": "1:29:30", "remaining_time": "1:03:48", "throughput": 4639.27, "total_tokens": 24917152} {"current_steps": 24770, "total_steps": 42420, "loss": 0.2396, "lr": 2.204864385820212e-05, "epoch": 11.678453559641678, "percentage": 58.39, "elapsed_time": "1:29:31", "remaining_time": "1:03:47", "throughput": 4639.3, "total_tokens": 24921664} {"current_steps": 24775, "total_steps": 42420, "loss": 0.1598, "lr": 2.2038430032259983e-05, "epoch": 11.68081093823668, "percentage": 58.4, "elapsed_time": "1:29:32", "remaining_time": "1:03:46", "throughput": 4639.33, "total_tokens": 24926144} {"current_steps": 24780, "total_steps": 42420, "loss": 0.1124, "lr": 2.2028216707661357e-05, "epoch": 11.683168316831683, "percentage": 58.42, "elapsed_time": "1:29:33", "remaining_time": "1:03:45", "throughput": 4639.38, "total_tokens": 24931904} {"current_steps": 24785, "total_steps": 42420, "loss": 0.0381, "lr": 2.201800388613518e-05, "epoch": 11.685525695426685, "percentage": 58.43, "elapsed_time": "1:29:34", "remaining_time": "1:03:44", "throughput": 4639.36, "total_tokens": 24936352} {"current_steps": 24790, "total_steps": 42420, "loss": 0.0768, "lr": 2.2007791569410318e-05, "epoch": 11.687883074021688, "percentage": 58.44, "elapsed_time": "1:29:35", "remaining_time": "1:03:43", "throughput": 4639.39, "total_tokens": 24940960} {"current_steps": 24795, "total_steps": 42420, "loss": 0.0532, "lr": 2.1997579759215543e-05, "epoch": 11.69024045261669, "percentage": 58.45, "elapsed_time": "1:29:37", "remaining_time": "1:03:42", "throughput": 4639.46, "total_tokens": 24947328} {"current_steps": 24800, "total_steps": 42420, "loss": 0.0965, "lr": 2.1987368457279527e-05, "epoch": 11.692597831211692, "percentage": 58.46, "elapsed_time": "1:29:38", "remaining_time": "1:03:41", "throughput": 4639.46, "total_tokens": 24951936} {"current_steps": 24805, "total_steps": 42420, "loss": 0.1043, "lr": 2.1977157665330884e-05, "epoch": 11.694955209806695, "percentage": 58.47, "elapsed_time": "1:29:39", "remaining_time": "1:03:40", "throughput": 4639.54, "total_tokens": 24958208} {"current_steps": 24810, "total_steps": 42420, "loss": 0.235, "lr": 2.1966947385098125e-05, "epoch": 11.697312588401697, "percentage": 58.49, "elapsed_time": "1:29:40", "remaining_time": "1:03:39", "throughput": 4639.54, "total_tokens": 24963552} {"current_steps": 24815, "total_steps": 42420, "loss": 0.1501, "lr": 2.1956737618309674e-05, "epoch": 11.6996699669967, "percentage": 58.5, "elapsed_time": "1:29:41", "remaining_time": "1:03:37", "throughput": 4639.58, "total_tokens": 24968352} {"current_steps": 24820, "total_steps": 42420, "loss": 0.0219, "lr": 2.1946528366693875e-05, "epoch": 11.702027345591702, "percentage": 58.51, "elapsed_time": "1:29:42", "remaining_time": "1:03:36", "throughput": 4639.6, "total_tokens": 24972800} {"current_steps": 24825, "total_steps": 42420, "loss": 0.1378, "lr": 2.1936319631978974e-05, "epoch": 11.704384724186705, "percentage": 58.52, "elapsed_time": "1:29:43", "remaining_time": "1:03:35", "throughput": 4639.63, "total_tokens": 24977664} {"current_steps": 24830, "total_steps": 42420, "loss": 0.0494, "lr": 2.192611141589314e-05, "epoch": 11.706742102781707, "percentage": 58.53, "elapsed_time": "1:29:44", "remaining_time": "1:03:34", "throughput": 4639.59, "total_tokens": 24981920} {"current_steps": 24835, "total_steps": 42420, "loss": 0.0865, "lr": 2.191590372016446e-05, "epoch": 11.70909948137671, "percentage": 58.55, "elapsed_time": "1:29:45", "remaining_time": "1:03:33", "throughput": 4639.67, "total_tokens": 24988160} {"current_steps": 24840, "total_steps": 42420, "loss": 0.1466, "lr": 2.190569654652091e-05, "epoch": 11.711456859971712, "percentage": 58.56, "elapsed_time": "1:29:47", "remaining_time": "1:03:32", "throughput": 4639.76, "total_tokens": 24994496} {"current_steps": 24845, "total_steps": 42420, "loss": 0.0552, "lr": 2.1895489896690393e-05, "epoch": 11.713814238566714, "percentage": 58.57, "elapsed_time": "1:29:48", "remaining_time": "1:03:31", "throughput": 4639.82, "total_tokens": 25000320} {"current_steps": 24850, "total_steps": 42420, "loss": 0.0346, "lr": 2.1885283772400727e-05, "epoch": 11.716171617161717, "percentage": 58.58, "elapsed_time": "1:29:49", "remaining_time": "1:03:30", "throughput": 4639.83, "total_tokens": 25004416} {"current_steps": 24855, "total_steps": 42420, "loss": 0.0586, "lr": 2.187507817537964e-05, "epoch": 11.718528995756719, "percentage": 58.59, "elapsed_time": "1:29:50", "remaining_time": "1:03:29", "throughput": 4639.86, "total_tokens": 25009824} {"current_steps": 24860, "total_steps": 42420, "loss": 0.0991, "lr": 2.1864873107354752e-05, "epoch": 11.720886374351721, "percentage": 58.6, "elapsed_time": "1:29:51", "remaining_time": "1:03:28", "throughput": 4639.9, "total_tokens": 25015136} {"current_steps": 24865, "total_steps": 42420, "loss": 0.2131, "lr": 2.1854668570053616e-05, "epoch": 11.723243752946724, "percentage": 58.62, "elapsed_time": "1:29:52", "remaining_time": "1:03:27", "throughput": 4639.94, "total_tokens": 25020576} {"current_steps": 24870, "total_steps": 42420, "loss": 0.0218, "lr": 2.184446456520369e-05, "epoch": 11.725601131541726, "percentage": 58.63, "elapsed_time": "1:29:53", "remaining_time": "1:03:25", "throughput": 4639.96, "total_tokens": 25024736} {"current_steps": 24875, "total_steps": 42420, "loss": 0.1021, "lr": 2.1834261094532338e-05, "epoch": 11.727958510136729, "percentage": 58.64, "elapsed_time": "1:29:54", "remaining_time": "1:03:24", "throughput": 4639.97, "total_tokens": 25029664} {"current_steps": 24880, "total_steps": 42420, "loss": 0.1045, "lr": 2.1824058159766824e-05, "epoch": 11.730315888731731, "percentage": 58.65, "elapsed_time": "1:29:55", "remaining_time": "1:03:23", "throughput": 4640.02, "total_tokens": 25034624} {"current_steps": 24885, "total_steps": 42420, "loss": 0.1535, "lr": 2.1813855762634342e-05, "epoch": 11.732673267326733, "percentage": 58.66, "elapsed_time": "1:29:56", "remaining_time": "1:03:22", "throughput": 4640.0, "total_tokens": 25038688} {"current_steps": 24890, "total_steps": 42420, "loss": 0.0477, "lr": 2.1803653904861978e-05, "epoch": 11.735030645921736, "percentage": 58.68, "elapsed_time": "1:29:57", "remaining_time": "1:03:21", "throughput": 4640.07, "total_tokens": 25044832} {"current_steps": 24895, "total_steps": 42420, "loss": 0.1747, "lr": 2.1793452588176747e-05, "epoch": 11.737388024516738, "percentage": 58.69, "elapsed_time": "1:29:58", "remaining_time": "1:03:20", "throughput": 4640.11, "total_tokens": 25049696} {"current_steps": 24900, "total_steps": 42420, "loss": 0.1231, "lr": 2.178325181430554e-05, "epoch": 11.73974540311174, "percentage": 58.7, "elapsed_time": "1:29:59", "remaining_time": "1:03:19", "throughput": 4640.14, "total_tokens": 25054848} {"current_steps": 24905, "total_steps": 42420, "loss": 0.1372, "lr": 2.1773051584975186e-05, "epoch": 11.742102781706743, "percentage": 58.71, "elapsed_time": "1:30:00", "remaining_time": "1:03:18", "throughput": 4640.16, "total_tokens": 25059104} {"current_steps": 24910, "total_steps": 42420, "loss": 0.2243, "lr": 2.1762851901912406e-05, "epoch": 11.744460160301745, "percentage": 58.72, "elapsed_time": "1:30:01", "remaining_time": "1:03:16", "throughput": 4640.2, "total_tokens": 25064096} {"current_steps": 24915, "total_steps": 42420, "loss": 0.0521, "lr": 2.175265276684384e-05, "epoch": 11.746817538896746, "percentage": 58.73, "elapsed_time": "1:30:02", "remaining_time": "1:03:15", "throughput": 4640.25, "total_tokens": 25069216} {"current_steps": 24920, "total_steps": 42420, "loss": 0.2958, "lr": 2.174245418149602e-05, "epoch": 11.749174917491748, "percentage": 58.75, "elapsed_time": "1:30:03", "remaining_time": "1:03:14", "throughput": 4640.27, "total_tokens": 25073952} {"current_steps": 24925, "total_steps": 42420, "loss": 0.0465, "lr": 2.17322561475954e-05, "epoch": 11.75153229608675, "percentage": 58.76, "elapsed_time": "1:30:04", "remaining_time": "1:03:13", "throughput": 4640.31, "total_tokens": 25079040} {"current_steps": 24930, "total_steps": 42420, "loss": 0.1111, "lr": 2.1722058666868326e-05, "epoch": 11.753889674681753, "percentage": 58.77, "elapsed_time": "1:30:05", "remaining_time": "1:03:12", "throughput": 4640.34, "total_tokens": 25084320} {"current_steps": 24935, "total_steps": 42420, "loss": 0.0404, "lr": 2.171186174104108e-05, "epoch": 11.756247053276756, "percentage": 58.78, "elapsed_time": "1:30:06", "remaining_time": "1:03:11", "throughput": 4640.4, "total_tokens": 25089760} {"current_steps": 24940, "total_steps": 42420, "loss": 0.0562, "lr": 2.1701665371839797e-05, "epoch": 11.758604431871758, "percentage": 58.79, "elapsed_time": "1:30:08", "remaining_time": "1:03:10", "throughput": 4640.47, "total_tokens": 25095840} {"current_steps": 24945, "total_steps": 42420, "loss": 0.0898, "lr": 2.169146956099057e-05, "epoch": 11.76096181046676, "percentage": 58.8, "elapsed_time": "1:30:09", "remaining_time": "1:03:09", "throughput": 4640.49, "total_tokens": 25100640} {"current_steps": 24950, "total_steps": 42420, "loss": 0.3545, "lr": 2.1681274310219367e-05, "epoch": 11.763319189061763, "percentage": 58.82, "elapsed_time": "1:30:10", "remaining_time": "1:03:08", "throughput": 4640.55, "total_tokens": 25106016} {"current_steps": 24955, "total_steps": 42420, "loss": 0.0178, "lr": 2.1671079621252072e-05, "epoch": 11.765676567656765, "percentage": 58.83, "elapsed_time": "1:30:11", "remaining_time": "1:03:07", "throughput": 4640.6, "total_tokens": 25110912} {"current_steps": 24960, "total_steps": 42420, "loss": 0.0861, "lr": 2.1660885495814476e-05, "epoch": 11.768033946251768, "percentage": 58.84, "elapsed_time": "1:30:12", "remaining_time": "1:03:05", "throughput": 4640.58, "total_tokens": 25115200} {"current_steps": 24965, "total_steps": 42420, "loss": 0.1555, "lr": 2.1650691935632276e-05, "epoch": 11.77039132484677, "percentage": 58.85, "elapsed_time": "1:30:13", "remaining_time": "1:03:04", "throughput": 4640.5, "total_tokens": 25119072} {"current_steps": 24970, "total_steps": 42420, "loss": 0.1953, "lr": 2.1640498942431058e-05, "epoch": 11.772748703441772, "percentage": 58.86, "elapsed_time": "1:30:14", "remaining_time": "1:03:03", "throughput": 4640.53, "total_tokens": 25124320} {"current_steps": 24975, "total_steps": 42420, "loss": 0.142, "lr": 2.163030651793633e-05, "epoch": 11.775106082036775, "percentage": 58.88, "elapsed_time": "1:30:15", "remaining_time": "1:03:02", "throughput": 4640.54, "total_tokens": 25129056} {"current_steps": 24980, "total_steps": 42420, "loss": 0.1761, "lr": 2.1620114663873492e-05, "epoch": 11.777463460631777, "percentage": 58.89, "elapsed_time": "1:30:16", "remaining_time": "1:03:01", "throughput": 4640.6, "total_tokens": 25133952} {"current_steps": 24985, "total_steps": 42420, "loss": 0.1508, "lr": 2.160992338196786e-05, "epoch": 11.77982083922678, "percentage": 58.9, "elapsed_time": "1:30:17", "remaining_time": "1:03:00", "throughput": 4640.66, "total_tokens": 25138976} {"current_steps": 24990, "total_steps": 42420, "loss": 0.152, "lr": 2.1599732673944634e-05, "epoch": 11.782178217821782, "percentage": 58.91, "elapsed_time": "1:30:18", "remaining_time": "1:02:58", "throughput": 4640.7, "total_tokens": 25143488} {"current_steps": 24995, "total_steps": 42420, "loss": 0.204, "lr": 2.158954254152893e-05, "epoch": 11.784535596416784, "percentage": 58.92, "elapsed_time": "1:30:19", "remaining_time": "1:02:57", "throughput": 4640.71, "total_tokens": 25148224} {"current_steps": 25000, "total_steps": 42420, "loss": 0.1061, "lr": 2.1579352986445772e-05, "epoch": 11.786892975011787, "percentage": 58.93, "elapsed_time": "1:30:20", "remaining_time": "1:02:56", "throughput": 4640.77, "total_tokens": 25154144} {"current_steps": 25005, "total_steps": 42420, "loss": 0.0281, "lr": 2.156916401042008e-05, "epoch": 11.78925035360679, "percentage": 58.95, "elapsed_time": "1:30:21", "remaining_time": "1:02:55", "throughput": 4640.8, "total_tokens": 25158656} {"current_steps": 25010, "total_steps": 42420, "loss": 0.1115, "lr": 2.1558975615176658e-05, "epoch": 11.791607732201792, "percentage": 58.96, "elapsed_time": "1:30:22", "remaining_time": "1:02:54", "throughput": 4640.83, "total_tokens": 25163488} {"current_steps": 25015, "total_steps": 42420, "loss": 0.0788, "lr": 2.1548787802440244e-05, "epoch": 11.793965110796794, "percentage": 58.97, "elapsed_time": "1:30:23", "remaining_time": "1:02:53", "throughput": 4640.85, "total_tokens": 25168256} {"current_steps": 25020, "total_steps": 42420, "loss": 0.0709, "lr": 2.153860057393545e-05, "epoch": 11.796322489391796, "percentage": 58.98, "elapsed_time": "1:30:24", "remaining_time": "1:02:52", "throughput": 4640.88, "total_tokens": 25172672} {"current_steps": 25025, "total_steps": 42420, "loss": 0.3341, "lr": 2.152841393138682e-05, "epoch": 11.798679867986799, "percentage": 58.99, "elapsed_time": "1:30:25", "remaining_time": "1:02:51", "throughput": 4640.92, "total_tokens": 25177760} {"current_steps": 25030, "total_steps": 42420, "loss": 0.1762, "lr": 2.151822787651876e-05, "epoch": 11.801037246581801, "percentage": 59.01, "elapsed_time": "1:30:26", "remaining_time": "1:02:49", "throughput": 4640.97, "total_tokens": 25182752} {"current_steps": 25035, "total_steps": 42420, "loss": 0.3467, "lr": 2.1508042411055606e-05, "epoch": 11.803394625176804, "percentage": 59.02, "elapsed_time": "1:30:27", "remaining_time": "1:02:48", "throughput": 4640.99, "total_tokens": 25187168} {"current_steps": 25040, "total_steps": 42420, "loss": 0.1385, "lr": 2.149785753672158e-05, "epoch": 11.805752003771806, "percentage": 59.03, "elapsed_time": "1:30:28", "remaining_time": "1:02:47", "throughput": 4641.01, "total_tokens": 25191552} {"current_steps": 25045, "total_steps": 42420, "loss": 0.1239, "lr": 2.1487673255240816e-05, "epoch": 11.808109382366808, "percentage": 59.04, "elapsed_time": "1:30:29", "remaining_time": "1:02:46", "throughput": 4641.04, "total_tokens": 25196256} {"current_steps": 25050, "total_steps": 42420, "loss": 0.0316, "lr": 2.1477489568337324e-05, "epoch": 11.81046676096181, "percentage": 59.05, "elapsed_time": "1:30:30", "remaining_time": "1:02:45", "throughput": 4641.09, "total_tokens": 25201632} {"current_steps": 25055, "total_steps": 42420, "loss": 0.0649, "lr": 2.1467306477735042e-05, "epoch": 11.812824139556813, "percentage": 59.06, "elapsed_time": "1:30:31", "remaining_time": "1:02:44", "throughput": 4641.12, "total_tokens": 25206656} {"current_steps": 25060, "total_steps": 42420, "loss": 0.1206, "lr": 2.145712398515779e-05, "epoch": 11.815181518151816, "percentage": 59.08, "elapsed_time": "1:30:32", "remaining_time": "1:02:43", "throughput": 4641.13, "total_tokens": 25211104} {"current_steps": 25065, "total_steps": 42420, "loss": 0.2116, "lr": 2.1446942092329303e-05, "epoch": 11.817538896746818, "percentage": 59.09, "elapsed_time": "1:30:33", "remaining_time": "1:02:41", "throughput": 4641.19, "total_tokens": 25215936} {"current_steps": 25070, "total_steps": 42420, "loss": 0.2557, "lr": 2.143676080097318e-05, "epoch": 11.81989627534182, "percentage": 59.1, "elapsed_time": "1:30:34", "remaining_time": "1:02:40", "throughput": 4641.26, "total_tokens": 25221984} {"current_steps": 25075, "total_steps": 42420, "loss": 0.0727, "lr": 2.1426580112812962e-05, "epoch": 11.822253653936823, "percentage": 59.11, "elapsed_time": "1:30:35", "remaining_time": "1:02:39", "throughput": 4641.31, "total_tokens": 25226720} {"current_steps": 25080, "total_steps": 42420, "loss": 0.0186, "lr": 2.1416400029572052e-05, "epoch": 11.824611032531825, "percentage": 59.12, "elapsed_time": "1:30:36", "remaining_time": "1:02:38", "throughput": 4641.37, "total_tokens": 25232672} {"current_steps": 25085, "total_steps": 42420, "loss": 0.2457, "lr": 2.1406220552973777e-05, "epoch": 11.826968411126828, "percentage": 59.13, "elapsed_time": "1:30:37", "remaining_time": "1:02:37", "throughput": 4641.42, "total_tokens": 25237856} {"current_steps": 25090, "total_steps": 42420, "loss": 0.1957, "lr": 2.1396041684741335e-05, "epoch": 11.82932578972183, "percentage": 59.15, "elapsed_time": "1:30:38", "remaining_time": "1:02:36", "throughput": 4641.44, "total_tokens": 25242208} {"current_steps": 25095, "total_steps": 42420, "loss": 0.1623, "lr": 2.1385863426597847e-05, "epoch": 11.831683168316832, "percentage": 59.16, "elapsed_time": "1:30:39", "remaining_time": "1:02:35", "throughput": 4641.48, "total_tokens": 25247296} {"current_steps": 25100, "total_steps": 42420, "loss": 0.0241, "lr": 2.137568578026632e-05, "epoch": 11.834040546911835, "percentage": 59.17, "elapsed_time": "1:30:40", "remaining_time": "1:02:34", "throughput": 4641.53, "total_tokens": 25252480} {"current_steps": 25105, "total_steps": 42420, "loss": 0.3384, "lr": 2.1365508747469655e-05, "epoch": 11.836397925506837, "percentage": 59.18, "elapsed_time": "1:30:41", "remaining_time": "1:02:33", "throughput": 4641.57, "total_tokens": 25257536} {"current_steps": 25110, "total_steps": 42420, "loss": 0.1106, "lr": 2.1355332329930642e-05, "epoch": 11.838755304101838, "percentage": 59.19, "elapsed_time": "1:30:42", "remaining_time": "1:02:31", "throughput": 4641.62, "total_tokens": 25262720} {"current_steps": 25115, "total_steps": 42420, "loss": 0.0746, "lr": 2.1345156529371983e-05, "epoch": 11.841112682696842, "percentage": 59.21, "elapsed_time": "1:30:43", "remaining_time": "1:02:30", "throughput": 4641.68, "total_tokens": 25268000} {"current_steps": 25120, "total_steps": 42420, "loss": 0.1218, "lr": 2.133498134751627e-05, "epoch": 11.843470061291843, "percentage": 59.22, "elapsed_time": "1:30:44", "remaining_time": "1:02:29", "throughput": 4641.71, "total_tokens": 25272800} {"current_steps": 25125, "total_steps": 42420, "loss": 0.0207, "lr": 2.1324806786085992e-05, "epoch": 11.845827439886845, "percentage": 59.23, "elapsed_time": "1:30:45", "remaining_time": "1:02:28", "throughput": 4641.74, "total_tokens": 25278240} {"current_steps": 25130, "total_steps": 42420, "loss": 0.1504, "lr": 2.1314632846803515e-05, "epoch": 11.848184818481847, "percentage": 59.24, "elapsed_time": "1:30:46", "remaining_time": "1:02:27", "throughput": 4641.78, "total_tokens": 25282880} {"current_steps": 25135, "total_steps": 42420, "loss": 0.0644, "lr": 2.1304459531391124e-05, "epoch": 11.85054219707685, "percentage": 59.25, "elapsed_time": "1:30:47", "remaining_time": "1:02:26", "throughput": 4641.81, "total_tokens": 25288128} {"current_steps": 25140, "total_steps": 42420, "loss": 0.1099, "lr": 2.129428684157099e-05, "epoch": 11.852899575671852, "percentage": 59.26, "elapsed_time": "1:30:49", "remaining_time": "1:02:25", "throughput": 4641.87, "total_tokens": 25293536} {"current_steps": 25145, "total_steps": 42420, "loss": 0.1722, "lr": 2.1284114779065177e-05, "epoch": 11.855256954266855, "percentage": 59.28, "elapsed_time": "1:30:49", "remaining_time": "1:02:24", "throughput": 4641.9, "total_tokens": 25297984} {"current_steps": 25150, "total_steps": 42420, "loss": 0.2045, "lr": 2.1273943345595637e-05, "epoch": 11.857614332861857, "percentage": 59.29, "elapsed_time": "1:30:50", "remaining_time": "1:02:23", "throughput": 4641.93, "total_tokens": 25302656} {"current_steps": 25155, "total_steps": 42420, "loss": 0.1052, "lr": 2.1263772542884224e-05, "epoch": 11.85997171145686, "percentage": 59.3, "elapsed_time": "1:30:51", "remaining_time": "1:02:21", "throughput": 4641.93, "total_tokens": 25307072} {"current_steps": 25160, "total_steps": 42420, "loss": 0.0859, "lr": 2.1253602372652692e-05, "epoch": 11.862329090051862, "percentage": 59.31, "elapsed_time": "1:30:52", "remaining_time": "1:02:20", "throughput": 4641.93, "total_tokens": 25311616} {"current_steps": 25165, "total_steps": 42420, "loss": 0.0364, "lr": 2.1243432836622656e-05, "epoch": 11.864686468646864, "percentage": 59.32, "elapsed_time": "1:30:53", "remaining_time": "1:02:19", "throughput": 4641.91, "total_tokens": 25316480} {"current_steps": 25170, "total_steps": 42420, "loss": 0.0268, "lr": 2.1233263936515657e-05, "epoch": 11.867043847241867, "percentage": 59.34, "elapsed_time": "1:30:55", "remaining_time": "1:02:18", "throughput": 4641.99, "total_tokens": 25322304} {"current_steps": 25175, "total_steps": 42420, "loss": 0.1254, "lr": 2.1223095674053125e-05, "epoch": 11.869401225836869, "percentage": 59.35, "elapsed_time": "1:30:56", "remaining_time": "1:02:17", "throughput": 4642.02, "total_tokens": 25326944} {"current_steps": 25180, "total_steps": 42420, "loss": 0.0677, "lr": 2.1212928050956362e-05, "epoch": 11.871758604431871, "percentage": 59.36, "elapsed_time": "1:30:57", "remaining_time": "1:02:16", "throughput": 4642.07, "total_tokens": 25332128} {"current_steps": 25185, "total_steps": 42420, "loss": 0.2183, "lr": 2.120276106894658e-05, "epoch": 11.874115983026874, "percentage": 59.37, "elapsed_time": "1:30:58", "remaining_time": "1:02:15", "throughput": 4642.08, "total_tokens": 25336768} {"current_steps": 25190, "total_steps": 42420, "loss": 0.1129, "lr": 2.1192594729744876e-05, "epoch": 11.876473361621876, "percentage": 59.38, "elapsed_time": "1:30:59", "remaining_time": "1:02:14", "throughput": 4642.12, "total_tokens": 25341728} {"current_steps": 25195, "total_steps": 42420, "loss": 0.2055, "lr": 2.118242903507224e-05, "epoch": 11.878830740216879, "percentage": 59.39, "elapsed_time": "1:30:59", "remaining_time": "1:02:12", "throughput": 4642.12, "total_tokens": 25345888} {"current_steps": 25200, "total_steps": 42420, "loss": 0.0549, "lr": 2.117226398664955e-05, "epoch": 11.881188118811881, "percentage": 59.41, "elapsed_time": "1:31:01", "remaining_time": "1:02:11", "throughput": 4642.17, "total_tokens": 25350976} {"current_steps": 25205, "total_steps": 42420, "loss": 0.0319, "lr": 2.116209958619757e-05, "epoch": 11.883545497406883, "percentage": 59.42, "elapsed_time": "1:31:01", "remaining_time": "1:02:10", "throughput": 4642.2, "total_tokens": 25355584} {"current_steps": 25210, "total_steps": 42420, "loss": 0.0743, "lr": 2.1151935835436967e-05, "epoch": 11.885902876001886, "percentage": 59.43, "elapsed_time": "1:31:03", "remaining_time": "1:02:09", "throughput": 4642.23, "total_tokens": 25360544} {"current_steps": 25215, "total_steps": 42420, "loss": 0.086, "lr": 2.11417727360883e-05, "epoch": 11.888260254596888, "percentage": 59.44, "elapsed_time": "1:31:04", "remaining_time": "1:02:08", "throughput": 4642.25, "total_tokens": 25365280} {"current_steps": 25220, "total_steps": 42420, "loss": 0.0778, "lr": 2.1131610289871988e-05, "epoch": 11.89061763319189, "percentage": 59.45, "elapsed_time": "1:31:04", "remaining_time": "1:02:07", "throughput": 4642.29, "total_tokens": 25369952} {"current_steps": 25225, "total_steps": 42420, "loss": 0.1867, "lr": 2.112144849850838e-05, "epoch": 11.892975011786893, "percentage": 59.46, "elapsed_time": "1:31:06", "remaining_time": "1:02:05", "throughput": 4642.35, "total_tokens": 25375136} {"current_steps": 25230, "total_steps": 42420, "loss": 0.1361, "lr": 2.111128736371768e-05, "epoch": 11.895332390381895, "percentage": 59.48, "elapsed_time": "1:31:07", "remaining_time": "1:02:04", "throughput": 4642.42, "total_tokens": 25381152} {"current_steps": 25235, "total_steps": 42420, "loss": 0.0989, "lr": 2.1101126887220014e-05, "epoch": 11.897689768976898, "percentage": 59.49, "elapsed_time": "1:31:08", "remaining_time": "1:02:03", "throughput": 4642.48, "total_tokens": 25387008} {"current_steps": 25240, "total_steps": 42420, "loss": 0.0634, "lr": 2.1090967070735357e-05, "epoch": 11.9000471475719, "percentage": 59.5, "elapsed_time": "1:31:09", "remaining_time": "1:02:02", "throughput": 4642.49, "total_tokens": 25391616} {"current_steps": 25245, "total_steps": 42420, "loss": 0.0251, "lr": 2.1080807915983607e-05, "epoch": 11.902404526166903, "percentage": 59.51, "elapsed_time": "1:31:10", "remaining_time": "1:02:01", "throughput": 4642.57, "total_tokens": 25397760} {"current_steps": 25250, "total_steps": 42420, "loss": 0.1086, "lr": 2.107064942468453e-05, "epoch": 11.904761904761905, "percentage": 59.52, "elapsed_time": "1:31:11", "remaining_time": "1:02:00", "throughput": 4642.63, "total_tokens": 25403392} {"current_steps": 25255, "total_steps": 42420, "loss": 0.0454, "lr": 2.1060491598557795e-05, "epoch": 11.907119283356908, "percentage": 59.54, "elapsed_time": "1:31:12", "remaining_time": "1:01:59", "throughput": 4642.66, "total_tokens": 25408032} {"current_steps": 25260, "total_steps": 42420, "loss": 0.0698, "lr": 2.105033443932294e-05, "epoch": 11.90947666195191, "percentage": 59.55, "elapsed_time": "1:31:13", "remaining_time": "1:01:58", "throughput": 4642.7, "total_tokens": 25412640} {"current_steps": 25265, "total_steps": 42420, "loss": 0.0789, "lr": 2.10401779486994e-05, "epoch": 11.911834040546912, "percentage": 59.56, "elapsed_time": "1:31:14", "remaining_time": "1:01:57", "throughput": 4642.78, "total_tokens": 25418336} {"current_steps": 25270, "total_steps": 42420, "loss": 0.0577, "lr": 2.1030022128406502e-05, "epoch": 11.914191419141915, "percentage": 59.57, "elapsed_time": "1:31:15", "remaining_time": "1:01:56", "throughput": 4642.81, "total_tokens": 25422688} {"current_steps": 25275, "total_steps": 42420, "loss": 0.2053, "lr": 2.1019866980163456e-05, "epoch": 11.916548797736917, "percentage": 59.58, "elapsed_time": "1:31:16", "remaining_time": "1:01:54", "throughput": 4642.82, "total_tokens": 25426784} {"current_steps": 25280, "total_steps": 42420, "loss": 0.039, "lr": 2.1009712505689345e-05, "epoch": 11.91890617633192, "percentage": 59.59, "elapsed_time": "1:31:17", "remaining_time": "1:01:53", "throughput": 4642.88, "total_tokens": 25432448} {"current_steps": 25285, "total_steps": 42420, "loss": 0.0314, "lr": 2.0999558706703156e-05, "epoch": 11.921263554926922, "percentage": 59.61, "elapsed_time": "1:31:18", "remaining_time": "1:01:52", "throughput": 4642.92, "total_tokens": 25437568} {"current_steps": 25290, "total_steps": 42420, "loss": 0.1012, "lr": 2.098940558492375e-05, "epoch": 11.923620933521924, "percentage": 59.62, "elapsed_time": "1:31:19", "remaining_time": "1:01:51", "throughput": 4642.94, "total_tokens": 25442016} {"current_steps": 25295, "total_steps": 42420, "loss": 0.2196, "lr": 2.0979253142069894e-05, "epoch": 11.925978312116927, "percentage": 59.63, "elapsed_time": "1:31:20", "remaining_time": "1:01:50", "throughput": 4642.95, "total_tokens": 25446080} {"current_steps": 25300, "total_steps": 42420, "loss": 0.1493, "lr": 2.0969101379860207e-05, "epoch": 11.92833569071193, "percentage": 59.64, "elapsed_time": "1:31:21", "remaining_time": "1:01:49", "throughput": 4642.98, "total_tokens": 25450592} {"current_steps": 25305, "total_steps": 42420, "loss": 0.0315, "lr": 2.0958950300013212e-05, "epoch": 11.930693069306932, "percentage": 59.65, "elapsed_time": "1:31:22", "remaining_time": "1:01:48", "throughput": 4642.98, "total_tokens": 25455392} {"current_steps": 25310, "total_steps": 42420, "loss": 0.2602, "lr": 2.094879990424732e-05, "epoch": 11.933050447901934, "percentage": 59.67, "elapsed_time": "1:31:23", "remaining_time": "1:01:47", "throughput": 4643.04, "total_tokens": 25461376} {"current_steps": 25315, "total_steps": 42420, "loss": 0.1017, "lr": 2.0938650194280823e-05, "epoch": 11.935407826496935, "percentage": 59.68, "elapsed_time": "1:31:24", "remaining_time": "1:01:45", "throughput": 4643.06, "total_tokens": 25465920} {"current_steps": 25320, "total_steps": 42420, "loss": 0.1531, "lr": 2.092850117183189e-05, "epoch": 11.937765205091937, "percentage": 59.69, "elapsed_time": "1:31:25", "remaining_time": "1:01:44", "throughput": 4643.13, "total_tokens": 25471168} {"current_steps": 25325, "total_steps": 42420, "loss": 0.1021, "lr": 2.091835283861857e-05, "epoch": 11.94012258368694, "percentage": 59.7, "elapsed_time": "1:31:27", "remaining_time": "1:01:44", "throughput": 4643.23, "total_tokens": 25478464} {"current_steps": 25330, "total_steps": 42420, "loss": 0.0412, "lr": 2.090820519635882e-05, "epoch": 11.942479962281942, "percentage": 59.71, "elapsed_time": "1:31:28", "remaining_time": "1:01:42", "throughput": 4643.29, "total_tokens": 25483904} {"current_steps": 25335, "total_steps": 42420, "loss": 0.097, "lr": 2.0898058246770456e-05, "epoch": 11.944837340876944, "percentage": 59.72, "elapsed_time": "1:31:29", "remaining_time": "1:01:41", "throughput": 4643.33, "total_tokens": 25488608} {"current_steps": 25340, "total_steps": 42420, "loss": 0.299, "lr": 2.088791199157118e-05, "epoch": 11.947194719471947, "percentage": 59.74, "elapsed_time": "1:31:30", "remaining_time": "1:01:40", "throughput": 4643.33, "total_tokens": 25492960} {"current_steps": 25345, "total_steps": 42420, "loss": 0.0298, "lr": 2.0877766432478586e-05, "epoch": 11.949552098066949, "percentage": 59.75, "elapsed_time": "1:31:31", "remaining_time": "1:01:39", "throughput": 4643.36, "total_tokens": 25497152} {"current_steps": 25350, "total_steps": 42420, "loss": 0.071, "lr": 2.086762157121014e-05, "epoch": 11.951909476661951, "percentage": 59.76, "elapsed_time": "1:31:32", "remaining_time": "1:01:38", "throughput": 4643.4, "total_tokens": 25501824} {"current_steps": 25355, "total_steps": 42420, "loss": 0.0277, "lr": 2.0857477409483206e-05, "epoch": 11.954266855256954, "percentage": 59.77, "elapsed_time": "1:31:33", "remaining_time": "1:01:37", "throughput": 4643.48, "total_tokens": 25508064} {"current_steps": 25360, "total_steps": 42420, "loss": 0.1124, "lr": 2.0847333949015006e-05, "epoch": 11.956624233851956, "percentage": 59.78, "elapsed_time": "1:31:34", "remaining_time": "1:01:36", "throughput": 4643.5, "total_tokens": 25512352} {"current_steps": 25365, "total_steps": 42420, "loss": 0.303, "lr": 2.0837191191522657e-05, "epoch": 11.958981612446959, "percentage": 59.79, "elapsed_time": "1:31:35", "remaining_time": "1:01:35", "throughput": 4643.57, "total_tokens": 25518560} {"current_steps": 25370, "total_steps": 42420, "loss": 0.0219, "lr": 2.082704913872316e-05, "epoch": 11.961338991041961, "percentage": 59.81, "elapsed_time": "1:31:36", "remaining_time": "1:01:33", "throughput": 4643.6, "total_tokens": 25522880} {"current_steps": 25375, "total_steps": 42420, "loss": 0.0748, "lr": 2.08169077923334e-05, "epoch": 11.963696369636963, "percentage": 59.82, "elapsed_time": "1:31:37", "remaining_time": "1:01:32", "throughput": 4643.64, "total_tokens": 25528032} {"current_steps": 25380, "total_steps": 42420, "loss": 0.0936, "lr": 2.0806767154070118e-05, "epoch": 11.966053748231966, "percentage": 59.83, "elapsed_time": "1:31:38", "remaining_time": "1:01:31", "throughput": 4643.66, "total_tokens": 25533792} {"current_steps": 25385, "total_steps": 42420, "loss": 0.1522, "lr": 2.0796627225649967e-05, "epoch": 11.968411126826968, "percentage": 59.84, "elapsed_time": "1:31:39", "remaining_time": "1:01:30", "throughput": 4643.71, "total_tokens": 25538784} {"current_steps": 25390, "total_steps": 42420, "loss": 0.1773, "lr": 2.078648800878945e-05, "epoch": 11.97076850542197, "percentage": 59.85, "elapsed_time": "1:31:40", "remaining_time": "1:01:29", "throughput": 4643.78, "total_tokens": 25545024} {"current_steps": 25395, "total_steps": 42420, "loss": 0.0319, "lr": 2.0776349505204972e-05, "epoch": 11.973125884016973, "percentage": 59.87, "elapsed_time": "1:31:41", "remaining_time": "1:01:28", "throughput": 4643.74, "total_tokens": 25548800} {"current_steps": 25400, "total_steps": 42420, "loss": 0.09, "lr": 2.0766211716612816e-05, "epoch": 11.975483262611975, "percentage": 59.88, "elapsed_time": "1:31:42", "remaining_time": "1:01:27", "throughput": 4643.74, "total_tokens": 25553056} {"current_steps": 25405, "total_steps": 42420, "loss": 0.2047, "lr": 2.0756074644729124e-05, "epoch": 11.977840641206978, "percentage": 59.89, "elapsed_time": "1:31:43", "remaining_time": "1:01:26", "throughput": 4643.78, "total_tokens": 25558112} {"current_steps": 25410, "total_steps": 42420, "loss": 0.281, "lr": 2.0745938291269932e-05, "epoch": 11.98019801980198, "percentage": 59.9, "elapsed_time": "1:31:44", "remaining_time": "1:01:24", "throughput": 4643.81, "total_tokens": 25562688} {"current_steps": 25415, "total_steps": 42420, "loss": 0.1104, "lr": 2.0735802657951166e-05, "epoch": 11.982555398396983, "percentage": 59.91, "elapsed_time": "1:31:45", "remaining_time": "1:01:23", "throughput": 4643.86, "total_tokens": 25567936} {"current_steps": 25420, "total_steps": 42420, "loss": 0.0132, "lr": 2.072566774648861e-05, "epoch": 11.984912776991985, "percentage": 59.92, "elapsed_time": "1:31:46", "remaining_time": "1:01:22", "throughput": 4643.88, "total_tokens": 25572320} {"current_steps": 25425, "total_steps": 42420, "loss": 0.0641, "lr": 2.0715533558597922e-05, "epoch": 11.987270155586987, "percentage": 59.94, "elapsed_time": "1:31:47", "remaining_time": "1:01:21", "throughput": 4643.89, "total_tokens": 25576800} {"current_steps": 25430, "total_steps": 42420, "loss": 0.0562, "lr": 2.070540009599466e-05, "epoch": 11.98962753418199, "percentage": 59.95, "elapsed_time": "1:31:48", "remaining_time": "1:01:20", "throughput": 4643.92, "total_tokens": 25581408} {"current_steps": 25435, "total_steps": 42420, "loss": 0.0961, "lr": 2.0695267360394245e-05, "epoch": 11.991984912776992, "percentage": 59.96, "elapsed_time": "1:31:49", "remaining_time": "1:01:19", "throughput": 4643.94, "total_tokens": 25585728} {"current_steps": 25440, "total_steps": 42420, "loss": 0.0538, "lr": 2.0685135353511974e-05, "epoch": 11.994342291371995, "percentage": 59.97, "elapsed_time": "1:31:50", "remaining_time": "1:01:18", "throughput": 4644.0, "total_tokens": 25591424} {"current_steps": 25445, "total_steps": 42420, "loss": 0.1025, "lr": 2.0675004077063026e-05, "epoch": 11.996699669966997, "percentage": 59.98, "elapsed_time": "1:31:51", "remaining_time": "1:01:16", "throughput": 4644.01, "total_tokens": 25596128} {"current_steps": 25450, "total_steps": 42420, "loss": 0.0925, "lr": 2.0664873532762452e-05, "epoch": 11.999057048562, "percentage": 60.0, "elapsed_time": "1:31:52", "remaining_time": "1:01:15", "throughput": 4644.01, "total_tokens": 25600288} {"current_steps": 25452, "total_steps": 42420, "eval_loss": 0.1521083414554596, "epoch": 12.0, "percentage": 60.0, "elapsed_time": "1:32:08", "remaining_time": "1:01:25", "throughput": 4631.25, "total_tokens": 25602144} {"current_steps": 25455, "total_steps": 42420, "loss": 0.1475, "lr": 2.0654743722325186e-05, "epoch": 12.001414427157002, "percentage": 60.01, "elapsed_time": "1:32:10", "remaining_time": "1:01:25", "throughput": 4630.01, "total_tokens": 25605408} {"current_steps": 25460, "total_steps": 42420, "loss": 0.1234, "lr": 2.064461464746603e-05, "epoch": 12.003771805752004, "percentage": 60.02, "elapsed_time": "1:32:11", "remaining_time": "1:01:24", "throughput": 4630.01, "total_tokens": 25609760} {"current_steps": 25465, "total_steps": 42420, "loss": 0.0854, "lr": 2.0634486309899657e-05, "epoch": 12.006129184347007, "percentage": 60.03, "elapsed_time": "1:32:12", "remaining_time": "1:01:23", "throughput": 4630.03, "total_tokens": 25615296} {"current_steps": 25470, "total_steps": 42420, "loss": 0.1065, "lr": 2.0624358711340634e-05, "epoch": 12.008486562942009, "percentage": 60.04, "elapsed_time": "1:32:13", "remaining_time": "1:01:22", "throughput": 4630.01, "total_tokens": 25619840} {"current_steps": 25475, "total_steps": 42420, "loss": 0.0909, "lr": 2.061423185350339e-05, "epoch": 12.010843941537011, "percentage": 60.05, "elapsed_time": "1:32:14", "remaining_time": "1:01:21", "throughput": 4630.01, "total_tokens": 25624416} {"current_steps": 25480, "total_steps": 42420, "loss": 0.0402, "lr": 2.0604105738102225e-05, "epoch": 12.013201320132014, "percentage": 60.07, "elapsed_time": "1:32:15", "remaining_time": "1:01:20", "throughput": 4630.03, "total_tokens": 25629312} {"current_steps": 25485, "total_steps": 42420, "loss": 0.2107, "lr": 2.0593980366851316e-05, "epoch": 12.015558698727016, "percentage": 60.08, "elapsed_time": "1:32:16", "remaining_time": "1:01:19", "throughput": 4630.09, "total_tokens": 25635520} {"current_steps": 25490, "total_steps": 42420, "loss": 0.3121, "lr": 2.0583855741464725e-05, "epoch": 12.017916077322019, "percentage": 60.09, "elapsed_time": "1:32:17", "remaining_time": "1:01:17", "throughput": 4630.11, "total_tokens": 25639840} {"current_steps": 25495, "total_steps": 42420, "loss": 0.0573, "lr": 2.0573731863656376e-05, "epoch": 12.020273455917021, "percentage": 60.1, "elapsed_time": "1:32:18", "remaining_time": "1:01:16", "throughput": 4630.09, "total_tokens": 25644224} {"current_steps": 25500, "total_steps": 42420, "loss": 0.135, "lr": 2.056360873514007e-05, "epoch": 12.022630834512023, "percentage": 60.11, "elapsed_time": "1:32:19", "remaining_time": "1:01:15", "throughput": 4630.15, "total_tokens": 25649440} {"current_steps": 25505, "total_steps": 42420, "loss": 0.0774, "lr": 2.0553486357629474e-05, "epoch": 12.024988213107026, "percentage": 60.12, "elapsed_time": "1:32:20", "remaining_time": "1:01:14", "throughput": 4630.18, "total_tokens": 25653952} {"current_steps": 25510, "total_steps": 42420, "loss": 0.0491, "lr": 2.0543364732838143e-05, "epoch": 12.027345591702028, "percentage": 60.14, "elapsed_time": "1:32:21", "remaining_time": "1:01:13", "throughput": 4630.2, "total_tokens": 25658240} {"current_steps": 25515, "total_steps": 42420, "loss": 0.1467, "lr": 2.0533243862479494e-05, "epoch": 12.029702970297029, "percentage": 60.15, "elapsed_time": "1:32:22", "remaining_time": "1:01:12", "throughput": 4630.23, "total_tokens": 25662784} {"current_steps": 25520, "total_steps": 42420, "loss": 0.1262, "lr": 2.052312374826682e-05, "epoch": 12.032060348892031, "percentage": 60.16, "elapsed_time": "1:32:23", "remaining_time": "1:01:11", "throughput": 4630.3, "total_tokens": 25668992} {"current_steps": 25525, "total_steps": 42420, "loss": 0.1313, "lr": 2.051300439191328e-05, "epoch": 12.034417727487034, "percentage": 60.17, "elapsed_time": "1:32:24", "remaining_time": "1:01:10", "throughput": 4630.29, "total_tokens": 25673344} {"current_steps": 25530, "total_steps": 42420, "loss": 0.1028, "lr": 2.050288579513191e-05, "epoch": 12.036775106082036, "percentage": 60.18, "elapsed_time": "1:32:25", "remaining_time": "1:01:08", "throughput": 4630.35, "total_tokens": 25679104} {"current_steps": 25535, "total_steps": 42420, "loss": 0.0842, "lr": 2.0492767959635618e-05, "epoch": 12.039132484677038, "percentage": 60.2, "elapsed_time": "1:32:26", "remaining_time": "1:01:07", "throughput": 4630.36, "total_tokens": 25683136} {"current_steps": 25540, "total_steps": 42420, "loss": 0.1378, "lr": 2.048265088713719e-05, "epoch": 12.04148986327204, "percentage": 60.21, "elapsed_time": "1:32:27", "remaining_time": "1:01:06", "throughput": 4630.43, "total_tokens": 25689088} {"current_steps": 25545, "total_steps": 42420, "loss": 0.1063, "lr": 2.0472534579349256e-05, "epoch": 12.043847241867043, "percentage": 60.22, "elapsed_time": "1:32:28", "remaining_time": "1:01:05", "throughput": 4630.46, "total_tokens": 25693952} {"current_steps": 25550, "total_steps": 42420, "loss": 0.0585, "lr": 2.046241903798435e-05, "epoch": 12.046204620462046, "percentage": 60.23, "elapsed_time": "1:32:30", "remaining_time": "1:01:04", "throughput": 4630.19, "total_tokens": 25697984} {"current_steps": 25555, "total_steps": 42420, "loss": 0.3135, "lr": 2.0452304264754854e-05, "epoch": 12.048561999057048, "percentage": 60.24, "elapsed_time": "1:32:31", "remaining_time": "1:01:03", "throughput": 4630.18, "total_tokens": 25702144} {"current_steps": 25560, "total_steps": 42420, "loss": 0.0964, "lr": 2.044219026137304e-05, "epoch": 12.05091937765205, "percentage": 60.25, "elapsed_time": "1:32:32", "remaining_time": "1:01:02", "throughput": 4630.25, "total_tokens": 25707968} {"current_steps": 25565, "total_steps": 42420, "loss": 0.1715, "lr": 2.043207702955102e-05, "epoch": 12.053276756247053, "percentage": 60.27, "elapsed_time": "1:32:33", "remaining_time": "1:01:01", "throughput": 4630.29, "total_tokens": 25712736} {"current_steps": 25570, "total_steps": 42420, "loss": 0.1213, "lr": 2.0421964571000797e-05, "epoch": 12.055634134842055, "percentage": 60.28, "elapsed_time": "1:32:34", "remaining_time": "1:01:00", "throughput": 4630.34, "total_tokens": 25718176} {"current_steps": 25575, "total_steps": 42420, "loss": 0.2551, "lr": 2.0411852887434246e-05, "epoch": 12.057991513437058, "percentage": 60.29, "elapsed_time": "1:32:35", "remaining_time": "1:00:58", "throughput": 4630.33, "total_tokens": 25722400} {"current_steps": 25580, "total_steps": 42420, "loss": 0.2008, "lr": 2.04017419805631e-05, "epoch": 12.06034889203206, "percentage": 60.3, "elapsed_time": "1:32:36", "remaining_time": "1:00:57", "throughput": 4630.36, "total_tokens": 25727200} {"current_steps": 25585, "total_steps": 42420, "loss": 0.1148, "lr": 2.0391631852098964e-05, "epoch": 12.062706270627062, "percentage": 60.31, "elapsed_time": "1:32:37", "remaining_time": "1:00:56", "throughput": 4630.43, "total_tokens": 25732896} {"current_steps": 25590, "total_steps": 42420, "loss": 0.1021, "lr": 2.0381522503753304e-05, "epoch": 12.065063649222065, "percentage": 60.33, "elapsed_time": "1:32:38", "remaining_time": "1:00:55", "throughput": 4630.52, "total_tokens": 25739776} {"current_steps": 25595, "total_steps": 42420, "loss": 0.1742, "lr": 2.037141393723747e-05, "epoch": 12.067421027817067, "percentage": 60.34, "elapsed_time": "1:32:39", "remaining_time": "1:00:54", "throughput": 4630.49, "total_tokens": 25743840} {"current_steps": 25600, "total_steps": 42420, "loss": 0.2091, "lr": 2.0361306154262668e-05, "epoch": 12.06977840641207, "percentage": 60.35, "elapsed_time": "1:32:40", "remaining_time": "1:00:53", "throughput": 4630.55, "total_tokens": 25749440} {"current_steps": 25605, "total_steps": 42420, "loss": 0.0861, "lr": 2.0351199156539972e-05, "epoch": 12.072135785007072, "percentage": 60.36, "elapsed_time": "1:32:41", "remaining_time": "1:00:52", "throughput": 4630.54, "total_tokens": 25754016} {"current_steps": 25610, "total_steps": 42420, "loss": 0.0985, "lr": 2.034109294578034e-05, "epoch": 12.074493163602074, "percentage": 60.37, "elapsed_time": "1:32:42", "remaining_time": "1:00:51", "throughput": 4630.53, "total_tokens": 25758368} {"current_steps": 25615, "total_steps": 42420, "loss": 0.0503, "lr": 2.0330987523694552e-05, "epoch": 12.076850542197077, "percentage": 60.38, "elapsed_time": "1:32:43", "remaining_time": "1:00:50", "throughput": 4630.57, "total_tokens": 25763264} {"current_steps": 25620, "total_steps": 42420, "loss": 0.023, "lr": 2.0320882891993305e-05, "epoch": 12.07920792079208, "percentage": 60.4, "elapsed_time": "1:32:44", "remaining_time": "1:00:49", "throughput": 4630.6, "total_tokens": 25768576} {"current_steps": 25625, "total_steps": 42420, "loss": 0.0552, "lr": 2.0310779052387136e-05, "epoch": 12.081565299387082, "percentage": 60.41, "elapsed_time": "1:32:45", "remaining_time": "1:00:47", "throughput": 4630.65, "total_tokens": 25773440} {"current_steps": 25630, "total_steps": 42420, "loss": 0.0725, "lr": 2.0300676006586462e-05, "epoch": 12.083922677982084, "percentage": 60.42, "elapsed_time": "1:32:46", "remaining_time": "1:00:46", "throughput": 4630.68, "total_tokens": 25778752} {"current_steps": 25635, "total_steps": 42420, "loss": 0.1294, "lr": 2.0290573756301544e-05, "epoch": 12.086280056577086, "percentage": 60.43, "elapsed_time": "1:32:48", "remaining_time": "1:00:45", "throughput": 4630.73, "total_tokens": 25783936} {"current_steps": 25640, "total_steps": 42420, "loss": 0.1424, "lr": 2.0280472303242525e-05, "epoch": 12.088637435172089, "percentage": 60.44, "elapsed_time": "1:32:48", "remaining_time": "1:00:44", "throughput": 4630.74, "total_tokens": 25787968} {"current_steps": 25645, "total_steps": 42420, "loss": 0.0536, "lr": 2.0270371649119412e-05, "epoch": 12.090994813767091, "percentage": 60.45, "elapsed_time": "1:32:49", "remaining_time": "1:00:43", "throughput": 4630.79, "total_tokens": 25792992} {"current_steps": 25650, "total_steps": 42420, "loss": 0.0446, "lr": 2.0260271795642083e-05, "epoch": 12.093352192362094, "percentage": 60.47, "elapsed_time": "1:32:50", "remaining_time": "1:00:42", "throughput": 4630.83, "total_tokens": 25798144} {"current_steps": 25655, "total_steps": 42420, "loss": 0.1022, "lr": 2.0250172744520258e-05, "epoch": 12.095709570957096, "percentage": 60.48, "elapsed_time": "1:32:52", "remaining_time": "1:00:41", "throughput": 4630.87, "total_tokens": 25803488} {"current_steps": 25660, "total_steps": 42420, "loss": 0.0781, "lr": 2.0240074497463536e-05, "epoch": 12.098066949552098, "percentage": 60.49, "elapsed_time": "1:32:53", "remaining_time": "1:00:40", "throughput": 4630.9, "total_tokens": 25808384} {"current_steps": 25665, "total_steps": 42420, "loss": 0.0262, "lr": 2.0229977056181383e-05, "epoch": 12.100424328147101, "percentage": 60.5, "elapsed_time": "1:32:54", "remaining_time": "1:00:39", "throughput": 4630.94, "total_tokens": 25814816} {"current_steps": 25670, "total_steps": 42420, "loss": 0.1124, "lr": 2.0219880422383135e-05, "epoch": 12.102781706742103, "percentage": 60.51, "elapsed_time": "1:32:55", "remaining_time": "1:00:38", "throughput": 4630.99, "total_tokens": 25820128} {"current_steps": 25675, "total_steps": 42420, "loss": 0.3187, "lr": 2.0209784597777958e-05, "epoch": 12.105139085337106, "percentage": 60.53, "elapsed_time": "1:32:56", "remaining_time": "1:00:36", "throughput": 4631.04, "total_tokens": 25824864} {"current_steps": 25680, "total_steps": 42420, "loss": 0.1648, "lr": 2.019968958407492e-05, "epoch": 12.107496463932108, "percentage": 60.54, "elapsed_time": "1:32:57", "remaining_time": "1:00:35", "throughput": 4631.12, "total_tokens": 25830848} {"current_steps": 25685, "total_steps": 42420, "loss": 0.1634, "lr": 2.0189595382982925e-05, "epoch": 12.10985384252711, "percentage": 60.55, "elapsed_time": "1:32:58", "remaining_time": "1:00:34", "throughput": 4631.14, "total_tokens": 25835648} {"current_steps": 25690, "total_steps": 42420, "loss": 0.0811, "lr": 2.0179501996210765e-05, "epoch": 12.112211221122113, "percentage": 60.56, "elapsed_time": "1:32:59", "remaining_time": "1:00:33", "throughput": 4631.1, "total_tokens": 25839968} {"current_steps": 25695, "total_steps": 42420, "loss": 0.0592, "lr": 2.0169409425467063e-05, "epoch": 12.114568599717115, "percentage": 60.57, "elapsed_time": "1:33:00", "remaining_time": "1:00:32", "throughput": 4631.17, "total_tokens": 25845344} {"current_steps": 25700, "total_steps": 42420, "loss": 0.0581, "lr": 2.015931767246033e-05, "epoch": 12.116925978312118, "percentage": 60.58, "elapsed_time": "1:33:01", "remaining_time": "1:00:31", "throughput": 4631.17, "total_tokens": 25849536} {"current_steps": 25705, "total_steps": 42420, "loss": 0.1491, "lr": 2.014922673889892e-05, "epoch": 12.11928335690712, "percentage": 60.6, "elapsed_time": "1:33:02", "remaining_time": "1:00:30", "throughput": 4631.2, "total_tokens": 25854688} {"current_steps": 25710, "total_steps": 42420, "loss": 0.0768, "lr": 2.013913662649107e-05, "epoch": 12.121640735502123, "percentage": 60.61, "elapsed_time": "1:33:03", "remaining_time": "1:00:29", "throughput": 4631.3, "total_tokens": 25861088} {"current_steps": 25715, "total_steps": 42420, "loss": 0.0484, "lr": 2.012904733694485e-05, "epoch": 12.123998114097123, "percentage": 60.62, "elapsed_time": "1:33:05", "remaining_time": "1:00:28", "throughput": 4631.36, "total_tokens": 25866816} {"current_steps": 25720, "total_steps": 42420, "loss": 0.1246, "lr": 2.011895887196821e-05, "epoch": 12.126355492692126, "percentage": 60.63, "elapsed_time": "1:33:06", "remaining_time": "1:00:27", "throughput": 4631.41, "total_tokens": 25872032} {"current_steps": 25725, "total_steps": 42420, "loss": 0.155, "lr": 2.0108871233268964e-05, "epoch": 12.128712871287128, "percentage": 60.64, "elapsed_time": "1:33:07", "remaining_time": "1:00:25", "throughput": 4631.44, "total_tokens": 25876896} {"current_steps": 25730, "total_steps": 42420, "loss": 0.0631, "lr": 2.0098784422554774e-05, "epoch": 12.13107024988213, "percentage": 60.66, "elapsed_time": "1:33:08", "remaining_time": "1:00:24", "throughput": 4631.49, "total_tokens": 25882880} {"current_steps": 25735, "total_steps": 42420, "loss": 0.1147, "lr": 2.0088698441533153e-05, "epoch": 12.133427628477133, "percentage": 60.67, "elapsed_time": "1:33:09", "remaining_time": "1:00:23", "throughput": 4631.55, "total_tokens": 25888544} {"current_steps": 25740, "total_steps": 42420, "loss": 0.0084, "lr": 2.00786132919115e-05, "epoch": 12.135785007072135, "percentage": 60.68, "elapsed_time": "1:33:10", "remaining_time": "1:00:22", "throughput": 4631.56, "total_tokens": 25893376} {"current_steps": 25745, "total_steps": 42420, "loss": 0.0735, "lr": 2.006852897539706e-05, "epoch": 12.138142385667138, "percentage": 60.69, "elapsed_time": "1:33:11", "remaining_time": "1:00:21", "throughput": 4631.58, "total_tokens": 25898016} {"current_steps": 25750, "total_steps": 42420, "loss": 0.1667, "lr": 2.0058445493696935e-05, "epoch": 12.14049976426214, "percentage": 60.7, "elapsed_time": "1:33:12", "remaining_time": "1:00:20", "throughput": 4631.62, "total_tokens": 25902784} {"current_steps": 25755, "total_steps": 42420, "loss": 0.0946, "lr": 2.0048362848518076e-05, "epoch": 12.142857142857142, "percentage": 60.71, "elapsed_time": "1:33:13", "remaining_time": "1:00:19", "throughput": 4631.66, "total_tokens": 25907840} {"current_steps": 25760, "total_steps": 42420, "loss": 0.2502, "lr": 2.003828104156732e-05, "epoch": 12.145214521452145, "percentage": 60.73, "elapsed_time": "1:33:14", "remaining_time": "1:00:18", "throughput": 4631.69, "total_tokens": 25912544} {"current_steps": 25765, "total_steps": 42420, "loss": 0.0952, "lr": 2.0028200074551333e-05, "epoch": 12.147571900047147, "percentage": 60.74, "elapsed_time": "1:33:15", "remaining_time": "1:00:17", "throughput": 4631.74, "total_tokens": 25917760} {"current_steps": 25770, "total_steps": 42420, "loss": 0.2085, "lr": 2.0018119949176663e-05, "epoch": 12.14992927864215, "percentage": 60.75, "elapsed_time": "1:33:16", "remaining_time": "1:00:16", "throughput": 4631.78, "total_tokens": 25923008} {"current_steps": 25775, "total_steps": 42420, "loss": 0.1777, "lr": 2.0008040667149694e-05, "epoch": 12.152286657237152, "percentage": 60.76, "elapsed_time": "1:33:17", "remaining_time": "1:00:14", "throughput": 4631.83, "total_tokens": 25927936} {"current_steps": 25780, "total_steps": 42420, "loss": 0.101, "lr": 1.999796223017668e-05, "epoch": 12.154644035832154, "percentage": 60.77, "elapsed_time": "1:33:18", "remaining_time": "1:00:13", "throughput": 4631.88, "total_tokens": 25933056} {"current_steps": 25785, "total_steps": 42420, "loss": 0.0661, "lr": 1.9987884639963734e-05, "epoch": 12.157001414427157, "percentage": 60.79, "elapsed_time": "1:33:19", "remaining_time": "1:00:12", "throughput": 4631.93, "total_tokens": 25938368} {"current_steps": 25790, "total_steps": 42420, "loss": 0.1263, "lr": 1.997780789821682e-05, "epoch": 12.15935879302216, "percentage": 60.8, "elapsed_time": "1:33:20", "remaining_time": "1:00:11", "throughput": 4631.96, "total_tokens": 25942976} {"current_steps": 25795, "total_steps": 42420, "loss": 0.0912, "lr": 1.9967732006641754e-05, "epoch": 12.161716171617162, "percentage": 60.81, "elapsed_time": "1:33:21", "remaining_time": "1:00:10", "throughput": 4632.0, "total_tokens": 25947520} {"current_steps": 25800, "total_steps": 42420, "loss": 0.1491, "lr": 1.9957656966944213e-05, "epoch": 12.164073550212164, "percentage": 60.82, "elapsed_time": "1:33:22", "remaining_time": "1:00:09", "throughput": 4632.04, "total_tokens": 25953024} {"current_steps": 25805, "total_steps": 42420, "loss": 0.0247, "lr": 1.9947582780829736e-05, "epoch": 12.166430928807166, "percentage": 60.83, "elapsed_time": "1:33:23", "remaining_time": "1:00:08", "throughput": 4632.07, "total_tokens": 25957792} {"current_steps": 25810, "total_steps": 42420, "loss": 0.0732, "lr": 1.9937509450003714e-05, "epoch": 12.168788307402169, "percentage": 60.84, "elapsed_time": "1:33:25", "remaining_time": "1:00:07", "throughput": 4632.12, "total_tokens": 25963584} {"current_steps": 25815, "total_steps": 42420, "loss": 0.0128, "lr": 1.992743697617138e-05, "epoch": 12.171145685997171, "percentage": 60.86, "elapsed_time": "1:33:26", "remaining_time": "1:00:06", "throughput": 4632.13, "total_tokens": 25968224} {"current_steps": 25820, "total_steps": 42420, "loss": 0.1839, "lr": 1.9917365361037837e-05, "epoch": 12.173503064592174, "percentage": 60.87, "elapsed_time": "1:33:27", "remaining_time": "1:00:04", "throughput": 4632.19, "total_tokens": 25973344} {"current_steps": 25825, "total_steps": 42420, "loss": 0.102, "lr": 1.9907294606308042e-05, "epoch": 12.175860443187176, "percentage": 60.88, "elapsed_time": "1:33:28", "remaining_time": "1:00:03", "throughput": 4632.24, "total_tokens": 25978560} {"current_steps": 25830, "total_steps": 42420, "loss": 0.0609, "lr": 1.9897224713686806e-05, "epoch": 12.178217821782178, "percentage": 60.89, "elapsed_time": "1:33:29", "remaining_time": "1:00:02", "throughput": 4632.25, "total_tokens": 25983040} {"current_steps": 25835, "total_steps": 42420, "loss": 0.0449, "lr": 1.9887155684878785e-05, "epoch": 12.18057520037718, "percentage": 60.9, "elapsed_time": "1:33:30", "remaining_time": "1:00:01", "throughput": 4632.33, "total_tokens": 25989440} {"current_steps": 25840, "total_steps": 42420, "loss": 0.0724, "lr": 1.98770875215885e-05, "epoch": 12.182932578972183, "percentage": 60.91, "elapsed_time": "1:33:31", "remaining_time": "1:00:00", "throughput": 4632.39, "total_tokens": 25995936} {"current_steps": 25845, "total_steps": 42420, "loss": 0.1164, "lr": 1.9867020225520306e-05, "epoch": 12.185289957567186, "percentage": 60.93, "elapsed_time": "1:33:32", "remaining_time": "0:59:59", "throughput": 4632.4, "total_tokens": 26000352} {"current_steps": 25850, "total_steps": 42420, "loss": 0.0662, "lr": 1.9856953798378434e-05, "epoch": 12.187647336162188, "percentage": 60.94, "elapsed_time": "1:33:34", "remaining_time": "0:59:58", "throughput": 4632.49, "total_tokens": 26007200} {"current_steps": 25855, "total_steps": 42420, "loss": 0.214, "lr": 1.9846888241866963e-05, "epoch": 12.19000471475719, "percentage": 60.95, "elapsed_time": "1:33:35", "remaining_time": "0:59:57", "throughput": 4632.51, "total_tokens": 26011584} {"current_steps": 25860, "total_steps": 42420, "loss": 0.0948, "lr": 1.9836823557689822e-05, "epoch": 12.192362093352193, "percentage": 60.96, "elapsed_time": "1:33:35", "remaining_time": "0:59:56", "throughput": 4632.55, "total_tokens": 26016384} {"current_steps": 25865, "total_steps": 42420, "loss": 0.0449, "lr": 1.9826759747550777e-05, "epoch": 12.194719471947195, "percentage": 60.97, "elapsed_time": "1:33:37", "remaining_time": "0:59:55", "throughput": 4632.56, "total_tokens": 26022112} {"current_steps": 25870, "total_steps": 42420, "loss": 0.1266, "lr": 1.9816696813153478e-05, "epoch": 12.197076850542198, "percentage": 60.99, "elapsed_time": "1:33:38", "remaining_time": "0:59:54", "throughput": 4632.6, "total_tokens": 26028704} {"current_steps": 25875, "total_steps": 42420, "loss": 0.113, "lr": 1.9806634756201394e-05, "epoch": 12.1994342291372, "percentage": 61.0, "elapsed_time": "1:33:39", "remaining_time": "0:59:53", "throughput": 4632.57, "total_tokens": 26032736} {"current_steps": 25880, "total_steps": 42420, "loss": 0.2518, "lr": 1.9796573578397877e-05, "epoch": 12.201791607732202, "percentage": 61.01, "elapsed_time": "1:33:40", "remaining_time": "0:59:52", "throughput": 4632.55, "total_tokens": 26037664} {"current_steps": 25885, "total_steps": 42420, "loss": 0.0828, "lr": 1.9786513281446097e-05, "epoch": 12.204148986327205, "percentage": 61.02, "elapsed_time": "1:33:42", "remaining_time": "0:59:51", "throughput": 4632.62, "total_tokens": 26045152} {"current_steps": 25890, "total_steps": 42420, "loss": 0.1524, "lr": 1.97764538670491e-05, "epoch": 12.206506364922207, "percentage": 61.03, "elapsed_time": "1:33:43", "remaining_time": "0:59:50", "throughput": 4632.7, "total_tokens": 26051488} {"current_steps": 25895, "total_steps": 42420, "loss": 0.0494, "lr": 1.976639533690977e-05, "epoch": 12.20886374351721, "percentage": 61.04, "elapsed_time": "1:33:44", "remaining_time": "0:59:49", "throughput": 4632.74, "total_tokens": 26057184} {"current_steps": 25900, "total_steps": 42420, "loss": 0.0255, "lr": 1.9756337692730856e-05, "epoch": 12.211221122112212, "percentage": 61.06, "elapsed_time": "1:33:45", "remaining_time": "0:59:48", "throughput": 4632.69, "total_tokens": 26061440} {"current_steps": 25905, "total_steps": 42420, "loss": 0.0454, "lr": 1.974628093621493e-05, "epoch": 12.213578500707214, "percentage": 61.07, "elapsed_time": "1:33:46", "remaining_time": "0:59:47", "throughput": 4632.74, "total_tokens": 26066304} {"current_steps": 25910, "total_steps": 42420, "loss": 0.0846, "lr": 1.973622506906444e-05, "epoch": 12.215935879302217, "percentage": 61.08, "elapsed_time": "1:33:47", "remaining_time": "0:59:45", "throughput": 4632.76, "total_tokens": 26071648} {"current_steps": 25915, "total_steps": 42420, "loss": 0.2236, "lr": 1.9726170092981675e-05, "epoch": 12.218293257897217, "percentage": 61.09, "elapsed_time": "1:33:48", "remaining_time": "0:59:44", "throughput": 4632.79, "total_tokens": 26076160} {"current_steps": 25920, "total_steps": 42420, "loss": 0.2046, "lr": 1.971611600966877e-05, "epoch": 12.22065063649222, "percentage": 61.1, "elapsed_time": "1:33:49", "remaining_time": "0:59:43", "throughput": 4632.81, "total_tokens": 26080736} {"current_steps": 25925, "total_steps": 42420, "loss": 0.1554, "lr": 1.9706062820827707e-05, "epoch": 12.223008015087222, "percentage": 61.12, "elapsed_time": "1:33:50", "remaining_time": "0:59:42", "throughput": 4632.83, "total_tokens": 26086528} {"current_steps": 25930, "total_steps": 42420, "loss": 0.1471, "lr": 1.969601052816032e-05, "epoch": 12.225365393682225, "percentage": 61.13, "elapsed_time": "1:33:51", "remaining_time": "0:59:41", "throughput": 4632.86, "total_tokens": 26091072} {"current_steps": 25935, "total_steps": 42420, "loss": 0.0138, "lr": 1.9685959133368294e-05, "epoch": 12.227722772277227, "percentage": 61.14, "elapsed_time": "1:33:52", "remaining_time": "0:59:40", "throughput": 4632.78, "total_tokens": 26094816} {"current_steps": 25940, "total_steps": 42420, "loss": 0.1036, "lr": 1.9675908638153167e-05, "epoch": 12.23008015087223, "percentage": 61.15, "elapsed_time": "1:33:53", "remaining_time": "0:59:39", "throughput": 4632.79, "total_tokens": 26098912} {"current_steps": 25945, "total_steps": 42420, "loss": 0.1777, "lr": 1.96658590442163e-05, "epoch": 12.232437529467232, "percentage": 61.16, "elapsed_time": "1:33:54", "remaining_time": "0:59:37", "throughput": 4632.83, "total_tokens": 26104096} {"current_steps": 25950, "total_steps": 42420, "loss": 0.0487, "lr": 1.9655810353258933e-05, "epoch": 12.234794908062234, "percentage": 61.17, "elapsed_time": "1:33:55", "remaining_time": "0:59:36", "throughput": 4632.89, "total_tokens": 26109344} {"current_steps": 25955, "total_steps": 42420, "loss": 0.0448, "lr": 1.964576256698213e-05, "epoch": 12.237152286657237, "percentage": 61.19, "elapsed_time": "1:33:56", "remaining_time": "0:59:35", "throughput": 4632.95, "total_tokens": 26115136} {"current_steps": 25960, "total_steps": 42420, "loss": 0.1183, "lr": 1.9635715687086825e-05, "epoch": 12.239509665252239, "percentage": 61.2, "elapsed_time": "1:33:57", "remaining_time": "0:59:34", "throughput": 4633.01, "total_tokens": 26120608} {"current_steps": 25965, "total_steps": 42420, "loss": 0.0507, "lr": 1.9625669715273763e-05, "epoch": 12.241867043847241, "percentage": 61.21, "elapsed_time": "1:33:58", "remaining_time": "0:59:33", "throughput": 4633.01, "total_tokens": 26124800} {"current_steps": 25970, "total_steps": 42420, "loss": 0.2242, "lr": 1.9615624653243574e-05, "epoch": 12.244224422442244, "percentage": 61.22, "elapsed_time": "1:33:59", "remaining_time": "0:59:32", "throughput": 4633.06, "total_tokens": 26129888} {"current_steps": 25975, "total_steps": 42420, "loss": 0.0329, "lr": 1.9605580502696703e-05, "epoch": 12.246581801037246, "percentage": 61.23, "elapsed_time": "1:34:00", "remaining_time": "0:59:31", "throughput": 4633.1, "total_tokens": 26134688} {"current_steps": 25980, "total_steps": 42420, "loss": 0.0276, "lr": 1.9595537265333467e-05, "epoch": 12.248939179632249, "percentage": 61.24, "elapsed_time": "1:34:01", "remaining_time": "0:59:30", "throughput": 4633.09, "total_tokens": 26138848} {"current_steps": 25985, "total_steps": 42420, "loss": 0.1236, "lr": 1.9585494942854008e-05, "epoch": 12.251296558227251, "percentage": 61.26, "elapsed_time": "1:34:03", "remaining_time": "0:59:29", "throughput": 4633.19, "total_tokens": 26146432} {"current_steps": 25990, "total_steps": 42420, "loss": 0.0647, "lr": 1.9575453536958323e-05, "epoch": 12.253653936822253, "percentage": 61.27, "elapsed_time": "1:34:04", "remaining_time": "0:59:28", "throughput": 4633.22, "total_tokens": 26151200} {"current_steps": 25995, "total_steps": 42420, "loss": 0.0955, "lr": 1.9565413049346242e-05, "epoch": 12.256011315417256, "percentage": 61.28, "elapsed_time": "1:34:05", "remaining_time": "0:59:27", "throughput": 4633.27, "total_tokens": 26156384} {"current_steps": 26000, "total_steps": 42420, "loss": 0.0888, "lr": 1.955537348171747e-05, "epoch": 12.258368694012258, "percentage": 61.29, "elapsed_time": "1:34:06", "remaining_time": "0:59:25", "throughput": 4633.25, "total_tokens": 26160192} {"current_steps": 26005, "total_steps": 42420, "loss": 0.1209, "lr": 1.9545334835771516e-05, "epoch": 12.26072607260726, "percentage": 61.3, "elapsed_time": "1:34:07", "remaining_time": "0:59:24", "throughput": 4633.28, "total_tokens": 26164864} {"current_steps": 26010, "total_steps": 42420, "loss": 0.1046, "lr": 1.9535297113207764e-05, "epoch": 12.263083451202263, "percentage": 61.32, "elapsed_time": "1:34:08", "remaining_time": "0:59:23", "throughput": 4633.33, "total_tokens": 26170432} {"current_steps": 26015, "total_steps": 42420, "loss": 0.0125, "lr": 1.952526031572542e-05, "epoch": 12.265440829797265, "percentage": 61.33, "elapsed_time": "1:34:09", "remaining_time": "0:59:22", "throughput": 4633.36, "total_tokens": 26175168} {"current_steps": 26020, "total_steps": 42420, "loss": 0.0951, "lr": 1.9515224445023553e-05, "epoch": 12.267798208392268, "percentage": 61.34, "elapsed_time": "1:34:10", "remaining_time": "0:59:21", "throughput": 4633.35, "total_tokens": 26179168} {"current_steps": 26025, "total_steps": 42420, "loss": 0.1471, "lr": 1.950518950280106e-05, "epoch": 12.27015558698727, "percentage": 61.35, "elapsed_time": "1:34:11", "remaining_time": "0:59:20", "throughput": 4633.41, "total_tokens": 26184800} {"current_steps": 26030, "total_steps": 42420, "loss": 0.0538, "lr": 1.9495155490756683e-05, "epoch": 12.272512965582273, "percentage": 61.36, "elapsed_time": "1:34:12", "remaining_time": "0:59:19", "throughput": 4633.48, "total_tokens": 26190720} {"current_steps": 26035, "total_steps": 42420, "loss": 0.1673, "lr": 1.9485122410589017e-05, "epoch": 12.274870344177275, "percentage": 61.37, "elapsed_time": "1:34:13", "remaining_time": "0:59:18", "throughput": 4633.53, "total_tokens": 26195872} {"current_steps": 26040, "total_steps": 42420, "loss": 0.2574, "lr": 1.9475090263996495e-05, "epoch": 12.277227722772277, "percentage": 61.39, "elapsed_time": "1:34:14", "remaining_time": "0:59:16", "throughput": 4633.57, "total_tokens": 26200800} {"current_steps": 26045, "total_steps": 42420, "loss": 0.0496, "lr": 1.946505905267738e-05, "epoch": 12.27958510136728, "percentage": 61.4, "elapsed_time": "1:34:15", "remaining_time": "0:59:15", "throughput": 4633.61, "total_tokens": 26206400} {"current_steps": 26050, "total_steps": 42420, "loss": 0.0787, "lr": 1.9455028778329786e-05, "epoch": 12.281942479962282, "percentage": 61.41, "elapsed_time": "1:34:16", "remaining_time": "0:59:14", "throughput": 4633.61, "total_tokens": 26210464} {"current_steps": 26055, "total_steps": 42420, "loss": 0.0326, "lr": 1.9444999442651675e-05, "epoch": 12.284299858557285, "percentage": 61.42, "elapsed_time": "1:34:17", "remaining_time": "0:59:13", "throughput": 4633.63, "total_tokens": 26215584} {"current_steps": 26060, "total_steps": 42420, "loss": 0.0725, "lr": 1.943497104734085e-05, "epoch": 12.286657237152287, "percentage": 61.43, "elapsed_time": "1:34:19", "remaining_time": "0:59:12", "throughput": 4633.68, "total_tokens": 26223136} {"current_steps": 26065, "total_steps": 42420, "loss": 0.0497, "lr": 1.9424943594094925e-05, "epoch": 12.28901461574729, "percentage": 61.45, "elapsed_time": "1:34:20", "remaining_time": "0:59:11", "throughput": 4633.7, "total_tokens": 26227936} {"current_steps": 26070, "total_steps": 42420, "loss": 0.0818, "lr": 1.9414917084611398e-05, "epoch": 12.291371994342292, "percentage": 61.46, "elapsed_time": "1:34:21", "remaining_time": "0:59:10", "throughput": 4633.74, "total_tokens": 26233056} {"current_steps": 26075, "total_steps": 42420, "loss": 0.0738, "lr": 1.9404891520587574e-05, "epoch": 12.293729372937294, "percentage": 61.47, "elapsed_time": "1:34:22", "remaining_time": "0:59:09", "throughput": 4633.75, "total_tokens": 26237632} {"current_steps": 26080, "total_steps": 42420, "loss": 0.2118, "lr": 1.9394866903720614e-05, "epoch": 12.296086751532297, "percentage": 61.48, "elapsed_time": "1:34:23", "remaining_time": "0:59:08", "throughput": 4633.79, "total_tokens": 26242976} {"current_steps": 26085, "total_steps": 42420, "loss": 0.0293, "lr": 1.9384843235707516e-05, "epoch": 12.298444130127299, "percentage": 61.49, "elapsed_time": "1:34:24", "remaining_time": "0:59:07", "throughput": 4633.85, "total_tokens": 26248864} {"current_steps": 26090, "total_steps": 42420, "loss": 0.1933, "lr": 1.937482051824513e-05, "epoch": 12.300801508722301, "percentage": 61.5, "elapsed_time": "1:34:25", "remaining_time": "0:59:06", "throughput": 4633.9, "total_tokens": 26254464} {"current_steps": 26095, "total_steps": 42420, "loss": 0.1624, "lr": 1.9364798753030107e-05, "epoch": 12.303158887317304, "percentage": 61.52, "elapsed_time": "1:34:26", "remaining_time": "0:59:05", "throughput": 4633.91, "total_tokens": 26259072} {"current_steps": 26100, "total_steps": 42420, "loss": 0.0619, "lr": 1.935477794175898e-05, "epoch": 12.305516265912306, "percentage": 61.53, "elapsed_time": "1:34:27", "remaining_time": "0:59:03", "throughput": 4633.94, "total_tokens": 26264224} {"current_steps": 26105, "total_steps": 42420, "loss": 0.1082, "lr": 1.9344758086128096e-05, "epoch": 12.307873644507309, "percentage": 61.54, "elapsed_time": "1:34:28", "remaining_time": "0:59:02", "throughput": 4633.98, "total_tokens": 26268896} {"current_steps": 26110, "total_steps": 42420, "loss": 0.3559, "lr": 1.9334739187833652e-05, "epoch": 12.310231023102311, "percentage": 61.55, "elapsed_time": "1:34:29", "remaining_time": "0:59:01", "throughput": 4634.04, "total_tokens": 26274848} {"current_steps": 26115, "total_steps": 42420, "loss": 0.2551, "lr": 1.9324721248571667e-05, "epoch": 12.312588401697312, "percentage": 61.56, "elapsed_time": "1:34:30", "remaining_time": "0:59:00", "throughput": 4634.05, "total_tokens": 26279680} {"current_steps": 26120, "total_steps": 42420, "loss": 0.109, "lr": 1.9314704270038014e-05, "epoch": 12.314945780292314, "percentage": 61.57, "elapsed_time": "1:34:32", "remaining_time": "0:58:59", "throughput": 4634.11, "total_tokens": 26284832} {"current_steps": 26125, "total_steps": 42420, "loss": 0.1924, "lr": 1.9304688253928398e-05, "epoch": 12.317303158887317, "percentage": 61.59, "elapsed_time": "1:34:33", "remaining_time": "0:58:58", "throughput": 4634.16, "total_tokens": 26290464} {"current_steps": 26130, "total_steps": 42420, "loss": 0.023, "lr": 1.9294673201938367e-05, "epoch": 12.319660537482319, "percentage": 61.6, "elapsed_time": "1:34:34", "remaining_time": "0:58:57", "throughput": 4634.2, "total_tokens": 26295360} {"current_steps": 26135, "total_steps": 42420, "loss": 0.0114, "lr": 1.9284659115763284e-05, "epoch": 12.322017916077321, "percentage": 61.61, "elapsed_time": "1:34:35", "remaining_time": "0:58:56", "throughput": 4634.24, "total_tokens": 26300096} {"current_steps": 26140, "total_steps": 42420, "loss": 0.0583, "lr": 1.9274645997098373e-05, "epoch": 12.324375294672324, "percentage": 61.62, "elapsed_time": "1:34:36", "remaining_time": "0:58:55", "throughput": 4634.27, "total_tokens": 26305504} {"current_steps": 26145, "total_steps": 42420, "loss": 0.1144, "lr": 1.9264633847638686e-05, "epoch": 12.326732673267326, "percentage": 61.63, "elapsed_time": "1:34:37", "remaining_time": "0:58:54", "throughput": 4634.35, "total_tokens": 26311776} {"current_steps": 26150, "total_steps": 42420, "loss": 0.2091, "lr": 1.9254622669079108e-05, "epoch": 12.329090051862329, "percentage": 61.65, "elapsed_time": "1:34:38", "remaining_time": "0:58:53", "throughput": 4634.4, "total_tokens": 26317216} {"current_steps": 26155, "total_steps": 42420, "loss": 0.129, "lr": 1.9244612463114357e-05, "epoch": 12.331447430457331, "percentage": 61.66, "elapsed_time": "1:34:39", "remaining_time": "0:58:51", "throughput": 4634.44, "total_tokens": 26321920} {"current_steps": 26160, "total_steps": 42420, "loss": 0.0705, "lr": 1.9234603231438995e-05, "epoch": 12.333804809052333, "percentage": 61.67, "elapsed_time": "1:34:40", "remaining_time": "0:58:50", "throughput": 4634.47, "total_tokens": 26326176} {"current_steps": 26165, "total_steps": 42420, "loss": 0.0382, "lr": 1.922459497574742e-05, "epoch": 12.336162187647336, "percentage": 61.68, "elapsed_time": "1:34:41", "remaining_time": "0:58:49", "throughput": 4634.51, "total_tokens": 26331200} {"current_steps": 26170, "total_steps": 42420, "loss": 0.0154, "lr": 1.9214587697733854e-05, "epoch": 12.338519566242338, "percentage": 61.69, "elapsed_time": "1:34:42", "remaining_time": "0:58:48", "throughput": 4634.52, "total_tokens": 26335456} {"current_steps": 26175, "total_steps": 42420, "loss": 0.14, "lr": 1.9204581399092357e-05, "epoch": 12.34087694483734, "percentage": 61.7, "elapsed_time": "1:34:43", "remaining_time": "0:58:47", "throughput": 4634.51, "total_tokens": 26340096} {"current_steps": 26180, "total_steps": 42420, "loss": 0.1437, "lr": 1.919457608151683e-05, "epoch": 12.343234323432343, "percentage": 61.72, "elapsed_time": "1:34:44", "remaining_time": "0:58:46", "throughput": 4634.56, "total_tokens": 26345760} {"current_steps": 26185, "total_steps": 42420, "loss": 0.0954, "lr": 1.9184571746701e-05, "epoch": 12.345591702027345, "percentage": 61.73, "elapsed_time": "1:34:45", "remaining_time": "0:58:45", "throughput": 4634.6, "total_tokens": 26350752} {"current_steps": 26190, "total_steps": 42420, "loss": 0.0317, "lr": 1.917456839633844e-05, "epoch": 12.347949080622348, "percentage": 61.74, "elapsed_time": "1:34:46", "remaining_time": "0:58:44", "throughput": 4634.64, "total_tokens": 26356480} {"current_steps": 26195, "total_steps": 42420, "loss": 0.0273, "lr": 1.916456603212253e-05, "epoch": 12.35030645921735, "percentage": 61.75, "elapsed_time": "1:34:47", "remaining_time": "0:58:43", "throughput": 4634.68, "total_tokens": 26361792} {"current_steps": 26200, "total_steps": 42420, "loss": 0.1365, "lr": 1.9154564655746517e-05, "epoch": 12.352663837812353, "percentage": 61.76, "elapsed_time": "1:34:48", "remaining_time": "0:58:41", "throughput": 4634.73, "total_tokens": 26366720} {"current_steps": 26205, "total_steps": 42420, "loss": 0.2079, "lr": 1.9144564268903455e-05, "epoch": 12.355021216407355, "percentage": 61.78, "elapsed_time": "1:34:50", "remaining_time": "0:58:40", "throughput": 4634.79, "total_tokens": 26372160} {"current_steps": 26210, "total_steps": 42420, "loss": 0.1809, "lr": 1.913456487328625e-05, "epoch": 12.357378595002357, "percentage": 61.79, "elapsed_time": "1:34:51", "remaining_time": "0:58:39", "throughput": 4634.82, "total_tokens": 26376992} {"current_steps": 26215, "total_steps": 42420, "loss": 0.1786, "lr": 1.9124566470587616e-05, "epoch": 12.35973597359736, "percentage": 61.8, "elapsed_time": "1:34:51", "remaining_time": "0:58:38", "throughput": 4634.82, "total_tokens": 26381184} {"current_steps": 26220, "total_steps": 42420, "loss": 0.1136, "lr": 1.911456906250012e-05, "epoch": 12.362093352192362, "percentage": 61.81, "elapsed_time": "1:34:52", "remaining_time": "0:58:37", "throughput": 4634.88, "total_tokens": 26386272} {"current_steps": 26225, "total_steps": 42420, "loss": 0.2963, "lr": 1.9104572650716148e-05, "epoch": 12.364450730787365, "percentage": 61.82, "elapsed_time": "1:34:53", "remaining_time": "0:58:36", "throughput": 4634.91, "total_tokens": 26391104} {"current_steps": 26230, "total_steps": 42420, "loss": 0.0096, "lr": 1.9094577236927938e-05, "epoch": 12.366808109382367, "percentage": 61.83, "elapsed_time": "1:34:54", "remaining_time": "0:58:35", "throughput": 4634.93, "total_tokens": 26395648} {"current_steps": 26235, "total_steps": 42420, "loss": 0.2489, "lr": 1.9084582822827525e-05, "epoch": 12.36916548797737, "percentage": 61.85, "elapsed_time": "1:34:55", "remaining_time": "0:58:33", "throughput": 4634.93, "total_tokens": 26399936} {"current_steps": 26240, "total_steps": 42420, "loss": 0.0204, "lr": 1.9074589410106806e-05, "epoch": 12.371522866572372, "percentage": 61.86, "elapsed_time": "1:34:57", "remaining_time": "0:58:32", "throughput": 4635.02, "total_tokens": 26406368} {"current_steps": 26245, "total_steps": 42420, "loss": 0.2097, "lr": 1.906459700045749e-05, "epoch": 12.373880245167374, "percentage": 61.87, "elapsed_time": "1:34:58", "remaining_time": "0:58:31", "throughput": 4635.04, "total_tokens": 26411136} {"current_steps": 26250, "total_steps": 42420, "loss": 0.0954, "lr": 1.9054605595571128e-05, "epoch": 12.376237623762377, "percentage": 61.88, "elapsed_time": "1:34:59", "remaining_time": "0:58:30", "throughput": 4635.08, "total_tokens": 26415968} {"current_steps": 26255, "total_steps": 42420, "loss": 0.0923, "lr": 1.9044615197139087e-05, "epoch": 12.378595002357379, "percentage": 61.89, "elapsed_time": "1:35:00", "remaining_time": "0:58:29", "throughput": 4635.14, "total_tokens": 26421632} {"current_steps": 26260, "total_steps": 42420, "loss": 0.0509, "lr": 1.9034625806852578e-05, "epoch": 12.380952380952381, "percentage": 61.9, "elapsed_time": "1:35:01", "remaining_time": "0:58:28", "throughput": 4635.17, "total_tokens": 26427264} {"current_steps": 26265, "total_steps": 42420, "loss": 0.0671, "lr": 1.9024637426402632e-05, "epoch": 12.383309759547384, "percentage": 61.92, "elapsed_time": "1:35:02", "remaining_time": "0:58:27", "throughput": 4635.23, "total_tokens": 26432576} {"current_steps": 26270, "total_steps": 42420, "loss": 0.1863, "lr": 1.9014650057480123e-05, "epoch": 12.385667138142386, "percentage": 61.93, "elapsed_time": "1:35:03", "remaining_time": "0:58:26", "throughput": 4635.28, "total_tokens": 26437728} {"current_steps": 26275, "total_steps": 42420, "loss": 0.0176, "lr": 1.9004663701775724e-05, "epoch": 12.388024516737389, "percentage": 61.94, "elapsed_time": "1:35:04", "remaining_time": "0:58:25", "throughput": 4635.28, "total_tokens": 26441696} {"current_steps": 26280, "total_steps": 42420, "loss": 0.0817, "lr": 1.8994678360979966e-05, "epoch": 12.390381895332391, "percentage": 61.95, "elapsed_time": "1:35:05", "remaining_time": "0:58:23", "throughput": 4635.25, "total_tokens": 26445632} {"current_steps": 26285, "total_steps": 42420, "loss": 0.0623, "lr": 1.898469403678321e-05, "epoch": 12.392739273927393, "percentage": 61.96, "elapsed_time": "1:35:06", "remaining_time": "0:58:23", "throughput": 4635.3, "total_tokens": 26452128} {"current_steps": 26290, "total_steps": 42420, "loss": 0.1016, "lr": 1.8974710730875606e-05, "epoch": 12.395096652522396, "percentage": 61.98, "elapsed_time": "1:35:07", "remaining_time": "0:58:21", "throughput": 4635.33, "total_tokens": 26457568} {"current_steps": 26295, "total_steps": 42420, "loss": 0.0334, "lr": 1.896472844494718e-05, "epoch": 12.397454031117398, "percentage": 61.99, "elapsed_time": "1:35:08", "remaining_time": "0:58:20", "throughput": 4635.37, "total_tokens": 26462336} {"current_steps": 26300, "total_steps": 42420, "loss": 0.0358, "lr": 1.895474718068775e-05, "epoch": 12.3998114097124, "percentage": 62.0, "elapsed_time": "1:35:09", "remaining_time": "0:58:19", "throughput": 4635.4, "total_tokens": 26467488} {"current_steps": 26305, "total_steps": 42420, "loss": 0.2136, "lr": 1.8944766939786977e-05, "epoch": 12.402168788307403, "percentage": 62.01, "elapsed_time": "1:35:10", "remaining_time": "0:58:18", "throughput": 4635.46, "total_tokens": 26473056} {"current_steps": 26310, "total_steps": 42420, "loss": 0.1166, "lr": 1.893478772393435e-05, "epoch": 12.404526166902404, "percentage": 62.02, "elapsed_time": "1:35:12", "remaining_time": "0:58:17", "throughput": 4635.5, "total_tokens": 26478336} {"current_steps": 26315, "total_steps": 42420, "loss": 0.0617, "lr": 1.892480953481918e-05, "epoch": 12.406883545497408, "percentage": 62.03, "elapsed_time": "1:35:13", "remaining_time": "0:58:16", "throughput": 4635.47, "total_tokens": 26482688} {"current_steps": 26320, "total_steps": 42420, "loss": 0.2265, "lr": 1.891483237413061e-05, "epoch": 12.409240924092408, "percentage": 62.05, "elapsed_time": "1:35:14", "remaining_time": "0:58:15", "throughput": 4635.52, "total_tokens": 26487840} {"current_steps": 26325, "total_steps": 42420, "loss": 0.0407, "lr": 1.890485624355759e-05, "epoch": 12.41159830268741, "percentage": 62.06, "elapsed_time": "1:35:15", "remaining_time": "0:58:14", "throughput": 4635.58, "total_tokens": 26493248} {"current_steps": 26330, "total_steps": 42420, "loss": 0.1099, "lr": 1.8894881144788924e-05, "epoch": 12.413955681282413, "percentage": 62.07, "elapsed_time": "1:35:16", "remaining_time": "0:58:13", "throughput": 4635.61, "total_tokens": 26498304} {"current_steps": 26335, "total_steps": 42420, "loss": 0.1713, "lr": 1.8884907079513224e-05, "epoch": 12.416313059877416, "percentage": 62.08, "elapsed_time": "1:35:17", "remaining_time": "0:58:12", "throughput": 4635.68, "total_tokens": 26504160} {"current_steps": 26340, "total_steps": 42420, "loss": 0.0656, "lr": 1.8874934049418925e-05, "epoch": 12.418670438472418, "percentage": 62.09, "elapsed_time": "1:35:18", "remaining_time": "0:58:10", "throughput": 4635.72, "total_tokens": 26508832} {"current_steps": 26345, "total_steps": 42420, "loss": 0.0678, "lr": 1.886496205619429e-05, "epoch": 12.42102781706742, "percentage": 62.11, "elapsed_time": "1:35:19", "remaining_time": "0:58:09", "throughput": 4635.74, "total_tokens": 26513472} {"current_steps": 26350, "total_steps": 42420, "loss": 0.0768, "lr": 1.8854991101527412e-05, "epoch": 12.423385195662423, "percentage": 62.12, "elapsed_time": "1:35:20", "remaining_time": "0:58:08", "throughput": 4635.76, "total_tokens": 26517888} {"current_steps": 26355, "total_steps": 42420, "loss": 0.081, "lr": 1.884502118710621e-05, "epoch": 12.425742574257425, "percentage": 62.13, "elapsed_time": "1:35:21", "remaining_time": "0:58:07", "throughput": 4635.8, "total_tokens": 26523840} {"current_steps": 26360, "total_steps": 42420, "loss": 0.1915, "lr": 1.883505231461841e-05, "epoch": 12.428099952852428, "percentage": 62.14, "elapsed_time": "1:35:22", "remaining_time": "0:58:06", "throughput": 4635.79, "total_tokens": 26527712} {"current_steps": 26365, "total_steps": 42420, "loss": 0.1497, "lr": 1.882508448575158e-05, "epoch": 12.43045733144743, "percentage": 62.15, "elapsed_time": "1:35:23", "remaining_time": "0:58:05", "throughput": 4635.82, "total_tokens": 26532864} {"current_steps": 26370, "total_steps": 42420, "loss": 0.0965, "lr": 1.88151177021931e-05, "epoch": 12.432814710042432, "percentage": 62.16, "elapsed_time": "1:35:24", "remaining_time": "0:58:04", "throughput": 4635.89, "total_tokens": 26538240} {"current_steps": 26375, "total_steps": 42420, "loss": 0.1476, "lr": 1.8805151965630184e-05, "epoch": 12.435172088637435, "percentage": 62.18, "elapsed_time": "1:35:25", "remaining_time": "0:58:03", "throughput": 4635.93, "total_tokens": 26543168} {"current_steps": 26380, "total_steps": 42420, "loss": 0.185, "lr": 1.8795187277749856e-05, "epoch": 12.437529467232437, "percentage": 62.19, "elapsed_time": "1:35:26", "remaining_time": "0:58:01", "throughput": 4635.97, "total_tokens": 26548000} {"current_steps": 26385, "total_steps": 42420, "loss": 0.1658, "lr": 1.8785223640238968e-05, "epoch": 12.43988684582744, "percentage": 62.2, "elapsed_time": "1:35:27", "remaining_time": "0:58:00", "throughput": 4636.0, "total_tokens": 26553152} {"current_steps": 26390, "total_steps": 42420, "loss": 0.0749, "lr": 1.87752610547842e-05, "epoch": 12.442244224422442, "percentage": 62.21, "elapsed_time": "1:35:28", "remaining_time": "0:57:59", "throughput": 4636.02, "total_tokens": 26558080} {"current_steps": 26395, "total_steps": 42420, "loss": 0.0839, "lr": 1.8765299523072046e-05, "epoch": 12.444601603017444, "percentage": 62.22, "elapsed_time": "1:35:29", "remaining_time": "0:57:58", "throughput": 4636.04, "total_tokens": 26562880} {"current_steps": 26400, "total_steps": 42420, "loss": 0.0115, "lr": 1.8755339046788823e-05, "epoch": 12.446958981612447, "percentage": 62.23, "elapsed_time": "1:35:30", "remaining_time": "0:57:57", "throughput": 4636.04, "total_tokens": 26567584} {"current_steps": 26405, "total_steps": 42420, "loss": 0.0555, "lr": 1.8745379627620668e-05, "epoch": 12.44931636020745, "percentage": 62.25, "elapsed_time": "1:35:31", "remaining_time": "0:57:56", "throughput": 4636.09, "total_tokens": 26573152} {"current_steps": 26410, "total_steps": 42420, "loss": 0.1749, "lr": 1.8735421267253546e-05, "epoch": 12.451673738802452, "percentage": 62.26, "elapsed_time": "1:35:32", "remaining_time": "0:57:55", "throughput": 4636.11, "total_tokens": 26577568} {"current_steps": 26415, "total_steps": 42420, "loss": 0.1447, "lr": 1.872546396737324e-05, "epoch": 12.454031117397454, "percentage": 62.27, "elapsed_time": "1:35:33", "remaining_time": "0:57:54", "throughput": 4636.14, "total_tokens": 26581888} {"current_steps": 26420, "total_steps": 42420, "loss": 0.0514, "lr": 1.8715507729665345e-05, "epoch": 12.456388495992456, "percentage": 62.28, "elapsed_time": "1:35:34", "remaining_time": "0:57:52", "throughput": 4636.15, "total_tokens": 26586784} {"current_steps": 26425, "total_steps": 42420, "loss": 0.0624, "lr": 1.8705552555815286e-05, "epoch": 12.458745874587459, "percentage": 62.29, "elapsed_time": "1:35:35", "remaining_time": "0:57:51", "throughput": 4636.17, "total_tokens": 26591264} {"current_steps": 26430, "total_steps": 42420, "loss": 0.1076, "lr": 1.8695598447508305e-05, "epoch": 12.461103253182461, "percentage": 62.31, "elapsed_time": "1:35:36", "remaining_time": "0:57:50", "throughput": 4636.15, "total_tokens": 26596736} {"current_steps": 26435, "total_steps": 42420, "loss": 0.2259, "lr": 1.868564540642947e-05, "epoch": 12.463460631777464, "percentage": 62.32, "elapsed_time": "1:35:37", "remaining_time": "0:57:49", "throughput": 4636.21, "total_tokens": 26602080} {"current_steps": 26440, "total_steps": 42420, "loss": 0.1654, "lr": 1.8675693434263654e-05, "epoch": 12.465818010372466, "percentage": 62.33, "elapsed_time": "1:35:39", "remaining_time": "0:57:48", "throughput": 4636.25, "total_tokens": 26607456} {"current_steps": 26445, "total_steps": 42420, "loss": 0.0884, "lr": 1.8665742532695556e-05, "epoch": 12.468175388967468, "percentage": 62.34, "elapsed_time": "1:35:40", "remaining_time": "0:57:47", "throughput": 4636.27, "total_tokens": 26612256} {"current_steps": 26450, "total_steps": 42420, "loss": 0.0561, "lr": 1.86557927034097e-05, "epoch": 12.47053276756247, "percentage": 62.35, "elapsed_time": "1:35:41", "remaining_time": "0:57:46", "throughput": 4636.33, "total_tokens": 26618016} {"current_steps": 26455, "total_steps": 42420, "loss": 0.2689, "lr": 1.8645843948090423e-05, "epoch": 12.472890146157473, "percentage": 62.36, "elapsed_time": "1:35:42", "remaining_time": "0:57:45", "throughput": 4636.35, "total_tokens": 26622464} {"current_steps": 26460, "total_steps": 42420, "loss": 0.0698, "lr": 1.863589626842187e-05, "epoch": 12.475247524752476, "percentage": 62.38, "elapsed_time": "1:35:43", "remaining_time": "0:57:44", "throughput": 4636.4, "total_tokens": 26627840} {"current_steps": 26465, "total_steps": 42420, "loss": 0.0454, "lr": 1.862594966608803e-05, "epoch": 12.477604903347478, "percentage": 62.39, "elapsed_time": "1:35:44", "remaining_time": "0:57:43", "throughput": 4636.4, "total_tokens": 26632640} {"current_steps": 26470, "total_steps": 42420, "loss": 0.0631, "lr": 1.8616004142772682e-05, "epoch": 12.47996228194248, "percentage": 62.4, "elapsed_time": "1:35:45", "remaining_time": "0:57:41", "throughput": 4636.43, "total_tokens": 26637888} {"current_steps": 26475, "total_steps": 42420, "loss": 0.048, "lr": 1.8606059700159446e-05, "epoch": 12.482319660537483, "percentage": 62.41, "elapsed_time": "1:35:46", "remaining_time": "0:57:40", "throughput": 4636.46, "total_tokens": 26642912} {"current_steps": 26480, "total_steps": 42420, "loss": 0.0727, "lr": 1.8596116339931733e-05, "epoch": 12.484677039132485, "percentage": 62.42, "elapsed_time": "1:35:47", "remaining_time": "0:57:39", "throughput": 4636.49, "total_tokens": 26647488} {"current_steps": 26485, "total_steps": 42420, "loss": 0.0296, "lr": 1.858617406377279e-05, "epoch": 12.487034417727488, "percentage": 62.44, "elapsed_time": "1:35:48", "remaining_time": "0:57:38", "throughput": 4636.49, "total_tokens": 26652128} {"current_steps": 26490, "total_steps": 42420, "loss": 0.1105, "lr": 1.8576232873365678e-05, "epoch": 12.48939179632249, "percentage": 62.45, "elapsed_time": "1:35:49", "remaining_time": "0:57:37", "throughput": 4636.54, "total_tokens": 26657120} {"current_steps": 26495, "total_steps": 42420, "loss": 0.0465, "lr": 1.8566292770393278e-05, "epoch": 12.491749174917492, "percentage": 62.46, "elapsed_time": "1:35:50", "remaining_time": "0:57:36", "throughput": 4636.59, "total_tokens": 26663136} {"current_steps": 26500, "total_steps": 42420, "loss": 0.1163, "lr": 1.855635375653827e-05, "epoch": 12.494106553512495, "percentage": 62.47, "elapsed_time": "1:35:51", "remaining_time": "0:57:35", "throughput": 4636.63, "total_tokens": 26668096} {"current_steps": 26505, "total_steps": 42420, "loss": 0.0801, "lr": 1.8546415833483165e-05, "epoch": 12.496463932107497, "percentage": 62.48, "elapsed_time": "1:35:52", "remaining_time": "0:57:34", "throughput": 4636.67, "total_tokens": 26673792} {"current_steps": 26510, "total_steps": 42420, "loss": 0.163, "lr": 1.853647900291029e-05, "epoch": 12.4988213107025, "percentage": 62.49, "elapsed_time": "1:35:53", "remaining_time": "0:57:33", "throughput": 4636.68, "total_tokens": 26678208} {"current_steps": 26515, "total_steps": 42420, "loss": 0.0717, "lr": 1.8526543266501767e-05, "epoch": 12.5011786892975, "percentage": 62.51, "elapsed_time": "1:35:54", "remaining_time": "0:57:31", "throughput": 4636.71, "total_tokens": 26683232} {"current_steps": 26520, "total_steps": 42420, "loss": 0.0624, "lr": 1.8516608625939557e-05, "epoch": 12.503536067892503, "percentage": 62.52, "elapsed_time": "1:35:55", "remaining_time": "0:57:30", "throughput": 4636.68, "total_tokens": 26687360} {"current_steps": 26525, "total_steps": 42420, "loss": 0.1794, "lr": 1.850667508290543e-05, "epoch": 12.505893446487505, "percentage": 62.53, "elapsed_time": "1:35:56", "remaining_time": "0:57:29", "throughput": 4636.72, "total_tokens": 26692544} {"current_steps": 26530, "total_steps": 42420, "loss": 0.1964, "lr": 1.8496742639080955e-05, "epoch": 12.508250825082508, "percentage": 62.54, "elapsed_time": "1:35:57", "remaining_time": "0:57:28", "throughput": 4636.72, "total_tokens": 26697088} {"current_steps": 26535, "total_steps": 42420, "loss": 0.124, "lr": 1.8486811296147534e-05, "epoch": 12.51060820367751, "percentage": 62.55, "elapsed_time": "1:35:58", "remaining_time": "0:57:27", "throughput": 4636.77, "total_tokens": 26702176} {"current_steps": 26540, "total_steps": 42420, "loss": 0.1671, "lr": 1.847688105578637e-05, "epoch": 12.512965582272512, "percentage": 62.56, "elapsed_time": "1:35:59", "remaining_time": "0:57:26", "throughput": 4636.8, "total_tokens": 26707168} {"current_steps": 26545, "total_steps": 42420, "loss": 0.041, "lr": 1.846695191967849e-05, "epoch": 12.515322960867515, "percentage": 62.58, "elapsed_time": "1:36:00", "remaining_time": "0:57:25", "throughput": 4636.83, "total_tokens": 26711616} {"current_steps": 26550, "total_steps": 42420, "loss": 0.1358, "lr": 1.8457023889504723e-05, "epoch": 12.517680339462517, "percentage": 62.59, "elapsed_time": "1:36:01", "remaining_time": "0:57:24", "throughput": 4636.87, "total_tokens": 26717024} {"current_steps": 26555, "total_steps": 42420, "loss": 0.2376, "lr": 1.8447096966945722e-05, "epoch": 12.52003771805752, "percentage": 62.6, "elapsed_time": "1:36:02", "remaining_time": "0:57:22", "throughput": 4636.86, "total_tokens": 26721696} {"current_steps": 26560, "total_steps": 42420, "loss": 0.1227, "lr": 1.8437171153681935e-05, "epoch": 12.522395096652522, "percentage": 62.61, "elapsed_time": "1:36:03", "remaining_time": "0:57:21", "throughput": 4636.87, "total_tokens": 26726688} {"current_steps": 26565, "total_steps": 42420, "loss": 0.1945, "lr": 1.842724645139365e-05, "epoch": 12.524752475247524, "percentage": 62.62, "elapsed_time": "1:36:04", "remaining_time": "0:57:20", "throughput": 4636.9, "total_tokens": 26731488} {"current_steps": 26570, "total_steps": 42420, "loss": 0.1259, "lr": 1.8417322861760937e-05, "epoch": 12.527109853842527, "percentage": 62.64, "elapsed_time": "1:36:06", "remaining_time": "0:57:19", "throughput": 4636.95, "total_tokens": 26737152} {"current_steps": 26575, "total_steps": 42420, "loss": 0.0812, "lr": 1.8407400386463698e-05, "epoch": 12.52946723243753, "percentage": 62.65, "elapsed_time": "1:36:07", "remaining_time": "0:57:18", "throughput": 4636.97, "total_tokens": 26741728} {"current_steps": 26580, "total_steps": 42420, "loss": 0.0633, "lr": 1.8397479027181637e-05, "epoch": 12.531824611032532, "percentage": 62.66, "elapsed_time": "1:36:08", "remaining_time": "0:57:17", "throughput": 4636.99, "total_tokens": 26746304} {"current_steps": 26585, "total_steps": 42420, "loss": 0.0855, "lr": 1.838755878559427e-05, "epoch": 12.534181989627534, "percentage": 62.67, "elapsed_time": "1:36:09", "remaining_time": "0:57:16", "throughput": 4637.01, "total_tokens": 26751232} {"current_steps": 26590, "total_steps": 42420, "loss": 0.0297, "lr": 1.837763966338093e-05, "epoch": 12.536539368222536, "percentage": 62.68, "elapsed_time": "1:36:10", "remaining_time": "0:57:15", "throughput": 4637.04, "total_tokens": 26756288} {"current_steps": 26595, "total_steps": 42420, "loss": 0.1954, "lr": 1.8367721662220754e-05, "epoch": 12.538896746817539, "percentage": 62.69, "elapsed_time": "1:36:11", "remaining_time": "0:57:14", "throughput": 4637.03, "total_tokens": 26760704} {"current_steps": 26600, "total_steps": 42420, "loss": 0.12, "lr": 1.8357804783792688e-05, "epoch": 12.541254125412541, "percentage": 62.71, "elapsed_time": "1:36:12", "remaining_time": "0:57:12", "throughput": 4637.06, "total_tokens": 26765856} {"current_steps": 26605, "total_steps": 42420, "loss": 0.1588, "lr": 1.83478890297755e-05, "epoch": 12.543611504007544, "percentage": 62.72, "elapsed_time": "1:36:13", "remaining_time": "0:57:11", "throughput": 4637.1, "total_tokens": 26770784} {"current_steps": 26610, "total_steps": 42420, "loss": 0.1677, "lr": 1.833797440184775e-05, "epoch": 12.545968882602546, "percentage": 62.73, "elapsed_time": "1:36:14", "remaining_time": "0:57:10", "throughput": 4637.12, "total_tokens": 26776928} {"current_steps": 26615, "total_steps": 42420, "loss": 0.111, "lr": 1.8328060901687815e-05, "epoch": 12.548326261197548, "percentage": 62.74, "elapsed_time": "1:36:15", "remaining_time": "0:57:09", "throughput": 4637.18, "total_tokens": 26782464} {"current_steps": 26620, "total_steps": 42420, "loss": 0.0713, "lr": 1.831814853097389e-05, "epoch": 12.55068363979255, "percentage": 62.75, "elapsed_time": "1:36:16", "remaining_time": "0:57:08", "throughput": 4637.21, "total_tokens": 26787456} {"current_steps": 26625, "total_steps": 42420, "loss": 0.029, "lr": 1.830823729138397e-05, "epoch": 12.553041018387553, "percentage": 62.77, "elapsed_time": "1:36:17", "remaining_time": "0:57:07", "throughput": 4637.24, "total_tokens": 26792896} {"current_steps": 26630, "total_steps": 42420, "loss": 0.0474, "lr": 1.8298327184595853e-05, "epoch": 12.555398396982556, "percentage": 62.78, "elapsed_time": "1:36:18", "remaining_time": "0:57:06", "throughput": 4637.26, "total_tokens": 26797536} {"current_steps": 26635, "total_steps": 42420, "loss": 0.0256, "lr": 1.8288418212287157e-05, "epoch": 12.557755775577558, "percentage": 62.79, "elapsed_time": "1:36:19", "remaining_time": "0:57:05", "throughput": 4637.31, "total_tokens": 26802624} {"current_steps": 26640, "total_steps": 42420, "loss": 0.1222, "lr": 1.8278510376135296e-05, "epoch": 12.56011315417256, "percentage": 62.8, "elapsed_time": "1:36:20", "remaining_time": "0:57:04", "throughput": 4637.33, "total_tokens": 26807040} {"current_steps": 26645, "total_steps": 42420, "loss": 0.0485, "lr": 1.8268603677817514e-05, "epoch": 12.562470532767563, "percentage": 62.81, "elapsed_time": "1:36:21", "remaining_time": "0:57:02", "throughput": 4637.33, "total_tokens": 26811328} {"current_steps": 26650, "total_steps": 42420, "loss": 0.1946, "lr": 1.825869811901083e-05, "epoch": 12.564827911362565, "percentage": 62.82, "elapsed_time": "1:36:22", "remaining_time": "0:57:01", "throughput": 4637.38, "total_tokens": 26816768} {"current_steps": 26655, "total_steps": 42420, "loss": 0.0358, "lr": 1.824879370139209e-05, "epoch": 12.567185289957568, "percentage": 62.84, "elapsed_time": "1:36:23", "remaining_time": "0:57:00", "throughput": 4637.42, "total_tokens": 26821728} {"current_steps": 26660, "total_steps": 42420, "loss": 0.0438, "lr": 1.8238890426637954e-05, "epoch": 12.56954266855257, "percentage": 62.85, "elapsed_time": "1:36:24", "remaining_time": "0:56:59", "throughput": 4637.45, "total_tokens": 26826752} {"current_steps": 26665, "total_steps": 42420, "loss": 0.1072, "lr": 1.8228988296424877e-05, "epoch": 12.571900047147572, "percentage": 62.86, "elapsed_time": "1:36:25", "remaining_time": "0:56:58", "throughput": 4637.48, "total_tokens": 26831584} {"current_steps": 26670, "total_steps": 42420, "loss": 0.1822, "lr": 1.8219087312429106e-05, "epoch": 12.574257425742575, "percentage": 62.87, "elapsed_time": "1:36:26", "remaining_time": "0:56:57", "throughput": 4637.46, "total_tokens": 26835872} {"current_steps": 26675, "total_steps": 42420, "loss": 0.1285, "lr": 1.820918747632672e-05, "epoch": 12.576614804337577, "percentage": 62.88, "elapsed_time": "1:36:27", "remaining_time": "0:56:56", "throughput": 4637.51, "total_tokens": 26840768} {"current_steps": 26680, "total_steps": 42420, "loss": 0.0376, "lr": 1.8199288789793596e-05, "epoch": 12.57897218293258, "percentage": 62.89, "elapsed_time": "1:36:28", "remaining_time": "0:56:55", "throughput": 4637.51, "total_tokens": 26845120} {"current_steps": 26685, "total_steps": 42420, "loss": 0.1594, "lr": 1.8189391254505416e-05, "epoch": 12.581329561527582, "percentage": 62.91, "elapsed_time": "1:36:29", "remaining_time": "0:56:54", "throughput": 4637.57, "total_tokens": 26850816} {"current_steps": 26690, "total_steps": 42420, "loss": 0.0573, "lr": 1.817949487213765e-05, "epoch": 12.583686940122584, "percentage": 62.92, "elapsed_time": "1:36:30", "remaining_time": "0:56:52", "throughput": 4637.61, "total_tokens": 26855968} {"current_steps": 26695, "total_steps": 42420, "loss": 0.0635, "lr": 1.8169599644365597e-05, "epoch": 12.586044318717587, "percentage": 62.93, "elapsed_time": "1:36:31", "remaining_time": "0:56:51", "throughput": 4637.65, "total_tokens": 26860832} {"current_steps": 26700, "total_steps": 42420, "loss": 0.1387, "lr": 1.8159705572864356e-05, "epoch": 12.58840169731259, "percentage": 62.94, "elapsed_time": "1:36:33", "remaining_time": "0:56:50", "throughput": 4637.65, "total_tokens": 26866112} {"current_steps": 26705, "total_steps": 42420, "loss": 0.0171, "lr": 1.814981265930882e-05, "epoch": 12.590759075907592, "percentage": 62.95, "elapsed_time": "1:36:34", "remaining_time": "0:56:49", "throughput": 4637.72, "total_tokens": 26872448} {"current_steps": 26710, "total_steps": 42420, "loss": 0.1264, "lr": 1.8139920905373687e-05, "epoch": 12.593116454502592, "percentage": 62.97, "elapsed_time": "1:36:35", "remaining_time": "0:56:48", "throughput": 4637.74, "total_tokens": 26876864} {"current_steps": 26715, "total_steps": 42420, "loss": 0.0924, "lr": 1.813003031273347e-05, "epoch": 12.595473833097596, "percentage": 62.98, "elapsed_time": "1:36:36", "remaining_time": "0:56:47", "throughput": 4637.76, "total_tokens": 26881056} {"current_steps": 26720, "total_steps": 42420, "loss": 0.1318, "lr": 1.8120140883062472e-05, "epoch": 12.597831211692597, "percentage": 62.99, "elapsed_time": "1:36:37", "remaining_time": "0:56:46", "throughput": 4637.82, "total_tokens": 26886912} {"current_steps": 26725, "total_steps": 42420, "loss": 0.1318, "lr": 1.811025261803482e-05, "epoch": 12.6001885902876, "percentage": 63.0, "elapsed_time": "1:36:38", "remaining_time": "0:56:45", "throughput": 4637.86, "total_tokens": 26891680} {"current_steps": 26730, "total_steps": 42420, "loss": 0.18, "lr": 1.8100365519324402e-05, "epoch": 12.602545968882602, "percentage": 63.01, "elapsed_time": "1:36:39", "remaining_time": "0:56:44", "throughput": 4637.9, "total_tokens": 26896928} {"current_steps": 26735, "total_steps": 42420, "loss": 0.039, "lr": 1.8090479588604972e-05, "epoch": 12.604903347477604, "percentage": 63.02, "elapsed_time": "1:36:40", "remaining_time": "0:56:43", "throughput": 4637.96, "total_tokens": 26902048} {"current_steps": 26740, "total_steps": 42420, "loss": 0.1198, "lr": 1.808059482755002e-05, "epoch": 12.607260726072607, "percentage": 63.04, "elapsed_time": "1:36:41", "remaining_time": "0:56:41", "throughput": 4638.0, "total_tokens": 26907232} {"current_steps": 26745, "total_steps": 42420, "loss": 0.1528, "lr": 1.8070711237832875e-05, "epoch": 12.609618104667609, "percentage": 63.05, "elapsed_time": "1:36:42", "remaining_time": "0:56:40", "throughput": 4638.03, "total_tokens": 26912672} {"current_steps": 26750, "total_steps": 42420, "loss": 0.0948, "lr": 1.806082882112667e-05, "epoch": 12.611975483262611, "percentage": 63.06, "elapsed_time": "1:36:43", "remaining_time": "0:56:39", "throughput": 4638.05, "total_tokens": 26917280} {"current_steps": 26755, "total_steps": 42420, "loss": 0.0413, "lr": 1.8050947579104326e-05, "epoch": 12.614332861857614, "percentage": 63.07, "elapsed_time": "1:36:44", "remaining_time": "0:56:38", "throughput": 4638.1, "total_tokens": 26923424} {"current_steps": 26760, "total_steps": 42420, "loss": 0.1547, "lr": 1.8041067513438564e-05, "epoch": 12.616690240452616, "percentage": 63.08, "elapsed_time": "1:36:45", "remaining_time": "0:56:37", "throughput": 4638.12, "total_tokens": 26928576} {"current_steps": 26765, "total_steps": 42420, "loss": 0.1755, "lr": 1.8031188625801916e-05, "epoch": 12.619047619047619, "percentage": 63.1, "elapsed_time": "1:36:47", "remaining_time": "0:56:36", "throughput": 4638.13, "total_tokens": 26933792} {"current_steps": 26770, "total_steps": 42420, "loss": 0.329, "lr": 1.802131091786671e-05, "epoch": 12.621404997642621, "percentage": 63.11, "elapsed_time": "1:36:47", "remaining_time": "0:56:35", "throughput": 4638.15, "total_tokens": 26938304} {"current_steps": 26775, "total_steps": 42420, "loss": 0.1959, "lr": 1.801143439130508e-05, "epoch": 12.623762376237623, "percentage": 63.12, "elapsed_time": "1:36:48", "remaining_time": "0:56:34", "throughput": 4638.09, "total_tokens": 26941920} {"current_steps": 26780, "total_steps": 42420, "loss": 0.0282, "lr": 1.8001559047788943e-05, "epoch": 12.626119754832626, "percentage": 63.13, "elapsed_time": "1:36:49", "remaining_time": "0:56:33", "throughput": 4638.12, "total_tokens": 26946816} {"current_steps": 26785, "total_steps": 42420, "loss": 0.1827, "lr": 1.7991684888990032e-05, "epoch": 12.628477133427628, "percentage": 63.14, "elapsed_time": "1:36:50", "remaining_time": "0:56:31", "throughput": 4638.09, "total_tokens": 26951072} {"current_steps": 26790, "total_steps": 42420, "loss": 0.1855, "lr": 1.7981811916579876e-05, "epoch": 12.63083451202263, "percentage": 63.15, "elapsed_time": "1:36:51", "remaining_time": "0:56:30", "throughput": 4638.1, "total_tokens": 26955712} {"current_steps": 26795, "total_steps": 42420, "loss": 0.1663, "lr": 1.7971940132229804e-05, "epoch": 12.633191890617633, "percentage": 63.17, "elapsed_time": "1:36:52", "remaining_time": "0:56:29", "throughput": 4638.02, "total_tokens": 26959648} {"current_steps": 26800, "total_steps": 42420, "loss": 0.0622, "lr": 1.7962069537610938e-05, "epoch": 12.635549269212635, "percentage": 63.18, "elapsed_time": "1:36:53", "remaining_time": "0:56:28", "throughput": 4637.99, "total_tokens": 26963552} {"current_steps": 26805, "total_steps": 42420, "loss": 0.0589, "lr": 1.7952200134394195e-05, "epoch": 12.637906647807638, "percentage": 63.19, "elapsed_time": "1:36:54", "remaining_time": "0:56:27", "throughput": 4638.03, "total_tokens": 26969152} {"current_steps": 26810, "total_steps": 42420, "loss": 0.0361, "lr": 1.7942331924250308e-05, "epoch": 12.64026402640264, "percentage": 63.2, "elapsed_time": "1:36:56", "remaining_time": "0:56:26", "throughput": 4638.04, "total_tokens": 26976064} {"current_steps": 26815, "total_steps": 42420, "loss": 0.0492, "lr": 1.79324649088498e-05, "epoch": 12.642621404997643, "percentage": 63.21, "elapsed_time": "1:36:57", "remaining_time": "0:56:25", "throughput": 4638.0, "total_tokens": 26980576} {"current_steps": 26820, "total_steps": 42420, "loss": 0.0851, "lr": 1.7922599089862973e-05, "epoch": 12.644978783592645, "percentage": 63.22, "elapsed_time": "1:36:58", "remaining_time": "0:56:24", "throughput": 4637.99, "total_tokens": 26985152} {"current_steps": 26825, "total_steps": 42420, "loss": 0.1555, "lr": 1.791273446895996e-05, "epoch": 12.647336162187647, "percentage": 63.24, "elapsed_time": "1:36:59", "remaining_time": "0:56:23", "throughput": 4638.03, "total_tokens": 26991616} {"current_steps": 26830, "total_steps": 42420, "loss": 0.1756, "lr": 1.790287104781066e-05, "epoch": 12.64969354078265, "percentage": 63.25, "elapsed_time": "1:37:00", "remaining_time": "0:56:22", "throughput": 4638.08, "total_tokens": 26997568} {"current_steps": 26835, "total_steps": 42420, "loss": 0.0823, "lr": 1.7893008828084795e-05, "epoch": 12.652050919377652, "percentage": 63.26, "elapsed_time": "1:37:02", "remaining_time": "0:56:21", "throughput": 4638.15, "total_tokens": 27003840} {"current_steps": 26840, "total_steps": 42420, "loss": 0.1157, "lr": 1.788314781145186e-05, "epoch": 12.654408297972655, "percentage": 63.27, "elapsed_time": "1:37:03", "remaining_time": "0:56:20", "throughput": 4638.2, "total_tokens": 27010112} {"current_steps": 26845, "total_steps": 42420, "loss": 0.2873, "lr": 1.7873287999581167e-05, "epoch": 12.656765676567657, "percentage": 63.28, "elapsed_time": "1:37:04", "remaining_time": "0:56:19", "throughput": 4638.27, "total_tokens": 27016128} {"current_steps": 26850, "total_steps": 42420, "loss": 0.2137, "lr": 1.7863429394141813e-05, "epoch": 12.65912305516266, "percentage": 63.3, "elapsed_time": "1:37:05", "remaining_time": "0:56:18", "throughput": 4638.29, "total_tokens": 27020608} {"current_steps": 26855, "total_steps": 42420, "loss": 0.2033, "lr": 1.785357199680269e-05, "epoch": 12.661480433757662, "percentage": 63.31, "elapsed_time": "1:37:06", "remaining_time": "0:56:17", "throughput": 4638.34, "total_tokens": 27025856} {"current_steps": 26860, "total_steps": 42420, "loss": 0.0866, "lr": 1.7843715809232487e-05, "epoch": 12.663837812352664, "percentage": 63.32, "elapsed_time": "1:37:07", "remaining_time": "0:56:16", "throughput": 4638.41, "total_tokens": 27032256} {"current_steps": 26865, "total_steps": 42420, "loss": 0.0642, "lr": 1.7833860833099685e-05, "epoch": 12.666195190947667, "percentage": 63.33, "elapsed_time": "1:37:08", "remaining_time": "0:56:14", "throughput": 4638.43, "total_tokens": 27036864} {"current_steps": 26870, "total_steps": 42420, "loss": 0.2172, "lr": 1.7824007070072576e-05, "epoch": 12.668552569542669, "percentage": 63.34, "elapsed_time": "1:37:10", "remaining_time": "0:56:13", "throughput": 4638.5, "total_tokens": 27042880} {"current_steps": 26875, "total_steps": 42420, "loss": 0.2135, "lr": 1.7814154521819232e-05, "epoch": 12.670909948137671, "percentage": 63.35, "elapsed_time": "1:37:11", "remaining_time": "0:56:12", "throughput": 4638.54, "total_tokens": 27048160} {"current_steps": 26880, "total_steps": 42420, "loss": 0.0988, "lr": 1.7804303190007515e-05, "epoch": 12.673267326732674, "percentage": 63.37, "elapsed_time": "1:37:12", "remaining_time": "0:56:11", "throughput": 4638.58, "total_tokens": 27053120} {"current_steps": 26885, "total_steps": 42420, "loss": 0.2163, "lr": 1.779445307630509e-05, "epoch": 12.675624705327676, "percentage": 63.38, "elapsed_time": "1:37:13", "remaining_time": "0:56:10", "throughput": 4638.58, "total_tokens": 27057920} {"current_steps": 26890, "total_steps": 42420, "loss": 0.2985, "lr": 1.7784604182379417e-05, "epoch": 12.677982083922679, "percentage": 63.39, "elapsed_time": "1:37:14", "remaining_time": "0:56:09", "throughput": 4638.65, "total_tokens": 27063936} {"current_steps": 26895, "total_steps": 42420, "loss": 0.0876, "lr": 1.777475650989775e-05, "epoch": 12.680339462517681, "percentage": 63.4, "elapsed_time": "1:37:15", "remaining_time": "0:56:08", "throughput": 4638.7, "total_tokens": 27069536} {"current_steps": 26900, "total_steps": 42420, "loss": 0.1442, "lr": 1.7764910060527122e-05, "epoch": 12.682696841112683, "percentage": 63.41, "elapsed_time": "1:37:16", "remaining_time": "0:56:07", "throughput": 4638.65, "total_tokens": 27073792} {"current_steps": 26905, "total_steps": 42420, "loss": 0.0627, "lr": 1.7755064835934377e-05, "epoch": 12.685054219707686, "percentage": 63.43, "elapsed_time": "1:37:17", "remaining_time": "0:56:06", "throughput": 4638.64, "total_tokens": 27078144} {"current_steps": 26910, "total_steps": 42420, "loss": 0.0435, "lr": 1.774522083778614e-05, "epoch": 12.687411598302688, "percentage": 63.44, "elapsed_time": "1:37:18", "remaining_time": "0:56:05", "throughput": 4638.67, "total_tokens": 27082656} {"current_steps": 26915, "total_steps": 42420, "loss": 0.1408, "lr": 1.773537806774885e-05, "epoch": 12.689768976897689, "percentage": 63.45, "elapsed_time": "1:37:19", "remaining_time": "0:56:03", "throughput": 4638.7, "total_tokens": 27087296} {"current_steps": 26920, "total_steps": 42420, "loss": 0.1804, "lr": 1.7725536527488694e-05, "epoch": 12.692126355492691, "percentage": 63.46, "elapsed_time": "1:37:20", "remaining_time": "0:56:02", "throughput": 4638.7, "total_tokens": 27091968} {"current_steps": 26925, "total_steps": 42420, "loss": 0.2068, "lr": 1.771569621867169e-05, "epoch": 12.694483734087694, "percentage": 63.47, "elapsed_time": "1:37:21", "remaining_time": "0:56:01", "throughput": 4638.76, "total_tokens": 27097312} {"current_steps": 26930, "total_steps": 42420, "loss": 0.1225, "lr": 1.770585714296364e-05, "epoch": 12.696841112682696, "percentage": 63.48, "elapsed_time": "1:37:22", "remaining_time": "0:56:00", "throughput": 4638.79, "total_tokens": 27102400} {"current_steps": 26935, "total_steps": 42420, "loss": 0.1266, "lr": 1.7696019302030133e-05, "epoch": 12.699198491277699, "percentage": 63.5, "elapsed_time": "1:37:23", "remaining_time": "0:55:59", "throughput": 4638.79, "total_tokens": 27106880} {"current_steps": 26940, "total_steps": 42420, "loss": 0.2216, "lr": 1.7686182697536536e-05, "epoch": 12.701555869872701, "percentage": 63.51, "elapsed_time": "1:37:24", "remaining_time": "0:55:58", "throughput": 4638.84, "total_tokens": 27112704} {"current_steps": 26945, "total_steps": 42420, "loss": 0.0628, "lr": 1.7676347331148026e-05, "epoch": 12.703913248467703, "percentage": 63.52, "elapsed_time": "1:37:25", "remaining_time": "0:55:57", "throughput": 4638.85, "total_tokens": 27116960} {"current_steps": 26950, "total_steps": 42420, "loss": 0.0471, "lr": 1.7666513204529566e-05, "epoch": 12.706270627062706, "percentage": 63.53, "elapsed_time": "1:37:26", "remaining_time": "0:55:56", "throughput": 4638.87, "total_tokens": 27121216} {"current_steps": 26955, "total_steps": 42420, "loss": 0.0528, "lr": 1.765668031934591e-05, "epoch": 12.708628005657708, "percentage": 63.54, "elapsed_time": "1:37:27", "remaining_time": "0:55:54", "throughput": 4638.89, "total_tokens": 27125600} {"current_steps": 26960, "total_steps": 42420, "loss": 0.2318, "lr": 1.7646848677261595e-05, "epoch": 12.71098538425271, "percentage": 63.55, "elapsed_time": "1:37:28", "remaining_time": "0:55:53", "throughput": 4638.93, "total_tokens": 27130784} {"current_steps": 26965, "total_steps": 42420, "loss": 0.1232, "lr": 1.7637018279940947e-05, "epoch": 12.713342762847713, "percentage": 63.57, "elapsed_time": "1:37:29", "remaining_time": "0:55:52", "throughput": 4638.94, "total_tokens": 27135136} {"current_steps": 26970, "total_steps": 42420, "loss": 0.2008, "lr": 1.7627189129048085e-05, "epoch": 12.715700141442715, "percentage": 63.58, "elapsed_time": "1:37:30", "remaining_time": "0:55:51", "throughput": 4638.92, "total_tokens": 27139232} {"current_steps": 26975, "total_steps": 42420, "loss": 0.02, "lr": 1.761736122624692e-05, "epoch": 12.718057520037718, "percentage": 63.59, "elapsed_time": "1:37:31", "remaining_time": "0:55:50", "throughput": 4638.91, "total_tokens": 27143808} {"current_steps": 26980, "total_steps": 42420, "loss": 0.1425, "lr": 1.760753457320115e-05, "epoch": 12.72041489863272, "percentage": 63.6, "elapsed_time": "1:37:32", "remaining_time": "0:55:49", "throughput": 4638.93, "total_tokens": 27148288} {"current_steps": 26985, "total_steps": 42420, "loss": 0.113, "lr": 1.7597709171574263e-05, "epoch": 12.722772277227723, "percentage": 63.61, "elapsed_time": "1:37:33", "remaining_time": "0:55:47", "throughput": 4638.94, "total_tokens": 27153088} {"current_steps": 26990, "total_steps": 42420, "loss": 0.1922, "lr": 1.7587885023029525e-05, "epoch": 12.725129655822725, "percentage": 63.63, "elapsed_time": "1:37:34", "remaining_time": "0:55:46", "throughput": 4638.98, "total_tokens": 27157888} {"current_steps": 26995, "total_steps": 42420, "loss": 0.0365, "lr": 1.757806212923e-05, "epoch": 12.727487034417727, "percentage": 63.64, "elapsed_time": "1:37:35", "remaining_time": "0:55:45", "throughput": 4639.0, "total_tokens": 27162592} {"current_steps": 27000, "total_steps": 42420, "loss": 0.1694, "lr": 1.7568240491838546e-05, "epoch": 12.72984441301273, "percentage": 63.65, "elapsed_time": "1:37:36", "remaining_time": "0:55:44", "throughput": 4639.02, "total_tokens": 27167328} {"current_steps": 27005, "total_steps": 42420, "loss": 0.0732, "lr": 1.755842011251779e-05, "epoch": 12.732201791607732, "percentage": 63.66, "elapsed_time": "1:37:37", "remaining_time": "0:55:43", "throughput": 4639.03, "total_tokens": 27171360} {"current_steps": 27010, "total_steps": 42420, "loss": 0.1955, "lr": 1.7548600992930158e-05, "epoch": 12.734559170202735, "percentage": 63.67, "elapsed_time": "1:37:38", "remaining_time": "0:55:42", "throughput": 4639.07, "total_tokens": 27176096} {"current_steps": 27015, "total_steps": 42420, "loss": 0.1607, "lr": 1.753878313473786e-05, "epoch": 12.736916548797737, "percentage": 63.68, "elapsed_time": "1:37:39", "remaining_time": "0:55:41", "throughput": 4639.09, "total_tokens": 27180576} {"current_steps": 27020, "total_steps": 42420, "loss": 0.0227, "lr": 1.7528966539602886e-05, "epoch": 12.73927392739274, "percentage": 63.7, "elapsed_time": "1:37:40", "remaining_time": "0:55:39", "throughput": 4639.14, "total_tokens": 27185440} {"current_steps": 27025, "total_steps": 42420, "loss": 0.1863, "lr": 1.7519151209187037e-05, "epoch": 12.741631305987742, "percentage": 63.71, "elapsed_time": "1:37:41", "remaining_time": "0:55:38", "throughput": 4639.18, "total_tokens": 27190784} {"current_steps": 27030, "total_steps": 42420, "loss": 0.0878, "lr": 1.7509337145151865e-05, "epoch": 12.743988684582744, "percentage": 63.72, "elapsed_time": "1:37:42", "remaining_time": "0:55:37", "throughput": 4639.24, "total_tokens": 27196544} {"current_steps": 27035, "total_steps": 42420, "loss": 0.0907, "lr": 1.749952434915873e-05, "epoch": 12.746346063177747, "percentage": 63.73, "elapsed_time": "1:37:43", "remaining_time": "0:55:36", "throughput": 4639.28, "total_tokens": 27201248} {"current_steps": 27040, "total_steps": 42420, "loss": 0.2218, "lr": 1.7489712822868773e-05, "epoch": 12.748703441772749, "percentage": 63.74, "elapsed_time": "1:37:44", "remaining_time": "0:55:35", "throughput": 4639.27, "total_tokens": 27205920} {"current_steps": 27045, "total_steps": 42420, "loss": 0.0563, "lr": 1.747990256794292e-05, "epoch": 12.751060820367751, "percentage": 63.76, "elapsed_time": "1:37:45", "remaining_time": "0:55:34", "throughput": 4639.3, "total_tokens": 27210880} {"current_steps": 27050, "total_steps": 42420, "loss": 0.0722, "lr": 1.7470093586041874e-05, "epoch": 12.753418198962754, "percentage": 63.77, "elapsed_time": "1:37:46", "remaining_time": "0:55:33", "throughput": 4639.33, "total_tokens": 27215584} {"current_steps": 27055, "total_steps": 42420, "loss": 0.1195, "lr": 1.7460285878826138e-05, "epoch": 12.755775577557756, "percentage": 63.78, "elapsed_time": "1:37:47", "remaining_time": "0:55:32", "throughput": 4639.38, "total_tokens": 27220768} {"current_steps": 27060, "total_steps": 42420, "loss": 0.1528, "lr": 1.745047944795598e-05, "epoch": 12.758132956152759, "percentage": 63.79, "elapsed_time": "1:37:48", "remaining_time": "0:55:31", "throughput": 4639.41, "total_tokens": 27225696} {"current_steps": 27065, "total_steps": 42420, "loss": 0.0545, "lr": 1.7440674295091476e-05, "epoch": 12.760490334747761, "percentage": 63.8, "elapsed_time": "1:37:49", "remaining_time": "0:55:29", "throughput": 4639.46, "total_tokens": 27230848} {"current_steps": 27070, "total_steps": 42420, "loss": 0.0859, "lr": 1.7430870421892458e-05, "epoch": 12.762847713342763, "percentage": 63.81, "elapsed_time": "1:37:50", "remaining_time": "0:55:28", "throughput": 4639.5, "total_tokens": 27236096} {"current_steps": 27075, "total_steps": 42420, "loss": 0.0093, "lr": 1.742106783001856e-05, "epoch": 12.765205091937766, "percentage": 63.83, "elapsed_time": "1:37:51", "remaining_time": "0:55:27", "throughput": 4639.56, "total_tokens": 27241600} {"current_steps": 27080, "total_steps": 42420, "loss": 0.0353, "lr": 1.7411266521129195e-05, "epoch": 12.767562470532768, "percentage": 63.84, "elapsed_time": "1:37:52", "remaining_time": "0:55:26", "throughput": 4639.57, "total_tokens": 27246560} {"current_steps": 27085, "total_steps": 42420, "loss": 0.1825, "lr": 1.7401466496883567e-05, "epoch": 12.76991984912777, "percentage": 63.85, "elapsed_time": "1:37:53", "remaining_time": "0:55:25", "throughput": 4639.64, "total_tokens": 27252896} {"current_steps": 27090, "total_steps": 42420, "loss": 0.0601, "lr": 1.7391667758940638e-05, "epoch": 12.772277227722773, "percentage": 63.86, "elapsed_time": "1:37:55", "remaining_time": "0:55:24", "throughput": 4639.73, "total_tokens": 27260256} {"current_steps": 27095, "total_steps": 42420, "loss": 0.0639, "lr": 1.7381870308959176e-05, "epoch": 12.774634606317775, "percentage": 63.87, "elapsed_time": "1:37:56", "remaining_time": "0:55:23", "throughput": 4639.78, "total_tokens": 27265824} {"current_steps": 27100, "total_steps": 42420, "loss": 0.0748, "lr": 1.737207414859772e-05, "epoch": 12.776991984912778, "percentage": 63.88, "elapsed_time": "1:37:57", "remaining_time": "0:55:22", "throughput": 4639.84, "total_tokens": 27271712} {"current_steps": 27105, "total_steps": 42420, "loss": 0.142, "lr": 1.7362279279514605e-05, "epoch": 12.77934936350778, "percentage": 63.9, "elapsed_time": "1:37:58", "remaining_time": "0:55:21", "throughput": 4639.87, "total_tokens": 27276448} {"current_steps": 27110, "total_steps": 42420, "loss": 0.0496, "lr": 1.7352485703367915e-05, "epoch": 12.78170674210278, "percentage": 63.91, "elapsed_time": "1:37:59", "remaining_time": "0:55:20", "throughput": 4639.92, "total_tokens": 27281760} {"current_steps": 27115, "total_steps": 42420, "loss": 0.1635, "lr": 1.7342693421815554e-05, "epoch": 12.784064120697785, "percentage": 63.92, "elapsed_time": "1:38:01", "remaining_time": "0:55:19", "throughput": 4639.99, "total_tokens": 27288384} {"current_steps": 27120, "total_steps": 42420, "loss": 0.0125, "lr": 1.733290243651518e-05, "epoch": 12.786421499292786, "percentage": 63.93, "elapsed_time": "1:38:01", "remaining_time": "0:55:18", "throughput": 4639.99, "total_tokens": 27292416} {"current_steps": 27125, "total_steps": 42420, "loss": 0.1093, "lr": 1.7323112749124253e-05, "epoch": 12.788778877887788, "percentage": 63.94, "elapsed_time": "1:38:03", "remaining_time": "0:55:17", "throughput": 4639.97, "total_tokens": 27296992} {"current_steps": 27130, "total_steps": 42420, "loss": 0.0352, "lr": 1.731332436129998e-05, "epoch": 12.79113625648279, "percentage": 63.96, "elapsed_time": "1:38:04", "remaining_time": "0:55:16", "throughput": 4640.02, "total_tokens": 27302016} {"current_steps": 27135, "total_steps": 42420, "loss": 0.2661, "lr": 1.7303537274699384e-05, "epoch": 12.793493635077793, "percentage": 63.97, "elapsed_time": "1:38:04", "remaining_time": "0:55:14", "throughput": 4639.99, "total_tokens": 27305760} {"current_steps": 27140, "total_steps": 42420, "loss": 0.1877, "lr": 1.729375149097925e-05, "epoch": 12.795851013672795, "percentage": 63.98, "elapsed_time": "1:38:05", "remaining_time": "0:55:13", "throughput": 4640.05, "total_tokens": 27311264} {"current_steps": 27145, "total_steps": 42420, "loss": 0.1656, "lr": 1.728396701179615e-05, "epoch": 12.798208392267798, "percentage": 63.99, "elapsed_time": "1:38:06", "remaining_time": "0:55:12", "throughput": 4640.1, "total_tokens": 27316160} {"current_steps": 27150, "total_steps": 42420, "loss": 0.1456, "lr": 1.7274183838806412e-05, "epoch": 12.8005657708628, "percentage": 64.0, "elapsed_time": "1:38:08", "remaining_time": "0:55:11", "throughput": 4640.13, "total_tokens": 27321248} {"current_steps": 27155, "total_steps": 42420, "loss": 0.1675, "lr": 1.726440197366618e-05, "epoch": 12.802923149457802, "percentage": 64.01, "elapsed_time": "1:38:09", "remaining_time": "0:55:10", "throughput": 4640.12, "total_tokens": 27325856} {"current_steps": 27160, "total_steps": 42420, "loss": 0.2316, "lr": 1.7254621418031346e-05, "epoch": 12.805280528052805, "percentage": 64.03, "elapsed_time": "1:38:10", "remaining_time": "0:55:09", "throughput": 4640.15, "total_tokens": 27331296} {"current_steps": 27165, "total_steps": 42420, "loss": 0.0987, "lr": 1.7244842173557606e-05, "epoch": 12.807637906647807, "percentage": 64.04, "elapsed_time": "1:38:11", "remaining_time": "0:55:08", "throughput": 4640.16, "total_tokens": 27335712} {"current_steps": 27170, "total_steps": 42420, "loss": 0.2136, "lr": 1.7235064241900408e-05, "epoch": 12.80999528524281, "percentage": 64.05, "elapsed_time": "1:38:12", "remaining_time": "0:55:07", "throughput": 4640.21, "total_tokens": 27341024} {"current_steps": 27175, "total_steps": 42420, "loss": 0.1962, "lr": 1.7225287624714985e-05, "epoch": 12.812352663837812, "percentage": 64.06, "elapsed_time": "1:38:13", "remaining_time": "0:55:06", "throughput": 4640.24, "total_tokens": 27345536} {"current_steps": 27180, "total_steps": 42420, "loss": 0.2587, "lr": 1.7215512323656362e-05, "epoch": 12.814710042432814, "percentage": 64.07, "elapsed_time": "1:38:14", "remaining_time": "0:55:04", "throughput": 4640.27, "total_tokens": 27350912} {"current_steps": 27185, "total_steps": 42420, "loss": 0.085, "lr": 1.7205738340379347e-05, "epoch": 12.817067421027817, "percentage": 64.09, "elapsed_time": "1:38:15", "remaining_time": "0:55:03", "throughput": 4640.3, "total_tokens": 27356256} {"current_steps": 27190, "total_steps": 42420, "loss": 0.1389, "lr": 1.7195965676538476e-05, "epoch": 12.81942479962282, "percentage": 64.1, "elapsed_time": "1:38:16", "remaining_time": "0:55:02", "throughput": 4640.32, "total_tokens": 27361088} {"current_steps": 27195, "total_steps": 42420, "loss": 0.0486, "lr": 1.7186194333788114e-05, "epoch": 12.821782178217822, "percentage": 64.11, "elapsed_time": "1:38:17", "remaining_time": "0:55:01", "throughput": 4640.35, "total_tokens": 27365376} {"current_steps": 27200, "total_steps": 42420, "loss": 0.2353, "lr": 1.717642431378238e-05, "epoch": 12.824139556812824, "percentage": 64.12, "elapsed_time": "1:38:18", "remaining_time": "0:55:00", "throughput": 4640.37, "total_tokens": 27369824} {"current_steps": 27205, "total_steps": 42420, "loss": 0.2298, "lr": 1.716665561817517e-05, "epoch": 12.826496935407826, "percentage": 64.13, "elapsed_time": "1:38:19", "remaining_time": "0:54:59", "throughput": 4640.36, "total_tokens": 27373920} {"current_steps": 27210, "total_steps": 42420, "loss": 0.1249, "lr": 1.715688824862016e-05, "epoch": 12.828854314002829, "percentage": 64.14, "elapsed_time": "1:38:20", "remaining_time": "0:54:58", "throughput": 4640.41, "total_tokens": 27379648} {"current_steps": 27215, "total_steps": 42420, "loss": 0.0492, "lr": 1.714712220677081e-05, "epoch": 12.831211692597831, "percentage": 64.16, "elapsed_time": "1:38:21", "remaining_time": "0:54:57", "throughput": 4640.45, "total_tokens": 27384800} {"current_steps": 27220, "total_steps": 42420, "loss": 0.258, "lr": 1.7137357494280332e-05, "epoch": 12.833569071192834, "percentage": 64.17, "elapsed_time": "1:38:22", "remaining_time": "0:54:56", "throughput": 4640.51, "total_tokens": 27390528} {"current_steps": 27225, "total_steps": 42420, "loss": 0.1837, "lr": 1.7127594112801724e-05, "epoch": 12.835926449787836, "percentage": 64.18, "elapsed_time": "1:38:23", "remaining_time": "0:54:54", "throughput": 4640.54, "total_tokens": 27395136} {"current_steps": 27230, "total_steps": 42420, "loss": 0.0784, "lr": 1.711783206398777e-05, "epoch": 12.838283828382838, "percentage": 64.19, "elapsed_time": "1:38:24", "remaining_time": "0:54:53", "throughput": 4640.56, "total_tokens": 27399872} {"current_steps": 27235, "total_steps": 42420, "loss": 0.0581, "lr": 1.7108071349491022e-05, "epoch": 12.84064120697784, "percentage": 64.2, "elapsed_time": "1:38:25", "remaining_time": "0:54:52", "throughput": 4640.6, "total_tokens": 27404928} {"current_steps": 27240, "total_steps": 42420, "loss": 0.0439, "lr": 1.7098311970963793e-05, "epoch": 12.842998585572843, "percentage": 64.21, "elapsed_time": "1:38:26", "remaining_time": "0:54:51", "throughput": 4640.65, "total_tokens": 27409984} {"current_steps": 27245, "total_steps": 42420, "loss": 0.1297, "lr": 1.708855393005818e-05, "epoch": 12.845355964167846, "percentage": 64.23, "elapsed_time": "1:38:27", "remaining_time": "0:54:50", "throughput": 4640.7, "total_tokens": 27415200} {"current_steps": 27250, "total_steps": 42420, "loss": 0.236, "lr": 1.7078797228426065e-05, "epoch": 12.847713342762848, "percentage": 64.24, "elapsed_time": "1:38:28", "remaining_time": "0:54:49", "throughput": 4640.76, "total_tokens": 27420000} {"current_steps": 27255, "total_steps": 42420, "loss": 0.1015, "lr": 1.7069041867719085e-05, "epoch": 12.85007072135785, "percentage": 64.25, "elapsed_time": "1:38:29", "remaining_time": "0:54:48", "throughput": 4640.74, "total_tokens": 27424480} {"current_steps": 27260, "total_steps": 42420, "loss": 0.1061, "lr": 1.705928784958865e-05, "epoch": 12.852428099952853, "percentage": 64.26, "elapsed_time": "1:38:30", "remaining_time": "0:54:47", "throughput": 4640.79, "total_tokens": 27429728} {"current_steps": 27265, "total_steps": 42420, "loss": 0.0357, "lr": 1.704953517568596e-05, "epoch": 12.854785478547855, "percentage": 64.27, "elapsed_time": "1:38:31", "remaining_time": "0:54:45", "throughput": 4640.81, "total_tokens": 27434080} {"current_steps": 27270, "total_steps": 42420, "loss": 0.2193, "lr": 1.7039783847661973e-05, "epoch": 12.857142857142858, "percentage": 64.29, "elapsed_time": "1:38:32", "remaining_time": "0:54:44", "throughput": 4640.87, "total_tokens": 27439616} {"current_steps": 27275, "total_steps": 42420, "loss": 0.0445, "lr": 1.703003386716743e-05, "epoch": 12.85950023573786, "percentage": 64.3, "elapsed_time": "1:38:33", "remaining_time": "0:54:43", "throughput": 4640.92, "total_tokens": 27445056} {"current_steps": 27280, "total_steps": 42420, "loss": 0.0505, "lr": 1.7020285235852824e-05, "epoch": 12.861857614332862, "percentage": 64.31, "elapsed_time": "1:38:34", "remaining_time": "0:54:42", "throughput": 4640.95, "total_tokens": 27450176} {"current_steps": 27285, "total_steps": 42420, "loss": 0.0705, "lr": 1.7010537955368438e-05, "epoch": 12.864214992927865, "percentage": 64.32, "elapsed_time": "1:38:35", "remaining_time": "0:54:41", "throughput": 4640.99, "total_tokens": 27455264} {"current_steps": 27290, "total_steps": 42420, "loss": 0.1085, "lr": 1.7000792027364327e-05, "epoch": 12.866572371522867, "percentage": 64.33, "elapsed_time": "1:38:36", "remaining_time": "0:54:40", "throughput": 4640.97, "total_tokens": 27459104} {"current_steps": 27295, "total_steps": 42420, "loss": 0.1372, "lr": 1.6991047453490312e-05, "epoch": 12.86892975011787, "percentage": 64.34, "elapsed_time": "1:38:37", "remaining_time": "0:54:39", "throughput": 4640.99, "total_tokens": 27463936} {"current_steps": 27300, "total_steps": 42420, "loss": 0.0875, "lr": 1.698130423539597e-05, "epoch": 12.871287128712872, "percentage": 64.36, "elapsed_time": "1:38:38", "remaining_time": "0:54:37", "throughput": 4641.01, "total_tokens": 27468320} {"current_steps": 27305, "total_steps": 42420, "loss": 0.1172, "lr": 1.697156237473067e-05, "epoch": 12.873644507307874, "percentage": 64.37, "elapsed_time": "1:38:39", "remaining_time": "0:54:36", "throughput": 4641.02, "total_tokens": 27472544} {"current_steps": 27310, "total_steps": 42420, "loss": 0.0395, "lr": 1.6961821873143553e-05, "epoch": 12.876001885902877, "percentage": 64.38, "elapsed_time": "1:38:40", "remaining_time": "0:54:35", "throughput": 4641.04, "total_tokens": 27477408} {"current_steps": 27315, "total_steps": 42420, "loss": 0.2438, "lr": 1.6952082732283507e-05, "epoch": 12.878359264497877, "percentage": 64.39, "elapsed_time": "1:38:41", "remaining_time": "0:54:34", "throughput": 4641.07, "total_tokens": 27482240} {"current_steps": 27320, "total_steps": 42420, "loss": 0.3395, "lr": 1.694234495379921e-05, "epoch": 12.88071664309288, "percentage": 64.4, "elapsed_time": "1:38:42", "remaining_time": "0:54:33", "throughput": 4641.08, "total_tokens": 27486752} {"current_steps": 27325, "total_steps": 42420, "loss": 0.0494, "lr": 1.69326085393391e-05, "epoch": 12.883074021687882, "percentage": 64.42, "elapsed_time": "1:38:43", "remaining_time": "0:54:32", "throughput": 4641.14, "total_tokens": 27491584} {"current_steps": 27330, "total_steps": 42420, "loss": 0.2484, "lr": 1.692287349055139e-05, "epoch": 12.885431400282885, "percentage": 64.43, "elapsed_time": "1:38:44", "remaining_time": "0:54:31", "throughput": 4641.19, "total_tokens": 27496608} {"current_steps": 27335, "total_steps": 42420, "loss": 0.1434, "lr": 1.6913139809084054e-05, "epoch": 12.887788778877887, "percentage": 64.44, "elapsed_time": "1:38:45", "remaining_time": "0:54:30", "throughput": 4641.22, "total_tokens": 27501632} {"current_steps": 27340, "total_steps": 42420, "loss": 0.0232, "lr": 1.6903407496584843e-05, "epoch": 12.89014615747289, "percentage": 64.45, "elapsed_time": "1:38:46", "remaining_time": "0:54:28", "throughput": 4641.24, "total_tokens": 27506784} {"current_steps": 27345, "total_steps": 42420, "loss": 0.0855, "lr": 1.6893676554701272e-05, "epoch": 12.892503536067892, "percentage": 64.46, "elapsed_time": "1:38:47", "remaining_time": "0:54:27", "throughput": 4641.28, "total_tokens": 27511744} {"current_steps": 27350, "total_steps": 42420, "loss": 0.0899, "lr": 1.6883946985080617e-05, "epoch": 12.894860914662894, "percentage": 64.47, "elapsed_time": "1:38:48", "remaining_time": "0:54:26", "throughput": 4641.35, "total_tokens": 27517952} {"current_steps": 27355, "total_steps": 42420, "loss": 0.0524, "lr": 1.687421878936994e-05, "epoch": 12.897218293257897, "percentage": 64.49, "elapsed_time": "1:38:49", "remaining_time": "0:54:25", "throughput": 4641.36, "total_tokens": 27522432} {"current_steps": 27360, "total_steps": 42420, "loss": 0.1111, "lr": 1.6864491969216054e-05, "epoch": 12.899575671852899, "percentage": 64.5, "elapsed_time": "1:38:50", "remaining_time": "0:54:24", "throughput": 4641.38, "total_tokens": 27526688} {"current_steps": 27365, "total_steps": 42420, "loss": 0.1915, "lr": 1.685476652626554e-05, "epoch": 12.901933050447902, "percentage": 64.51, "elapsed_time": "1:38:51", "remaining_time": "0:54:23", "throughput": 4641.43, "total_tokens": 27531424} {"current_steps": 27370, "total_steps": 42420, "loss": 0.1885, "lr": 1.6845042462164758e-05, "epoch": 12.904290429042904, "percentage": 64.52, "elapsed_time": "1:38:52", "remaining_time": "0:54:22", "throughput": 4641.47, "total_tokens": 27536928} {"current_steps": 27375, "total_steps": 42420, "loss": 0.2026, "lr": 1.6835319778559827e-05, "epoch": 12.906647807637906, "percentage": 64.53, "elapsed_time": "1:38:53", "remaining_time": "0:54:21", "throughput": 4641.51, "total_tokens": 27542592} {"current_steps": 27380, "total_steps": 42420, "loss": 0.0257, "lr": 1.6825598477096625e-05, "epoch": 12.909005186232909, "percentage": 64.55, "elapsed_time": "1:38:55", "remaining_time": "0:54:20", "throughput": 4641.56, "total_tokens": 27547712} {"current_steps": 27385, "total_steps": 42420, "loss": 0.0958, "lr": 1.6815878559420805e-05, "epoch": 12.911362564827911, "percentage": 64.56, "elapsed_time": "1:38:55", "remaining_time": "0:54:18", "throughput": 4641.57, "total_tokens": 27552128} {"current_steps": 27390, "total_steps": 42420, "loss": 0.0346, "lr": 1.680616002717779e-05, "epoch": 12.913719943422914, "percentage": 64.57, "elapsed_time": "1:38:56", "remaining_time": "0:54:17", "throughput": 4641.62, "total_tokens": 27557184} {"current_steps": 27395, "total_steps": 42420, "loss": 0.0392, "lr": 1.679644288201276e-05, "epoch": 12.916077322017916, "percentage": 64.58, "elapsed_time": "1:38:58", "remaining_time": "0:54:16", "throughput": 4641.68, "total_tokens": 27562464} {"current_steps": 27400, "total_steps": 42420, "loss": 0.209, "lr": 1.6786727125570663e-05, "epoch": 12.918434700612918, "percentage": 64.59, "elapsed_time": "1:38:59", "remaining_time": "0:54:15", "throughput": 4641.7, "total_tokens": 27567680} {"current_steps": 27405, "total_steps": 42420, "loss": 0.0739, "lr": 1.6777012759496204e-05, "epoch": 12.92079207920792, "percentage": 64.6, "elapsed_time": "1:39:00", "remaining_time": "0:54:14", "throughput": 4641.78, "total_tokens": 27573792} {"current_steps": 27410, "total_steps": 42420, "loss": 0.1299, "lr": 1.6767299785433877e-05, "epoch": 12.923149457802923, "percentage": 64.62, "elapsed_time": "1:39:01", "remaining_time": "0:54:13", "throughput": 4641.87, "total_tokens": 27580512} {"current_steps": 27415, "total_steps": 42420, "loss": 0.0668, "lr": 1.6757588205027907e-05, "epoch": 12.925506836397926, "percentage": 64.63, "elapsed_time": "1:39:02", "remaining_time": "0:54:12", "throughput": 4641.91, "total_tokens": 27585504} {"current_steps": 27420, "total_steps": 42420, "loss": 0.0589, "lr": 1.674787801992231e-05, "epoch": 12.927864214992928, "percentage": 64.64, "elapsed_time": "1:39:03", "remaining_time": "0:54:11", "throughput": 4641.95, "total_tokens": 27590464} {"current_steps": 27425, "total_steps": 42420, "loss": 0.0093, "lr": 1.6738169231760842e-05, "epoch": 12.93022159358793, "percentage": 64.65, "elapsed_time": "1:39:04", "remaining_time": "0:54:10", "throughput": 4642.0, "total_tokens": 27596000} {"current_steps": 27430, "total_steps": 42420, "loss": 0.0926, "lr": 1.672846184218705e-05, "epoch": 12.932578972182933, "percentage": 64.66, "elapsed_time": "1:39:05", "remaining_time": "0:54:09", "throughput": 4642.06, "total_tokens": 27601280} {"current_steps": 27435, "total_steps": 42420, "loss": 0.1627, "lr": 1.671875585284422e-05, "epoch": 12.934936350777935, "percentage": 64.67, "elapsed_time": "1:39:06", "remaining_time": "0:54:08", "throughput": 4642.08, "total_tokens": 27606144} {"current_steps": 27440, "total_steps": 42420, "loss": 0.2003, "lr": 1.6709051265375424e-05, "epoch": 12.937293729372938, "percentage": 64.69, "elapsed_time": "1:39:07", "remaining_time": "0:54:07", "throughput": 4642.09, "total_tokens": 27610592} {"current_steps": 27445, "total_steps": 42420, "loss": 0.1029, "lr": 1.669934808142347e-05, "epoch": 12.93965110796794, "percentage": 64.7, "elapsed_time": "1:39:08", "remaining_time": "0:54:05", "throughput": 4642.12, "total_tokens": 27615328} {"current_steps": 27450, "total_steps": 42420, "loss": 0.0537, "lr": 1.668964630263095e-05, "epoch": 12.942008486562942, "percentage": 64.71, "elapsed_time": "1:39:09", "remaining_time": "0:54:04", "throughput": 4642.15, "total_tokens": 27620032} {"current_steps": 27455, "total_steps": 42420, "loss": 0.1227, "lr": 1.667994593064021e-05, "epoch": 12.944365865157945, "percentage": 64.72, "elapsed_time": "1:39:10", "remaining_time": "0:54:03", "throughput": 4642.19, "total_tokens": 27625504} {"current_steps": 27460, "total_steps": 42420, "loss": 0.1924, "lr": 1.6670246967093367e-05, "epoch": 12.946723243752947, "percentage": 64.73, "elapsed_time": "1:39:11", "remaining_time": "0:54:02", "throughput": 4642.12, "total_tokens": 27629440} {"current_steps": 27465, "total_steps": 42420, "loss": 0.118, "lr": 1.666054941363227e-05, "epoch": 12.94908062234795, "percentage": 64.75, "elapsed_time": "1:39:12", "remaining_time": "0:54:01", "throughput": 4642.16, "total_tokens": 27634528} {"current_steps": 27470, "total_steps": 42420, "loss": 0.0401, "lr": 1.6650853271898564e-05, "epoch": 12.951438000942952, "percentage": 64.76, "elapsed_time": "1:39:13", "remaining_time": "0:54:00", "throughput": 4642.19, "total_tokens": 27639328} {"current_steps": 27475, "total_steps": 42420, "loss": 0.2022, "lr": 1.6641158543533637e-05, "epoch": 12.953795379537954, "percentage": 64.77, "elapsed_time": "1:39:14", "remaining_time": "0:53:59", "throughput": 4642.23, "total_tokens": 27644224} {"current_steps": 27480, "total_steps": 42420, "loss": 0.0758, "lr": 1.663146523017865e-05, "epoch": 12.956152758132957, "percentage": 64.78, "elapsed_time": "1:39:15", "remaining_time": "0:53:58", "throughput": 4642.28, "total_tokens": 27649376} {"current_steps": 27485, "total_steps": 42420, "loss": 0.1526, "lr": 1.6621773333474507e-05, "epoch": 12.95851013672796, "percentage": 64.79, "elapsed_time": "1:39:17", "remaining_time": "0:53:57", "throughput": 4642.32, "total_tokens": 27654720} {"current_steps": 27490, "total_steps": 42420, "loss": 0.1885, "lr": 1.6612082855061878e-05, "epoch": 12.960867515322962, "percentage": 64.8, "elapsed_time": "1:39:18", "remaining_time": "0:53:55", "throughput": 4642.33, "total_tokens": 27659520} {"current_steps": 27495, "total_steps": 42420, "loss": 0.1171, "lr": 1.6602393796581205e-05, "epoch": 12.963224893917964, "percentage": 64.82, "elapsed_time": "1:39:19", "remaining_time": "0:53:54", "throughput": 4642.36, "total_tokens": 27664128} {"current_steps": 27500, "total_steps": 42420, "loss": 0.2103, "lr": 1.6592706159672688e-05, "epoch": 12.965582272512966, "percentage": 64.83, "elapsed_time": "1:39:20", "remaining_time": "0:53:53", "throughput": 4642.41, "total_tokens": 27669408} {"current_steps": 27505, "total_steps": 42420, "loss": 0.0321, "lr": 1.6583019945976264e-05, "epoch": 12.967939651107969, "percentage": 64.84, "elapsed_time": "1:39:21", "remaining_time": "0:53:52", "throughput": 4642.41, "total_tokens": 27673600} {"current_steps": 27510, "total_steps": 42420, "loss": 0.047, "lr": 1.6573335157131647e-05, "epoch": 12.97029702970297, "percentage": 64.85, "elapsed_time": "1:39:21", "remaining_time": "0:53:51", "throughput": 4642.44, "total_tokens": 27678080} {"current_steps": 27515, "total_steps": 42420, "loss": 0.1832, "lr": 1.6563651794778317e-05, "epoch": 12.972654408297974, "percentage": 64.86, "elapsed_time": "1:39:23", "remaining_time": "0:53:50", "throughput": 4642.48, "total_tokens": 27683200} {"current_steps": 27520, "total_steps": 42420, "loss": 0.0805, "lr": 1.65539698605555e-05, "epoch": 12.975011786892974, "percentage": 64.88, "elapsed_time": "1:39:24", "remaining_time": "0:53:49", "throughput": 4642.51, "total_tokens": 27688256} {"current_steps": 27525, "total_steps": 42420, "loss": 0.0862, "lr": 1.6544289356102172e-05, "epoch": 12.977369165487977, "percentage": 64.89, "elapsed_time": "1:39:25", "remaining_time": "0:53:48", "throughput": 4642.57, "total_tokens": 27693984} {"current_steps": 27530, "total_steps": 42420, "loss": 0.2051, "lr": 1.653461028305709e-05, "epoch": 12.979726544082979, "percentage": 64.9, "elapsed_time": "1:39:26", "remaining_time": "0:53:46", "throughput": 4642.57, "total_tokens": 27698656} {"current_steps": 27535, "total_steps": 42420, "loss": 0.1017, "lr": 1.6524932643058753e-05, "epoch": 12.982083922677981, "percentage": 64.91, "elapsed_time": "1:39:27", "remaining_time": "0:53:45", "throughput": 4642.58, "total_tokens": 27702880} {"current_steps": 27540, "total_steps": 42420, "loss": 0.0374, "lr": 1.6515256437745425e-05, "epoch": 12.984441301272984, "percentage": 64.92, "elapsed_time": "1:39:28", "remaining_time": "0:53:44", "throughput": 4642.61, "total_tokens": 27707616} {"current_steps": 27545, "total_steps": 42420, "loss": 0.1796, "lr": 1.6505581668755112e-05, "epoch": 12.986798679867986, "percentage": 64.93, "elapsed_time": "1:39:29", "remaining_time": "0:53:43", "throughput": 4642.65, "total_tokens": 27712288} {"current_steps": 27550, "total_steps": 42420, "loss": 0.1706, "lr": 1.64959083377256e-05, "epoch": 12.989156058462989, "percentage": 64.95, "elapsed_time": "1:39:30", "remaining_time": "0:53:42", "throughput": 4642.69, "total_tokens": 27716928} {"current_steps": 27555, "total_steps": 42420, "loss": 0.0309, "lr": 1.6486236446294413e-05, "epoch": 12.991513437057991, "percentage": 64.96, "elapsed_time": "1:39:30", "remaining_time": "0:53:41", "throughput": 4642.72, "total_tokens": 27721152} {"current_steps": 27560, "total_steps": 42420, "loss": 0.041, "lr": 1.6476565996098845e-05, "epoch": 12.993870815652993, "percentage": 64.97, "elapsed_time": "1:39:32", "remaining_time": "0:53:40", "throughput": 4642.78, "total_tokens": 27727168} {"current_steps": 27565, "total_steps": 42420, "loss": 0.0089, "lr": 1.6466896988775927e-05, "epoch": 12.996228194247996, "percentage": 64.98, "elapsed_time": "1:39:33", "remaining_time": "0:53:38", "throughput": 4642.81, "total_tokens": 27731968} {"current_steps": 27570, "total_steps": 42420, "loss": 0.0795, "lr": 1.6457229425962466e-05, "epoch": 12.998585572842998, "percentage": 64.99, "elapsed_time": "1:39:33", "remaining_time": "0:53:37", "throughput": 4642.82, "total_tokens": 27736064} {"current_steps": 27573, "total_steps": 42420, "eval_loss": 0.1524803191423416, "epoch": 13.0, "percentage": 65.0, "elapsed_time": "1:39:49", "remaining_time": "0:53:45", "throughput": 4631.1, "total_tokens": 27739072} {"current_steps": 27575, "total_steps": 42420, "loss": 0.1305, "lr": 1.6447563309295016e-05, "epoch": 13.000942951438, "percentage": 65.0, "elapsed_time": "1:39:51", "remaining_time": "0:53:45", "throughput": 4629.91, "total_tokens": 27741632} {"current_steps": 27580, "total_steps": 42420, "loss": 0.0888, "lr": 1.6437898640409894e-05, "epoch": 13.003300330033003, "percentage": 65.02, "elapsed_time": "1:39:52", "remaining_time": "0:53:44", "throughput": 4629.98, "total_tokens": 27747392} {"current_steps": 27585, "total_steps": 42420, "loss": 0.1499, "lr": 1.6428235420943146e-05, "epoch": 13.005657708628005, "percentage": 65.03, "elapsed_time": "1:39:53", "remaining_time": "0:53:43", "throughput": 4629.99, "total_tokens": 27751808} {"current_steps": 27590, "total_steps": 42420, "loss": 0.0521, "lr": 1.6418573652530606e-05, "epoch": 13.008015087223008, "percentage": 65.04, "elapsed_time": "1:39:54", "remaining_time": "0:53:42", "throughput": 4630.03, "total_tokens": 27756448} {"current_steps": 27595, "total_steps": 42420, "loss": 0.0961, "lr": 1.6408913336807835e-05, "epoch": 13.01037246581801, "percentage": 65.05, "elapsed_time": "1:39:55", "remaining_time": "0:53:41", "throughput": 4630.05, "total_tokens": 27761216} {"current_steps": 27600, "total_steps": 42420, "loss": 0.1868, "lr": 1.639925447541018e-05, "epoch": 13.012729844413013, "percentage": 65.06, "elapsed_time": "1:39:56", "remaining_time": "0:53:39", "throughput": 4630.03, "total_tokens": 27765120} {"current_steps": 27605, "total_steps": 42420, "loss": 0.0868, "lr": 1.6389597069972702e-05, "epoch": 13.015087223008015, "percentage": 65.08, "elapsed_time": "1:39:57", "remaining_time": "0:53:38", "throughput": 4630.07, "total_tokens": 27770336} {"current_steps": 27610, "total_steps": 42420, "loss": 0.1219, "lr": 1.6379941122130243e-05, "epoch": 13.017444601603017, "percentage": 65.09, "elapsed_time": "1:39:58", "remaining_time": "0:53:37", "throughput": 4630.1, "total_tokens": 27775104} {"current_steps": 27615, "total_steps": 42420, "loss": 0.0498, "lr": 1.637028663351739e-05, "epoch": 13.01980198019802, "percentage": 65.1, "elapsed_time": "1:39:59", "remaining_time": "0:53:36", "throughput": 4630.12, "total_tokens": 27779872} {"current_steps": 27620, "total_steps": 42420, "loss": 0.0262, "lr": 1.6360633605768495e-05, "epoch": 13.022159358793022, "percentage": 65.11, "elapsed_time": "1:40:00", "remaining_time": "0:53:35", "throughput": 4630.1, "total_tokens": 27783584} {"current_steps": 27625, "total_steps": 42420, "loss": 0.0574, "lr": 1.635098204051764e-05, "epoch": 13.024516737388025, "percentage": 65.12, "elapsed_time": "1:40:01", "remaining_time": "0:53:34", "throughput": 4630.11, "total_tokens": 27787712} {"current_steps": 27630, "total_steps": 42420, "loss": 0.197, "lr": 1.634133193939866e-05, "epoch": 13.026874115983027, "percentage": 65.13, "elapsed_time": "1:40:02", "remaining_time": "0:53:33", "throughput": 4630.15, "total_tokens": 27792352} {"current_steps": 27635, "total_steps": 42420, "loss": 0.128, "lr": 1.6331683304045192e-05, "epoch": 13.02923149457803, "percentage": 65.15, "elapsed_time": "1:40:03", "remaining_time": "0:53:31", "throughput": 4630.2, "total_tokens": 27797472} {"current_steps": 27640, "total_steps": 42420, "loss": 0.1246, "lr": 1.6322036136090547e-05, "epoch": 13.031588873173032, "percentage": 65.16, "elapsed_time": "1:40:04", "remaining_time": "0:53:30", "throughput": 4630.24, "total_tokens": 27802848} {"current_steps": 27645, "total_steps": 42420, "loss": 0.1853, "lr": 1.6312390437167835e-05, "epoch": 13.033946251768034, "percentage": 65.17, "elapsed_time": "1:40:05", "remaining_time": "0:53:29", "throughput": 4630.28, "total_tokens": 27807968} {"current_steps": 27650, "total_steps": 42420, "loss": 0.201, "lr": 1.6302746208909924e-05, "epoch": 13.036303630363037, "percentage": 65.18, "elapsed_time": "1:40:06", "remaining_time": "0:53:28", "throughput": 4630.3, "total_tokens": 27813088} {"current_steps": 27655, "total_steps": 42420, "loss": 0.0723, "lr": 1.6293103452949405e-05, "epoch": 13.038661008958039, "percentage": 65.19, "elapsed_time": "1:40:07", "remaining_time": "0:53:27", "throughput": 4630.35, "total_tokens": 27818272} {"current_steps": 27660, "total_steps": 42420, "loss": 0.0823, "lr": 1.6283462170918635e-05, "epoch": 13.041018387553041, "percentage": 65.21, "elapsed_time": "1:40:08", "remaining_time": "0:53:26", "throughput": 4630.34, "total_tokens": 27822528} {"current_steps": 27665, "total_steps": 42420, "loss": 0.0576, "lr": 1.627382236444972e-05, "epoch": 13.043375766148044, "percentage": 65.22, "elapsed_time": "1:40:10", "remaining_time": "0:53:25", "throughput": 4630.36, "total_tokens": 27828704} {"current_steps": 27670, "total_steps": 42420, "loss": 0.0976, "lr": 1.6264184035174523e-05, "epoch": 13.045733144743046, "percentage": 65.23, "elapsed_time": "1:40:11", "remaining_time": "0:53:24", "throughput": 4630.38, "total_tokens": 27833920} {"current_steps": 27675, "total_steps": 42420, "loss": 0.0719, "lr": 1.625454718472464e-05, "epoch": 13.048090523338049, "percentage": 65.24, "elapsed_time": "1:40:12", "remaining_time": "0:53:23", "throughput": 4630.36, "total_tokens": 27838624} {"current_steps": 27680, "total_steps": 42420, "loss": 0.1779, "lr": 1.624491181473142e-05, "epoch": 13.050447901933051, "percentage": 65.25, "elapsed_time": "1:40:13", "remaining_time": "0:53:22", "throughput": 4630.42, "total_tokens": 27844864} {"current_steps": 27685, "total_steps": 42420, "loss": 0.0489, "lr": 1.6235277926825986e-05, "epoch": 13.052805280528053, "percentage": 65.26, "elapsed_time": "1:40:14", "remaining_time": "0:53:21", "throughput": 4630.42, "total_tokens": 27849312} {"current_steps": 27690, "total_steps": 42420, "loss": 0.0836, "lr": 1.622564552263919e-05, "epoch": 13.055162659123056, "percentage": 65.28, "elapsed_time": "1:40:15", "remaining_time": "0:53:19", "throughput": 4630.44, "total_tokens": 27854016} {"current_steps": 27695, "total_steps": 42420, "loss": 0.0712, "lr": 1.6216014603801616e-05, "epoch": 13.057520037718058, "percentage": 65.29, "elapsed_time": "1:40:16", "remaining_time": "0:53:18", "throughput": 4630.45, "total_tokens": 27858880} {"current_steps": 27700, "total_steps": 42420, "loss": 0.1705, "lr": 1.6206385171943626e-05, "epoch": 13.05987741631306, "percentage": 65.3, "elapsed_time": "1:40:17", "remaining_time": "0:53:17", "throughput": 4630.51, "total_tokens": 27864320} {"current_steps": 27705, "total_steps": 42420, "loss": 0.1502, "lr": 1.619675722869532e-05, "epoch": 13.062234794908063, "percentage": 65.31, "elapsed_time": "1:40:18", "remaining_time": "0:53:16", "throughput": 4630.55, "total_tokens": 27870144} {"current_steps": 27710, "total_steps": 42420, "loss": 0.0798, "lr": 1.6187130775686554e-05, "epoch": 13.064592173503065, "percentage": 65.32, "elapsed_time": "1:40:19", "remaining_time": "0:53:15", "throughput": 4630.55, "total_tokens": 27874624} {"current_steps": 27715, "total_steps": 42420, "loss": 0.05, "lr": 1.6177505814546902e-05, "epoch": 13.066949552098066, "percentage": 65.33, "elapsed_time": "1:40:20", "remaining_time": "0:53:14", "throughput": 4630.56, "total_tokens": 27879840} {"current_steps": 27720, "total_steps": 42420, "loss": 0.2073, "lr": 1.616788234690572e-05, "epoch": 13.069306930693068, "percentage": 65.35, "elapsed_time": "1:40:21", "remaining_time": "0:53:13", "throughput": 4630.57, "total_tokens": 27884576} {"current_steps": 27725, "total_steps": 42420, "loss": 0.0986, "lr": 1.6158260374392098e-05, "epoch": 13.07166430928807, "percentage": 65.36, "elapsed_time": "1:40:22", "remaining_time": "0:53:12", "throughput": 4630.55, "total_tokens": 27888416} {"current_steps": 27730, "total_steps": 42420, "loss": 0.1681, "lr": 1.6148639898634875e-05, "epoch": 13.074021687883073, "percentage": 65.37, "elapsed_time": "1:40:23", "remaining_time": "0:53:11", "throughput": 4630.59, "total_tokens": 27893856} {"current_steps": 27735, "total_steps": 42420, "loss": 0.0213, "lr": 1.6139020921262626e-05, "epoch": 13.076379066478076, "percentage": 65.38, "elapsed_time": "1:40:24", "remaining_time": "0:53:09", "throughput": 4630.61, "total_tokens": 27898464} {"current_steps": 27740, "total_steps": 42420, "loss": 0.0984, "lr": 1.6129403443903683e-05, "epoch": 13.078736445073078, "percentage": 65.39, "elapsed_time": "1:40:25", "remaining_time": "0:53:08", "throughput": 4630.67, "total_tokens": 27904224} {"current_steps": 27745, "total_steps": 42420, "loss": 0.0889, "lr": 1.611978746818612e-05, "epoch": 13.08109382366808, "percentage": 65.41, "elapsed_time": "1:40:26", "remaining_time": "0:53:07", "throughput": 4630.7, "total_tokens": 27909120} {"current_steps": 27750, "total_steps": 42420, "loss": 0.042, "lr": 1.611017299573777e-05, "epoch": 13.083451202263083, "percentage": 65.42, "elapsed_time": "1:40:28", "remaining_time": "0:53:06", "throughput": 4630.75, "total_tokens": 27914368} {"current_steps": 27755, "total_steps": 42420, "loss": 0.04, "lr": 1.6100560028186184e-05, "epoch": 13.085808580858085, "percentage": 65.43, "elapsed_time": "1:40:28", "remaining_time": "0:53:05", "throughput": 4630.77, "total_tokens": 27918784} {"current_steps": 27760, "total_steps": 42420, "loss": 0.2318, "lr": 1.6090948567158682e-05, "epoch": 13.088165959453088, "percentage": 65.44, "elapsed_time": "1:40:30", "remaining_time": "0:53:04", "throughput": 4630.82, "total_tokens": 27923904} {"current_steps": 27765, "total_steps": 42420, "loss": 0.0295, "lr": 1.6081338614282322e-05, "epoch": 13.09052333804809, "percentage": 65.45, "elapsed_time": "1:40:30", "remaining_time": "0:53:03", "throughput": 4630.84, "total_tokens": 27928352} {"current_steps": 27770, "total_steps": 42420, "loss": 0.0292, "lr": 1.6071730171183908e-05, "epoch": 13.092880716643092, "percentage": 65.46, "elapsed_time": "1:40:31", "remaining_time": "0:53:02", "throughput": 4630.86, "total_tokens": 27932960} {"current_steps": 27775, "total_steps": 42420, "loss": 0.2908, "lr": 1.6062123239489973e-05, "epoch": 13.095238095238095, "percentage": 65.48, "elapsed_time": "1:40:32", "remaining_time": "0:53:00", "throughput": 4630.9, "total_tokens": 27937568} {"current_steps": 27780, "total_steps": 42420, "loss": 0.136, "lr": 1.6052517820826824e-05, "epoch": 13.097595473833097, "percentage": 65.49, "elapsed_time": "1:40:33", "remaining_time": "0:52:59", "throughput": 4630.95, "total_tokens": 27942944} {"current_steps": 27785, "total_steps": 42420, "loss": 0.0244, "lr": 1.6042913916820484e-05, "epoch": 13.0999528524281, "percentage": 65.5, "elapsed_time": "1:40:34", "remaining_time": "0:52:58", "throughput": 4630.93, "total_tokens": 27947552} {"current_steps": 27790, "total_steps": 42420, "loss": 0.1135, "lr": 1.6033311529096743e-05, "epoch": 13.102310231023102, "percentage": 65.51, "elapsed_time": "1:40:36", "remaining_time": "0:52:57", "throughput": 4630.94, "total_tokens": 27952448} {"current_steps": 27795, "total_steps": 42420, "loss": 0.0655, "lr": 1.602371065928111e-05, "epoch": 13.104667609618105, "percentage": 65.52, "elapsed_time": "1:40:37", "remaining_time": "0:52:56", "throughput": 4630.98, "total_tokens": 27958080} {"current_steps": 27800, "total_steps": 42420, "loss": 0.1675, "lr": 1.601411130899885e-05, "epoch": 13.107024988213107, "percentage": 65.54, "elapsed_time": "1:40:38", "remaining_time": "0:52:55", "throughput": 4631.01, "total_tokens": 27962912} {"current_steps": 27805, "total_steps": 42420, "loss": 0.0574, "lr": 1.6004513479874974e-05, "epoch": 13.10938236680811, "percentage": 65.55, "elapsed_time": "1:40:39", "remaining_time": "0:52:54", "throughput": 4631.06, "total_tokens": 27968544} {"current_steps": 27810, "total_steps": 42420, "loss": 0.0793, "lr": 1.599491717353424e-05, "epoch": 13.111739745403112, "percentage": 65.56, "elapsed_time": "1:40:40", "remaining_time": "0:52:53", "throughput": 4631.12, "total_tokens": 27974816} {"current_steps": 27815, "total_steps": 42420, "loss": 0.0814, "lr": 1.5985322391601124e-05, "epoch": 13.114097123998114, "percentage": 65.57, "elapsed_time": "1:40:41", "remaining_time": "0:52:52", "throughput": 4631.14, "total_tokens": 27979104} {"current_steps": 27820, "total_steps": 42420, "loss": 0.0488, "lr": 1.5975729135699865e-05, "epoch": 13.116454502593117, "percentage": 65.58, "elapsed_time": "1:40:42", "remaining_time": "0:52:51", "throughput": 4631.12, "total_tokens": 27983136} {"current_steps": 27825, "total_steps": 42420, "loss": 0.0378, "lr": 1.596613740745444e-05, "epoch": 13.118811881188119, "percentage": 65.59, "elapsed_time": "1:40:43", "remaining_time": "0:52:50", "throughput": 4631.17, "total_tokens": 27988640} {"current_steps": 27830, "total_steps": 42420, "loss": 0.0393, "lr": 1.5956547208488572e-05, "epoch": 13.121169259783121, "percentage": 65.61, "elapsed_time": "1:40:44", "remaining_time": "0:52:48", "throughput": 4631.21, "total_tokens": 27993984} {"current_steps": 27835, "total_steps": 42420, "loss": 0.1196, "lr": 1.594695854042571e-05, "epoch": 13.123526638378124, "percentage": 65.62, "elapsed_time": "1:40:45", "remaining_time": "0:52:47", "throughput": 4631.22, "total_tokens": 27998624} {"current_steps": 27840, "total_steps": 42420, "loss": 0.1115, "lr": 1.5937371404889052e-05, "epoch": 13.125884016973126, "percentage": 65.63, "elapsed_time": "1:40:46", "remaining_time": "0:52:46", "throughput": 4631.24, "total_tokens": 28003168} {"current_steps": 27845, "total_steps": 42420, "loss": 0.0427, "lr": 1.592778580350154e-05, "epoch": 13.128241395568129, "percentage": 65.64, "elapsed_time": "1:40:47", "remaining_time": "0:52:45", "throughput": 4631.25, "total_tokens": 28007584} {"current_steps": 27850, "total_steps": 42420, "loss": 0.1095, "lr": 1.5918201737885863e-05, "epoch": 13.130598774163131, "percentage": 65.65, "elapsed_time": "1:40:48", "remaining_time": "0:52:44", "throughput": 4631.3, "total_tokens": 28013216} {"current_steps": 27855, "total_steps": 42420, "loss": 0.254, "lr": 1.5908619209664423e-05, "epoch": 13.132956152758133, "percentage": 65.66, "elapsed_time": "1:40:49", "remaining_time": "0:52:43", "throughput": 4631.33, "total_tokens": 28017824} {"current_steps": 27860, "total_steps": 42420, "loss": 0.0356, "lr": 1.58990382204594e-05, "epoch": 13.135313531353136, "percentage": 65.68, "elapsed_time": "1:40:50", "remaining_time": "0:52:42", "throughput": 4631.37, "total_tokens": 28022976} {"current_steps": 27865, "total_steps": 42420, "loss": 0.1085, "lr": 1.5889458771892667e-05, "epoch": 13.137670909948138, "percentage": 65.69, "elapsed_time": "1:40:51", "remaining_time": "0:52:41", "throughput": 4631.39, "total_tokens": 28027552} {"current_steps": 27870, "total_steps": 42420, "loss": 0.153, "lr": 1.5879880865585878e-05, "epoch": 13.14002828854314, "percentage": 65.7, "elapsed_time": "1:40:52", "remaining_time": "0:52:39", "throughput": 4631.4, "total_tokens": 28031872} {"current_steps": 27875, "total_steps": 42420, "loss": 0.0704, "lr": 1.5870304503160407e-05, "epoch": 13.142385667138143, "percentage": 65.71, "elapsed_time": "1:40:53", "remaining_time": "0:52:38", "throughput": 4631.44, "total_tokens": 28037152} {"current_steps": 27880, "total_steps": 42420, "loss": 0.0815, "lr": 1.5860729686237378e-05, "epoch": 13.144743045733145, "percentage": 65.72, "elapsed_time": "1:40:54", "remaining_time": "0:52:37", "throughput": 4631.48, "total_tokens": 28042912} {"current_steps": 27885, "total_steps": 42420, "loss": 0.094, "lr": 1.585115641643763e-05, "epoch": 13.147100424328148, "percentage": 65.74, "elapsed_time": "1:40:56", "remaining_time": "0:52:36", "throughput": 4631.55, "total_tokens": 28048928} {"current_steps": 27890, "total_steps": 42420, "loss": 0.0284, "lr": 1.584158469538176e-05, "epoch": 13.14945780292315, "percentage": 65.75, "elapsed_time": "1:40:57", "remaining_time": "0:52:35", "throughput": 4631.59, "total_tokens": 28054112} {"current_steps": 27895, "total_steps": 42420, "loss": 0.2265, "lr": 1.5832014524690102e-05, "epoch": 13.151815181518153, "percentage": 65.76, "elapsed_time": "1:40:58", "remaining_time": "0:52:34", "throughput": 4631.62, "total_tokens": 28059488} {"current_steps": 27900, "total_steps": 42420, "loss": 0.0527, "lr": 1.582244590598273e-05, "epoch": 13.154172560113155, "percentage": 65.77, "elapsed_time": "1:40:59", "remaining_time": "0:52:33", "throughput": 4631.67, "total_tokens": 28065056} {"current_steps": 27905, "total_steps": 42420, "loss": 0.3188, "lr": 1.581287884087943e-05, "epoch": 13.156529938708157, "percentage": 65.78, "elapsed_time": "1:41:00", "remaining_time": "0:52:32", "throughput": 4631.73, "total_tokens": 28071584} {"current_steps": 27910, "total_steps": 42420, "loss": 0.0499, "lr": 1.5803313330999758e-05, "epoch": 13.15888731730316, "percentage": 65.79, "elapsed_time": "1:41:01", "remaining_time": "0:52:31", "throughput": 4631.75, "total_tokens": 28075968} {"current_steps": 27915, "total_steps": 42420, "loss": 0.052, "lr": 1.5793749377962986e-05, "epoch": 13.16124469589816, "percentage": 65.81, "elapsed_time": "1:41:02", "remaining_time": "0:52:30", "throughput": 4631.79, "total_tokens": 28080992} {"current_steps": 27920, "total_steps": 42420, "loss": 0.03, "lr": 1.5784186983388134e-05, "epoch": 13.163602074493163, "percentage": 65.82, "elapsed_time": "1:41:03", "remaining_time": "0:52:29", "throughput": 4631.8, "total_tokens": 28085280} {"current_steps": 27925, "total_steps": 42420, "loss": 0.2594, "lr": 1.577462614889395e-05, "epoch": 13.165959453088165, "percentage": 65.83, "elapsed_time": "1:41:04", "remaining_time": "0:52:28", "throughput": 4631.84, "total_tokens": 28090816} {"current_steps": 27930, "total_steps": 42420, "loss": 0.0496, "lr": 1.5765066876098916e-05, "epoch": 13.168316831683168, "percentage": 65.84, "elapsed_time": "1:41:05", "remaining_time": "0:52:26", "throughput": 4631.83, "total_tokens": 28095168} {"current_steps": 27935, "total_steps": 42420, "loss": 0.0316, "lr": 1.5755509166621264e-05, "epoch": 13.17067421027817, "percentage": 65.85, "elapsed_time": "1:41:06", "remaining_time": "0:52:25", "throughput": 4631.84, "total_tokens": 28099776} {"current_steps": 27940, "total_steps": 42420, "loss": 0.1029, "lr": 1.574595302207895e-05, "epoch": 13.173031588873172, "percentage": 65.87, "elapsed_time": "1:41:07", "remaining_time": "0:52:24", "throughput": 4631.85, "total_tokens": 28104352} {"current_steps": 27945, "total_steps": 42420, "loss": 0.1616, "lr": 1.573639844408966e-05, "epoch": 13.175388967468175, "percentage": 65.88, "elapsed_time": "1:41:08", "remaining_time": "0:52:23", "throughput": 4631.85, "total_tokens": 28108480} {"current_steps": 27950, "total_steps": 42420, "loss": 0.2537, "lr": 1.5726845434270827e-05, "epoch": 13.177746346063177, "percentage": 65.89, "elapsed_time": "1:41:09", "remaining_time": "0:52:22", "throughput": 4631.88, "total_tokens": 28113152} {"current_steps": 27955, "total_steps": 42420, "loss": 0.0498, "lr": 1.571729399423961e-05, "epoch": 13.18010372465818, "percentage": 65.9, "elapsed_time": "1:41:10", "remaining_time": "0:52:21", "throughput": 4631.94, "total_tokens": 28118720} {"current_steps": 27960, "total_steps": 42420, "loss": 0.148, "lr": 1.5707744125612915e-05, "epoch": 13.182461103253182, "percentage": 65.91, "elapsed_time": "1:41:11", "remaining_time": "0:52:20", "throughput": 4632.0, "total_tokens": 28124512} {"current_steps": 27965, "total_steps": 42420, "loss": 0.1151, "lr": 1.5698195830007363e-05, "epoch": 13.184818481848184, "percentage": 65.92, "elapsed_time": "1:41:13", "remaining_time": "0:52:19", "throughput": 4632.04, "total_tokens": 28130528} {"current_steps": 27970, "total_steps": 42420, "loss": 0.1705, "lr": 1.568864910903932e-05, "epoch": 13.187175860443187, "percentage": 65.94, "elapsed_time": "1:41:13", "remaining_time": "0:52:17", "throughput": 4632.06, "total_tokens": 28135040} {"current_steps": 27975, "total_steps": 42420, "loss": 0.0648, "lr": 1.5679103964324884e-05, "epoch": 13.18953323903819, "percentage": 65.95, "elapsed_time": "1:41:15", "remaining_time": "0:52:16", "throughput": 4632.1, "total_tokens": 28140096} {"current_steps": 27980, "total_steps": 42420, "loss": 0.0949, "lr": 1.5669560397479894e-05, "epoch": 13.191890617633192, "percentage": 65.96, "elapsed_time": "1:41:16", "remaining_time": "0:52:15", "throughput": 4632.16, "total_tokens": 28145248} {"current_steps": 27985, "total_steps": 42420, "loss": 0.2867, "lr": 1.56600184101199e-05, "epoch": 13.194247996228194, "percentage": 65.97, "elapsed_time": "1:41:16", "remaining_time": "0:52:14", "throughput": 4632.18, "total_tokens": 28149696} {"current_steps": 27990, "total_steps": 42420, "loss": 0.2572, "lr": 1.565047800386021e-05, "epoch": 13.196605374823196, "percentage": 65.98, "elapsed_time": "1:41:18", "remaining_time": "0:52:13", "throughput": 4632.22, "total_tokens": 28155488} {"current_steps": 27995, "total_steps": 42420, "loss": 0.0817, "lr": 1.5640939180315843e-05, "epoch": 13.198962753418199, "percentage": 65.99, "elapsed_time": "1:41:19", "remaining_time": "0:52:12", "throughput": 4632.2, "total_tokens": 28160000} {"current_steps": 28000, "total_steps": 42420, "loss": 0.0188, "lr": 1.563140194110157e-05, "epoch": 13.201320132013201, "percentage": 66.01, "elapsed_time": "1:41:20", "remaining_time": "0:52:11", "throughput": 4632.27, "total_tokens": 28165920} {"current_steps": 28005, "total_steps": 42420, "loss": 0.1451, "lr": 1.5621866287831872e-05, "epoch": 13.203677510608204, "percentage": 66.02, "elapsed_time": "1:41:21", "remaining_time": "0:52:10", "throughput": 4632.31, "total_tokens": 28170880} {"current_steps": 28010, "total_steps": 42420, "loss": 0.1746, "lr": 1.5612332222120984e-05, "epoch": 13.206034889203206, "percentage": 66.03, "elapsed_time": "1:41:22", "remaining_time": "0:52:09", "throughput": 4632.37, "total_tokens": 28176416} {"current_steps": 28015, "total_steps": 42420, "loss": 0.0852, "lr": 1.560279974558286e-05, "epoch": 13.208392267798208, "percentage": 66.04, "elapsed_time": "1:41:23", "remaining_time": "0:52:08", "throughput": 4632.41, "total_tokens": 28181152} {"current_steps": 28020, "total_steps": 42420, "loss": 0.0835, "lr": 1.5593268859831182e-05, "epoch": 13.21074964639321, "percentage": 66.05, "elapsed_time": "1:41:24", "remaining_time": "0:52:06", "throughput": 4632.4, "total_tokens": 28185344} {"current_steps": 28025, "total_steps": 42420, "loss": 0.0802, "lr": 1.5583739566479367e-05, "epoch": 13.213107024988213, "percentage": 66.07, "elapsed_time": "1:41:25", "remaining_time": "0:52:05", "throughput": 4632.42, "total_tokens": 28189568} {"current_steps": 28030, "total_steps": 42420, "loss": 0.2036, "lr": 1.5574211867140565e-05, "epoch": 13.215464403583216, "percentage": 66.08, "elapsed_time": "1:41:26", "remaining_time": "0:52:04", "throughput": 4632.43, "total_tokens": 28193824} {"current_steps": 28035, "total_steps": 42420, "loss": 0.07, "lr": 1.556468576342765e-05, "epoch": 13.217821782178218, "percentage": 66.09, "elapsed_time": "1:41:27", "remaining_time": "0:52:03", "throughput": 4632.46, "total_tokens": 28198336} {"current_steps": 28040, "total_steps": 42420, "loss": 0.0432, "lr": 1.555516125695324e-05, "epoch": 13.22017916077322, "percentage": 66.1, "elapsed_time": "1:41:28", "remaining_time": "0:52:02", "throughput": 4632.49, "total_tokens": 28203776} {"current_steps": 28045, "total_steps": 42420, "loss": 0.0665, "lr": 1.5545638349329662e-05, "epoch": 13.222536539368223, "percentage": 66.11, "elapsed_time": "1:41:29", "remaining_time": "0:52:01", "throughput": 4632.57, "total_tokens": 28210560} {"current_steps": 28050, "total_steps": 42420, "loss": 0.1275, "lr": 1.553611704216898e-05, "epoch": 13.224893917963225, "percentage": 66.12, "elapsed_time": "1:41:30", "remaining_time": "0:52:00", "throughput": 4632.6, "total_tokens": 28215648} {"current_steps": 28055, "total_steps": 42420, "loss": 0.1729, "lr": 1.5526597337083e-05, "epoch": 13.227251296558228, "percentage": 66.14, "elapsed_time": "1:41:31", "remaining_time": "0:51:59", "throughput": 4632.64, "total_tokens": 28220992} {"current_steps": 28060, "total_steps": 42420, "loss": 0.4442, "lr": 1.5517079235683245e-05, "epoch": 13.22960867515323, "percentage": 66.15, "elapsed_time": "1:41:32", "remaining_time": "0:51:57", "throughput": 4632.67, "total_tokens": 28225376} {"current_steps": 28065, "total_steps": 42420, "loss": 0.0737, "lr": 1.550756273958096e-05, "epoch": 13.231966053748232, "percentage": 66.16, "elapsed_time": "1:41:33", "remaining_time": "0:51:56", "throughput": 4632.67, "total_tokens": 28230144} {"current_steps": 28070, "total_steps": 42420, "loss": 0.0715, "lr": 1.549804785038713e-05, "epoch": 13.234323432343235, "percentage": 66.17, "elapsed_time": "1:41:34", "remaining_time": "0:51:55", "throughput": 4632.65, "total_tokens": 28234240} {"current_steps": 28075, "total_steps": 42420, "loss": 0.163, "lr": 1.5488534569712465e-05, "epoch": 13.236680810938237, "percentage": 66.18, "elapsed_time": "1:41:36", "remaining_time": "0:51:54", "throughput": 4632.72, "total_tokens": 28241248} {"current_steps": 28080, "total_steps": 42420, "loss": 0.1323, "lr": 1.5479022899167407e-05, "epoch": 13.23903818953324, "percentage": 66.2, "elapsed_time": "1:41:36", "remaining_time": "0:51:53", "throughput": 4632.72, "total_tokens": 28245504} {"current_steps": 28085, "total_steps": 42420, "loss": 0.0609, "lr": 1.5469512840362117e-05, "epoch": 13.241395568128242, "percentage": 66.21, "elapsed_time": "1:41:37", "remaining_time": "0:51:52", "throughput": 4632.75, "total_tokens": 28250272} {"current_steps": 28090, "total_steps": 42420, "loss": 0.0789, "lr": 1.5460004394906484e-05, "epoch": 13.243752946723244, "percentage": 66.22, "elapsed_time": "1:41:39", "remaining_time": "0:51:51", "throughput": 4632.79, "total_tokens": 28255424} {"current_steps": 28095, "total_steps": 42420, "loss": 0.073, "lr": 1.545049756441012e-05, "epoch": 13.246110325318247, "percentage": 66.23, "elapsed_time": "1:41:40", "remaining_time": "0:51:50", "throughput": 4632.87, "total_tokens": 28261728} {"current_steps": 28100, "total_steps": 42420, "loss": 0.0908, "lr": 1.5440992350482377e-05, "epoch": 13.24846770391325, "percentage": 66.24, "elapsed_time": "1:41:41", "remaining_time": "0:51:49", "throughput": 4632.91, "total_tokens": 28266464} {"current_steps": 28105, "total_steps": 42420, "loss": 0.1528, "lr": 1.543148875473233e-05, "epoch": 13.250825082508252, "percentage": 66.25, "elapsed_time": "1:41:42", "remaining_time": "0:51:48", "throughput": 4632.96, "total_tokens": 28271968} {"current_steps": 28110, "total_steps": 42420, "loss": 0.1119, "lr": 1.5421986778768774e-05, "epoch": 13.253182461103254, "percentage": 66.27, "elapsed_time": "1:41:43", "remaining_time": "0:51:46", "throughput": 4632.97, "total_tokens": 28276224} {"current_steps": 28115, "total_steps": 42420, "loss": 0.2031, "lr": 1.541248642420023e-05, "epoch": 13.255539839698255, "percentage": 66.28, "elapsed_time": "1:41:44", "remaining_time": "0:51:45", "throughput": 4632.96, "total_tokens": 28281088} {"current_steps": 28120, "total_steps": 42420, "loss": 0.2592, "lr": 1.540298769263494e-05, "epoch": 13.257897218293257, "percentage": 66.29, "elapsed_time": "1:41:45", "remaining_time": "0:51:44", "throughput": 4633.04, "total_tokens": 28288000} {"current_steps": 28125, "total_steps": 42420, "loss": 0.109, "lr": 1.539349058568089e-05, "epoch": 13.26025459688826, "percentage": 66.3, "elapsed_time": "1:41:46", "remaining_time": "0:51:43", "throughput": 4633.1, "total_tokens": 28293472} {"current_steps": 28130, "total_steps": 42420, "loss": 0.1026, "lr": 1.538399510494578e-05, "epoch": 13.262611975483262, "percentage": 66.31, "elapsed_time": "1:41:47", "remaining_time": "0:51:42", "throughput": 4633.16, "total_tokens": 28298976} {"current_steps": 28135, "total_steps": 42420, "loss": 0.3376, "lr": 1.5374501252037028e-05, "epoch": 13.264969354078264, "percentage": 66.32, "elapsed_time": "1:41:48", "remaining_time": "0:51:41", "throughput": 4633.18, "total_tokens": 28303840} {"current_steps": 28140, "total_steps": 42420, "loss": 0.0827, "lr": 1.536500902856178e-05, "epoch": 13.267326732673267, "percentage": 66.34, "elapsed_time": "1:41:49", "remaining_time": "0:51:40", "throughput": 4633.22, "total_tokens": 28308864} {"current_steps": 28145, "total_steps": 42420, "loss": 0.2335, "lr": 1.5355518436126902e-05, "epoch": 13.269684111268269, "percentage": 66.35, "elapsed_time": "1:41:51", "remaining_time": "0:51:39", "throughput": 4633.22, "total_tokens": 28313920} {"current_steps": 28150, "total_steps": 42420, "loss": 0.2831, "lr": 1.5346029476339015e-05, "epoch": 13.272041489863271, "percentage": 66.36, "elapsed_time": "1:41:52", "remaining_time": "0:51:38", "throughput": 4633.27, "total_tokens": 28319232} {"current_steps": 28155, "total_steps": 42420, "loss": 0.1717, "lr": 1.533654215080441e-05, "epoch": 13.274398868458274, "percentage": 66.37, "elapsed_time": "1:41:53", "remaining_time": "0:51:37", "throughput": 4633.32, "total_tokens": 28324992} {"current_steps": 28160, "total_steps": 42420, "loss": 0.1388, "lr": 1.5327056461129145e-05, "epoch": 13.276756247053276, "percentage": 66.38, "elapsed_time": "1:41:54", "remaining_time": "0:51:36", "throughput": 4633.36, "total_tokens": 28329536} {"current_steps": 28165, "total_steps": 42420, "loss": 0.0773, "lr": 1.5317572408918983e-05, "epoch": 13.279113625648279, "percentage": 66.4, "elapsed_time": "1:41:55", "remaining_time": "0:51:35", "throughput": 4633.35, "total_tokens": 28334208} {"current_steps": 28170, "total_steps": 42420, "loss": 0.0893, "lr": 1.5308089995779424e-05, "epoch": 13.281471004243281, "percentage": 66.41, "elapsed_time": "1:41:56", "remaining_time": "0:51:33", "throughput": 4633.38, "total_tokens": 28338784} {"current_steps": 28175, "total_steps": 42420, "loss": 0.0381, "lr": 1.5298609223315657e-05, "epoch": 13.283828382838283, "percentage": 66.42, "elapsed_time": "1:41:57", "remaining_time": "0:51:32", "throughput": 4633.43, "total_tokens": 28344096} {"current_steps": 28180, "total_steps": 42420, "loss": 0.1517, "lr": 1.5289130093132632e-05, "epoch": 13.286185761433286, "percentage": 66.43, "elapsed_time": "1:41:58", "remaining_time": "0:51:31", "throughput": 4633.47, "total_tokens": 28348992} {"current_steps": 28185, "total_steps": 42420, "loss": 0.018, "lr": 1.5279652606835004e-05, "epoch": 13.288543140028288, "percentage": 66.44, "elapsed_time": "1:41:59", "remaining_time": "0:51:30", "throughput": 4633.51, "total_tokens": 28355936} {"current_steps": 28190, "total_steps": 42420, "loss": 0.1816, "lr": 1.527017676602715e-05, "epoch": 13.29090051862329, "percentage": 66.45, "elapsed_time": "1:42:00", "remaining_time": "0:51:29", "throughput": 4633.55, "total_tokens": 28361120} {"current_steps": 28195, "total_steps": 42420, "loss": 0.2076, "lr": 1.526070257231316e-05, "epoch": 13.293257897218293, "percentage": 66.47, "elapsed_time": "1:42:01", "remaining_time": "0:51:28", "throughput": 4633.61, "total_tokens": 28366272} {"current_steps": 28200, "total_steps": 42420, "loss": 0.035, "lr": 1.5251230027296861e-05, "epoch": 13.295615275813295, "percentage": 66.48, "elapsed_time": "1:42:02", "remaining_time": "0:51:27", "throughput": 4633.6, "total_tokens": 28370368} {"current_steps": 28205, "total_steps": 42420, "loss": 0.0377, "lr": 1.5241759132581795e-05, "epoch": 13.297972654408298, "percentage": 66.49, "elapsed_time": "1:42:03", "remaining_time": "0:51:26", "throughput": 4633.62, "total_tokens": 28375328} {"current_steps": 28210, "total_steps": 42420, "loss": 0.0543, "lr": 1.523228988977123e-05, "epoch": 13.3003300330033, "percentage": 66.5, "elapsed_time": "1:42:04", "remaining_time": "0:51:25", "throughput": 4633.66, "total_tokens": 28380256} {"current_steps": 28215, "total_steps": 42420, "loss": 0.0604, "lr": 1.5222822300468129e-05, "epoch": 13.302687411598303, "percentage": 66.51, "elapsed_time": "1:42:05", "remaining_time": "0:51:24", "throughput": 4633.7, "total_tokens": 28385536} {"current_steps": 28220, "total_steps": 42420, "loss": 0.0613, "lr": 1.5213356366275209e-05, "epoch": 13.305044790193305, "percentage": 66.53, "elapsed_time": "1:42:06", "remaining_time": "0:51:22", "throughput": 4633.7, "total_tokens": 28389632} {"current_steps": 28225, "total_steps": 42420, "loss": 0.0666, "lr": 1.5203892088794889e-05, "epoch": 13.307402168788308, "percentage": 66.54, "elapsed_time": "1:42:07", "remaining_time": "0:51:21", "throughput": 4633.75, "total_tokens": 28395072} {"current_steps": 28230, "total_steps": 42420, "loss": 0.1873, "lr": 1.5194429469629312e-05, "epoch": 13.30975954738331, "percentage": 66.55, "elapsed_time": "1:42:08", "remaining_time": "0:51:20", "throughput": 4633.78, "total_tokens": 28399904} {"current_steps": 28235, "total_steps": 42420, "loss": 0.0959, "lr": 1.5184968510380335e-05, "epoch": 13.312116925978312, "percentage": 66.56, "elapsed_time": "1:42:09", "remaining_time": "0:51:19", "throughput": 4633.76, "total_tokens": 28403872} {"current_steps": 28240, "total_steps": 42420, "loss": 0.1056, "lr": 1.5175509212649536e-05, "epoch": 13.314474304573315, "percentage": 66.57, "elapsed_time": "1:42:10", "remaining_time": "0:51:18", "throughput": 4633.79, "total_tokens": 28408576} {"current_steps": 28245, "total_steps": 42420, "loss": 0.0408, "lr": 1.516605157803822e-05, "epoch": 13.316831683168317, "percentage": 66.58, "elapsed_time": "1:42:11", "remaining_time": "0:51:17", "throughput": 4633.83, "total_tokens": 28414304} {"current_steps": 28250, "total_steps": 42420, "loss": 0.2177, "lr": 1.5156595608147406e-05, "epoch": 13.31918906176332, "percentage": 66.6, "elapsed_time": "1:42:12", "remaining_time": "0:51:16", "throughput": 4633.85, "total_tokens": 28418592} {"current_steps": 28255, "total_steps": 42420, "loss": 0.0502, "lr": 1.5147141304577816e-05, "epoch": 13.321546440358322, "percentage": 66.61, "elapsed_time": "1:42:13", "remaining_time": "0:51:15", "throughput": 4633.88, "total_tokens": 28423456} {"current_steps": 28260, "total_steps": 42420, "loss": 0.1562, "lr": 1.5137688668929918e-05, "epoch": 13.323903818953324, "percentage": 66.62, "elapsed_time": "1:42:14", "remaining_time": "0:51:13", "throughput": 4633.93, "total_tokens": 28428480} {"current_steps": 28265, "total_steps": 42420, "loss": 0.1179, "lr": 1.5128237702803868e-05, "epoch": 13.326261197548327, "percentage": 66.63, "elapsed_time": "1:42:15", "remaining_time": "0:51:12", "throughput": 4633.96, "total_tokens": 28433120} {"current_steps": 28270, "total_steps": 42420, "loss": 0.0446, "lr": 1.511878840779957e-05, "epoch": 13.32861857614333, "percentage": 66.64, "elapsed_time": "1:42:16", "remaining_time": "0:51:11", "throughput": 4634.01, "total_tokens": 28438560} {"current_steps": 28275, "total_steps": 42420, "loss": 0.0847, "lr": 1.5109340785516616e-05, "epoch": 13.330975954738332, "percentage": 66.65, "elapsed_time": "1:42:18", "remaining_time": "0:51:10", "throughput": 4634.06, "total_tokens": 28444000} {"current_steps": 28280, "total_steps": 42420, "loss": 0.1419, "lr": 1.5099894837554335e-05, "epoch": 13.333333333333334, "percentage": 66.67, "elapsed_time": "1:42:19", "remaining_time": "0:51:09", "throughput": 4634.1, "total_tokens": 28449088} {"current_steps": 28285, "total_steps": 42420, "loss": 0.0453, "lr": 1.509045056551176e-05, "epoch": 13.335690711928336, "percentage": 66.68, "elapsed_time": "1:42:20", "remaining_time": "0:51:08", "throughput": 4634.14, "total_tokens": 28454688} {"current_steps": 28290, "total_steps": 42420, "loss": 0.1226, "lr": 1.5081007970987657e-05, "epoch": 13.338048090523339, "percentage": 66.69, "elapsed_time": "1:42:21", "remaining_time": "0:51:07", "throughput": 4634.2, "total_tokens": 28460224} {"current_steps": 28295, "total_steps": 42420, "loss": 0.0572, "lr": 1.5071567055580482e-05, "epoch": 13.340405469118341, "percentage": 66.7, "elapsed_time": "1:42:22", "remaining_time": "0:51:06", "throughput": 4634.2, "total_tokens": 28464704} {"current_steps": 28300, "total_steps": 42420, "loss": 0.0805, "lr": 1.5062127820888433e-05, "epoch": 13.342762847713344, "percentage": 66.71, "elapsed_time": "1:42:23", "remaining_time": "0:51:05", "throughput": 4634.25, "total_tokens": 28469952} {"current_steps": 28305, "total_steps": 42420, "loss": 0.0145, "lr": 1.5052690268509407e-05, "epoch": 13.345120226308346, "percentage": 66.73, "elapsed_time": "1:42:24", "remaining_time": "0:51:04", "throughput": 4634.31, "total_tokens": 28477312} {"current_steps": 28310, "total_steps": 42420, "loss": 0.1747, "lr": 1.5043254400041035e-05, "epoch": 13.347477604903348, "percentage": 66.74, "elapsed_time": "1:42:25", "remaining_time": "0:51:03", "throughput": 4634.35, "total_tokens": 28482336} {"current_steps": 28315, "total_steps": 42420, "loss": 0.0975, "lr": 1.5033820217080629e-05, "epoch": 13.34983498349835, "percentage": 66.75, "elapsed_time": "1:42:26", "remaining_time": "0:51:02", "throughput": 4634.38, "total_tokens": 28487456} {"current_steps": 28320, "total_steps": 42420, "loss": 0.1811, "lr": 1.5024387721225242e-05, "epoch": 13.352192362093351, "percentage": 66.76, "elapsed_time": "1:42:27", "remaining_time": "0:51:00", "throughput": 4634.4, "total_tokens": 28491520} {"current_steps": 28325, "total_steps": 42420, "loss": 0.0377, "lr": 1.5014956914071635e-05, "epoch": 13.354549740688354, "percentage": 66.77, "elapsed_time": "1:42:28", "remaining_time": "0:50:59", "throughput": 4634.41, "total_tokens": 28495808} {"current_steps": 28330, "total_steps": 42420, "loss": 0.2769, "lr": 1.5005527797216284e-05, "epoch": 13.356907119283356, "percentage": 66.78, "elapsed_time": "1:42:29", "remaining_time": "0:50:58", "throughput": 4634.45, "total_tokens": 28500768} {"current_steps": 28335, "total_steps": 42420, "loss": 0.0207, "lr": 1.499610037225539e-05, "epoch": 13.359264497878359, "percentage": 66.8, "elapsed_time": "1:42:30", "remaining_time": "0:50:57", "throughput": 4634.47, "total_tokens": 28505376} {"current_steps": 28340, "total_steps": 42420, "loss": 0.176, "lr": 1.498667464078484e-05, "epoch": 13.361621876473361, "percentage": 66.81, "elapsed_time": "1:42:31", "remaining_time": "0:50:56", "throughput": 4634.54, "total_tokens": 28511296} {"current_steps": 28345, "total_steps": 42420, "loss": 0.0984, "lr": 1.4977250604400256e-05, "epoch": 13.363979255068363, "percentage": 66.82, "elapsed_time": "1:42:32", "remaining_time": "0:50:55", "throughput": 4634.57, "total_tokens": 28516224} {"current_steps": 28350, "total_steps": 42420, "loss": 0.1396, "lr": 1.496782826469697e-05, "epoch": 13.366336633663366, "percentage": 66.83, "elapsed_time": "1:42:34", "remaining_time": "0:50:54", "throughput": 4634.63, "total_tokens": 28522848} {"current_steps": 28355, "total_steps": 42420, "loss": 0.0414, "lr": 1.4958407623270027e-05, "epoch": 13.368694012258368, "percentage": 66.84, "elapsed_time": "1:42:35", "remaining_time": "0:50:53", "throughput": 4634.64, "total_tokens": 28527168} {"current_steps": 28360, "total_steps": 42420, "loss": 0.0984, "lr": 1.4948988681714168e-05, "epoch": 13.37105139085337, "percentage": 66.86, "elapsed_time": "1:42:36", "remaining_time": "0:50:52", "throughput": 4634.66, "total_tokens": 28531968} {"current_steps": 28365, "total_steps": 42420, "loss": 0.0598, "lr": 1.4939571441623874e-05, "epoch": 13.373408769448373, "percentage": 66.87, "elapsed_time": "1:42:37", "remaining_time": "0:50:50", "throughput": 4634.7, "total_tokens": 28537216} {"current_steps": 28370, "total_steps": 42420, "loss": 0.1123, "lr": 1.4930155904593312e-05, "epoch": 13.375766148043375, "percentage": 66.88, "elapsed_time": "1:42:38", "remaining_time": "0:50:49", "throughput": 4634.74, "total_tokens": 28542464} {"current_steps": 28375, "total_steps": 42420, "loss": 0.0346, "lr": 1.492074207221639e-05, "epoch": 13.378123526638378, "percentage": 66.89, "elapsed_time": "1:42:39", "remaining_time": "0:50:48", "throughput": 4634.79, "total_tokens": 28548064} {"current_steps": 28380, "total_steps": 42420, "loss": 0.0537, "lr": 1.4911329946086691e-05, "epoch": 13.38048090523338, "percentage": 66.9, "elapsed_time": "1:42:40", "remaining_time": "0:50:47", "throughput": 4634.8, "total_tokens": 28552192} {"current_steps": 28385, "total_steps": 42420, "loss": 0.255, "lr": 1.4901919527797536e-05, "epoch": 13.382838283828383, "percentage": 66.91, "elapsed_time": "1:42:41", "remaining_time": "0:50:46", "throughput": 4634.65, "total_tokens": 28557504} {"current_steps": 28390, "total_steps": 42420, "loss": 0.116, "lr": 1.489251081894195e-05, "epoch": 13.385195662423385, "percentage": 66.93, "elapsed_time": "1:42:42", "remaining_time": "0:50:45", "throughput": 4634.68, "total_tokens": 28562528} {"current_steps": 28395, "total_steps": 42420, "loss": 0.1488, "lr": 1.4883103821112677e-05, "epoch": 13.387553041018387, "percentage": 66.94, "elapsed_time": "1:42:43", "remaining_time": "0:50:44", "throughput": 4634.69, "total_tokens": 28567040} {"current_steps": 28400, "total_steps": 42420, "loss": 0.1568, "lr": 1.4873698535902142e-05, "epoch": 13.38991041961339, "percentage": 66.95, "elapsed_time": "1:42:44", "remaining_time": "0:50:43", "throughput": 4634.73, "total_tokens": 28572192} {"current_steps": 28405, "total_steps": 42420, "loss": 0.2838, "lr": 1.486429496490251e-05, "epoch": 13.392267798208392, "percentage": 66.96, "elapsed_time": "1:42:45", "remaining_time": "0:50:42", "throughput": 4634.78, "total_tokens": 28577312} {"current_steps": 28410, "total_steps": 42420, "loss": 0.0359, "lr": 1.4854893109705647e-05, "epoch": 13.394625176803395, "percentage": 66.97, "elapsed_time": "1:42:47", "remaining_time": "0:50:41", "throughput": 4634.83, "total_tokens": 28583040} {"current_steps": 28415, "total_steps": 42420, "loss": 0.1137, "lr": 1.484549297190313e-05, "epoch": 13.396982555398397, "percentage": 66.98, "elapsed_time": "1:42:48", "remaining_time": "0:50:40", "throughput": 4634.88, "total_tokens": 28588544} {"current_steps": 28420, "total_steps": 42420, "loss": 0.1474, "lr": 1.4836094553086235e-05, "epoch": 13.3993399339934, "percentage": 67.0, "elapsed_time": "1:42:49", "remaining_time": "0:50:38", "throughput": 4634.84, "total_tokens": 28592736} {"current_steps": 28425, "total_steps": 42420, "loss": 0.3304, "lr": 1.482669785484596e-05, "epoch": 13.401697312588402, "percentage": 67.01, "elapsed_time": "1:42:50", "remaining_time": "0:50:37", "throughput": 4634.87, "total_tokens": 28597632} {"current_steps": 28430, "total_steps": 42420, "loss": 0.2248, "lr": 1.4817302878773003e-05, "epoch": 13.404054691183404, "percentage": 67.02, "elapsed_time": "1:42:51", "remaining_time": "0:50:36", "throughput": 4634.89, "total_tokens": 28602272} {"current_steps": 28435, "total_steps": 42420, "loss": 0.1216, "lr": 1.4807909626457782e-05, "epoch": 13.406412069778407, "percentage": 67.03, "elapsed_time": "1:42:52", "remaining_time": "0:50:35", "throughput": 4634.95, "total_tokens": 28608672} {"current_steps": 28440, "total_steps": 42420, "loss": 0.175, "lr": 1.4798518099490405e-05, "epoch": 13.408769448373409, "percentage": 67.04, "elapsed_time": "1:42:53", "remaining_time": "0:50:34", "throughput": 4634.99, "total_tokens": 28613792} {"current_steps": 28445, "total_steps": 42420, "loss": 0.07, "lr": 1.4789128299460703e-05, "epoch": 13.411126826968411, "percentage": 67.06, "elapsed_time": "1:42:54", "remaining_time": "0:50:33", "throughput": 4635.04, "total_tokens": 28619520} {"current_steps": 28450, "total_steps": 42420, "loss": 0.1027, "lr": 1.477974022795821e-05, "epoch": 13.413484205563414, "percentage": 67.07, "elapsed_time": "1:42:55", "remaining_time": "0:50:32", "throughput": 4635.04, "total_tokens": 28623872} {"current_steps": 28455, "total_steps": 42420, "loss": 0.0505, "lr": 1.4770353886572169e-05, "epoch": 13.415841584158416, "percentage": 67.08, "elapsed_time": "1:42:56", "remaining_time": "0:50:31", "throughput": 4635.09, "total_tokens": 28629344} {"current_steps": 28460, "total_steps": 42420, "loss": 0.0585, "lr": 1.4760969276891523e-05, "epoch": 13.418198962753419, "percentage": 67.09, "elapsed_time": "1:42:57", "remaining_time": "0:50:30", "throughput": 4635.09, "total_tokens": 28633504} {"current_steps": 28465, "total_steps": 42420, "loss": 0.0801, "lr": 1.4751586400504927e-05, "epoch": 13.420556341348421, "percentage": 67.1, "elapsed_time": "1:42:58", "remaining_time": "0:50:29", "throughput": 4635.11, "total_tokens": 28637888} {"current_steps": 28470, "total_steps": 42420, "loss": 0.0911, "lr": 1.4742205259000747e-05, "epoch": 13.422913719943423, "percentage": 67.11, "elapsed_time": "1:42:59", "remaining_time": "0:50:27", "throughput": 4635.14, "total_tokens": 28642592} {"current_steps": 28475, "total_steps": 42420, "loss": 0.037, "lr": 1.4732825853967053e-05, "epoch": 13.425271098538426, "percentage": 67.13, "elapsed_time": "1:43:00", "remaining_time": "0:50:26", "throughput": 4635.18, "total_tokens": 28648224} {"current_steps": 28480, "total_steps": 42420, "loss": 0.1929, "lr": 1.4723448186991612e-05, "epoch": 13.427628477133428, "percentage": 67.14, "elapsed_time": "1:43:01", "remaining_time": "0:50:25", "throughput": 4635.22, "total_tokens": 28653600} {"current_steps": 28485, "total_steps": 42420, "loss": 0.0655, "lr": 1.4714072259661904e-05, "epoch": 13.42998585572843, "percentage": 67.15, "elapsed_time": "1:43:02", "remaining_time": "0:50:24", "throughput": 4635.28, "total_tokens": 28659520} {"current_steps": 28490, "total_steps": 42420, "loss": 0.0756, "lr": 1.4704698073565121e-05, "epoch": 13.432343234323433, "percentage": 67.16, "elapsed_time": "1:43:03", "remaining_time": "0:50:23", "throughput": 4635.32, "total_tokens": 28664352} {"current_steps": 28495, "total_steps": 42420, "loss": 0.0241, "lr": 1.4695325630288151e-05, "epoch": 13.434700612918435, "percentage": 67.17, "elapsed_time": "1:43:04", "remaining_time": "0:50:22", "throughput": 4635.36, "total_tokens": 28669184} {"current_steps": 28500, "total_steps": 42420, "loss": 0.123, "lr": 1.4685954931417587e-05, "epoch": 13.437057991513438, "percentage": 67.19, "elapsed_time": "1:43:05", "remaining_time": "0:50:21", "throughput": 4635.35, "total_tokens": 28673952} {"current_steps": 28505, "total_steps": 42420, "loss": 0.2198, "lr": 1.4676585978539729e-05, "epoch": 13.43941537010844, "percentage": 67.2, "elapsed_time": "1:43:07", "remaining_time": "0:50:20", "throughput": 4635.39, "total_tokens": 28679712} {"current_steps": 28510, "total_steps": 42420, "loss": 0.0632, "lr": 1.4667218773240582e-05, "epoch": 13.441772748703443, "percentage": 67.21, "elapsed_time": "1:43:08", "remaining_time": "0:50:19", "throughput": 4635.44, "total_tokens": 28684768} {"current_steps": 28515, "total_steps": 42420, "loss": 0.1939, "lr": 1.4657853317105863e-05, "epoch": 13.444130127298443, "percentage": 67.22, "elapsed_time": "1:43:09", "remaining_time": "0:50:18", "throughput": 4635.41, "total_tokens": 28689248} {"current_steps": 28520, "total_steps": 42420, "loss": 0.0707, "lr": 1.4648489611720973e-05, "epoch": 13.446487505893446, "percentage": 67.23, "elapsed_time": "1:43:10", "remaining_time": "0:50:16", "throughput": 4635.4, "total_tokens": 28693728} {"current_steps": 28525, "total_steps": 42420, "loss": 0.1567, "lr": 1.4639127658671032e-05, "epoch": 13.448844884488448, "percentage": 67.24, "elapsed_time": "1:43:11", "remaining_time": "0:50:15", "throughput": 4635.45, "total_tokens": 28699584} {"current_steps": 28530, "total_steps": 42420, "loss": 0.1533, "lr": 1.4629767459540861e-05, "epoch": 13.45120226308345, "percentage": 67.26, "elapsed_time": "1:43:12", "remaining_time": "0:50:14", "throughput": 4635.48, "total_tokens": 28704160} {"current_steps": 28535, "total_steps": 42420, "loss": 0.2409, "lr": 1.462040901591499e-05, "epoch": 13.453559641678453, "percentage": 67.27, "elapsed_time": "1:43:13", "remaining_time": "0:50:13", "throughput": 4635.5, "total_tokens": 28709280} {"current_steps": 28540, "total_steps": 42420, "loss": 0.295, "lr": 1.4611052329377628e-05, "epoch": 13.455917020273455, "percentage": 67.28, "elapsed_time": "1:43:14", "remaining_time": "0:50:12", "throughput": 4635.53, "total_tokens": 28714176} {"current_steps": 28545, "total_steps": 42420, "loss": 0.041, "lr": 1.460169740151272e-05, "epoch": 13.458274398868458, "percentage": 67.29, "elapsed_time": "1:43:15", "remaining_time": "0:50:11", "throughput": 4635.55, "total_tokens": 28718944} {"current_steps": 28550, "total_steps": 42420, "loss": 0.121, "lr": 1.4592344233903879e-05, "epoch": 13.46063177746346, "percentage": 67.3, "elapsed_time": "1:43:16", "remaining_time": "0:50:10", "throughput": 4635.56, "total_tokens": 28723616} {"current_steps": 28555, "total_steps": 42420, "loss": 0.0682, "lr": 1.4582992828134462e-05, "epoch": 13.462989156058462, "percentage": 67.31, "elapsed_time": "1:43:17", "remaining_time": "0:50:09", "throughput": 4635.57, "total_tokens": 28727648} {"current_steps": 28560, "total_steps": 42420, "loss": 0.0406, "lr": 1.4573643185787478e-05, "epoch": 13.465346534653465, "percentage": 67.33, "elapsed_time": "1:43:18", "remaining_time": "0:50:08", "throughput": 4635.65, "total_tokens": 28734240} {"current_steps": 28565, "total_steps": 42420, "loss": 0.1236, "lr": 1.4564295308445669e-05, "epoch": 13.467703913248467, "percentage": 67.34, "elapsed_time": "1:43:19", "remaining_time": "0:50:07", "throughput": 4635.72, "total_tokens": 28740832} {"current_steps": 28570, "total_steps": 42420, "loss": 0.0379, "lr": 1.455494919769148e-05, "epoch": 13.47006129184347, "percentage": 67.35, "elapsed_time": "1:43:20", "remaining_time": "0:50:06", "throughput": 4635.75, "total_tokens": 28745824} {"current_steps": 28575, "total_steps": 42420, "loss": 0.0194, "lr": 1.4545604855107048e-05, "epoch": 13.472418670438472, "percentage": 67.36, "elapsed_time": "1:43:22", "remaining_time": "0:50:04", "throughput": 4635.8, "total_tokens": 28751424} {"current_steps": 28580, "total_steps": 42420, "loss": 0.0445, "lr": 1.4536262282274205e-05, "epoch": 13.474776049033474, "percentage": 67.37, "elapsed_time": "1:43:22", "remaining_time": "0:50:03", "throughput": 4635.82, "total_tokens": 28755712} {"current_steps": 28585, "total_steps": 42420, "loss": 0.1278, "lr": 1.4526921480774492e-05, "epoch": 13.477133427628477, "percentage": 67.39, "elapsed_time": "1:43:24", "remaining_time": "0:50:02", "throughput": 4635.85, "total_tokens": 28761024} {"current_steps": 28590, "total_steps": 42420, "loss": 0.0736, "lr": 1.4517582452189153e-05, "epoch": 13.47949080622348, "percentage": 67.4, "elapsed_time": "1:43:25", "remaining_time": "0:50:01", "throughput": 4635.88, "total_tokens": 28766144} {"current_steps": 28595, "total_steps": 42420, "loss": 0.0151, "lr": 1.450824519809913e-05, "epoch": 13.481848184818482, "percentage": 67.41, "elapsed_time": "1:43:26", "remaining_time": "0:50:00", "throughput": 4635.92, "total_tokens": 28770816} {"current_steps": 28600, "total_steps": 42420, "loss": 0.14, "lr": 1.4498909720085047e-05, "epoch": 13.484205563413484, "percentage": 67.42, "elapsed_time": "1:43:27", "remaining_time": "0:49:59", "throughput": 4635.96, "total_tokens": 28776320} {"current_steps": 28605, "total_steps": 42420, "loss": 0.082, "lr": 1.448957601972725e-05, "epoch": 13.486562942008486, "percentage": 67.43, "elapsed_time": "1:43:28", "remaining_time": "0:49:58", "throughput": 4636.0, "total_tokens": 28781792} {"current_steps": 28610, "total_steps": 42420, "loss": 0.1114, "lr": 1.4480244098605778e-05, "epoch": 13.488920320603489, "percentage": 67.44, "elapsed_time": "1:43:29", "remaining_time": "0:49:57", "throughput": 4636.05, "total_tokens": 28787104} {"current_steps": 28615, "total_steps": 42420, "loss": 0.0635, "lr": 1.4470913958300362e-05, "epoch": 13.491277699198491, "percentage": 67.46, "elapsed_time": "1:43:30", "remaining_time": "0:49:56", "throughput": 4636.06, "total_tokens": 28791808} {"current_steps": 28620, "total_steps": 42420, "loss": 0.0676, "lr": 1.4461585600390437e-05, "epoch": 13.493635077793494, "percentage": 67.47, "elapsed_time": "1:43:31", "remaining_time": "0:49:55", "throughput": 4636.11, "total_tokens": 28797344} {"current_steps": 28625, "total_steps": 42420, "loss": 0.2442, "lr": 1.4452259026455143e-05, "epoch": 13.495992456388496, "percentage": 67.48, "elapsed_time": "1:43:32", "remaining_time": "0:49:53", "throughput": 4636.12, "total_tokens": 28801632} {"current_steps": 28630, "total_steps": 42420, "loss": 0.0356, "lr": 1.4442934238073302e-05, "epoch": 13.498349834983498, "percentage": 67.49, "elapsed_time": "1:43:33", "remaining_time": "0:49:52", "throughput": 4636.13, "total_tokens": 28806560} {"current_steps": 28635, "total_steps": 42420, "loss": 0.2732, "lr": 1.4433611236823458e-05, "epoch": 13.500707213578501, "percentage": 67.5, "elapsed_time": "1:43:34", "remaining_time": "0:49:51", "throughput": 4636.17, "total_tokens": 28811808} {"current_steps": 28640, "total_steps": 42420, "loss": 0.1502, "lr": 1.4424290024283812e-05, "epoch": 13.503064592173503, "percentage": 67.52, "elapsed_time": "1:43:35", "remaining_time": "0:49:50", "throughput": 4636.17, "total_tokens": 28816160} {"current_steps": 28645, "total_steps": 42420, "loss": 0.1112, "lr": 1.4414970602032302e-05, "epoch": 13.505421970768506, "percentage": 67.53, "elapsed_time": "1:43:36", "remaining_time": "0:49:49", "throughput": 4636.24, "total_tokens": 28822080} {"current_steps": 28650, "total_steps": 42420, "loss": 0.0449, "lr": 1.4405652971646544e-05, "epoch": 13.507779349363508, "percentage": 67.54, "elapsed_time": "1:43:37", "remaining_time": "0:49:48", "throughput": 4636.29, "total_tokens": 28827264} {"current_steps": 28655, "total_steps": 42420, "loss": 0.0753, "lr": 1.4396337134703857e-05, "epoch": 13.51013672795851, "percentage": 67.55, "elapsed_time": "1:43:38", "remaining_time": "0:49:47", "throughput": 4636.33, "total_tokens": 28832224} {"current_steps": 28660, "total_steps": 42420, "loss": 0.0452, "lr": 1.4387023092781252e-05, "epoch": 13.512494106553513, "percentage": 67.56, "elapsed_time": "1:43:39", "remaining_time": "0:49:46", "throughput": 4636.36, "total_tokens": 28837216} {"current_steps": 28665, "total_steps": 42420, "loss": 0.1006, "lr": 1.4377710847455439e-05, "epoch": 13.514851485148515, "percentage": 67.57, "elapsed_time": "1:43:40", "remaining_time": "0:49:45", "throughput": 4636.35, "total_tokens": 28841344} {"current_steps": 28670, "total_steps": 42420, "loss": 0.2593, "lr": 1.4368400400302825e-05, "epoch": 13.517208863743518, "percentage": 67.59, "elapsed_time": "1:43:41", "remaining_time": "0:49:43", "throughput": 4636.36, "total_tokens": 28846016} {"current_steps": 28675, "total_steps": 42420, "loss": 0.0107, "lr": 1.4359091752899518e-05, "epoch": 13.51956624233852, "percentage": 67.6, "elapsed_time": "1:43:42", "remaining_time": "0:49:42", "throughput": 4636.42, "total_tokens": 28852224} {"current_steps": 28680, "total_steps": 42420, "loss": 0.0896, "lr": 1.4349784906821295e-05, "epoch": 13.521923620933523, "percentage": 67.61, "elapsed_time": "1:43:43", "remaining_time": "0:49:41", "throughput": 4636.42, "total_tokens": 28857024} {"current_steps": 28685, "total_steps": 42420, "loss": 0.0939, "lr": 1.4340479863643658e-05, "epoch": 13.524280999528525, "percentage": 67.62, "elapsed_time": "1:43:44", "remaining_time": "0:49:40", "throughput": 4636.45, "total_tokens": 28861472} {"current_steps": 28690, "total_steps": 42420, "loss": 0.037, "lr": 1.433117662494179e-05, "epoch": 13.526638378123527, "percentage": 67.63, "elapsed_time": "1:43:45", "remaining_time": "0:49:39", "throughput": 4636.47, "total_tokens": 28865984} {"current_steps": 28695, "total_steps": 42420, "loss": 0.0774, "lr": 1.4321875192290573e-05, "epoch": 13.52899575671853, "percentage": 67.64, "elapsed_time": "1:43:46", "remaining_time": "0:49:38", "throughput": 4636.51, "total_tokens": 28871200} {"current_steps": 28700, "total_steps": 42420, "loss": 0.1923, "lr": 1.4312575567264586e-05, "epoch": 13.531353135313532, "percentage": 67.66, "elapsed_time": "1:43:48", "remaining_time": "0:49:37", "throughput": 4636.54, "total_tokens": 28876576} {"current_steps": 28705, "total_steps": 42420, "loss": 0.1402, "lr": 1.4303277751438087e-05, "epoch": 13.533710513908535, "percentage": 67.67, "elapsed_time": "1:43:49", "remaining_time": "0:49:36", "throughput": 4636.61, "total_tokens": 28882496} {"current_steps": 28710, "total_steps": 42420, "loss": 0.1361, "lr": 1.4293981746385049e-05, "epoch": 13.536067892503535, "percentage": 67.68, "elapsed_time": "1:43:50", "remaining_time": "0:49:35", "throughput": 4636.66, "total_tokens": 28887360} {"current_steps": 28715, "total_steps": 42420, "loss": 0.1348, "lr": 1.4284687553679132e-05, "epoch": 13.53842527109854, "percentage": 67.69, "elapsed_time": "1:43:51", "remaining_time": "0:49:34", "throughput": 4636.71, "total_tokens": 28892576} {"current_steps": 28720, "total_steps": 42420, "loss": 0.1032, "lr": 1.4275395174893666e-05, "epoch": 13.54078264969354, "percentage": 67.7, "elapsed_time": "1:43:52", "remaining_time": "0:49:32", "throughput": 4636.73, "total_tokens": 28897472} {"current_steps": 28725, "total_steps": 42420, "loss": 0.1566, "lr": 1.4266104611601705e-05, "epoch": 13.543140028288542, "percentage": 67.72, "elapsed_time": "1:43:53", "remaining_time": "0:49:31", "throughput": 4636.77, "total_tokens": 28903040} {"current_steps": 28730, "total_steps": 42420, "loss": 0.0838, "lr": 1.4256815865375981e-05, "epoch": 13.545497406883545, "percentage": 67.73, "elapsed_time": "1:43:54", "remaining_time": "0:49:30", "throughput": 4636.8, "total_tokens": 28907712} {"current_steps": 28735, "total_steps": 42420, "loss": 0.1189, "lr": 1.4247528937788921e-05, "epoch": 13.547854785478547, "percentage": 67.74, "elapsed_time": "1:43:55", "remaining_time": "0:49:29", "throughput": 4636.82, "total_tokens": 28911968} {"current_steps": 28740, "total_steps": 42420, "loss": 0.4737, "lr": 1.4238243830412646e-05, "epoch": 13.55021216407355, "percentage": 67.75, "elapsed_time": "1:43:56", "remaining_time": "0:49:28", "throughput": 4636.85, "total_tokens": 28917024} {"current_steps": 28745, "total_steps": 42420, "loss": 0.0583, "lr": 1.4228960544818967e-05, "epoch": 13.552569542668552, "percentage": 67.76, "elapsed_time": "1:43:57", "remaining_time": "0:49:27", "throughput": 4636.92, "total_tokens": 28923328} {"current_steps": 28750, "total_steps": 42420, "loss": 0.198, "lr": 1.4219679082579385e-05, "epoch": 13.554926921263554, "percentage": 67.77, "elapsed_time": "1:43:58", "remaining_time": "0:49:26", "throughput": 4636.97, "total_tokens": 28928832} {"current_steps": 28755, "total_steps": 42420, "loss": 0.1139, "lr": 1.4210399445265104e-05, "epoch": 13.557284299858557, "percentage": 67.79, "elapsed_time": "1:43:59", "remaining_time": "0:49:25", "throughput": 4637.0, "total_tokens": 28933600} {"current_steps": 28760, "total_steps": 42420, "loss": 0.0391, "lr": 1.4201121634446996e-05, "epoch": 13.55964167845356, "percentage": 67.8, "elapsed_time": "1:44:00", "remaining_time": "0:49:24", "throughput": 4637.04, "total_tokens": 28938848} {"current_steps": 28765, "total_steps": 42420, "loss": 0.1555, "lr": 1.4191845651695645e-05, "epoch": 13.561999057048562, "percentage": 67.81, "elapsed_time": "1:44:01", "remaining_time": "0:49:23", "throughput": 4637.09, "total_tokens": 28943808} {"current_steps": 28770, "total_steps": 42420, "loss": 0.1065, "lr": 1.4182571498581304e-05, "epoch": 13.564356435643564, "percentage": 67.82, "elapsed_time": "1:44:03", "remaining_time": "0:49:22", "throughput": 4637.15, "total_tokens": 28950272} {"current_steps": 28775, "total_steps": 42420, "loss": 0.0336, "lr": 1.4173299176673938e-05, "epoch": 13.566713814238566, "percentage": 67.83, "elapsed_time": "1:44:04", "remaining_time": "0:49:20", "throughput": 4637.18, "total_tokens": 28954720} {"current_steps": 28780, "total_steps": 42420, "loss": 0.13, "lr": 1.4164028687543196e-05, "epoch": 13.569071192833569, "percentage": 67.85, "elapsed_time": "1:44:05", "remaining_time": "0:49:19", "throughput": 4637.23, "total_tokens": 28959840} {"current_steps": 28785, "total_steps": 42420, "loss": 0.16, "lr": 1.4154760032758412e-05, "epoch": 13.571428571428571, "percentage": 67.86, "elapsed_time": "1:44:06", "remaining_time": "0:49:18", "throughput": 4637.28, "total_tokens": 28965248} {"current_steps": 28790, "total_steps": 42420, "loss": 0.0296, "lr": 1.4145493213888616e-05, "epoch": 13.573785950023574, "percentage": 67.87, "elapsed_time": "1:44:07", "remaining_time": "0:49:17", "throughput": 4637.3, "total_tokens": 28970592} {"current_steps": 28795, "total_steps": 42420, "loss": 0.0394, "lr": 1.4136228232502516e-05, "epoch": 13.576143328618576, "percentage": 67.88, "elapsed_time": "1:44:08", "remaining_time": "0:49:16", "throughput": 4637.35, "total_tokens": 28976736} {"current_steps": 28800, "total_steps": 42420, "loss": 0.1859, "lr": 1.412696509016852e-05, "epoch": 13.578500707213578, "percentage": 67.89, "elapsed_time": "1:44:09", "remaining_time": "0:49:15", "throughput": 4637.41, "total_tokens": 28982432} {"current_steps": 28805, "total_steps": 42420, "loss": 0.0429, "lr": 1.4117703788454734e-05, "epoch": 13.58085808580858, "percentage": 67.9, "elapsed_time": "1:44:10", "remaining_time": "0:49:14", "throughput": 4637.46, "total_tokens": 28987904} {"current_steps": 28810, "total_steps": 42420, "loss": 0.0773, "lr": 1.410844432892891e-05, "epoch": 13.583215464403583, "percentage": 67.92, "elapsed_time": "1:44:11", "remaining_time": "0:49:13", "throughput": 4637.47, "total_tokens": 28992416} {"current_steps": 28815, "total_steps": 42420, "loss": 0.0608, "lr": 1.4099186713158538e-05, "epoch": 13.585572842998586, "percentage": 67.93, "elapsed_time": "1:44:12", "remaining_time": "0:49:12", "throughput": 4637.52, "total_tokens": 28997568} {"current_steps": 28820, "total_steps": 42420, "loss": 0.0884, "lr": 1.408993094271077e-05, "epoch": 13.587930221593588, "percentage": 67.94, "elapsed_time": "1:44:13", "remaining_time": "0:49:11", "throughput": 4637.58, "total_tokens": 29003168} {"current_steps": 28825, "total_steps": 42420, "loss": 0.0913, "lr": 1.408067701915245e-05, "epoch": 13.59028760018859, "percentage": 67.95, "elapsed_time": "1:44:14", "remaining_time": "0:49:10", "throughput": 4637.62, "total_tokens": 29008128} {"current_steps": 28830, "total_steps": 42420, "loss": 0.071, "lr": 1.407142494405011e-05, "epoch": 13.592644978783593, "percentage": 67.96, "elapsed_time": "1:44:15", "remaining_time": "0:49:08", "throughput": 4637.68, "total_tokens": 29013280} {"current_steps": 28835, "total_steps": 42420, "loss": 0.2677, "lr": 1.4062174718969973e-05, "epoch": 13.595002357378595, "percentage": 67.98, "elapsed_time": "1:44:17", "remaining_time": "0:49:07", "throughput": 4637.72, "total_tokens": 29018432} {"current_steps": 28840, "total_steps": 42420, "loss": 0.0588, "lr": 1.405292634547794e-05, "epoch": 13.597359735973598, "percentage": 67.99, "elapsed_time": "1:44:18", "remaining_time": "0:49:06", "throughput": 4637.79, "total_tokens": 29024512} {"current_steps": 28845, "total_steps": 42420, "loss": 0.0995, "lr": 1.4043679825139615e-05, "epoch": 13.5997171145686, "percentage": 68.0, "elapsed_time": "1:44:19", "remaining_time": "0:49:05", "throughput": 4637.83, "total_tokens": 29029600} {"current_steps": 28850, "total_steps": 42420, "loss": 0.0866, "lr": 1.403443515952026e-05, "epoch": 13.602074493163602, "percentage": 68.01, "elapsed_time": "1:44:20", "remaining_time": "0:49:04", "throughput": 4637.88, "total_tokens": 29035136} {"current_steps": 28855, "total_steps": 42420, "loss": 0.0818, "lr": 1.4025192350184846e-05, "epoch": 13.604431871758605, "percentage": 68.02, "elapsed_time": "1:44:21", "remaining_time": "0:49:03", "throughput": 4637.92, "total_tokens": 29040064} {"current_steps": 28860, "total_steps": 42420, "loss": 0.2528, "lr": 1.4015951398698027e-05, "epoch": 13.606789250353607, "percentage": 68.03, "elapsed_time": "1:44:22", "remaining_time": "0:49:02", "throughput": 4637.94, "total_tokens": 29044576} {"current_steps": 28865, "total_steps": 42420, "loss": 0.0707, "lr": 1.4006712306624137e-05, "epoch": 13.60914662894861, "percentage": 68.05, "elapsed_time": "1:44:23", "remaining_time": "0:49:01", "throughput": 4638.0, "total_tokens": 29050272} {"current_steps": 28870, "total_steps": 42420, "loss": 0.1063, "lr": 1.39974750755272e-05, "epoch": 13.611504007543612, "percentage": 68.06, "elapsed_time": "1:44:24", "remaining_time": "0:49:00", "throughput": 4638.04, "total_tokens": 29055456} {"current_steps": 28875, "total_steps": 42420, "loss": 0.1511, "lr": 1.3988239706970917e-05, "epoch": 13.613861386138614, "percentage": 68.07, "elapsed_time": "1:44:25", "remaining_time": "0:48:59", "throughput": 4638.11, "total_tokens": 29061088} {"current_steps": 28880, "total_steps": 42420, "loss": 0.0407, "lr": 1.3979006202518685e-05, "epoch": 13.616218764733617, "percentage": 68.08, "elapsed_time": "1:44:26", "remaining_time": "0:48:58", "throughput": 4638.18, "total_tokens": 29066880} {"current_steps": 28885, "total_steps": 42420, "loss": 0.3119, "lr": 1.3969774563733585e-05, "epoch": 13.61857614332862, "percentage": 68.09, "elapsed_time": "1:44:27", "remaining_time": "0:48:57", "throughput": 4638.21, "total_tokens": 29071712} {"current_steps": 28890, "total_steps": 42420, "loss": 0.0386, "lr": 1.396054479217836e-05, "epoch": 13.620933521923622, "percentage": 68.1, "elapsed_time": "1:44:28", "remaining_time": "0:48:55", "throughput": 4638.18, "total_tokens": 29075744} {"current_steps": 28895, "total_steps": 42420, "loss": 0.0882, "lr": 1.3951316889415464e-05, "epoch": 13.623290900518624, "percentage": 68.12, "elapsed_time": "1:44:29", "remaining_time": "0:48:54", "throughput": 4638.22, "total_tokens": 29081056} {"current_steps": 28900, "total_steps": 42420, "loss": 0.0849, "lr": 1.3942090857007024e-05, "epoch": 13.625648279113626, "percentage": 68.13, "elapsed_time": "1:44:31", "remaining_time": "0:48:53", "throughput": 4638.24, "total_tokens": 29086720} {"current_steps": 28905, "total_steps": 42420, "loss": 0.0732, "lr": 1.3932866696514846e-05, "epoch": 13.628005657708629, "percentage": 68.14, "elapsed_time": "1:44:32", "remaining_time": "0:48:52", "throughput": 4638.28, "total_tokens": 29091424} {"current_steps": 28910, "total_steps": 42420, "loss": 0.1532, "lr": 1.3923644409500425e-05, "epoch": 13.630363036303631, "percentage": 68.15, "elapsed_time": "1:44:33", "remaining_time": "0:48:51", "throughput": 4638.34, "total_tokens": 29097152} {"current_steps": 28915, "total_steps": 42420, "loss": 0.0863, "lr": 1.3914423997524945e-05, "epoch": 13.632720414898632, "percentage": 68.16, "elapsed_time": "1:44:34", "remaining_time": "0:48:50", "throughput": 4638.38, "total_tokens": 29102272} {"current_steps": 28920, "total_steps": 42420, "loss": 0.2161, "lr": 1.3905205462149257e-05, "epoch": 13.635077793493634, "percentage": 68.18, "elapsed_time": "1:44:35", "remaining_time": "0:48:49", "throughput": 4638.41, "total_tokens": 29107712} {"current_steps": 28925, "total_steps": 42420, "loss": 0.0807, "lr": 1.3895988804933913e-05, "epoch": 13.637435172088637, "percentage": 68.19, "elapsed_time": "1:44:36", "remaining_time": "0:48:48", "throughput": 4638.45, "total_tokens": 29112480} {"current_steps": 28930, "total_steps": 42420, "loss": 0.0557, "lr": 1.3886774027439124e-05, "epoch": 13.639792550683639, "percentage": 68.2, "elapsed_time": "1:44:37", "remaining_time": "0:48:47", "throughput": 4638.47, "total_tokens": 29117248} {"current_steps": 28935, "total_steps": 42420, "loss": 0.0624, "lr": 1.3877561131224798e-05, "epoch": 13.642149929278641, "percentage": 68.21, "elapsed_time": "1:44:38", "remaining_time": "0:48:46", "throughput": 4638.47, "total_tokens": 29122624} {"current_steps": 28940, "total_steps": 42420, "loss": 0.1066, "lr": 1.386835011785052e-05, "epoch": 13.644507307873644, "percentage": 68.22, "elapsed_time": "1:44:39", "remaining_time": "0:48:44", "throughput": 4638.49, "total_tokens": 29126816} {"current_steps": 28945, "total_steps": 42420, "loss": 0.0397, "lr": 1.3859140988875569e-05, "epoch": 13.646864686468646, "percentage": 68.23, "elapsed_time": "1:44:40", "remaining_time": "0:48:43", "throughput": 4638.53, "total_tokens": 29132352} {"current_steps": 28950, "total_steps": 42420, "loss": 0.2056, "lr": 1.3849933745858885e-05, "epoch": 13.649222065063649, "percentage": 68.25, "elapsed_time": "1:44:41", "remaining_time": "0:48:42", "throughput": 4638.57, "total_tokens": 29137504} {"current_steps": 28955, "total_steps": 42420, "loss": 0.1189, "lr": 1.38407283903591e-05, "epoch": 13.651579443658651, "percentage": 68.26, "elapsed_time": "1:44:42", "remaining_time": "0:48:41", "throughput": 4638.6, "total_tokens": 29142336} {"current_steps": 28960, "total_steps": 42420, "loss": 0.3073, "lr": 1.3831524923934525e-05, "epoch": 13.653936822253653, "percentage": 68.27, "elapsed_time": "1:44:43", "remaining_time": "0:48:40", "throughput": 4638.65, "total_tokens": 29148448} {"current_steps": 28965, "total_steps": 42420, "loss": 0.0997, "lr": 1.3822323348143163e-05, "epoch": 13.656294200848656, "percentage": 68.28, "elapsed_time": "1:44:44", "remaining_time": "0:48:39", "throughput": 4638.67, "total_tokens": 29153120} {"current_steps": 28970, "total_steps": 42420, "loss": 0.2159, "lr": 1.381312366454266e-05, "epoch": 13.658651579443658, "percentage": 68.29, "elapsed_time": "1:44:45", "remaining_time": "0:48:38", "throughput": 4638.71, "total_tokens": 29158624} {"current_steps": 28975, "total_steps": 42420, "loss": 0.1019, "lr": 1.3803925874690377e-05, "epoch": 13.66100895803866, "percentage": 68.31, "elapsed_time": "1:44:47", "remaining_time": "0:48:37", "throughput": 4638.75, "total_tokens": 29164064} {"current_steps": 28980, "total_steps": 42420, "loss": 0.328, "lr": 1.3794729980143344e-05, "epoch": 13.663366336633663, "percentage": 68.32, "elapsed_time": "1:44:47", "remaining_time": "0:48:36", "throughput": 4638.8, "total_tokens": 29168608} {"current_steps": 28985, "total_steps": 42420, "loss": 0.0317, "lr": 1.3785535982458284e-05, "epoch": 13.665723715228665, "percentage": 68.33, "elapsed_time": "1:44:48", "remaining_time": "0:48:35", "throughput": 4638.82, "total_tokens": 29173120} {"current_steps": 28990, "total_steps": 42420, "loss": 0.1834, "lr": 1.3776343883191562e-05, "epoch": 13.668081093823668, "percentage": 68.34, "elapsed_time": "1:44:49", "remaining_time": "0:48:33", "throughput": 4638.83, "total_tokens": 29177920} {"current_steps": 28995, "total_steps": 42420, "loss": 0.0653, "lr": 1.376715368389925e-05, "epoch": 13.67043847241867, "percentage": 68.35, "elapsed_time": "1:44:50", "remaining_time": "0:48:32", "throughput": 4638.84, "total_tokens": 29182528} {"current_steps": 29000, "total_steps": 42420, "loss": 0.126, "lr": 1.3757965386137098e-05, "epoch": 13.672795851013673, "percentage": 68.36, "elapsed_time": "1:44:51", "remaining_time": "0:48:31", "throughput": 4638.84, "total_tokens": 29186368} {"current_steps": 29005, "total_steps": 42420, "loss": 0.1346, "lr": 1.3748778991460526e-05, "epoch": 13.675153229608675, "percentage": 68.38, "elapsed_time": "1:44:52", "remaining_time": "0:48:30", "throughput": 4638.85, "total_tokens": 29191552} {"current_steps": 29010, "total_steps": 42420, "loss": 0.0395, "lr": 1.3739594501424641e-05, "epoch": 13.677510608203677, "percentage": 68.39, "elapsed_time": "1:44:53", "remaining_time": "0:48:29", "throughput": 4638.87, "total_tokens": 29196352} {"current_steps": 29015, "total_steps": 42420, "loss": 0.1731, "lr": 1.373041191758422e-05, "epoch": 13.67986798679868, "percentage": 68.4, "elapsed_time": "1:44:54", "remaining_time": "0:48:28", "throughput": 4638.9, "total_tokens": 29200960} {"current_steps": 29020, "total_steps": 42420, "loss": 0.1987, "lr": 1.372123124149371e-05, "epoch": 13.682225365393682, "percentage": 68.41, "elapsed_time": "1:44:55", "remaining_time": "0:48:27", "throughput": 4638.93, "total_tokens": 29205312} {"current_steps": 29025, "total_steps": 42420, "loss": 0.0833, "lr": 1.3712052474707243e-05, "epoch": 13.684582743988685, "percentage": 68.42, "elapsed_time": "1:44:56", "remaining_time": "0:48:25", "throughput": 4638.97, "total_tokens": 29209952} {"current_steps": 29030, "total_steps": 42420, "loss": 0.0942, "lr": 1.3702875618778638e-05, "epoch": 13.686940122583687, "percentage": 68.43, "elapsed_time": "1:44:57", "remaining_time": "0:48:24", "throughput": 4639.02, "total_tokens": 29215424} {"current_steps": 29035, "total_steps": 42420, "loss": 0.0369, "lr": 1.3693700675261373e-05, "epoch": 13.68929750117869, "percentage": 68.45, "elapsed_time": "1:44:58", "remaining_time": "0:48:23", "throughput": 4639.06, "total_tokens": 29221024} {"current_steps": 29040, "total_steps": 42420, "loss": 0.0751, "lr": 1.3684527645708616e-05, "epoch": 13.691654879773692, "percentage": 68.46, "elapsed_time": "1:44:59", "remaining_time": "0:48:22", "throughput": 4639.09, "total_tokens": 29225824} {"current_steps": 29045, "total_steps": 42420, "loss": 0.0182, "lr": 1.36753565316732e-05, "epoch": 13.694012258368694, "percentage": 68.47, "elapsed_time": "1:45:00", "remaining_time": "0:48:21", "throughput": 4639.1, "total_tokens": 29230144} {"current_steps": 29050, "total_steps": 42420, "loss": 0.0784, "lr": 1.3666187334707645e-05, "epoch": 13.696369636963697, "percentage": 68.48, "elapsed_time": "1:45:02", "remaining_time": "0:48:20", "throughput": 4639.14, "total_tokens": 29237152} {"current_steps": 29055, "total_steps": 42420, "loss": 0.1419, "lr": 1.3657020056364145e-05, "epoch": 13.698727015558699, "percentage": 68.49, "elapsed_time": "1:45:03", "remaining_time": "0:48:19", "throughput": 4639.15, "total_tokens": 29242720} {"current_steps": 29060, "total_steps": 42420, "loss": 0.0257, "lr": 1.3647854698194545e-05, "epoch": 13.701084394153701, "percentage": 68.51, "elapsed_time": "1:45:04", "remaining_time": "0:48:18", "throughput": 4639.17, "total_tokens": 29247104} {"current_steps": 29065, "total_steps": 42420, "loss": 0.1742, "lr": 1.3638691261750403e-05, "epoch": 13.703441772748704, "percentage": 68.52, "elapsed_time": "1:45:05", "remaining_time": "0:48:17", "throughput": 4639.21, "total_tokens": 29251712} {"current_steps": 29070, "total_steps": 42420, "loss": 0.1157, "lr": 1.362952974858292e-05, "epoch": 13.705799151343706, "percentage": 68.53, "elapsed_time": "1:45:06", "remaining_time": "0:48:16", "throughput": 4639.23, "total_tokens": 29255936} {"current_steps": 29075, "total_steps": 42420, "loss": 0.0498, "lr": 1.3620370160242993e-05, "epoch": 13.708156529938709, "percentage": 68.54, "elapsed_time": "1:45:07", "remaining_time": "0:48:14", "throughput": 4639.26, "total_tokens": 29260448} {"current_steps": 29080, "total_steps": 42420, "loss": 0.1318, "lr": 1.361121249828118e-05, "epoch": 13.710513908533711, "percentage": 68.55, "elapsed_time": "1:45:08", "remaining_time": "0:48:13", "throughput": 4639.29, "total_tokens": 29265760} {"current_steps": 29085, "total_steps": 42420, "loss": 0.0938, "lr": 1.3602056764247722e-05, "epoch": 13.712871287128714, "percentage": 68.56, "elapsed_time": "1:45:09", "remaining_time": "0:48:12", "throughput": 4639.3, "total_tokens": 29270208} {"current_steps": 29090, "total_steps": 42420, "loss": 0.0144, "lr": 1.3592902959692533e-05, "epoch": 13.715228665723716, "percentage": 68.58, "elapsed_time": "1:45:10", "remaining_time": "0:48:11", "throughput": 4639.35, "total_tokens": 29275520} {"current_steps": 29095, "total_steps": 42420, "loss": 0.1455, "lr": 1.3583751086165197e-05, "epoch": 13.717586044318718, "percentage": 68.59, "elapsed_time": "1:45:11", "remaining_time": "0:48:10", "throughput": 4639.38, "total_tokens": 29280544} {"current_steps": 29100, "total_steps": 42420, "loss": 0.0986, "lr": 1.3574601145214954e-05, "epoch": 13.71994342291372, "percentage": 68.6, "elapsed_time": "1:45:12", "remaining_time": "0:48:09", "throughput": 4639.42, "total_tokens": 29285568} {"current_steps": 29105, "total_steps": 42420, "loss": 0.1057, "lr": 1.3565453138390746e-05, "epoch": 13.722300801508723, "percentage": 68.61, "elapsed_time": "1:45:13", "remaining_time": "0:48:08", "throughput": 4639.49, "total_tokens": 29291520} {"current_steps": 29110, "total_steps": 42420, "loss": 0.0645, "lr": 1.3556307067241175e-05, "epoch": 13.724658180103724, "percentage": 68.62, "elapsed_time": "1:45:14", "remaining_time": "0:48:07", "throughput": 4639.54, "total_tokens": 29297376} {"current_steps": 29115, "total_steps": 42420, "loss": 0.2249, "lr": 1.3547162933314514e-05, "epoch": 13.727015558698728, "percentage": 68.64, "elapsed_time": "1:45:15", "remaining_time": "0:48:06", "throughput": 4639.57, "total_tokens": 29302080} {"current_steps": 29120, "total_steps": 42420, "loss": 0.2106, "lr": 1.3538020738158708e-05, "epoch": 13.729372937293729, "percentage": 68.65, "elapsed_time": "1:45:16", "remaining_time": "0:48:05", "throughput": 4639.62, "total_tokens": 29307008} {"current_steps": 29125, "total_steps": 42420, "loss": 0.2031, "lr": 1.3528880483321383e-05, "epoch": 13.731730315888731, "percentage": 68.66, "elapsed_time": "1:45:17", "remaining_time": "0:48:03", "throughput": 4639.66, "total_tokens": 29312160} {"current_steps": 29130, "total_steps": 42420, "loss": 0.084, "lr": 1.351974217034982e-05, "epoch": 13.734087694483733, "percentage": 68.67, "elapsed_time": "1:45:18", "remaining_time": "0:48:02", "throughput": 4639.67, "total_tokens": 29316416} {"current_steps": 29135, "total_steps": 42420, "loss": 0.1073, "lr": 1.3510605800790994e-05, "epoch": 13.736445073078736, "percentage": 68.68, "elapsed_time": "1:45:19", "remaining_time": "0:48:01", "throughput": 4639.7, "total_tokens": 29321344} {"current_steps": 29140, "total_steps": 42420, "loss": 0.1934, "lr": 1.3501471376191516e-05, "epoch": 13.738802451673738, "percentage": 68.69, "elapsed_time": "1:45:20", "remaining_time": "0:48:00", "throughput": 4639.75, "total_tokens": 29327136} {"current_steps": 29145, "total_steps": 42420, "loss": 0.1369, "lr": 1.3492338898097703e-05, "epoch": 13.74115983026874, "percentage": 68.71, "elapsed_time": "1:45:21", "remaining_time": "0:47:59", "throughput": 4639.77, "total_tokens": 29331712} {"current_steps": 29150, "total_steps": 42420, "loss": 0.2846, "lr": 1.3483208368055524e-05, "epoch": 13.743517208863743, "percentage": 68.72, "elapsed_time": "1:45:22", "remaining_time": "0:47:58", "throughput": 4639.81, "total_tokens": 29336512} {"current_steps": 29155, "total_steps": 42420, "loss": 0.0253, "lr": 1.3474079787610624e-05, "epoch": 13.745874587458745, "percentage": 68.73, "elapsed_time": "1:45:23", "remaining_time": "0:47:57", "throughput": 4639.82, "total_tokens": 29340832} {"current_steps": 29160, "total_steps": 42420, "loss": 0.1728, "lr": 1.3464953158308319e-05, "epoch": 13.748231966053748, "percentage": 68.74, "elapsed_time": "1:45:24", "remaining_time": "0:47:56", "throughput": 4639.88, "total_tokens": 29346016} {"current_steps": 29165, "total_steps": 42420, "loss": 0.0779, "lr": 1.3455828481693589e-05, "epoch": 13.75058934464875, "percentage": 68.75, "elapsed_time": "1:45:25", "remaining_time": "0:47:55", "throughput": 4639.91, "total_tokens": 29351488} {"current_steps": 29170, "total_steps": 42420, "loss": 0.168, "lr": 1.3446705759311088e-05, "epoch": 13.752946723243753, "percentage": 68.76, "elapsed_time": "1:45:26", "remaining_time": "0:47:53", "throughput": 4639.92, "total_tokens": 29355712} {"current_steps": 29175, "total_steps": 42420, "loss": 0.1488, "lr": 1.343758499270515e-05, "epoch": 13.755304101838755, "percentage": 68.78, "elapsed_time": "1:45:27", "remaining_time": "0:47:52", "throughput": 4639.95, "total_tokens": 29360256} {"current_steps": 29180, "total_steps": 42420, "loss": 0.0266, "lr": 1.342846618341974e-05, "epoch": 13.757661480433757, "percentage": 68.79, "elapsed_time": "1:45:28", "remaining_time": "0:47:51", "throughput": 4639.99, "total_tokens": 29365088} {"current_steps": 29185, "total_steps": 42420, "loss": 0.0832, "lr": 1.3419349332998534e-05, "epoch": 13.76001885902876, "percentage": 68.8, "elapsed_time": "1:45:29", "remaining_time": "0:47:50", "throughput": 4640.04, "total_tokens": 29369952} {"current_steps": 29190, "total_steps": 42420, "loss": 0.0439, "lr": 1.3410234442984859e-05, "epoch": 13.762376237623762, "percentage": 68.81, "elapsed_time": "1:45:30", "remaining_time": "0:47:49", "throughput": 4640.08, "total_tokens": 29375392} {"current_steps": 29195, "total_steps": 42420, "loss": 0.1019, "lr": 1.3401121514921708e-05, "epoch": 13.764733616218765, "percentage": 68.82, "elapsed_time": "1:45:31", "remaining_time": "0:47:48", "throughput": 4640.11, "total_tokens": 29381024} {"current_steps": 29200, "total_steps": 42420, "loss": 0.2359, "lr": 1.3392010550351747e-05, "epoch": 13.767090994813767, "percentage": 68.84, "elapsed_time": "1:45:33", "remaining_time": "0:47:47", "throughput": 4640.17, "total_tokens": 29387232} {"current_steps": 29205, "total_steps": 42420, "loss": 0.1371, "lr": 1.3382901550817309e-05, "epoch": 13.76944837340877, "percentage": 68.85, "elapsed_time": "1:45:34", "remaining_time": "0:47:46", "throughput": 4640.16, "total_tokens": 29391232} {"current_steps": 29210, "total_steps": 42420, "loss": 0.0783, "lr": 1.33737945178604e-05, "epoch": 13.771805752003772, "percentage": 68.86, "elapsed_time": "1:45:35", "remaining_time": "0:47:44", "throughput": 4640.19, "total_tokens": 29395936} {"current_steps": 29215, "total_steps": 42420, "loss": 0.0477, "lr": 1.3364689453022666e-05, "epoch": 13.774163130598774, "percentage": 68.87, "elapsed_time": "1:45:36", "remaining_time": "0:47:43", "throughput": 4640.25, "total_tokens": 29401600} {"current_steps": 29220, "total_steps": 42420, "loss": 0.1154, "lr": 1.3355586357845453e-05, "epoch": 13.776520509193777, "percentage": 68.88, "elapsed_time": "1:45:37", "remaining_time": "0:47:42", "throughput": 4640.31, "total_tokens": 29407648} {"current_steps": 29225, "total_steps": 42420, "loss": 0.0466, "lr": 1.3346485233869768e-05, "epoch": 13.778877887788779, "percentage": 68.89, "elapsed_time": "1:45:38", "remaining_time": "0:47:41", "throughput": 4640.35, "total_tokens": 29412416} {"current_steps": 29230, "total_steps": 42420, "loss": 0.1048, "lr": 1.333738608263626e-05, "epoch": 13.781235266383781, "percentage": 68.91, "elapsed_time": "1:45:39", "remaining_time": "0:47:40", "throughput": 4640.36, "total_tokens": 29417376} {"current_steps": 29235, "total_steps": 42420, "loss": 0.1052, "lr": 1.3328288905685266e-05, "epoch": 13.783592644978784, "percentage": 68.92, "elapsed_time": "1:45:40", "remaining_time": "0:47:39", "throughput": 4640.38, "total_tokens": 29421952} {"current_steps": 29240, "total_steps": 42420, "loss": 0.0349, "lr": 1.3319193704556786e-05, "epoch": 13.785950023573786, "percentage": 68.93, "elapsed_time": "1:45:41", "remaining_time": "0:47:38", "throughput": 4640.43, "total_tokens": 29427232} {"current_steps": 29245, "total_steps": 42420, "loss": 0.0776, "lr": 1.3310100480790483e-05, "epoch": 13.788307402168789, "percentage": 68.94, "elapsed_time": "1:45:42", "remaining_time": "0:47:37", "throughput": 4640.44, "total_tokens": 29431488} {"current_steps": 29250, "total_steps": 42420, "loss": 0.134, "lr": 1.3301009235925684e-05, "epoch": 13.790664780763791, "percentage": 68.95, "elapsed_time": "1:45:43", "remaining_time": "0:47:36", "throughput": 4640.5, "total_tokens": 29437536} {"current_steps": 29255, "total_steps": 42420, "loss": 0.0409, "lr": 1.3291919971501387e-05, "epoch": 13.793022159358793, "percentage": 68.97, "elapsed_time": "1:45:44", "remaining_time": "0:47:35", "throughput": 4640.55, "total_tokens": 29442624} {"current_steps": 29260, "total_steps": 42420, "loss": 0.0677, "lr": 1.3282832689056246e-05, "epoch": 13.795379537953796, "percentage": 68.98, "elapsed_time": "1:45:45", "remaining_time": "0:47:34", "throughput": 4640.59, "total_tokens": 29447904} {"current_steps": 29265, "total_steps": 42420, "loss": 0.0698, "lr": 1.3273747390128593e-05, "epoch": 13.797736916548798, "percentage": 68.99, "elapsed_time": "1:45:46", "remaining_time": "0:47:32", "throughput": 4640.62, "total_tokens": 29453024} {"current_steps": 29270, "total_steps": 42420, "loss": 0.1617, "lr": 1.3264664076256398e-05, "epoch": 13.8000942951438, "percentage": 69.0, "elapsed_time": "1:45:47", "remaining_time": "0:47:31", "throughput": 4640.66, "total_tokens": 29458560} {"current_steps": 29275, "total_steps": 42420, "loss": 0.0691, "lr": 1.325558274897732e-05, "epoch": 13.802451673738803, "percentage": 69.01, "elapsed_time": "1:45:48", "remaining_time": "0:47:30", "throughput": 4640.67, "total_tokens": 29462688} {"current_steps": 29280, "total_steps": 42420, "loss": 0.0762, "lr": 1.324650340982867e-05, "epoch": 13.804809052333805, "percentage": 69.02, "elapsed_time": "1:45:49", "remaining_time": "0:47:29", "throughput": 4640.72, "total_tokens": 29467680} {"current_steps": 29285, "total_steps": 42420, "loss": 0.0477, "lr": 1.3237426060347436e-05, "epoch": 13.807166430928808, "percentage": 69.04, "elapsed_time": "1:45:50", "remaining_time": "0:47:28", "throughput": 4640.73, "total_tokens": 29471968} {"current_steps": 29290, "total_steps": 42420, "loss": 0.1983, "lr": 1.3228350702070247e-05, "epoch": 13.80952380952381, "percentage": 69.05, "elapsed_time": "1:45:51", "remaining_time": "0:47:27", "throughput": 4640.75, "total_tokens": 29477088} {"current_steps": 29295, "total_steps": 42420, "loss": 0.1669, "lr": 1.3219277336533418e-05, "epoch": 13.811881188118813, "percentage": 69.06, "elapsed_time": "1:45:52", "remaining_time": "0:47:26", "throughput": 4640.75, "total_tokens": 29481056} {"current_steps": 29300, "total_steps": 42420, "loss": 0.0502, "lr": 1.3210205965272909e-05, "epoch": 13.814238566713815, "percentage": 69.07, "elapsed_time": "1:45:53", "remaining_time": "0:47:25", "throughput": 4640.77, "total_tokens": 29486016} {"current_steps": 29305, "total_steps": 42420, "loss": 0.0937, "lr": 1.3201136589824359e-05, "epoch": 13.816595945308817, "percentage": 69.08, "elapsed_time": "1:45:54", "remaining_time": "0:47:24", "throughput": 4640.84, "total_tokens": 29492096} {"current_steps": 29310, "total_steps": 42420, "loss": 0.0475, "lr": 1.319206921172304e-05, "epoch": 13.81895332390382, "percentage": 69.09, "elapsed_time": "1:45:56", "remaining_time": "0:47:23", "throughput": 4640.92, "total_tokens": 29498752} {"current_steps": 29315, "total_steps": 42420, "loss": 0.0634, "lr": 1.318300383250392e-05, "epoch": 13.82131070249882, "percentage": 69.11, "elapsed_time": "1:45:57", "remaining_time": "0:47:21", "throughput": 4640.89, "total_tokens": 29502720} {"current_steps": 29320, "total_steps": 42420, "loss": 0.1778, "lr": 1.3173940453701608e-05, "epoch": 13.823668081093825, "percentage": 69.12, "elapsed_time": "1:45:57", "remaining_time": "0:47:20", "throughput": 4640.89, "total_tokens": 29506496} {"current_steps": 29325, "total_steps": 42420, "loss": 0.0438, "lr": 1.3164879076850384e-05, "epoch": 13.826025459688825, "percentage": 69.13, "elapsed_time": "1:45:59", "remaining_time": "0:47:19", "throughput": 4640.95, "total_tokens": 29512384} {"current_steps": 29330, "total_steps": 42420, "loss": 0.0612, "lr": 1.3155819703484179e-05, "epoch": 13.828382838283828, "percentage": 69.14, "elapsed_time": "1:46:00", "remaining_time": "0:47:18", "throughput": 4640.98, "total_tokens": 29516800} {"current_steps": 29335, "total_steps": 42420, "loss": 0.1801, "lr": 1.31467623351366e-05, "epoch": 13.83074021687883, "percentage": 69.15, "elapsed_time": "1:46:01", "remaining_time": "0:47:17", "throughput": 4641.04, "total_tokens": 29522368} {"current_steps": 29340, "total_steps": 42420, "loss": 0.1767, "lr": 1.3137706973340899e-05, "epoch": 13.833097595473832, "percentage": 69.17, "elapsed_time": "1:46:02", "remaining_time": "0:47:16", "throughput": 4641.05, "total_tokens": 29526720} {"current_steps": 29345, "total_steps": 42420, "loss": 0.0919, "lr": 1.3128653619630007e-05, "epoch": 13.835454974068835, "percentage": 69.18, "elapsed_time": "1:46:03", "remaining_time": "0:47:15", "throughput": 4641.05, "total_tokens": 29531200} {"current_steps": 29350, "total_steps": 42420, "loss": 0.0876, "lr": 1.3119602275536485e-05, "epoch": 13.837812352663837, "percentage": 69.19, "elapsed_time": "1:46:04", "remaining_time": "0:47:14", "throughput": 4641.12, "total_tokens": 29537312} {"current_steps": 29355, "total_steps": 42420, "loss": 0.0594, "lr": 1.311055294259258e-05, "epoch": 13.84016973125884, "percentage": 69.2, "elapsed_time": "1:46:05", "remaining_time": "0:47:12", "throughput": 4641.16, "total_tokens": 29542400} {"current_steps": 29360, "total_steps": 42420, "loss": 0.3815, "lr": 1.310150562233019e-05, "epoch": 13.842527109853842, "percentage": 69.21, "elapsed_time": "1:46:06", "remaining_time": "0:47:11", "throughput": 4641.2, "total_tokens": 29547232} {"current_steps": 29365, "total_steps": 42420, "loss": 0.1157, "lr": 1.3092460316280869e-05, "epoch": 13.844884488448844, "percentage": 69.22, "elapsed_time": "1:46:07", "remaining_time": "0:47:10", "throughput": 4641.26, "total_tokens": 29553888} {"current_steps": 29370, "total_steps": 42420, "loss": 0.1861, "lr": 1.3083417025975841e-05, "epoch": 13.847241867043847, "percentage": 69.24, "elapsed_time": "1:46:08", "remaining_time": "0:47:09", "throughput": 4641.25, "total_tokens": 29558240} {"current_steps": 29375, "total_steps": 42420, "loss": 0.0741, "lr": 1.3074375752945982e-05, "epoch": 13.84959924563885, "percentage": 69.25, "elapsed_time": "1:46:09", "remaining_time": "0:47:08", "throughput": 4641.28, "total_tokens": 29563456} {"current_steps": 29380, "total_steps": 42420, "loss": 0.1007, "lr": 1.306533649872182e-05, "epoch": 13.851956624233852, "percentage": 69.26, "elapsed_time": "1:46:10", "remaining_time": "0:47:07", "throughput": 4641.31, "total_tokens": 29568256} {"current_steps": 29385, "total_steps": 42420, "loss": 0.0897, "lr": 1.3056299264833558e-05, "epoch": 13.854314002828854, "percentage": 69.27, "elapsed_time": "1:46:11", "remaining_time": "0:47:06", "throughput": 4641.37, "total_tokens": 29573568} {"current_steps": 29390, "total_steps": 42420, "loss": 0.071, "lr": 1.3047264052811028e-05, "epoch": 13.856671381423856, "percentage": 69.28, "elapsed_time": "1:46:12", "remaining_time": "0:47:05", "throughput": 4641.36, "total_tokens": 29577632} {"current_steps": 29395, "total_steps": 42420, "loss": 0.1342, "lr": 1.303823086418375e-05, "epoch": 13.859028760018859, "percentage": 69.3, "elapsed_time": "1:46:13", "remaining_time": "0:47:04", "throughput": 4641.37, "total_tokens": 29581888} {"current_steps": 29400, "total_steps": 42420, "loss": 0.0469, "lr": 1.3029199700480887e-05, "epoch": 13.861386138613861, "percentage": 69.31, "elapsed_time": "1:46:14", "remaining_time": "0:47:03", "throughput": 4641.41, "total_tokens": 29586848} {"current_steps": 29405, "total_steps": 42420, "loss": 0.1399, "lr": 1.302017056323126e-05, "epoch": 13.863743517208864, "percentage": 69.32, "elapsed_time": "1:46:15", "remaining_time": "0:47:01", "throughput": 4641.44, "total_tokens": 29591616} {"current_steps": 29410, "total_steps": 42420, "loss": 0.0206, "lr": 1.3011143453963353e-05, "epoch": 13.866100895803866, "percentage": 69.33, "elapsed_time": "1:46:16", "remaining_time": "0:47:00", "throughput": 4641.48, "total_tokens": 29596416} {"current_steps": 29415, "total_steps": 42420, "loss": 0.0572, "lr": 1.3002118374205302e-05, "epoch": 13.868458274398868, "percentage": 69.34, "elapsed_time": "1:46:17", "remaining_time": "0:46:59", "throughput": 4641.49, "total_tokens": 29600960} {"current_steps": 29420, "total_steps": 42420, "loss": 0.2694, "lr": 1.2993095325484894e-05, "epoch": 13.87081565299387, "percentage": 69.35, "elapsed_time": "1:46:18", "remaining_time": "0:46:58", "throughput": 4641.47, "total_tokens": 29604736} {"current_steps": 29425, "total_steps": 42420, "loss": 0.1486, "lr": 1.2984074309329592e-05, "epoch": 13.873173031588873, "percentage": 69.37, "elapsed_time": "1:46:19", "remaining_time": "0:46:57", "throughput": 4641.49, "total_tokens": 29608768} {"current_steps": 29430, "total_steps": 42420, "loss": 0.1932, "lr": 1.2975055327266482e-05, "epoch": 13.875530410183876, "percentage": 69.38, "elapsed_time": "1:46:20", "remaining_time": "0:46:56", "throughput": 4641.54, "total_tokens": 29616352} {"current_steps": 29435, "total_steps": 42420, "loss": 0.1753, "lr": 1.2966038380822344e-05, "epoch": 13.877887788778878, "percentage": 69.39, "elapsed_time": "1:46:22", "remaining_time": "0:46:55", "throughput": 4641.6, "total_tokens": 29622912} {"current_steps": 29440, "total_steps": 42420, "loss": 0.0584, "lr": 1.2957023471523571e-05, "epoch": 13.88024516737388, "percentage": 69.4, "elapsed_time": "1:46:22", "remaining_time": "0:46:54", "throughput": 4641.61, "total_tokens": 29627328} {"current_steps": 29445, "total_steps": 42420, "loss": 0.0586, "lr": 1.2948010600896246e-05, "epoch": 13.882602545968883, "percentage": 69.41, "elapsed_time": "1:46:24", "remaining_time": "0:46:53", "throughput": 4641.66, "total_tokens": 29633536} {"current_steps": 29450, "total_steps": 42420, "loss": 0.093, "lr": 1.2938999770466098e-05, "epoch": 13.884959924563885, "percentage": 69.42, "elapsed_time": "1:46:25", "remaining_time": "0:46:52", "throughput": 4641.72, "total_tokens": 29639200} {"current_steps": 29455, "total_steps": 42420, "loss": 0.1534, "lr": 1.29299909817585e-05, "epoch": 13.887317303158888, "percentage": 69.44, "elapsed_time": "1:46:26", "remaining_time": "0:46:51", "throughput": 4641.76, "total_tokens": 29644416} {"current_steps": 29460, "total_steps": 42420, "loss": 0.1329, "lr": 1.2920984236298494e-05, "epoch": 13.88967468175389, "percentage": 69.45, "elapsed_time": "1:46:27", "remaining_time": "0:46:49", "throughput": 4641.8, "total_tokens": 29649216} {"current_steps": 29465, "total_steps": 42420, "loss": 0.2314, "lr": 1.291197953561077e-05, "epoch": 13.892032060348892, "percentage": 69.46, "elapsed_time": "1:46:28", "remaining_time": "0:46:48", "throughput": 4641.85, "total_tokens": 29654528} {"current_steps": 29470, "total_steps": 42420, "loss": 0.0988, "lr": 1.2902976881219676e-05, "epoch": 13.894389438943895, "percentage": 69.47, "elapsed_time": "1:46:29", "remaining_time": "0:46:47", "throughput": 4641.9, "total_tokens": 29659456} {"current_steps": 29475, "total_steps": 42420, "loss": 0.0742, "lr": 1.289397627464919e-05, "epoch": 13.896746817538897, "percentage": 69.48, "elapsed_time": "1:46:30", "remaining_time": "0:46:46", "throughput": 4641.95, "total_tokens": 29664992} {"current_steps": 29480, "total_steps": 42420, "loss": 0.13, "lr": 1.2884977717422969e-05, "epoch": 13.8991041961339, "percentage": 69.5, "elapsed_time": "1:46:31", "remaining_time": "0:46:45", "throughput": 4642.05, "total_tokens": 29671776} {"current_steps": 29485, "total_steps": 42420, "loss": 0.262, "lr": 1.287598121106432e-05, "epoch": 13.901461574728902, "percentage": 69.51, "elapsed_time": "1:46:32", "remaining_time": "0:46:44", "throughput": 4642.07, "total_tokens": 29676128} {"current_steps": 29490, "total_steps": 42420, "loss": 0.1636, "lr": 1.28669867570962e-05, "epoch": 13.903818953323904, "percentage": 69.52, "elapsed_time": "1:46:33", "remaining_time": "0:46:43", "throughput": 4642.08, "total_tokens": 29680736} {"current_steps": 29495, "total_steps": 42420, "loss": 0.0485, "lr": 1.2857994357041214e-05, "epoch": 13.906176331918907, "percentage": 69.53, "elapsed_time": "1:46:34", "remaining_time": "0:46:42", "throughput": 4642.12, "total_tokens": 29685664} {"current_steps": 29500, "total_steps": 42420, "loss": 0.0513, "lr": 1.2849004012421626e-05, "epoch": 13.90853371051391, "percentage": 69.54, "elapsed_time": "1:46:35", "remaining_time": "0:46:41", "throughput": 4642.14, "total_tokens": 29690272} {"current_steps": 29505, "total_steps": 42420, "loss": 0.092, "lr": 1.2840015724759344e-05, "epoch": 13.910891089108912, "percentage": 69.55, "elapsed_time": "1:46:36", "remaining_time": "0:46:40", "throughput": 4642.19, "total_tokens": 29695904} {"current_steps": 29510, "total_steps": 42420, "loss": 0.0786, "lr": 1.2831029495575947e-05, "epoch": 13.913248467703912, "percentage": 69.57, "elapsed_time": "1:46:37", "remaining_time": "0:46:38", "throughput": 4642.18, "total_tokens": 29699776} {"current_steps": 29515, "total_steps": 42420, "loss": 0.1039, "lr": 1.2822045326392627e-05, "epoch": 13.915605846298917, "percentage": 69.58, "elapsed_time": "1:46:39", "remaining_time": "0:46:37", "throughput": 4642.26, "total_tokens": 29706144} {"current_steps": 29520, "total_steps": 42420, "loss": 0.0389, "lr": 1.2813063218730265e-05, "epoch": 13.917963224893917, "percentage": 69.59, "elapsed_time": "1:46:39", "remaining_time": "0:46:36", "throughput": 4642.24, "total_tokens": 29709792} {"current_steps": 29525, "total_steps": 42420, "loss": 0.0763, "lr": 1.2804083174109377e-05, "epoch": 13.92032060348892, "percentage": 69.6, "elapsed_time": "1:46:41", "remaining_time": "0:46:35", "throughput": 4642.3, "total_tokens": 29716512} {"current_steps": 29530, "total_steps": 42420, "loss": 0.0939, "lr": 1.2795105194050133e-05, "epoch": 13.922677982083922, "percentage": 69.61, "elapsed_time": "1:46:42", "remaining_time": "0:46:34", "throughput": 4642.34, "total_tokens": 29721568} {"current_steps": 29535, "total_steps": 42420, "loss": 0.0299, "lr": 1.278612928007235e-05, "epoch": 13.925035360678924, "percentage": 69.63, "elapsed_time": "1:46:43", "remaining_time": "0:46:33", "throughput": 4642.37, "total_tokens": 29725984} {"current_steps": 29540, "total_steps": 42420, "loss": 0.0868, "lr": 1.2777155433695503e-05, "epoch": 13.927392739273927, "percentage": 69.64, "elapsed_time": "1:46:44", "remaining_time": "0:46:32", "throughput": 4642.44, "total_tokens": 29732448} {"current_steps": 29545, "total_steps": 42420, "loss": 0.1426, "lr": 1.2768183656438709e-05, "epoch": 13.92975011786893, "percentage": 69.65, "elapsed_time": "1:46:45", "remaining_time": "0:46:31", "throughput": 4642.47, "total_tokens": 29737088} {"current_steps": 29550, "total_steps": 42420, "loss": 0.1679, "lr": 1.2759213949820748e-05, "epoch": 13.932107496463932, "percentage": 69.66, "elapsed_time": "1:46:46", "remaining_time": "0:46:30", "throughput": 4642.49, "total_tokens": 29741984} {"current_steps": 29555, "total_steps": 42420, "loss": 0.1847, "lr": 1.2750246315360015e-05, "epoch": 13.934464875058934, "percentage": 69.67, "elapsed_time": "1:46:47", "remaining_time": "0:46:29", "throughput": 4642.5, "total_tokens": 29746784} {"current_steps": 29560, "total_steps": 42420, "loss": 0.2549, "lr": 1.2741280754574595e-05, "epoch": 13.936822253653936, "percentage": 69.68, "elapsed_time": "1:46:48", "remaining_time": "0:46:27", "throughput": 4642.54, "total_tokens": 29751616} {"current_steps": 29565, "total_steps": 42420, "loss": 0.1952, "lr": 1.27323172689822e-05, "epoch": 13.939179632248939, "percentage": 69.7, "elapsed_time": "1:46:49", "remaining_time": "0:46:26", "throughput": 4642.55, "total_tokens": 29755936} {"current_steps": 29570, "total_steps": 42420, "loss": 0.0305, "lr": 1.27233558601002e-05, "epoch": 13.941537010843941, "percentage": 69.71, "elapsed_time": "1:46:50", "remaining_time": "0:46:25", "throughput": 4642.53, "total_tokens": 29759936} {"current_steps": 29575, "total_steps": 42420, "loss": 0.1503, "lr": 1.2714396529445605e-05, "epoch": 13.943894389438944, "percentage": 69.72, "elapsed_time": "1:46:51", "remaining_time": "0:46:24", "throughput": 4642.57, "total_tokens": 29765632} {"current_steps": 29580, "total_steps": 42420, "loss": 0.0588, "lr": 1.270543927853508e-05, "epoch": 13.946251768033946, "percentage": 69.73, "elapsed_time": "1:46:52", "remaining_time": "0:46:23", "throughput": 4642.61, "total_tokens": 29770656} {"current_steps": 29585, "total_steps": 42420, "loss": 0.1958, "lr": 1.2696484108884938e-05, "epoch": 13.948609146628948, "percentage": 69.74, "elapsed_time": "1:46:53", "remaining_time": "0:46:22", "throughput": 4642.64, "total_tokens": 29775456} {"current_steps": 29590, "total_steps": 42420, "loss": 0.0702, "lr": 1.2687531022011145e-05, "epoch": 13.95096652522395, "percentage": 69.75, "elapsed_time": "1:46:54", "remaining_time": "0:46:21", "throughput": 4642.66, "total_tokens": 29779808} {"current_steps": 29595, "total_steps": 42420, "loss": 0.1733, "lr": 1.2678580019429282e-05, "epoch": 13.953323903818953, "percentage": 69.77, "elapsed_time": "1:46:55", "remaining_time": "0:46:20", "throughput": 4642.72, "total_tokens": 29785664} {"current_steps": 29600, "total_steps": 42420, "loss": 0.0537, "lr": 1.266963110265462e-05, "epoch": 13.955681282413956, "percentage": 69.78, "elapsed_time": "1:46:56", "remaining_time": "0:46:19", "throughput": 4642.76, "total_tokens": 29790752} {"current_steps": 29605, "total_steps": 42420, "loss": 0.0839, "lr": 1.2660684273202053e-05, "epoch": 13.958038661008958, "percentage": 69.79, "elapsed_time": "1:46:57", "remaining_time": "0:46:17", "throughput": 4642.75, "total_tokens": 29794464} {"current_steps": 29610, "total_steps": 42420, "loss": 0.1009, "lr": 1.265173953258613e-05, "epoch": 13.96039603960396, "percentage": 69.8, "elapsed_time": "1:46:58", "remaining_time": "0:46:16", "throughput": 4642.74, "total_tokens": 29799168} {"current_steps": 29615, "total_steps": 42420, "loss": 0.0218, "lr": 1.2642796882321039e-05, "epoch": 13.962753418198963, "percentage": 69.81, "elapsed_time": "1:46:59", "remaining_time": "0:46:15", "throughput": 4642.77, "total_tokens": 29804064} {"current_steps": 29620, "total_steps": 42420, "loss": 0.0145, "lr": 1.2633856323920626e-05, "epoch": 13.965110796793965, "percentage": 69.83, "elapsed_time": "1:47:00", "remaining_time": "0:46:14", "throughput": 4642.82, "total_tokens": 29809312} {"current_steps": 29625, "total_steps": 42420, "loss": 0.2384, "lr": 1.2624917858898373e-05, "epoch": 13.967468175388968, "percentage": 69.84, "elapsed_time": "1:47:01", "remaining_time": "0:46:13", "throughput": 4642.82, "total_tokens": 29813408} {"current_steps": 29630, "total_steps": 42420, "loss": 0.1421, "lr": 1.2615981488767415e-05, "epoch": 13.96982555398397, "percentage": 69.85, "elapsed_time": "1:47:02", "remaining_time": "0:46:12", "throughput": 4642.88, "total_tokens": 29819296} {"current_steps": 29635, "total_steps": 42420, "loss": 0.0852, "lr": 1.2607047215040515e-05, "epoch": 13.972182932578972, "percentage": 69.86, "elapsed_time": "1:47:03", "remaining_time": "0:46:11", "throughput": 4642.92, "total_tokens": 29824064} {"current_steps": 29640, "total_steps": 42420, "loss": 0.091, "lr": 1.2598115039230102e-05, "epoch": 13.974540311173975, "percentage": 69.87, "elapsed_time": "1:47:04", "remaining_time": "0:46:10", "throughput": 4642.95, "total_tokens": 29828832} {"current_steps": 29645, "total_steps": 42420, "loss": 0.0767, "lr": 1.2589184962848239e-05, "epoch": 13.976897689768977, "percentage": 69.88, "elapsed_time": "1:47:05", "remaining_time": "0:46:08", "throughput": 4642.93, "total_tokens": 29833280} {"current_steps": 29650, "total_steps": 42420, "loss": 0.1252, "lr": 1.258025698740664e-05, "epoch": 13.97925506836398, "percentage": 69.9, "elapsed_time": "1:47:06", "remaining_time": "0:46:07", "throughput": 4642.95, "total_tokens": 29838016} {"current_steps": 29655, "total_steps": 42420, "loss": 0.1376, "lr": 1.2571331114416657e-05, "epoch": 13.981612446958982, "percentage": 69.91, "elapsed_time": "1:47:07", "remaining_time": "0:46:06", "throughput": 4643.0, "total_tokens": 29843456} {"current_steps": 29660, "total_steps": 42420, "loss": 0.1642, "lr": 1.2562407345389298e-05, "epoch": 13.983969825553984, "percentage": 69.92, "elapsed_time": "1:47:08", "remaining_time": "0:46:05", "throughput": 4643.03, "total_tokens": 29848128} {"current_steps": 29665, "total_steps": 42420, "loss": 0.0784, "lr": 1.255348568183519e-05, "epoch": 13.986327204148987, "percentage": 69.93, "elapsed_time": "1:47:09", "remaining_time": "0:46:04", "throughput": 4643.04, "total_tokens": 29852512} {"current_steps": 29670, "total_steps": 42420, "loss": 0.0763, "lr": 1.2544566125264623e-05, "epoch": 13.98868458274399, "percentage": 69.94, "elapsed_time": "1:47:10", "remaining_time": "0:46:03", "throughput": 4643.05, "total_tokens": 29856832} {"current_steps": 29675, "total_steps": 42420, "loss": 0.0915, "lr": 1.2535648677187534e-05, "epoch": 13.991041961338992, "percentage": 69.96, "elapsed_time": "1:47:11", "remaining_time": "0:46:02", "throughput": 4643.07, "total_tokens": 29861600} {"current_steps": 29680, "total_steps": 42420, "loss": 0.0691, "lr": 1.2526733339113498e-05, "epoch": 13.993399339933994, "percentage": 69.97, "elapsed_time": "1:47:12", "remaining_time": "0:46:01", "throughput": 4643.09, "total_tokens": 29866272} {"current_steps": 29685, "total_steps": 42420, "loss": 0.0871, "lr": 1.2517820112551714e-05, "epoch": 13.995756718528996, "percentage": 69.98, "elapsed_time": "1:47:13", "remaining_time": "0:46:00", "throughput": 4643.14, "total_tokens": 29872192} {"current_steps": 29690, "total_steps": 42420, "loss": 0.0417, "lr": 1.250890899901105e-05, "epoch": 13.998114097123999, "percentage": 69.99, "elapsed_time": "1:47:14", "remaining_time": "0:45:58", "throughput": 4643.15, "total_tokens": 29877120} {"current_steps": 29694, "total_steps": 42420, "eval_loss": 0.151794895529747, "epoch": 14.0, "percentage": 70.0, "elapsed_time": "1:47:30", "remaining_time": "0:46:04", "throughput": 4632.21, "total_tokens": 29880544} {"current_steps": 29695, "total_steps": 42420, "loss": 0.0831, "lr": 1.2500000000000006e-05, "epoch": 14.000471475719001, "percentage": 70.0, "elapsed_time": "1:47:32", "remaining_time": "0:46:04", "throughput": 4631.13, "total_tokens": 29881408} {"current_steps": 29700, "total_steps": 42420, "loss": 0.1805, "lr": 1.2491093117026723e-05, "epoch": 14.002828854314004, "percentage": 70.01, "elapsed_time": "1:47:33", "remaining_time": "0:46:03", "throughput": 4631.14, "total_tokens": 29885824} {"current_steps": 29705, "total_steps": 42420, "loss": 0.1282, "lr": 1.248218835159899e-05, "epoch": 14.005186232909006, "percentage": 70.03, "elapsed_time": "1:47:34", "remaining_time": "0:46:02", "throughput": 4631.17, "total_tokens": 29890688} {"current_steps": 29710, "total_steps": 42420, "loss": 0.0264, "lr": 1.2473285705224225e-05, "epoch": 14.007543611504008, "percentage": 70.04, "elapsed_time": "1:47:35", "remaining_time": "0:46:01", "throughput": 4631.19, "total_tokens": 29895584} {"current_steps": 29715, "total_steps": 42420, "loss": 0.1677, "lr": 1.2464385179409499e-05, "epoch": 14.009900990099009, "percentage": 70.05, "elapsed_time": "1:47:36", "remaining_time": "0:46:00", "throughput": 4631.25, "total_tokens": 29901760} {"current_steps": 29720, "total_steps": 42420, "loss": 0.0201, "lr": 1.2455486775661529e-05, "epoch": 14.012258368694011, "percentage": 70.06, "elapsed_time": "1:47:37", "remaining_time": "0:45:59", "throughput": 4631.29, "total_tokens": 29907392} {"current_steps": 29725, "total_steps": 42420, "loss": 0.1111, "lr": 1.2446590495486645e-05, "epoch": 14.014615747289014, "percentage": 70.07, "elapsed_time": "1:47:38", "remaining_time": "0:45:58", "throughput": 4631.32, "total_tokens": 29912288} {"current_steps": 29730, "total_steps": 42420, "loss": 0.0205, "lr": 1.2437696340390844e-05, "epoch": 14.016973125884016, "percentage": 70.08, "elapsed_time": "1:47:39", "remaining_time": "0:45:57", "throughput": 4631.29, "total_tokens": 29916128} {"current_steps": 29735, "total_steps": 42420, "loss": 0.0846, "lr": 1.242880431187976e-05, "epoch": 14.019330504479019, "percentage": 70.1, "elapsed_time": "1:47:40", "remaining_time": "0:45:56", "throughput": 4631.28, "total_tokens": 29920384} {"current_steps": 29740, "total_steps": 42420, "loss": 0.0733, "lr": 1.2419914411458657e-05, "epoch": 14.021687883074021, "percentage": 70.11, "elapsed_time": "1:47:41", "remaining_time": "0:45:54", "throughput": 4631.32, "total_tokens": 29925664} {"current_steps": 29745, "total_steps": 42420, "loss": 0.1449, "lr": 1.2411026640632448e-05, "epoch": 14.024045261669023, "percentage": 70.12, "elapsed_time": "1:47:42", "remaining_time": "0:45:53", "throughput": 4631.39, "total_tokens": 29932128} {"current_steps": 29750, "total_steps": 42420, "loss": 0.0979, "lr": 1.2402141000905678e-05, "epoch": 14.026402640264026, "percentage": 70.13, "elapsed_time": "1:47:43", "remaining_time": "0:45:52", "throughput": 4631.38, "total_tokens": 29936512} {"current_steps": 29755, "total_steps": 42420, "loss": 0.1846, "lr": 1.239325749378254e-05, "epoch": 14.028760018859028, "percentage": 70.14, "elapsed_time": "1:47:44", "remaining_time": "0:45:51", "throughput": 4631.41, "total_tokens": 29940992} {"current_steps": 29760, "total_steps": 42420, "loss": 0.056, "lr": 1.2384376120766867e-05, "epoch": 14.03111739745403, "percentage": 70.16, "elapsed_time": "1:47:45", "remaining_time": "0:45:50", "throughput": 4631.43, "total_tokens": 29946080} {"current_steps": 29765, "total_steps": 42420, "loss": 0.0549, "lr": 1.2375496883362103e-05, "epoch": 14.033474776049033, "percentage": 70.17, "elapsed_time": "1:47:46", "remaining_time": "0:45:49", "throughput": 4631.43, "total_tokens": 29950368} {"current_steps": 29770, "total_steps": 42420, "loss": 0.0519, "lr": 1.2366619783071368e-05, "epoch": 14.035832154644035, "percentage": 70.18, "elapsed_time": "1:47:47", "remaining_time": "0:45:48", "throughput": 4631.45, "total_tokens": 29955136} {"current_steps": 29775, "total_steps": 42420, "loss": 0.036, "lr": 1.23577448213974e-05, "epoch": 14.038189533239038, "percentage": 70.19, "elapsed_time": "1:47:48", "remaining_time": "0:45:47", "throughput": 4631.5, "total_tokens": 29960864} {"current_steps": 29780, "total_steps": 42420, "loss": 0.057, "lr": 1.2348871999842579e-05, "epoch": 14.04054691183404, "percentage": 70.2, "elapsed_time": "1:47:49", "remaining_time": "0:45:46", "throughput": 4631.51, "total_tokens": 29965600} {"current_steps": 29785, "total_steps": 42420, "loss": 0.2013, "lr": 1.2340001319908925e-05, "epoch": 14.042904290429043, "percentage": 70.21, "elapsed_time": "1:47:50", "remaining_time": "0:45:44", "throughput": 4631.48, "total_tokens": 29969600} {"current_steps": 29790, "total_steps": 42420, "loss": 0.106, "lr": 1.2331132783098096e-05, "epoch": 14.045261669024045, "percentage": 70.23, "elapsed_time": "1:47:51", "remaining_time": "0:45:43", "throughput": 4631.47, "total_tokens": 29973888} {"current_steps": 29795, "total_steps": 42420, "loss": 0.2196, "lr": 1.2322266390911378e-05, "epoch": 14.047619047619047, "percentage": 70.24, "elapsed_time": "1:47:52", "remaining_time": "0:45:42", "throughput": 4631.48, "total_tokens": 29979040} {"current_steps": 29800, "total_steps": 42420, "loss": 0.2336, "lr": 1.2313402144849714e-05, "epoch": 14.04997642621405, "percentage": 70.25, "elapsed_time": "1:47:53", "remaining_time": "0:45:41", "throughput": 4631.5, "total_tokens": 29984256} {"current_steps": 29805, "total_steps": 42420, "loss": 0.128, "lr": 1.2304540046413655e-05, "epoch": 14.052333804809052, "percentage": 70.26, "elapsed_time": "1:47:55", "remaining_time": "0:45:40", "throughput": 4631.52, "total_tokens": 29989152} {"current_steps": 29810, "total_steps": 42420, "loss": 0.1009, "lr": 1.2295680097103407e-05, "epoch": 14.054691183404055, "percentage": 70.27, "elapsed_time": "1:47:56", "remaining_time": "0:45:39", "throughput": 4631.55, "total_tokens": 29994464} {"current_steps": 29815, "total_steps": 42420, "loss": 0.1376, "lr": 1.228682229841881e-05, "epoch": 14.057048561999057, "percentage": 70.29, "elapsed_time": "1:47:57", "remaining_time": "0:45:38", "throughput": 4631.55, "total_tokens": 29998848} {"current_steps": 29820, "total_steps": 42420, "loss": 0.2694, "lr": 1.2277966651859343e-05, "epoch": 14.05940594059406, "percentage": 70.3, "elapsed_time": "1:47:58", "remaining_time": "0:45:37", "throughput": 4631.56, "total_tokens": 30003520} {"current_steps": 29825, "total_steps": 42420, "loss": 0.1541, "lr": 1.2269113158924111e-05, "epoch": 14.061763319189062, "percentage": 70.31, "elapsed_time": "1:47:59", "remaining_time": "0:45:36", "throughput": 4631.58, "total_tokens": 30008320} {"current_steps": 29830, "total_steps": 42420, "loss": 0.0851, "lr": 1.2260261821111866e-05, "epoch": 14.064120697784064, "percentage": 70.32, "elapsed_time": "1:48:00", "remaining_time": "0:45:35", "throughput": 4631.58, "total_tokens": 30013344} {"current_steps": 29835, "total_steps": 42420, "loss": 0.1372, "lr": 1.2251412639920986e-05, "epoch": 14.066478076379067, "percentage": 70.33, "elapsed_time": "1:48:01", "remaining_time": "0:45:33", "throughput": 4631.62, "total_tokens": 30018592} {"current_steps": 29840, "total_steps": 42420, "loss": 0.078, "lr": 1.2242565616849497e-05, "epoch": 14.068835454974069, "percentage": 70.34, "elapsed_time": "1:48:02", "remaining_time": "0:45:32", "throughput": 4631.65, "total_tokens": 30023616} {"current_steps": 29845, "total_steps": 42420, "loss": 0.1704, "lr": 1.2233720753395028e-05, "epoch": 14.071192833569071, "percentage": 70.36, "elapsed_time": "1:48:03", "remaining_time": "0:45:31", "throughput": 4631.67, "total_tokens": 30028576} {"current_steps": 29850, "total_steps": 42420, "loss": 0.0521, "lr": 1.2224878051054877e-05, "epoch": 14.073550212164074, "percentage": 70.37, "elapsed_time": "1:48:04", "remaining_time": "0:45:30", "throughput": 4631.7, "total_tokens": 30033728} {"current_steps": 29855, "total_steps": 42420, "loss": 0.035, "lr": 1.2216037511325968e-05, "epoch": 14.075907590759076, "percentage": 70.38, "elapsed_time": "1:48:05", "remaining_time": "0:45:29", "throughput": 4631.73, "total_tokens": 30038368} {"current_steps": 29860, "total_steps": 42420, "loss": 0.1451, "lr": 1.2207199135704842e-05, "epoch": 14.078264969354079, "percentage": 70.39, "elapsed_time": "1:48:06", "remaining_time": "0:45:28", "throughput": 4631.72, "total_tokens": 30042688} {"current_steps": 29865, "total_steps": 42420, "loss": 0.234, "lr": 1.2198362925687698e-05, "epoch": 14.080622347949081, "percentage": 70.4, "elapsed_time": "1:48:07", "remaining_time": "0:45:27", "throughput": 4631.73, "total_tokens": 30047296} {"current_steps": 29870, "total_steps": 42420, "loss": 0.2409, "lr": 1.2189528882770349e-05, "epoch": 14.082979726544083, "percentage": 70.41, "elapsed_time": "1:48:08", "remaining_time": "0:45:26", "throughput": 4631.75, "total_tokens": 30051904} {"current_steps": 29875, "total_steps": 42420, "loss": 0.1998, "lr": 1.218069700844825e-05, "epoch": 14.085337105139086, "percentage": 70.43, "elapsed_time": "1:48:09", "remaining_time": "0:45:24", "throughput": 4631.76, "total_tokens": 30057088} {"current_steps": 29880, "total_steps": 42420, "loss": 0.0981, "lr": 1.2171867304216497e-05, "epoch": 14.087694483734088, "percentage": 70.44, "elapsed_time": "1:48:10", "remaining_time": "0:45:23", "throughput": 4631.73, "total_tokens": 30061504} {"current_steps": 29885, "total_steps": 42420, "loss": 0.2414, "lr": 1.2163039771569793e-05, "epoch": 14.09005186232909, "percentage": 70.45, "elapsed_time": "1:48:11", "remaining_time": "0:45:22", "throughput": 4631.75, "total_tokens": 30066528} {"current_steps": 29890, "total_steps": 42420, "loss": 0.0418, "lr": 1.2154214412002504e-05, "epoch": 14.092409240924093, "percentage": 70.46, "elapsed_time": "1:48:12", "remaining_time": "0:45:21", "throughput": 4631.77, "total_tokens": 30071360} {"current_steps": 29895, "total_steps": 42420, "loss": 0.0376, "lr": 1.2145391227008598e-05, "epoch": 14.094766619519095, "percentage": 70.47, "elapsed_time": "1:48:13", "remaining_time": "0:45:20", "throughput": 4631.84, "total_tokens": 30077536} {"current_steps": 29900, "total_steps": 42420, "loss": 0.0888, "lr": 1.21365702180817e-05, "epoch": 14.097123998114098, "percentage": 70.49, "elapsed_time": "1:48:14", "remaining_time": "0:45:19", "throughput": 4631.84, "total_tokens": 30082176} {"current_steps": 29905, "total_steps": 42420, "loss": 0.121, "lr": 1.2127751386715052e-05, "epoch": 14.0994813767091, "percentage": 70.5, "elapsed_time": "1:48:15", "remaining_time": "0:45:18", "throughput": 4631.84, "total_tokens": 30086912} {"current_steps": 29910, "total_steps": 42420, "loss": 0.1322, "lr": 1.2118934734401538e-05, "epoch": 14.101838755304103, "percentage": 70.51, "elapsed_time": "1:48:16", "remaining_time": "0:45:17", "throughput": 4631.86, "total_tokens": 30091328} {"current_steps": 29915, "total_steps": 42420, "loss": 0.1451, "lr": 1.2110120262633664e-05, "epoch": 14.104196133899103, "percentage": 70.52, "elapsed_time": "1:48:17", "remaining_time": "0:45:16", "throughput": 4631.87, "total_tokens": 30096000} {"current_steps": 29920, "total_steps": 42420, "loss": 0.1027, "lr": 1.2101307972903573e-05, "epoch": 14.106553512494106, "percentage": 70.53, "elapsed_time": "1:48:18", "remaining_time": "0:45:15", "throughput": 4631.92, "total_tokens": 30101952} {"current_steps": 29925, "total_steps": 42420, "loss": 0.038, "lr": 1.2092497866703034e-05, "epoch": 14.108910891089108, "percentage": 70.54, "elapsed_time": "1:48:19", "remaining_time": "0:45:13", "throughput": 4631.96, "total_tokens": 30106912} {"current_steps": 29930, "total_steps": 42420, "loss": 0.2499, "lr": 1.208368994552346e-05, "epoch": 14.11126826968411, "percentage": 70.56, "elapsed_time": "1:48:21", "remaining_time": "0:45:13", "throughput": 4632.04, "total_tokens": 30114144} {"current_steps": 29935, "total_steps": 42420, "loss": 0.0861, "lr": 1.207488421085586e-05, "epoch": 14.113625648279113, "percentage": 70.57, "elapsed_time": "1:48:22", "remaining_time": "0:45:11", "throughput": 4632.03, "total_tokens": 30118976} {"current_steps": 29940, "total_steps": 42420, "loss": 0.0685, "lr": 1.2066080664190909e-05, "epoch": 14.115983026874115, "percentage": 70.58, "elapsed_time": "1:48:23", "remaining_time": "0:45:10", "throughput": 4632.08, "total_tokens": 30124608} {"current_steps": 29945, "total_steps": 42420, "loss": 0.157, "lr": 1.2057279307018896e-05, "epoch": 14.118340405469118, "percentage": 70.59, "elapsed_time": "1:48:24", "remaining_time": "0:45:09", "throughput": 4632.13, "total_tokens": 30130080} {"current_steps": 29950, "total_steps": 42420, "loss": 0.1247, "lr": 1.2048480140829741e-05, "epoch": 14.12069778406412, "percentage": 70.6, "elapsed_time": "1:48:25", "remaining_time": "0:45:08", "throughput": 4632.16, "total_tokens": 30135648} {"current_steps": 29955, "total_steps": 42420, "loss": 0.1632, "lr": 1.2039683167112995e-05, "epoch": 14.123055162659123, "percentage": 70.62, "elapsed_time": "1:48:26", "remaining_time": "0:45:07", "throughput": 4632.23, "total_tokens": 30141376} {"current_steps": 29960, "total_steps": 42420, "loss": 0.0311, "lr": 1.2030888387357834e-05, "epoch": 14.125412541254125, "percentage": 70.63, "elapsed_time": "1:48:27", "remaining_time": "0:45:06", "throughput": 4632.27, "total_tokens": 30146656} {"current_steps": 29965, "total_steps": 42420, "loss": 0.168, "lr": 1.2022095803053066e-05, "epoch": 14.127769919849127, "percentage": 70.64, "elapsed_time": "1:48:29", "remaining_time": "0:45:05", "throughput": 4632.3, "total_tokens": 30152224} {"current_steps": 29970, "total_steps": 42420, "loss": 0.1915, "lr": 1.2013305415687137e-05, "epoch": 14.13012729844413, "percentage": 70.65, "elapsed_time": "1:48:30", "remaining_time": "0:45:04", "throughput": 4632.33, "total_tokens": 30157696} {"current_steps": 29975, "total_steps": 42420, "loss": 0.0703, "lr": 1.2004517226748089e-05, "epoch": 14.132484677039132, "percentage": 70.66, "elapsed_time": "1:48:31", "remaining_time": "0:45:03", "throughput": 4632.35, "total_tokens": 30162368} {"current_steps": 29980, "total_steps": 42420, "loss": 0.2457, "lr": 1.1995731237723623e-05, "epoch": 14.134842055634135, "percentage": 70.67, "elapsed_time": "1:48:32", "remaining_time": "0:45:02", "throughput": 4632.39, "total_tokens": 30168320} {"current_steps": 29985, "total_steps": 42420, "loss": 0.0392, "lr": 1.198694745010106e-05, "epoch": 14.137199434229137, "percentage": 70.69, "elapsed_time": "1:48:33", "remaining_time": "0:45:01", "throughput": 4632.41, "total_tokens": 30172736} {"current_steps": 29990, "total_steps": 42420, "loss": 0.1466, "lr": 1.1978165865367344e-05, "epoch": 14.13955681282414, "percentage": 70.7, "elapsed_time": "1:48:34", "remaining_time": "0:44:59", "throughput": 4632.42, "total_tokens": 30176832} {"current_steps": 29995, "total_steps": 42420, "loss": 0.1261, "lr": 1.1969386485009049e-05, "epoch": 14.141914191419142, "percentage": 70.71, "elapsed_time": "1:48:35", "remaining_time": "0:44:58", "throughput": 4632.42, "total_tokens": 30181280} {"current_steps": 30000, "total_steps": 42420, "loss": 0.2021, "lr": 1.1960609310512375e-05, "epoch": 14.144271570014144, "percentage": 70.72, "elapsed_time": "1:48:36", "remaining_time": "0:44:57", "throughput": 4632.45, "total_tokens": 30186624} {"current_steps": 30005, "total_steps": 42420, "loss": 0.1355, "lr": 1.1951834343363146e-05, "epoch": 14.146628948609147, "percentage": 70.73, "elapsed_time": "1:48:37", "remaining_time": "0:44:56", "throughput": 4632.48, "total_tokens": 30191584} {"current_steps": 30010, "total_steps": 42420, "loss": 0.164, "lr": 1.194306158504683e-05, "epoch": 14.148986327204149, "percentage": 70.74, "elapsed_time": "1:48:38", "remaining_time": "0:44:55", "throughput": 4632.52, "total_tokens": 30197024} {"current_steps": 30015, "total_steps": 42420, "loss": 0.1212, "lr": 1.1934291037048483e-05, "epoch": 14.151343705799151, "percentage": 70.76, "elapsed_time": "1:48:39", "remaining_time": "0:44:54", "throughput": 4632.55, "total_tokens": 30202208} {"current_steps": 30020, "total_steps": 42420, "loss": 0.0263, "lr": 1.1925522700852821e-05, "epoch": 14.153701084394154, "percentage": 70.77, "elapsed_time": "1:48:40", "remaining_time": "0:44:53", "throughput": 4632.55, "total_tokens": 30207232} {"current_steps": 30025, "total_steps": 42420, "loss": 0.1291, "lr": 1.1916756577944174e-05, "epoch": 14.156058462989156, "percentage": 70.78, "elapsed_time": "1:48:41", "remaining_time": "0:44:52", "throughput": 4632.59, "total_tokens": 30212352} {"current_steps": 30030, "total_steps": 42420, "loss": 0.1907, "lr": 1.1907992669806495e-05, "epoch": 14.158415841584159, "percentage": 70.79, "elapsed_time": "1:48:42", "remaining_time": "0:44:51", "throughput": 4632.61, "total_tokens": 30217280} {"current_steps": 30035, "total_steps": 42420, "loss": 0.0587, "lr": 1.189923097792337e-05, "epoch": 14.160773220179161, "percentage": 70.8, "elapsed_time": "1:48:43", "remaining_time": "0:44:50", "throughput": 4632.6, "total_tokens": 30221568} {"current_steps": 30040, "total_steps": 42420, "loss": 0.0231, "lr": 1.1890471503778e-05, "epoch": 14.163130598774163, "percentage": 70.82, "elapsed_time": "1:48:44", "remaining_time": "0:44:48", "throughput": 4632.6, "total_tokens": 30226432} {"current_steps": 30045, "total_steps": 42420, "loss": 0.0604, "lr": 1.1881714248853218e-05, "epoch": 14.165487977369166, "percentage": 70.83, "elapsed_time": "1:48:45", "remaining_time": "0:44:47", "throughput": 4632.62, "total_tokens": 30230816} {"current_steps": 30050, "total_steps": 42420, "loss": 0.1564, "lr": 1.1872959214631487e-05, "epoch": 14.167845355964168, "percentage": 70.84, "elapsed_time": "1:48:46", "remaining_time": "0:44:46", "throughput": 4632.67, "total_tokens": 30237088} {"current_steps": 30055, "total_steps": 42420, "loss": 0.1248, "lr": 1.1864206402594869e-05, "epoch": 14.17020273455917, "percentage": 70.85, "elapsed_time": "1:48:47", "remaining_time": "0:44:45", "throughput": 4632.68, "total_tokens": 30241888} {"current_steps": 30060, "total_steps": 42420, "loss": 0.1369, "lr": 1.1855455814225071e-05, "epoch": 14.172560113154173, "percentage": 70.86, "elapsed_time": "1:48:49", "remaining_time": "0:44:44", "throughput": 4632.74, "total_tokens": 30248192} {"current_steps": 30065, "total_steps": 42420, "loss": 0.0328, "lr": 1.1846707451003425e-05, "epoch": 14.174917491749175, "percentage": 70.87, "elapsed_time": "1:48:50", "remaining_time": "0:44:43", "throughput": 4632.78, "total_tokens": 30253056} {"current_steps": 30070, "total_steps": 42420, "loss": 0.0308, "lr": 1.1837961314410879e-05, "epoch": 14.177274870344178, "percentage": 70.89, "elapsed_time": "1:48:51", "remaining_time": "0:44:42", "throughput": 4632.74, "total_tokens": 30257056} {"current_steps": 30075, "total_steps": 42420, "loss": 0.0948, "lr": 1.1829217405928e-05, "epoch": 14.17963224893918, "percentage": 70.9, "elapsed_time": "1:48:52", "remaining_time": "0:44:41", "throughput": 4632.78, "total_tokens": 30262624} {"current_steps": 30080, "total_steps": 42420, "loss": 0.0405, "lr": 1.1820475727034989e-05, "epoch": 14.181989627534183, "percentage": 70.91, "elapsed_time": "1:48:53", "remaining_time": "0:44:40", "throughput": 4632.79, "total_tokens": 30267232} {"current_steps": 30085, "total_steps": 42420, "loss": 0.0701, "lr": 1.1811736279211657e-05, "epoch": 14.184347006129185, "percentage": 70.92, "elapsed_time": "1:48:54", "remaining_time": "0:44:39", "throughput": 4632.83, "total_tokens": 30273088} {"current_steps": 30090, "total_steps": 42420, "loss": 0.0289, "lr": 1.1802999063937465e-05, "epoch": 14.186704384724187, "percentage": 70.93, "elapsed_time": "1:48:55", "remaining_time": "0:44:38", "throughput": 4632.87, "total_tokens": 30278624} {"current_steps": 30095, "total_steps": 42420, "loss": 0.1846, "lr": 1.1794264082691444e-05, "epoch": 14.18906176331919, "percentage": 70.95, "elapsed_time": "1:48:56", "remaining_time": "0:44:37", "throughput": 4632.92, "total_tokens": 30284544} {"current_steps": 30100, "total_steps": 42420, "loss": 0.0348, "lr": 1.1785531336952296e-05, "epoch": 14.191419141914192, "percentage": 70.96, "elapsed_time": "1:48:58", "remaining_time": "0:44:36", "throughput": 4632.98, "total_tokens": 30291488} {"current_steps": 30105, "total_steps": 42420, "loss": 0.0125, "lr": 1.1776800828198325e-05, "epoch": 14.193776520509195, "percentage": 70.97, "elapsed_time": "1:48:59", "remaining_time": "0:44:34", "throughput": 4632.98, "total_tokens": 30296000} {"current_steps": 30110, "total_steps": 42420, "loss": 0.2326, "lr": 1.1768072557907465e-05, "epoch": 14.196133899104197, "percentage": 70.98, "elapsed_time": "1:49:00", "remaining_time": "0:44:33", "throughput": 4633.02, "total_tokens": 30301120} {"current_steps": 30115, "total_steps": 42420, "loss": 0.0747, "lr": 1.1759346527557246e-05, "epoch": 14.198491277699198, "percentage": 70.99, "elapsed_time": "1:49:01", "remaining_time": "0:44:32", "throughput": 4633.06, "total_tokens": 30306432} {"current_steps": 30120, "total_steps": 42420, "loss": 0.0657, "lr": 1.1750622738624847e-05, "epoch": 14.2008486562942, "percentage": 71.0, "elapsed_time": "1:49:02", "remaining_time": "0:44:31", "throughput": 4633.11, "total_tokens": 30312352} {"current_steps": 30125, "total_steps": 42420, "loss": 0.0449, "lr": 1.1741901192587053e-05, "epoch": 14.203206034889202, "percentage": 71.02, "elapsed_time": "1:49:03", "remaining_time": "0:44:30", "throughput": 4633.13, "total_tokens": 30317120} {"current_steps": 30130, "total_steps": 42420, "loss": 0.0955, "lr": 1.1733181890920283e-05, "epoch": 14.205563413484205, "percentage": 71.03, "elapsed_time": "1:49:04", "remaining_time": "0:44:29", "throughput": 4633.18, "total_tokens": 30322112} {"current_steps": 30135, "total_steps": 42420, "loss": 0.094, "lr": 1.172446483510056e-05, "epoch": 14.207920792079207, "percentage": 71.04, "elapsed_time": "1:49:05", "remaining_time": "0:44:28", "throughput": 4633.2, "total_tokens": 30328064} {"current_steps": 30140, "total_steps": 42420, "loss": 0.1298, "lr": 1.1715750026603542e-05, "epoch": 14.21027817067421, "percentage": 71.05, "elapsed_time": "1:49:06", "remaining_time": "0:44:27", "throughput": 4633.24, "total_tokens": 30333632} {"current_steps": 30145, "total_steps": 42420, "loss": 0.0494, "lr": 1.170703746690448e-05, "epoch": 14.212635549269212, "percentage": 71.06, "elapsed_time": "1:49:07", "remaining_time": "0:44:26", "throughput": 4633.25, "total_tokens": 30338400} {"current_steps": 30150, "total_steps": 42420, "loss": 0.2485, "lr": 1.1698327157478275e-05, "epoch": 14.214992927864214, "percentage": 71.07, "elapsed_time": "1:49:08", "remaining_time": "0:44:25", "throughput": 4633.29, "total_tokens": 30343296} {"current_steps": 30155, "total_steps": 42420, "loss": 0.1981, "lr": 1.1689619099799434e-05, "epoch": 14.217350306459217, "percentage": 71.09, "elapsed_time": "1:49:10", "remaining_time": "0:44:24", "throughput": 4633.28, "total_tokens": 30348320} {"current_steps": 30160, "total_steps": 42420, "loss": 0.1481, "lr": 1.168091329534208e-05, "epoch": 14.21970768505422, "percentage": 71.1, "elapsed_time": "1:49:11", "remaining_time": "0:44:23", "throughput": 4633.32, "total_tokens": 30353344} {"current_steps": 30165, "total_steps": 42420, "loss": 0.2126, "lr": 1.1672209745579962e-05, "epoch": 14.222065063649222, "percentage": 71.11, "elapsed_time": "1:49:12", "remaining_time": "0:44:21", "throughput": 4633.38, "total_tokens": 30359040} {"current_steps": 30170, "total_steps": 42420, "loss": 0.107, "lr": 1.1663508451986442e-05, "epoch": 14.224422442244224, "percentage": 71.12, "elapsed_time": "1:49:13", "remaining_time": "0:44:20", "throughput": 4633.41, "total_tokens": 30363840} {"current_steps": 30175, "total_steps": 42420, "loss": 0.0672, "lr": 1.1654809416034496e-05, "epoch": 14.226779820839226, "percentage": 71.13, "elapsed_time": "1:49:14", "remaining_time": "0:44:19", "throughput": 4633.44, "total_tokens": 30368832} {"current_steps": 30180, "total_steps": 42420, "loss": 0.0629, "lr": 1.1646112639196739e-05, "epoch": 14.229137199434229, "percentage": 71.15, "elapsed_time": "1:49:15", "remaining_time": "0:44:18", "throughput": 4633.43, "total_tokens": 30372896} {"current_steps": 30185, "total_steps": 42420, "loss": 0.2569, "lr": 1.1637418122945368e-05, "epoch": 14.231494578029231, "percentage": 71.16, "elapsed_time": "1:49:16", "remaining_time": "0:44:17", "throughput": 4633.46, "total_tokens": 30377696} {"current_steps": 30190, "total_steps": 42420, "loss": 0.0998, "lr": 1.1628725868752222e-05, "epoch": 14.233851956624234, "percentage": 71.17, "elapsed_time": "1:49:17", "remaining_time": "0:44:16", "throughput": 4633.51, "total_tokens": 30383584} {"current_steps": 30195, "total_steps": 42420, "loss": 0.1648, "lr": 1.162003587808876e-05, "epoch": 14.236209335219236, "percentage": 71.18, "elapsed_time": "1:49:18", "remaining_time": "0:44:15", "throughput": 4633.53, "total_tokens": 30388640} {"current_steps": 30200, "total_steps": 42420, "loss": 0.0298, "lr": 1.161134815242604e-05, "epoch": 14.238566713814238, "percentage": 71.19, "elapsed_time": "1:49:19", "remaining_time": "0:44:14", "throughput": 4633.61, "total_tokens": 30395712} {"current_steps": 30205, "total_steps": 42420, "loss": 0.1535, "lr": 1.1602662693234753e-05, "epoch": 14.24092409240924, "percentage": 71.2, "elapsed_time": "1:49:20", "remaining_time": "0:44:13", "throughput": 4633.64, "total_tokens": 30400768} {"current_steps": 30210, "total_steps": 42420, "loss": 0.0379, "lr": 1.1593979501985198e-05, "epoch": 14.243281471004243, "percentage": 71.22, "elapsed_time": "1:49:21", "remaining_time": "0:44:12", "throughput": 4633.68, "total_tokens": 30405696} {"current_steps": 30215, "total_steps": 42420, "loss": 0.011, "lr": 1.1585298580147294e-05, "epoch": 14.245638849599246, "percentage": 71.23, "elapsed_time": "1:49:22", "remaining_time": "0:44:10", "throughput": 4633.68, "total_tokens": 30410144} {"current_steps": 30220, "total_steps": 42420, "loss": 0.0686, "lr": 1.157661992919058e-05, "epoch": 14.247996228194248, "percentage": 71.24, "elapsed_time": "1:49:23", "remaining_time": "0:44:09", "throughput": 4633.71, "total_tokens": 30415200} {"current_steps": 30225, "total_steps": 42420, "loss": 0.1959, "lr": 1.1567943550584185e-05, "epoch": 14.25035360678925, "percentage": 71.25, "elapsed_time": "1:49:25", "remaining_time": "0:44:08", "throughput": 4633.75, "total_tokens": 30420736} {"current_steps": 30230, "total_steps": 42420, "loss": 0.1548, "lr": 1.1559269445796886e-05, "epoch": 14.252710985384253, "percentage": 71.26, "elapsed_time": "1:49:25", "remaining_time": "0:44:07", "throughput": 4633.73, "total_tokens": 30424832} {"current_steps": 30235, "total_steps": 42420, "loss": 0.0325, "lr": 1.1550597616297057e-05, "epoch": 14.255068363979255, "percentage": 71.28, "elapsed_time": "1:49:26", "remaining_time": "0:44:06", "throughput": 4633.73, "total_tokens": 30429312} {"current_steps": 30240, "total_steps": 42420, "loss": 0.106, "lr": 1.1541928063552696e-05, "epoch": 14.257425742574258, "percentage": 71.29, "elapsed_time": "1:49:27", "remaining_time": "0:44:05", "throughput": 4633.77, "total_tokens": 30434560} {"current_steps": 30245, "total_steps": 42420, "loss": 0.0652, "lr": 1.1533260789031405e-05, "epoch": 14.25978312116926, "percentage": 71.3, "elapsed_time": "1:49:29", "remaining_time": "0:44:04", "throughput": 4633.85, "total_tokens": 30442432} {"current_steps": 30250, "total_steps": 42420, "loss": 0.0227, "lr": 1.1524595794200413e-05, "epoch": 14.262140499764262, "percentage": 71.31, "elapsed_time": "1:49:30", "remaining_time": "0:44:03", "throughput": 4633.86, "total_tokens": 30446784} {"current_steps": 30255, "total_steps": 42420, "loss": 0.0543, "lr": 1.1515933080526553e-05, "epoch": 14.264497878359265, "percentage": 71.32, "elapsed_time": "1:49:31", "remaining_time": "0:44:02", "throughput": 4633.9, "total_tokens": 30452224} {"current_steps": 30260, "total_steps": 42420, "loss": 0.1468, "lr": 1.1507272649476286e-05, "epoch": 14.266855256954267, "percentage": 71.33, "elapsed_time": "1:49:32", "remaining_time": "0:44:01", "throughput": 4633.92, "total_tokens": 30456864} {"current_steps": 30265, "total_steps": 42420, "loss": 0.2481, "lr": 1.1498614502515656e-05, "epoch": 14.26921263554927, "percentage": 71.35, "elapsed_time": "1:49:33", "remaining_time": "0:44:00", "throughput": 4633.97, "total_tokens": 30462336} {"current_steps": 30270, "total_steps": 42420, "loss": 0.1431, "lr": 1.1489958641110351e-05, "epoch": 14.271570014144272, "percentage": 71.36, "elapsed_time": "1:49:34", "remaining_time": "0:43:59", "throughput": 4633.98, "total_tokens": 30467104} {"current_steps": 30275, "total_steps": 42420, "loss": 0.1356, "lr": 1.1481305066725662e-05, "epoch": 14.273927392739274, "percentage": 71.37, "elapsed_time": "1:49:35", "remaining_time": "0:43:57", "throughput": 4634.01, "total_tokens": 30472736} {"current_steps": 30280, "total_steps": 42420, "loss": 0.0997, "lr": 1.1472653780826486e-05, "epoch": 14.276284771334277, "percentage": 71.38, "elapsed_time": "1:49:37", "remaining_time": "0:43:56", "throughput": 4634.05, "total_tokens": 30478272} {"current_steps": 30285, "total_steps": 42420, "loss": 0.0609, "lr": 1.146400478487735e-05, "epoch": 14.27864214992928, "percentage": 71.39, "elapsed_time": "1:49:38", "remaining_time": "0:43:55", "throughput": 4634.06, "total_tokens": 30483584} {"current_steps": 30290, "total_steps": 42420, "loss": 0.1006, "lr": 1.1455358080342372e-05, "epoch": 14.280999528524282, "percentage": 71.4, "elapsed_time": "1:49:39", "remaining_time": "0:43:54", "throughput": 4634.13, "total_tokens": 30489888} {"current_steps": 30295, "total_steps": 42420, "loss": 0.0537, "lr": 1.1446713668685297e-05, "epoch": 14.283356907119284, "percentage": 71.42, "elapsed_time": "1:49:40", "remaining_time": "0:43:53", "throughput": 4634.11, "total_tokens": 30494080} {"current_steps": 30300, "total_steps": 42420, "loss": 0.113, "lr": 1.1438071551369484e-05, "epoch": 14.285714285714286, "percentage": 71.43, "elapsed_time": "1:49:41", "remaining_time": "0:43:52", "throughput": 4634.13, "total_tokens": 30498880} {"current_steps": 30305, "total_steps": 42420, "loss": 0.0185, "lr": 1.1429431729857881e-05, "epoch": 14.288071664309289, "percentage": 71.44, "elapsed_time": "1:49:42", "remaining_time": "0:43:51", "throughput": 4634.18, "total_tokens": 30504288} {"current_steps": 30310, "total_steps": 42420, "loss": 0.1094, "lr": 1.142079420561307e-05, "epoch": 14.290429042904291, "percentage": 71.45, "elapsed_time": "1:49:43", "remaining_time": "0:43:50", "throughput": 4634.21, "total_tokens": 30509248} {"current_steps": 30315, "total_steps": 42420, "loss": 0.0636, "lr": 1.141215898009724e-05, "epoch": 14.292786421499294, "percentage": 71.46, "elapsed_time": "1:49:44", "remaining_time": "0:43:49", "throughput": 4634.22, "total_tokens": 30513984} {"current_steps": 30320, "total_steps": 42420, "loss": 0.0306, "lr": 1.1403526054772184e-05, "epoch": 14.295143800094294, "percentage": 71.48, "elapsed_time": "1:49:45", "remaining_time": "0:43:48", "throughput": 4634.25, "total_tokens": 30518848} {"current_steps": 30325, "total_steps": 42420, "loss": 0.2146, "lr": 1.1394895431099314e-05, "epoch": 14.297501178689297, "percentage": 71.49, "elapsed_time": "1:49:46", "remaining_time": "0:43:46", "throughput": 4634.27, "total_tokens": 30523296} {"current_steps": 30330, "total_steps": 42420, "loss": 0.1051, "lr": 1.1386267110539644e-05, "epoch": 14.299858557284299, "percentage": 71.5, "elapsed_time": "1:49:47", "remaining_time": "0:43:45", "throughput": 4634.32, "total_tokens": 30528864} {"current_steps": 30335, "total_steps": 42420, "loss": 0.1974, "lr": 1.1377641094553815e-05, "epoch": 14.302215935879302, "percentage": 71.51, "elapsed_time": "1:49:48", "remaining_time": "0:43:44", "throughput": 4634.37, "total_tokens": 30534400} {"current_steps": 30340, "total_steps": 42420, "loss": 0.1009, "lr": 1.1369017384602046e-05, "epoch": 14.304573314474304, "percentage": 71.52, "elapsed_time": "1:49:49", "remaining_time": "0:43:43", "throughput": 4634.42, "total_tokens": 30539712} {"current_steps": 30345, "total_steps": 42420, "loss": 0.0435, "lr": 1.1360395982144201e-05, "epoch": 14.306930693069306, "percentage": 71.53, "elapsed_time": "1:49:50", "remaining_time": "0:43:42", "throughput": 4634.44, "total_tokens": 30544544} {"current_steps": 30350, "total_steps": 42420, "loss": 0.0235, "lr": 1.1351776888639717e-05, "epoch": 14.309288071664309, "percentage": 71.55, "elapsed_time": "1:49:51", "remaining_time": "0:43:41", "throughput": 4634.46, "total_tokens": 30549088} {"current_steps": 30355, "total_steps": 42420, "loss": 0.2816, "lr": 1.1343160105547677e-05, "epoch": 14.311645450259311, "percentage": 71.56, "elapsed_time": "1:49:52", "remaining_time": "0:43:40", "throughput": 4634.48, "total_tokens": 30554272} {"current_steps": 30360, "total_steps": 42420, "loss": 0.1599, "lr": 1.1334545634326746e-05, "epoch": 14.314002828854314, "percentage": 71.57, "elapsed_time": "1:49:53", "remaining_time": "0:43:39", "throughput": 4634.52, "total_tokens": 30559424} {"current_steps": 30365, "total_steps": 42420, "loss": 0.0439, "lr": 1.1325933476435216e-05, "epoch": 14.316360207449316, "percentage": 71.58, "elapsed_time": "1:49:54", "remaining_time": "0:43:38", "throughput": 4634.54, "total_tokens": 30564352} {"current_steps": 30370, "total_steps": 42420, "loss": 0.123, "lr": 1.1317323633330975e-05, "epoch": 14.318717586044318, "percentage": 71.59, "elapsed_time": "1:49:55", "remaining_time": "0:43:37", "throughput": 4634.55, "total_tokens": 30568800} {"current_steps": 30375, "total_steps": 42420, "loss": 0.0789, "lr": 1.1308716106471526e-05, "epoch": 14.32107496463932, "percentage": 71.61, "elapsed_time": "1:49:56", "remaining_time": "0:43:35", "throughput": 4634.56, "total_tokens": 30573024} {"current_steps": 30380, "total_steps": 42420, "loss": 0.1532, "lr": 1.1300110897313973e-05, "epoch": 14.323432343234323, "percentage": 71.62, "elapsed_time": "1:49:57", "remaining_time": "0:43:34", "throughput": 4634.56, "total_tokens": 30577760} {"current_steps": 30385, "total_steps": 42420, "loss": 0.1607, "lr": 1.1291508007315046e-05, "epoch": 14.325789721829326, "percentage": 71.63, "elapsed_time": "1:49:58", "remaining_time": "0:43:33", "throughput": 4634.6, "total_tokens": 30582880} {"current_steps": 30390, "total_steps": 42420, "loss": 0.1384, "lr": 1.1282907437931046e-05, "epoch": 14.328147100424328, "percentage": 71.64, "elapsed_time": "1:49:59", "remaining_time": "0:43:32", "throughput": 4634.62, "total_tokens": 30587264} {"current_steps": 30395, "total_steps": 42420, "loss": 0.196, "lr": 1.1274309190617913e-05, "epoch": 14.33050447901933, "percentage": 71.65, "elapsed_time": "1:50:00", "remaining_time": "0:43:31", "throughput": 4634.59, "total_tokens": 30590944} {"current_steps": 30400, "total_steps": 42420, "loss": 0.1687, "lr": 1.1265713266831184e-05, "epoch": 14.332861857614333, "percentage": 71.66, "elapsed_time": "1:50:01", "remaining_time": "0:43:30", "throughput": 4634.62, "total_tokens": 30595968} {"current_steps": 30405, "total_steps": 42420, "loss": 0.0709, "lr": 1.1257119668026006e-05, "epoch": 14.335219236209335, "percentage": 71.68, "elapsed_time": "1:50:02", "remaining_time": "0:43:29", "throughput": 4634.65, "total_tokens": 30600448} {"current_steps": 30410, "total_steps": 42420, "loss": 0.0765, "lr": 1.1248528395657129e-05, "epoch": 14.337576614804338, "percentage": 71.69, "elapsed_time": "1:50:04", "remaining_time": "0:43:28", "throughput": 4634.69, "total_tokens": 30607968} {"current_steps": 30415, "total_steps": 42420, "loss": 0.1108, "lr": 1.1239939451178905e-05, "epoch": 14.33993399339934, "percentage": 71.7, "elapsed_time": "1:50:04", "remaining_time": "0:43:27", "throughput": 4634.68, "total_tokens": 30612000} {"current_steps": 30420, "total_steps": 42420, "loss": 0.1293, "lr": 1.12313528360453e-05, "epoch": 14.342291371994342, "percentage": 71.71, "elapsed_time": "1:50:05", "remaining_time": "0:43:25", "throughput": 4634.69, "total_tokens": 30616704} {"current_steps": 30425, "total_steps": 42420, "loss": 0.0294, "lr": 1.1222768551709892e-05, "epoch": 14.344648750589345, "percentage": 71.72, "elapsed_time": "1:50:06", "remaining_time": "0:43:24", "throughput": 4634.72, "total_tokens": 30621536} {"current_steps": 30430, "total_steps": 42420, "loss": 0.1025, "lr": 1.1214186599625833e-05, "epoch": 14.347006129184347, "percentage": 71.74, "elapsed_time": "1:50:07", "remaining_time": "0:43:23", "throughput": 4634.76, "total_tokens": 30626112} {"current_steps": 30435, "total_steps": 42420, "loss": 0.1094, "lr": 1.1205606981245914e-05, "epoch": 14.34936350777935, "percentage": 71.75, "elapsed_time": "1:50:09", "remaining_time": "0:43:22", "throughput": 4634.81, "total_tokens": 30632224} {"current_steps": 30440, "total_steps": 42420, "loss": 0.0739, "lr": 1.1197029698022519e-05, "epoch": 14.351720886374352, "percentage": 71.76, "elapsed_time": "1:50:10", "remaining_time": "0:43:21", "throughput": 4634.83, "total_tokens": 30637824} {"current_steps": 30445, "total_steps": 42420, "loss": 0.1691, "lr": 1.118845475140763e-05, "epoch": 14.354078264969354, "percentage": 71.77, "elapsed_time": "1:50:11", "remaining_time": "0:43:20", "throughput": 4634.85, "total_tokens": 30642496} {"current_steps": 30450, "total_steps": 42420, "loss": 0.0947, "lr": 1.1179882142852852e-05, "epoch": 14.356435643564357, "percentage": 71.78, "elapsed_time": "1:50:12", "remaining_time": "0:43:19", "throughput": 4634.86, "total_tokens": 30647744} {"current_steps": 30455, "total_steps": 42420, "loss": 0.1077, "lr": 1.117131187380937e-05, "epoch": 14.35879302215936, "percentage": 71.79, "elapsed_time": "1:50:13", "remaining_time": "0:43:18", "throughput": 4634.88, "total_tokens": 30652576} {"current_steps": 30460, "total_steps": 42420, "loss": 0.1644, "lr": 1.1162743945727991e-05, "epoch": 14.361150400754362, "percentage": 71.81, "elapsed_time": "1:50:14", "remaining_time": "0:43:17", "throughput": 4634.92, "total_tokens": 30657760} {"current_steps": 30465, "total_steps": 42420, "loss": 0.0298, "lr": 1.1154178360059129e-05, "epoch": 14.363507779349364, "percentage": 71.82, "elapsed_time": "1:50:15", "remaining_time": "0:43:16", "throughput": 4634.95, "total_tokens": 30662976} {"current_steps": 30470, "total_steps": 42420, "loss": 0.0172, "lr": 1.1145615118252772e-05, "epoch": 14.365865157944366, "percentage": 71.83, "elapsed_time": "1:50:16", "remaining_time": "0:43:14", "throughput": 4634.96, "total_tokens": 30667200} {"current_steps": 30475, "total_steps": 42420, "loss": 0.1901, "lr": 1.1137054221758541e-05, "epoch": 14.368222536539369, "percentage": 71.84, "elapsed_time": "1:50:17", "remaining_time": "0:43:13", "throughput": 4634.99, "total_tokens": 30671872} {"current_steps": 30480, "total_steps": 42420, "loss": 0.2697, "lr": 1.1128495672025652e-05, "epoch": 14.370579915134371, "percentage": 71.85, "elapsed_time": "1:50:18", "remaining_time": "0:43:12", "throughput": 4635.03, "total_tokens": 30676480} {"current_steps": 30485, "total_steps": 42420, "loss": 0.1233, "lr": 1.1119939470502921e-05, "epoch": 14.372937293729374, "percentage": 71.86, "elapsed_time": "1:50:19", "remaining_time": "0:43:11", "throughput": 4635.1, "total_tokens": 30683456} {"current_steps": 30490, "total_steps": 42420, "loss": 0.1164, "lr": 1.1111385618638767e-05, "epoch": 14.375294672324376, "percentage": 71.88, "elapsed_time": "1:50:20", "remaining_time": "0:43:10", "throughput": 4635.11, "total_tokens": 30687680} {"current_steps": 30495, "total_steps": 42420, "loss": 0.0382, "lr": 1.110283411788121e-05, "epoch": 14.377652050919378, "percentage": 71.89, "elapsed_time": "1:50:21", "remaining_time": "0:43:09", "throughput": 4635.11, "total_tokens": 30692736} {"current_steps": 30500, "total_steps": 42420, "loss": 0.077, "lr": 1.1094284969677881e-05, "epoch": 14.38000942951438, "percentage": 71.9, "elapsed_time": "1:50:22", "remaining_time": "0:43:08", "throughput": 4635.13, "total_tokens": 30696960} {"current_steps": 30505, "total_steps": 42420, "loss": 0.1763, "lr": 1.1085738175476008e-05, "epoch": 14.382366808109383, "percentage": 71.91, "elapsed_time": "1:50:23", "remaining_time": "0:43:07", "throughput": 4635.09, "total_tokens": 30701024} {"current_steps": 30510, "total_steps": 42420, "loss": 0.2376, "lr": 1.1077193736722402e-05, "epoch": 14.384724186704386, "percentage": 71.92, "elapsed_time": "1:50:24", "remaining_time": "0:43:05", "throughput": 4635.11, "total_tokens": 30705440} {"current_steps": 30515, "total_steps": 42420, "loss": 0.014, "lr": 1.1068651654863502e-05, "epoch": 14.387081565299386, "percentage": 71.94, "elapsed_time": "1:50:25", "remaining_time": "0:43:04", "throughput": 4635.1, "total_tokens": 30709888} {"current_steps": 30520, "total_steps": 42420, "loss": 0.045, "lr": 1.1060111931345336e-05, "epoch": 14.389438943894389, "percentage": 71.95, "elapsed_time": "1:50:26", "remaining_time": "0:43:03", "throughput": 4635.14, "total_tokens": 30714848} {"current_steps": 30525, "total_steps": 42420, "loss": 0.1263, "lr": 1.1051574567613532e-05, "epoch": 14.391796322489391, "percentage": 71.96, "elapsed_time": "1:50:27", "remaining_time": "0:43:02", "throughput": 4635.19, "total_tokens": 30720160} {"current_steps": 30530, "total_steps": 42420, "loss": 0.1158, "lr": 1.1043039565113322e-05, "epoch": 14.394153701084393, "percentage": 71.97, "elapsed_time": "1:50:28", "remaining_time": "0:43:01", "throughput": 4635.19, "total_tokens": 30724800} {"current_steps": 30535, "total_steps": 42420, "loss": 0.1032, "lr": 1.103450692528954e-05, "epoch": 14.396511079679396, "percentage": 71.98, "elapsed_time": "1:50:29", "remaining_time": "0:43:00", "throughput": 4635.24, "total_tokens": 30730528} {"current_steps": 30540, "total_steps": 42420, "loss": 0.1022, "lr": 1.1025976649586615e-05, "epoch": 14.398868458274398, "percentage": 71.99, "elapsed_time": "1:50:30", "remaining_time": "0:42:59", "throughput": 4635.27, "total_tokens": 30735808} {"current_steps": 30545, "total_steps": 42420, "loss": 0.0805, "lr": 1.1017448739448586e-05, "epoch": 14.4012258368694, "percentage": 72.01, "elapsed_time": "1:50:31", "remaining_time": "0:42:58", "throughput": 4635.29, "total_tokens": 30740928} {"current_steps": 30550, "total_steps": 42420, "loss": 0.1939, "lr": 1.1008923196319068e-05, "epoch": 14.403583215464403, "percentage": 72.02, "elapsed_time": "1:50:33", "remaining_time": "0:42:57", "throughput": 4635.34, "total_tokens": 30746592} {"current_steps": 30555, "total_steps": 42420, "loss": 0.1202, "lr": 1.1000400021641296e-05, "epoch": 14.405940594059405, "percentage": 72.03, "elapsed_time": "1:50:34", "remaining_time": "0:42:56", "throughput": 4635.37, "total_tokens": 30752032} {"current_steps": 30560, "total_steps": 42420, "loss": 0.1418, "lr": 1.0991879216858112e-05, "epoch": 14.408297972654408, "percentage": 72.04, "elapsed_time": "1:50:35", "remaining_time": "0:42:55", "throughput": 4635.38, "total_tokens": 30756448} {"current_steps": 30565, "total_steps": 42420, "loss": 0.0607, "lr": 1.098336078341192e-05, "epoch": 14.41065535124941, "percentage": 72.05, "elapsed_time": "1:50:36", "remaining_time": "0:42:53", "throughput": 4635.36, "total_tokens": 30760544} {"current_steps": 30570, "total_steps": 42420, "loss": 0.0604, "lr": 1.097484472274476e-05, "epoch": 14.413012729844413, "percentage": 72.07, "elapsed_time": "1:50:37", "remaining_time": "0:42:52", "throughput": 4635.39, "total_tokens": 30766112} {"current_steps": 30575, "total_steps": 42420, "loss": 0.1652, "lr": 1.0966331036298255e-05, "epoch": 14.415370108439415, "percentage": 72.08, "elapsed_time": "1:50:38", "remaining_time": "0:42:51", "throughput": 4635.44, "total_tokens": 30771808} {"current_steps": 30580, "total_steps": 42420, "loss": 0.1516, "lr": 1.0957819725513627e-05, "epoch": 14.417727487034417, "percentage": 72.09, "elapsed_time": "1:50:39", "remaining_time": "0:42:50", "throughput": 4635.47, "total_tokens": 30776864} {"current_steps": 30585, "total_steps": 42420, "loss": 0.0613, "lr": 1.0949310791831696e-05, "epoch": 14.42008486562942, "percentage": 72.1, "elapsed_time": "1:50:40", "remaining_time": "0:42:49", "throughput": 4635.49, "total_tokens": 30781568} {"current_steps": 30590, "total_steps": 42420, "loss": 0.1496, "lr": 1.0940804236692884e-05, "epoch": 14.422442244224422, "percentage": 72.11, "elapsed_time": "1:50:41", "remaining_time": "0:42:48", "throughput": 4635.52, "total_tokens": 30786688} {"current_steps": 30595, "total_steps": 42420, "loss": 0.0509, "lr": 1.093230006153721e-05, "epoch": 14.424799622819425, "percentage": 72.12, "elapsed_time": "1:50:42", "remaining_time": "0:42:47", "throughput": 4635.53, "total_tokens": 30790784} {"current_steps": 30600, "total_steps": 42420, "loss": 0.1967, "lr": 1.0923798267804269e-05, "epoch": 14.427157001414427, "percentage": 72.14, "elapsed_time": "1:50:43", "remaining_time": "0:42:46", "throughput": 4635.57, "total_tokens": 30796160} {"current_steps": 30605, "total_steps": 42420, "loss": 0.0661, "lr": 1.0915298856933285e-05, "epoch": 14.42951438000943, "percentage": 72.15, "elapsed_time": "1:50:44", "remaining_time": "0:42:45", "throughput": 4635.6, "total_tokens": 30801504} {"current_steps": 30610, "total_steps": 42420, "loss": 0.0661, "lr": 1.0906801830363056e-05, "epoch": 14.431871758604432, "percentage": 72.16, "elapsed_time": "1:50:45", "remaining_time": "0:42:43", "throughput": 4635.6, "total_tokens": 30805696} {"current_steps": 30615, "total_steps": 42420, "loss": 0.0614, "lr": 1.089830718953199e-05, "epoch": 14.434229137199434, "percentage": 72.17, "elapsed_time": "1:50:46", "remaining_time": "0:42:42", "throughput": 4635.65, "total_tokens": 30811200} {"current_steps": 30620, "total_steps": 42420, "loss": 0.227, "lr": 1.0889814935878084e-05, "epoch": 14.436586515794437, "percentage": 72.18, "elapsed_time": "1:50:47", "remaining_time": "0:42:41", "throughput": 4635.67, "total_tokens": 30815904} {"current_steps": 30625, "total_steps": 42420, "loss": 0.0463, "lr": 1.088132507083893e-05, "epoch": 14.438943894389439, "percentage": 72.19, "elapsed_time": "1:50:48", "remaining_time": "0:42:40", "throughput": 4635.66, "total_tokens": 30820544} {"current_steps": 30630, "total_steps": 42420, "loss": 0.2096, "lr": 1.0872837595851723e-05, "epoch": 14.441301272984441, "percentage": 72.21, "elapsed_time": "1:50:49", "remaining_time": "0:42:39", "throughput": 4635.69, "total_tokens": 30825152} {"current_steps": 30635, "total_steps": 42420, "loss": 0.0939, "lr": 1.0864352512353251e-05, "epoch": 14.443658651579444, "percentage": 72.22, "elapsed_time": "1:50:50", "remaining_time": "0:42:38", "throughput": 4635.74, "total_tokens": 30831072} {"current_steps": 30640, "total_steps": 42420, "loss": 0.0866, "lr": 1.0855869821779882e-05, "epoch": 14.446016030174446, "percentage": 72.23, "elapsed_time": "1:50:51", "remaining_time": "0:42:37", "throughput": 4635.76, "total_tokens": 30835200} {"current_steps": 30645, "total_steps": 42420, "loss": 0.1273, "lr": 1.08473895255676e-05, "epoch": 14.448373408769449, "percentage": 72.24, "elapsed_time": "1:50:52", "remaining_time": "0:42:36", "throughput": 4635.75, "total_tokens": 30839584} {"current_steps": 30650, "total_steps": 42420, "loss": 0.1128, "lr": 1.0838911625151973e-05, "epoch": 14.450730787364451, "percentage": 72.25, "elapsed_time": "1:50:53", "remaining_time": "0:42:35", "throughput": 4635.79, "total_tokens": 30845056} {"current_steps": 30655, "total_steps": 42420, "loss": 0.147, "lr": 1.0830436121968166e-05, "epoch": 14.453088165959453, "percentage": 72.27, "elapsed_time": "1:50:54", "remaining_time": "0:42:34", "throughput": 4635.85, "total_tokens": 30850976} {"current_steps": 30660, "total_steps": 42420, "loss": 0.2309, "lr": 1.0821963017450937e-05, "epoch": 14.455445544554456, "percentage": 72.28, "elapsed_time": "1:50:55", "remaining_time": "0:42:32", "throughput": 4635.87, "total_tokens": 30855136} {"current_steps": 30665, "total_steps": 42420, "loss": 0.0405, "lr": 1.081349231303464e-05, "epoch": 14.457802923149458, "percentage": 72.29, "elapsed_time": "1:50:56", "remaining_time": "0:42:31", "throughput": 4635.9, "total_tokens": 30859712} {"current_steps": 30670, "total_steps": 42420, "loss": 0.1468, "lr": 1.080502401015322e-05, "epoch": 14.46016030174446, "percentage": 72.3, "elapsed_time": "1:50:57", "remaining_time": "0:42:30", "throughput": 4635.92, "total_tokens": 30863936} {"current_steps": 30675, "total_steps": 42420, "loss": 0.0528, "lr": 1.079655811024023e-05, "epoch": 14.462517680339463, "percentage": 72.31, "elapsed_time": "1:50:58", "remaining_time": "0:42:29", "throughput": 4635.95, "total_tokens": 30869216} {"current_steps": 30680, "total_steps": 42420, "loss": 0.1693, "lr": 1.078809461472878e-05, "epoch": 14.464875058934465, "percentage": 72.32, "elapsed_time": "1:50:59", "remaining_time": "0:42:28", "throughput": 4635.98, "total_tokens": 30874080} {"current_steps": 30685, "total_steps": 42420, "loss": 0.0629, "lr": 1.0779633525051608e-05, "epoch": 14.467232437529468, "percentage": 72.34, "elapsed_time": "1:51:00", "remaining_time": "0:42:27", "throughput": 4636.01, "total_tokens": 30878784} {"current_steps": 30690, "total_steps": 42420, "loss": 0.3089, "lr": 1.0771174842641032e-05, "epoch": 14.46958981612447, "percentage": 72.35, "elapsed_time": "1:51:01", "remaining_time": "0:42:26", "throughput": 4636.06, "total_tokens": 30884096} {"current_steps": 30695, "total_steps": 42420, "loss": 0.05, "lr": 1.0762718568928965e-05, "epoch": 14.471947194719473, "percentage": 72.36, "elapsed_time": "1:51:02", "remaining_time": "0:42:25", "throughput": 4636.1, "total_tokens": 30889952} {"current_steps": 30700, "total_steps": 42420, "loss": 0.0171, "lr": 1.0754264705346908e-05, "epoch": 14.474304573314475, "percentage": 72.37, "elapsed_time": "1:51:03", "remaining_time": "0:42:24", "throughput": 4636.11, "total_tokens": 30894560} {"current_steps": 30705, "total_steps": 42420, "loss": 0.2915, "lr": 1.0745813253325957e-05, "epoch": 14.476661951909477, "percentage": 72.38, "elapsed_time": "1:51:05", "remaining_time": "0:42:22", "throughput": 4636.17, "total_tokens": 30900288} {"current_steps": 30710, "total_steps": 42420, "loss": 0.0569, "lr": 1.07373642142968e-05, "epoch": 14.47901933050448, "percentage": 72.4, "elapsed_time": "1:51:06", "remaining_time": "0:42:21", "throughput": 4636.2, "total_tokens": 30905024} {"current_steps": 30715, "total_steps": 42420, "loss": 0.0723, "lr": 1.0728917589689725e-05, "epoch": 14.481376709099482, "percentage": 72.41, "elapsed_time": "1:51:06", "remaining_time": "0:42:20", "throughput": 4636.22, "total_tokens": 30909408} {"current_steps": 30720, "total_steps": 42420, "loss": 0.2735, "lr": 1.0720473380934584e-05, "epoch": 14.483734087694483, "percentage": 72.42, "elapsed_time": "1:51:07", "remaining_time": "0:42:19", "throughput": 4636.25, "total_tokens": 30914272} {"current_steps": 30725, "total_steps": 42420, "loss": 0.1284, "lr": 1.0712031589460846e-05, "epoch": 14.486091466289485, "percentage": 72.43, "elapsed_time": "1:51:08", "remaining_time": "0:42:18", "throughput": 4636.24, "total_tokens": 30918432} {"current_steps": 30730, "total_steps": 42420, "loss": 0.147, "lr": 1.0703592216697567e-05, "epoch": 14.488448844884488, "percentage": 72.44, "elapsed_time": "1:51:09", "remaining_time": "0:42:17", "throughput": 4636.29, "total_tokens": 30923648} {"current_steps": 30735, "total_steps": 42420, "loss": 0.1545, "lr": 1.0695155264073384e-05, "epoch": 14.49080622347949, "percentage": 72.45, "elapsed_time": "1:51:10", "remaining_time": "0:42:16", "throughput": 4636.33, "total_tokens": 30928736} {"current_steps": 30740, "total_steps": 42420, "loss": 0.0766, "lr": 1.0686720733016531e-05, "epoch": 14.493163602074493, "percentage": 72.47, "elapsed_time": "1:51:12", "remaining_time": "0:42:15", "throughput": 4636.36, "total_tokens": 30933824} {"current_steps": 30745, "total_steps": 42420, "loss": 0.1384, "lr": 1.0678288624954835e-05, "epoch": 14.495520980669495, "percentage": 72.48, "elapsed_time": "1:51:13", "remaining_time": "0:42:14", "throughput": 4636.39, "total_tokens": 30938880} {"current_steps": 30750, "total_steps": 42420, "loss": 0.0555, "lr": 1.0669858941315705e-05, "epoch": 14.497878359264497, "percentage": 72.49, "elapsed_time": "1:51:14", "remaining_time": "0:42:12", "throughput": 4636.4, "total_tokens": 30943392} {"current_steps": 30755, "total_steps": 42420, "loss": 0.0688, "lr": 1.0661431683526155e-05, "epoch": 14.5002357378595, "percentage": 72.5, "elapsed_time": "1:51:15", "remaining_time": "0:42:11", "throughput": 4636.46, "total_tokens": 30948896} {"current_steps": 30760, "total_steps": 42420, "loss": 0.0918, "lr": 1.0653006853012753e-05, "epoch": 14.502593116454502, "percentage": 72.51, "elapsed_time": "1:51:16", "remaining_time": "0:42:10", "throughput": 4636.5, "total_tokens": 30953952} {"current_steps": 30765, "total_steps": 42420, "loss": 0.1171, "lr": 1.0644584451201694e-05, "epoch": 14.504950495049505, "percentage": 72.52, "elapsed_time": "1:51:17", "remaining_time": "0:42:09", "throughput": 4636.51, "total_tokens": 30958048} {"current_steps": 30770, "total_steps": 42420, "loss": 0.0777, "lr": 1.0636164479518748e-05, "epoch": 14.507307873644507, "percentage": 72.54, "elapsed_time": "1:51:17", "remaining_time": "0:42:08", "throughput": 4636.53, "total_tokens": 30962400} {"current_steps": 30775, "total_steps": 42420, "loss": 0.0112, "lr": 1.0627746939389272e-05, "epoch": 14.50966525223951, "percentage": 72.55, "elapsed_time": "1:51:18", "remaining_time": "0:42:07", "throughput": 4636.54, "total_tokens": 30966528} {"current_steps": 30780, "total_steps": 42420, "loss": 0.0298, "lr": 1.061933183223821e-05, "epoch": 14.512022630834512, "percentage": 72.56, "elapsed_time": "1:51:19", "remaining_time": "0:42:06", "throughput": 4636.55, "total_tokens": 30970816} {"current_steps": 30785, "total_steps": 42420, "loss": 0.1007, "lr": 1.061091915949011e-05, "epoch": 14.514380009429514, "percentage": 72.57, "elapsed_time": "1:51:20", "remaining_time": "0:42:04", "throughput": 4636.61, "total_tokens": 30976352} {"current_steps": 30790, "total_steps": 42420, "loss": 0.0987, "lr": 1.0602508922569075e-05, "epoch": 14.516737388024517, "percentage": 72.58, "elapsed_time": "1:51:22", "remaining_time": "0:42:03", "throughput": 4636.67, "total_tokens": 30982912} {"current_steps": 30795, "total_steps": 42420, "loss": 0.1227, "lr": 1.0594101122898823e-05, "epoch": 14.519094766619519, "percentage": 72.6, "elapsed_time": "1:51:23", "remaining_time": "0:42:02", "throughput": 4636.7, "total_tokens": 30987744} {"current_steps": 30800, "total_steps": 42420, "loss": 0.1305, "lr": 1.058569576190265e-05, "epoch": 14.521452145214521, "percentage": 72.61, "elapsed_time": "1:51:24", "remaining_time": "0:42:01", "throughput": 4636.73, "total_tokens": 30992544} {"current_steps": 30805, "total_steps": 42420, "loss": 0.0165, "lr": 1.0577292841003456e-05, "epoch": 14.523809523809524, "percentage": 72.62, "elapsed_time": "1:51:25", "remaining_time": "0:42:00", "throughput": 4636.75, "total_tokens": 30997152} {"current_steps": 30810, "total_steps": 42420, "loss": 0.0998, "lr": 1.056889236162369e-05, "epoch": 14.526166902404526, "percentage": 72.63, "elapsed_time": "1:51:26", "remaining_time": "0:41:59", "throughput": 4636.77, "total_tokens": 31001760} {"current_steps": 30815, "total_steps": 42420, "loss": 0.0282, "lr": 1.0560494325185422e-05, "epoch": 14.528524280999529, "percentage": 72.64, "elapsed_time": "1:51:27", "remaining_time": "0:41:58", "throughput": 4636.82, "total_tokens": 31007072} {"current_steps": 30820, "total_steps": 42420, "loss": 0.0557, "lr": 1.0552098733110294e-05, "epoch": 14.530881659594531, "percentage": 72.65, "elapsed_time": "1:51:28", "remaining_time": "0:41:57", "throughput": 4636.85, "total_tokens": 31011680} {"current_steps": 30825, "total_steps": 42420, "loss": 0.1853, "lr": 1.0543705586819541e-05, "epoch": 14.533239038189533, "percentage": 72.67, "elapsed_time": "1:51:29", "remaining_time": "0:41:56", "throughput": 4636.86, "total_tokens": 31016032} {"current_steps": 30830, "total_steps": 42420, "loss": 0.2129, "lr": 1.0535314887733977e-05, "epoch": 14.535596416784536, "percentage": 72.68, "elapsed_time": "1:51:30", "remaining_time": "0:41:55", "throughput": 4636.91, "total_tokens": 31021728} {"current_steps": 30835, "total_steps": 42420, "loss": 0.0914, "lr": 1.0526926637274007e-05, "epoch": 14.537953795379538, "percentage": 72.69, "elapsed_time": "1:51:31", "remaining_time": "0:41:53", "throughput": 4636.93, "total_tokens": 31026112} {"current_steps": 30840, "total_steps": 42420, "loss": 0.0332, "lr": 1.0518540836859616e-05, "epoch": 14.54031117397454, "percentage": 72.7, "elapsed_time": "1:51:32", "remaining_time": "0:41:52", "throughput": 4636.97, "total_tokens": 31031904} {"current_steps": 30845, "total_steps": 42420, "loss": 0.1062, "lr": 1.051015748791039e-05, "epoch": 14.542668552569543, "percentage": 72.71, "elapsed_time": "1:51:33", "remaining_time": "0:41:51", "throughput": 4637.03, "total_tokens": 31037600} {"current_steps": 30850, "total_steps": 42420, "loss": 0.078, "lr": 1.0501776591845472e-05, "epoch": 14.545025931164545, "percentage": 72.73, "elapsed_time": "1:51:34", "remaining_time": "0:41:50", "throughput": 4637.06, "total_tokens": 31042816} {"current_steps": 30855, "total_steps": 42420, "loss": 0.0647, "lr": 1.0493398150083608e-05, "epoch": 14.547383309759548, "percentage": 72.74, "elapsed_time": "1:51:35", "remaining_time": "0:41:49", "throughput": 4637.12, "total_tokens": 31049088} {"current_steps": 30860, "total_steps": 42420, "loss": 0.0844, "lr": 1.0485022164043132e-05, "epoch": 14.54974068835455, "percentage": 72.75, "elapsed_time": "1:51:36", "remaining_time": "0:41:48", "throughput": 4637.15, "total_tokens": 31053952} {"current_steps": 30865, "total_steps": 42420, "loss": 0.0245, "lr": 1.047664863514195e-05, "epoch": 14.552098066949553, "percentage": 72.76, "elapsed_time": "1:51:37", "remaining_time": "0:41:47", "throughput": 4637.21, "total_tokens": 31059360} {"current_steps": 30870, "total_steps": 42420, "loss": 0.0132, "lr": 1.0468277564797563e-05, "epoch": 14.554455445544555, "percentage": 72.77, "elapsed_time": "1:51:38", "remaining_time": "0:41:46", "throughput": 4637.2, "total_tokens": 31063552} {"current_steps": 30875, "total_steps": 42420, "loss": 0.0338, "lr": 1.045990895442705e-05, "epoch": 14.556812824139557, "percentage": 72.78, "elapsed_time": "1:51:39", "remaining_time": "0:41:45", "throughput": 4637.21, "total_tokens": 31067840} {"current_steps": 30880, "total_steps": 42420, "loss": 0.1075, "lr": 1.0451542805447073e-05, "epoch": 14.55917020273456, "percentage": 72.8, "elapsed_time": "1:51:40", "remaining_time": "0:41:44", "throughput": 4637.25, "total_tokens": 31072864} {"current_steps": 30885, "total_steps": 42420, "loss": 0.0966, "lr": 1.044317911927389e-05, "epoch": 14.561527581329562, "percentage": 72.81, "elapsed_time": "1:51:41", "remaining_time": "0:41:42", "throughput": 4637.25, "total_tokens": 31076992} {"current_steps": 30890, "total_steps": 42420, "loss": 0.0992, "lr": 1.0434817897323315e-05, "epoch": 14.563884959924565, "percentage": 72.82, "elapsed_time": "1:51:42", "remaining_time": "0:41:41", "throughput": 4637.25, "total_tokens": 31081504} {"current_steps": 30895, "total_steps": 42420, "loss": 0.0567, "lr": 1.0426459141010764e-05, "epoch": 14.566242338519567, "percentage": 72.83, "elapsed_time": "1:51:43", "remaining_time": "0:41:40", "throughput": 4637.28, "total_tokens": 31086048} {"current_steps": 30900, "total_steps": 42420, "loss": 0.2218, "lr": 1.0418102851751237e-05, "epoch": 14.56859971711457, "percentage": 72.84, "elapsed_time": "1:51:44", "remaining_time": "0:41:39", "throughput": 4637.3, "total_tokens": 31090688} {"current_steps": 30905, "total_steps": 42420, "loss": 0.0554, "lr": 1.0409749030959309e-05, "epoch": 14.570957095709572, "percentage": 72.85, "elapsed_time": "1:51:45", "remaining_time": "0:41:38", "throughput": 4637.34, "total_tokens": 31095680} {"current_steps": 30910, "total_steps": 42420, "loss": 0.0912, "lr": 1.0401397680049143e-05, "epoch": 14.573314474304574, "percentage": 72.87, "elapsed_time": "1:51:46", "remaining_time": "0:41:37", "throughput": 4637.35, "total_tokens": 31100096} {"current_steps": 30915, "total_steps": 42420, "loss": 0.3244, "lr": 1.0393048800434482e-05, "epoch": 14.575671852899575, "percentage": 72.88, "elapsed_time": "1:51:47", "remaining_time": "0:41:36", "throughput": 4637.38, "total_tokens": 31104928} {"current_steps": 30920, "total_steps": 42420, "loss": 0.0453, "lr": 1.0384702393528646e-05, "epoch": 14.578029231494579, "percentage": 72.89, "elapsed_time": "1:51:48", "remaining_time": "0:41:35", "throughput": 4637.42, "total_tokens": 31110176} {"current_steps": 30925, "total_steps": 42420, "loss": 0.1746, "lr": 1.0376358460744549e-05, "epoch": 14.58038661008958, "percentage": 72.9, "elapsed_time": "1:51:49", "remaining_time": "0:41:33", "throughput": 4637.46, "total_tokens": 31115456} {"current_steps": 30930, "total_steps": 42420, "loss": 0.0317, "lr": 1.036801700349466e-05, "epoch": 14.582743988684582, "percentage": 72.91, "elapsed_time": "1:51:50", "remaining_time": "0:41:32", "throughput": 4637.48, "total_tokens": 31120320} {"current_steps": 30935, "total_steps": 42420, "loss": 0.1747, "lr": 1.0359678023191056e-05, "epoch": 14.585101367279584, "percentage": 72.93, "elapsed_time": "1:51:51", "remaining_time": "0:41:31", "throughput": 4637.49, "total_tokens": 31124544} {"current_steps": 30940, "total_steps": 42420, "loss": 0.118, "lr": 1.0351341521245384e-05, "epoch": 14.587458745874587, "percentage": 72.94, "elapsed_time": "1:51:52", "remaining_time": "0:41:30", "throughput": 4637.52, "total_tokens": 31129024} {"current_steps": 30945, "total_steps": 42420, "loss": 0.113, "lr": 1.0343007499068872e-05, "epoch": 14.58981612446959, "percentage": 72.95, "elapsed_time": "1:51:53", "remaining_time": "0:41:29", "throughput": 4637.57, "total_tokens": 31135104} {"current_steps": 30950, "total_steps": 42420, "loss": 0.0813, "lr": 1.0334675958072329e-05, "epoch": 14.592173503064592, "percentage": 72.96, "elapsed_time": "1:51:54", "remaining_time": "0:41:28", "throughput": 4637.64, "total_tokens": 31141312} {"current_steps": 30955, "total_steps": 42420, "loss": 0.1365, "lr": 1.0326346899666142e-05, "epoch": 14.594530881659594, "percentage": 72.97, "elapsed_time": "1:51:56", "remaining_time": "0:41:27", "throughput": 4637.7, "total_tokens": 31147296} {"current_steps": 30960, "total_steps": 42420, "loss": 0.0455, "lr": 1.0318020325260282e-05, "epoch": 14.596888260254596, "percentage": 72.98, "elapsed_time": "1:51:57", "remaining_time": "0:41:26", "throughput": 4637.76, "total_tokens": 31152768} {"current_steps": 30965, "total_steps": 42420, "loss": 0.0567, "lr": 1.0309696236264304e-05, "epoch": 14.599245638849599, "percentage": 73.0, "elapsed_time": "1:51:58", "remaining_time": "0:41:25", "throughput": 4637.8, "total_tokens": 31157824} {"current_steps": 30970, "total_steps": 42420, "loss": 0.1849, "lr": 1.030137463408732e-05, "epoch": 14.601603017444601, "percentage": 73.01, "elapsed_time": "1:51:59", "remaining_time": "0:41:24", "throughput": 4637.86, "total_tokens": 31164224} {"current_steps": 30975, "total_steps": 42420, "loss": 0.0566, "lr": 1.0293055520138037e-05, "epoch": 14.603960396039604, "percentage": 73.02, "elapsed_time": "1:52:00", "remaining_time": "0:41:23", "throughput": 4637.89, "total_tokens": 31169056} {"current_steps": 30980, "total_steps": 42420, "loss": 0.1621, "lr": 1.0284738895824748e-05, "epoch": 14.606317774634606, "percentage": 73.03, "elapsed_time": "1:52:01", "remaining_time": "0:41:22", "throughput": 4637.95, "total_tokens": 31174976} {"current_steps": 30985, "total_steps": 42420, "loss": 0.0617, "lr": 1.0276424762555308e-05, "epoch": 14.608675153229608, "percentage": 73.04, "elapsed_time": "1:52:02", "remaining_time": "0:41:21", "throughput": 4637.97, "total_tokens": 31179744} {"current_steps": 30990, "total_steps": 42420, "loss": 0.0863, "lr": 1.0268113121737169e-05, "epoch": 14.61103253182461, "percentage": 73.06, "elapsed_time": "1:52:03", "remaining_time": "0:41:19", "throughput": 4637.98, "total_tokens": 31184416} {"current_steps": 30995, "total_steps": 42420, "loss": 0.0857, "lr": 1.0259803974777343e-05, "epoch": 14.613389910419613, "percentage": 73.07, "elapsed_time": "1:52:04", "remaining_time": "0:41:18", "throughput": 4638.01, "total_tokens": 31189216} {"current_steps": 31000, "total_steps": 42420, "loss": 0.0707, "lr": 1.0251497323082432e-05, "epoch": 14.615747289014616, "percentage": 73.08, "elapsed_time": "1:52:05", "remaining_time": "0:41:17", "throughput": 4637.99, "total_tokens": 31193216} {"current_steps": 31005, "total_steps": 42420, "loss": 0.0196, "lr": 1.0243193168058616e-05, "epoch": 14.618104667609618, "percentage": 73.09, "elapsed_time": "1:52:06", "remaining_time": "0:41:16", "throughput": 4638.0, "total_tokens": 31197600} {"current_steps": 31010, "total_steps": 42420, "loss": 0.1148, "lr": 1.0234891511111633e-05, "epoch": 14.62046204620462, "percentage": 73.1, "elapsed_time": "1:52:07", "remaining_time": "0:41:15", "throughput": 4638.03, "total_tokens": 31202752} {"current_steps": 31015, "total_steps": 42420, "loss": 0.0634, "lr": 1.0226592353646828e-05, "epoch": 14.622819424799623, "percentage": 73.11, "elapsed_time": "1:52:08", "remaining_time": "0:41:14", "throughput": 4638.07, "total_tokens": 31208256} {"current_steps": 31020, "total_steps": 42420, "loss": 0.0526, "lr": 1.0218295697069089e-05, "epoch": 14.625176803394625, "percentage": 73.13, "elapsed_time": "1:52:09", "remaining_time": "0:41:13", "throughput": 4638.06, "total_tokens": 31212416} {"current_steps": 31025, "total_steps": 42420, "loss": 0.1146, "lr": 1.021000154278291e-05, "epoch": 14.627534181989628, "percentage": 73.14, "elapsed_time": "1:52:10", "remaining_time": "0:41:12", "throughput": 4638.11, "total_tokens": 31218528} {"current_steps": 31030, "total_steps": 42420, "loss": 0.0807, "lr": 1.0201709892192352e-05, "epoch": 14.62989156058463, "percentage": 73.15, "elapsed_time": "1:52:11", "remaining_time": "0:41:10", "throughput": 4638.09, "total_tokens": 31222208} {"current_steps": 31035, "total_steps": 42420, "loss": 0.043, "lr": 1.0193420746701047e-05, "epoch": 14.632248939179632, "percentage": 73.16, "elapsed_time": "1:52:12", "remaining_time": "0:41:09", "throughput": 4638.11, "total_tokens": 31226560} {"current_steps": 31040, "total_steps": 42420, "loss": 0.0279, "lr": 1.0185134107712208e-05, "epoch": 14.634606317774635, "percentage": 73.17, "elapsed_time": "1:52:13", "remaining_time": "0:41:08", "throughput": 4638.14, "total_tokens": 31231264} {"current_steps": 31045, "total_steps": 42420, "loss": 0.1611, "lr": 1.0176849976628622e-05, "epoch": 14.636963696369637, "percentage": 73.18, "elapsed_time": "1:52:14", "remaining_time": "0:41:07", "throughput": 4638.14, "total_tokens": 31235648} {"current_steps": 31050, "total_steps": 42420, "loss": 0.0595, "lr": 1.0168568354852651e-05, "epoch": 14.63932107496464, "percentage": 73.2, "elapsed_time": "1:52:15", "remaining_time": "0:41:06", "throughput": 4638.17, "total_tokens": 31241344} {"current_steps": 31055, "total_steps": 42420, "loss": 0.0491, "lr": 1.0160289243786245e-05, "epoch": 14.641678453559642, "percentage": 73.21, "elapsed_time": "1:52:16", "remaining_time": "0:41:05", "throughput": 4638.17, "total_tokens": 31245376} {"current_steps": 31060, "total_steps": 42420, "loss": 0.2576, "lr": 1.0152012644830897e-05, "epoch": 14.644035832154644, "percentage": 73.22, "elapsed_time": "1:52:17", "remaining_time": "0:41:04", "throughput": 4638.23, "total_tokens": 31251520} {"current_steps": 31065, "total_steps": 42420, "loss": 0.0908, "lr": 1.0143738559387702e-05, "epoch": 14.646393210749647, "percentage": 73.23, "elapsed_time": "1:52:19", "remaining_time": "0:41:03", "throughput": 4638.29, "total_tokens": 31257824} {"current_steps": 31070, "total_steps": 42420, "loss": 0.2127, "lr": 1.0135466988857329e-05, "epoch": 14.64875058934465, "percentage": 73.24, "elapsed_time": "1:52:20", "remaining_time": "0:41:02", "throughput": 4638.27, "total_tokens": 31262016} {"current_steps": 31075, "total_steps": 42420, "loss": 0.2105, "lr": 1.0127197934640003e-05, "epoch": 14.651107967939652, "percentage": 73.26, "elapsed_time": "1:52:20", "remaining_time": "0:41:01", "throughput": 4638.28, "total_tokens": 31266592} {"current_steps": 31080, "total_steps": 42420, "loss": 0.1024, "lr": 1.0118931398135545e-05, "epoch": 14.653465346534654, "percentage": 73.27, "elapsed_time": "1:52:22", "remaining_time": "0:40:59", "throughput": 4638.32, "total_tokens": 31272096} {"current_steps": 31085, "total_steps": 42420, "loss": 0.0156, "lr": 1.0110667380743335e-05, "epoch": 14.655822725129656, "percentage": 73.28, "elapsed_time": "1:52:23", "remaining_time": "0:40:58", "throughput": 4638.35, "total_tokens": 31276768} {"current_steps": 31090, "total_steps": 42420, "loss": 0.0339, "lr": 1.0102405883862328e-05, "epoch": 14.658180103724659, "percentage": 73.29, "elapsed_time": "1:52:24", "remaining_time": "0:40:57", "throughput": 4638.38, "total_tokens": 31281696} {"current_steps": 31095, "total_steps": 42420, "loss": 0.0897, "lr": 1.009414690889107e-05, "epoch": 14.660537482319661, "percentage": 73.3, "elapsed_time": "1:52:25", "remaining_time": "0:40:56", "throughput": 4638.42, "total_tokens": 31287232} {"current_steps": 31100, "total_steps": 42420, "loss": 0.0706, "lr": 1.0085890457227645e-05, "epoch": 14.662894860914664, "percentage": 73.31, "elapsed_time": "1:52:26", "remaining_time": "0:40:55", "throughput": 4638.45, "total_tokens": 31292192} {"current_steps": 31105, "total_steps": 42420, "loss": 0.0644, "lr": 1.0077636530269735e-05, "epoch": 14.665252239509666, "percentage": 73.33, "elapsed_time": "1:52:27", "remaining_time": "0:40:54", "throughput": 4638.51, "total_tokens": 31298208} {"current_steps": 31110, "total_steps": 42420, "loss": 0.0932, "lr": 1.0069385129414596e-05, "epoch": 14.667609618104667, "percentage": 73.34, "elapsed_time": "1:52:28", "remaining_time": "0:40:53", "throughput": 4638.54, "total_tokens": 31303616} {"current_steps": 31115, "total_steps": 42420, "loss": 0.1217, "lr": 1.0061136256059045e-05, "epoch": 14.66996699669967, "percentage": 73.35, "elapsed_time": "1:52:29", "remaining_time": "0:40:52", "throughput": 4638.58, "total_tokens": 31310368} {"current_steps": 31120, "total_steps": 42420, "loss": 0.0648, "lr": 1.005288991159948e-05, "epoch": 14.672324375294671, "percentage": 73.36, "elapsed_time": "1:52:30", "remaining_time": "0:40:51", "throughput": 4638.59, "total_tokens": 31314816} {"current_steps": 31125, "total_steps": 42420, "loss": 0.1038, "lr": 1.0044646097431865e-05, "epoch": 14.674681753889674, "percentage": 73.37, "elapsed_time": "1:52:31", "remaining_time": "0:40:50", "throughput": 4638.64, "total_tokens": 31319776} {"current_steps": 31130, "total_steps": 42420, "loss": 0.1547, "lr": 1.0036404814951739e-05, "epoch": 14.677039132484676, "percentage": 73.39, "elapsed_time": "1:52:33", "remaining_time": "0:40:49", "throughput": 4638.7, "total_tokens": 31325824} {"current_steps": 31135, "total_steps": 42420, "loss": 0.1233, "lr": 1.0028166065554218e-05, "epoch": 14.679396511079679, "percentage": 73.4, "elapsed_time": "1:52:34", "remaining_time": "0:40:48", "throughput": 4638.71, "total_tokens": 31330688} {"current_steps": 31140, "total_steps": 42420, "loss": 0.0848, "lr": 1.0019929850633967e-05, "epoch": 14.681753889674681, "percentage": 73.41, "elapsed_time": "1:52:35", "remaining_time": "0:40:46", "throughput": 4638.71, "total_tokens": 31335136} {"current_steps": 31145, "total_steps": 42420, "loss": 0.1155, "lr": 1.0011696171585245e-05, "epoch": 14.684111268269683, "percentage": 73.42, "elapsed_time": "1:52:36", "remaining_time": "0:40:45", "throughput": 4638.76, "total_tokens": 31340352} {"current_steps": 31150, "total_steps": 42420, "loss": 0.1926, "lr": 1.0003465029801873e-05, "epoch": 14.686468646864686, "percentage": 73.43, "elapsed_time": "1:52:37", "remaining_time": "0:40:44", "throughput": 4638.77, "total_tokens": 31344896} {"current_steps": 31155, "total_steps": 42420, "loss": 0.212, "lr": 9.995236426677245e-06, "epoch": 14.688826025459688, "percentage": 73.44, "elapsed_time": "1:52:38", "remaining_time": "0:40:43", "throughput": 4638.8, "total_tokens": 31349984} {"current_steps": 31160, "total_steps": 42420, "loss": 0.2056, "lr": 9.987010363604327e-06, "epoch": 14.69118340405469, "percentage": 73.46, "elapsed_time": "1:52:39", "remaining_time": "0:40:42", "throughput": 4638.83, "total_tokens": 31354592} {"current_steps": 31165, "total_steps": 42420, "loss": 0.173, "lr": 9.978786841975646e-06, "epoch": 14.693540782649693, "percentage": 73.47, "elapsed_time": "1:52:40", "remaining_time": "0:40:41", "throughput": 4638.83, "total_tokens": 31359072} {"current_steps": 31170, "total_steps": 42420, "loss": 0.08, "lr": 9.970565863183306e-06, "epoch": 14.695898161244696, "percentage": 73.48, "elapsed_time": "1:52:41", "remaining_time": "0:40:40", "throughput": 4638.84, "total_tokens": 31365216} {"current_steps": 31175, "total_steps": 42420, "loss": 0.1001, "lr": 9.96234742861899e-06, "epoch": 14.698255539839698, "percentage": 73.49, "elapsed_time": "1:52:42", "remaining_time": "0:40:39", "throughput": 4638.87, "total_tokens": 31370144} {"current_steps": 31180, "total_steps": 42420, "loss": 0.0769, "lr": 9.95413153967392e-06, "epoch": 14.7006129184347, "percentage": 73.5, "elapsed_time": "1:52:43", "remaining_time": "0:40:38", "throughput": 4638.87, "total_tokens": 31374400} {"current_steps": 31185, "total_steps": 42420, "loss": 0.2135, "lr": 9.945918197738915e-06, "epoch": 14.702970297029703, "percentage": 73.51, "elapsed_time": "1:52:44", "remaining_time": "0:40:36", "throughput": 4638.88, "total_tokens": 31378688} {"current_steps": 31190, "total_steps": 42420, "loss": 0.0274, "lr": 9.937707404204358e-06, "epoch": 14.705327675624705, "percentage": 73.53, "elapsed_time": "1:52:45", "remaining_time": "0:40:35", "throughput": 4638.91, "total_tokens": 31383424} {"current_steps": 31195, "total_steps": 42420, "loss": 0.0838, "lr": 9.929499160460193e-06, "epoch": 14.707685054219708, "percentage": 73.54, "elapsed_time": "1:52:46", "remaining_time": "0:40:34", "throughput": 4638.88, "total_tokens": 31387840} {"current_steps": 31200, "total_steps": 42420, "loss": 0.1856, "lr": 9.921293467895937e-06, "epoch": 14.71004243281471, "percentage": 73.55, "elapsed_time": "1:52:47", "remaining_time": "0:40:33", "throughput": 4638.88, "total_tokens": 31392000} {"current_steps": 31205, "total_steps": 42420, "loss": 0.0624, "lr": 9.913090327900677e-06, "epoch": 14.712399811409712, "percentage": 73.56, "elapsed_time": "1:52:48", "remaining_time": "0:40:32", "throughput": 4638.86, "total_tokens": 31396224} {"current_steps": 31210, "total_steps": 42420, "loss": 0.0389, "lr": 9.90488974186306e-06, "epoch": 14.714757190004715, "percentage": 73.57, "elapsed_time": "1:52:49", "remaining_time": "0:40:31", "throughput": 4638.88, "total_tokens": 31401472} {"current_steps": 31215, "total_steps": 42420, "loss": 0.0284, "lr": 9.89669171117132e-06, "epoch": 14.717114568599717, "percentage": 73.59, "elapsed_time": "1:52:50", "remaining_time": "0:40:30", "throughput": 4638.88, "total_tokens": 31405696} {"current_steps": 31220, "total_steps": 42420, "loss": 0.0927, "lr": 9.888496237213226e-06, "epoch": 14.71947194719472, "percentage": 73.6, "elapsed_time": "1:52:51", "remaining_time": "0:40:29", "throughput": 4638.9, "total_tokens": 31410400} {"current_steps": 31225, "total_steps": 42420, "loss": 0.0771, "lr": 9.880303321376139e-06, "epoch": 14.721829325789722, "percentage": 73.61, "elapsed_time": "1:52:52", "remaining_time": "0:40:27", "throughput": 4638.91, "total_tokens": 31415040} {"current_steps": 31230, "total_steps": 42420, "loss": 0.075, "lr": 9.872112965046984e-06, "epoch": 14.724186704384724, "percentage": 73.62, "elapsed_time": "1:52:53", "remaining_time": "0:40:26", "throughput": 4638.94, "total_tokens": 31419776} {"current_steps": 31235, "total_steps": 42420, "loss": 0.1926, "lr": 9.863925169612253e-06, "epoch": 14.726544082979727, "percentage": 73.63, "elapsed_time": "1:52:54", "remaining_time": "0:40:26", "throughput": 4638.81, "total_tokens": 31427008} {"current_steps": 31240, "total_steps": 42420, "loss": 0.0636, "lr": 9.855739936457986e-06, "epoch": 14.72890146157473, "percentage": 73.64, "elapsed_time": "1:52:55", "remaining_time": "0:40:24", "throughput": 4638.84, "total_tokens": 31432064} {"current_steps": 31245, "total_steps": 42420, "loss": 0.1413, "lr": 9.847557266969814e-06, "epoch": 14.731258840169732, "percentage": 73.66, "elapsed_time": "1:52:56", "remaining_time": "0:40:23", "throughput": 4638.82, "total_tokens": 31436160} {"current_steps": 31250, "total_steps": 42420, "loss": 0.0398, "lr": 9.839377162532924e-06, "epoch": 14.733616218764734, "percentage": 73.67, "elapsed_time": "1:52:57", "remaining_time": "0:40:22", "throughput": 4638.8, "total_tokens": 31440000} {"current_steps": 31255, "total_steps": 42420, "loss": 0.1318, "lr": 9.831199624532067e-06, "epoch": 14.735973597359736, "percentage": 73.68, "elapsed_time": "1:52:58", "remaining_time": "0:40:21", "throughput": 4638.84, "total_tokens": 31445952} {"current_steps": 31260, "total_steps": 42420, "loss": 0.0771, "lr": 9.823024654351562e-06, "epoch": 14.738330975954739, "percentage": 73.69, "elapsed_time": "1:52:59", "remaining_time": "0:40:20", "throughput": 4638.86, "total_tokens": 31450336} {"current_steps": 31265, "total_steps": 42420, "loss": 0.0593, "lr": 9.8148522533753e-06, "epoch": 14.740688354549741, "percentage": 73.7, "elapsed_time": "1:53:01", "remaining_time": "0:40:19", "throughput": 4638.89, "total_tokens": 31456608} {"current_steps": 31270, "total_steps": 42420, "loss": 0.0599, "lr": 9.806682422986715e-06, "epoch": 14.743045733144744, "percentage": 73.72, "elapsed_time": "1:53:01", "remaining_time": "0:40:18", "throughput": 4638.89, "total_tokens": 31460864} {"current_steps": 31275, "total_steps": 42420, "loss": 0.1384, "lr": 9.798515164568827e-06, "epoch": 14.745403111739746, "percentage": 73.73, "elapsed_time": "1:53:03", "remaining_time": "0:40:17", "throughput": 4638.93, "total_tokens": 31466304} {"current_steps": 31280, "total_steps": 42420, "loss": 0.1223, "lr": 9.790350479504215e-06, "epoch": 14.747760490334748, "percentage": 73.74, "elapsed_time": "1:53:04", "remaining_time": "0:40:16", "throughput": 4638.94, "total_tokens": 31471072} {"current_steps": 31285, "total_steps": 42420, "loss": 0.1419, "lr": 9.782188369175024e-06, "epoch": 14.75011786892975, "percentage": 73.75, "elapsed_time": "1:53:05", "remaining_time": "0:40:14", "throughput": 4638.91, "total_tokens": 31475360} {"current_steps": 31290, "total_steps": 42420, "loss": 0.0343, "lr": 9.774028834962956e-06, "epoch": 14.752475247524753, "percentage": 73.76, "elapsed_time": "1:53:06", "remaining_time": "0:40:13", "throughput": 4638.96, "total_tokens": 31480896} {"current_steps": 31295, "total_steps": 42420, "loss": 0.1234, "lr": 9.765871878249286e-06, "epoch": 14.754832626119756, "percentage": 73.77, "elapsed_time": "1:53:07", "remaining_time": "0:40:12", "throughput": 4639.01, "total_tokens": 31486048} {"current_steps": 31300, "total_steps": 42420, "loss": 0.0293, "lr": 9.757717500414842e-06, "epoch": 14.757190004714758, "percentage": 73.79, "elapsed_time": "1:53:08", "remaining_time": "0:40:11", "throughput": 4639.04, "total_tokens": 31490752} {"current_steps": 31305, "total_steps": 42420, "loss": 0.1201, "lr": 9.749565702840038e-06, "epoch": 14.75954738330976, "percentage": 73.8, "elapsed_time": "1:53:09", "remaining_time": "0:40:10", "throughput": 4639.02, "total_tokens": 31494848} {"current_steps": 31310, "total_steps": 42420, "loss": 0.1159, "lr": 9.741416486904814e-06, "epoch": 14.761904761904763, "percentage": 73.81, "elapsed_time": "1:53:10", "remaining_time": "0:40:09", "throughput": 4639.07, "total_tokens": 31500256} {"current_steps": 31315, "total_steps": 42420, "loss": 0.0852, "lr": 9.733269853988703e-06, "epoch": 14.764262140499763, "percentage": 73.82, "elapsed_time": "1:53:11", "remaining_time": "0:40:08", "throughput": 4639.1, "total_tokens": 31505344} {"current_steps": 31320, "total_steps": 42420, "loss": 0.1946, "lr": 9.725125805470792e-06, "epoch": 14.766619519094768, "percentage": 73.83, "elapsed_time": "1:53:12", "remaining_time": "0:40:07", "throughput": 4639.15, "total_tokens": 31512608} {"current_steps": 31325, "total_steps": 42420, "loss": 0.2275, "lr": 9.716984342729727e-06, "epoch": 14.768976897689768, "percentage": 73.84, "elapsed_time": "1:53:14", "remaining_time": "0:40:06", "throughput": 4639.2, "total_tokens": 31519200} {"current_steps": 31330, "total_steps": 42420, "loss": 0.1303, "lr": 9.708845467143723e-06, "epoch": 14.77133427628477, "percentage": 73.86, "elapsed_time": "1:53:15", "remaining_time": "0:40:05", "throughput": 4639.22, "total_tokens": 31523712} {"current_steps": 31335, "total_steps": 42420, "loss": 0.0204, "lr": 9.700709180090553e-06, "epoch": 14.773691654879773, "percentage": 73.87, "elapsed_time": "1:53:16", "remaining_time": "0:40:04", "throughput": 4639.23, "total_tokens": 31528416} {"current_steps": 31340, "total_steps": 42420, "loss": 0.1504, "lr": 9.692575482947552e-06, "epoch": 14.776049033474775, "percentage": 73.88, "elapsed_time": "1:53:17", "remaining_time": "0:40:03", "throughput": 4639.26, "total_tokens": 31534208} {"current_steps": 31345, "total_steps": 42420, "loss": 0.1112, "lr": 9.684444377091625e-06, "epoch": 14.778406412069778, "percentage": 73.89, "elapsed_time": "1:53:18", "remaining_time": "0:40:02", "throughput": 4639.31, "total_tokens": 31539744} {"current_steps": 31350, "total_steps": 42420, "loss": 0.115, "lr": 9.676315863899213e-06, "epoch": 14.78076379066478, "percentage": 73.9, "elapsed_time": "1:53:19", "remaining_time": "0:40:00", "throughput": 4639.35, "total_tokens": 31545376} {"current_steps": 31355, "total_steps": 42420, "loss": 0.1022, "lr": 9.668189944746343e-06, "epoch": 14.783121169259783, "percentage": 73.92, "elapsed_time": "1:53:20", "remaining_time": "0:39:59", "throughput": 4639.41, "total_tokens": 31551424} {"current_steps": 31360, "total_steps": 42420, "loss": 0.3049, "lr": 9.660066621008595e-06, "epoch": 14.785478547854785, "percentage": 73.93, "elapsed_time": "1:53:21", "remaining_time": "0:39:58", "throughput": 4639.42, "total_tokens": 31555840} {"current_steps": 31365, "total_steps": 42420, "loss": 0.1042, "lr": 9.651945894061112e-06, "epoch": 14.787835926449787, "percentage": 73.94, "elapsed_time": "1:53:22", "remaining_time": "0:39:57", "throughput": 4639.44, "total_tokens": 31560416} {"current_steps": 31370, "total_steps": 42420, "loss": 0.1535, "lr": 9.643827765278596e-06, "epoch": 14.79019330504479, "percentage": 73.95, "elapsed_time": "1:53:23", "remaining_time": "0:39:56", "throughput": 4639.46, "total_tokens": 31565216} {"current_steps": 31375, "total_steps": 42420, "loss": 0.1064, "lr": 9.635712236035305e-06, "epoch": 14.792550683639792, "percentage": 73.96, "elapsed_time": "1:53:24", "remaining_time": "0:39:55", "throughput": 4639.48, "total_tokens": 31569888} {"current_steps": 31380, "total_steps": 42420, "loss": 0.1124, "lr": 9.62759930770506e-06, "epoch": 14.794908062234795, "percentage": 73.97, "elapsed_time": "1:53:25", "remaining_time": "0:39:54", "throughput": 4639.51, "total_tokens": 31574656} {"current_steps": 31385, "total_steps": 42420, "loss": 0.079, "lr": 9.619488981661254e-06, "epoch": 14.797265440829797, "percentage": 73.99, "elapsed_time": "1:53:26", "remaining_time": "0:39:53", "throughput": 4639.54, "total_tokens": 31579552} {"current_steps": 31390, "total_steps": 42420, "loss": 0.0346, "lr": 9.611381259276808e-06, "epoch": 14.7996228194248, "percentage": 74.0, "elapsed_time": "1:53:27", "remaining_time": "0:39:52", "throughput": 4639.58, "total_tokens": 31584960} {"current_steps": 31395, "total_steps": 42420, "loss": 0.2221, "lr": 9.60327614192423e-06, "epoch": 14.801980198019802, "percentage": 74.01, "elapsed_time": "1:53:28", "remaining_time": "0:39:51", "throughput": 4639.59, "total_tokens": 31589728} {"current_steps": 31400, "total_steps": 42420, "loss": 0.1251, "lr": 9.595173630975582e-06, "epoch": 14.804337576614804, "percentage": 74.02, "elapsed_time": "1:53:29", "remaining_time": "0:39:49", "throughput": 4639.6, "total_tokens": 31594080} {"current_steps": 31405, "total_steps": 42420, "loss": 0.0282, "lr": 9.587073727802478e-06, "epoch": 14.806694955209807, "percentage": 74.03, "elapsed_time": "1:53:30", "remaining_time": "0:39:48", "throughput": 4639.63, "total_tokens": 31598656} {"current_steps": 31410, "total_steps": 42420, "loss": 0.0943, "lr": 9.578976433776096e-06, "epoch": 14.809052333804809, "percentage": 74.05, "elapsed_time": "1:53:31", "remaining_time": "0:39:47", "throughput": 4639.64, "total_tokens": 31603200} {"current_steps": 31415, "total_steps": 42420, "loss": 0.0809, "lr": 9.57088175026717e-06, "epoch": 14.811409712399811, "percentage": 74.06, "elapsed_time": "1:53:32", "remaining_time": "0:39:46", "throughput": 4639.68, "total_tokens": 31608704} {"current_steps": 31420, "total_steps": 42420, "loss": 0.1564, "lr": 9.56278967864599e-06, "epoch": 14.813767090994814, "percentage": 74.07, "elapsed_time": "1:53:33", "remaining_time": "0:39:45", "throughput": 4639.72, "total_tokens": 31614016} {"current_steps": 31425, "total_steps": 42420, "loss": 0.0122, "lr": 9.554700220282417e-06, "epoch": 14.816124469589816, "percentage": 74.08, "elapsed_time": "1:53:34", "remaining_time": "0:39:44", "throughput": 4639.72, "total_tokens": 31618656} {"current_steps": 31430, "total_steps": 42420, "loss": 0.0932, "lr": 9.546613376545844e-06, "epoch": 14.818481848184819, "percentage": 74.09, "elapsed_time": "1:53:35", "remaining_time": "0:39:43", "throughput": 4639.77, "total_tokens": 31623872} {"current_steps": 31435, "total_steps": 42420, "loss": 0.0923, "lr": 9.538529148805242e-06, "epoch": 14.820839226779821, "percentage": 74.1, "elapsed_time": "1:53:36", "remaining_time": "0:39:42", "throughput": 4639.81, "total_tokens": 31629184} {"current_steps": 31440, "total_steps": 42420, "loss": 0.1809, "lr": 9.530447538429135e-06, "epoch": 14.823196605374823, "percentage": 74.12, "elapsed_time": "1:53:37", "remaining_time": "0:39:41", "throughput": 4639.81, "total_tokens": 31633376} {"current_steps": 31445, "total_steps": 42420, "loss": 0.121, "lr": 9.522368546785602e-06, "epoch": 14.825553983969826, "percentage": 74.13, "elapsed_time": "1:53:38", "remaining_time": "0:39:39", "throughput": 4639.82, "total_tokens": 31637632} {"current_steps": 31450, "total_steps": 42420, "loss": 0.0249, "lr": 9.514292175242277e-06, "epoch": 14.827911362564828, "percentage": 74.14, "elapsed_time": "1:53:39", "remaining_time": "0:39:38", "throughput": 4639.82, "total_tokens": 31642304} {"current_steps": 31455, "total_steps": 42420, "loss": 0.2357, "lr": 9.506218425166355e-06, "epoch": 14.83026874115983, "percentage": 74.15, "elapsed_time": "1:53:40", "remaining_time": "0:39:37", "throughput": 4639.83, "total_tokens": 31646720} {"current_steps": 31460, "total_steps": 42420, "loss": 0.0863, "lr": 9.498147297924593e-06, "epoch": 14.832626119754833, "percentage": 74.16, "elapsed_time": "1:53:41", "remaining_time": "0:39:36", "throughput": 4639.82, "total_tokens": 31651200} {"current_steps": 31465, "total_steps": 42420, "loss": 0.1222, "lr": 9.490078794883277e-06, "epoch": 14.834983498349835, "percentage": 74.17, "elapsed_time": "1:53:42", "remaining_time": "0:39:35", "throughput": 4639.85, "total_tokens": 31655776} {"current_steps": 31470, "total_steps": 42420, "loss": 0.0854, "lr": 9.482012917408286e-06, "epoch": 14.837340876944838, "percentage": 74.19, "elapsed_time": "1:53:43", "remaining_time": "0:39:34", "throughput": 4639.89, "total_tokens": 31661408} {"current_steps": 31475, "total_steps": 42420, "loss": 0.2087, "lr": 9.473949666865023e-06, "epoch": 14.83969825553984, "percentage": 74.2, "elapsed_time": "1:53:44", "remaining_time": "0:39:33", "throughput": 4639.95, "total_tokens": 31667584} {"current_steps": 31480, "total_steps": 42420, "loss": 0.07, "lr": 9.465889044618462e-06, "epoch": 14.842055634134843, "percentage": 74.21, "elapsed_time": "1:53:45", "remaining_time": "0:39:32", "throughput": 4639.93, "total_tokens": 31671904} {"current_steps": 31485, "total_steps": 42420, "loss": 0.0571, "lr": 9.457831052033132e-06, "epoch": 14.844413012729845, "percentage": 74.22, "elapsed_time": "1:53:47", "remaining_time": "0:39:31", "throughput": 4639.95, "total_tokens": 31677152} {"current_steps": 31490, "total_steps": 42420, "loss": 0.0404, "lr": 9.449775690473112e-06, "epoch": 14.846770391324847, "percentage": 74.23, "elapsed_time": "1:53:48", "remaining_time": "0:39:30", "throughput": 4639.98, "total_tokens": 31682720} {"current_steps": 31495, "total_steps": 42420, "loss": 0.133, "lr": 9.441722961302039e-06, "epoch": 14.84912776991985, "percentage": 74.25, "elapsed_time": "1:53:49", "remaining_time": "0:39:28", "throughput": 4639.99, "total_tokens": 31687392} {"current_steps": 31500, "total_steps": 42420, "loss": 0.0593, "lr": 9.433672865883106e-06, "epoch": 14.851485148514852, "percentage": 74.26, "elapsed_time": "1:53:50", "remaining_time": "0:39:27", "throughput": 4640.01, "total_tokens": 31691904} {"current_steps": 31505, "total_steps": 42420, "loss": 0.1888, "lr": 9.425625405579055e-06, "epoch": 14.853842527109855, "percentage": 74.27, "elapsed_time": "1:53:51", "remaining_time": "0:39:26", "throughput": 4640.03, "total_tokens": 31696512} {"current_steps": 31510, "total_steps": 42420, "loss": 0.0196, "lr": 9.417580581752194e-06, "epoch": 14.856199905704855, "percentage": 74.28, "elapsed_time": "1:53:52", "remaining_time": "0:39:25", "throughput": 4640.08, "total_tokens": 31703232} {"current_steps": 31515, "total_steps": 42420, "loss": 0.2044, "lr": 9.409538395764358e-06, "epoch": 14.85855728429986, "percentage": 74.29, "elapsed_time": "1:53:53", "remaining_time": "0:39:24", "throughput": 4640.11, "total_tokens": 31708000} {"current_steps": 31520, "total_steps": 42420, "loss": 0.1011, "lr": 9.401498848976962e-06, "epoch": 14.86091466289486, "percentage": 74.3, "elapsed_time": "1:53:54", "remaining_time": "0:39:23", "throughput": 4640.14, "total_tokens": 31713120} {"current_steps": 31525, "total_steps": 42420, "loss": 0.2202, "lr": 9.393461942750961e-06, "epoch": 14.863272041489862, "percentage": 74.32, "elapsed_time": "1:53:55", "remaining_time": "0:39:22", "throughput": 4640.18, "total_tokens": 31718528} {"current_steps": 31530, "total_steps": 42420, "loss": 0.1559, "lr": 9.38542767844687e-06, "epoch": 14.865629420084865, "percentage": 74.33, "elapsed_time": "1:53:56", "remaining_time": "0:39:21", "throughput": 4640.16, "total_tokens": 31723488} {"current_steps": 31535, "total_steps": 42420, "loss": 0.1519, "lr": 9.377396057424751e-06, "epoch": 14.867986798679867, "percentage": 74.34, "elapsed_time": "1:53:57", "remaining_time": "0:39:20", "throughput": 4640.22, "total_tokens": 31729536} {"current_steps": 31540, "total_steps": 42420, "loss": 0.1879, "lr": 9.369367081044226e-06, "epoch": 14.87034417727487, "percentage": 74.35, "elapsed_time": "1:53:58", "remaining_time": "0:39:19", "throughput": 4640.23, "total_tokens": 31733984} {"current_steps": 31545, "total_steps": 42420, "loss": 0.0318, "lr": 9.361340750664458e-06, "epoch": 14.872701555869872, "percentage": 74.36, "elapsed_time": "1:54:00", "remaining_time": "0:39:18", "throughput": 4640.26, "total_tokens": 31739840} {"current_steps": 31550, "total_steps": 42420, "loss": 0.0761, "lr": 9.353317067644182e-06, "epoch": 14.875058934464874, "percentage": 74.38, "elapsed_time": "1:54:01", "remaining_time": "0:39:17", "throughput": 4640.3, "total_tokens": 31745024} {"current_steps": 31555, "total_steps": 42420, "loss": 0.23, "lr": 9.345296033341652e-06, "epoch": 14.877416313059877, "percentage": 74.39, "elapsed_time": "1:54:02", "remaining_time": "0:39:15", "throughput": 4640.32, "total_tokens": 31749536} {"current_steps": 31560, "total_steps": 42420, "loss": 0.0844, "lr": 9.3372776491147e-06, "epoch": 14.87977369165488, "percentage": 74.4, "elapsed_time": "1:54:03", "remaining_time": "0:39:14", "throughput": 4640.35, "total_tokens": 31754528} {"current_steps": 31565, "total_steps": 42420, "loss": 0.1292, "lr": 9.329261916320709e-06, "epoch": 14.882131070249882, "percentage": 74.41, "elapsed_time": "1:54:04", "remaining_time": "0:39:13", "throughput": 4640.39, "total_tokens": 31759168} {"current_steps": 31570, "total_steps": 42420, "loss": 0.0143, "lr": 9.321248836316596e-06, "epoch": 14.884488448844884, "percentage": 74.42, "elapsed_time": "1:54:04", "remaining_time": "0:39:12", "throughput": 4640.36, "total_tokens": 31763200} {"current_steps": 31575, "total_steps": 42420, "loss": 0.068, "lr": 9.313238410458849e-06, "epoch": 14.886845827439886, "percentage": 74.43, "elapsed_time": "1:54:06", "remaining_time": "0:39:11", "throughput": 4640.39, "total_tokens": 31768192} {"current_steps": 31580, "total_steps": 42420, "loss": 0.0436, "lr": 9.30523064010349e-06, "epoch": 14.889203206034889, "percentage": 74.45, "elapsed_time": "1:54:07", "remaining_time": "0:39:10", "throughput": 4640.43, "total_tokens": 31773344} {"current_steps": 31585, "total_steps": 42420, "loss": 0.1456, "lr": 9.297225526606104e-06, "epoch": 14.891560584629891, "percentage": 74.46, "elapsed_time": "1:54:08", "remaining_time": "0:39:09", "throughput": 4640.41, "total_tokens": 31778240} {"current_steps": 31590, "total_steps": 42420, "loss": 0.2107, "lr": 9.289223071321826e-06, "epoch": 14.893917963224894, "percentage": 74.47, "elapsed_time": "1:54:09", "remaining_time": "0:39:08", "throughput": 4640.46, "total_tokens": 31783552} {"current_steps": 31595, "total_steps": 42420, "loss": 0.0949, "lr": 9.281223275605319e-06, "epoch": 14.896275341819896, "percentage": 74.48, "elapsed_time": "1:54:10", "remaining_time": "0:39:07", "throughput": 4640.52, "total_tokens": 31790080} {"current_steps": 31600, "total_steps": 42420, "loss": 0.0486, "lr": 9.273226140810822e-06, "epoch": 14.898632720414899, "percentage": 74.49, "elapsed_time": "1:54:11", "remaining_time": "0:39:06", "throughput": 4640.56, "total_tokens": 31795296} {"current_steps": 31605, "total_steps": 42420, "loss": 0.0907, "lr": 9.265231668292114e-06, "epoch": 14.900990099009901, "percentage": 74.5, "elapsed_time": "1:54:12", "remaining_time": "0:39:04", "throughput": 4640.57, "total_tokens": 31799680} {"current_steps": 31610, "total_steps": 42420, "loss": 0.1464, "lr": 9.257239859402525e-06, "epoch": 14.903347477604903, "percentage": 74.52, "elapsed_time": "1:54:13", "remaining_time": "0:39:03", "throughput": 4640.58, "total_tokens": 31804544} {"current_steps": 31615, "total_steps": 42420, "loss": 0.1831, "lr": 9.24925071549493e-06, "epoch": 14.905704856199906, "percentage": 74.53, "elapsed_time": "1:54:14", "remaining_time": "0:39:02", "throughput": 4640.6, "total_tokens": 31809056} {"current_steps": 31620, "total_steps": 42420, "loss": 0.0597, "lr": 9.241264237921757e-06, "epoch": 14.908062234794908, "percentage": 74.54, "elapsed_time": "1:54:15", "remaining_time": "0:39:01", "throughput": 4640.6, "total_tokens": 31813440} {"current_steps": 31625, "total_steps": 42420, "loss": 0.3281, "lr": 9.23328042803498e-06, "epoch": 14.91041961338991, "percentage": 74.55, "elapsed_time": "1:54:16", "remaining_time": "0:39:00", "throughput": 4640.63, "total_tokens": 31818848} {"current_steps": 31630, "total_steps": 42420, "loss": 0.1235, "lr": 9.22529928718613e-06, "epoch": 14.912776991984913, "percentage": 74.56, "elapsed_time": "1:54:17", "remaining_time": "0:38:59", "throughput": 4640.66, "total_tokens": 31824032} {"current_steps": 31635, "total_steps": 42420, "loss": 0.1096, "lr": 9.217320816726263e-06, "epoch": 14.915134370579915, "percentage": 74.58, "elapsed_time": "1:54:18", "remaining_time": "0:38:58", "throughput": 4640.69, "total_tokens": 31828832} {"current_steps": 31640, "total_steps": 42420, "loss": 0.0977, "lr": 9.209345018006008e-06, "epoch": 14.917491749174918, "percentage": 74.59, "elapsed_time": "1:54:19", "remaining_time": "0:38:57", "throughput": 4640.73, "total_tokens": 31834112} {"current_steps": 31645, "total_steps": 42420, "loss": 0.0794, "lr": 9.201371892375533e-06, "epoch": 14.91984912776992, "percentage": 74.6, "elapsed_time": "1:54:20", "remaining_time": "0:38:56", "throughput": 4640.77, "total_tokens": 31839872} {"current_steps": 31650, "total_steps": 42420, "loss": 0.223, "lr": 9.19340144118455e-06, "epoch": 14.922206506364923, "percentage": 74.61, "elapsed_time": "1:54:21", "remaining_time": "0:38:55", "throughput": 4640.81, "total_tokens": 31845152} {"current_steps": 31655, "total_steps": 42420, "loss": 0.0653, "lr": 9.18543366578232e-06, "epoch": 14.924563884959925, "percentage": 74.62, "elapsed_time": "1:54:22", "remaining_time": "0:38:53", "throughput": 4640.82, "total_tokens": 31849376} {"current_steps": 31660, "total_steps": 42420, "loss": 0.1783, "lr": 9.177468567517656e-06, "epoch": 14.926921263554927, "percentage": 74.63, "elapsed_time": "1:54:23", "remaining_time": "0:38:52", "throughput": 4640.84, "total_tokens": 31854464} {"current_steps": 31665, "total_steps": 42420, "loss": 0.0803, "lr": 9.169506147738913e-06, "epoch": 14.92927864214993, "percentage": 74.65, "elapsed_time": "1:54:24", "remaining_time": "0:38:51", "throughput": 4640.86, "total_tokens": 31858976} {"current_steps": 31670, "total_steps": 42420, "loss": 0.1634, "lr": 9.161546407794e-06, "epoch": 14.931636020744932, "percentage": 74.66, "elapsed_time": "1:54:25", "remaining_time": "0:38:50", "throughput": 4640.87, "total_tokens": 31863616} {"current_steps": 31675, "total_steps": 42420, "loss": 0.2116, "lr": 9.153589349030351e-06, "epoch": 14.933993399339935, "percentage": 74.67, "elapsed_time": "1:54:26", "remaining_time": "0:38:49", "throughput": 4640.88, "total_tokens": 31868288} {"current_steps": 31680, "total_steps": 42420, "loss": 0.0605, "lr": 9.14563497279497e-06, "epoch": 14.936350777934937, "percentage": 74.68, "elapsed_time": "1:54:28", "remaining_time": "0:38:48", "throughput": 4640.93, "total_tokens": 31874016} {"current_steps": 31685, "total_steps": 42420, "loss": 0.1119, "lr": 9.1376832804344e-06, "epoch": 14.93870815652994, "percentage": 74.69, "elapsed_time": "1:54:29", "remaining_time": "0:38:47", "throughput": 4640.96, "total_tokens": 31879072} {"current_steps": 31690, "total_steps": 42420, "loss": 0.0295, "lr": 9.129734273294718e-06, "epoch": 14.941065535124942, "percentage": 74.71, "elapsed_time": "1:54:30", "remaining_time": "0:38:46", "throughput": 4641.01, "total_tokens": 31884576} {"current_steps": 31695, "total_steps": 42420, "loss": 0.067, "lr": 9.121787952721564e-06, "epoch": 14.943422913719944, "percentage": 74.72, "elapsed_time": "1:54:31", "remaining_time": "0:38:45", "throughput": 4641.06, "total_tokens": 31890816} {"current_steps": 31700, "total_steps": 42420, "loss": 0.1276, "lr": 9.113844320060111e-06, "epoch": 14.945780292314947, "percentage": 74.73, "elapsed_time": "1:54:32", "remaining_time": "0:38:44", "throughput": 4641.09, "total_tokens": 31895488} {"current_steps": 31705, "total_steps": 42420, "loss": 0.0904, "lr": 9.10590337665508e-06, "epoch": 14.948137670909949, "percentage": 74.74, "elapsed_time": "1:54:33", "remaining_time": "0:38:43", "throughput": 4641.13, "total_tokens": 31901408} {"current_steps": 31710, "total_steps": 42420, "loss": 0.0873, "lr": 9.097965123850746e-06, "epoch": 14.950495049504951, "percentage": 74.75, "elapsed_time": "1:54:34", "remaining_time": "0:38:41", "throughput": 4641.17, "total_tokens": 31906336} {"current_steps": 31715, "total_steps": 42420, "loss": 0.0766, "lr": 9.090029562990911e-06, "epoch": 14.952852428099952, "percentage": 74.76, "elapsed_time": "1:54:35", "remaining_time": "0:38:40", "throughput": 4641.18, "total_tokens": 31910560} {"current_steps": 31720, "total_steps": 42420, "loss": 0.0709, "lr": 9.082096695418949e-06, "epoch": 14.955209806694956, "percentage": 74.78, "elapsed_time": "1:54:36", "remaining_time": "0:38:39", "throughput": 4641.21, "total_tokens": 31915200} {"current_steps": 31725, "total_steps": 42420, "loss": 0.1328, "lr": 9.074166522477734e-06, "epoch": 14.957567185289957, "percentage": 74.79, "elapsed_time": "1:54:37", "remaining_time": "0:38:38", "throughput": 4641.25, "total_tokens": 31920960} {"current_steps": 31730, "total_steps": 42420, "loss": 0.164, "lr": 9.066239045509723e-06, "epoch": 14.95992456388496, "percentage": 74.8, "elapsed_time": "1:54:38", "remaining_time": "0:38:37", "throughput": 4641.29, "total_tokens": 31926080} {"current_steps": 31735, "total_steps": 42420, "loss": 0.11, "lr": 9.058314265856899e-06, "epoch": 14.962281942479962, "percentage": 74.81, "elapsed_time": "1:54:39", "remaining_time": "0:38:36", "throughput": 4641.32, "total_tokens": 31932160} {"current_steps": 31740, "total_steps": 42420, "loss": 0.1241, "lr": 9.050392184860796e-06, "epoch": 14.964639321074964, "percentage": 74.82, "elapsed_time": "1:54:41", "remaining_time": "0:38:35", "throughput": 4641.37, "total_tokens": 31937536} {"current_steps": 31745, "total_steps": 42420, "loss": 0.0586, "lr": 9.042472803862489e-06, "epoch": 14.966996699669966, "percentage": 74.83, "elapsed_time": "1:54:42", "remaining_time": "0:38:34", "throughput": 4641.42, "total_tokens": 31942976} {"current_steps": 31750, "total_steps": 42420, "loss": 0.3403, "lr": 9.034556124202592e-06, "epoch": 14.969354078264969, "percentage": 74.85, "elapsed_time": "1:54:43", "remaining_time": "0:38:33", "throughput": 4641.44, "total_tokens": 31947584} {"current_steps": 31755, "total_steps": 42420, "loss": 0.0467, "lr": 9.026642147221264e-06, "epoch": 14.971711456859971, "percentage": 74.86, "elapsed_time": "1:54:44", "remaining_time": "0:38:32", "throughput": 4641.44, "total_tokens": 31952096} {"current_steps": 31760, "total_steps": 42420, "loss": 0.2326, "lr": 9.018730874258219e-06, "epoch": 14.974068835454974, "percentage": 74.87, "elapsed_time": "1:54:45", "remaining_time": "0:38:30", "throughput": 4641.48, "total_tokens": 31957504} {"current_steps": 31765, "total_steps": 42420, "loss": 0.1468, "lr": 9.01082230665268e-06, "epoch": 14.976426214049976, "percentage": 74.88, "elapsed_time": "1:54:46", "remaining_time": "0:38:29", "throughput": 4641.5, "total_tokens": 31962112} {"current_steps": 31770, "total_steps": 42420, "loss": 0.0775, "lr": 9.002916445743445e-06, "epoch": 14.978783592644978, "percentage": 74.89, "elapsed_time": "1:54:47", "remaining_time": "0:38:28", "throughput": 4641.52, "total_tokens": 31966880} {"current_steps": 31775, "total_steps": 42420, "loss": 0.1818, "lr": 8.99501329286884e-06, "epoch": 14.98114097123998, "percentage": 74.91, "elapsed_time": "1:54:48", "remaining_time": "0:38:27", "throughput": 4641.55, "total_tokens": 31971488} {"current_steps": 31780, "total_steps": 42420, "loss": 0.1481, "lr": 8.987112849366735e-06, "epoch": 14.983498349834983, "percentage": 74.92, "elapsed_time": "1:54:49", "remaining_time": "0:38:26", "throughput": 4641.59, "total_tokens": 31977152} {"current_steps": 31785, "total_steps": 42420, "loss": 0.1713, "lr": 8.979215116574544e-06, "epoch": 14.985855728429986, "percentage": 74.93, "elapsed_time": "1:54:50", "remaining_time": "0:38:25", "throughput": 4641.6, "total_tokens": 31981568} {"current_steps": 31790, "total_steps": 42420, "loss": 0.1665, "lr": 8.971320095829214e-06, "epoch": 14.988213107024988, "percentage": 74.94, "elapsed_time": "1:54:51", "remaining_time": "0:38:24", "throughput": 4641.63, "total_tokens": 31987488} {"current_steps": 31795, "total_steps": 42420, "loss": 0.13, "lr": 8.963427788467241e-06, "epoch": 14.99057048561999, "percentage": 74.95, "elapsed_time": "1:54:52", "remaining_time": "0:38:23", "throughput": 4641.68, "total_tokens": 31992672} {"current_steps": 31800, "total_steps": 42420, "loss": 0.0661, "lr": 8.955538195824664e-06, "epoch": 14.992927864214993, "percentage": 74.96, "elapsed_time": "1:54:53", "remaining_time": "0:38:22", "throughput": 4641.7, "total_tokens": 31997472} {"current_steps": 31805, "total_steps": 42420, "loss": 0.1253, "lr": 8.947651319237046e-06, "epoch": 14.995285242809995, "percentage": 74.98, "elapsed_time": "1:54:54", "remaining_time": "0:38:21", "throughput": 4641.76, "total_tokens": 32003456} {"current_steps": 31810, "total_steps": 42420, "loss": 0.1677, "lr": 8.939767160039503e-06, "epoch": 14.997642621404998, "percentage": 74.99, "elapsed_time": "1:54:55", "remaining_time": "0:38:20", "throughput": 4641.75, "total_tokens": 32008512} {"current_steps": 31815, "total_steps": 42420, "loss": 0.0246, "lr": 8.931885719566697e-06, "epoch": 15.0, "percentage": 75.0, "elapsed_time": "1:54:56", "remaining_time": "0:38:18", "throughput": 4641.7, "total_tokens": 32013760} {"current_steps": 31815, "total_steps": 42420, "eval_loss": 0.153660848736763, "epoch": 15.0, "percentage": 75.0, "elapsed_time": "1:55:12", "remaining_time": "0:38:24", "throughput": 4631.53, "total_tokens": 32013760} {"current_steps": 31820, "total_steps": 42420, "loss": 0.0704, "lr": 8.924006999152815e-06, "epoch": 15.002357378595002, "percentage": 75.01, "elapsed_time": "1:55:14", "remaining_time": "0:38:23", "throughput": 4630.52, "total_tokens": 32018688} {"current_steps": 31825, "total_steps": 42420, "loss": 0.1114, "lr": 8.916131000131592e-06, "epoch": 15.004714757190005, "percentage": 75.02, "elapsed_time": "1:55:16", "remaining_time": "0:38:22", "throughput": 4630.57, "total_tokens": 32025088} {"current_steps": 31830, "total_steps": 42420, "loss": 0.014, "lr": 8.908257723836303e-06, "epoch": 15.007072135785007, "percentage": 75.04, "elapsed_time": "1:55:16", "remaining_time": "0:38:21", "throughput": 4630.56, "total_tokens": 32029184} {"current_steps": 31835, "total_steps": 42420, "loss": 0.1588, "lr": 8.900387171599759e-06, "epoch": 15.00942951438001, "percentage": 75.05, "elapsed_time": "1:55:17", "remaining_time": "0:38:20", "throughput": 4630.58, "total_tokens": 32033920} {"current_steps": 31840, "total_steps": 42420, "loss": 0.2232, "lr": 8.89251934475432e-06, "epoch": 15.011786892975012, "percentage": 75.06, "elapsed_time": "1:55:19", "remaining_time": "0:38:19", "throughput": 4630.6, "total_tokens": 32039232} {"current_steps": 31845, "total_steps": 42420, "loss": 0.0256, "lr": 8.884654244631857e-06, "epoch": 15.014144271570014, "percentage": 75.07, "elapsed_time": "1:55:20", "remaining_time": "0:38:17", "throughput": 4630.58, "total_tokens": 32043808} {"current_steps": 31850, "total_steps": 42420, "loss": 0.0874, "lr": 8.876791872563808e-06, "epoch": 15.016501650165017, "percentage": 75.08, "elapsed_time": "1:55:21", "remaining_time": "0:38:16", "throughput": 4630.6, "total_tokens": 32048768} {"current_steps": 31855, "total_steps": 42420, "loss": 0.058, "lr": 8.868932229881142e-06, "epoch": 15.01885902876002, "percentage": 75.09, "elapsed_time": "1:55:22", "remaining_time": "0:38:15", "throughput": 4630.63, "total_tokens": 32053824} {"current_steps": 31860, "total_steps": 42420, "loss": 0.1313, "lr": 8.861075317914356e-06, "epoch": 15.021216407355022, "percentage": 75.11, "elapsed_time": "1:55:23", "remaining_time": "0:38:14", "throughput": 4630.68, "total_tokens": 32059584} {"current_steps": 31865, "total_steps": 42420, "loss": 0.0827, "lr": 8.853221137993494e-06, "epoch": 15.023573785950024, "percentage": 75.12, "elapsed_time": "1:55:24", "remaining_time": "0:38:13", "throughput": 4630.64, "total_tokens": 32063680} {"current_steps": 31870, "total_steps": 42420, "loss": 0.0654, "lr": 8.845369691448138e-06, "epoch": 15.025931164545026, "percentage": 75.13, "elapsed_time": "1:55:25", "remaining_time": "0:38:12", "throughput": 4630.65, "total_tokens": 32068416} {"current_steps": 31875, "total_steps": 42420, "loss": 0.0661, "lr": 8.837520979607403e-06, "epoch": 15.028288543140029, "percentage": 75.14, "elapsed_time": "1:55:26", "remaining_time": "0:38:11", "throughput": 4630.66, "total_tokens": 32072736} {"current_steps": 31880, "total_steps": 42420, "loss": 0.0145, "lr": 8.829675003799954e-06, "epoch": 15.030645921735031, "percentage": 75.15, "elapsed_time": "1:55:27", "remaining_time": "0:38:10", "throughput": 4630.66, "total_tokens": 32077088} {"current_steps": 31885, "total_steps": 42420, "loss": 0.2106, "lr": 8.821831765353957e-06, "epoch": 15.033003300330034, "percentage": 75.17, "elapsed_time": "1:55:28", "remaining_time": "0:38:09", "throughput": 4630.72, "total_tokens": 32083392} {"current_steps": 31890, "total_steps": 42420, "loss": 0.1773, "lr": 8.813991265597158e-06, "epoch": 15.035360678925036, "percentage": 75.18, "elapsed_time": "1:55:29", "remaining_time": "0:38:08", "throughput": 4630.76, "total_tokens": 32089312} {"current_steps": 31895, "total_steps": 42420, "loss": 0.2276, "lr": 8.806153505856813e-06, "epoch": 15.037718057520038, "percentage": 75.19, "elapsed_time": "1:55:30", "remaining_time": "0:38:07", "throughput": 4630.78, "total_tokens": 32094496} {"current_steps": 31900, "total_steps": 42420, "loss": 0.0519, "lr": 8.79831848745972e-06, "epoch": 15.04007543611504, "percentage": 75.2, "elapsed_time": "1:55:31", "remaining_time": "0:38:05", "throughput": 4630.75, "total_tokens": 32098464} {"current_steps": 31905, "total_steps": 42420, "loss": 0.1716, "lr": 8.790486211732221e-06, "epoch": 15.042432814710043, "percentage": 75.21, "elapsed_time": "1:55:32", "remaining_time": "0:38:04", "throughput": 4630.78, "total_tokens": 32103168} {"current_steps": 31910, "total_steps": 42420, "loss": 0.1739, "lr": 8.782656680000192e-06, "epoch": 15.044790193305046, "percentage": 75.22, "elapsed_time": "1:55:33", "remaining_time": "0:38:03", "throughput": 4630.75, "total_tokens": 32107360} {"current_steps": 31915, "total_steps": 42420, "loss": 0.098, "lr": 8.774829893589026e-06, "epoch": 15.047147571900048, "percentage": 75.24, "elapsed_time": "1:55:34", "remaining_time": "0:38:02", "throughput": 4630.73, "total_tokens": 32111648} {"current_steps": 31920, "total_steps": 42420, "loss": 0.1423, "lr": 8.767005853823671e-06, "epoch": 15.049504950495049, "percentage": 75.25, "elapsed_time": "1:55:35", "remaining_time": "0:38:01", "throughput": 4630.72, "total_tokens": 32115648} {"current_steps": 31925, "total_steps": 42420, "loss": 0.1309, "lr": 8.759184562028602e-06, "epoch": 15.051862329090051, "percentage": 75.26, "elapsed_time": "1:55:36", "remaining_time": "0:38:00", "throughput": 4630.74, "total_tokens": 32120672} {"current_steps": 31930, "total_steps": 42420, "loss": 0.1759, "lr": 8.751366019527842e-06, "epoch": 15.054219707685053, "percentage": 75.27, "elapsed_time": "1:55:37", "remaining_time": "0:37:59", "throughput": 4630.76, "total_tokens": 32125536} {"current_steps": 31935, "total_steps": 42420, "loss": 0.0711, "lr": 8.743550227644923e-06, "epoch": 15.056577086280056, "percentage": 75.28, "elapsed_time": "1:55:38", "remaining_time": "0:37:58", "throughput": 4630.79, "total_tokens": 32131104} {"current_steps": 31940, "total_steps": 42420, "loss": 0.0172, "lr": 8.735737187702931e-06, "epoch": 15.058934464875058, "percentage": 75.29, "elapsed_time": "1:55:39", "remaining_time": "0:37:57", "throughput": 4630.82, "total_tokens": 32136256} {"current_steps": 31945, "total_steps": 42420, "loss": 0.0865, "lr": 8.72792690102448e-06, "epoch": 15.06129184347006, "percentage": 75.31, "elapsed_time": "1:55:40", "remaining_time": "0:37:55", "throughput": 4630.82, "total_tokens": 32141024} {"current_steps": 31950, "total_steps": 42420, "loss": 0.0941, "lr": 8.720119368931722e-06, "epoch": 15.063649222065063, "percentage": 75.32, "elapsed_time": "1:55:41", "remaining_time": "0:37:54", "throughput": 4630.84, "total_tokens": 32146336} {"current_steps": 31955, "total_steps": 42420, "loss": 0.0613, "lr": 8.712314592746338e-06, "epoch": 15.066006600660065, "percentage": 75.33, "elapsed_time": "1:55:42", "remaining_time": "0:37:53", "throughput": 4630.87, "total_tokens": 32151040} {"current_steps": 31960, "total_steps": 42420, "loss": 0.0623, "lr": 8.704512573789545e-06, "epoch": 15.068363979255068, "percentage": 75.34, "elapsed_time": "1:55:43", "remaining_time": "0:37:52", "throughput": 4630.87, "total_tokens": 32155328} {"current_steps": 31965, "total_steps": 42420, "loss": 0.1134, "lr": 8.696713313382089e-06, "epoch": 15.07072135785007, "percentage": 75.35, "elapsed_time": "1:55:44", "remaining_time": "0:37:51", "throughput": 4630.91, "total_tokens": 32160544} {"current_steps": 31970, "total_steps": 42420, "loss": 0.1052, "lr": 8.688916812844264e-06, "epoch": 15.073078736445073, "percentage": 75.37, "elapsed_time": "1:55:45", "remaining_time": "0:37:50", "throughput": 4630.91, "total_tokens": 32164608} {"current_steps": 31975, "total_steps": 42420, "loss": 0.0937, "lr": 8.68112307349587e-06, "epoch": 15.075436115040075, "percentage": 75.38, "elapsed_time": "1:55:46", "remaining_time": "0:37:49", "throughput": 4630.93, "total_tokens": 32170208} {"current_steps": 31980, "total_steps": 42420, "loss": 0.02, "lr": 8.673332096656259e-06, "epoch": 15.077793493635077, "percentage": 75.39, "elapsed_time": "1:55:47", "remaining_time": "0:37:48", "throughput": 4630.97, "total_tokens": 32175200} {"current_steps": 31985, "total_steps": 42420, "loss": 0.0405, "lr": 8.665543883644315e-06, "epoch": 15.08015087223008, "percentage": 75.4, "elapsed_time": "1:55:48", "remaining_time": "0:37:47", "throughput": 4630.98, "total_tokens": 32179776} {"current_steps": 31990, "total_steps": 42420, "loss": 0.1371, "lr": 8.657758435778447e-06, "epoch": 15.082508250825082, "percentage": 75.41, "elapsed_time": "1:55:49", "remaining_time": "0:37:45", "throughput": 4631.0, "total_tokens": 32184640} {"current_steps": 31995, "total_steps": 42420, "loss": 0.0648, "lr": 8.6499757543766e-06, "epoch": 15.084865629420085, "percentage": 75.42, "elapsed_time": "1:55:51", "remaining_time": "0:37:44", "throughput": 4631.05, "total_tokens": 32190592} {"current_steps": 32000, "total_steps": 42420, "loss": 0.0802, "lr": 8.642195840756248e-06, "epoch": 15.087223008015087, "percentage": 75.44, "elapsed_time": "1:55:52", "remaining_time": "0:37:43", "throughput": 4631.06, "total_tokens": 32195296} {"current_steps": 32005, "total_steps": 42420, "loss": 0.086, "lr": 8.634418696234404e-06, "epoch": 15.08958038661009, "percentage": 75.45, "elapsed_time": "1:55:53", "remaining_time": "0:37:42", "throughput": 4631.09, "total_tokens": 32200896} {"current_steps": 32010, "total_steps": 42420, "loss": 0.2447, "lr": 8.62664432212761e-06, "epoch": 15.091937765205092, "percentage": 75.46, "elapsed_time": "1:55:54", "remaining_time": "0:37:41", "throughput": 4631.14, "total_tokens": 32207904} {"current_steps": 32015, "total_steps": 42420, "loss": 0.0892, "lr": 8.61887271975192e-06, "epoch": 15.094295143800094, "percentage": 75.47, "elapsed_time": "1:55:55", "remaining_time": "0:37:40", "throughput": 4631.18, "total_tokens": 32213504} {"current_steps": 32020, "total_steps": 42420, "loss": 0.1248, "lr": 8.611103890422941e-06, "epoch": 15.096652522395097, "percentage": 75.48, "elapsed_time": "1:55:56", "remaining_time": "0:37:39", "throughput": 4631.19, "total_tokens": 32218976} {"current_steps": 32025, "total_steps": 42420, "loss": 0.0618, "lr": 8.60333783545581e-06, "epoch": 15.099009900990099, "percentage": 75.5, "elapsed_time": "1:55:57", "remaining_time": "0:37:38", "throughput": 4631.16, "total_tokens": 32222816} {"current_steps": 32030, "total_steps": 42420, "loss": 0.1798, "lr": 8.59557455616518e-06, "epoch": 15.101367279585101, "percentage": 75.51, "elapsed_time": "1:55:59", "remaining_time": "0:37:37", "throughput": 4631.23, "total_tokens": 32229632} {"current_steps": 32035, "total_steps": 42420, "loss": 0.0519, "lr": 8.58781405386525e-06, "epoch": 15.103724658180104, "percentage": 75.52, "elapsed_time": "1:56:00", "remaining_time": "0:37:36", "throughput": 4631.25, "total_tokens": 32234656} {"current_steps": 32040, "total_steps": 42420, "loss": 0.0846, "lr": 8.580056329869735e-06, "epoch": 15.106082036775106, "percentage": 75.53, "elapsed_time": "1:56:01", "remaining_time": "0:37:35", "throughput": 4631.27, "total_tokens": 32240416} {"current_steps": 32045, "total_steps": 42420, "loss": 0.1798, "lr": 8.572301385491891e-06, "epoch": 15.108439415370109, "percentage": 75.54, "elapsed_time": "1:56:02", "remaining_time": "0:37:34", "throughput": 4631.29, "total_tokens": 32244672} {"current_steps": 32050, "total_steps": 42420, "loss": 0.2242, "lr": 8.564549222044501e-06, "epoch": 15.110796793965111, "percentage": 75.55, "elapsed_time": "1:56:03", "remaining_time": "0:37:33", "throughput": 4631.33, "total_tokens": 32250624} {"current_steps": 32055, "total_steps": 42420, "loss": 0.1073, "lr": 8.556799840839864e-06, "epoch": 15.113154172560114, "percentage": 75.57, "elapsed_time": "1:56:04", "remaining_time": "0:37:32", "throughput": 4631.36, "total_tokens": 32255968} {"current_steps": 32060, "total_steps": 42420, "loss": 0.0423, "lr": 8.549053243189823e-06, "epoch": 15.115511551155116, "percentage": 75.58, "elapsed_time": "1:56:05", "remaining_time": "0:37:30", "throughput": 4631.39, "total_tokens": 32261248} {"current_steps": 32065, "total_steps": 42420, "loss": 0.0498, "lr": 8.541309430405747e-06, "epoch": 15.117868929750118, "percentage": 75.59, "elapsed_time": "1:56:06", "remaining_time": "0:37:29", "throughput": 4631.43, "total_tokens": 32266560} {"current_steps": 32070, "total_steps": 42420, "loss": 0.0387, "lr": 8.53356840379853e-06, "epoch": 15.12022630834512, "percentage": 75.6, "elapsed_time": "1:56:07", "remaining_time": "0:37:28", "throughput": 4631.45, "total_tokens": 32271328} {"current_steps": 32075, "total_steps": 42420, "loss": 0.035, "lr": 8.525830164678603e-06, "epoch": 15.122583686940123, "percentage": 75.61, "elapsed_time": "1:56:08", "remaining_time": "0:37:27", "throughput": 4631.46, "total_tokens": 32275616} {"current_steps": 32080, "total_steps": 42420, "loss": 0.1161, "lr": 8.51809471435591e-06, "epoch": 15.124941065535126, "percentage": 75.62, "elapsed_time": "1:56:09", "remaining_time": "0:37:26", "throughput": 4631.48, "total_tokens": 32280768} {"current_steps": 32085, "total_steps": 42420, "loss": 0.1073, "lr": 8.510362054139937e-06, "epoch": 15.127298444130128, "percentage": 75.64, "elapsed_time": "1:56:10", "remaining_time": "0:37:25", "throughput": 4631.52, "total_tokens": 32286272} {"current_steps": 32090, "total_steps": 42420, "loss": 0.1135, "lr": 8.502632185339696e-06, "epoch": 15.12965582272513, "percentage": 75.65, "elapsed_time": "1:56:12", "remaining_time": "0:37:24", "throughput": 4631.56, "total_tokens": 32292832} {"current_steps": 32095, "total_steps": 42420, "loss": 0.0509, "lr": 8.494905109263709e-06, "epoch": 15.132013201320133, "percentage": 75.66, "elapsed_time": "1:56:13", "remaining_time": "0:37:23", "throughput": 4631.58, "total_tokens": 32298592} {"current_steps": 32100, "total_steps": 42420, "loss": 0.0668, "lr": 8.487180827220045e-06, "epoch": 15.134370579915135, "percentage": 75.67, "elapsed_time": "1:56:14", "remaining_time": "0:37:22", "throughput": 4631.61, "total_tokens": 32304032} {"current_steps": 32105, "total_steps": 42420, "loss": 0.1326, "lr": 8.4794593405163e-06, "epoch": 15.136727958510138, "percentage": 75.68, "elapsed_time": "1:56:15", "remaining_time": "0:37:21", "throughput": 4631.64, "total_tokens": 32309216} {"current_steps": 32110, "total_steps": 42420, "loss": 0.0885, "lr": 8.47174065045958e-06, "epoch": 15.13908533710514, "percentage": 75.7, "elapsed_time": "1:56:16", "remaining_time": "0:37:20", "throughput": 4631.63, "total_tokens": 32313312} {"current_steps": 32115, "total_steps": 42420, "loss": 0.1648, "lr": 8.464024758356539e-06, "epoch": 15.14144271570014, "percentage": 75.71, "elapsed_time": "1:56:17", "remaining_time": "0:37:18", "throughput": 4631.66, "total_tokens": 32318048} {"current_steps": 32120, "total_steps": 42420, "loss": 0.081, "lr": 8.456311665513338e-06, "epoch": 15.143800094295143, "percentage": 75.72, "elapsed_time": "1:56:18", "remaining_time": "0:37:17", "throughput": 4631.67, "total_tokens": 32322208} {"current_steps": 32125, "total_steps": 42420, "loss": 0.2181, "lr": 8.448601373235678e-06, "epoch": 15.146157472890145, "percentage": 75.73, "elapsed_time": "1:56:19", "remaining_time": "0:37:16", "throughput": 4631.69, "total_tokens": 32326944} {"current_steps": 32130, "total_steps": 42420, "loss": 0.2167, "lr": 8.440893882828788e-06, "epoch": 15.148514851485148, "percentage": 75.74, "elapsed_time": "1:56:20", "remaining_time": "0:37:15", "throughput": 4631.69, "total_tokens": 32331168} {"current_steps": 32135, "total_steps": 42420, "loss": 0.0832, "lr": 8.433189195597396e-06, "epoch": 15.15087223008015, "percentage": 75.75, "elapsed_time": "1:56:21", "remaining_time": "0:37:14", "throughput": 4631.75, "total_tokens": 32337568} {"current_steps": 32140, "total_steps": 42420, "loss": 0.0859, "lr": 8.425487312845792e-06, "epoch": 15.153229608675153, "percentage": 75.77, "elapsed_time": "1:56:22", "remaining_time": "0:37:13", "throughput": 4631.77, "total_tokens": 32342176} {"current_steps": 32145, "total_steps": 42420, "loss": 0.0515, "lr": 8.41778823587776e-06, "epoch": 15.155586987270155, "percentage": 75.78, "elapsed_time": "1:56:23", "remaining_time": "0:37:12", "throughput": 4631.8, "total_tokens": 32347072} {"current_steps": 32150, "total_steps": 42420, "loss": 0.05, "lr": 8.41009196599663e-06, "epoch": 15.157944365865157, "percentage": 75.79, "elapsed_time": "1:56:24", "remaining_time": "0:37:11", "throughput": 4631.8, "total_tokens": 32351392} {"current_steps": 32155, "total_steps": 42420, "loss": 0.0473, "lr": 8.402398504505252e-06, "epoch": 15.16030174446016, "percentage": 75.8, "elapsed_time": "1:56:25", "remaining_time": "0:37:10", "throughput": 4631.83, "total_tokens": 32356160} {"current_steps": 32160, "total_steps": 42420, "loss": 0.0974, "lr": 8.394707852705991e-06, "epoch": 15.162659123055162, "percentage": 75.81, "elapsed_time": "1:56:26", "remaining_time": "0:37:08", "throughput": 4631.84, "total_tokens": 32360896} {"current_steps": 32165, "total_steps": 42420, "loss": 0.0648, "lr": 8.387020011900751e-06, "epoch": 15.165016501650165, "percentage": 75.83, "elapsed_time": "1:56:27", "remaining_time": "0:37:07", "throughput": 4631.84, "total_tokens": 32365152} {"current_steps": 32170, "total_steps": 42420, "loss": 0.0177, "lr": 8.379334983390951e-06, "epoch": 15.167373880245167, "percentage": 75.84, "elapsed_time": "1:56:28", "remaining_time": "0:37:06", "throughput": 4631.88, "total_tokens": 32370848} {"current_steps": 32175, "total_steps": 42420, "loss": 0.0409, "lr": 8.371652768477536e-06, "epoch": 15.16973125884017, "percentage": 75.85, "elapsed_time": "1:56:29", "remaining_time": "0:37:05", "throughput": 4631.92, "total_tokens": 32376672} {"current_steps": 32180, "total_steps": 42420, "loss": 0.019, "lr": 8.363973368460981e-06, "epoch": 15.172088637435172, "percentage": 75.86, "elapsed_time": "1:56:30", "remaining_time": "0:37:04", "throughput": 4631.93, "total_tokens": 32381120} {"current_steps": 32185, "total_steps": 42420, "loss": 0.1008, "lr": 8.356296784641263e-06, "epoch": 15.174446016030174, "percentage": 75.87, "elapsed_time": "1:56:32", "remaining_time": "0:37:03", "throughput": 4632.0, "total_tokens": 32387520} {"current_steps": 32190, "total_steps": 42420, "loss": 0.1689, "lr": 8.348623018317905e-06, "epoch": 15.176803394625177, "percentage": 75.88, "elapsed_time": "1:56:33", "remaining_time": "0:37:02", "throughput": 4632.04, "total_tokens": 32392608} {"current_steps": 32195, "total_steps": 42420, "loss": 0.1095, "lr": 8.340952070789946e-06, "epoch": 15.179160773220179, "percentage": 75.9, "elapsed_time": "1:56:34", "remaining_time": "0:37:01", "throughput": 4632.05, "total_tokens": 32397056} {"current_steps": 32200, "total_steps": 42420, "loss": 0.1001, "lr": 8.333283943355945e-06, "epoch": 15.181518151815181, "percentage": 75.91, "elapsed_time": "1:56:35", "remaining_time": "0:37:00", "throughput": 4632.08, "total_tokens": 32402048} {"current_steps": 32205, "total_steps": 42420, "loss": 0.0975, "lr": 8.325618637313993e-06, "epoch": 15.183875530410184, "percentage": 75.92, "elapsed_time": "1:56:36", "remaining_time": "0:36:59", "throughput": 4632.14, "total_tokens": 32409440} {"current_steps": 32210, "total_steps": 42420, "loss": 0.1265, "lr": 8.317956153961688e-06, "epoch": 15.186232909005186, "percentage": 75.93, "elapsed_time": "1:56:37", "remaining_time": "0:36:58", "throughput": 4632.17, "total_tokens": 32414944} {"current_steps": 32215, "total_steps": 42420, "loss": 0.0212, "lr": 8.31029649459616e-06, "epoch": 15.188590287600189, "percentage": 75.94, "elapsed_time": "1:56:38", "remaining_time": "0:36:57", "throughput": 4632.22, "total_tokens": 32420544} {"current_steps": 32220, "total_steps": 42420, "loss": 0.0149, "lr": 8.302639660514069e-06, "epoch": 15.190947666195191, "percentage": 75.95, "elapsed_time": "1:56:40", "remaining_time": "0:36:56", "throughput": 4632.26, "total_tokens": 32425984} {"current_steps": 32225, "total_steps": 42420, "loss": 0.0241, "lr": 8.29498565301157e-06, "epoch": 15.193305044790193, "percentage": 75.97, "elapsed_time": "1:56:41", "remaining_time": "0:36:54", "throughput": 4632.3, "total_tokens": 32431680} {"current_steps": 32230, "total_steps": 42420, "loss": 0.1244, "lr": 8.287334473384367e-06, "epoch": 15.195662423385196, "percentage": 75.98, "elapsed_time": "1:56:42", "remaining_time": "0:36:53", "throughput": 4632.33, "total_tokens": 32436448} {"current_steps": 32235, "total_steps": 42420, "loss": 0.0934, "lr": 8.27968612292767e-06, "epoch": 15.198019801980198, "percentage": 75.99, "elapsed_time": "1:56:43", "remaining_time": "0:36:52", "throughput": 4632.39, "total_tokens": 32442976} {"current_steps": 32240, "total_steps": 42420, "loss": 0.0682, "lr": 8.272040602936218e-06, "epoch": 15.2003771805752, "percentage": 76.0, "elapsed_time": "1:56:44", "remaining_time": "0:36:51", "throughput": 4632.41, "total_tokens": 32447840} {"current_steps": 32245, "total_steps": 42420, "loss": 0.2543, "lr": 8.26439791470427e-06, "epoch": 15.202734559170203, "percentage": 76.01, "elapsed_time": "1:56:45", "remaining_time": "0:36:50", "throughput": 4632.44, "total_tokens": 32452352} {"current_steps": 32250, "total_steps": 42420, "loss": 0.018, "lr": 8.256758059525598e-06, "epoch": 15.205091937765205, "percentage": 76.03, "elapsed_time": "1:56:46", "remaining_time": "0:36:49", "throughput": 4632.43, "total_tokens": 32456448} {"current_steps": 32255, "total_steps": 42420, "loss": 0.0592, "lr": 8.249121038693505e-06, "epoch": 15.207449316360208, "percentage": 76.04, "elapsed_time": "1:56:47", "remaining_time": "0:36:48", "throughput": 4632.42, "total_tokens": 32460544} {"current_steps": 32260, "total_steps": 42420, "loss": 0.0376, "lr": 8.241486853500814e-06, "epoch": 15.20980669495521, "percentage": 76.05, "elapsed_time": "1:56:48", "remaining_time": "0:36:47", "throughput": 4632.46, "total_tokens": 32465728} {"current_steps": 32265, "total_steps": 42420, "loss": 0.1425, "lr": 8.233855505239843e-06, "epoch": 15.212164073550213, "percentage": 76.06, "elapsed_time": "1:56:49", "remaining_time": "0:36:46", "throughput": 4632.47, "total_tokens": 32471200} {"current_steps": 32270, "total_steps": 42420, "loss": 0.1038, "lr": 8.226226995202466e-06, "epoch": 15.214521452145215, "percentage": 76.07, "elapsed_time": "1:56:50", "remaining_time": "0:36:45", "throughput": 4632.49, "total_tokens": 32476000} {"current_steps": 32275, "total_steps": 42420, "loss": 0.0984, "lr": 8.218601324680055e-06, "epoch": 15.216878830740217, "percentage": 76.08, "elapsed_time": "1:56:51", "remaining_time": "0:36:43", "throughput": 4632.53, "total_tokens": 32481056} {"current_steps": 32280, "total_steps": 42420, "loss": 0.0558, "lr": 8.21097849496351e-06, "epoch": 15.21923620933522, "percentage": 76.1, "elapsed_time": "1:56:52", "remaining_time": "0:36:42", "throughput": 4632.54, "total_tokens": 32486240} {"current_steps": 32285, "total_steps": 42420, "loss": 0.1523, "lr": 8.203358507343242e-06, "epoch": 15.221593587930222, "percentage": 76.11, "elapsed_time": "1:56:53", "remaining_time": "0:36:41", "throughput": 4632.54, "total_tokens": 32491072} {"current_steps": 32290, "total_steps": 42420, "loss": 0.0548, "lr": 8.195741363109188e-06, "epoch": 15.223950966525225, "percentage": 76.12, "elapsed_time": "1:56:54", "remaining_time": "0:36:40", "throughput": 4632.53, "total_tokens": 32495232} {"current_steps": 32295, "total_steps": 42420, "loss": 0.2658, "lr": 8.188127063550801e-06, "epoch": 15.226308345120227, "percentage": 76.13, "elapsed_time": "1:56:55", "remaining_time": "0:36:39", "throughput": 4632.56, "total_tokens": 32499936} {"current_steps": 32300, "total_steps": 42420, "loss": 0.0368, "lr": 8.180515609957062e-06, "epoch": 15.22866572371523, "percentage": 76.14, "elapsed_time": "1:56:56", "remaining_time": "0:36:38", "throughput": 4632.6, "total_tokens": 32504768} {"current_steps": 32305, "total_steps": 42420, "loss": 0.1082, "lr": 8.172907003616445e-06, "epoch": 15.231023102310232, "percentage": 76.16, "elapsed_time": "1:56:57", "remaining_time": "0:36:37", "throughput": 4632.63, "total_tokens": 32510208} {"current_steps": 32310, "total_steps": 42420, "loss": 0.1645, "lr": 8.165301245816961e-06, "epoch": 15.233380480905234, "percentage": 76.17, "elapsed_time": "1:56:58", "remaining_time": "0:36:36", "throughput": 4632.67, "total_tokens": 32515712} {"current_steps": 32315, "total_steps": 42420, "loss": 0.1203, "lr": 8.157698337846143e-06, "epoch": 15.235737859500237, "percentage": 76.18, "elapsed_time": "1:56:59", "remaining_time": "0:36:35", "throughput": 4632.68, "total_tokens": 32520096} {"current_steps": 32320, "total_steps": 42420, "loss": 0.0499, "lr": 8.150098280991028e-06, "epoch": 15.238095238095237, "percentage": 76.19, "elapsed_time": "1:57:00", "remaining_time": "0:36:33", "throughput": 4632.69, "total_tokens": 32524512} {"current_steps": 32325, "total_steps": 42420, "loss": 0.0184, "lr": 8.142501076538178e-06, "epoch": 15.24045261669024, "percentage": 76.2, "elapsed_time": "1:57:01", "remaining_time": "0:36:32", "throughput": 4632.73, "total_tokens": 32529408} {"current_steps": 32330, "total_steps": 42420, "loss": 0.0584, "lr": 8.134906725773674e-06, "epoch": 15.242809995285242, "percentage": 76.21, "elapsed_time": "1:57:02", "remaining_time": "0:36:31", "throughput": 4632.76, "total_tokens": 32534016} {"current_steps": 32335, "total_steps": 42420, "loss": 0.1195, "lr": 8.127315229983106e-06, "epoch": 15.245167373880244, "percentage": 76.23, "elapsed_time": "1:57:03", "remaining_time": "0:36:30", "throughput": 4632.78, "total_tokens": 32539200} {"current_steps": 32340, "total_steps": 42420, "loss": 0.0269, "lr": 8.119726590451598e-06, "epoch": 15.247524752475247, "percentage": 76.24, "elapsed_time": "1:57:04", "remaining_time": "0:36:29", "throughput": 4632.76, "total_tokens": 32543552} {"current_steps": 32345, "total_steps": 42420, "loss": 0.1024, "lr": 8.112140808463759e-06, "epoch": 15.24988213107025, "percentage": 76.25, "elapsed_time": "1:57:05", "remaining_time": "0:36:28", "throughput": 4632.78, "total_tokens": 32548864} {"current_steps": 32350, "total_steps": 42420, "loss": 0.1331, "lr": 8.10455788530374e-06, "epoch": 15.252239509665252, "percentage": 76.26, "elapsed_time": "1:57:06", "remaining_time": "0:36:27", "throughput": 4632.74, "total_tokens": 32552736} {"current_steps": 32355, "total_steps": 42420, "loss": 0.1673, "lr": 8.096977822255205e-06, "epoch": 15.254596888260254, "percentage": 76.27, "elapsed_time": "1:57:07", "remaining_time": "0:36:26", "throughput": 4632.8, "total_tokens": 32558368} {"current_steps": 32360, "total_steps": 42420, "loss": 0.1286, "lr": 8.089400620601334e-06, "epoch": 15.256954266855256, "percentage": 76.28, "elapsed_time": "1:57:08", "remaining_time": "0:36:25", "throughput": 4632.83, "total_tokens": 32563680} {"current_steps": 32365, "total_steps": 42420, "loss": 0.0252, "lr": 8.081826281624805e-06, "epoch": 15.259311645450259, "percentage": 76.3, "elapsed_time": "1:57:09", "remaining_time": "0:36:24", "throughput": 4632.86, "total_tokens": 32568448} {"current_steps": 32370, "total_steps": 42420, "loss": 0.2125, "lr": 8.074254806607833e-06, "epoch": 15.261669024045261, "percentage": 76.31, "elapsed_time": "1:57:10", "remaining_time": "0:36:22", "throughput": 4632.89, "total_tokens": 32573824} {"current_steps": 32375, "total_steps": 42420, "loss": 0.171, "lr": 8.066686196832138e-06, "epoch": 15.264026402640264, "percentage": 76.32, "elapsed_time": "1:57:12", "remaining_time": "0:36:21", "throughput": 4632.94, "total_tokens": 32579072} {"current_steps": 32380, "total_steps": 42420, "loss": 0.1335, "lr": 8.05912045357896e-06, "epoch": 15.266383781235266, "percentage": 76.33, "elapsed_time": "1:57:13", "remaining_time": "0:36:20", "throughput": 4632.96, "total_tokens": 32583712} {"current_steps": 32385, "total_steps": 42420, "loss": 0.0583, "lr": 8.051557578129057e-06, "epoch": 15.268741159830268, "percentage": 76.34, "elapsed_time": "1:57:14", "remaining_time": "0:36:19", "throughput": 4632.99, "total_tokens": 32588704} {"current_steps": 32390, "total_steps": 42420, "loss": 0.097, "lr": 8.043997571762679e-06, "epoch": 15.27109853842527, "percentage": 76.36, "elapsed_time": "1:57:15", "remaining_time": "0:36:18", "throughput": 4632.99, "total_tokens": 32593376} {"current_steps": 32395, "total_steps": 42420, "loss": 0.1247, "lr": 8.036440435759616e-06, "epoch": 15.273455917020273, "percentage": 76.37, "elapsed_time": "1:57:16", "remaining_time": "0:36:17", "throughput": 4633.0, "total_tokens": 32598016} {"current_steps": 32400, "total_steps": 42420, "loss": 0.0801, "lr": 8.028886171399164e-06, "epoch": 15.275813295615276, "percentage": 76.38, "elapsed_time": "1:57:17", "remaining_time": "0:36:16", "throughput": 4633.1, "total_tokens": 32605280} {"current_steps": 32405, "total_steps": 42420, "loss": 0.0915, "lr": 8.021334779960127e-06, "epoch": 15.278170674210278, "percentage": 76.39, "elapsed_time": "1:57:18", "remaining_time": "0:36:15", "throughput": 4633.13, "total_tokens": 32610304} {"current_steps": 32410, "total_steps": 42420, "loss": 0.0503, "lr": 8.013786262720832e-06, "epoch": 15.28052805280528, "percentage": 76.4, "elapsed_time": "1:57:19", "remaining_time": "0:36:14", "throughput": 4633.14, "total_tokens": 32615232} {"current_steps": 32415, "total_steps": 42420, "loss": 0.1012, "lr": 8.006240620959112e-06, "epoch": 15.282885431400283, "percentage": 76.41, "elapsed_time": "1:57:20", "remaining_time": "0:36:13", "throughput": 4633.16, "total_tokens": 32619712} {"current_steps": 32420, "total_steps": 42420, "loss": 0.0537, "lr": 7.99869785595232e-06, "epoch": 15.285242809995285, "percentage": 76.43, "elapsed_time": "1:57:21", "remaining_time": "0:36:11", "throughput": 4633.18, "total_tokens": 32624448} {"current_steps": 32425, "total_steps": 42420, "loss": 0.2084, "lr": 7.991157968977323e-06, "epoch": 15.287600188590288, "percentage": 76.44, "elapsed_time": "1:57:22", "remaining_time": "0:36:10", "throughput": 4633.21, "total_tokens": 32629152} {"current_steps": 32430, "total_steps": 42420, "loss": 0.1668, "lr": 7.983620961310478e-06, "epoch": 15.28995756718529, "percentage": 76.45, "elapsed_time": "1:57:23", "remaining_time": "0:36:09", "throughput": 4633.23, "total_tokens": 32634816} {"current_steps": 32435, "total_steps": 42420, "loss": 0.2493, "lr": 7.976086834227684e-06, "epoch": 15.292314945780292, "percentage": 76.46, "elapsed_time": "1:57:24", "remaining_time": "0:36:08", "throughput": 4633.26, "total_tokens": 32639744} {"current_steps": 32440, "total_steps": 42420, "loss": 0.02, "lr": 7.96855558900434e-06, "epoch": 15.294672324375295, "percentage": 76.47, "elapsed_time": "1:57:25", "remaining_time": "0:36:07", "throughput": 4633.26, "total_tokens": 32643968} {"current_steps": 32445, "total_steps": 42420, "loss": 0.0422, "lr": 7.961027226915355e-06, "epoch": 15.297029702970297, "percentage": 76.49, "elapsed_time": "1:57:26", "remaining_time": "0:36:06", "throughput": 4633.3, "total_tokens": 32649120} {"current_steps": 32450, "total_steps": 42420, "loss": 0.046, "lr": 7.953501749235157e-06, "epoch": 15.2993870815653, "percentage": 76.5, "elapsed_time": "1:57:27", "remaining_time": "0:36:05", "throughput": 4633.29, "total_tokens": 32653088} {"current_steps": 32455, "total_steps": 42420, "loss": 0.1137, "lr": 7.94597915723768e-06, "epoch": 15.301744460160302, "percentage": 76.51, "elapsed_time": "1:57:28", "remaining_time": "0:36:04", "throughput": 4633.32, "total_tokens": 32658176} {"current_steps": 32460, "total_steps": 42420, "loss": 0.047, "lr": 7.938459452196367e-06, "epoch": 15.304101838755304, "percentage": 76.52, "elapsed_time": "1:57:29", "remaining_time": "0:36:03", "throughput": 4633.34, "total_tokens": 32663232} {"current_steps": 32465, "total_steps": 42420, "loss": 0.0394, "lr": 7.930942635384192e-06, "epoch": 15.306459217350307, "percentage": 76.53, "elapsed_time": "1:57:31", "remaining_time": "0:36:02", "throughput": 4633.4, "total_tokens": 32670272} {"current_steps": 32470, "total_steps": 42420, "loss": 0.2586, "lr": 7.923428708073605e-06, "epoch": 15.30881659594531, "percentage": 76.54, "elapsed_time": "1:57:31", "remaining_time": "0:36:00", "throughput": 4633.41, "total_tokens": 32674656} {"current_steps": 32475, "total_steps": 42420, "loss": 0.0827, "lr": 7.915917671536594e-06, "epoch": 15.311173974540312, "percentage": 76.56, "elapsed_time": "1:57:33", "remaining_time": "0:36:00", "throughput": 4633.45, "total_tokens": 32683008} {"current_steps": 32480, "total_steps": 42420, "loss": 0.1303, "lr": 7.908409527044647e-06, "epoch": 15.313531353135314, "percentage": 76.57, "elapsed_time": "1:57:34", "remaining_time": "0:35:58", "throughput": 4633.48, "total_tokens": 32687776} {"current_steps": 32485, "total_steps": 42420, "loss": 0.0942, "lr": 7.90090427586877e-06, "epoch": 15.315888731730317, "percentage": 76.58, "elapsed_time": "1:57:35", "remaining_time": "0:35:57", "throughput": 4633.51, "total_tokens": 32692576} {"current_steps": 32490, "total_steps": 42420, "loss": 0.0258, "lr": 7.893401919279475e-06, "epoch": 15.318246110325319, "percentage": 76.59, "elapsed_time": "1:57:36", "remaining_time": "0:35:56", "throughput": 4633.53, "total_tokens": 32697376} {"current_steps": 32495, "total_steps": 42420, "loss": 0.214, "lr": 7.885902458546779e-06, "epoch": 15.320603488920321, "percentage": 76.6, "elapsed_time": "1:57:37", "remaining_time": "0:35:55", "throughput": 4633.55, "total_tokens": 32702432} {"current_steps": 32500, "total_steps": 42420, "loss": 0.0665, "lr": 7.878405894940219e-06, "epoch": 15.322960867515324, "percentage": 76.61, "elapsed_time": "1:57:38", "remaining_time": "0:35:54", "throughput": 4633.55, "total_tokens": 32706944} {"current_steps": 32505, "total_steps": 42420, "loss": 0.0422, "lr": 7.870912229728838e-06, "epoch": 15.325318246110326, "percentage": 76.63, "elapsed_time": "1:57:39", "remaining_time": "0:35:53", "throughput": 4633.58, "total_tokens": 32711264} {"current_steps": 32510, "total_steps": 42420, "loss": 0.1496, "lr": 7.863421464181173e-06, "epoch": 15.327675624705329, "percentage": 76.64, "elapsed_time": "1:57:40", "remaining_time": "0:35:52", "throughput": 4633.6, "total_tokens": 32715744} {"current_steps": 32515, "total_steps": 42420, "loss": 0.1499, "lr": 7.855933599565293e-06, "epoch": 15.33003300330033, "percentage": 76.65, "elapsed_time": "1:57:41", "remaining_time": "0:35:51", "throughput": 4633.63, "total_tokens": 32721248} {"current_steps": 32520, "total_steps": 42420, "loss": 0.1251, "lr": 7.848448637148765e-06, "epoch": 15.332390381895332, "percentage": 76.66, "elapsed_time": "1:57:42", "remaining_time": "0:35:50", "throughput": 4633.66, "total_tokens": 32725888} {"current_steps": 32525, "total_steps": 42420, "loss": 0.149, "lr": 7.840966578198666e-06, "epoch": 15.334747760490334, "percentage": 76.67, "elapsed_time": "1:57:43", "remaining_time": "0:35:48", "throughput": 4633.69, "total_tokens": 32730944} {"current_steps": 32530, "total_steps": 42420, "loss": 0.0436, "lr": 7.833487423981581e-06, "epoch": 15.337105139085336, "percentage": 76.69, "elapsed_time": "1:57:44", "remaining_time": "0:35:47", "throughput": 4633.72, "total_tokens": 32735840} {"current_steps": 32535, "total_steps": 42420, "loss": 0.0107, "lr": 7.826011175763603e-06, "epoch": 15.339462517680339, "percentage": 76.7, "elapsed_time": "1:57:45", "remaining_time": "0:35:46", "throughput": 4633.71, "total_tokens": 32740000} {"current_steps": 32540, "total_steps": 42420, "loss": 0.0612, "lr": 7.818537834810339e-06, "epoch": 15.341819896275341, "percentage": 76.71, "elapsed_time": "1:57:46", "remaining_time": "0:35:45", "throughput": 4633.78, "total_tokens": 32746400} {"current_steps": 32545, "total_steps": 42420, "loss": 0.2102, "lr": 7.811067402386898e-06, "epoch": 15.344177274870344, "percentage": 76.72, "elapsed_time": "1:57:47", "remaining_time": "0:35:44", "throughput": 4633.83, "total_tokens": 32751840} {"current_steps": 32550, "total_steps": 42420, "loss": 0.0331, "lr": 7.803599879757889e-06, "epoch": 15.346534653465346, "percentage": 76.73, "elapsed_time": "1:57:49", "remaining_time": "0:35:43", "throughput": 4633.88, "total_tokens": 32757504} {"current_steps": 32555, "total_steps": 42420, "loss": 0.0549, "lr": 7.796135268187444e-06, "epoch": 15.348892032060348, "percentage": 76.74, "elapsed_time": "1:57:50", "remaining_time": "0:35:42", "throughput": 4633.88, "total_tokens": 32761824} {"current_steps": 32560, "total_steps": 42420, "loss": 0.1041, "lr": 7.78867356893919e-06, "epoch": 15.35124941065535, "percentage": 76.76, "elapsed_time": "1:57:51", "remaining_time": "0:35:41", "throughput": 4633.91, "total_tokens": 32766528} {"current_steps": 32565, "total_steps": 42420, "loss": 0.0916, "lr": 7.78121478327627e-06, "epoch": 15.353606789250353, "percentage": 76.77, "elapsed_time": "1:57:52", "remaining_time": "0:35:40", "throughput": 4633.94, "total_tokens": 32771712} {"current_steps": 32570, "total_steps": 42420, "loss": 0.073, "lr": 7.77375891246133e-06, "epoch": 15.355964167845356, "percentage": 76.78, "elapsed_time": "1:57:53", "remaining_time": "0:35:39", "throughput": 4633.96, "total_tokens": 32776192} {"current_steps": 32575, "total_steps": 42420, "loss": 0.0598, "lr": 7.766305957756517e-06, "epoch": 15.358321546440358, "percentage": 76.79, "elapsed_time": "1:57:53", "remaining_time": "0:35:37", "throughput": 4633.96, "total_tokens": 32780288} {"current_steps": 32580, "total_steps": 42420, "loss": 0.1591, "lr": 7.7588559204235e-06, "epoch": 15.36067892503536, "percentage": 76.8, "elapsed_time": "1:57:54", "remaining_time": "0:35:36", "throughput": 4633.98, "total_tokens": 32784992} {"current_steps": 32585, "total_steps": 42420, "loss": 0.2084, "lr": 7.751408801723442e-06, "epoch": 15.363036303630363, "percentage": 76.82, "elapsed_time": "1:57:55", "remaining_time": "0:35:35", "throughput": 4633.99, "total_tokens": 32789664} {"current_steps": 32590, "total_steps": 42420, "loss": 0.0972, "lr": 7.743964602917e-06, "epoch": 15.365393682225365, "percentage": 76.83, "elapsed_time": "1:57:56", "remaining_time": "0:35:34", "throughput": 4634.02, "total_tokens": 32794400} {"current_steps": 32595, "total_steps": 42420, "loss": 0.0693, "lr": 7.736523325264373e-06, "epoch": 15.367751060820368, "percentage": 76.84, "elapsed_time": "1:57:58", "remaining_time": "0:35:33", "throughput": 4634.07, "total_tokens": 32800192} {"current_steps": 32600, "total_steps": 42420, "loss": 0.0845, "lr": 7.72908497002522e-06, "epoch": 15.37010843941537, "percentage": 76.85, "elapsed_time": "1:57:59", "remaining_time": "0:35:32", "throughput": 4634.09, "total_tokens": 32804832} {"current_steps": 32605, "total_steps": 42420, "loss": 0.1317, "lr": 7.721649538458734e-06, "epoch": 15.372465818010372, "percentage": 76.86, "elapsed_time": "1:57:59", "remaining_time": "0:35:31", "throughput": 4634.11, "total_tokens": 32809248} {"current_steps": 32610, "total_steps": 42420, "loss": 0.1018, "lr": 7.714217031823615e-06, "epoch": 15.374823196605375, "percentage": 76.87, "elapsed_time": "1:58:00", "remaining_time": "0:35:30", "throughput": 4634.13, "total_tokens": 32814208} {"current_steps": 32615, "total_steps": 42420, "loss": 0.0216, "lr": 7.706787451378055e-06, "epoch": 15.377180575200377, "percentage": 76.89, "elapsed_time": "1:58:02", "remaining_time": "0:35:29", "throughput": 4634.18, "total_tokens": 32820256} {"current_steps": 32620, "total_steps": 42420, "loss": 0.1755, "lr": 7.69936079837976e-06, "epoch": 15.37953795379538, "percentage": 76.9, "elapsed_time": "1:58:03", "remaining_time": "0:35:27", "throughput": 4634.19, "total_tokens": 32824640} {"current_steps": 32625, "total_steps": 42420, "loss": 0.0968, "lr": 7.691937074085934e-06, "epoch": 15.381895332390382, "percentage": 76.91, "elapsed_time": "1:58:04", "remaining_time": "0:35:26", "throughput": 4634.23, "total_tokens": 32829888} {"current_steps": 32630, "total_steps": 42420, "loss": 0.2201, "lr": 7.684516279753284e-06, "epoch": 15.384252710985384, "percentage": 76.92, "elapsed_time": "1:58:05", "remaining_time": "0:35:25", "throughput": 4634.21, "total_tokens": 32833792} {"current_steps": 32635, "total_steps": 42420, "loss": 0.0806, "lr": 7.677098416638037e-06, "epoch": 15.386610089580387, "percentage": 76.93, "elapsed_time": "1:58:06", "remaining_time": "0:35:24", "throughput": 4634.26, "total_tokens": 32839264} {"current_steps": 32640, "total_steps": 42420, "loss": 0.0863, "lr": 7.669683485995893e-06, "epoch": 15.38896746817539, "percentage": 76.94, "elapsed_time": "1:58:07", "remaining_time": "0:35:23", "throughput": 4634.31, "total_tokens": 32845280} {"current_steps": 32645, "total_steps": 42420, "loss": 0.0311, "lr": 7.662271489082084e-06, "epoch": 15.391324846770392, "percentage": 76.96, "elapsed_time": "1:58:08", "remaining_time": "0:35:22", "throughput": 4634.33, "total_tokens": 32849728} {"current_steps": 32650, "total_steps": 42420, "loss": 0.2215, "lr": 7.654862427151336e-06, "epoch": 15.393682225365394, "percentage": 76.97, "elapsed_time": "1:58:09", "remaining_time": "0:35:21", "throughput": 4634.36, "total_tokens": 32854336} {"current_steps": 32655, "total_steps": 42420, "loss": 0.0737, "lr": 7.647456301457873e-06, "epoch": 15.396039603960396, "percentage": 76.98, "elapsed_time": "1:58:10", "remaining_time": "0:35:20", "throughput": 4634.39, "total_tokens": 32859008} {"current_steps": 32660, "total_steps": 42420, "loss": 0.2301, "lr": 7.640053113255427e-06, "epoch": 15.398396982555399, "percentage": 76.99, "elapsed_time": "1:58:11", "remaining_time": "0:35:19", "throughput": 4634.39, "total_tokens": 32863808} {"current_steps": 32665, "total_steps": 42420, "loss": 0.0673, "lr": 7.632652863797238e-06, "epoch": 15.400754361150401, "percentage": 77.0, "elapsed_time": "1:58:12", "remaining_time": "0:35:18", "throughput": 4634.41, "total_tokens": 32868320} {"current_steps": 32670, "total_steps": 42420, "loss": 0.1419, "lr": 7.625255554336036e-06, "epoch": 15.403111739745404, "percentage": 77.02, "elapsed_time": "1:58:13", "remaining_time": "0:35:16", "throughput": 4634.46, "total_tokens": 32874368} {"current_steps": 32675, "total_steps": 42420, "loss": 0.0873, "lr": 7.61786118612407e-06, "epoch": 15.405469118340406, "percentage": 77.03, "elapsed_time": "1:58:14", "remaining_time": "0:35:15", "throughput": 4634.48, "total_tokens": 32879264} {"current_steps": 32680, "total_steps": 42420, "loss": 0.0284, "lr": 7.6104697604130664e-06, "epoch": 15.407826496935408, "percentage": 77.04, "elapsed_time": "1:58:15", "remaining_time": "0:35:14", "throughput": 4634.5, "total_tokens": 32883840} {"current_steps": 32685, "total_steps": 42420, "loss": 0.0641, "lr": 7.603081278454274e-06, "epoch": 15.41018387553041, "percentage": 77.05, "elapsed_time": "1:58:16", "remaining_time": "0:35:13", "throughput": 4634.54, "total_tokens": 32889312} {"current_steps": 32690, "total_steps": 42420, "loss": 0.3549, "lr": 7.595695741498438e-06, "epoch": 15.412541254125413, "percentage": 77.06, "elapsed_time": "1:58:17", "remaining_time": "0:35:12", "throughput": 4634.55, "total_tokens": 32893888} {"current_steps": 32695, "total_steps": 42420, "loss": 0.0475, "lr": 7.588313150795806e-06, "epoch": 15.414898632720416, "percentage": 77.07, "elapsed_time": "1:58:18", "remaining_time": "0:35:11", "throughput": 4634.6, "total_tokens": 32899488} {"current_steps": 32700, "total_steps": 42420, "loss": 0.0736, "lr": 7.580933507596124e-06, "epoch": 15.417256011315418, "percentage": 77.09, "elapsed_time": "1:58:19", "remaining_time": "0:35:10", "throughput": 4634.65, "total_tokens": 32905056} {"current_steps": 32705, "total_steps": 42420, "loss": 0.1387, "lr": 7.573556813148639e-06, "epoch": 15.41961338991042, "percentage": 77.1, "elapsed_time": "1:58:20", "remaining_time": "0:35:09", "throughput": 4634.68, "total_tokens": 32910176} {"current_steps": 32710, "total_steps": 42420, "loss": 0.0626, "lr": 7.566183068702101e-06, "epoch": 15.421970768505423, "percentage": 77.11, "elapsed_time": "1:58:21", "remaining_time": "0:35:08", "throughput": 4634.72, "total_tokens": 32914944} {"current_steps": 32715, "total_steps": 42420, "loss": 0.0476, "lr": 7.55881227550477e-06, "epoch": 15.424328147100425, "percentage": 77.12, "elapsed_time": "1:58:22", "remaining_time": "0:35:07", "throughput": 4634.74, "total_tokens": 32919264} {"current_steps": 32720, "total_steps": 42420, "loss": 0.0592, "lr": 7.5514444348043775e-06, "epoch": 15.426685525695426, "percentage": 77.13, "elapsed_time": "1:58:23", "remaining_time": "0:35:05", "throughput": 4634.76, "total_tokens": 32924288} {"current_steps": 32725, "total_steps": 42420, "loss": 0.2539, "lr": 7.5440795478481815e-06, "epoch": 15.429042904290428, "percentage": 77.15, "elapsed_time": "1:58:24", "remaining_time": "0:35:04", "throughput": 4634.8, "total_tokens": 32929792} {"current_steps": 32730, "total_steps": 42420, "loss": 0.1946, "lr": 7.536717615882935e-06, "epoch": 15.43140028288543, "percentage": 77.16, "elapsed_time": "1:58:26", "remaining_time": "0:35:03", "throughput": 4634.86, "total_tokens": 32936032} {"current_steps": 32735, "total_steps": 42420, "loss": 0.0733, "lr": 7.529358640154885e-06, "epoch": 15.433757661480433, "percentage": 77.17, "elapsed_time": "1:58:27", "remaining_time": "0:35:02", "throughput": 4634.86, "total_tokens": 32940064} {"current_steps": 32740, "total_steps": 42420, "loss": 0.2648, "lr": 7.522002621909785e-06, "epoch": 15.436115040075435, "percentage": 77.18, "elapsed_time": "1:58:28", "remaining_time": "0:35:01", "throughput": 4634.9, "total_tokens": 32945824} {"current_steps": 32745, "total_steps": 42420, "loss": 0.124, "lr": 7.5146495623928785e-06, "epoch": 15.438472418670438, "percentage": 77.19, "elapsed_time": "1:58:29", "remaining_time": "0:35:00", "throughput": 4634.94, "total_tokens": 32950496} {"current_steps": 32750, "total_steps": 42420, "loss": 0.0958, "lr": 7.5072994628489185e-06, "epoch": 15.44082979726544, "percentage": 77.2, "elapsed_time": "1:58:30", "remaining_time": "0:34:59", "throughput": 4634.97, "total_tokens": 32955616} {"current_steps": 32755, "total_steps": 42420, "loss": 0.2224, "lr": 7.499952324522158e-06, "epoch": 15.443187175860443, "percentage": 77.22, "elapsed_time": "1:58:31", "remaining_time": "0:34:58", "throughput": 4634.97, "total_tokens": 32960384} {"current_steps": 32760, "total_steps": 42420, "loss": 0.1918, "lr": 7.492608148656327e-06, "epoch": 15.445544554455445, "percentage": 77.23, "elapsed_time": "1:58:32", "remaining_time": "0:34:57", "throughput": 4635.03, "total_tokens": 32967872} {"current_steps": 32765, "total_steps": 42420, "loss": 0.0923, "lr": 7.485266936494678e-06, "epoch": 15.447901933050447, "percentage": 77.24, "elapsed_time": "1:58:34", "remaining_time": "0:34:56", "throughput": 4635.12, "total_tokens": 32975872} {"current_steps": 32770, "total_steps": 42420, "loss": 0.1048, "lr": 7.477928689279953e-06, "epoch": 15.45025931164545, "percentage": 77.25, "elapsed_time": "1:58:35", "remaining_time": "0:34:55", "throughput": 4635.11, "total_tokens": 32980064} {"current_steps": 32775, "total_steps": 42420, "loss": 0.1591, "lr": 7.470593408254395e-06, "epoch": 15.452616690240452, "percentage": 77.26, "elapsed_time": "1:58:36", "remaining_time": "0:34:54", "throughput": 4635.16, "total_tokens": 32985312} {"current_steps": 32780, "total_steps": 42420, "loss": 0.1626, "lr": 7.463261094659738e-06, "epoch": 15.454974068835455, "percentage": 77.27, "elapsed_time": "1:58:37", "remaining_time": "0:34:53", "throughput": 4635.2, "total_tokens": 32990368} {"current_steps": 32785, "total_steps": 42420, "loss": 0.0119, "lr": 7.455931749737222e-06, "epoch": 15.457331447430457, "percentage": 77.29, "elapsed_time": "1:58:38", "remaining_time": "0:34:51", "throughput": 4635.23, "total_tokens": 32995264} {"current_steps": 32790, "total_steps": 42420, "loss": 0.284, "lr": 7.44860537472758e-06, "epoch": 15.45968882602546, "percentage": 77.3, "elapsed_time": "1:58:39", "remaining_time": "0:34:50", "throughput": 4635.26, "total_tokens": 33000992} {"current_steps": 32795, "total_steps": 42420, "loss": 0.0597, "lr": 7.441281970871047e-06, "epoch": 15.462046204620462, "percentage": 77.31, "elapsed_time": "1:58:40", "remaining_time": "0:34:49", "throughput": 4635.3, "total_tokens": 33005920} {"current_steps": 32800, "total_steps": 42420, "loss": 0.1313, "lr": 7.433961539407341e-06, "epoch": 15.464403583215464, "percentage": 77.32, "elapsed_time": "1:58:41", "remaining_time": "0:34:48", "throughput": 4635.36, "total_tokens": 33012192} {"current_steps": 32805, "total_steps": 42420, "loss": 0.0531, "lr": 7.426644081575693e-06, "epoch": 15.466760961810467, "percentage": 77.33, "elapsed_time": "1:58:42", "remaining_time": "0:34:47", "throughput": 4635.36, "total_tokens": 33016032} {"current_steps": 32810, "total_steps": 42420, "loss": 0.1532, "lr": 7.41932959861483e-06, "epoch": 15.469118340405469, "percentage": 77.35, "elapsed_time": "1:58:43", "remaining_time": "0:34:46", "throughput": 4635.41, "total_tokens": 33021760} {"current_steps": 32815, "total_steps": 42420, "loss": 0.136, "lr": 7.4120180917629565e-06, "epoch": 15.471475719000471, "percentage": 77.36, "elapsed_time": "1:58:44", "remaining_time": "0:34:45", "throughput": 4635.45, "total_tokens": 33026432} {"current_steps": 32820, "total_steps": 42420, "loss": 0.0349, "lr": 7.404709562257791e-06, "epoch": 15.473833097595474, "percentage": 77.37, "elapsed_time": "1:58:45", "remaining_time": "0:34:44", "throughput": 4635.48, "total_tokens": 33031360} {"current_steps": 32825, "total_steps": 42420, "loss": 0.1755, "lr": 7.397404011336548e-06, "epoch": 15.476190476190476, "percentage": 77.38, "elapsed_time": "1:58:47", "remaining_time": "0:34:43", "throughput": 4635.52, "total_tokens": 33037664} {"current_steps": 32830, "total_steps": 42420, "loss": 0.1368, "lr": 7.390101440235927e-06, "epoch": 15.478547854785479, "percentage": 77.39, "elapsed_time": "1:58:48", "remaining_time": "0:34:42", "throughput": 4635.56, "total_tokens": 33042848} {"current_steps": 32835, "total_steps": 42420, "loss": 0.07, "lr": 7.382801850192136e-06, "epoch": 15.480905233380481, "percentage": 77.4, "elapsed_time": "1:58:49", "remaining_time": "0:34:41", "throughput": 4635.6, "total_tokens": 33049120} {"current_steps": 32840, "total_steps": 42420, "loss": 0.0625, "lr": 7.37550524244087e-06, "epoch": 15.483262611975483, "percentage": 77.42, "elapsed_time": "1:58:50", "remaining_time": "0:34:40", "throughput": 4635.64, "total_tokens": 33054176} {"current_steps": 32845, "total_steps": 42420, "loss": 0.3472, "lr": 7.3682116182173245e-06, "epoch": 15.485619990570486, "percentage": 77.43, "elapsed_time": "1:58:51", "remaining_time": "0:34:38", "throughput": 4635.65, "total_tokens": 33058368} {"current_steps": 32850, "total_steps": 42420, "loss": 0.0957, "lr": 7.360920978756175e-06, "epoch": 15.487977369165488, "percentage": 77.44, "elapsed_time": "1:58:52", "remaining_time": "0:34:37", "throughput": 4635.65, "total_tokens": 33063104} {"current_steps": 32855, "total_steps": 42420, "loss": 0.1478, "lr": 7.353633325291609e-06, "epoch": 15.49033474776049, "percentage": 77.45, "elapsed_time": "1:58:53", "remaining_time": "0:34:36", "throughput": 4635.69, "total_tokens": 33068320} {"current_steps": 32860, "total_steps": 42420, "loss": 0.1138, "lr": 7.346348659057303e-06, "epoch": 15.492692126355493, "percentage": 77.46, "elapsed_time": "1:58:54", "remaining_time": "0:34:35", "throughput": 4635.69, "total_tokens": 33072480} {"current_steps": 32865, "total_steps": 42420, "loss": 0.1355, "lr": 7.339066981286427e-06, "epoch": 15.495049504950495, "percentage": 77.48, "elapsed_time": "1:58:55", "remaining_time": "0:34:34", "throughput": 4635.76, "total_tokens": 33079168} {"current_steps": 32870, "total_steps": 42420, "loss": 0.0436, "lr": 7.331788293211644e-06, "epoch": 15.497406883545498, "percentage": 77.49, "elapsed_time": "1:58:56", "remaining_time": "0:34:33", "throughput": 4635.79, "total_tokens": 33083552} {"current_steps": 32875, "total_steps": 42420, "loss": 0.0724, "lr": 7.324512596065117e-06, "epoch": 15.4997642621405, "percentage": 77.5, "elapsed_time": "1:58:57", "remaining_time": "0:34:32", "throughput": 4635.84, "total_tokens": 33088928} {"current_steps": 32880, "total_steps": 42420, "loss": 0.1387, "lr": 7.317239891078492e-06, "epoch": 15.502121640735503, "percentage": 77.51, "elapsed_time": "1:58:58", "remaining_time": "0:34:31", "throughput": 4635.9, "total_tokens": 33094720} {"current_steps": 32885, "total_steps": 42420, "loss": 0.2859, "lr": 7.309970179482925e-06, "epoch": 15.504479019330505, "percentage": 77.52, "elapsed_time": "1:58:59", "remaining_time": "0:34:30", "throughput": 4635.94, "total_tokens": 33100000} {"current_steps": 32890, "total_steps": 42420, "loss": 0.1679, "lr": 7.302703462509042e-06, "epoch": 15.506836397925507, "percentage": 77.53, "elapsed_time": "1:59:00", "remaining_time": "0:34:29", "throughput": 4635.96, "total_tokens": 33105088} {"current_steps": 32895, "total_steps": 42420, "loss": 0.0825, "lr": 7.295439741386978e-06, "epoch": 15.50919377652051, "percentage": 77.55, "elapsed_time": "1:59:01", "remaining_time": "0:34:27", "throughput": 4635.92, "total_tokens": 33108672} {"current_steps": 32900, "total_steps": 42420, "loss": 0.2231, "lr": 7.288179017346358e-06, "epoch": 15.511551155115512, "percentage": 77.56, "elapsed_time": "1:59:02", "remaining_time": "0:34:26", "throughput": 4635.93, "total_tokens": 33113120} {"current_steps": 32905, "total_steps": 42420, "loss": 0.0245, "lr": 7.280921291616302e-06, "epoch": 15.513908533710515, "percentage": 77.57, "elapsed_time": "1:59:03", "remaining_time": "0:34:25", "throughput": 4635.96, "total_tokens": 33118176} {"current_steps": 32910, "total_steps": 42420, "loss": 0.0382, "lr": 7.273666565425419e-06, "epoch": 15.516265912305517, "percentage": 77.58, "elapsed_time": "1:59:04", "remaining_time": "0:34:24", "throughput": 4635.97, "total_tokens": 33122784} {"current_steps": 32915, "total_steps": 42420, "loss": 0.0641, "lr": 7.266414840001812e-06, "epoch": 15.518623290900518, "percentage": 77.59, "elapsed_time": "1:59:05", "remaining_time": "0:34:23", "throughput": 4636.0, "total_tokens": 33128672} {"current_steps": 32920, "total_steps": 42420, "loss": 0.0353, "lr": 7.259166116573071e-06, "epoch": 15.520980669495522, "percentage": 77.6, "elapsed_time": "1:59:06", "remaining_time": "0:34:22", "throughput": 4636.0, "total_tokens": 33132736} {"current_steps": 32925, "total_steps": 42420, "loss": 0.1627, "lr": 7.251920396366293e-06, "epoch": 15.523338048090523, "percentage": 77.62, "elapsed_time": "1:59:07", "remaining_time": "0:34:21", "throughput": 4636.03, "total_tokens": 33137568} {"current_steps": 32930, "total_steps": 42420, "loss": 0.0562, "lr": 7.244677680608039e-06, "epoch": 15.525695426685525, "percentage": 77.63, "elapsed_time": "1:59:08", "remaining_time": "0:34:20", "throughput": 4636.06, "total_tokens": 33142368} {"current_steps": 32935, "total_steps": 42420, "loss": 0.1226, "lr": 7.237437970524385e-06, "epoch": 15.528052805280527, "percentage": 77.64, "elapsed_time": "1:59:09", "remaining_time": "0:34:19", "throughput": 4636.05, "total_tokens": 33146752} {"current_steps": 32940, "total_steps": 42420, "loss": 0.1031, "lr": 7.230201267340891e-06, "epoch": 15.53041018387553, "percentage": 77.65, "elapsed_time": "1:59:10", "remaining_time": "0:34:18", "throughput": 4636.07, "total_tokens": 33152384} {"current_steps": 32945, "total_steps": 42420, "loss": 0.0889, "lr": 7.22296757228261e-06, "epoch": 15.532767562470532, "percentage": 77.66, "elapsed_time": "1:59:12", "remaining_time": "0:34:16", "throughput": 4636.1, "total_tokens": 33157888} {"current_steps": 32950, "total_steps": 42420, "loss": 0.1703, "lr": 7.215736886574079e-06, "epoch": 15.535124941065535, "percentage": 77.68, "elapsed_time": "1:59:13", "remaining_time": "0:34:15", "throughput": 4636.14, "total_tokens": 33163648} {"current_steps": 32955, "total_steps": 42420, "loss": 0.137, "lr": 7.2085092114393375e-06, "epoch": 15.537482319660537, "percentage": 77.69, "elapsed_time": "1:59:14", "remaining_time": "0:34:14", "throughput": 4636.13, "total_tokens": 33167808} {"current_steps": 32960, "total_steps": 42420, "loss": 0.0857, "lr": 7.2012845481019026e-06, "epoch": 15.53983969825554, "percentage": 77.7, "elapsed_time": "1:59:15", "remaining_time": "0:34:13", "throughput": 4636.15, "total_tokens": 33172480} {"current_steps": 32965, "total_steps": 42420, "loss": 0.1898, "lr": 7.194062897784795e-06, "epoch": 15.542197076850542, "percentage": 77.71, "elapsed_time": "1:59:16", "remaining_time": "0:34:12", "throughput": 4636.17, "total_tokens": 33177056} {"current_steps": 32970, "total_steps": 42420, "loss": 0.1189, "lr": 7.186844261710504e-06, "epoch": 15.544554455445544, "percentage": 77.72, "elapsed_time": "1:59:17", "remaining_time": "0:34:11", "throughput": 4636.21, "total_tokens": 33182624} {"current_steps": 32975, "total_steps": 42420, "loss": 0.0966, "lr": 7.17962864110103e-06, "epoch": 15.546911834040547, "percentage": 77.73, "elapsed_time": "1:59:18", "remaining_time": "0:34:10", "throughput": 4636.22, "total_tokens": 33187552} {"current_steps": 32980, "total_steps": 42420, "loss": 0.1348, "lr": 7.172416037177854e-06, "epoch": 15.549269212635549, "percentage": 77.75, "elapsed_time": "1:59:19", "remaining_time": "0:34:09", "throughput": 4636.25, "total_tokens": 33192768} {"current_steps": 32985, "total_steps": 42420, "loss": 0.024, "lr": 7.165206451161949e-06, "epoch": 15.551626591230551, "percentage": 77.76, "elapsed_time": "1:59:20", "remaining_time": "0:34:08", "throughput": 4636.21, "total_tokens": 33196544} {"current_steps": 32990, "total_steps": 42420, "loss": 0.0392, "lr": 7.157999884273772e-06, "epoch": 15.553983969825554, "percentage": 77.77, "elapsed_time": "1:59:21", "remaining_time": "0:34:07", "throughput": 4636.25, "total_tokens": 33202016} {"current_steps": 32995, "total_steps": 42420, "loss": 0.0569, "lr": 7.150796337733276e-06, "epoch": 15.556341348420556, "percentage": 77.78, "elapsed_time": "1:59:22", "remaining_time": "0:34:05", "throughput": 4636.23, "total_tokens": 33206656} {"current_steps": 33000, "total_steps": 42420, "loss": 0.0795, "lr": 7.143595812759899e-06, "epoch": 15.558698727015559, "percentage": 77.79, "elapsed_time": "1:59:23", "remaining_time": "0:34:04", "throughput": 4636.25, "total_tokens": 33211872} {"current_steps": 33005, "total_steps": 42420, "loss": 0.0396, "lr": 7.136398310572573e-06, "epoch": 15.561056105610561, "percentage": 77.81, "elapsed_time": "1:59:24", "remaining_time": "0:34:03", "throughput": 4636.28, "total_tokens": 33216832} {"current_steps": 33010, "total_steps": 42420, "loss": 0.0637, "lr": 7.1292038323897e-06, "epoch": 15.563413484205563, "percentage": 77.82, "elapsed_time": "1:59:25", "remaining_time": "0:34:02", "throughput": 4636.3, "total_tokens": 33221664} {"current_steps": 33015, "total_steps": 42420, "loss": 0.1022, "lr": 7.1220123794291855e-06, "epoch": 15.565770862800566, "percentage": 77.83, "elapsed_time": "1:59:26", "remaining_time": "0:34:01", "throughput": 4636.34, "total_tokens": 33226848} {"current_steps": 33020, "total_steps": 42420, "loss": 0.0422, "lr": 7.114823952908428e-06, "epoch": 15.568128241395568, "percentage": 77.84, "elapsed_time": "1:59:27", "remaining_time": "0:34:00", "throughput": 4636.37, "total_tokens": 33232192} {"current_steps": 33025, "total_steps": 42420, "loss": 0.1869, "lr": 7.107638554044302e-06, "epoch": 15.57048561999057, "percentage": 77.85, "elapsed_time": "1:59:28", "remaining_time": "0:33:59", "throughput": 4636.37, "total_tokens": 33236800} {"current_steps": 33030, "total_steps": 42420, "loss": 0.1591, "lr": 7.100456184053173e-06, "epoch": 15.572842998585573, "percentage": 77.86, "elapsed_time": "1:59:29", "remaining_time": "0:33:58", "throughput": 4636.4, "total_tokens": 33242080} {"current_steps": 33035, "total_steps": 42420, "loss": 0.1599, "lr": 7.0932768441509e-06, "epoch": 15.575200377180575, "percentage": 77.88, "elapsed_time": "1:59:30", "remaining_time": "0:33:57", "throughput": 4636.42, "total_tokens": 33246976} {"current_steps": 33040, "total_steps": 42420, "loss": 0.0245, "lr": 7.086100535552814e-06, "epoch": 15.577557755775578, "percentage": 77.89, "elapsed_time": "1:59:31", "remaining_time": "0:33:56", "throughput": 4636.45, "total_tokens": 33252160} {"current_steps": 33045, "total_steps": 42420, "loss": 0.1625, "lr": 7.078927259473745e-06, "epoch": 15.57991513437058, "percentage": 77.9, "elapsed_time": "1:59:32", "remaining_time": "0:33:54", "throughput": 4636.45, "total_tokens": 33256096} {"current_steps": 33050, "total_steps": 42420, "loss": 0.1005, "lr": 7.071757017128011e-06, "epoch": 15.582272512965583, "percentage": 77.91, "elapsed_time": "1:59:33", "remaining_time": "0:33:53", "throughput": 4636.46, "total_tokens": 33260672} {"current_steps": 33055, "total_steps": 42420, "loss": 0.1106, "lr": 7.064589809729416e-06, "epoch": 15.584629891560585, "percentage": 77.92, "elapsed_time": "1:59:34", "remaining_time": "0:33:52", "throughput": 4636.47, "total_tokens": 33265696} {"current_steps": 33060, "total_steps": 42420, "loss": 0.0114, "lr": 7.05742563849123e-06, "epoch": 15.586987270155587, "percentage": 77.93, "elapsed_time": "1:59:35", "remaining_time": "0:33:51", "throughput": 4636.49, "total_tokens": 33271424} {"current_steps": 33065, "total_steps": 42420, "loss": 0.3097, "lr": 7.050264504626239e-06, "epoch": 15.58934464875059, "percentage": 77.95, "elapsed_time": "1:59:36", "remaining_time": "0:33:50", "throughput": 4636.49, "total_tokens": 33276096} {"current_steps": 33070, "total_steps": 42420, "loss": 0.0201, "lr": 7.043106409346698e-06, "epoch": 15.591702027345592, "percentage": 77.96, "elapsed_time": "1:59:38", "remaining_time": "0:33:49", "throughput": 4636.56, "total_tokens": 33282272} {"current_steps": 33075, "total_steps": 42420, "loss": 0.1717, "lr": 7.035951353864351e-06, "epoch": 15.594059405940595, "percentage": 77.97, "elapsed_time": "1:59:39", "remaining_time": "0:33:48", "throughput": 4636.57, "total_tokens": 33286784} {"current_steps": 33080, "total_steps": 42420, "loss": 0.0733, "lr": 7.028799339390427e-06, "epoch": 15.596416784535597, "percentage": 77.98, "elapsed_time": "1:59:40", "remaining_time": "0:33:47", "throughput": 4636.62, "total_tokens": 33292736} {"current_steps": 33085, "total_steps": 42420, "loss": 0.0588, "lr": 7.0216503671356406e-06, "epoch": 15.5987741631306, "percentage": 77.99, "elapsed_time": "1:59:41", "remaining_time": "0:33:46", "throughput": 4636.63, "total_tokens": 33297696} {"current_steps": 33090, "total_steps": 42420, "loss": 0.0984, "lr": 7.014504438310193e-06, "epoch": 15.601131541725602, "percentage": 78.01, "elapsed_time": "1:59:42", "remaining_time": "0:33:45", "throughput": 4636.64, "total_tokens": 33303296} {"current_steps": 33095, "total_steps": 42420, "loss": 0.2227, "lr": 7.007361554123776e-06, "epoch": 15.603488920320604, "percentage": 78.02, "elapsed_time": "1:59:43", "remaining_time": "0:33:44", "throughput": 4636.67, "total_tokens": 33308224} {"current_steps": 33100, "total_steps": 42420, "loss": 0.0276, "lr": 7.0002217157855405e-06, "epoch": 15.605846298915607, "percentage": 78.03, "elapsed_time": "1:59:44", "remaining_time": "0:33:42", "throughput": 4636.69, "total_tokens": 33312736} {"current_steps": 33105, "total_steps": 42420, "loss": 0.0578, "lr": 6.993084924504151e-06, "epoch": 15.608203677510609, "percentage": 78.04, "elapsed_time": "1:59:45", "remaining_time": "0:33:41", "throughput": 4636.71, "total_tokens": 33317824} {"current_steps": 33110, "total_steps": 42420, "loss": 0.1324, "lr": 6.985951181487743e-06, "epoch": 15.61056105610561, "percentage": 78.05, "elapsed_time": "1:59:46", "remaining_time": "0:33:40", "throughput": 4636.73, "total_tokens": 33322688} {"current_steps": 33115, "total_steps": 42420, "loss": 0.1456, "lr": 6.978820487943941e-06, "epoch": 15.612918434700614, "percentage": 78.06, "elapsed_time": "1:59:47", "remaining_time": "0:33:39", "throughput": 4636.75, "total_tokens": 33327648} {"current_steps": 33120, "total_steps": 42420, "loss": 0.0406, "lr": 6.971692845079847e-06, "epoch": 15.615275813295614, "percentage": 78.08, "elapsed_time": "1:59:48", "remaining_time": "0:33:38", "throughput": 4636.76, "total_tokens": 33332992} {"current_steps": 33125, "total_steps": 42420, "loss": 0.0743, "lr": 6.964568254102049e-06, "epoch": 15.617633191890617, "percentage": 78.09, "elapsed_time": "1:59:50", "remaining_time": "0:33:37", "throughput": 4636.8, "total_tokens": 33338816} {"current_steps": 33130, "total_steps": 42420, "loss": 0.1464, "lr": 6.9574467162166254e-06, "epoch": 15.61999057048562, "percentage": 78.1, "elapsed_time": "1:59:51", "remaining_time": "0:33:36", "throughput": 4636.83, "total_tokens": 33343936} {"current_steps": 33135, "total_steps": 42420, "loss": 0.376, "lr": 6.950328232629133e-06, "epoch": 15.622347949080622, "percentage": 78.11, "elapsed_time": "1:59:52", "remaining_time": "0:33:35", "throughput": 4636.86, "total_tokens": 33349152} {"current_steps": 33140, "total_steps": 42420, "loss": 0.2444, "lr": 6.943212804544597e-06, "epoch": 15.624705327675624, "percentage": 78.12, "elapsed_time": "1:59:53", "remaining_time": "0:33:34", "throughput": 4636.91, "total_tokens": 33355424} {"current_steps": 33145, "total_steps": 42420, "loss": 0.1604, "lr": 6.936100433167547e-06, "epoch": 15.627062706270626, "percentage": 78.14, "elapsed_time": "1:59:54", "remaining_time": "0:33:33", "throughput": 4636.91, "total_tokens": 33359584} {"current_steps": 33150, "total_steps": 42420, "loss": 0.118, "lr": 6.928991119701986e-06, "epoch": 15.629420084865629, "percentage": 78.15, "elapsed_time": "1:59:55", "remaining_time": "0:33:32", "throughput": 4636.91, "total_tokens": 33364672} {"current_steps": 33155, "total_steps": 42420, "loss": 0.0377, "lr": 6.9218848653513995e-06, "epoch": 15.631777463460631, "percentage": 78.16, "elapsed_time": "1:59:56", "remaining_time": "0:33:31", "throughput": 4636.93, "total_tokens": 33370208} {"current_steps": 33160, "total_steps": 42420, "loss": 0.1551, "lr": 6.914781671318757e-06, "epoch": 15.634134842055634, "percentage": 78.17, "elapsed_time": "1:59:57", "remaining_time": "0:33:29", "throughput": 4636.94, "total_tokens": 33374656} {"current_steps": 33165, "total_steps": 42420, "loss": 0.0621, "lr": 6.907681538806507e-06, "epoch": 15.636492220650636, "percentage": 78.18, "elapsed_time": "1:59:58", "remaining_time": "0:33:28", "throughput": 4636.97, "total_tokens": 33380000} {"current_steps": 33170, "total_steps": 42420, "loss": 0.0762, "lr": 6.900584469016583e-06, "epoch": 15.638849599245638, "percentage": 78.19, "elapsed_time": "2:00:00", "remaining_time": "0:33:27", "throughput": 4637.01, "total_tokens": 33386688} {"current_steps": 33175, "total_steps": 42420, "loss": 0.1624, "lr": 6.893490463150407e-06, "epoch": 15.64120697784064, "percentage": 78.21, "elapsed_time": "2:00:01", "remaining_time": "0:33:26", "throughput": 4637.03, "total_tokens": 33392416} {"current_steps": 33180, "total_steps": 42420, "loss": 0.0929, "lr": 6.886399522408854e-06, "epoch": 15.643564356435643, "percentage": 78.22, "elapsed_time": "2:00:02", "remaining_time": "0:33:25", "throughput": 4637.03, "total_tokens": 33396416} {"current_steps": 33185, "total_steps": 42420, "loss": 0.055, "lr": 6.879311647992312e-06, "epoch": 15.645921735030646, "percentage": 78.23, "elapsed_time": "2:00:03", "remaining_time": "0:33:24", "throughput": 4637.02, "total_tokens": 33401024} {"current_steps": 33190, "total_steps": 42420, "loss": 0.025, "lr": 6.872226841100637e-06, "epoch": 15.648279113625648, "percentage": 78.24, "elapsed_time": "2:00:04", "remaining_time": "0:33:23", "throughput": 4637.05, "total_tokens": 33405888} {"current_steps": 33195, "total_steps": 42420, "loss": 0.2617, "lr": 6.865145102933165e-06, "epoch": 15.65063649222065, "percentage": 78.25, "elapsed_time": "2:00:05", "remaining_time": "0:33:22", "throughput": 4637.07, "total_tokens": 33410656} {"current_steps": 33200, "total_steps": 42420, "loss": 0.1041, "lr": 6.8580664346887145e-06, "epoch": 15.652993870815653, "percentage": 78.26, "elapsed_time": "2:00:06", "remaining_time": "0:33:21", "throughput": 4637.0, "total_tokens": 33414368} {"current_steps": 33205, "total_steps": 42420, "loss": 0.1845, "lr": 6.850990837565585e-06, "epoch": 15.655351249410655, "percentage": 78.28, "elapsed_time": "2:00:07", "remaining_time": "0:33:20", "throughput": 4637.01, "total_tokens": 33419776} {"current_steps": 33210, "total_steps": 42420, "loss": 0.1317, "lr": 6.843918312761555e-06, "epoch": 15.657708628005658, "percentage": 78.29, "elapsed_time": "2:00:08", "remaining_time": "0:33:19", "throughput": 4637.04, "total_tokens": 33425216} {"current_steps": 33215, "total_steps": 42420, "loss": 0.1353, "lr": 6.836848861473888e-06, "epoch": 15.66006600660066, "percentage": 78.3, "elapsed_time": "2:00:09", "remaining_time": "0:33:17", "throughput": 4637.06, "total_tokens": 33430432} {"current_steps": 33220, "total_steps": 42420, "loss": 0.0351, "lr": 6.829782484899308e-06, "epoch": 15.662423385195662, "percentage": 78.31, "elapsed_time": "2:00:10", "remaining_time": "0:33:16", "throughput": 4637.02, "total_tokens": 33434528} {"current_steps": 33225, "total_steps": 42420, "loss": 0.0264, "lr": 6.822719184234039e-06, "epoch": 15.664780763790665, "percentage": 78.32, "elapsed_time": "2:00:11", "remaining_time": "0:33:15", "throughput": 4637.02, "total_tokens": 33439488} {"current_steps": 33230, "total_steps": 42420, "loss": 0.1289, "lr": 6.815658960673782e-06, "epoch": 15.667138142385667, "percentage": 78.34, "elapsed_time": "2:00:12", "remaining_time": "0:33:14", "throughput": 4637.03, "total_tokens": 33444192} {"current_steps": 33235, "total_steps": 42420, "loss": 0.1337, "lr": 6.808601815413709e-06, "epoch": 15.66949552098067, "percentage": 78.35, "elapsed_time": "2:00:13", "remaining_time": "0:33:13", "throughput": 4637.03, "total_tokens": 33448416} {"current_steps": 33240, "total_steps": 42420, "loss": 0.0129, "lr": 6.8015477496484794e-06, "epoch": 15.671852899575672, "percentage": 78.36, "elapsed_time": "2:00:14", "remaining_time": "0:33:12", "throughput": 4637.05, "total_tokens": 33453440} {"current_steps": 33245, "total_steps": 42420, "loss": 0.1008, "lr": 6.7944967645722195e-06, "epoch": 15.674210278170674, "percentage": 78.37, "elapsed_time": "2:00:15", "remaining_time": "0:33:11", "throughput": 4637.08, "total_tokens": 33459168} {"current_steps": 33250, "total_steps": 42420, "loss": 0.2952, "lr": 6.787448861378548e-06, "epoch": 15.676567656765677, "percentage": 78.38, "elapsed_time": "2:00:16", "remaining_time": "0:33:10", "throughput": 4637.1, "total_tokens": 33464224} {"current_steps": 33255, "total_steps": 42420, "loss": 0.0964, "lr": 6.78040404126056e-06, "epoch": 15.67892503536068, "percentage": 78.39, "elapsed_time": "2:00:17", "remaining_time": "0:33:09", "throughput": 4637.07, "total_tokens": 33468416} {"current_steps": 33260, "total_steps": 42420, "loss": 0.137, "lr": 6.773362305410816e-06, "epoch": 15.681282413955682, "percentage": 78.41, "elapsed_time": "2:00:18", "remaining_time": "0:33:08", "throughput": 4637.12, "total_tokens": 33474336} {"current_steps": 33265, "total_steps": 42420, "loss": 0.016, "lr": 6.766323655021356e-06, "epoch": 15.683639792550684, "percentage": 78.42, "elapsed_time": "2:00:19", "remaining_time": "0:33:06", "throughput": 4637.14, "total_tokens": 33479104} {"current_steps": 33270, "total_steps": 42420, "loss": 0.2063, "lr": 6.759288091283711e-06, "epoch": 15.685997171145686, "percentage": 78.43, "elapsed_time": "2:00:20", "remaining_time": "0:33:05", "throughput": 4637.15, "total_tokens": 33484224} {"current_steps": 33275, "total_steps": 42420, "loss": 0.0615, "lr": 6.752255615388883e-06, "epoch": 15.688354549740689, "percentage": 78.44, "elapsed_time": "2:00:22", "remaining_time": "0:33:04", "throughput": 4637.2, "total_tokens": 33491328} {"current_steps": 33280, "total_steps": 42420, "loss": 0.0231, "lr": 6.745226228527348e-06, "epoch": 15.690711928335691, "percentage": 78.45, "elapsed_time": "2:00:23", "remaining_time": "0:33:03", "throughput": 4637.23, "total_tokens": 33496640} {"current_steps": 33285, "total_steps": 42420, "loss": 0.0523, "lr": 6.738199931889066e-06, "epoch": 15.693069306930694, "percentage": 78.47, "elapsed_time": "2:00:24", "remaining_time": "0:33:02", "throughput": 4637.23, "total_tokens": 33501248} {"current_steps": 33290, "total_steps": 42420, "loss": 0.1354, "lr": 6.731176726663469e-06, "epoch": 15.695426685525696, "percentage": 78.48, "elapsed_time": "2:00:25", "remaining_time": "0:33:01", "throughput": 4637.22, "total_tokens": 33506528} {"current_steps": 33295, "total_steps": 42420, "loss": 0.0511, "lr": 6.724156614039462e-06, "epoch": 15.697784064120698, "percentage": 78.49, "elapsed_time": "2:00:26", "remaining_time": "0:33:00", "throughput": 4637.23, "total_tokens": 33511232} {"current_steps": 33300, "total_steps": 42420, "loss": 0.1623, "lr": 6.717139595205443e-06, "epoch": 15.700141442715701, "percentage": 78.5, "elapsed_time": "2:00:27", "remaining_time": "0:32:59", "throughput": 4637.25, "total_tokens": 33515840} {"current_steps": 33305, "total_steps": 42420, "loss": 0.1254, "lr": 6.71012567134926e-06, "epoch": 15.702498821310703, "percentage": 78.51, "elapsed_time": "2:00:28", "remaining_time": "0:32:58", "throughput": 4637.28, "total_tokens": 33520704} {"current_steps": 33310, "total_steps": 42420, "loss": 0.0998, "lr": 6.703114843658254e-06, "epoch": 15.704856199905706, "percentage": 78.52, "elapsed_time": "2:00:29", "remaining_time": "0:32:57", "throughput": 4637.34, "total_tokens": 33527264} {"current_steps": 33315, "total_steps": 42420, "loss": 0.1507, "lr": 6.696107113319242e-06, "epoch": 15.707213578500706, "percentage": 78.54, "elapsed_time": "2:00:30", "remaining_time": "0:32:56", "throughput": 4637.36, "total_tokens": 33531584} {"current_steps": 33320, "total_steps": 42420, "loss": 0.0962, "lr": 6.689102481518514e-06, "epoch": 15.70957095709571, "percentage": 78.55, "elapsed_time": "2:00:31", "remaining_time": "0:32:55", "throughput": 4637.33, "total_tokens": 33535648} {"current_steps": 33325, "total_steps": 42420, "loss": 0.3897, "lr": 6.682100949441833e-06, "epoch": 15.711928335690711, "percentage": 78.56, "elapsed_time": "2:00:32", "remaining_time": "0:32:53", "throughput": 4637.36, "total_tokens": 33540928} {"current_steps": 33330, "total_steps": 42420, "loss": 0.0121, "lr": 6.675102518274443e-06, "epoch": 15.714285714285714, "percentage": 78.57, "elapsed_time": "2:00:33", "remaining_time": "0:32:52", "throughput": 4637.39, "total_tokens": 33545312} {"current_steps": 33335, "total_steps": 42420, "loss": 0.0855, "lr": 6.668107189201056e-06, "epoch": 15.716643092880716, "percentage": 78.58, "elapsed_time": "2:00:34", "remaining_time": "0:32:51", "throughput": 4637.41, "total_tokens": 33550496} {"current_steps": 33340, "total_steps": 42420, "loss": 0.0831, "lr": 6.661114963405871e-06, "epoch": 15.719000471475718, "percentage": 78.6, "elapsed_time": "2:00:35", "remaining_time": "0:32:50", "throughput": 4637.42, "total_tokens": 33555008} {"current_steps": 33345, "total_steps": 42420, "loss": 0.1528, "lr": 6.65412584207254e-06, "epoch": 15.72135785007072, "percentage": 78.61, "elapsed_time": "2:00:36", "remaining_time": "0:32:49", "throughput": 4637.4, "total_tokens": 33559104} {"current_steps": 33350, "total_steps": 42420, "loss": 0.0633, "lr": 6.647139826384208e-06, "epoch": 15.723715228665723, "percentage": 78.62, "elapsed_time": "2:00:37", "remaining_time": "0:32:48", "throughput": 4637.37, "total_tokens": 33563680} {"current_steps": 33355, "total_steps": 42420, "loss": 0.0665, "lr": 6.640156917523491e-06, "epoch": 15.726072607260726, "percentage": 78.63, "elapsed_time": "2:00:38", "remaining_time": "0:32:47", "throughput": 4637.38, "total_tokens": 33568064} {"current_steps": 33360, "total_steps": 42420, "loss": 0.1816, "lr": 6.633177116672473e-06, "epoch": 15.728429985855728, "percentage": 78.64, "elapsed_time": "2:00:39", "remaining_time": "0:32:46", "throughput": 4637.38, "total_tokens": 33573856} {"current_steps": 33365, "total_steps": 42420, "loss": 0.1747, "lr": 6.626200425012721e-06, "epoch": 15.73078736445073, "percentage": 78.65, "elapsed_time": "2:00:40", "remaining_time": "0:32:45", "throughput": 4637.42, "total_tokens": 33579328} {"current_steps": 33370, "total_steps": 42420, "loss": 0.1734, "lr": 6.619226843725265e-06, "epoch": 15.733144743045733, "percentage": 78.67, "elapsed_time": "2:00:41", "remaining_time": "0:32:44", "throughput": 4637.43, "total_tokens": 33583520} {"current_steps": 33375, "total_steps": 42420, "loss": 0.0753, "lr": 6.612256373990619e-06, "epoch": 15.735502121640735, "percentage": 78.68, "elapsed_time": "2:00:42", "remaining_time": "0:32:42", "throughput": 4637.47, "total_tokens": 33589152} {"current_steps": 33380, "total_steps": 42420, "loss": 0.2003, "lr": 6.605289016988761e-06, "epoch": 15.737859500235738, "percentage": 78.69, "elapsed_time": "2:00:43", "remaining_time": "0:32:41", "throughput": 4637.45, "total_tokens": 33593312} {"current_steps": 33385, "total_steps": 42420, "loss": 0.1925, "lr": 6.598324773899156e-06, "epoch": 15.74021687883074, "percentage": 78.7, "elapsed_time": "2:00:44", "remaining_time": "0:32:40", "throughput": 4637.46, "total_tokens": 33598016} {"current_steps": 33390, "total_steps": 42420, "loss": 0.0785, "lr": 6.591363645900719e-06, "epoch": 15.742574257425742, "percentage": 78.71, "elapsed_time": "2:00:45", "remaining_time": "0:32:39", "throughput": 4637.47, "total_tokens": 33602560} {"current_steps": 33395, "total_steps": 42420, "loss": 0.185, "lr": 6.584405634171853e-06, "epoch": 15.744931636020745, "percentage": 78.72, "elapsed_time": "2:00:46", "remaining_time": "0:32:38", "throughput": 4637.49, "total_tokens": 33607360} {"current_steps": 33400, "total_steps": 42420, "loss": 0.1164, "lr": 6.577450739890434e-06, "epoch": 15.747289014615747, "percentage": 78.74, "elapsed_time": "2:00:47", "remaining_time": "0:32:37", "throughput": 4637.47, "total_tokens": 33612224} {"current_steps": 33405, "total_steps": 42420, "loss": 0.0508, "lr": 6.570498964233809e-06, "epoch": 15.74964639321075, "percentage": 78.75, "elapsed_time": "2:00:48", "remaining_time": "0:32:36", "throughput": 4637.48, "total_tokens": 33617088} {"current_steps": 33410, "total_steps": 42420, "loss": 0.1725, "lr": 6.563550308378794e-06, "epoch": 15.752003771805752, "percentage": 78.76, "elapsed_time": "2:00:50", "remaining_time": "0:32:35", "throughput": 4637.53, "total_tokens": 33623264} {"current_steps": 33415, "total_steps": 42420, "loss": 0.1248, "lr": 6.556604773501679e-06, "epoch": 15.754361150400754, "percentage": 78.77, "elapsed_time": "2:00:51", "remaining_time": "0:32:34", "throughput": 4637.56, "total_tokens": 33627776} {"current_steps": 33420, "total_steps": 42420, "loss": 0.0953, "lr": 6.549662360778225e-06, "epoch": 15.756718528995757, "percentage": 78.78, "elapsed_time": "2:00:52", "remaining_time": "0:32:33", "throughput": 4637.57, "total_tokens": 33632416} {"current_steps": 33425, "total_steps": 42420, "loss": 0.0653, "lr": 6.542723071383672e-06, "epoch": 15.75907590759076, "percentage": 78.8, "elapsed_time": "2:00:53", "remaining_time": "0:32:31", "throughput": 4637.58, "total_tokens": 33637312} {"current_steps": 33430, "total_steps": 42420, "loss": 0.1651, "lr": 6.535786906492708e-06, "epoch": 15.761433286185762, "percentage": 78.81, "elapsed_time": "2:00:54", "remaining_time": "0:32:30", "throughput": 4637.61, "total_tokens": 33642528} {"current_steps": 33435, "total_steps": 42420, "loss": 0.1003, "lr": 6.5288538672795166e-06, "epoch": 15.763790664780764, "percentage": 78.82, "elapsed_time": "2:00:55", "remaining_time": "0:32:29", "throughput": 4637.61, "total_tokens": 33646912} {"current_steps": 33440, "total_steps": 42420, "loss": 0.0258, "lr": 6.521923954917741e-06, "epoch": 15.766148043375766, "percentage": 78.83, "elapsed_time": "2:00:56", "remaining_time": "0:32:28", "throughput": 4637.65, "total_tokens": 33652672} {"current_steps": 33445, "total_steps": 42420, "loss": 0.1443, "lr": 6.514997170580503e-06, "epoch": 15.768505421970769, "percentage": 78.84, "elapsed_time": "2:00:57", "remaining_time": "0:32:27", "throughput": 4637.68, "total_tokens": 33658336} {"current_steps": 33450, "total_steps": 42420, "loss": 0.1843, "lr": 6.508073515440385e-06, "epoch": 15.770862800565771, "percentage": 78.85, "elapsed_time": "2:00:58", "remaining_time": "0:32:26", "throughput": 4637.71, "total_tokens": 33663712} {"current_steps": 33455, "total_steps": 42420, "loss": 0.1303, "lr": 6.501152990669445e-06, "epoch": 15.773220179160774, "percentage": 78.87, "elapsed_time": "2:00:59", "remaining_time": "0:32:25", "throughput": 4637.74, "total_tokens": 33669280} {"current_steps": 33460, "total_steps": 42420, "loss": 0.1157, "lr": 6.4942355974392135e-06, "epoch": 15.775577557755776, "percentage": 78.88, "elapsed_time": "2:01:00", "remaining_time": "0:32:24", "throughput": 4637.75, "total_tokens": 33673600} {"current_steps": 33465, "total_steps": 42420, "loss": 0.0778, "lr": 6.48732133692069e-06, "epoch": 15.777934936350778, "percentage": 78.89, "elapsed_time": "2:01:01", "remaining_time": "0:32:23", "throughput": 4637.75, "total_tokens": 33677760} {"current_steps": 33470, "total_steps": 42420, "loss": 0.1128, "lr": 6.480410210284332e-06, "epoch": 15.78029231494578, "percentage": 78.9, "elapsed_time": "2:01:02", "remaining_time": "0:32:22", "throughput": 4637.78, "total_tokens": 33683008} {"current_steps": 33475, "total_steps": 42420, "loss": 0.0973, "lr": 6.473502218700081e-06, "epoch": 15.782649693540783, "percentage": 78.91, "elapsed_time": "2:01:03", "remaining_time": "0:32:20", "throughput": 4637.8, "total_tokens": 33687936} {"current_steps": 33480, "total_steps": 42420, "loss": 0.0742, "lr": 6.46659736333734e-06, "epoch": 15.785007072135786, "percentage": 78.93, "elapsed_time": "2:01:04", "remaining_time": "0:32:19", "throughput": 4637.77, "total_tokens": 33692352} {"current_steps": 33485, "total_steps": 42420, "loss": 0.1094, "lr": 6.459695645364994e-06, "epoch": 15.787364450730788, "percentage": 78.94, "elapsed_time": "2:01:05", "remaining_time": "0:32:18", "throughput": 4637.77, "total_tokens": 33697056} {"current_steps": 33490, "total_steps": 42420, "loss": 0.1441, "lr": 6.452797065951374e-06, "epoch": 15.78972182932579, "percentage": 78.95, "elapsed_time": "2:01:06", "remaining_time": "0:32:17", "throughput": 4637.77, "total_tokens": 33701536} {"current_steps": 33495, "total_steps": 42420, "loss": 0.0577, "lr": 6.445901626264295e-06, "epoch": 15.792079207920793, "percentage": 78.96, "elapsed_time": "2:01:07", "remaining_time": "0:32:16", "throughput": 4637.8, "total_tokens": 33707104} {"current_steps": 33500, "total_steps": 42420, "loss": 0.0826, "lr": 6.439009327471038e-06, "epoch": 15.794436586515795, "percentage": 78.97, "elapsed_time": "2:01:09", "remaining_time": "0:32:15", "throughput": 4637.82, "total_tokens": 33712352} {"current_steps": 33505, "total_steps": 42420, "loss": 0.1062, "lr": 6.432120170738357e-06, "epoch": 15.796793965110798, "percentage": 78.98, "elapsed_time": "2:01:10", "remaining_time": "0:32:14", "throughput": 4637.84, "total_tokens": 33718176} {"current_steps": 33510, "total_steps": 42420, "loss": 0.0879, "lr": 6.425234157232473e-06, "epoch": 15.799151343705798, "percentage": 79.0, "elapsed_time": "2:01:11", "remaining_time": "0:32:13", "throughput": 4637.85, "total_tokens": 33724064} {"current_steps": 33515, "total_steps": 42420, "loss": 0.095, "lr": 6.418351288119057e-06, "epoch": 15.801508722300802, "percentage": 79.01, "elapsed_time": "2:01:12", "remaining_time": "0:32:12", "throughput": 4637.87, "total_tokens": 33728640} {"current_steps": 33520, "total_steps": 42420, "loss": 0.0553, "lr": 6.41147156456327e-06, "epoch": 15.803866100895803, "percentage": 79.02, "elapsed_time": "2:01:13", "remaining_time": "0:32:11", "throughput": 4637.86, "total_tokens": 33733472} {"current_steps": 33525, "total_steps": 42420, "loss": 0.1827, "lr": 6.404594987729731e-06, "epoch": 15.806223479490805, "percentage": 79.03, "elapsed_time": "2:01:14", "remaining_time": "0:32:10", "throughput": 4637.85, "total_tokens": 33738240} {"current_steps": 33530, "total_steps": 42420, "loss": 0.132, "lr": 6.39772155878253e-06, "epoch": 15.808580858085808, "percentage": 79.04, "elapsed_time": "2:01:15", "remaining_time": "0:32:09", "throughput": 4637.87, "total_tokens": 33743392} {"current_steps": 33535, "total_steps": 42420, "loss": 0.1207, "lr": 6.390851278885221e-06, "epoch": 15.81093823668081, "percentage": 79.05, "elapsed_time": "2:01:16", "remaining_time": "0:32:07", "throughput": 4637.85, "total_tokens": 33747776} {"current_steps": 33540, "total_steps": 42420, "loss": 0.118, "lr": 6.383984149200822e-06, "epoch": 15.813295615275813, "percentage": 79.07, "elapsed_time": "2:01:17", "remaining_time": "0:32:06", "throughput": 4637.84, "total_tokens": 33752576} {"current_steps": 33545, "total_steps": 42420, "loss": 0.129, "lr": 6.377120170891829e-06, "epoch": 15.815652993870815, "percentage": 79.08, "elapsed_time": "2:01:18", "remaining_time": "0:32:05", "throughput": 4637.84, "total_tokens": 33757472} {"current_steps": 33550, "total_steps": 42420, "loss": 0.1905, "lr": 6.3702593451201966e-06, "epoch": 15.818010372465817, "percentage": 79.09, "elapsed_time": "2:01:19", "remaining_time": "0:32:04", "throughput": 4637.84, "total_tokens": 33762272} {"current_steps": 33555, "total_steps": 42420, "loss": 0.0259, "lr": 6.363401673047334e-06, "epoch": 15.82036775106082, "percentage": 79.1, "elapsed_time": "2:01:20", "remaining_time": "0:32:03", "throughput": 4637.83, "total_tokens": 33766592} {"current_steps": 33560, "total_steps": 42420, "loss": 0.0709, "lr": 6.356547155834139e-06, "epoch": 15.822725129655822, "percentage": 79.11, "elapsed_time": "2:01:21", "remaining_time": "0:32:02", "throughput": 4637.83, "total_tokens": 33771808} {"current_steps": 33565, "total_steps": 42420, "loss": 0.091, "lr": 6.349695794640961e-06, "epoch": 15.825082508250825, "percentage": 79.13, "elapsed_time": "2:01:22", "remaining_time": "0:32:01", "throughput": 4637.86, "total_tokens": 33777408} {"current_steps": 33570, "total_steps": 42420, "loss": 0.0392, "lr": 6.342847590627623e-06, "epoch": 15.827439886845827, "percentage": 79.14, "elapsed_time": "2:01:23", "remaining_time": "0:32:00", "throughput": 4637.83, "total_tokens": 33781600} {"current_steps": 33575, "total_steps": 42420, "loss": 0.1344, "lr": 6.336002544953407e-06, "epoch": 15.82979726544083, "percentage": 79.15, "elapsed_time": "2:01:24", "remaining_time": "0:31:59", "throughput": 4637.83, "total_tokens": 33786112} {"current_steps": 33580, "total_steps": 42420, "loss": 0.2009, "lr": 6.329160658777061e-06, "epoch": 15.832154644035832, "percentage": 79.16, "elapsed_time": "2:01:25", "remaining_time": "0:31:58", "throughput": 4637.85, "total_tokens": 33791232} {"current_steps": 33585, "total_steps": 42420, "loss": 0.1324, "lr": 6.322321933256805e-06, "epoch": 15.834512022630834, "percentage": 79.17, "elapsed_time": "2:01:27", "remaining_time": "0:31:56", "throughput": 4637.85, "total_tokens": 33796544} {"current_steps": 33590, "total_steps": 42420, "loss": 0.0793, "lr": 6.315486369550322e-06, "epoch": 15.836869401225837, "percentage": 79.18, "elapsed_time": "2:01:28", "remaining_time": "0:31:55", "throughput": 4637.88, "total_tokens": 33801920} {"current_steps": 33595, "total_steps": 42420, "loss": 0.1327, "lr": 6.308653968814746e-06, "epoch": 15.839226779820839, "percentage": 79.2, "elapsed_time": "2:01:29", "remaining_time": "0:31:54", "throughput": 4637.89, "total_tokens": 33806624} {"current_steps": 33600, "total_steps": 42420, "loss": 0.0291, "lr": 6.301824732206693e-06, "epoch": 15.841584158415841, "percentage": 79.21, "elapsed_time": "2:01:30", "remaining_time": "0:31:53", "throughput": 4637.93, "total_tokens": 33811744} {"current_steps": 33605, "total_steps": 42420, "loss": 0.1667, "lr": 6.2949986608822345e-06, "epoch": 15.843941537010844, "percentage": 79.22, "elapsed_time": "2:01:31", "remaining_time": "0:31:52", "throughput": 4637.96, "total_tokens": 33816832} {"current_steps": 33610, "total_steps": 42420, "loss": 0.0863, "lr": 6.288175755996911e-06, "epoch": 15.846298915605846, "percentage": 79.23, "elapsed_time": "2:01:32", "remaining_time": "0:31:51", "throughput": 4638.0, "total_tokens": 33822464} {"current_steps": 33615, "total_steps": 42420, "loss": 0.1802, "lr": 6.2813560187057225e-06, "epoch": 15.848656294200849, "percentage": 79.24, "elapsed_time": "2:01:33", "remaining_time": "0:31:50", "throughput": 4638.01, "total_tokens": 33826560} {"current_steps": 33620, "total_steps": 42420, "loss": 0.0661, "lr": 6.274539450163133e-06, "epoch": 15.851013672795851, "percentage": 79.26, "elapsed_time": "2:01:34", "remaining_time": "0:31:49", "throughput": 4638.03, "total_tokens": 33831072} {"current_steps": 33625, "total_steps": 42420, "loss": 0.0063, "lr": 6.267726051523079e-06, "epoch": 15.853371051390853, "percentage": 79.27, "elapsed_time": "2:01:35", "remaining_time": "0:31:48", "throughput": 4638.05, "total_tokens": 33836032} {"current_steps": 33630, "total_steps": 42420, "loss": 0.0389, "lr": 6.260915823938954e-06, "epoch": 15.855728429985856, "percentage": 79.28, "elapsed_time": "2:01:36", "remaining_time": "0:31:47", "throughput": 4638.1, "total_tokens": 33841824} {"current_steps": 33635, "total_steps": 42420, "loss": 0.1512, "lr": 6.254108768563599e-06, "epoch": 15.858085808580858, "percentage": 79.29, "elapsed_time": "2:01:37", "remaining_time": "0:31:45", "throughput": 4638.11, "total_tokens": 33846016} {"current_steps": 33640, "total_steps": 42420, "loss": 0.1231, "lr": 6.247304886549346e-06, "epoch": 15.86044318717586, "percentage": 79.3, "elapsed_time": "2:01:38", "remaining_time": "0:31:44", "throughput": 4638.15, "total_tokens": 33851456} {"current_steps": 33645, "total_steps": 42420, "loss": 0.1587, "lr": 6.240504179047971e-06, "epoch": 15.862800565770863, "percentage": 79.31, "elapsed_time": "2:01:39", "remaining_time": "0:31:43", "throughput": 4638.18, "total_tokens": 33857024} {"current_steps": 33650, "total_steps": 42420, "loss": 0.0797, "lr": 6.233706647210722e-06, "epoch": 15.865157944365865, "percentage": 79.33, "elapsed_time": "2:01:40", "remaining_time": "0:31:42", "throughput": 4638.2, "total_tokens": 33861952} {"current_steps": 33655, "total_steps": 42420, "loss": 0.1247, "lr": 6.2269122921883e-06, "epoch": 15.867515322960868, "percentage": 79.34, "elapsed_time": "2:01:41", "remaining_time": "0:31:41", "throughput": 4638.22, "total_tokens": 33866432} {"current_steps": 33660, "total_steps": 42420, "loss": 0.1628, "lr": 6.2201211151308806e-06, "epoch": 15.86987270155587, "percentage": 79.35, "elapsed_time": "2:01:42", "remaining_time": "0:31:40", "throughput": 4638.23, "total_tokens": 33871104} {"current_steps": 33665, "total_steps": 42420, "loss": 0.2646, "lr": 6.213333117188095e-06, "epoch": 15.872230080150873, "percentage": 79.36, "elapsed_time": "2:01:43", "remaining_time": "0:31:39", "throughput": 4638.25, "total_tokens": 33875840} {"current_steps": 33670, "total_steps": 42420, "loss": 0.1691, "lr": 6.206548299509038e-06, "epoch": 15.874587458745875, "percentage": 79.37, "elapsed_time": "2:01:44", "remaining_time": "0:31:38", "throughput": 4638.27, "total_tokens": 33880928} {"current_steps": 33675, "total_steps": 42420, "loss": 0.1904, "lr": 6.199766663242252e-06, "epoch": 15.876944837340877, "percentage": 79.38, "elapsed_time": "2:01:45", "remaining_time": "0:31:37", "throughput": 4638.29, "total_tokens": 33887168} {"current_steps": 33680, "total_steps": 42420, "loss": 0.0893, "lr": 6.192988209535757e-06, "epoch": 15.87930221593588, "percentage": 79.4, "elapsed_time": "2:01:46", "remaining_time": "0:31:36", "throughput": 4638.31, "total_tokens": 33891744} {"current_steps": 33685, "total_steps": 42420, "loss": 0.1326, "lr": 6.186212939537039e-06, "epoch": 15.881659594530882, "percentage": 79.41, "elapsed_time": "2:01:48", "remaining_time": "0:31:35", "throughput": 4638.33, "total_tokens": 33896960} {"current_steps": 33690, "total_steps": 42420, "loss": 0.1224, "lr": 6.179440854393026e-06, "epoch": 15.884016973125885, "percentage": 79.42, "elapsed_time": "2:01:48", "remaining_time": "0:31:33", "throughput": 4638.32, "total_tokens": 33901152} {"current_steps": 33695, "total_steps": 42420, "loss": 0.2039, "lr": 6.172671955250126e-06, "epoch": 15.886374351720887, "percentage": 79.43, "elapsed_time": "2:01:49", "remaining_time": "0:31:32", "throughput": 4638.32, "total_tokens": 33905440} {"current_steps": 33700, "total_steps": 42420, "loss": 0.0856, "lr": 6.165906243254191e-06, "epoch": 15.88873173031589, "percentage": 79.44, "elapsed_time": "2:01:50", "remaining_time": "0:31:31", "throughput": 4638.33, "total_tokens": 33910464} {"current_steps": 33705, "total_steps": 42420, "loss": 0.2945, "lr": 6.159143719550542e-06, "epoch": 15.891089108910892, "percentage": 79.46, "elapsed_time": "2:01:51", "remaining_time": "0:31:30", "throughput": 4638.34, "total_tokens": 33914944} {"current_steps": 33710, "total_steps": 42420, "loss": 0.1919, "lr": 6.152384385283974e-06, "epoch": 15.893446487505894, "percentage": 79.47, "elapsed_time": "2:01:52", "remaining_time": "0:31:29", "throughput": 4638.34, "total_tokens": 33919616} {"current_steps": 33715, "total_steps": 42420, "loss": 0.1218, "lr": 6.145628241598705e-06, "epoch": 15.895803866100895, "percentage": 79.48, "elapsed_time": "2:01:53", "remaining_time": "0:31:28", "throughput": 4638.31, "total_tokens": 33923808} {"current_steps": 33720, "total_steps": 42420, "loss": 0.0703, "lr": 6.138875289638455e-06, "epoch": 15.898161244695899, "percentage": 79.49, "elapsed_time": "2:01:54", "remaining_time": "0:31:27", "throughput": 4638.33, "total_tokens": 33928192} {"current_steps": 33725, "total_steps": 42420, "loss": 0.0799, "lr": 6.132125530546365e-06, "epoch": 15.9005186232909, "percentage": 79.5, "elapsed_time": "2:01:55", "remaining_time": "0:31:26", "throughput": 4638.36, "total_tokens": 33933632} {"current_steps": 33730, "total_steps": 42420, "loss": 0.08, "lr": 6.125378965465065e-06, "epoch": 15.902876001885902, "percentage": 79.51, "elapsed_time": "2:01:56", "remaining_time": "0:31:25", "throughput": 4638.39, "total_tokens": 33938880} {"current_steps": 33735, "total_steps": 42420, "loss": 0.1393, "lr": 6.118635595536634e-06, "epoch": 15.905233380480905, "percentage": 79.53, "elapsed_time": "2:01:58", "remaining_time": "0:31:24", "throughput": 4638.43, "total_tokens": 33944896} {"current_steps": 33740, "total_steps": 42420, "loss": 0.0737, "lr": 6.111895421902608e-06, "epoch": 15.907590759075907, "percentage": 79.54, "elapsed_time": "2:01:59", "remaining_time": "0:31:22", "throughput": 4638.45, "total_tokens": 33949760} {"current_steps": 33745, "total_steps": 42420, "loss": 0.03, "lr": 6.105158445703987e-06, "epoch": 15.90994813767091, "percentage": 79.55, "elapsed_time": "2:02:00", "remaining_time": "0:31:21", "throughput": 4638.51, "total_tokens": 33955712} {"current_steps": 33750, "total_steps": 42420, "loss": 0.1801, "lr": 6.098424668081226e-06, "epoch": 15.912305516265912, "percentage": 79.56, "elapsed_time": "2:02:01", "remaining_time": "0:31:20", "throughput": 4638.52, "total_tokens": 33960064} {"current_steps": 33755, "total_steps": 42420, "loss": 0.2589, "lr": 6.0916940901742355e-06, "epoch": 15.914662894860914, "percentage": 79.57, "elapsed_time": "2:02:02", "remaining_time": "0:31:19", "throughput": 4638.5, "total_tokens": 33964960} {"current_steps": 33760, "total_steps": 42420, "loss": 0.0431, "lr": 6.0849667131224005e-06, "epoch": 15.917020273455917, "percentage": 79.59, "elapsed_time": "2:02:03", "remaining_time": "0:31:18", "throughput": 4638.52, "total_tokens": 33970176} {"current_steps": 33765, "total_steps": 42420, "loss": 0.128, "lr": 6.0782425380645325e-06, "epoch": 15.919377652050919, "percentage": 79.6, "elapsed_time": "2:02:04", "remaining_time": "0:31:17", "throughput": 4638.49, "total_tokens": 33974592} {"current_steps": 33770, "total_steps": 42420, "loss": 0.242, "lr": 6.071521566138929e-06, "epoch": 15.921735030645921, "percentage": 79.61, "elapsed_time": "2:02:05", "remaining_time": "0:31:16", "throughput": 4638.44, "total_tokens": 33978560} {"current_steps": 33775, "total_steps": 42420, "loss": 0.0316, "lr": 6.06480379848334e-06, "epoch": 15.924092409240924, "percentage": 79.62, "elapsed_time": "2:02:06", "remaining_time": "0:31:15", "throughput": 4638.46, "total_tokens": 33983584} {"current_steps": 33780, "total_steps": 42420, "loss": 0.0811, "lr": 6.058089236234965e-06, "epoch": 15.926449787835926, "percentage": 79.63, "elapsed_time": "2:02:07", "remaining_time": "0:31:14", "throughput": 4638.5, "total_tokens": 33990624} {"current_steps": 33785, "total_steps": 42420, "loss": 0.286, "lr": 6.0513778805304675e-06, "epoch": 15.928807166430929, "percentage": 79.64, "elapsed_time": "2:02:08", "remaining_time": "0:31:13", "throughput": 4638.47, "total_tokens": 33995296} {"current_steps": 33790, "total_steps": 42420, "loss": 0.2555, "lr": 6.044669732505967e-06, "epoch": 15.931164545025931, "percentage": 79.66, "elapsed_time": "2:02:09", "remaining_time": "0:31:12", "throughput": 4638.46, "total_tokens": 33999840} {"current_steps": 33795, "total_steps": 42420, "loss": 0.0226, "lr": 6.037964793297035e-06, "epoch": 15.933521923620933, "percentage": 79.67, "elapsed_time": "2:02:11", "remaining_time": "0:31:10", "throughput": 4638.48, "total_tokens": 34004768} {"current_steps": 33800, "total_steps": 42420, "loss": 0.0946, "lr": 6.0312630640387145e-06, "epoch": 15.935879302215936, "percentage": 79.68, "elapsed_time": "2:02:11", "remaining_time": "0:31:09", "throughput": 4638.49, "total_tokens": 34009120} {"current_steps": 33805, "total_steps": 42420, "loss": 0.1176, "lr": 6.02456454586548e-06, "epoch": 15.938236680810938, "percentage": 79.69, "elapsed_time": "2:02:13", "remaining_time": "0:31:08", "throughput": 4638.53, "total_tokens": 34014752} {"current_steps": 33810, "total_steps": 42420, "loss": 0.0407, "lr": 6.017869239911281e-06, "epoch": 15.94059405940594, "percentage": 79.7, "elapsed_time": "2:02:14", "remaining_time": "0:31:07", "throughput": 4638.56, "total_tokens": 34019616} {"current_steps": 33815, "total_steps": 42420, "loss": 0.1018, "lr": 6.011177147309524e-06, "epoch": 15.942951438000943, "percentage": 79.71, "elapsed_time": "2:02:14", "remaining_time": "0:31:06", "throughput": 4638.55, "total_tokens": 34023680} {"current_steps": 33820, "total_steps": 42420, "loss": 0.1678, "lr": 6.004488269193062e-06, "epoch": 15.945308816595945, "percentage": 79.73, "elapsed_time": "2:02:16", "remaining_time": "0:31:05", "throughput": 4638.6, "total_tokens": 34029760} {"current_steps": 33825, "total_steps": 42420, "loss": 0.1801, "lr": 5.997802606694214e-06, "epoch": 15.947666195190948, "percentage": 79.74, "elapsed_time": "2:02:17", "remaining_time": "0:31:04", "throughput": 4638.61, "total_tokens": 34034208} {"current_steps": 33830, "total_steps": 42420, "loss": 0.1322, "lr": 5.991120160944744e-06, "epoch": 15.95002357378595, "percentage": 79.75, "elapsed_time": "2:02:18", "remaining_time": "0:31:03", "throughput": 4638.59, "total_tokens": 34038880} {"current_steps": 33835, "total_steps": 42420, "loss": 0.121, "lr": 5.984440933075877e-06, "epoch": 15.952380952380953, "percentage": 79.76, "elapsed_time": "2:02:19", "remaining_time": "0:31:02", "throughput": 4638.61, "total_tokens": 34043712} {"current_steps": 33840, "total_steps": 42420, "loss": 0.171, "lr": 5.9777649242183016e-06, "epoch": 15.954738330975955, "percentage": 79.77, "elapsed_time": "2:02:20", "remaining_time": "0:31:01", "throughput": 4638.62, "total_tokens": 34048160} {"current_steps": 33845, "total_steps": 42420, "loss": 0.0625, "lr": 5.97109213550214e-06, "epoch": 15.957095709570957, "percentage": 79.79, "elapsed_time": "2:02:21", "remaining_time": "0:30:59", "throughput": 4638.6, "total_tokens": 34053216} {"current_steps": 33850, "total_steps": 42420, "loss": 0.1164, "lr": 5.964422568056985e-06, "epoch": 15.95945308816596, "percentage": 79.8, "elapsed_time": "2:02:22", "remaining_time": "0:30:58", "throughput": 4638.62, "total_tokens": 34057664} {"current_steps": 33855, "total_steps": 42420, "loss": 0.241, "lr": 5.957756223011885e-06, "epoch": 15.961810466760962, "percentage": 79.81, "elapsed_time": "2:02:23", "remaining_time": "0:30:57", "throughput": 4638.6, "total_tokens": 34061504} {"current_steps": 33860, "total_steps": 42420, "loss": 0.1148, "lr": 5.951093101495336e-06, "epoch": 15.964167845355965, "percentage": 79.82, "elapsed_time": "2:02:23", "remaining_time": "0:30:56", "throughput": 4638.61, "total_tokens": 34065952} {"current_steps": 33865, "total_steps": 42420, "loss": 0.0913, "lr": 5.944433204635297e-06, "epoch": 15.966525223950967, "percentage": 79.83, "elapsed_time": "2:02:24", "remaining_time": "0:30:55", "throughput": 4638.59, "total_tokens": 34070336} {"current_steps": 33870, "total_steps": 42420, "loss": 0.0334, "lr": 5.937776533559167e-06, "epoch": 15.96888260254597, "percentage": 79.84, "elapsed_time": "2:02:25", "remaining_time": "0:30:54", "throughput": 4638.61, "total_tokens": 34074656} {"current_steps": 33875, "total_steps": 42420, "loss": 0.0902, "lr": 5.9311230893938145e-06, "epoch": 15.971239981140972, "percentage": 79.86, "elapsed_time": "2:02:26", "remaining_time": "0:30:53", "throughput": 4638.63, "total_tokens": 34079456} {"current_steps": 33880, "total_steps": 42420, "loss": 0.1919, "lr": 5.9244728732655575e-06, "epoch": 15.973597359735974, "percentage": 79.87, "elapsed_time": "2:02:27", "remaining_time": "0:30:52", "throughput": 4638.63, "total_tokens": 34083680} {"current_steps": 33885, "total_steps": 42420, "loss": 0.0905, "lr": 5.917825886300152e-06, "epoch": 15.975954738330977, "percentage": 79.88, "elapsed_time": "2:02:28", "remaining_time": "0:30:51", "throughput": 4638.65, "total_tokens": 34088448} {"current_steps": 33890, "total_steps": 42420, "loss": 0.1022, "lr": 5.911182129622828e-06, "epoch": 15.978312116925979, "percentage": 79.89, "elapsed_time": "2:02:29", "remaining_time": "0:30:49", "throughput": 4638.6, "total_tokens": 34092352} {"current_steps": 33895, "total_steps": 42420, "loss": 0.039, "lr": 5.904541604358257e-06, "epoch": 15.980669495520981, "percentage": 79.9, "elapsed_time": "2:02:30", "remaining_time": "0:30:48", "throughput": 4638.56, "total_tokens": 34097376} {"current_steps": 33900, "total_steps": 42420, "loss": 0.1427, "lr": 5.897904311630573e-06, "epoch": 15.983026874115984, "percentage": 79.92, "elapsed_time": "2:02:31", "remaining_time": "0:30:47", "throughput": 4638.59, "total_tokens": 34102880} {"current_steps": 33905, "total_steps": 42420, "loss": 0.0833, "lr": 5.891270252563352e-06, "epoch": 15.985384252710986, "percentage": 79.93, "elapsed_time": "2:02:32", "remaining_time": "0:30:46", "throughput": 4638.6, "total_tokens": 34107488} {"current_steps": 33910, "total_steps": 42420, "loss": 0.0768, "lr": 5.884639428279632e-06, "epoch": 15.987741631305987, "percentage": 79.94, "elapsed_time": "2:02:33", "remaining_time": "0:30:45", "throughput": 4638.6, "total_tokens": 34111520} {"current_steps": 33915, "total_steps": 42420, "loss": 0.0295, "lr": 5.878011839901895e-06, "epoch": 15.990099009900991, "percentage": 79.95, "elapsed_time": "2:02:34", "remaining_time": "0:30:44", "throughput": 4638.63, "total_tokens": 34116640} {"current_steps": 33920, "total_steps": 42420, "loss": 0.0983, "lr": 5.871387488552088e-06, "epoch": 15.992456388495992, "percentage": 79.96, "elapsed_time": "2:02:36", "remaining_time": "0:30:43", "throughput": 4638.67, "total_tokens": 34122432} {"current_steps": 33925, "total_steps": 42420, "loss": 0.1305, "lr": 5.8647663753515854e-06, "epoch": 15.994813767090994, "percentage": 79.97, "elapsed_time": "2:02:37", "remaining_time": "0:30:42", "throughput": 4638.71, "total_tokens": 34127360} {"current_steps": 33930, "total_steps": 42420, "loss": 0.0974, "lr": 5.85814850142124e-06, "epoch": 15.997171145685996, "percentage": 79.99, "elapsed_time": "2:02:38", "remaining_time": "0:30:41", "throughput": 4638.76, "total_tokens": 34133376} {"current_steps": 33935, "total_steps": 42420, "loss": 0.0928, "lr": 5.851533867881348e-06, "epoch": 15.999528524280999, "percentage": 80.0, "elapsed_time": "2:02:39", "remaining_time": "0:30:40", "throughput": 4638.74, "total_tokens": 34137120} {"current_steps": 33936, "total_steps": 42420, "eval_loss": 0.1536126285791397, "epoch": 16.0, "percentage": 80.0, "elapsed_time": "2:02:54", "remaining_time": "0:30:43", "throughput": 4629.14, "total_tokens": 34138272} {"current_steps": 33940, "total_steps": 42420, "loss": 0.0461, "lr": 5.844922475851644e-06, "epoch": 16.001885902876, "percentage": 80.01, "elapsed_time": "2:02:57", "remaining_time": "0:30:43", "throughput": 4627.95, "total_tokens": 34142944} {"current_steps": 33945, "total_steps": 42420, "loss": 0.0548, "lr": 5.83831432645133e-06, "epoch": 16.004243281471005, "percentage": 80.02, "elapsed_time": "2:02:58", "remaining_time": "0:30:42", "throughput": 4627.98, "total_tokens": 34147552} {"current_steps": 33950, "total_steps": 42420, "loss": 0.118, "lr": 5.831709420799053e-06, "epoch": 16.006600660066006, "percentage": 80.03, "elapsed_time": "2:02:59", "remaining_time": "0:30:41", "throughput": 4627.95, "total_tokens": 34151296} {"current_steps": 33955, "total_steps": 42420, "loss": 0.0763, "lr": 5.825107760012913e-06, "epoch": 16.00895803866101, "percentage": 80.04, "elapsed_time": "2:03:00", "remaining_time": "0:30:39", "throughput": 4627.88, "total_tokens": 34155424} {"current_steps": 33960, "total_steps": 42420, "loss": 0.0197, "lr": 5.818509345210457e-06, "epoch": 16.01131541725601, "percentage": 80.06, "elapsed_time": "2:03:01", "remaining_time": "0:30:38", "throughput": 4627.9, "total_tokens": 34160736} {"current_steps": 33965, "total_steps": 42420, "loss": 0.0148, "lr": 5.811914177508684e-06, "epoch": 16.013672795851015, "percentage": 80.07, "elapsed_time": "2:03:02", "remaining_time": "0:30:37", "throughput": 4627.92, "total_tokens": 34165248} {"current_steps": 33970, "total_steps": 42420, "loss": 0.2167, "lr": 5.805322258024057e-06, "epoch": 16.016030174446016, "percentage": 80.08, "elapsed_time": "2:03:03", "remaining_time": "0:30:36", "throughput": 4627.94, "total_tokens": 34170880} {"current_steps": 33975, "total_steps": 42420, "loss": 0.0911, "lr": 5.798733587872454e-06, "epoch": 16.01838755304102, "percentage": 80.09, "elapsed_time": "2:03:04", "remaining_time": "0:30:35", "throughput": 4627.94, "total_tokens": 34175296} {"current_steps": 33980, "total_steps": 42420, "loss": 0.0604, "lr": 5.7921481681692366e-06, "epoch": 16.02074493163602, "percentage": 80.1, "elapsed_time": "2:03:05", "remaining_time": "0:30:34", "throughput": 4627.98, "total_tokens": 34180768} {"current_steps": 33985, "total_steps": 42420, "loss": 0.0747, "lr": 5.785566000029205e-06, "epoch": 16.023102310231025, "percentage": 80.12, "elapsed_time": "2:03:06", "remaining_time": "0:30:33", "throughput": 4628.02, "total_tokens": 34185888} {"current_steps": 33990, "total_steps": 42420, "loss": 0.047, "lr": 5.778987084566606e-06, "epoch": 16.025459688826025, "percentage": 80.13, "elapsed_time": "2:03:07", "remaining_time": "0:30:32", "throughput": 4628.05, "total_tokens": 34190752} {"current_steps": 33995, "total_steps": 42420, "loss": 0.1609, "lr": 5.772411422895138e-06, "epoch": 16.02781706742103, "percentage": 80.14, "elapsed_time": "2:03:08", "remaining_time": "0:30:31", "throughput": 4628.08, "total_tokens": 34196320} {"current_steps": 34000, "total_steps": 42420, "loss": 0.196, "lr": 5.765839016127953e-06, "epoch": 16.03017444601603, "percentage": 80.15, "elapsed_time": "2:03:09", "remaining_time": "0:30:30", "throughput": 4628.07, "total_tokens": 34200832} {"current_steps": 34005, "total_steps": 42420, "loss": 0.1611, "lr": 5.759269865377642e-06, "epoch": 16.032531824611034, "percentage": 80.16, "elapsed_time": "2:03:11", "remaining_time": "0:30:29", "throughput": 4628.11, "total_tokens": 34206816} {"current_steps": 34010, "total_steps": 42420, "loss": 0.1998, "lr": 5.7527039717562625e-06, "epoch": 16.034889203206035, "percentage": 80.17, "elapsed_time": "2:03:12", "remaining_time": "0:30:27", "throughput": 4628.13, "total_tokens": 34211744} {"current_steps": 34015, "total_steps": 42420, "loss": 0.1931, "lr": 5.746141336375294e-06, "epoch": 16.03724658180104, "percentage": 80.19, "elapsed_time": "2:03:13", "remaining_time": "0:30:26", "throughput": 4628.18, "total_tokens": 34217024} {"current_steps": 34020, "total_steps": 42420, "loss": 0.0818, "lr": 5.739581960345683e-06, "epoch": 16.03960396039604, "percentage": 80.2, "elapsed_time": "2:03:14", "remaining_time": "0:30:25", "throughput": 4628.2, "total_tokens": 34222208} {"current_steps": 34025, "total_steps": 42420, "loss": 0.198, "lr": 5.733025844777825e-06, "epoch": 16.04196133899104, "percentage": 80.21, "elapsed_time": "2:03:15", "remaining_time": "0:30:24", "throughput": 4628.24, "total_tokens": 34228416} {"current_steps": 34030, "total_steps": 42420, "loss": 0.0411, "lr": 5.726472990781556e-06, "epoch": 16.044318717586044, "percentage": 80.22, "elapsed_time": "2:03:16", "remaining_time": "0:30:23", "throughput": 4628.21, "total_tokens": 34232544} {"current_steps": 34035, "total_steps": 42420, "loss": 0.0268, "lr": 5.719923399466165e-06, "epoch": 16.046676096181045, "percentage": 80.23, "elapsed_time": "2:03:17", "remaining_time": "0:30:22", "throughput": 4628.23, "total_tokens": 34236992} {"current_steps": 34040, "total_steps": 42420, "loss": 0.0341, "lr": 5.713377071940384e-06, "epoch": 16.04903347477605, "percentage": 80.25, "elapsed_time": "2:03:18", "remaining_time": "0:30:21", "throughput": 4628.27, "total_tokens": 34243168} {"current_steps": 34045, "total_steps": 42420, "loss": 0.1859, "lr": 5.706834009312398e-06, "epoch": 16.05139085337105, "percentage": 80.26, "elapsed_time": "2:03:19", "remaining_time": "0:30:20", "throughput": 4628.29, "total_tokens": 34248416} {"current_steps": 34050, "total_steps": 42420, "loss": 0.025, "lr": 5.700294212689838e-06, "epoch": 16.053748231966054, "percentage": 80.27, "elapsed_time": "2:03:20", "remaining_time": "0:30:19", "throughput": 4628.3, "total_tokens": 34253280} {"current_steps": 34055, "total_steps": 42420, "loss": 0.0671, "lr": 5.693757683179774e-06, "epoch": 16.056105610561055, "percentage": 80.28, "elapsed_time": "2:03:21", "remaining_time": "0:30:18", "throughput": 4628.29, "total_tokens": 34257952} {"current_steps": 34060, "total_steps": 42420, "loss": 0.1571, "lr": 5.6872244218887314e-06, "epoch": 16.05846298915606, "percentage": 80.29, "elapsed_time": "2:03:22", "remaining_time": "0:30:17", "throughput": 4628.32, "total_tokens": 34262944} {"current_steps": 34065, "total_steps": 42420, "loss": 0.0463, "lr": 5.680694429922684e-06, "epoch": 16.06082036775106, "percentage": 80.3, "elapsed_time": "2:03:24", "remaining_time": "0:30:15", "throughput": 4628.35, "total_tokens": 34268416} {"current_steps": 34070, "total_steps": 42420, "loss": 0.2878, "lr": 5.674167708387046e-06, "epoch": 16.063177746346064, "percentage": 80.32, "elapsed_time": "2:03:25", "remaining_time": "0:30:14", "throughput": 4628.36, "total_tokens": 34273376} {"current_steps": 34075, "total_steps": 42420, "loss": 0.0366, "lr": 5.667644258386678e-06, "epoch": 16.065535124941064, "percentage": 80.33, "elapsed_time": "2:03:26", "remaining_time": "0:30:13", "throughput": 4628.19, "total_tokens": 34278688} {"current_steps": 34080, "total_steps": 42420, "loss": 0.0462, "lr": 5.661124081025895e-06, "epoch": 16.06789250353607, "percentage": 80.34, "elapsed_time": "2:03:27", "remaining_time": "0:30:12", "throughput": 4628.24, "total_tokens": 34284352} {"current_steps": 34085, "total_steps": 42420, "loss": 0.0654, "lr": 5.65460717740845e-06, "epoch": 16.07024988213107, "percentage": 80.35, "elapsed_time": "2:03:29", "remaining_time": "0:30:11", "throughput": 4628.3, "total_tokens": 34291264} {"current_steps": 34090, "total_steps": 42420, "loss": 0.1325, "lr": 5.648093548637551e-06, "epoch": 16.072607260726073, "percentage": 80.36, "elapsed_time": "2:03:30", "remaining_time": "0:30:10", "throughput": 4628.33, "total_tokens": 34296192} {"current_steps": 34095, "total_steps": 42420, "loss": 0.0643, "lr": 5.641583195815828e-06, "epoch": 16.074964639321074, "percentage": 80.37, "elapsed_time": "2:03:31", "remaining_time": "0:30:09", "throughput": 4628.33, "total_tokens": 34300672} {"current_steps": 34100, "total_steps": 42420, "loss": 0.152, "lr": 5.635076120045385e-06, "epoch": 16.077322017916078, "percentage": 80.39, "elapsed_time": "2:03:32", "remaining_time": "0:30:08", "throughput": 4628.36, "total_tokens": 34305472} {"current_steps": 34105, "total_steps": 42420, "loss": 0.1945, "lr": 5.628572322427755e-06, "epoch": 16.07967939651108, "percentage": 80.4, "elapsed_time": "2:03:33", "remaining_time": "0:30:07", "throughput": 4628.39, "total_tokens": 34311008} {"current_steps": 34110, "total_steps": 42420, "loss": 0.1173, "lr": 5.6220718040639244e-06, "epoch": 16.082036775106083, "percentage": 80.41, "elapsed_time": "2:03:34", "remaining_time": "0:30:06", "throughput": 4628.38, "total_tokens": 34314944} {"current_steps": 34115, "total_steps": 42420, "loss": 0.066, "lr": 5.615574566054319e-06, "epoch": 16.084394153701083, "percentage": 80.42, "elapsed_time": "2:03:35", "remaining_time": "0:30:05", "throughput": 4628.41, "total_tokens": 34320672} {"current_steps": 34120, "total_steps": 42420, "loss": 0.2741, "lr": 5.60908060949881e-06, "epoch": 16.086751532296088, "percentage": 80.43, "elapsed_time": "2:03:36", "remaining_time": "0:30:04", "throughput": 4628.44, "total_tokens": 34325440} {"current_steps": 34125, "total_steps": 42420, "loss": 0.0305, "lr": 5.602589935496716e-06, "epoch": 16.08910891089109, "percentage": 80.45, "elapsed_time": "2:03:37", "remaining_time": "0:30:02", "throughput": 4628.44, "total_tokens": 34330400} {"current_steps": 34130, "total_steps": 42420, "loss": 0.1286, "lr": 5.5961025451468026e-06, "epoch": 16.091466289486092, "percentage": 80.46, "elapsed_time": "2:03:38", "remaining_time": "0:30:01", "throughput": 4628.47, "total_tokens": 34335744} {"current_steps": 34135, "total_steps": 42420, "loss": 0.1021, "lr": 5.5896184395472615e-06, "epoch": 16.093823668081093, "percentage": 80.47, "elapsed_time": "2:03:39", "remaining_time": "0:30:00", "throughput": 4628.49, "total_tokens": 34341056} {"current_steps": 34140, "total_steps": 42420, "loss": 0.1258, "lr": 5.58313761979575e-06, "epoch": 16.096181046676097, "percentage": 80.48, "elapsed_time": "2:03:40", "remaining_time": "0:29:59", "throughput": 4628.52, "total_tokens": 34346080} {"current_steps": 34145, "total_steps": 42420, "loss": 0.1158, "lr": 5.576660086989358e-06, "epoch": 16.098538425271098, "percentage": 80.49, "elapsed_time": "2:03:41", "remaining_time": "0:29:58", "throughput": 4628.53, "total_tokens": 34350624} {"current_steps": 34150, "total_steps": 42420, "loss": 0.0929, "lr": 5.570185842224626e-06, "epoch": 16.100895803866102, "percentage": 80.5, "elapsed_time": "2:03:42", "remaining_time": "0:29:57", "throughput": 4628.55, "total_tokens": 34357472} {"current_steps": 34155, "total_steps": 42420, "loss": 0.0446, "lr": 5.563714886597529e-06, "epoch": 16.103253182461103, "percentage": 80.52, "elapsed_time": "2:03:43", "remaining_time": "0:29:56", "throughput": 4628.58, "total_tokens": 34362336} {"current_steps": 34160, "total_steps": 42420, "loss": 0.0584, "lr": 5.557247221203501e-06, "epoch": 16.105610561056107, "percentage": 80.53, "elapsed_time": "2:03:44", "remaining_time": "0:29:55", "throughput": 4628.6, "total_tokens": 34367104} {"current_steps": 34165, "total_steps": 42420, "loss": 0.1392, "lr": 5.5507828471373926e-06, "epoch": 16.107967939651108, "percentage": 80.54, "elapsed_time": "2:03:45", "remaining_time": "0:29:54", "throughput": 4628.6, "total_tokens": 34371616} {"current_steps": 34170, "total_steps": 42420, "loss": 0.222, "lr": 5.544321765493521e-06, "epoch": 16.11032531824611, "percentage": 80.55, "elapsed_time": "2:03:46", "remaining_time": "0:29:53", "throughput": 4628.64, "total_tokens": 34376928} {"current_steps": 34175, "total_steps": 42420, "loss": 0.1552, "lr": 5.5378639773656345e-06, "epoch": 16.112682696841112, "percentage": 80.56, "elapsed_time": "2:03:47", "remaining_time": "0:29:52", "throughput": 4628.66, "total_tokens": 34381440} {"current_steps": 34180, "total_steps": 42420, "loss": 0.2087, "lr": 5.531409483846933e-06, "epoch": 16.115040075436116, "percentage": 80.58, "elapsed_time": "2:03:49", "remaining_time": "0:29:50", "throughput": 4628.71, "total_tokens": 34387072} {"current_steps": 34185, "total_steps": 42420, "loss": 0.089, "lr": 5.5249582860300435e-06, "epoch": 16.117397454031117, "percentage": 80.59, "elapsed_time": "2:03:50", "remaining_time": "0:29:49", "throughput": 4628.72, "total_tokens": 34392128} {"current_steps": 34190, "total_steps": 42420, "loss": 0.1109, "lr": 5.518510385007048e-06, "epoch": 16.11975483262612, "percentage": 80.6, "elapsed_time": "2:03:51", "remaining_time": "0:29:48", "throughput": 4628.73, "total_tokens": 34396096} {"current_steps": 34195, "total_steps": 42420, "loss": 0.0616, "lr": 5.512065781869466e-06, "epoch": 16.122112211221122, "percentage": 80.61, "elapsed_time": "2:03:51", "remaining_time": "0:29:47", "throughput": 4628.74, "total_tokens": 34400480} {"current_steps": 34200, "total_steps": 42420, "loss": 0.0854, "lr": 5.505624477708263e-06, "epoch": 16.124469589816126, "percentage": 80.62, "elapsed_time": "2:03:53", "remaining_time": "0:29:46", "throughput": 4628.79, "total_tokens": 34406304} {"current_steps": 34205, "total_steps": 42420, "loss": 0.1266, "lr": 5.499186473613841e-06, "epoch": 16.126826968411127, "percentage": 80.63, "elapsed_time": "2:03:54", "remaining_time": "0:29:45", "throughput": 4628.83, "total_tokens": 34412704} {"current_steps": 34210, "total_steps": 42420, "loss": 0.0733, "lr": 5.492751770676041e-06, "epoch": 16.12918434700613, "percentage": 80.65, "elapsed_time": "2:03:55", "remaining_time": "0:29:44", "throughput": 4628.84, "total_tokens": 34417248} {"current_steps": 34215, "total_steps": 42420, "loss": 0.0853, "lr": 5.486320369984155e-06, "epoch": 16.13154172560113, "percentage": 80.66, "elapsed_time": "2:03:56", "remaining_time": "0:29:43", "throughput": 4628.85, "total_tokens": 34421376} {"current_steps": 34220, "total_steps": 42420, "loss": 0.1777, "lr": 5.479892272626913e-06, "epoch": 16.133899104196132, "percentage": 80.67, "elapsed_time": "2:03:57", "remaining_time": "0:29:42", "throughput": 4628.82, "total_tokens": 34425024} {"current_steps": 34225, "total_steps": 42420, "loss": 0.2043, "lr": 5.473467479692468e-06, "epoch": 16.136256482791136, "percentage": 80.68, "elapsed_time": "2:03:58", "remaining_time": "0:29:41", "throughput": 4628.87, "total_tokens": 34432704} {"current_steps": 34230, "total_steps": 42420, "loss": 0.0981, "lr": 5.467045992268438e-06, "epoch": 16.138613861386137, "percentage": 80.69, "elapsed_time": "2:03:59", "remaining_time": "0:29:40", "throughput": 4628.89, "total_tokens": 34437856} {"current_steps": 34235, "total_steps": 42420, "loss": 0.1507, "lr": 5.460627811441871e-06, "epoch": 16.14097123998114, "percentage": 80.7, "elapsed_time": "2:04:00", "remaining_time": "0:29:38", "throughput": 4628.92, "total_tokens": 34442432} {"current_steps": 34240, "total_steps": 42420, "loss": 0.2018, "lr": 5.454212938299255e-06, "epoch": 16.14332861857614, "percentage": 80.72, "elapsed_time": "2:04:01", "remaining_time": "0:29:37", "throughput": 4628.95, "total_tokens": 34447488} {"current_steps": 34245, "total_steps": 42420, "loss": 0.1944, "lr": 5.447801373926522e-06, "epoch": 16.145685997171146, "percentage": 80.73, "elapsed_time": "2:04:02", "remaining_time": "0:29:36", "throughput": 4628.95, "total_tokens": 34451904} {"current_steps": 34250, "total_steps": 42420, "loss": 0.1476, "lr": 5.441393119409038e-06, "epoch": 16.148043375766147, "percentage": 80.74, "elapsed_time": "2:04:03", "remaining_time": "0:29:35", "throughput": 4628.97, "total_tokens": 34457152} {"current_steps": 34255, "total_steps": 42420, "loss": 0.173, "lr": 5.434988175831612e-06, "epoch": 16.15040075436115, "percentage": 80.75, "elapsed_time": "2:04:04", "remaining_time": "0:29:34", "throughput": 4628.97, "total_tokens": 34461376} {"current_steps": 34260, "total_steps": 42420, "loss": 0.0381, "lr": 5.428586544278502e-06, "epoch": 16.15275813295615, "percentage": 80.76, "elapsed_time": "2:04:05", "remaining_time": "0:29:33", "throughput": 4629.0, "total_tokens": 34465984} {"current_steps": 34265, "total_steps": 42420, "loss": 0.1428, "lr": 5.422188225833377e-06, "epoch": 16.155115511551156, "percentage": 80.78, "elapsed_time": "2:04:06", "remaining_time": "0:29:32", "throughput": 4629.04, "total_tokens": 34471200} {"current_steps": 34270, "total_steps": 42420, "loss": 0.1241, "lr": 5.415793221579374e-06, "epoch": 16.157472890146156, "percentage": 80.79, "elapsed_time": "2:04:07", "remaining_time": "0:29:31", "throughput": 4629.07, "total_tokens": 34475808} {"current_steps": 34275, "total_steps": 42420, "loss": 0.0583, "lr": 5.409401532599057e-06, "epoch": 16.15983026874116, "percentage": 80.8, "elapsed_time": "2:04:08", "remaining_time": "0:29:30", "throughput": 4629.06, "total_tokens": 34480064} {"current_steps": 34280, "total_steps": 42420, "loss": 0.0868, "lr": 5.403013159974432e-06, "epoch": 16.16218764733616, "percentage": 80.81, "elapsed_time": "2:04:09", "remaining_time": "0:29:28", "throughput": 4629.09, "total_tokens": 34485280} {"current_steps": 34285, "total_steps": 42420, "loss": 0.1164, "lr": 5.396628104786941e-06, "epoch": 16.164545025931165, "percentage": 80.82, "elapsed_time": "2:04:10", "remaining_time": "0:29:27", "throughput": 4629.15, "total_tokens": 34491008} {"current_steps": 34290, "total_steps": 42420, "loss": 0.1008, "lr": 5.390246368117466e-06, "epoch": 16.166902404526166, "percentage": 80.83, "elapsed_time": "2:04:11", "remaining_time": "0:29:26", "throughput": 4629.18, "total_tokens": 34495936} {"current_steps": 34295, "total_steps": 42420, "loss": 0.1495, "lr": 5.383867951046326e-06, "epoch": 16.16925978312117, "percentage": 80.85, "elapsed_time": "2:04:12", "remaining_time": "0:29:25", "throughput": 4629.22, "total_tokens": 34501440} {"current_steps": 34300, "total_steps": 42420, "loss": 0.0371, "lr": 5.377492854653285e-06, "epoch": 16.17161716171617, "percentage": 80.86, "elapsed_time": "2:04:13", "remaining_time": "0:29:24", "throughput": 4629.26, "total_tokens": 34506112} {"current_steps": 34305, "total_steps": 42420, "loss": 0.1251, "lr": 5.371121080017525e-06, "epoch": 16.173974540311175, "percentage": 80.87, "elapsed_time": "2:04:14", "remaining_time": "0:29:23", "throughput": 4629.26, "total_tokens": 34510624} {"current_steps": 34310, "total_steps": 42420, "loss": 0.3307, "lr": 5.364752628217687e-06, "epoch": 16.176331918906175, "percentage": 80.88, "elapsed_time": "2:04:15", "remaining_time": "0:29:22", "throughput": 4629.27, "total_tokens": 34514688} {"current_steps": 34315, "total_steps": 42420, "loss": 0.036, "lr": 5.358387500331843e-06, "epoch": 16.17868929750118, "percentage": 80.89, "elapsed_time": "2:04:16", "remaining_time": "0:29:21", "throughput": 4629.32, "total_tokens": 34519872} {"current_steps": 34320, "total_steps": 42420, "loss": 0.0216, "lr": 5.3520256974374986e-06, "epoch": 16.18104667609618, "percentage": 80.91, "elapsed_time": "2:04:17", "remaining_time": "0:29:20", "throughput": 4629.33, "total_tokens": 34524800} {"current_steps": 34325, "total_steps": 42420, "loss": 0.0243, "lr": 5.3456672206116e-06, "epoch": 16.183404054691184, "percentage": 80.92, "elapsed_time": "2:04:18", "remaining_time": "0:29:19", "throughput": 4629.37, "total_tokens": 34530304} {"current_steps": 34330, "total_steps": 42420, "loss": 0.0366, "lr": 5.33931207093053e-06, "epoch": 16.185761433286185, "percentage": 80.93, "elapsed_time": "2:04:19", "remaining_time": "0:29:17", "throughput": 4629.37, "total_tokens": 34534528} {"current_steps": 34335, "total_steps": 42420, "loss": 0.024, "lr": 5.332960249470106e-06, "epoch": 16.18811881188119, "percentage": 80.94, "elapsed_time": "2:04:20", "remaining_time": "0:29:16", "throughput": 4629.4, "total_tokens": 34539520} {"current_steps": 34340, "total_steps": 42420, "loss": 0.1922, "lr": 5.326611757305591e-06, "epoch": 16.19047619047619, "percentage": 80.95, "elapsed_time": "2:04:21", "remaining_time": "0:29:15", "throughput": 4629.42, "total_tokens": 34544352} {"current_steps": 34345, "total_steps": 42420, "loss": 0.1605, "lr": 5.320266595511666e-06, "epoch": 16.192833569071194, "percentage": 80.96, "elapsed_time": "2:04:22", "remaining_time": "0:29:14", "throughput": 4629.44, "total_tokens": 34549184} {"current_steps": 34350, "total_steps": 42420, "loss": 0.1146, "lr": 5.313924765162462e-06, "epoch": 16.195190947666195, "percentage": 80.98, "elapsed_time": "2:04:23", "remaining_time": "0:29:13", "throughput": 4629.45, "total_tokens": 34553248} {"current_steps": 34355, "total_steps": 42420, "loss": 0.0109, "lr": 5.307586267331543e-06, "epoch": 16.1975483262612, "percentage": 80.99, "elapsed_time": "2:04:25", "remaining_time": "0:29:12", "throughput": 4629.5, "total_tokens": 34560576} {"current_steps": 34360, "total_steps": 42420, "loss": 0.1177, "lr": 5.301251103091915e-06, "epoch": 16.1999057048562, "percentage": 81.0, "elapsed_time": "2:04:26", "remaining_time": "0:29:11", "throughput": 4629.53, "total_tokens": 34566112} {"current_steps": 34365, "total_steps": 42420, "loss": 0.143, "lr": 5.2949192735160055e-06, "epoch": 16.202263083451204, "percentage": 81.01, "elapsed_time": "2:04:27", "remaining_time": "0:29:10", "throughput": 4629.56, "total_tokens": 34571200} {"current_steps": 34370, "total_steps": 42420, "loss": 0.1977, "lr": 5.288590779675692e-06, "epoch": 16.204620462046204, "percentage": 81.02, "elapsed_time": "2:04:28", "remaining_time": "0:29:09", "throughput": 4629.58, "total_tokens": 34575744} {"current_steps": 34375, "total_steps": 42420, "loss": 0.0352, "lr": 5.2822656226422765e-06, "epoch": 16.20697784064121, "percentage": 81.03, "elapsed_time": "2:04:29", "remaining_time": "0:29:08", "throughput": 4629.62, "total_tokens": 34581216} {"current_steps": 34380, "total_steps": 42420, "loss": 0.1573, "lr": 5.275943803486513e-06, "epoch": 16.20933521923621, "percentage": 81.05, "elapsed_time": "2:04:30", "remaining_time": "0:29:07", "throughput": 4629.65, "total_tokens": 34586368} {"current_steps": 34385, "total_steps": 42420, "loss": 0.0197, "lr": 5.269625323278565e-06, "epoch": 16.211692597831213, "percentage": 81.06, "elapsed_time": "2:04:31", "remaining_time": "0:29:05", "throughput": 4629.66, "total_tokens": 34590752} {"current_steps": 34390, "total_steps": 42420, "loss": 0.3197, "lr": 5.263310183088043e-06, "epoch": 16.214049976426214, "percentage": 81.07, "elapsed_time": "2:04:32", "remaining_time": "0:29:04", "throughput": 4629.7, "total_tokens": 34595712} {"current_steps": 34395, "total_steps": 42420, "loss": 0.0972, "lr": 5.256998383983997e-06, "epoch": 16.216407355021218, "percentage": 81.08, "elapsed_time": "2:04:33", "remaining_time": "0:29:03", "throughput": 4629.72, "total_tokens": 34600512} {"current_steps": 34400, "total_steps": 42420, "loss": 0.196, "lr": 5.2506899270349045e-06, "epoch": 16.21876473361622, "percentage": 81.09, "elapsed_time": "2:04:34", "remaining_time": "0:29:02", "throughput": 4629.76, "total_tokens": 34606112} {"current_steps": 34405, "total_steps": 42420, "loss": 0.1555, "lr": 5.244384813308687e-06, "epoch": 16.221122112211223, "percentage": 81.11, "elapsed_time": "2:04:35", "remaining_time": "0:29:01", "throughput": 4629.81, "total_tokens": 34611840} {"current_steps": 34410, "total_steps": 42420, "loss": 0.0642, "lr": 5.238083043872686e-06, "epoch": 16.223479490806223, "percentage": 81.12, "elapsed_time": "2:04:36", "remaining_time": "0:29:00", "throughput": 4629.83, "total_tokens": 34616864} {"current_steps": 34415, "total_steps": 42420, "loss": 0.0904, "lr": 5.231784619793689e-06, "epoch": 16.225836869401228, "percentage": 81.13, "elapsed_time": "2:04:38", "remaining_time": "0:28:59", "throughput": 4629.88, "total_tokens": 34622720} {"current_steps": 34420, "total_steps": 42420, "loss": 0.1034, "lr": 5.225489542137909e-06, "epoch": 16.22819424799623, "percentage": 81.14, "elapsed_time": "2:04:39", "remaining_time": "0:28:58", "throughput": 4629.93, "total_tokens": 34628704} {"current_steps": 34425, "total_steps": 42420, "loss": 0.1825, "lr": 5.219197811971008e-06, "epoch": 16.23055162659123, "percentage": 81.15, "elapsed_time": "2:04:40", "remaining_time": "0:28:57", "throughput": 4629.96, "total_tokens": 34633504} {"current_steps": 34430, "total_steps": 42420, "loss": 0.168, "lr": 5.212909430358049e-06, "epoch": 16.232909005186233, "percentage": 81.16, "elapsed_time": "2:04:41", "remaining_time": "0:28:56", "throughput": 4629.98, "total_tokens": 34639360} {"current_steps": 34435, "total_steps": 42420, "loss": 0.1191, "lr": 5.206624398363558e-06, "epoch": 16.235266383781234, "percentage": 81.18, "elapsed_time": "2:04:42", "remaining_time": "0:28:55", "throughput": 4630.01, "total_tokens": 34644960} {"current_steps": 34440, "total_steps": 42420, "loss": 0.0422, "lr": 5.200342717051484e-06, "epoch": 16.237623762376238, "percentage": 81.19, "elapsed_time": "2:04:43", "remaining_time": "0:28:54", "throughput": 4630.0, "total_tokens": 34649376} {"current_steps": 34445, "total_steps": 42420, "loss": 0.0927, "lr": 5.194064387485209e-06, "epoch": 16.23998114097124, "percentage": 81.2, "elapsed_time": "2:04:44", "remaining_time": "0:28:52", "throughput": 4630.02, "total_tokens": 34653984} {"current_steps": 34450, "total_steps": 42420, "loss": 0.2064, "lr": 5.187789410727548e-06, "epoch": 16.242338519566243, "percentage": 81.21, "elapsed_time": "2:04:45", "remaining_time": "0:28:51", "throughput": 4630.06, "total_tokens": 34659552} {"current_steps": 34455, "total_steps": 42420, "loss": 0.0718, "lr": 5.181517787840745e-06, "epoch": 16.244695898161243, "percentage": 81.22, "elapsed_time": "2:04:46", "remaining_time": "0:28:50", "throughput": 4630.09, "total_tokens": 34664544} {"current_steps": 34460, "total_steps": 42420, "loss": 0.0391, "lr": 5.175249519886485e-06, "epoch": 16.247053276756247, "percentage": 81.24, "elapsed_time": "2:04:47", "remaining_time": "0:28:49", "throughput": 4630.15, "total_tokens": 34670240} {"current_steps": 34465, "total_steps": 42420, "loss": 0.0363, "lr": 5.168984607925884e-06, "epoch": 16.249410655351248, "percentage": 81.25, "elapsed_time": "2:04:48", "remaining_time": "0:28:48", "throughput": 4630.17, "total_tokens": 34675072} {"current_steps": 34470, "total_steps": 42420, "loss": 0.124, "lr": 5.162723053019467e-06, "epoch": 16.251768033946252, "percentage": 81.26, "elapsed_time": "2:04:50", "remaining_time": "0:28:47", "throughput": 4630.17, "total_tokens": 34680032} {"current_steps": 34475, "total_steps": 42420, "loss": 0.2329, "lr": 5.156464856227223e-06, "epoch": 16.254125412541253, "percentage": 81.27, "elapsed_time": "2:04:51", "remaining_time": "0:28:46", "throughput": 4630.21, "total_tokens": 34685632} {"current_steps": 34480, "total_steps": 42420, "loss": 0.1563, "lr": 5.150210018608551e-06, "epoch": 16.256482791136257, "percentage": 81.28, "elapsed_time": "2:04:52", "remaining_time": "0:28:45", "throughput": 4630.21, "total_tokens": 34692000} {"current_steps": 34485, "total_steps": 42420, "loss": 0.1583, "lr": 5.143958541222293e-06, "epoch": 16.258840169731258, "percentage": 81.29, "elapsed_time": "2:04:53", "remaining_time": "0:28:44", "throughput": 4630.22, "total_tokens": 34696192} {"current_steps": 34490, "total_steps": 42420, "loss": 0.0291, "lr": 5.137710425126721e-06, "epoch": 16.261197548326262, "percentage": 81.31, "elapsed_time": "2:04:54", "remaining_time": "0:28:43", "throughput": 4630.22, "total_tokens": 34700896} {"current_steps": 34495, "total_steps": 42420, "loss": 0.0549, "lr": 5.131465671379529e-06, "epoch": 16.263554926921262, "percentage": 81.32, "elapsed_time": "2:04:55", "remaining_time": "0:28:42", "throughput": 4630.26, "total_tokens": 34705792} {"current_steps": 34500, "total_steps": 42420, "loss": 0.2909, "lr": 5.125224281037852e-06, "epoch": 16.265912305516267, "percentage": 81.33, "elapsed_time": "2:04:56", "remaining_time": "0:28:40", "throughput": 4630.27, "total_tokens": 34710496} {"current_steps": 34505, "total_steps": 42420, "loss": 0.0877, "lr": 5.118986255158253e-06, "epoch": 16.268269684111267, "percentage": 81.34, "elapsed_time": "2:04:57", "remaining_time": "0:28:39", "throughput": 4630.28, "total_tokens": 34714560} {"current_steps": 34510, "total_steps": 42420, "loss": 0.2174, "lr": 5.112751594796717e-06, "epoch": 16.27062706270627, "percentage": 81.35, "elapsed_time": "2:04:58", "remaining_time": "0:28:38", "throughput": 4630.32, "total_tokens": 34719552} {"current_steps": 34515, "total_steps": 42420, "loss": 0.1772, "lr": 5.1065203010086685e-06, "epoch": 16.272984441301272, "percentage": 81.36, "elapsed_time": "2:04:59", "remaining_time": "0:28:37", "throughput": 4630.37, "total_tokens": 34725504} {"current_steps": 34520, "total_steps": 42420, "loss": 0.045, "lr": 5.100292374848961e-06, "epoch": 16.275341819896276, "percentage": 81.38, "elapsed_time": "2:05:00", "remaining_time": "0:28:36", "throughput": 4630.39, "total_tokens": 34730432} {"current_steps": 34525, "total_steps": 42420, "loss": 0.1181, "lr": 5.0940678173718785e-06, "epoch": 16.277699198491277, "percentage": 81.39, "elapsed_time": "2:05:01", "remaining_time": "0:28:35", "throughput": 4630.43, "total_tokens": 34735488} {"current_steps": 34530, "total_steps": 42420, "loss": 0.0788, "lr": 5.08784662963113e-06, "epoch": 16.28005657708628, "percentage": 81.4, "elapsed_time": "2:05:02", "remaining_time": "0:28:34", "throughput": 4630.48, "total_tokens": 34741440} {"current_steps": 34535, "total_steps": 42420, "loss": 0.151, "lr": 5.081628812679856e-06, "epoch": 16.28241395568128, "percentage": 81.41, "elapsed_time": "2:05:04", "remaining_time": "0:28:33", "throughput": 4630.52, "total_tokens": 34747936} {"current_steps": 34540, "total_steps": 42420, "loss": 0.2542, "lr": 5.075414367570633e-06, "epoch": 16.284771334276286, "percentage": 81.42, "elapsed_time": "2:05:05", "remaining_time": "0:28:32", "throughput": 4630.56, "total_tokens": 34753024} {"current_steps": 34545, "total_steps": 42420, "loss": 0.1379, "lr": 5.069203295355463e-06, "epoch": 16.287128712871286, "percentage": 81.44, "elapsed_time": "2:05:06", "remaining_time": "0:28:31", "throughput": 4630.59, "total_tokens": 34757600} {"current_steps": 34550, "total_steps": 42420, "loss": 0.1103, "lr": 5.062995597085759e-06, "epoch": 16.28948609146629, "percentage": 81.45, "elapsed_time": "2:05:07", "remaining_time": "0:28:30", "throughput": 4630.62, "total_tokens": 34762720} {"current_steps": 34555, "total_steps": 42420, "loss": 0.0921, "lr": 5.0567912738123914e-06, "epoch": 16.29184347006129, "percentage": 81.46, "elapsed_time": "2:05:08", "remaining_time": "0:28:28", "throughput": 4630.63, "total_tokens": 34767008} {"current_steps": 34560, "total_steps": 42420, "loss": 0.1407, "lr": 5.050590326585647e-06, "epoch": 16.294200848656295, "percentage": 81.47, "elapsed_time": "2:05:09", "remaining_time": "0:28:27", "throughput": 4630.67, "total_tokens": 34772608} {"current_steps": 34565, "total_steps": 42420, "loss": 0.1236, "lr": 5.044392756455238e-06, "epoch": 16.296558227251296, "percentage": 81.48, "elapsed_time": "2:05:10", "remaining_time": "0:28:26", "throughput": 4630.69, "total_tokens": 34777280} {"current_steps": 34570, "total_steps": 42420, "loss": 0.0475, "lr": 5.038198564470306e-06, "epoch": 16.2989156058463, "percentage": 81.49, "elapsed_time": "2:05:11", "remaining_time": "0:28:25", "throughput": 4630.74, "total_tokens": 34783104} {"current_steps": 34575, "total_steps": 42420, "loss": 0.1252, "lr": 5.032007751679426e-06, "epoch": 16.3012729844413, "percentage": 81.51, "elapsed_time": "2:05:12", "remaining_time": "0:28:24", "throughput": 4630.78, "total_tokens": 34788448} {"current_steps": 34580, "total_steps": 42420, "loss": 0.2755, "lr": 5.025820319130597e-06, "epoch": 16.303630363036305, "percentage": 81.52, "elapsed_time": "2:05:13", "remaining_time": "0:28:23", "throughput": 4630.8, "total_tokens": 34793728} {"current_steps": 34585, "total_steps": 42420, "loss": 0.1725, "lr": 5.019636267871253e-06, "epoch": 16.305987741631306, "percentage": 81.53, "elapsed_time": "2:05:14", "remaining_time": "0:28:22", "throughput": 4630.85, "total_tokens": 34799008} {"current_steps": 34590, "total_steps": 42420, "loss": 0.1099, "lr": 5.013455598948233e-06, "epoch": 16.30834512022631, "percentage": 81.54, "elapsed_time": "2:05:15", "remaining_time": "0:28:21", "throughput": 4630.87, "total_tokens": 34804544} {"current_steps": 34595, "total_steps": 42420, "loss": 0.1256, "lr": 5.0072783134078285e-06, "epoch": 16.31070249882131, "percentage": 81.55, "elapsed_time": "2:05:16", "remaining_time": "0:28:20", "throughput": 4630.9, "total_tokens": 34809856} {"current_steps": 34600, "total_steps": 42420, "loss": 0.1048, "lr": 5.0011044122957515e-06, "epoch": 16.313059877416315, "percentage": 81.57, "elapsed_time": "2:05:17", "remaining_time": "0:28:19", "throughput": 4630.93, "total_tokens": 34814816} {"current_steps": 34605, "total_steps": 42420, "loss": 0.1666, "lr": 4.994933896657131e-06, "epoch": 16.315417256011315, "percentage": 81.58, "elapsed_time": "2:05:19", "remaining_time": "0:28:18", "throughput": 4630.99, "total_tokens": 34821024} {"current_steps": 34610, "total_steps": 42420, "loss": 0.0892, "lr": 4.988766767536546e-06, "epoch": 16.31777463460632, "percentage": 81.59, "elapsed_time": "2:05:20", "remaining_time": "0:28:16", "throughput": 4630.98, "total_tokens": 34825376} {"current_steps": 34615, "total_steps": 42420, "loss": 0.0779, "lr": 4.982603025977966e-06, "epoch": 16.32013201320132, "percentage": 81.6, "elapsed_time": "2:05:21", "remaining_time": "0:28:15", "throughput": 4631.03, "total_tokens": 34831168} {"current_steps": 34620, "total_steps": 42420, "loss": 0.0403, "lr": 4.976442673024817e-06, "epoch": 16.32248939179632, "percentage": 81.61, "elapsed_time": "2:05:22", "remaining_time": "0:28:14", "throughput": 4631.07, "total_tokens": 34836384} {"current_steps": 34625, "total_steps": 42420, "loss": 0.058, "lr": 4.970285709719946e-06, "epoch": 16.324846770391325, "percentage": 81.62, "elapsed_time": "2:05:23", "remaining_time": "0:28:13", "throughput": 4631.13, "total_tokens": 34842432} {"current_steps": 34630, "total_steps": 42420, "loss": 0.0251, "lr": 4.964132137105618e-06, "epoch": 16.327204148986326, "percentage": 81.64, "elapsed_time": "2:05:24", "remaining_time": "0:28:12", "throughput": 4631.13, "total_tokens": 34846816} {"current_steps": 34635, "total_steps": 42420, "loss": 0.2566, "lr": 4.9579819562235345e-06, "epoch": 16.32956152758133, "percentage": 81.65, "elapsed_time": "2:05:25", "remaining_time": "0:28:11", "throughput": 4631.17, "total_tokens": 34851712} {"current_steps": 34640, "total_steps": 42420, "loss": 0.0579, "lr": 4.951835168114807e-06, "epoch": 16.33191890617633, "percentage": 81.66, "elapsed_time": "2:05:26", "remaining_time": "0:28:10", "throughput": 4631.2, "total_tokens": 34856960} {"current_steps": 34645, "total_steps": 42420, "loss": 0.0797, "lr": 4.945691773819985e-06, "epoch": 16.334276284771335, "percentage": 81.67, "elapsed_time": "2:05:27", "remaining_time": "0:28:09", "throughput": 4631.22, "total_tokens": 34862048} {"current_steps": 34650, "total_steps": 42420, "loss": 0.0867, "lr": 4.9395517743790446e-06, "epoch": 16.336633663366335, "percentage": 81.68, "elapsed_time": "2:05:28", "remaining_time": "0:28:08", "throughput": 4631.23, "total_tokens": 34867360} {"current_steps": 34655, "total_steps": 42420, "loss": 0.0754, "lr": 4.933415170831382e-06, "epoch": 16.33899104196134, "percentage": 81.69, "elapsed_time": "2:05:29", "remaining_time": "0:28:07", "throughput": 4631.22, "total_tokens": 34871552} {"current_steps": 34660, "total_steps": 42420, "loss": 0.1095, "lr": 4.9272819642158185e-06, "epoch": 16.34134842055634, "percentage": 81.71, "elapsed_time": "2:05:30", "remaining_time": "0:28:06", "throughput": 4631.15, "total_tokens": 34875520} {"current_steps": 34665, "total_steps": 42420, "loss": 0.0514, "lr": 4.921152155570604e-06, "epoch": 16.343705799151344, "percentage": 81.72, "elapsed_time": "2:05:31", "remaining_time": "0:28:04", "throughput": 4631.18, "total_tokens": 34880608} {"current_steps": 34670, "total_steps": 42420, "loss": 0.1251, "lr": 4.91502574593341e-06, "epoch": 16.346063177746345, "percentage": 81.73, "elapsed_time": "2:05:32", "remaining_time": "0:28:03", "throughput": 4631.21, "total_tokens": 34885728} {"current_steps": 34675, "total_steps": 42420, "loss": 0.1817, "lr": 4.908902736341342e-06, "epoch": 16.34842055634135, "percentage": 81.74, "elapsed_time": "2:05:33", "remaining_time": "0:28:02", "throughput": 4631.22, "total_tokens": 34890656} {"current_steps": 34680, "total_steps": 42420, "loss": 0.1624, "lr": 4.902783127830904e-06, "epoch": 16.35077793493635, "percentage": 81.75, "elapsed_time": "2:05:35", "remaining_time": "0:28:01", "throughput": 4631.27, "total_tokens": 34898112} {"current_steps": 34685, "total_steps": 42420, "loss": 0.0672, "lr": 4.896666921438053e-06, "epoch": 16.353135313531354, "percentage": 81.77, "elapsed_time": "2:05:36", "remaining_time": "0:28:00", "throughput": 4631.32, "total_tokens": 34903328} {"current_steps": 34690, "total_steps": 42420, "loss": 0.2317, "lr": 4.890554118198157e-06, "epoch": 16.355492692126354, "percentage": 81.78, "elapsed_time": "2:05:37", "remaining_time": "0:27:59", "throughput": 4631.35, "total_tokens": 34908928} {"current_steps": 34695, "total_steps": 42420, "loss": 0.0949, "lr": 4.8844447191460085e-06, "epoch": 16.35785007072136, "percentage": 81.79, "elapsed_time": "2:05:38", "remaining_time": "0:27:58", "throughput": 4631.39, "total_tokens": 34914784} {"current_steps": 34700, "total_steps": 42420, "loss": 0.0073, "lr": 4.878338725315826e-06, "epoch": 16.36020744931636, "percentage": 81.8, "elapsed_time": "2:05:39", "remaining_time": "0:27:57", "throughput": 4631.4, "total_tokens": 34919136} {"current_steps": 34705, "total_steps": 42420, "loss": 0.0103, "lr": 4.872236137741251e-06, "epoch": 16.362564827911363, "percentage": 81.81, "elapsed_time": "2:05:40", "remaining_time": "0:27:56", "throughput": 4631.42, "total_tokens": 34925088} {"current_steps": 34710, "total_steps": 42420, "loss": 0.1566, "lr": 4.86613695745535e-06, "epoch": 16.364922206506364, "percentage": 81.82, "elapsed_time": "2:05:42", "remaining_time": "0:27:55", "throughput": 4631.46, "total_tokens": 34930592} {"current_steps": 34715, "total_steps": 42420, "loss": 0.1349, "lr": 4.860041185490613e-06, "epoch": 16.367279585101368, "percentage": 81.84, "elapsed_time": "2:05:43", "remaining_time": "0:27:54", "throughput": 4631.48, "total_tokens": 34935488} {"current_steps": 34720, "total_steps": 42420, "loss": 0.0746, "lr": 4.853948822878943e-06, "epoch": 16.36963696369637, "percentage": 81.85, "elapsed_time": "2:05:44", "remaining_time": "0:27:53", "throughput": 4631.52, "total_tokens": 34941152} {"current_steps": 34725, "total_steps": 42420, "loss": 0.0339, "lr": 4.847859870651672e-06, "epoch": 16.371994342291373, "percentage": 81.86, "elapsed_time": "2:05:45", "remaining_time": "0:27:52", "throughput": 4631.57, "total_tokens": 34946496} {"current_steps": 34730, "total_steps": 42420, "loss": 0.1559, "lr": 4.841774329839563e-06, "epoch": 16.374351720886374, "percentage": 81.87, "elapsed_time": "2:05:46", "remaining_time": "0:27:50", "throughput": 4631.57, "total_tokens": 34951776} {"current_steps": 34735, "total_steps": 42420, "loss": 0.2066, "lr": 4.8356922014727944e-06, "epoch": 16.376709099481378, "percentage": 81.88, "elapsed_time": "2:05:47", "remaining_time": "0:27:49", "throughput": 4631.57, "total_tokens": 34956064} {"current_steps": 34740, "total_steps": 42420, "loss": 0.2244, "lr": 4.829613486580964e-06, "epoch": 16.37906647807638, "percentage": 81.9, "elapsed_time": "2:05:48", "remaining_time": "0:27:48", "throughput": 4631.6, "total_tokens": 34961248} {"current_steps": 34745, "total_steps": 42420, "loss": 0.1272, "lr": 4.823538186193097e-06, "epoch": 16.381423856671383, "percentage": 81.91, "elapsed_time": "2:05:49", "remaining_time": "0:27:47", "throughput": 4631.62, "total_tokens": 34965856} {"current_steps": 34750, "total_steps": 42420, "loss": 0.0369, "lr": 4.817466301337639e-06, "epoch": 16.383781235266383, "percentage": 81.92, "elapsed_time": "2:05:50", "remaining_time": "0:27:46", "throughput": 4631.65, "total_tokens": 34970752} {"current_steps": 34755, "total_steps": 42420, "loss": 0.1556, "lr": 4.811397833042461e-06, "epoch": 16.386138613861387, "percentage": 81.93, "elapsed_time": "2:05:51", "remaining_time": "0:27:45", "throughput": 4631.62, "total_tokens": 34975104} {"current_steps": 34760, "total_steps": 42420, "loss": 0.047, "lr": 4.805332782334842e-06, "epoch": 16.388495992456388, "percentage": 81.94, "elapsed_time": "2:05:52", "remaining_time": "0:27:44", "throughput": 4631.65, "total_tokens": 34980128} {"current_steps": 34765, "total_steps": 42420, "loss": 0.2027, "lr": 4.799271150241496e-06, "epoch": 16.390853371051392, "percentage": 81.95, "elapsed_time": "2:05:53", "remaining_time": "0:27:43", "throughput": 4631.68, "total_tokens": 34985408} {"current_steps": 34770, "total_steps": 42420, "loss": 0.2458, "lr": 4.793212937788558e-06, "epoch": 16.393210749646393, "percentage": 81.97, "elapsed_time": "2:05:54", "remaining_time": "0:27:42", "throughput": 4631.71, "total_tokens": 34990944} {"current_steps": 34775, "total_steps": 42420, "loss": 0.0406, "lr": 4.787158146001575e-06, "epoch": 16.395568128241397, "percentage": 81.98, "elapsed_time": "2:05:55", "remaining_time": "0:27:41", "throughput": 4631.7, "total_tokens": 34995584} {"current_steps": 34780, "total_steps": 42420, "loss": 0.1439, "lr": 4.781106775905525e-06, "epoch": 16.397925506836398, "percentage": 81.99, "elapsed_time": "2:05:56", "remaining_time": "0:27:39", "throughput": 4631.75, "total_tokens": 35001696} {"current_steps": 34785, "total_steps": 42420, "loss": 0.1372, "lr": 4.775058828524801e-06, "epoch": 16.400282885431402, "percentage": 82.0, "elapsed_time": "2:05:57", "remaining_time": "0:27:38", "throughput": 4631.77, "total_tokens": 35006688} {"current_steps": 34790, "total_steps": 42420, "loss": 0.0331, "lr": 4.7690143048832154e-06, "epoch": 16.402640264026402, "percentage": 82.01, "elapsed_time": "2:05:59", "remaining_time": "0:27:37", "throughput": 4631.8, "total_tokens": 35012128} {"current_steps": 34795, "total_steps": 42420, "loss": 0.0329, "lr": 4.762973206004012e-06, "epoch": 16.404997642621407, "percentage": 82.02, "elapsed_time": "2:05:59", "remaining_time": "0:27:36", "throughput": 4631.79, "total_tokens": 35016128} {"current_steps": 34800, "total_steps": 42420, "loss": 0.1028, "lr": 4.756935532909834e-06, "epoch": 16.407355021216407, "percentage": 82.04, "elapsed_time": "2:06:00", "remaining_time": "0:27:35", "throughput": 4631.77, "total_tokens": 35020032} {"current_steps": 34805, "total_steps": 42420, "loss": 0.0993, "lr": 4.7509012866227635e-06, "epoch": 16.40971239981141, "percentage": 82.05, "elapsed_time": "2:06:01", "remaining_time": "0:27:34", "throughput": 4631.79, "total_tokens": 35024480} {"current_steps": 34810, "total_steps": 42420, "loss": 0.068, "lr": 4.744870468164292e-06, "epoch": 16.412069778406412, "percentage": 82.06, "elapsed_time": "2:06:02", "remaining_time": "0:27:33", "throughput": 4631.82, "total_tokens": 35029664} {"current_steps": 34815, "total_steps": 42420, "loss": 0.1335, "lr": 4.738843078555341e-06, "epoch": 16.414427157001413, "percentage": 82.07, "elapsed_time": "2:06:03", "remaining_time": "0:27:32", "throughput": 4631.85, "total_tokens": 35034528} {"current_steps": 34820, "total_steps": 42420, "loss": 0.0709, "lr": 4.73281911881624e-06, "epoch": 16.416784535596417, "percentage": 82.08, "elapsed_time": "2:06:04", "remaining_time": "0:27:31", "throughput": 4631.87, "total_tokens": 35038880} {"current_steps": 34825, "total_steps": 42420, "loss": 0.1326, "lr": 4.726798589966747e-06, "epoch": 16.419141914191417, "percentage": 82.1, "elapsed_time": "2:06:05", "remaining_time": "0:27:30", "throughput": 4631.9, "total_tokens": 35044032} {"current_steps": 34830, "total_steps": 42420, "loss": 0.1878, "lr": 4.7207814930260305e-06, "epoch": 16.42149929278642, "percentage": 82.11, "elapsed_time": "2:06:06", "remaining_time": "0:27:28", "throughput": 4631.93, "total_tokens": 35049120} {"current_steps": 34835, "total_steps": 42420, "loss": 0.1728, "lr": 4.714767829012695e-06, "epoch": 16.423856671381422, "percentage": 82.12, "elapsed_time": "2:06:08", "remaining_time": "0:27:27", "throughput": 4631.97, "total_tokens": 35054848} {"current_steps": 34840, "total_steps": 42420, "loss": 0.0713, "lr": 4.708757598944735e-06, "epoch": 16.426214049976426, "percentage": 82.13, "elapsed_time": "2:06:09", "remaining_time": "0:27:26", "throughput": 4632.0, "total_tokens": 35059904} {"current_steps": 34845, "total_steps": 42420, "loss": 0.1423, "lr": 4.702750803839592e-06, "epoch": 16.428571428571427, "percentage": 82.14, "elapsed_time": "2:06:10", "remaining_time": "0:27:25", "throughput": 4632.03, "total_tokens": 35064992} {"current_steps": 34850, "total_steps": 42420, "loss": 0.0104, "lr": 4.6967474447141055e-06, "epoch": 16.43092880716643, "percentage": 82.15, "elapsed_time": "2:06:11", "remaining_time": "0:27:24", "throughput": 4632.05, "total_tokens": 35069952} {"current_steps": 34855, "total_steps": 42420, "loss": 0.0682, "lr": 4.6907475225845485e-06, "epoch": 16.433286185761432, "percentage": 82.17, "elapsed_time": "2:06:12", "remaining_time": "0:27:23", "throughput": 4632.06, "total_tokens": 35074368} {"current_steps": 34860, "total_steps": 42420, "loss": 0.1843, "lr": 4.684751038466603e-06, "epoch": 16.435643564356436, "percentage": 82.18, "elapsed_time": "2:06:13", "remaining_time": "0:27:22", "throughput": 4632.09, "total_tokens": 35079680} {"current_steps": 34865, "total_steps": 42420, "loss": 0.2514, "lr": 4.678757993375374e-06, "epoch": 16.438000942951437, "percentage": 82.19, "elapsed_time": "2:06:14", "remaining_time": "0:27:21", "throughput": 4632.1, "total_tokens": 35083840} {"current_steps": 34870, "total_steps": 42420, "loss": 0.0659, "lr": 4.672768388325382e-06, "epoch": 16.44035832154644, "percentage": 82.2, "elapsed_time": "2:06:15", "remaining_time": "0:27:20", "throughput": 4632.14, "total_tokens": 35089184} {"current_steps": 34875, "total_steps": 42420, "loss": 0.0749, "lr": 4.666782224330563e-06, "epoch": 16.44271570014144, "percentage": 82.21, "elapsed_time": "2:06:16", "remaining_time": "0:27:19", "throughput": 4632.18, "total_tokens": 35094400} {"current_steps": 34880, "total_steps": 42420, "loss": 0.1288, "lr": 4.660799502404278e-06, "epoch": 16.445073078736446, "percentage": 82.23, "elapsed_time": "2:06:17", "remaining_time": "0:27:17", "throughput": 4632.2, "total_tokens": 35099552} {"current_steps": 34885, "total_steps": 42420, "loss": 0.071, "lr": 4.6548202235593e-06, "epoch": 16.447430457331446, "percentage": 82.24, "elapsed_time": "2:06:18", "remaining_time": "0:27:16", "throughput": 4632.23, "total_tokens": 35104512} {"current_steps": 34890, "total_steps": 42420, "loss": 0.0689, "lr": 4.6488443888078136e-06, "epoch": 16.44978783592645, "percentage": 82.25, "elapsed_time": "2:06:19", "remaining_time": "0:27:15", "throughput": 4632.29, "total_tokens": 35111584} {"current_steps": 34895, "total_steps": 42420, "loss": 0.1795, "lr": 4.642871999161427e-06, "epoch": 16.45214521452145, "percentage": 82.26, "elapsed_time": "2:06:20", "remaining_time": "0:27:14", "throughput": 4632.3, "total_tokens": 35115744} {"current_steps": 34900, "total_steps": 42420, "loss": 0.072, "lr": 4.63690305563117e-06, "epoch": 16.454502593116455, "percentage": 82.27, "elapsed_time": "2:06:21", "remaining_time": "0:27:13", "throughput": 4632.34, "total_tokens": 35121440} {"current_steps": 34905, "total_steps": 42420, "loss": 0.1258, "lr": 4.630937559227477e-06, "epoch": 16.456859971711456, "percentage": 82.28, "elapsed_time": "2:06:22", "remaining_time": "0:27:12", "throughput": 4632.36, "total_tokens": 35126560} {"current_steps": 34910, "total_steps": 42420, "loss": 0.1158, "lr": 4.6249755109602085e-06, "epoch": 16.45921735030646, "percentage": 82.3, "elapsed_time": "2:06:23", "remaining_time": "0:27:11", "throughput": 4632.36, "total_tokens": 35130560} {"current_steps": 34915, "total_steps": 42420, "loss": 0.2744, "lr": 4.619016911838639e-06, "epoch": 16.46157472890146, "percentage": 82.31, "elapsed_time": "2:06:24", "remaining_time": "0:27:10", "throughput": 4632.38, "total_tokens": 35134976} {"current_steps": 34920, "total_steps": 42420, "loss": 0.0937, "lr": 4.613061762871454e-06, "epoch": 16.463932107496465, "percentage": 82.32, "elapsed_time": "2:06:25", "remaining_time": "0:27:09", "throughput": 4632.38, "total_tokens": 35139456} {"current_steps": 34925, "total_steps": 42420, "loss": 0.0927, "lr": 4.607110065066772e-06, "epoch": 16.466289486091465, "percentage": 82.33, "elapsed_time": "2:06:26", "remaining_time": "0:27:08", "throughput": 4632.42, "total_tokens": 35144288} {"current_steps": 34930, "total_steps": 42420, "loss": 0.1498, "lr": 4.601161819432096e-06, "epoch": 16.46864686468647, "percentage": 82.34, "elapsed_time": "2:06:27", "remaining_time": "0:27:07", "throughput": 4632.45, "total_tokens": 35149568} {"current_steps": 34935, "total_steps": 42420, "loss": 0.2124, "lr": 4.595217026974372e-06, "epoch": 16.47100424328147, "percentage": 82.36, "elapsed_time": "2:06:28", "remaining_time": "0:27:05", "throughput": 4632.45, "total_tokens": 35154240} {"current_steps": 34940, "total_steps": 42420, "loss": 0.0555, "lr": 4.589275688699951e-06, "epoch": 16.473361621876474, "percentage": 82.37, "elapsed_time": "2:06:29", "remaining_time": "0:27:04", "throughput": 4632.43, "total_tokens": 35158048} {"current_steps": 34945, "total_steps": 42420, "loss": 0.1616, "lr": 4.583337805614602e-06, "epoch": 16.475719000471475, "percentage": 82.38, "elapsed_time": "2:06:30", "remaining_time": "0:27:03", "throughput": 4632.46, "total_tokens": 35163328} {"current_steps": 34950, "total_steps": 42420, "loss": 0.1574, "lr": 4.577403378723507e-06, "epoch": 16.47807637906648, "percentage": 82.39, "elapsed_time": "2:06:31", "remaining_time": "0:27:02", "throughput": 4632.45, "total_tokens": 35167840} {"current_steps": 34955, "total_steps": 42420, "loss": 0.0554, "lr": 4.571472409031266e-06, "epoch": 16.48043375766148, "percentage": 82.4, "elapsed_time": "2:06:32", "remaining_time": "0:27:01", "throughput": 4632.51, "total_tokens": 35174144} {"current_steps": 34960, "total_steps": 42420, "loss": 0.0468, "lr": 4.565544897541887e-06, "epoch": 16.482791136256484, "percentage": 82.41, "elapsed_time": "2:06:33", "remaining_time": "0:27:00", "throughput": 4632.56, "total_tokens": 35179424} {"current_steps": 34965, "total_steps": 42420, "loss": 0.0551, "lr": 4.559620845258808e-06, "epoch": 16.485148514851485, "percentage": 82.43, "elapsed_time": "2:06:34", "remaining_time": "0:26:59", "throughput": 4632.59, "total_tokens": 35183808} {"current_steps": 34970, "total_steps": 42420, "loss": 0.0453, "lr": 4.553700253184853e-06, "epoch": 16.48750589344649, "percentage": 82.44, "elapsed_time": "2:06:35", "remaining_time": "0:26:58", "throughput": 4632.58, "total_tokens": 35188032} {"current_steps": 34975, "total_steps": 42420, "loss": 0.1656, "lr": 4.547783122322291e-06, "epoch": 16.48986327204149, "percentage": 82.45, "elapsed_time": "2:06:36", "remaining_time": "0:26:57", "throughput": 4632.58, "total_tokens": 35192256} {"current_steps": 34980, "total_steps": 42420, "loss": 0.2775, "lr": 4.5418694536727844e-06, "epoch": 16.492220650636494, "percentage": 82.46, "elapsed_time": "2:06:37", "remaining_time": "0:26:56", "throughput": 4632.61, "total_tokens": 35198432} {"current_steps": 34985, "total_steps": 42420, "loss": 0.0873, "lr": 4.535959248237421e-06, "epoch": 16.494578029231494, "percentage": 82.47, "elapsed_time": "2:06:38", "remaining_time": "0:26:54", "throughput": 4632.64, "total_tokens": 35203200} {"current_steps": 34990, "total_steps": 42420, "loss": 0.1858, "lr": 4.5300525070166965e-06, "epoch": 16.4969354078265, "percentage": 82.48, "elapsed_time": "2:06:39", "remaining_time": "0:26:53", "throughput": 4632.66, "total_tokens": 35207616} {"current_steps": 34995, "total_steps": 42420, "loss": 0.115, "lr": 4.524149231010522e-06, "epoch": 16.4992927864215, "percentage": 82.5, "elapsed_time": "2:06:40", "remaining_time": "0:26:52", "throughput": 4632.67, "total_tokens": 35212352} {"current_steps": 35000, "total_steps": 42420, "loss": 0.0643, "lr": 4.5182494212182234e-06, "epoch": 16.501650165016503, "percentage": 82.51, "elapsed_time": "2:06:41", "remaining_time": "0:26:51", "throughput": 4632.65, "total_tokens": 35216448} {"current_steps": 35005, "total_steps": 42420, "loss": 0.0463, "lr": 4.512353078638543e-06, "epoch": 16.504007543611504, "percentage": 82.52, "elapsed_time": "2:06:42", "remaining_time": "0:26:50", "throughput": 4632.68, "total_tokens": 35220960} {"current_steps": 35010, "total_steps": 42420, "loss": 0.1451, "lr": 4.506460204269622e-06, "epoch": 16.506364922206508, "percentage": 82.53, "elapsed_time": "2:06:43", "remaining_time": "0:26:49", "throughput": 4632.72, "total_tokens": 35226528} {"current_steps": 35015, "total_steps": 42420, "loss": 0.1979, "lr": 4.500570799109024e-06, "epoch": 16.50872230080151, "percentage": 82.54, "elapsed_time": "2:06:44", "remaining_time": "0:26:48", "throughput": 4632.75, "total_tokens": 35231648} {"current_steps": 35020, "total_steps": 42420, "loss": 0.1189, "lr": 4.494684864153734e-06, "epoch": 16.51107967939651, "percentage": 82.56, "elapsed_time": "2:06:45", "remaining_time": "0:26:47", "throughput": 4632.76, "total_tokens": 35236320} {"current_steps": 35025, "total_steps": 42420, "loss": 0.0241, "lr": 4.488802400400133e-06, "epoch": 16.513437057991514, "percentage": 82.57, "elapsed_time": "2:06:46", "remaining_time": "0:26:46", "throughput": 4632.78, "total_tokens": 35240608} {"current_steps": 35030, "total_steps": 42420, "loss": 0.0682, "lr": 4.482923408844025e-06, "epoch": 16.515794436586514, "percentage": 82.58, "elapsed_time": "2:06:48", "remaining_time": "0:26:45", "throughput": 4632.83, "total_tokens": 35247072} {"current_steps": 35035, "total_steps": 42420, "loss": 0.1303, "lr": 4.477047890480626e-06, "epoch": 16.51815181518152, "percentage": 82.59, "elapsed_time": "2:06:49", "remaining_time": "0:26:43", "throughput": 4632.83, "total_tokens": 35251488} {"current_steps": 35040, "total_steps": 42420, "loss": 0.0956, "lr": 4.471175846304557e-06, "epoch": 16.52050919377652, "percentage": 82.6, "elapsed_time": "2:06:50", "remaining_time": "0:26:42", "throughput": 4632.84, "total_tokens": 35255968} {"current_steps": 35045, "total_steps": 42420, "loss": 0.1036, "lr": 4.465307277309866e-06, "epoch": 16.522866572371523, "percentage": 82.61, "elapsed_time": "2:06:51", "remaining_time": "0:26:41", "throughput": 4632.89, "total_tokens": 35261376} {"current_steps": 35050, "total_steps": 42420, "loss": 0.0558, "lr": 4.459442184489985e-06, "epoch": 16.525223950966524, "percentage": 82.63, "elapsed_time": "2:06:52", "remaining_time": "0:26:40", "throughput": 4632.92, "total_tokens": 35266272} {"current_steps": 35055, "total_steps": 42420, "loss": 0.312, "lr": 4.453580568837784e-06, "epoch": 16.527581329561528, "percentage": 82.64, "elapsed_time": "2:06:53", "remaining_time": "0:26:39", "throughput": 4632.94, "total_tokens": 35271328} {"current_steps": 35060, "total_steps": 42420, "loss": 0.0448, "lr": 4.447722431345536e-06, "epoch": 16.52993870815653, "percentage": 82.65, "elapsed_time": "2:06:54", "remaining_time": "0:26:38", "throughput": 4632.94, "total_tokens": 35276288} {"current_steps": 35065, "total_steps": 42420, "loss": 0.0691, "lr": 4.441867773004929e-06, "epoch": 16.532296086751533, "percentage": 82.66, "elapsed_time": "2:06:55", "remaining_time": "0:26:37", "throughput": 4632.95, "total_tokens": 35280736} {"current_steps": 35070, "total_steps": 42420, "loss": 0.0823, "lr": 4.4360165948070405e-06, "epoch": 16.534653465346533, "percentage": 82.67, "elapsed_time": "2:06:56", "remaining_time": "0:26:36", "throughput": 4632.96, "total_tokens": 35285696} {"current_steps": 35075, "total_steps": 42420, "loss": 0.1149, "lr": 4.43016889774239e-06, "epoch": 16.537010843941538, "percentage": 82.69, "elapsed_time": "2:06:57", "remaining_time": "0:26:35", "throughput": 4633.01, "total_tokens": 35291520} {"current_steps": 35080, "total_steps": 42420, "loss": 0.1779, "lr": 4.424324682800887e-06, "epoch": 16.539368222536538, "percentage": 82.7, "elapsed_time": "2:06:58", "remaining_time": "0:26:34", "throughput": 4633.04, "total_tokens": 35296384} {"current_steps": 35085, "total_steps": 42420, "loss": 0.2035, "lr": 4.418483950971863e-06, "epoch": 16.541725601131542, "percentage": 82.71, "elapsed_time": "2:06:59", "remaining_time": "0:26:32", "throughput": 4633.08, "total_tokens": 35301568} {"current_steps": 35090, "total_steps": 42420, "loss": 0.0533, "lr": 4.41264670324405e-06, "epoch": 16.544082979726543, "percentage": 82.72, "elapsed_time": "2:07:00", "remaining_time": "0:26:31", "throughput": 4633.1, "total_tokens": 35306112} {"current_steps": 35095, "total_steps": 42420, "loss": 0.0964, "lr": 4.406812940605604e-06, "epoch": 16.546440358321547, "percentage": 82.73, "elapsed_time": "2:07:01", "remaining_time": "0:26:30", "throughput": 4633.13, "total_tokens": 35311424} {"current_steps": 35100, "total_steps": 42420, "loss": 0.09, "lr": 4.400982664044067e-06, "epoch": 16.548797736916548, "percentage": 82.74, "elapsed_time": "2:07:02", "remaining_time": "0:26:29", "throughput": 4633.16, "total_tokens": 35317184} {"current_steps": 35105, "total_steps": 42420, "loss": 0.2567, "lr": 4.395155874546414e-06, "epoch": 16.551155115511552, "percentage": 82.76, "elapsed_time": "2:07:03", "remaining_time": "0:26:28", "throughput": 4633.18, "total_tokens": 35321760} {"current_steps": 35110, "total_steps": 42420, "loss": 0.0729, "lr": 4.38933257309902e-06, "epoch": 16.553512494106553, "percentage": 82.77, "elapsed_time": "2:07:04", "remaining_time": "0:26:27", "throughput": 4633.23, "total_tokens": 35328000} {"current_steps": 35115, "total_steps": 42420, "loss": 0.1527, "lr": 4.383512760687675e-06, "epoch": 16.555869872701557, "percentage": 82.78, "elapsed_time": "2:07:05", "remaining_time": "0:26:26", "throughput": 4633.24, "total_tokens": 35332416} {"current_steps": 35120, "total_steps": 42420, "loss": 0.0986, "lr": 4.377696438297568e-06, "epoch": 16.558227251296557, "percentage": 82.79, "elapsed_time": "2:07:07", "remaining_time": "0:26:25", "throughput": 4633.29, "total_tokens": 35339488} {"current_steps": 35125, "total_steps": 42420, "loss": 0.3709, "lr": 4.37188360691331e-06, "epoch": 16.56058462989156, "percentage": 82.8, "elapsed_time": "2:07:08", "remaining_time": "0:26:24", "throughput": 4633.33, "total_tokens": 35344864} {"current_steps": 35130, "total_steps": 42420, "loss": 0.0235, "lr": 4.3660742675189105e-06, "epoch": 16.562942008486562, "percentage": 82.81, "elapsed_time": "2:07:09", "remaining_time": "0:26:23", "throughput": 4633.35, "total_tokens": 35349344} {"current_steps": 35135, "total_steps": 42420, "loss": 0.1547, "lr": 4.360268421097802e-06, "epoch": 16.565299387081566, "percentage": 82.83, "elapsed_time": "2:07:10", "remaining_time": "0:26:22", "throughput": 4633.37, "total_tokens": 35353888} {"current_steps": 35140, "total_steps": 42420, "loss": 0.1906, "lr": 4.3544660686327985e-06, "epoch": 16.567656765676567, "percentage": 82.84, "elapsed_time": "2:07:11", "remaining_time": "0:26:20", "throughput": 4633.39, "total_tokens": 35358560} {"current_steps": 35145, "total_steps": 42420, "loss": 0.215, "lr": 4.348667211106147e-06, "epoch": 16.57001414427157, "percentage": 82.85, "elapsed_time": "2:07:12", "remaining_time": "0:26:19", "throughput": 4633.4, "total_tokens": 35363040} {"current_steps": 35150, "total_steps": 42420, "loss": 0.0739, "lr": 4.3428718494995e-06, "epoch": 16.572371522866572, "percentage": 82.86, "elapsed_time": "2:07:13", "remaining_time": "0:26:18", "throughput": 4633.4, "total_tokens": 35368192} {"current_steps": 35155, "total_steps": 42420, "loss": 0.2108, "lr": 4.337079984793909e-06, "epoch": 16.574728901461576, "percentage": 82.87, "elapsed_time": "2:07:14", "remaining_time": "0:26:17", "throughput": 4633.39, "total_tokens": 35373376} {"current_steps": 35160, "total_steps": 42420, "loss": 0.0149, "lr": 4.331291617969843e-06, "epoch": 16.577086280056577, "percentage": 82.89, "elapsed_time": "2:07:15", "remaining_time": "0:26:16", "throughput": 4633.41, "total_tokens": 35377632} {"current_steps": 35165, "total_steps": 42420, "loss": 0.1547, "lr": 4.325506750007169e-06, "epoch": 16.57944365865158, "percentage": 82.9, "elapsed_time": "2:07:16", "remaining_time": "0:26:15", "throughput": 4633.44, "total_tokens": 35382752} {"current_steps": 35170, "total_steps": 42420, "loss": 0.1647, "lr": 4.3197253818851706e-06, "epoch": 16.58180103724658, "percentage": 82.91, "elapsed_time": "2:07:17", "remaining_time": "0:26:14", "throughput": 4633.47, "total_tokens": 35388128} {"current_steps": 35175, "total_steps": 42420, "loss": 0.0338, "lr": 4.313947514582536e-06, "epoch": 16.584158415841586, "percentage": 82.92, "elapsed_time": "2:07:18", "remaining_time": "0:26:13", "throughput": 4633.5, "total_tokens": 35393536} {"current_steps": 35180, "total_steps": 42420, "loss": 0.0355, "lr": 4.308173149077357e-06, "epoch": 16.586515794436586, "percentage": 82.93, "elapsed_time": "2:07:19", "remaining_time": "0:26:12", "throughput": 4633.46, "total_tokens": 35397376} {"current_steps": 35185, "total_steps": 42420, "loss": 0.0738, "lr": 4.302402286347135e-06, "epoch": 16.58887317303159, "percentage": 82.94, "elapsed_time": "2:07:20", "remaining_time": "0:26:11", "throughput": 4633.49, "total_tokens": 35402272} {"current_steps": 35190, "total_steps": 42420, "loss": 0.1167, "lr": 4.2966349273687785e-06, "epoch": 16.59123055162659, "percentage": 82.96, "elapsed_time": "2:07:21", "remaining_time": "0:26:10", "throughput": 4633.5, "total_tokens": 35407104} {"current_steps": 35195, "total_steps": 42420, "loss": 0.0363, "lr": 4.290871073118608e-06, "epoch": 16.593587930221595, "percentage": 82.97, "elapsed_time": "2:07:22", "remaining_time": "0:26:08", "throughput": 4633.49, "total_tokens": 35411200} {"current_steps": 35200, "total_steps": 42420, "loss": 0.0461, "lr": 4.285110724572345e-06, "epoch": 16.595945308816596, "percentage": 82.98, "elapsed_time": "2:07:23", "remaining_time": "0:26:07", "throughput": 4633.54, "total_tokens": 35416448} {"current_steps": 35205, "total_steps": 42420, "loss": 0.1611, "lr": 4.2793538827051145e-06, "epoch": 16.5983026874116, "percentage": 82.99, "elapsed_time": "2:07:24", "remaining_time": "0:26:06", "throughput": 4633.57, "total_tokens": 35421472} {"current_steps": 35210, "total_steps": 42420, "loss": 0.0362, "lr": 4.273600548491458e-06, "epoch": 16.6006600660066, "percentage": 83.0, "elapsed_time": "2:07:25", "remaining_time": "0:26:05", "throughput": 4633.57, "total_tokens": 35425504} {"current_steps": 35215, "total_steps": 42420, "loss": 0.039, "lr": 4.267850722905317e-06, "epoch": 16.603017444601605, "percentage": 83.02, "elapsed_time": "2:07:26", "remaining_time": "0:26:04", "throughput": 4633.63, "total_tokens": 35431200} {"current_steps": 35220, "total_steps": 42420, "loss": 0.022, "lr": 4.262104406920034e-06, "epoch": 16.605374823196605, "percentage": 83.03, "elapsed_time": "2:07:27", "remaining_time": "0:26:03", "throughput": 4633.63, "total_tokens": 35435936} {"current_steps": 35225, "total_steps": 42420, "loss": 0.1594, "lr": 4.256361601508363e-06, "epoch": 16.607732201791606, "percentage": 83.04, "elapsed_time": "2:07:28", "remaining_time": "0:26:02", "throughput": 4633.67, "total_tokens": 35441056} {"current_steps": 35230, "total_steps": 42420, "loss": 0.1006, "lr": 4.250622307642469e-06, "epoch": 16.61008958038661, "percentage": 83.05, "elapsed_time": "2:07:29", "remaining_time": "0:26:01", "throughput": 4633.73, "total_tokens": 35447328} {"current_steps": 35235, "total_steps": 42420, "loss": 0.0965, "lr": 4.244886526293909e-06, "epoch": 16.61244695898161, "percentage": 83.06, "elapsed_time": "2:07:30", "remaining_time": "0:26:00", "throughput": 4633.75, "total_tokens": 35452320} {"current_steps": 35240, "total_steps": 42420, "loss": 0.0701, "lr": 4.239154258433661e-06, "epoch": 16.614804337576615, "percentage": 83.07, "elapsed_time": "2:07:31", "remaining_time": "0:25:59", "throughput": 4633.78, "total_tokens": 35457472} {"current_steps": 35245, "total_steps": 42420, "loss": 0.0442, "lr": 4.233425505032099e-06, "epoch": 16.617161716171616, "percentage": 83.09, "elapsed_time": "2:07:32", "remaining_time": "0:25:57", "throughput": 4633.8, "total_tokens": 35462016} {"current_steps": 35250, "total_steps": 42420, "loss": 0.1225, "lr": 4.227700267059004e-06, "epoch": 16.61951909476662, "percentage": 83.1, "elapsed_time": "2:07:34", "remaining_time": "0:25:56", "throughput": 4633.86, "total_tokens": 35468544} {"current_steps": 35255, "total_steps": 42420, "loss": 0.0834, "lr": 4.221978545483563e-06, "epoch": 16.62187647336162, "percentage": 83.11, "elapsed_time": "2:07:35", "remaining_time": "0:25:55", "throughput": 4633.88, "total_tokens": 35473568} {"current_steps": 35260, "total_steps": 42420, "loss": 0.2451, "lr": 4.216260341274359e-06, "epoch": 16.624233851956625, "percentage": 83.12, "elapsed_time": "2:07:36", "remaining_time": "0:25:54", "throughput": 4633.93, "total_tokens": 35479424} {"current_steps": 35265, "total_steps": 42420, "loss": 0.066, "lr": 4.2105456553993895e-06, "epoch": 16.626591230551625, "percentage": 83.13, "elapsed_time": "2:07:37", "remaining_time": "0:25:53", "throughput": 4633.97, "total_tokens": 35484352} {"current_steps": 35270, "total_steps": 42420, "loss": 0.1592, "lr": 4.204834488826059e-06, "epoch": 16.62894860914663, "percentage": 83.14, "elapsed_time": "2:07:38", "remaining_time": "0:25:52", "throughput": 4634.0, "total_tokens": 35489024} {"current_steps": 35275, "total_steps": 42420, "loss": 0.1471, "lr": 4.199126842521164e-06, "epoch": 16.63130598774163, "percentage": 83.16, "elapsed_time": "2:07:39", "remaining_time": "0:25:51", "throughput": 4634.01, "total_tokens": 35493504} {"current_steps": 35280, "total_steps": 42420, "loss": 0.0349, "lr": 4.19342271745092e-06, "epoch": 16.633663366336634, "percentage": 83.17, "elapsed_time": "2:07:40", "remaining_time": "0:25:50", "throughput": 4634.04, "total_tokens": 35498208} {"current_steps": 35285, "total_steps": 42420, "loss": 0.0495, "lr": 4.18772211458093e-06, "epoch": 16.636020744931635, "percentage": 83.18, "elapsed_time": "2:07:41", "remaining_time": "0:25:49", "throughput": 4634.05, "total_tokens": 35502912} {"current_steps": 35290, "total_steps": 42420, "loss": 0.0877, "lr": 4.182025034876225e-06, "epoch": 16.63837812352664, "percentage": 83.19, "elapsed_time": "2:07:42", "remaining_time": "0:25:48", "throughput": 4634.08, "total_tokens": 35507808} {"current_steps": 35295, "total_steps": 42420, "loss": 0.0508, "lr": 4.176331479301201e-06, "epoch": 16.64073550212164, "percentage": 83.2, "elapsed_time": "2:07:43", "remaining_time": "0:25:46", "throughput": 4634.07, "total_tokens": 35512000} {"current_steps": 35300, "total_steps": 42420, "loss": 0.0911, "lr": 4.170641448819701e-06, "epoch": 16.643092880716644, "percentage": 83.22, "elapsed_time": "2:07:44", "remaining_time": "0:25:45", "throughput": 4634.09, "total_tokens": 35516448} {"current_steps": 35305, "total_steps": 42420, "loss": 0.1017, "lr": 4.164954944394933e-06, "epoch": 16.645450259311644, "percentage": 83.23, "elapsed_time": "2:07:45", "remaining_time": "0:25:44", "throughput": 4634.12, "total_tokens": 35522112} {"current_steps": 35310, "total_steps": 42420, "loss": 0.0281, "lr": 4.159271966989536e-06, "epoch": 16.64780763790665, "percentage": 83.24, "elapsed_time": "2:07:46", "remaining_time": "0:25:43", "throughput": 4634.16, "total_tokens": 35527840} {"current_steps": 35315, "total_steps": 42420, "loss": 0.0373, "lr": 4.153592517565541e-06, "epoch": 16.65016501650165, "percentage": 83.25, "elapsed_time": "2:07:47", "remaining_time": "0:25:42", "throughput": 4634.19, "total_tokens": 35532704} {"current_steps": 35320, "total_steps": 42420, "loss": 0.0568, "lr": 4.147916597084378e-06, "epoch": 16.652522395096653, "percentage": 83.26, "elapsed_time": "2:07:48", "remaining_time": "0:25:41", "throughput": 4634.22, "total_tokens": 35538144} {"current_steps": 35325, "total_steps": 42420, "loss": 0.1638, "lr": 4.142244206506887e-06, "epoch": 16.654879773691654, "percentage": 83.27, "elapsed_time": "2:07:49", "remaining_time": "0:25:40", "throughput": 4634.24, "total_tokens": 35543392} {"current_steps": 35330, "total_steps": 42420, "loss": 0.0482, "lr": 4.136575346793309e-06, "epoch": 16.65723715228666, "percentage": 83.29, "elapsed_time": "2:07:50", "remaining_time": "0:25:39", "throughput": 4634.25, "total_tokens": 35547872} {"current_steps": 35335, "total_steps": 42420, "loss": 0.2771, "lr": 4.130910018903284e-06, "epoch": 16.65959453088166, "percentage": 83.3, "elapsed_time": "2:07:51", "remaining_time": "0:25:38", "throughput": 4634.28, "total_tokens": 35553120} {"current_steps": 35340, "total_steps": 42420, "loss": 0.1385, "lr": 4.12524822379586e-06, "epoch": 16.661951909476663, "percentage": 83.31, "elapsed_time": "2:07:52", "remaining_time": "0:25:37", "throughput": 4634.32, "total_tokens": 35558336} {"current_steps": 35345, "total_steps": 42420, "loss": 0.1251, "lr": 4.119589962429474e-06, "epoch": 16.664309288071664, "percentage": 83.32, "elapsed_time": "2:07:53", "remaining_time": "0:25:36", "throughput": 4634.34, "total_tokens": 35562752} {"current_steps": 35350, "total_steps": 42420, "loss": 0.1296, "lr": 4.113935235761979e-06, "epoch": 16.666666666666668, "percentage": 83.33, "elapsed_time": "2:07:54", "remaining_time": "0:25:34", "throughput": 4634.36, "total_tokens": 35567040} {"current_steps": 35355, "total_steps": 42420, "loss": 0.0456, "lr": 4.108284044750621e-06, "epoch": 16.66902404526167, "percentage": 83.35, "elapsed_time": "2:07:55", "remaining_time": "0:25:33", "throughput": 4634.39, "total_tokens": 35572256} {"current_steps": 35360, "total_steps": 42420, "loss": 0.0451, "lr": 4.102636390352054e-06, "epoch": 16.671381423856673, "percentage": 83.36, "elapsed_time": "2:07:56", "remaining_time": "0:25:32", "throughput": 4634.38, "total_tokens": 35576160} {"current_steps": 35365, "total_steps": 42420, "loss": 0.1257, "lr": 4.096992273522329e-06, "epoch": 16.673738802451673, "percentage": 83.37, "elapsed_time": "2:07:57", "remaining_time": "0:25:31", "throughput": 4634.37, "total_tokens": 35580320} {"current_steps": 35370, "total_steps": 42420, "loss": 0.0827, "lr": 4.0913516952169e-06, "epoch": 16.676096181046677, "percentage": 83.38, "elapsed_time": "2:07:58", "remaining_time": "0:25:30", "throughput": 4634.38, "total_tokens": 35585024} {"current_steps": 35375, "total_steps": 42420, "loss": 0.0356, "lr": 4.085714656390618e-06, "epoch": 16.678453559641678, "percentage": 83.39, "elapsed_time": "2:07:59", "remaining_time": "0:25:29", "throughput": 4634.39, "total_tokens": 35589536} {"current_steps": 35380, "total_steps": 42420, "loss": 0.2069, "lr": 4.080081157997751e-06, "epoch": 16.680810938236682, "percentage": 83.4, "elapsed_time": "2:08:00", "remaining_time": "0:25:28", "throughput": 4634.4, "total_tokens": 35593536} {"current_steps": 35385, "total_steps": 42420, "loss": 0.1368, "lr": 4.074451200991933e-06, "epoch": 16.683168316831683, "percentage": 83.42, "elapsed_time": "2:08:01", "remaining_time": "0:25:27", "throughput": 4634.39, "total_tokens": 35597664} {"current_steps": 35390, "total_steps": 42420, "loss": 0.0968, "lr": 4.068824786326234e-06, "epoch": 16.685525695426687, "percentage": 83.43, "elapsed_time": "2:08:02", "remaining_time": "0:25:26", "throughput": 4634.43, "total_tokens": 35602976} {"current_steps": 35395, "total_steps": 42420, "loss": 0.0258, "lr": 4.063201914953107e-06, "epoch": 16.687883074021688, "percentage": 83.44, "elapsed_time": "2:08:03", "remaining_time": "0:25:24", "throughput": 4634.44, "total_tokens": 35607264} {"current_steps": 35400, "total_steps": 42420, "loss": 0.0594, "lr": 4.05758258782441e-06, "epoch": 16.690240452616692, "percentage": 83.45, "elapsed_time": "2:08:04", "remaining_time": "0:25:23", "throughput": 4634.47, "total_tokens": 35612512} {"current_steps": 35405, "total_steps": 42420, "loss": 0.0651, "lr": 4.051966805891396e-06, "epoch": 16.692597831211692, "percentage": 83.46, "elapsed_time": "2:08:05", "remaining_time": "0:25:22", "throughput": 4634.5, "total_tokens": 35617376} {"current_steps": 35410, "total_steps": 42420, "loss": 0.1487, "lr": 4.046354570104726e-06, "epoch": 16.694955209806697, "percentage": 83.47, "elapsed_time": "2:08:06", "remaining_time": "0:25:21", "throughput": 4634.52, "total_tokens": 35622176} {"current_steps": 35415, "total_steps": 42420, "loss": 0.0853, "lr": 4.040745881414457e-06, "epoch": 16.697312588401697, "percentage": 83.49, "elapsed_time": "2:08:07", "remaining_time": "0:25:20", "throughput": 4634.53, "total_tokens": 35626496} {"current_steps": 35420, "total_steps": 42420, "loss": 0.0292, "lr": 4.035140740770047e-06, "epoch": 16.6996699669967, "percentage": 83.5, "elapsed_time": "2:08:08", "remaining_time": "0:25:19", "throughput": 4634.58, "total_tokens": 35632256} {"current_steps": 35425, "total_steps": 42420, "loss": 0.1202, "lr": 4.029539149120337e-06, "epoch": 16.702027345591702, "percentage": 83.51, "elapsed_time": "2:08:09", "remaining_time": "0:25:18", "throughput": 4634.6, "total_tokens": 35636928} {"current_steps": 35430, "total_steps": 42420, "loss": 0.0608, "lr": 4.023941107413595e-06, "epoch": 16.704384724186703, "percentage": 83.52, "elapsed_time": "2:08:10", "remaining_time": "0:25:17", "throughput": 4634.6, "total_tokens": 35641440} {"current_steps": 35435, "total_steps": 42420, "loss": 0.1729, "lr": 4.018346616597468e-06, "epoch": 16.706742102781707, "percentage": 83.53, "elapsed_time": "2:08:11", "remaining_time": "0:25:16", "throughput": 4634.63, "total_tokens": 35647424} {"current_steps": 35440, "total_steps": 42420, "loss": 0.0259, "lr": 4.0127556776190125e-06, "epoch": 16.709099481376708, "percentage": 83.55, "elapsed_time": "2:08:12", "remaining_time": "0:25:15", "throughput": 4634.67, "total_tokens": 35652640} {"current_steps": 35445, "total_steps": 42420, "loss": 0.2169, "lr": 4.007168291424676e-06, "epoch": 16.71145685997171, "percentage": 83.56, "elapsed_time": "2:08:13", "remaining_time": "0:25:13", "throughput": 4634.7, "total_tokens": 35657632} {"current_steps": 35450, "total_steps": 42420, "loss": 0.0533, "lr": 4.001584458960311e-06, "epoch": 16.713814238566712, "percentage": 83.57, "elapsed_time": "2:08:14", "remaining_time": "0:25:12", "throughput": 4634.71, "total_tokens": 35662336} {"current_steps": 35455, "total_steps": 42420, "loss": 0.1104, "lr": 3.996004181171164e-06, "epoch": 16.716171617161717, "percentage": 83.58, "elapsed_time": "2:08:15", "remaining_time": "0:25:11", "throughput": 4634.7, "total_tokens": 35666144} {"current_steps": 35460, "total_steps": 42420, "loss": 0.1501, "lr": 3.99042745900188e-06, "epoch": 16.718528995756717, "percentage": 83.59, "elapsed_time": "2:08:16", "remaining_time": "0:25:10", "throughput": 4634.7, "total_tokens": 35671008} {"current_steps": 35465, "total_steps": 42420, "loss": 0.0792, "lr": 3.984854293396515e-06, "epoch": 16.72088637435172, "percentage": 83.6, "elapsed_time": "2:08:17", "remaining_time": "0:25:09", "throughput": 4634.71, "total_tokens": 35675424} {"current_steps": 35470, "total_steps": 42420, "loss": 0.1291, "lr": 3.979284685298493e-06, "epoch": 16.723243752946722, "percentage": 83.62, "elapsed_time": "2:08:18", "remaining_time": "0:25:08", "throughput": 4634.74, "total_tokens": 35680448} {"current_steps": 35475, "total_steps": 42420, "loss": 0.1016, "lr": 3.973718635650661e-06, "epoch": 16.725601131541726, "percentage": 83.63, "elapsed_time": "2:08:19", "remaining_time": "0:25:07", "throughput": 4634.77, "total_tokens": 35686688} {"current_steps": 35480, "total_steps": 42420, "loss": 0.0448, "lr": 3.968156145395258e-06, "epoch": 16.727958510136727, "percentage": 83.64, "elapsed_time": "2:08:20", "remaining_time": "0:25:06", "throughput": 4634.77, "total_tokens": 35691648} {"current_steps": 35485, "total_steps": 42420, "loss": 0.211, "lr": 3.962597215473921e-06, "epoch": 16.73031588873173, "percentage": 83.65, "elapsed_time": "2:08:21", "remaining_time": "0:25:05", "throughput": 4634.79, "total_tokens": 35696480} {"current_steps": 35490, "total_steps": 42420, "loss": 0.1458, "lr": 3.957041846827681e-06, "epoch": 16.73267326732673, "percentage": 83.66, "elapsed_time": "2:08:22", "remaining_time": "0:25:04", "throughput": 4634.78, "total_tokens": 35700960} {"current_steps": 35495, "total_steps": 42420, "loss": 0.0798, "lr": 3.951490040396966e-06, "epoch": 16.735030645921736, "percentage": 83.68, "elapsed_time": "2:08:23", "remaining_time": "0:25:03", "throughput": 4634.8, "total_tokens": 35706016} {"current_steps": 35500, "total_steps": 42420, "loss": 0.183, "lr": 3.945941797121602e-06, "epoch": 16.737388024516736, "percentage": 83.69, "elapsed_time": "2:08:24", "remaining_time": "0:25:01", "throughput": 4634.8, "total_tokens": 35710880} {"current_steps": 35505, "total_steps": 42420, "loss": 0.0448, "lr": 3.940397117940822e-06, "epoch": 16.73974540311174, "percentage": 83.7, "elapsed_time": "2:08:25", "remaining_time": "0:25:00", "throughput": 4634.82, "total_tokens": 35715456} {"current_steps": 35510, "total_steps": 42420, "loss": 0.1305, "lr": 3.934856003793233e-06, "epoch": 16.74210278170674, "percentage": 83.71, "elapsed_time": "2:08:26", "remaining_time": "0:24:59", "throughput": 4634.84, "total_tokens": 35720320} {"current_steps": 35515, "total_steps": 42420, "loss": 0.2281, "lr": 3.929318455616862e-06, "epoch": 16.744460160301745, "percentage": 83.72, "elapsed_time": "2:08:28", "remaining_time": "0:24:58", "throughput": 4634.89, "total_tokens": 35726240} {"current_steps": 35520, "total_steps": 42420, "loss": 0.0347, "lr": 3.923784474349113e-06, "epoch": 16.746817538896746, "percentage": 83.73, "elapsed_time": "2:08:29", "remaining_time": "0:24:57", "throughput": 4634.92, "total_tokens": 35732864} {"current_steps": 35525, "total_steps": 42420, "loss": 0.0333, "lr": 3.9182540609267955e-06, "epoch": 16.74917491749175, "percentage": 83.75, "elapsed_time": "2:08:30", "remaining_time": "0:24:56", "throughput": 4634.96, "total_tokens": 35738400} {"current_steps": 35530, "total_steps": 42420, "loss": 0.2052, "lr": 3.912727216286119e-06, "epoch": 16.75153229608675, "percentage": 83.76, "elapsed_time": "2:08:31", "remaining_time": "0:24:55", "throughput": 4634.98, "total_tokens": 35743168} {"current_steps": 35535, "total_steps": 42420, "loss": 0.0405, "lr": 3.907203941362683e-06, "epoch": 16.753889674681755, "percentage": 83.77, "elapsed_time": "2:08:32", "remaining_time": "0:24:54", "throughput": 4635.01, "total_tokens": 35748192} {"current_steps": 35540, "total_steps": 42420, "loss": 0.0562, "lr": 3.901684237091485e-06, "epoch": 16.756247053276756, "percentage": 83.78, "elapsed_time": "2:08:33", "remaining_time": "0:24:53", "throughput": 4635.06, "total_tokens": 35753824} {"current_steps": 35545, "total_steps": 42420, "loss": 0.0613, "lr": 3.896168104406917e-06, "epoch": 16.75860443187176, "percentage": 83.79, "elapsed_time": "2:08:34", "remaining_time": "0:24:52", "throughput": 4635.07, "total_tokens": 35758656} {"current_steps": 35550, "total_steps": 42420, "loss": 0.0338, "lr": 3.8906555442427685e-06, "epoch": 16.76096181046676, "percentage": 83.8, "elapsed_time": "2:08:35", "remaining_time": "0:24:51", "throughput": 4635.1, "total_tokens": 35763136} {"current_steps": 35555, "total_steps": 42420, "loss": 0.0409, "lr": 3.885146557532218e-06, "epoch": 16.763319189061765, "percentage": 83.82, "elapsed_time": "2:08:36", "remaining_time": "0:24:49", "throughput": 4635.1, "total_tokens": 35767424} {"current_steps": 35560, "total_steps": 42420, "loss": 0.0915, "lr": 3.879641145207846e-06, "epoch": 16.765676567656765, "percentage": 83.83, "elapsed_time": "2:08:37", "remaining_time": "0:24:48", "throughput": 4635.13, "total_tokens": 35772320} {"current_steps": 35565, "total_steps": 42420, "loss": 0.0449, "lr": 3.8741393082016215e-06, "epoch": 16.76803394625177, "percentage": 83.84, "elapsed_time": "2:08:38", "remaining_time": "0:24:47", "throughput": 4635.13, "total_tokens": 35776576} {"current_steps": 35570, "total_steps": 42420, "loss": 0.032, "lr": 3.868641047444918e-06, "epoch": 16.77039132484677, "percentage": 83.85, "elapsed_time": "2:08:39", "remaining_time": "0:24:46", "throughput": 4635.12, "total_tokens": 35781184} {"current_steps": 35575, "total_steps": 42420, "loss": 0.0805, "lr": 3.863146363868494e-06, "epoch": 16.772748703441774, "percentage": 83.86, "elapsed_time": "2:08:40", "remaining_time": "0:24:45", "throughput": 4635.17, "total_tokens": 35786944} {"current_steps": 35580, "total_steps": 42420, "loss": 0.0174, "lr": 3.85765525840251e-06, "epoch": 16.775106082036775, "percentage": 83.88, "elapsed_time": "2:08:41", "remaining_time": "0:24:44", "throughput": 4635.19, "total_tokens": 35791904} {"current_steps": 35585, "total_steps": 42420, "loss": 0.2006, "lr": 3.852167731976511e-06, "epoch": 16.77746346063178, "percentage": 83.89, "elapsed_time": "2:08:42", "remaining_time": "0:24:43", "throughput": 4635.23, "total_tokens": 35797408} {"current_steps": 35590, "total_steps": 42420, "loss": 0.1325, "lr": 3.8466837855194505e-06, "epoch": 16.77982083922678, "percentage": 83.9, "elapsed_time": "2:08:44", "remaining_time": "0:24:42", "throughput": 4635.28, "total_tokens": 35803264} {"current_steps": 35595, "total_steps": 42420, "loss": 0.0993, "lr": 3.841203419959657e-06, "epoch": 16.782178217821784, "percentage": 83.91, "elapsed_time": "2:08:45", "remaining_time": "0:24:41", "throughput": 4635.33, "total_tokens": 35809024} {"current_steps": 35600, "total_steps": 42420, "loss": 0.0109, "lr": 3.83572663622487e-06, "epoch": 16.784535596416784, "percentage": 83.92, "elapsed_time": "2:08:46", "remaining_time": "0:24:40", "throughput": 4635.37, "total_tokens": 35814496} {"current_steps": 35605, "total_steps": 42420, "loss": 0.0518, "lr": 3.830253435242215e-06, "epoch": 16.78689297501179, "percentage": 83.93, "elapsed_time": "2:08:47", "remaining_time": "0:24:39", "throughput": 4635.38, "total_tokens": 35818944} {"current_steps": 35610, "total_steps": 42420, "loss": 0.2707, "lr": 3.82478381793821e-06, "epoch": 16.78925035360679, "percentage": 83.95, "elapsed_time": "2:08:48", "remaining_time": "0:24:37", "throughput": 4635.39, "total_tokens": 35823648} {"current_steps": 35615, "total_steps": 42420, "loss": 0.0623, "lr": 3.8193177852387714e-06, "epoch": 16.79160773220179, "percentage": 83.96, "elapsed_time": "2:08:49", "remaining_time": "0:24:36", "throughput": 4635.45, "total_tokens": 35830976} {"current_steps": 35620, "total_steps": 42420, "loss": 0.1557, "lr": 3.8138553380692026e-06, "epoch": 16.793965110796794, "percentage": 83.97, "elapsed_time": "2:08:50", "remaining_time": "0:24:35", "throughput": 4635.49, "total_tokens": 35836320} {"current_steps": 35625, "total_steps": 42420, "loss": 0.0199, "lr": 3.8083964773542064e-06, "epoch": 16.796322489391795, "percentage": 83.98, "elapsed_time": "2:08:51", "remaining_time": "0:24:34", "throughput": 4635.51, "total_tokens": 35841056} {"current_steps": 35630, "total_steps": 42420, "loss": 0.0301, "lr": 3.802941204017879e-06, "epoch": 16.7986798679868, "percentage": 83.99, "elapsed_time": "2:08:52", "remaining_time": "0:24:33", "throughput": 4635.55, "total_tokens": 35846208} {"current_steps": 35635, "total_steps": 42420, "loss": 0.0571, "lr": 3.7974895189836936e-06, "epoch": 16.8010372465818, "percentage": 84.01, "elapsed_time": "2:08:53", "remaining_time": "0:24:32", "throughput": 4635.55, "total_tokens": 35851104} {"current_steps": 35640, "total_steps": 42420, "loss": 0.0758, "lr": 3.792041423174536e-06, "epoch": 16.803394625176804, "percentage": 84.02, "elapsed_time": "2:08:54", "remaining_time": "0:24:31", "throughput": 4635.54, "total_tokens": 35855264} {"current_steps": 35645, "total_steps": 42420, "loss": 0.0942, "lr": 3.786596917512672e-06, "epoch": 16.805752003771804, "percentage": 84.03, "elapsed_time": "2:08:55", "remaining_time": "0:24:30", "throughput": 4635.55, "total_tokens": 35860288} {"current_steps": 35650, "total_steps": 42420, "loss": 0.1153, "lr": 3.7811560029197695e-06, "epoch": 16.80810938236681, "percentage": 84.04, "elapsed_time": "2:08:56", "remaining_time": "0:24:29", "throughput": 4635.57, "total_tokens": 35865056} {"current_steps": 35655, "total_steps": 42420, "loss": 0.0668, "lr": 3.775718680316878e-06, "epoch": 16.81046676096181, "percentage": 84.05, "elapsed_time": "2:08:58", "remaining_time": "0:24:28", "throughput": 4635.6, "total_tokens": 35870400} {"current_steps": 35660, "total_steps": 42420, "loss": 0.1941, "lr": 3.7702849506244475e-06, "epoch": 16.812824139556813, "percentage": 84.06, "elapsed_time": "2:08:59", "remaining_time": "0:24:27", "throughput": 4635.63, "total_tokens": 35875840} {"current_steps": 35665, "total_steps": 42420, "loss": 0.1627, "lr": 3.7648548147623143e-06, "epoch": 16.815181518151814, "percentage": 84.08, "elapsed_time": "2:09:00", "remaining_time": "0:24:25", "throughput": 4635.66, "total_tokens": 35880704} {"current_steps": 35670, "total_steps": 42420, "loss": 0.0832, "lr": 3.759428273649715e-06, "epoch": 16.817538896746818, "percentage": 84.09, "elapsed_time": "2:09:01", "remaining_time": "0:24:24", "throughput": 4635.68, "total_tokens": 35885312} {"current_steps": 35675, "total_steps": 42420, "loss": 0.0741, "lr": 3.7540053282052596e-06, "epoch": 16.81989627534182, "percentage": 84.1, "elapsed_time": "2:09:02", "remaining_time": "0:24:23", "throughput": 4635.71, "total_tokens": 35890688} {"current_steps": 35680, "total_steps": 42420, "loss": 0.076, "lr": 3.7485859793469634e-06, "epoch": 16.822253653936823, "percentage": 84.11, "elapsed_time": "2:09:03", "remaining_time": "0:24:22", "throughput": 4635.73, "total_tokens": 35894912} {"current_steps": 35685, "total_steps": 42420, "loss": 0.1174, "lr": 3.743170227992235e-06, "epoch": 16.824611032531823, "percentage": 84.12, "elapsed_time": "2:09:04", "remaining_time": "0:24:21", "throughput": 4635.76, "total_tokens": 35900192} {"current_steps": 35690, "total_steps": 42420, "loss": 0.1015, "lr": 3.737758075057865e-06, "epoch": 16.826968411126828, "percentage": 84.13, "elapsed_time": "2:09:05", "remaining_time": "0:24:20", "throughput": 4635.78, "total_tokens": 35904704} {"current_steps": 35695, "total_steps": 42420, "loss": 0.053, "lr": 3.7323495214600407e-06, "epoch": 16.82932578972183, "percentage": 84.15, "elapsed_time": "2:09:06", "remaining_time": "0:24:19", "throughput": 4635.81, "total_tokens": 35910240} {"current_steps": 35700, "total_steps": 42420, "loss": 0.1371, "lr": 3.7269445681143407e-06, "epoch": 16.831683168316832, "percentage": 84.16, "elapsed_time": "2:09:07", "remaining_time": "0:24:18", "throughput": 4635.83, "total_tokens": 35915072} {"current_steps": 35705, "total_steps": 42420, "loss": 0.096, "lr": 3.721543215935727e-06, "epoch": 16.834040546911833, "percentage": 84.17, "elapsed_time": "2:09:08", "remaining_time": "0:24:17", "throughput": 4635.85, "total_tokens": 35919616} {"current_steps": 35710, "total_steps": 42420, "loss": 0.1614, "lr": 3.7161454658385634e-06, "epoch": 16.836397925506837, "percentage": 84.18, "elapsed_time": "2:09:09", "remaining_time": "0:24:16", "throughput": 4635.86, "total_tokens": 35924416} {"current_steps": 35715, "total_steps": 42420, "loss": 0.1958, "lr": 3.710751318736591e-06, "epoch": 16.838755304101838, "percentage": 84.19, "elapsed_time": "2:09:10", "remaining_time": "0:24:15", "throughput": 4635.89, "total_tokens": 35930304} {"current_steps": 35720, "total_steps": 42420, "loss": 0.1101, "lr": 3.705360775542946e-06, "epoch": 16.841112682696842, "percentage": 84.21, "elapsed_time": "2:09:11", "remaining_time": "0:24:13", "throughput": 4635.9, "total_tokens": 35935104} {"current_steps": 35725, "total_steps": 42420, "loss": 0.205, "lr": 3.699973837170162e-06, "epoch": 16.843470061291843, "percentage": 84.22, "elapsed_time": "2:09:12", "remaining_time": "0:24:12", "throughput": 4635.95, "total_tokens": 35940800} {"current_steps": 35730, "total_steps": 42420, "loss": 0.0875, "lr": 3.6945905045301516e-06, "epoch": 16.845827439886847, "percentage": 84.23, "elapsed_time": "2:09:13", "remaining_time": "0:24:11", "throughput": 4636.0, "total_tokens": 35946400} {"current_steps": 35735, "total_steps": 42420, "loss": 0.0553, "lr": 3.6892107785342246e-06, "epoch": 16.848184818481847, "percentage": 84.24, "elapsed_time": "2:09:14", "remaining_time": "0:24:10", "throughput": 4636.02, "total_tokens": 35951456} {"current_steps": 35740, "total_steps": 42420, "loss": 0.0766, "lr": 3.6838346600930827e-06, "epoch": 16.85054219707685, "percentage": 84.25, "elapsed_time": "2:09:15", "remaining_time": "0:24:09", "throughput": 4636.0, "total_tokens": 35955968} {"current_steps": 35745, "total_steps": 42420, "loss": 0.1232, "lr": 3.678462150116799e-06, "epoch": 16.852899575671852, "percentage": 84.26, "elapsed_time": "2:09:16", "remaining_time": "0:24:08", "throughput": 4636.04, "total_tokens": 35961344} {"current_steps": 35750, "total_steps": 42420, "loss": 0.0166, "lr": 3.673093249514853e-06, "epoch": 16.855256954266856, "percentage": 84.28, "elapsed_time": "2:09:17", "remaining_time": "0:24:07", "throughput": 4636.06, "total_tokens": 35965824} {"current_steps": 35755, "total_steps": 42420, "loss": 0.2354, "lr": 3.66772795919611e-06, "epoch": 16.857614332861857, "percentage": 84.29, "elapsed_time": "2:09:18", "remaining_time": "0:24:06", "throughput": 4636.04, "total_tokens": 35969920} {"current_steps": 35760, "total_steps": 42420, "loss": 0.1553, "lr": 3.662366280068827e-06, "epoch": 16.85997171145686, "percentage": 84.3, "elapsed_time": "2:09:19", "remaining_time": "0:24:05", "throughput": 4636.05, "total_tokens": 35975008} {"current_steps": 35765, "total_steps": 42420, "loss": 0.0437, "lr": 3.657008213040636e-06, "epoch": 16.862329090051862, "percentage": 84.31, "elapsed_time": "2:09:21", "remaining_time": "0:24:04", "throughput": 4636.07, "total_tokens": 35980640} {"current_steps": 35770, "total_steps": 42420, "loss": 0.2136, "lr": 3.6516537590185697e-06, "epoch": 16.864686468646866, "percentage": 84.32, "elapsed_time": "2:09:22", "remaining_time": "0:24:03", "throughput": 4636.09, "total_tokens": 35985824} {"current_steps": 35775, "total_steps": 42420, "loss": 0.0176, "lr": 3.64630291890905e-06, "epoch": 16.867043847241867, "percentage": 84.34, "elapsed_time": "2:09:23", "remaining_time": "0:24:01", "throughput": 4636.1, "total_tokens": 35990784} {"current_steps": 35780, "total_steps": 42420, "loss": 0.2195, "lr": 3.6409556936178784e-06, "epoch": 16.86940122583687, "percentage": 84.35, "elapsed_time": "2:09:24", "remaining_time": "0:24:00", "throughput": 4636.1, "total_tokens": 35995264} {"current_steps": 35785, "total_steps": 42420, "loss": 0.0642, "lr": 3.635612084050255e-06, "epoch": 16.87175860443187, "percentage": 84.36, "elapsed_time": "2:09:25", "remaining_time": "0:23:59", "throughput": 4636.09, "total_tokens": 35999264} {"current_steps": 35790, "total_steps": 42420, "loss": 0.0548, "lr": 3.630272091110756e-06, "epoch": 16.874115983026876, "percentage": 84.37, "elapsed_time": "2:09:26", "remaining_time": "0:23:58", "throughput": 4636.1, "total_tokens": 36003968} {"current_steps": 35795, "total_steps": 42420, "loss": 0.2334, "lr": 3.6249357157033565e-06, "epoch": 16.876473361621876, "percentage": 84.38, "elapsed_time": "2:09:26", "remaining_time": "0:23:57", "throughput": 4636.12, "total_tokens": 36008576} {"current_steps": 35800, "total_steps": 42420, "loss": 0.0289, "lr": 3.619602958731419e-06, "epoch": 16.87883074021688, "percentage": 84.39, "elapsed_time": "2:09:28", "remaining_time": "0:23:56", "throughput": 4636.16, "total_tokens": 36014464} {"current_steps": 35805, "total_steps": 42420, "loss": 0.0998, "lr": 3.6142738210976744e-06, "epoch": 16.88118811881188, "percentage": 84.41, "elapsed_time": "2:09:29", "remaining_time": "0:23:55", "throughput": 4636.15, "total_tokens": 36018496} {"current_steps": 35810, "total_steps": 42420, "loss": 0.0247, "lr": 3.6089483037042624e-06, "epoch": 16.883545497406885, "percentage": 84.42, "elapsed_time": "2:09:29", "remaining_time": "0:23:54", "throughput": 4636.16, "total_tokens": 36022624} {"current_steps": 35815, "total_steps": 42420, "loss": 0.1349, "lr": 3.603626407452704e-06, "epoch": 16.885902876001886, "percentage": 84.43, "elapsed_time": "2:09:31", "remaining_time": "0:23:53", "throughput": 4636.21, "total_tokens": 36028992} {"current_steps": 35820, "total_steps": 42420, "loss": 0.0394, "lr": 3.598308133243908e-06, "epoch": 16.888260254596887, "percentage": 84.44, "elapsed_time": "2:09:32", "remaining_time": "0:23:52", "throughput": 4636.23, "total_tokens": 36033472} {"current_steps": 35825, "total_steps": 42420, "loss": 0.12, "lr": 3.59299348197816e-06, "epoch": 16.89061763319189, "percentage": 84.45, "elapsed_time": "2:09:33", "remaining_time": "0:23:50", "throughput": 4636.27, "total_tokens": 36039264} {"current_steps": 35830, "total_steps": 42420, "loss": 0.1407, "lr": 3.5876824545551497e-06, "epoch": 16.89297501178689, "percentage": 84.46, "elapsed_time": "2:09:34", "remaining_time": "0:23:49", "throughput": 4636.33, "total_tokens": 36045696} {"current_steps": 35835, "total_steps": 42420, "loss": 0.0169, "lr": 3.5823750518739373e-06, "epoch": 16.895332390381895, "percentage": 84.48, "elapsed_time": "2:09:35", "remaining_time": "0:23:48", "throughput": 4636.34, "total_tokens": 36050272} {"current_steps": 35840, "total_steps": 42420, "loss": 0.0853, "lr": 3.5770712748329826e-06, "epoch": 16.897689768976896, "percentage": 84.49, "elapsed_time": "2:09:36", "remaining_time": "0:23:47", "throughput": 4636.37, "total_tokens": 36055232} {"current_steps": 35845, "total_steps": 42420, "loss": 0.135, "lr": 3.5717711243301172e-06, "epoch": 16.9000471475719, "percentage": 84.5, "elapsed_time": "2:09:37", "remaining_time": "0:23:46", "throughput": 4636.39, "total_tokens": 36061376} {"current_steps": 35850, "total_steps": 42420, "loss": 0.2309, "lr": 3.5664746012625677e-06, "epoch": 16.9024045261669, "percentage": 84.51, "elapsed_time": "2:09:38", "remaining_time": "0:23:45", "throughput": 4636.44, "total_tokens": 36066816} {"current_steps": 35855, "total_steps": 42420, "loss": 0.0737, "lr": 3.5611817065269475e-06, "epoch": 16.904761904761905, "percentage": 84.52, "elapsed_time": "2:09:40", "remaining_time": "0:23:44", "throughput": 4636.46, "total_tokens": 36071744} {"current_steps": 35860, "total_steps": 42420, "loss": 0.1456, "lr": 3.5558924410192566e-06, "epoch": 16.907119283356906, "percentage": 84.54, "elapsed_time": "2:09:40", "remaining_time": "0:23:43", "throughput": 4636.47, "total_tokens": 36075968} {"current_steps": 35865, "total_steps": 42420, "loss": 0.0314, "lr": 3.5506068056348736e-06, "epoch": 16.90947666195191, "percentage": 84.55, "elapsed_time": "2:09:42", "remaining_time": "0:23:42", "throughput": 4636.47, "total_tokens": 36081056} {"current_steps": 35870, "total_steps": 42420, "loss": 0.0752, "lr": 3.545324801268568e-06, "epoch": 16.91183404054691, "percentage": 84.56, "elapsed_time": "2:09:42", "remaining_time": "0:23:41", "throughput": 4636.49, "total_tokens": 36085536} {"current_steps": 35875, "total_steps": 42420, "loss": 0.116, "lr": 3.540046428814495e-06, "epoch": 16.914191419141915, "percentage": 84.57, "elapsed_time": "2:09:44", "remaining_time": "0:23:40", "throughput": 4636.5, "total_tokens": 36090720} {"current_steps": 35880, "total_steps": 42420, "loss": 0.1252, "lr": 3.534771689166197e-06, "epoch": 16.916548797736915, "percentage": 84.58, "elapsed_time": "2:09:44", "remaining_time": "0:23:38", "throughput": 4636.51, "total_tokens": 36094848} {"current_steps": 35885, "total_steps": 42420, "loss": 0.3096, "lr": 3.5295005832165884e-06, "epoch": 16.91890617633192, "percentage": 84.59, "elapsed_time": "2:09:46", "remaining_time": "0:23:37", "throughput": 4636.51, "total_tokens": 36100160} {"current_steps": 35890, "total_steps": 42420, "loss": 0.0434, "lr": 3.52423311185798e-06, "epoch": 16.92126355492692, "percentage": 84.61, "elapsed_time": "2:09:47", "remaining_time": "0:23:36", "throughput": 4636.57, "total_tokens": 36106496} {"current_steps": 35895, "total_steps": 42420, "loss": 0.2507, "lr": 3.5189692759820705e-06, "epoch": 16.923620933521924, "percentage": 84.62, "elapsed_time": "2:09:48", "remaining_time": "0:23:35", "throughput": 4636.6, "total_tokens": 36111552} {"current_steps": 35900, "total_steps": 42420, "loss": 0.0537, "lr": 3.5137090764799376e-06, "epoch": 16.925978312116925, "percentage": 84.63, "elapsed_time": "2:09:49", "remaining_time": "0:23:34", "throughput": 4636.6, "total_tokens": 36116416} {"current_steps": 35905, "total_steps": 42420, "loss": 0.1372, "lr": 3.5084525142420387e-06, "epoch": 16.92833569071193, "percentage": 84.64, "elapsed_time": "2:09:50", "remaining_time": "0:23:33", "throughput": 4636.64, "total_tokens": 36121920} {"current_steps": 35910, "total_steps": 42420, "loss": 0.063, "lr": 3.503199590158224e-06, "epoch": 16.93069306930693, "percentage": 84.65, "elapsed_time": "2:09:51", "remaining_time": "0:23:32", "throughput": 4636.66, "total_tokens": 36126560} {"current_steps": 35915, "total_steps": 42420, "loss": 0.0662, "lr": 3.4979503051177226e-06, "epoch": 16.933050447901934, "percentage": 84.67, "elapsed_time": "2:09:52", "remaining_time": "0:23:31", "throughput": 4636.69, "total_tokens": 36131072} {"current_steps": 35920, "total_steps": 42420, "loss": 0.1085, "lr": 3.4927046600091577e-06, "epoch": 16.935407826496935, "percentage": 84.68, "elapsed_time": "2:09:53", "remaining_time": "0:23:30", "throughput": 4636.72, "total_tokens": 36136320} {"current_steps": 35925, "total_steps": 42420, "loss": 0.1661, "lr": 3.4874626557205136e-06, "epoch": 16.93776520509194, "percentage": 84.69, "elapsed_time": "2:09:54", "remaining_time": "0:23:29", "throughput": 4636.76, "total_tokens": 36140992} {"current_steps": 35930, "total_steps": 42420, "loss": 0.0383, "lr": 3.482224293139183e-06, "epoch": 16.94012258368694, "percentage": 84.7, "elapsed_time": "2:09:55", "remaining_time": "0:23:28", "throughput": 4636.79, "total_tokens": 36146080} {"current_steps": 35935, "total_steps": 42420, "loss": 0.0248, "lr": 3.476989573151926e-06, "epoch": 16.942479962281944, "percentage": 84.71, "elapsed_time": "2:09:56", "remaining_time": "0:23:27", "throughput": 4636.84, "total_tokens": 36151712} {"current_steps": 35940, "total_steps": 42420, "loss": 0.2784, "lr": 3.4717584966448946e-06, "epoch": 16.944837340876944, "percentage": 84.72, "elapsed_time": "2:09:57", "remaining_time": "0:23:25", "throughput": 4636.83, "total_tokens": 36155968} {"current_steps": 35945, "total_steps": 42420, "loss": 0.097, "lr": 3.4665310645036197e-06, "epoch": 16.94719471947195, "percentage": 84.74, "elapsed_time": "2:09:58", "remaining_time": "0:23:24", "throughput": 4636.83, "total_tokens": 36160608} {"current_steps": 35950, "total_steps": 42420, "loss": 0.143, "lr": 3.4613072776130213e-06, "epoch": 16.94955209806695, "percentage": 84.75, "elapsed_time": "2:09:59", "remaining_time": "0:23:23", "throughput": 4636.87, "total_tokens": 36165984} {"current_steps": 35955, "total_steps": 42420, "loss": 0.0559, "lr": 3.4560871368573915e-06, "epoch": 16.951909476661953, "percentage": 84.76, "elapsed_time": "2:10:00", "remaining_time": "0:23:22", "throughput": 4636.89, "total_tokens": 36170848} {"current_steps": 35960, "total_steps": 42420, "loss": 0.0395, "lr": 3.450870643120421e-06, "epoch": 16.954266855256954, "percentage": 84.77, "elapsed_time": "2:10:01", "remaining_time": "0:23:21", "throughput": 4636.91, "total_tokens": 36175360} {"current_steps": 35965, "total_steps": 42420, "loss": 0.0419, "lr": 3.445657797285162e-06, "epoch": 16.956624233851958, "percentage": 84.78, "elapsed_time": "2:10:02", "remaining_time": "0:23:20", "throughput": 4636.93, "total_tokens": 36179584} {"current_steps": 35970, "total_steps": 42420, "loss": 0.0877, "lr": 3.4404486002340723e-06, "epoch": 16.95898161244696, "percentage": 84.79, "elapsed_time": "2:10:03", "remaining_time": "0:23:19", "throughput": 4636.96, "total_tokens": 36184800} {"current_steps": 35975, "total_steps": 42420, "loss": 0.0269, "lr": 3.435243052848969e-06, "epoch": 16.961338991041963, "percentage": 84.81, "elapsed_time": "2:10:04", "remaining_time": "0:23:18", "throughput": 4636.97, "total_tokens": 36189056} {"current_steps": 35980, "total_steps": 42420, "loss": 0.1136, "lr": 3.4300411560110656e-06, "epoch": 16.963696369636963, "percentage": 84.82, "elapsed_time": "2:10:05", "remaining_time": "0:23:17", "throughput": 4636.97, "total_tokens": 36193344} {"current_steps": 35985, "total_steps": 42420, "loss": 0.0347, "lr": 3.4248429106009616e-06, "epoch": 16.966053748231968, "percentage": 84.83, "elapsed_time": "2:10:06", "remaining_time": "0:23:15", "throughput": 4636.98, "total_tokens": 36198240} {"current_steps": 35990, "total_steps": 42420, "loss": 0.1005, "lr": 3.419648317498625e-06, "epoch": 16.968411126826968, "percentage": 84.84, "elapsed_time": "2:10:07", "remaining_time": "0:23:14", "throughput": 4636.99, "total_tokens": 36202656} {"current_steps": 35995, "total_steps": 42420, "loss": 0.0511, "lr": 3.4144573775834134e-06, "epoch": 16.970768505421972, "percentage": 84.85, "elapsed_time": "2:10:08", "remaining_time": "0:23:13", "throughput": 4637.01, "total_tokens": 36208064} {"current_steps": 36000, "total_steps": 42420, "loss": 0.1634, "lr": 3.409270091734068e-06, "epoch": 16.973125884016973, "percentage": 84.87, "elapsed_time": "2:10:09", "remaining_time": "0:23:12", "throughput": 4637.02, "total_tokens": 36212352} {"current_steps": 36005, "total_steps": 42420, "loss": 0.1399, "lr": 3.4040864608287067e-06, "epoch": 16.975483262611977, "percentage": 84.88, "elapsed_time": "2:10:10", "remaining_time": "0:23:11", "throughput": 4637.06, "total_tokens": 36217184} {"current_steps": 36010, "total_steps": 42420, "loss": 0.1385, "lr": 3.398906485744835e-06, "epoch": 16.977840641206978, "percentage": 84.89, "elapsed_time": "2:10:11", "remaining_time": "0:23:10", "throughput": 4637.07, "total_tokens": 36222400} {"current_steps": 36015, "total_steps": 42420, "loss": 0.0208, "lr": 3.393730167359321e-06, "epoch": 16.980198019801982, "percentage": 84.9, "elapsed_time": "2:10:12", "remaining_time": "0:23:09", "throughput": 4637.1, "total_tokens": 36227264} {"current_steps": 36020, "total_steps": 42420, "loss": 0.1717, "lr": 3.3885575065484397e-06, "epoch": 16.982555398396983, "percentage": 84.91, "elapsed_time": "2:10:13", "remaining_time": "0:23:08", "throughput": 4637.15, "total_tokens": 36232864} {"current_steps": 36025, "total_steps": 42420, "loss": 0.1768, "lr": 3.383388504187829e-06, "epoch": 16.984912776991983, "percentage": 84.92, "elapsed_time": "2:10:14", "remaining_time": "0:23:07", "throughput": 4637.16, "total_tokens": 36237664} {"current_steps": 36030, "total_steps": 42420, "loss": 0.063, "lr": 3.378223161152519e-06, "epoch": 16.987270155586987, "percentage": 84.94, "elapsed_time": "2:10:15", "remaining_time": "0:23:06", "throughput": 4637.17, "total_tokens": 36242752} {"current_steps": 36035, "total_steps": 42420, "loss": 0.1454, "lr": 3.373061478316908e-06, "epoch": 16.989627534181988, "percentage": 84.95, "elapsed_time": "2:10:16", "remaining_time": "0:23:05", "throughput": 4637.19, "total_tokens": 36247872} {"current_steps": 36040, "total_steps": 42420, "loss": 0.0221, "lr": 3.367903456554783e-06, "epoch": 16.991984912776992, "percentage": 84.96, "elapsed_time": "2:10:17", "remaining_time": "0:23:03", "throughput": 4637.22, "total_tokens": 36252800} {"current_steps": 36045, "total_steps": 42420, "loss": 0.0391, "lr": 3.362749096739312e-06, "epoch": 16.994342291371993, "percentage": 84.97, "elapsed_time": "2:10:18", "remaining_time": "0:23:02", "throughput": 4637.24, "total_tokens": 36257664} {"current_steps": 36050, "total_steps": 42420, "loss": 0.1019, "lr": 3.357598399743045e-06, "epoch": 16.996699669966997, "percentage": 84.98, "elapsed_time": "2:10:19", "remaining_time": "0:23:01", "throughput": 4637.23, "total_tokens": 36262112} {"current_steps": 36055, "total_steps": 42420, "loss": 0.0424, "lr": 3.3524513664378975e-06, "epoch": 16.999057048561998, "percentage": 85.0, "elapsed_time": "2:10:20", "remaining_time": "0:23:00", "throughput": 4637.26, "total_tokens": 36267328} {"current_steps": 36057, "total_steps": 42420, "eval_loss": 0.1527273803949356, "epoch": 17.0, "percentage": 85.0, "elapsed_time": "2:10:36", "remaining_time": "0:23:02", "throughput": 4628.3, "total_tokens": 36269152} {"current_steps": 36060, "total_steps": 42420, "loss": 0.0381, "lr": 3.347307997695179e-06, "epoch": 17.001414427157002, "percentage": 85.01, "elapsed_time": "2:10:38", "remaining_time": "0:23:02", "throughput": 4627.31, "total_tokens": 36272320} {"current_steps": 36065, "total_steps": 42420, "loss": 0.0891, "lr": 3.3421682943855727e-06, "epoch": 17.003771805752002, "percentage": 85.02, "elapsed_time": "2:10:39", "remaining_time": "0:23:01", "throughput": 4627.3, "total_tokens": 36276640} {"current_steps": 36070, "total_steps": 42420, "loss": 0.0952, "lr": 3.3370322573791468e-06, "epoch": 17.006129184347007, "percentage": 85.03, "elapsed_time": "2:10:40", "remaining_time": "0:23:00", "throughput": 4627.3, "total_tokens": 36281216} {"current_steps": 36075, "total_steps": 42420, "loss": 0.0214, "lr": 3.331899887545342e-06, "epoch": 17.008486562942007, "percentage": 85.04, "elapsed_time": "2:10:41", "remaining_time": "0:22:59", "throughput": 4627.27, "total_tokens": 36285952} {"current_steps": 36080, "total_steps": 42420, "loss": 0.0962, "lr": 3.326771185752986e-06, "epoch": 17.01084394153701, "percentage": 85.05, "elapsed_time": "2:10:42", "remaining_time": "0:22:58", "throughput": 4627.29, "total_tokens": 36290528} {"current_steps": 36085, "total_steps": 42420, "loss": 0.0669, "lr": 3.3216461528702753e-06, "epoch": 17.013201320132012, "percentage": 85.07, "elapsed_time": "2:10:43", "remaining_time": "0:22:57", "throughput": 4627.33, "total_tokens": 36295840} {"current_steps": 36090, "total_steps": 42420, "loss": 0.126, "lr": 3.3165247897647996e-06, "epoch": 17.015558698727016, "percentage": 85.08, "elapsed_time": "2:10:44", "remaining_time": "0:22:55", "throughput": 4627.34, "total_tokens": 36300704} {"current_steps": 36095, "total_steps": 42420, "loss": 0.1135, "lr": 3.3114070973035067e-06, "epoch": 17.017916077322017, "percentage": 85.09, "elapsed_time": "2:10:45", "remaining_time": "0:22:54", "throughput": 4627.37, "total_tokens": 36305376} {"current_steps": 36100, "total_steps": 42420, "loss": 0.1416, "lr": 3.30629307635274e-06, "epoch": 17.02027345591702, "percentage": 85.1, "elapsed_time": "2:10:46", "remaining_time": "0:22:53", "throughput": 4627.41, "total_tokens": 36310528} {"current_steps": 36105, "total_steps": 42420, "loss": 0.0411, "lr": 3.3011827277782183e-06, "epoch": 17.02263083451202, "percentage": 85.11, "elapsed_time": "2:10:47", "remaining_time": "0:22:52", "throughput": 4627.44, "total_tokens": 36316032} {"current_steps": 36110, "total_steps": 42420, "loss": 0.1029, "lr": 3.296076052445035e-06, "epoch": 17.024988213107026, "percentage": 85.12, "elapsed_time": "2:10:49", "remaining_time": "0:22:51", "throughput": 4627.5, "total_tokens": 36322656} {"current_steps": 36115, "total_steps": 42420, "loss": 0.127, "lr": 3.2909730512176664e-06, "epoch": 17.027345591702026, "percentage": 85.14, "elapsed_time": "2:10:50", "remaining_time": "0:22:50", "throughput": 4627.5, "total_tokens": 36327040} {"current_steps": 36120, "total_steps": 42420, "loss": 0.1527, "lr": 3.285873724959959e-06, "epoch": 17.02970297029703, "percentage": 85.15, "elapsed_time": "2:10:51", "remaining_time": "0:22:49", "throughput": 4627.54, "total_tokens": 36332480} {"current_steps": 36125, "total_steps": 42420, "loss": 0.0233, "lr": 3.2807780745351455e-06, "epoch": 17.03206034889203, "percentage": 85.16, "elapsed_time": "2:10:52", "remaining_time": "0:22:48", "throughput": 4627.57, "total_tokens": 36337312} {"current_steps": 36130, "total_steps": 42420, "loss": 0.0806, "lr": 3.2756861008058415e-06, "epoch": 17.034417727487035, "percentage": 85.17, "elapsed_time": "2:10:53", "remaining_time": "0:22:47", "throughput": 4627.59, "total_tokens": 36342272} {"current_steps": 36135, "total_steps": 42420, "loss": 0.0458, "lr": 3.2705978046340153e-06, "epoch": 17.036775106082036, "percentage": 85.18, "elapsed_time": "2:10:54", "remaining_time": "0:22:46", "throughput": 4627.61, "total_tokens": 36346880} {"current_steps": 36140, "total_steps": 42420, "loss": 0.0436, "lr": 3.2655131868810363e-06, "epoch": 17.03913248467704, "percentage": 85.2, "elapsed_time": "2:10:55", "remaining_time": "0:22:45", "throughput": 4627.64, "total_tokens": 36354240} {"current_steps": 36145, "total_steps": 42420, "loss": 0.0236, "lr": 3.2604322484076437e-06, "epoch": 17.04148986327204, "percentage": 85.21, "elapsed_time": "2:10:56", "remaining_time": "0:22:44", "throughput": 4627.66, "total_tokens": 36358912} {"current_steps": 36150, "total_steps": 42420, "loss": 0.1373, "lr": 3.2553549900739555e-06, "epoch": 17.043847241867045, "percentage": 85.22, "elapsed_time": "2:10:57", "remaining_time": "0:22:42", "throughput": 4627.67, "total_tokens": 36363456} {"current_steps": 36155, "total_steps": 42420, "loss": 0.1078, "lr": 3.2502814127394644e-06, "epoch": 17.046204620462046, "percentage": 85.23, "elapsed_time": "2:10:58", "remaining_time": "0:22:41", "throughput": 4627.67, "total_tokens": 36367744} {"current_steps": 36160, "total_steps": 42420, "loss": 0.1092, "lr": 3.245211517263039e-06, "epoch": 17.04856199905705, "percentage": 85.24, "elapsed_time": "2:10:59", "remaining_time": "0:22:40", "throughput": 4627.71, "total_tokens": 36373056} {"current_steps": 36165, "total_steps": 42420, "loss": 0.129, "lr": 3.240145304502931e-06, "epoch": 17.05091937765205, "percentage": 85.25, "elapsed_time": "2:11:01", "remaining_time": "0:22:39", "throughput": 4627.74, "total_tokens": 36379392} {"current_steps": 36170, "total_steps": 42420, "loss": 0.1901, "lr": 3.235082775316764e-06, "epoch": 17.053276756247055, "percentage": 85.27, "elapsed_time": "2:11:02", "remaining_time": "0:22:38", "throughput": 4627.77, "total_tokens": 36384320} {"current_steps": 36175, "total_steps": 42420, "loss": 0.1456, "lr": 3.2300239305615348e-06, "epoch": 17.055634134842055, "percentage": 85.28, "elapsed_time": "2:11:03", "remaining_time": "0:22:37", "throughput": 4627.84, "total_tokens": 36391168} {"current_steps": 36180, "total_steps": 42420, "loss": 0.0304, "lr": 3.224968771093617e-06, "epoch": 17.05799151343706, "percentage": 85.29, "elapsed_time": "2:11:04", "remaining_time": "0:22:36", "throughput": 4627.87, "total_tokens": 36396768} {"current_steps": 36185, "total_steps": 42420, "loss": 0.073, "lr": 3.2199172977687707e-06, "epoch": 17.06034889203206, "percentage": 85.3, "elapsed_time": "2:11:05", "remaining_time": "0:22:35", "throughput": 4627.89, "total_tokens": 36401952} {"current_steps": 36190, "total_steps": 42420, "loss": 0.2574, "lr": 3.2148695114421228e-06, "epoch": 17.062706270627064, "percentage": 85.31, "elapsed_time": "2:11:06", "remaining_time": "0:22:34", "throughput": 4627.9, "total_tokens": 36406368} {"current_steps": 36195, "total_steps": 42420, "loss": 0.1056, "lr": 3.209825412968173e-06, "epoch": 17.065063649222065, "percentage": 85.33, "elapsed_time": "2:11:07", "remaining_time": "0:22:33", "throughput": 4627.91, "total_tokens": 36410688} {"current_steps": 36200, "total_steps": 42420, "loss": 0.1517, "lr": 3.2047850032008054e-06, "epoch": 17.06742102781707, "percentage": 85.34, "elapsed_time": "2:11:08", "remaining_time": "0:22:32", "throughput": 4627.93, "total_tokens": 36416096} {"current_steps": 36205, "total_steps": 42420, "loss": 0.0287, "lr": 3.199748282993273e-06, "epoch": 17.06977840641207, "percentage": 85.35, "elapsed_time": "2:11:09", "remaining_time": "0:22:30", "throughput": 4627.96, "total_tokens": 36421440} {"current_steps": 36210, "total_steps": 42420, "loss": 0.0785, "lr": 3.1947152531982106e-06, "epoch": 17.072135785007074, "percentage": 85.36, "elapsed_time": "2:11:11", "remaining_time": "0:22:29", "throughput": 4627.99, "total_tokens": 36426880} {"current_steps": 36215, "total_steps": 42420, "loss": 0.1754, "lr": 3.189685914667623e-06, "epoch": 17.074493163602074, "percentage": 85.37, "elapsed_time": "2:11:12", "remaining_time": "0:22:28", "throughput": 4628.0, "total_tokens": 36431936} {"current_steps": 36220, "total_steps": 42420, "loss": 0.1233, "lr": 3.1846602682528983e-06, "epoch": 17.076850542197075, "percentage": 85.38, "elapsed_time": "2:11:13", "remaining_time": "0:22:27", "throughput": 4627.99, "total_tokens": 36436352} {"current_steps": 36225, "total_steps": 42420, "loss": 0.0349, "lr": 3.179638314804778e-06, "epoch": 17.07920792079208, "percentage": 85.4, "elapsed_time": "2:11:14", "remaining_time": "0:22:26", "throughput": 4627.99, "total_tokens": 36441312} {"current_steps": 36230, "total_steps": 42420, "loss": 0.1784, "lr": 3.174620055173405e-06, "epoch": 17.08156529938708, "percentage": 85.41, "elapsed_time": "2:11:15", "remaining_time": "0:22:25", "throughput": 4628.03, "total_tokens": 36446528} {"current_steps": 36235, "total_steps": 42420, "loss": 0.0465, "lr": 3.1696054902082828e-06, "epoch": 17.083922677982084, "percentage": 85.42, "elapsed_time": "2:11:16", "remaining_time": "0:22:24", "throughput": 4628.03, "total_tokens": 36451328} {"current_steps": 36240, "total_steps": 42420, "loss": 0.2452, "lr": 3.1645946207582932e-06, "epoch": 17.086280056577085, "percentage": 85.43, "elapsed_time": "2:11:17", "remaining_time": "0:22:23", "throughput": 4628.06, "total_tokens": 36456320} {"current_steps": 36245, "total_steps": 42420, "loss": 0.0807, "lr": 3.1595874476716888e-06, "epoch": 17.08863743517209, "percentage": 85.44, "elapsed_time": "2:11:18", "remaining_time": "0:22:22", "throughput": 4628.13, "total_tokens": 36463392} {"current_steps": 36250, "total_steps": 42420, "loss": 0.068, "lr": 3.154583971796099e-06, "epoch": 17.09099481376709, "percentage": 85.45, "elapsed_time": "2:11:19", "remaining_time": "0:22:21", "throughput": 4628.11, "total_tokens": 36467456} {"current_steps": 36255, "total_steps": 42420, "loss": 0.0627, "lr": 3.14958419397853e-06, "epoch": 17.093352192362094, "percentage": 85.47, "elapsed_time": "2:11:20", "remaining_time": "0:22:20", "throughput": 4628.15, "total_tokens": 36472800} {"current_steps": 36260, "total_steps": 42420, "loss": 0.187, "lr": 3.144588115065364e-06, "epoch": 17.095709570957094, "percentage": 85.48, "elapsed_time": "2:11:21", "remaining_time": "0:22:18", "throughput": 4628.15, "total_tokens": 36477216} {"current_steps": 36265, "total_steps": 42420, "loss": 0.1742, "lr": 3.13959573590234e-06, "epoch": 17.0980669495521, "percentage": 85.49, "elapsed_time": "2:11:22", "remaining_time": "0:22:17", "throughput": 4628.16, "total_tokens": 36481920} {"current_steps": 36270, "total_steps": 42420, "loss": 0.1886, "lr": 3.1346070573345904e-06, "epoch": 17.1004243281471, "percentage": 85.5, "elapsed_time": "2:11:23", "remaining_time": "0:22:16", "throughput": 4628.21, "total_tokens": 36487616} {"current_steps": 36275, "total_steps": 42420, "loss": 0.0735, "lr": 3.129622080206612e-06, "epoch": 17.102781706742103, "percentage": 85.51, "elapsed_time": "2:11:24", "remaining_time": "0:22:15", "throughput": 4628.24, "total_tokens": 36492672} {"current_steps": 36280, "total_steps": 42420, "loss": 0.0869, "lr": 3.124640805362278e-06, "epoch": 17.105139085337104, "percentage": 85.53, "elapsed_time": "2:11:25", "remaining_time": "0:22:14", "throughput": 4628.26, "total_tokens": 36497472} {"current_steps": 36285, "total_steps": 42420, "loss": 0.0942, "lr": 3.1196632336448317e-06, "epoch": 17.107496463932108, "percentage": 85.54, "elapsed_time": "2:11:26", "remaining_time": "0:22:13", "throughput": 4628.3, "total_tokens": 36502592} {"current_steps": 36290, "total_steps": 42420, "loss": 0.1563, "lr": 3.1146893658968947e-06, "epoch": 17.10985384252711, "percentage": 85.55, "elapsed_time": "2:11:27", "remaining_time": "0:22:12", "throughput": 4628.33, "total_tokens": 36507872} {"current_steps": 36295, "total_steps": 42420, "loss": 0.049, "lr": 3.1097192029604566e-06, "epoch": 17.112211221122113, "percentage": 85.56, "elapsed_time": "2:11:28", "remaining_time": "0:22:11", "throughput": 4628.34, "total_tokens": 36512672} {"current_steps": 36300, "total_steps": 42420, "loss": 0.1087, "lr": 3.1047527456768864e-06, "epoch": 17.114568599717114, "percentage": 85.57, "elapsed_time": "2:11:30", "remaining_time": "0:22:10", "throughput": 4628.37, "total_tokens": 36518336} {"current_steps": 36305, "total_steps": 42420, "loss": 0.1578, "lr": 3.099789994886909e-06, "epoch": 17.116925978312118, "percentage": 85.58, "elapsed_time": "2:11:31", "remaining_time": "0:22:09", "throughput": 4628.39, "total_tokens": 36522816} {"current_steps": 36310, "total_steps": 42420, "loss": 0.1327, "lr": 3.094830951430644e-06, "epoch": 17.11928335690712, "percentage": 85.6, "elapsed_time": "2:11:32", "remaining_time": "0:22:08", "throughput": 4628.44, "total_tokens": 36529472} {"current_steps": 36315, "total_steps": 42420, "loss": 0.1496, "lr": 3.0898756161475696e-06, "epoch": 17.121640735502123, "percentage": 85.61, "elapsed_time": "2:11:33", "remaining_time": "0:22:06", "throughput": 4628.46, "total_tokens": 36534496} {"current_steps": 36320, "total_steps": 42420, "loss": 0.2527, "lr": 3.0849239898765397e-06, "epoch": 17.123998114097123, "percentage": 85.62, "elapsed_time": "2:11:34", "remaining_time": "0:22:05", "throughput": 4628.5, "total_tokens": 36540128} {"current_steps": 36325, "total_steps": 42420, "loss": 0.1446, "lr": 3.0799760734557843e-06, "epoch": 17.126355492692127, "percentage": 85.63, "elapsed_time": "2:11:35", "remaining_time": "0:22:04", "throughput": 4628.53, "total_tokens": 36545440} {"current_steps": 36330, "total_steps": 42420, "loss": 0.2981, "lr": 3.0750318677228967e-06, "epoch": 17.128712871287128, "percentage": 85.64, "elapsed_time": "2:11:36", "remaining_time": "0:22:03", "throughput": 4628.55, "total_tokens": 36550272} {"current_steps": 36335, "total_steps": 42420, "loss": 0.0751, "lr": 3.070091373514847e-06, "epoch": 17.131070249882132, "percentage": 85.66, "elapsed_time": "2:11:37", "remaining_time": "0:22:02", "throughput": 4628.57, "total_tokens": 36555168} {"current_steps": 36340, "total_steps": 42420, "loss": 0.1866, "lr": 3.0651545916679876e-06, "epoch": 17.133427628477133, "percentage": 85.67, "elapsed_time": "2:11:38", "remaining_time": "0:22:01", "throughput": 4628.55, "total_tokens": 36559328} {"current_steps": 36345, "total_steps": 42420, "loss": 0.0994, "lr": 3.060221523018017e-06, "epoch": 17.135785007072137, "percentage": 85.68, "elapsed_time": "2:11:39", "remaining_time": "0:22:00", "throughput": 4628.57, "total_tokens": 36564288} {"current_steps": 36350, "total_steps": 42420, "loss": 0.0524, "lr": 3.055292168400026e-06, "epoch": 17.138142385667138, "percentage": 85.69, "elapsed_time": "2:11:40", "remaining_time": "0:21:59", "throughput": 4628.59, "total_tokens": 36569024} {"current_steps": 36355, "total_steps": 42420, "loss": 0.0578, "lr": 3.0503665286484712e-06, "epoch": 17.14049976426214, "percentage": 85.7, "elapsed_time": "2:11:41", "remaining_time": "0:21:58", "throughput": 4628.62, "total_tokens": 36573536} {"current_steps": 36360, "total_steps": 42420, "loss": 0.0286, "lr": 3.045444604597181e-06, "epoch": 17.142857142857142, "percentage": 85.71, "elapsed_time": "2:11:42", "remaining_time": "0:21:57", "throughput": 4628.64, "total_tokens": 36578304} {"current_steps": 36365, "total_steps": 42420, "loss": 0.0684, "lr": 3.040526397079349e-06, "epoch": 17.145214521452147, "percentage": 85.73, "elapsed_time": "2:11:43", "remaining_time": "0:21:55", "throughput": 4628.66, "total_tokens": 36583072} {"current_steps": 36370, "total_steps": 42420, "loss": 0.1674, "lr": 3.035611906927549e-06, "epoch": 17.147571900047147, "percentage": 85.74, "elapsed_time": "2:11:44", "remaining_time": "0:21:54", "throughput": 4628.68, "total_tokens": 36587808} {"current_steps": 36375, "total_steps": 42420, "loss": 0.0144, "lr": 3.030701134973721e-06, "epoch": 17.14992927864215, "percentage": 85.75, "elapsed_time": "2:11:45", "remaining_time": "0:21:53", "throughput": 4628.71, "total_tokens": 36592896} {"current_steps": 36380, "total_steps": 42420, "loss": 0.0197, "lr": 3.025794082049177e-06, "epoch": 17.152286657237152, "percentage": 85.76, "elapsed_time": "2:11:46", "remaining_time": "0:21:52", "throughput": 4628.69, "total_tokens": 36596896} {"current_steps": 36385, "total_steps": 42420, "loss": 0.1022, "lr": 3.0208907489845865e-06, "epoch": 17.154644035832156, "percentage": 85.77, "elapsed_time": "2:11:47", "remaining_time": "0:21:51", "throughput": 4628.73, "total_tokens": 36602304} {"current_steps": 36390, "total_steps": 42420, "loss": 0.2282, "lr": 3.0159911366100107e-06, "epoch": 17.157001414427157, "percentage": 85.79, "elapsed_time": "2:11:48", "remaining_time": "0:21:50", "throughput": 4628.76, "total_tokens": 36607488} {"current_steps": 36395, "total_steps": 42420, "loss": 0.1259, "lr": 3.0110952457548693e-06, "epoch": 17.15935879302216, "percentage": 85.8, "elapsed_time": "2:11:49", "remaining_time": "0:21:49", "throughput": 4628.8, "total_tokens": 36613120} {"current_steps": 36400, "total_steps": 42420, "loss": 0.0784, "lr": 3.0062030772479517e-06, "epoch": 17.16171617161716, "percentage": 85.81, "elapsed_time": "2:11:50", "remaining_time": "0:21:48", "throughput": 4628.82, "total_tokens": 36617472} {"current_steps": 36405, "total_steps": 42420, "loss": 0.1435, "lr": 3.0013146319174178e-06, "epoch": 17.164073550212166, "percentage": 85.82, "elapsed_time": "2:11:51", "remaining_time": "0:21:47", "throughput": 4628.85, "total_tokens": 36622656} {"current_steps": 36410, "total_steps": 42420, "loss": 0.0407, "lr": 2.9964299105908035e-06, "epoch": 17.166430928807166, "percentage": 85.83, "elapsed_time": "2:11:52", "remaining_time": "0:21:46", "throughput": 4628.88, "total_tokens": 36627264} {"current_steps": 36415, "total_steps": 42420, "loss": 0.0815, "lr": 2.9915489140950077e-06, "epoch": 17.16878830740217, "percentage": 85.84, "elapsed_time": "2:11:53", "remaining_time": "0:21:45", "throughput": 4628.92, "total_tokens": 36632768} {"current_steps": 36420, "total_steps": 42420, "loss": 0.1446, "lr": 2.9866716432562947e-06, "epoch": 17.17114568599717, "percentage": 85.86, "elapsed_time": "2:11:54", "remaining_time": "0:21:43", "throughput": 4628.95, "total_tokens": 36637952} {"current_steps": 36425, "total_steps": 42420, "loss": 0.1378, "lr": 2.9817980989003127e-06, "epoch": 17.173503064592172, "percentage": 85.87, "elapsed_time": "2:11:55", "remaining_time": "0:21:42", "throughput": 4628.99, "total_tokens": 36642752} {"current_steps": 36430, "total_steps": 42420, "loss": 0.0209, "lr": 2.9769282818520595e-06, "epoch": 17.175860443187176, "percentage": 85.88, "elapsed_time": "2:11:57", "remaining_time": "0:21:41", "throughput": 4629.03, "total_tokens": 36648288} {"current_steps": 36435, "total_steps": 42420, "loss": 0.2829, "lr": 2.9720621929359176e-06, "epoch": 17.178217821782177, "percentage": 85.89, "elapsed_time": "2:11:58", "remaining_time": "0:21:40", "throughput": 4629.04, "total_tokens": 36653056} {"current_steps": 36440, "total_steps": 42420, "loss": 0.0769, "lr": 2.967199832975634e-06, "epoch": 17.18057520037718, "percentage": 85.9, "elapsed_time": "2:11:59", "remaining_time": "0:21:39", "throughput": 4629.07, "total_tokens": 36658336} {"current_steps": 36445, "total_steps": 42420, "loss": 0.1524, "lr": 2.962341202794322e-06, "epoch": 17.18293257897218, "percentage": 85.91, "elapsed_time": "2:12:00", "remaining_time": "0:21:38", "throughput": 4629.14, "total_tokens": 36664096} {"current_steps": 36450, "total_steps": 42420, "loss": 0.1455, "lr": 2.9574863032144683e-06, "epoch": 17.185289957567186, "percentage": 85.93, "elapsed_time": "2:12:01", "remaining_time": "0:21:37", "throughput": 4629.18, "total_tokens": 36668736} {"current_steps": 36455, "total_steps": 42420, "loss": 0.1085, "lr": 2.9526351350579214e-06, "epoch": 17.187647336162186, "percentage": 85.94, "elapsed_time": "2:12:02", "remaining_time": "0:21:36", "throughput": 4629.17, "total_tokens": 36672576} {"current_steps": 36460, "total_steps": 42420, "loss": 0.0901, "lr": 2.9477876991459043e-06, "epoch": 17.19000471475719, "percentage": 85.95, "elapsed_time": "2:12:03", "remaining_time": "0:21:35", "throughput": 4629.22, "total_tokens": 36678176} {"current_steps": 36465, "total_steps": 42420, "loss": 0.0393, "lr": 2.942943996299008e-06, "epoch": 17.19236209335219, "percentage": 85.96, "elapsed_time": "2:12:04", "remaining_time": "0:21:34", "throughput": 4629.24, "total_tokens": 36682944} {"current_steps": 36470, "total_steps": 42420, "loss": 0.126, "lr": 2.9381040273371794e-06, "epoch": 17.194719471947195, "percentage": 85.97, "elapsed_time": "2:12:05", "remaining_time": "0:21:32", "throughput": 4629.26, "total_tokens": 36687360} {"current_steps": 36475, "total_steps": 42420, "loss": 0.109, "lr": 2.9332677930797527e-06, "epoch": 17.197076850542196, "percentage": 85.99, "elapsed_time": "2:12:06", "remaining_time": "0:21:31", "throughput": 4629.29, "total_tokens": 36692352} {"current_steps": 36480, "total_steps": 42420, "loss": 0.0801, "lr": 2.9284352943454134e-06, "epoch": 17.1994342291372, "percentage": 86.0, "elapsed_time": "2:12:07", "remaining_time": "0:21:30", "throughput": 4629.34, "total_tokens": 36697856} {"current_steps": 36485, "total_steps": 42420, "loss": 0.0458, "lr": 2.9236065319522276e-06, "epoch": 17.2017916077322, "percentage": 86.01, "elapsed_time": "2:12:08", "remaining_time": "0:21:29", "throughput": 4629.35, "total_tokens": 36702400} {"current_steps": 36490, "total_steps": 42420, "loss": 0.1732, "lr": 2.918781506717619e-06, "epoch": 17.204148986327205, "percentage": 86.02, "elapsed_time": "2:12:09", "remaining_time": "0:21:28", "throughput": 4629.38, "total_tokens": 36707680} {"current_steps": 36495, "total_steps": 42420, "loss": 0.1125, "lr": 2.9139602194583835e-06, "epoch": 17.206506364922205, "percentage": 86.03, "elapsed_time": "2:12:10", "remaining_time": "0:21:27", "throughput": 4629.36, "total_tokens": 36711840} {"current_steps": 36500, "total_steps": 42420, "loss": 0.1223, "lr": 2.909142670990683e-06, "epoch": 17.20886374351721, "percentage": 86.04, "elapsed_time": "2:12:11", "remaining_time": "0:21:26", "throughput": 4629.43, "total_tokens": 36718880} {"current_steps": 36505, "total_steps": 42420, "loss": 0.2773, "lr": 2.904328862130054e-06, "epoch": 17.21122112211221, "percentage": 86.06, "elapsed_time": "2:12:12", "remaining_time": "0:21:25", "throughput": 4629.45, "total_tokens": 36723840} {"current_steps": 36510, "total_steps": 42420, "loss": 0.086, "lr": 2.8995187936913778e-06, "epoch": 17.213578500707214, "percentage": 86.07, "elapsed_time": "2:12:13", "remaining_time": "0:21:24", "throughput": 4629.47, "total_tokens": 36728352} {"current_steps": 36515, "total_steps": 42420, "loss": 0.1999, "lr": 2.8947124664889274e-06, "epoch": 17.215935879302215, "percentage": 86.08, "elapsed_time": "2:12:14", "remaining_time": "0:21:23", "throughput": 4629.49, "total_tokens": 36733312} {"current_steps": 36520, "total_steps": 42420, "loss": 0.0632, "lr": 2.8899098813363278e-06, "epoch": 17.21829325789722, "percentage": 86.09, "elapsed_time": "2:12:15", "remaining_time": "0:21:22", "throughput": 4629.5, "total_tokens": 36737984} {"current_steps": 36525, "total_steps": 42420, "loss": 0.0906, "lr": 2.8851110390465784e-06, "epoch": 17.22065063649222, "percentage": 86.1, "elapsed_time": "2:12:16", "remaining_time": "0:21:20", "throughput": 4629.52, "total_tokens": 36743296} {"current_steps": 36530, "total_steps": 42420, "loss": 0.1618, "lr": 2.8803159404320406e-06, "epoch": 17.223008015087224, "percentage": 86.12, "elapsed_time": "2:12:17", "remaining_time": "0:21:19", "throughput": 4629.52, "total_tokens": 36747392} {"current_steps": 36535, "total_steps": 42420, "loss": 0.1747, "lr": 2.8755245863044426e-06, "epoch": 17.225365393682225, "percentage": 86.13, "elapsed_time": "2:12:19", "remaining_time": "0:21:18", "throughput": 4629.57, "total_tokens": 36754400} {"current_steps": 36540, "total_steps": 42420, "loss": 0.0313, "lr": 2.8707369774748806e-06, "epoch": 17.22772277227723, "percentage": 86.14, "elapsed_time": "2:12:20", "remaining_time": "0:21:17", "throughput": 4629.6, "total_tokens": 36759168} {"current_steps": 36545, "total_steps": 42420, "loss": 0.215, "lr": 2.8659531147538192e-06, "epoch": 17.23008015087223, "percentage": 86.15, "elapsed_time": "2:12:21", "remaining_time": "0:21:16", "throughput": 4629.61, "total_tokens": 36763936} {"current_steps": 36550, "total_steps": 42420, "loss": 0.0612, "lr": 2.861172998951078e-06, "epoch": 17.232437529467234, "percentage": 86.16, "elapsed_time": "2:12:21", "remaining_time": "0:21:15", "throughput": 4629.64, "total_tokens": 36768512} {"current_steps": 36555, "total_steps": 42420, "loss": 0.0757, "lr": 2.8563966308758487e-06, "epoch": 17.234794908062234, "percentage": 86.17, "elapsed_time": "2:12:22", "remaining_time": "0:21:14", "throughput": 4629.67, "total_tokens": 36773248} {"current_steps": 36560, "total_steps": 42420, "loss": 0.0669, "lr": 2.8516240113366955e-06, "epoch": 17.23715228665724, "percentage": 86.19, "elapsed_time": "2:12:23", "remaining_time": "0:21:13", "throughput": 4629.65, "total_tokens": 36777376} {"current_steps": 36565, "total_steps": 42420, "loss": 0.0861, "lr": 2.8468551411415384e-06, "epoch": 17.23950966525224, "percentage": 86.2, "elapsed_time": "2:12:24", "remaining_time": "0:21:12", "throughput": 4629.69, "total_tokens": 36782656} {"current_steps": 36570, "total_steps": 42420, "loss": 0.1122, "lr": 2.842090021097668e-06, "epoch": 17.241867043847243, "percentage": 86.21, "elapsed_time": "2:12:25", "remaining_time": "0:21:11", "throughput": 4629.71, "total_tokens": 36787616} {"current_steps": 36575, "total_steps": 42420, "loss": 0.0642, "lr": 2.8373286520117336e-06, "epoch": 17.244224422442244, "percentage": 86.22, "elapsed_time": "2:12:27", "remaining_time": "0:21:10", "throughput": 4629.74, "total_tokens": 36793408} {"current_steps": 36580, "total_steps": 42420, "loss": 0.0818, "lr": 2.83257103468976e-06, "epoch": 17.246581801037248, "percentage": 86.23, "elapsed_time": "2:12:28", "remaining_time": "0:21:08", "throughput": 4629.75, "total_tokens": 36798208} {"current_steps": 36585, "total_steps": 42420, "loss": 0.1429, "lr": 2.827817169937136e-06, "epoch": 17.24893917963225, "percentage": 86.24, "elapsed_time": "2:12:29", "remaining_time": "0:21:07", "throughput": 4629.8, "total_tokens": 36803808} {"current_steps": 36590, "total_steps": 42420, "loss": 0.1596, "lr": 2.8230670585585927e-06, "epoch": 17.251296558227253, "percentage": 86.26, "elapsed_time": "2:12:30", "remaining_time": "0:21:06", "throughput": 4629.84, "total_tokens": 36809728} {"current_steps": 36595, "total_steps": 42420, "loss": 0.046, "lr": 2.818320701358257e-06, "epoch": 17.253653936822253, "percentage": 86.27, "elapsed_time": "2:12:31", "remaining_time": "0:21:05", "throughput": 4629.87, "total_tokens": 36815232} {"current_steps": 36600, "total_steps": 42420, "loss": 0.1355, "lr": 2.813578099139602e-06, "epoch": 17.256011315417258, "percentage": 86.28, "elapsed_time": "2:12:33", "remaining_time": "0:21:04", "throughput": 4629.95, "total_tokens": 36822336} {"current_steps": 36605, "total_steps": 42420, "loss": 0.2503, "lr": 2.8088392527054723e-06, "epoch": 17.25836869401226, "percentage": 86.29, "elapsed_time": "2:12:34", "remaining_time": "0:21:03", "throughput": 4629.98, "total_tokens": 36827328} {"current_steps": 36610, "total_steps": 42420, "loss": 0.2512, "lr": 2.8041041628580707e-06, "epoch": 17.260726072607262, "percentage": 86.3, "elapsed_time": "2:12:35", "remaining_time": "0:21:02", "throughput": 4629.99, "total_tokens": 36831712} {"current_steps": 36615, "total_steps": 42420, "loss": 0.1717, "lr": 2.7993728303989717e-06, "epoch": 17.263083451202263, "percentage": 86.32, "elapsed_time": "2:12:35", "remaining_time": "0:21:01", "throughput": 4630.01, "total_tokens": 36836192} {"current_steps": 36620, "total_steps": 42420, "loss": 0.0808, "lr": 2.7946452561291053e-06, "epoch": 17.265440829797264, "percentage": 86.33, "elapsed_time": "2:12:36", "remaining_time": "0:21:00", "throughput": 4630.04, "total_tokens": 36841056} {"current_steps": 36625, "total_steps": 42420, "loss": 0.1838, "lr": 2.789921440848778e-06, "epoch": 17.267798208392268, "percentage": 86.34, "elapsed_time": "2:12:38", "remaining_time": "0:20:59", "throughput": 4630.05, "total_tokens": 36845984} {"current_steps": 36630, "total_steps": 42420, "loss": 0.1331, "lr": 2.7852013853576388e-06, "epoch": 17.27015558698727, "percentage": 86.35, "elapsed_time": "2:12:39", "remaining_time": "0:20:58", "throughput": 4630.09, "total_tokens": 36851392} {"current_steps": 36635, "total_steps": 42420, "loss": 0.0739, "lr": 2.780485090454721e-06, "epoch": 17.272512965582273, "percentage": 86.36, "elapsed_time": "2:12:40", "remaining_time": "0:20:56", "throughput": 4630.1, "total_tokens": 36855776} {"current_steps": 36640, "total_steps": 42420, "loss": 0.1806, "lr": 2.7757725569384135e-06, "epoch": 17.274870344177273, "percentage": 86.37, "elapsed_time": "2:12:41", "remaining_time": "0:20:55", "throughput": 4630.15, "total_tokens": 36861312} {"current_steps": 36645, "total_steps": 42420, "loss": 0.035, "lr": 2.771063785606465e-06, "epoch": 17.277227722772277, "percentage": 86.39, "elapsed_time": "2:12:42", "remaining_time": "0:20:54", "throughput": 4630.18, "total_tokens": 36866432} {"current_steps": 36650, "total_steps": 42420, "loss": 0.3068, "lr": 2.7663587772559896e-06, "epoch": 17.279585101367278, "percentage": 86.4, "elapsed_time": "2:12:43", "remaining_time": "0:20:53", "throughput": 4630.23, "total_tokens": 36872160} {"current_steps": 36655, "total_steps": 42420, "loss": 0.224, "lr": 2.7616575326834678e-06, "epoch": 17.281942479962282, "percentage": 86.41, "elapsed_time": "2:12:44", "remaining_time": "0:20:52", "throughput": 4630.26, "total_tokens": 36877216} {"current_steps": 36660, "total_steps": 42420, "loss": 0.0628, "lr": 2.756960052684737e-06, "epoch": 17.284299858557283, "percentage": 86.42, "elapsed_time": "2:12:45", "remaining_time": "0:20:51", "throughput": 4630.3, "total_tokens": 36882272} {"current_steps": 36665, "total_steps": 42420, "loss": 0.0559, "lr": 2.7522663380550097e-06, "epoch": 17.286657237152287, "percentage": 86.43, "elapsed_time": "2:12:46", "remaining_time": "0:20:50", "throughput": 4630.31, "total_tokens": 36886752} {"current_steps": 36670, "total_steps": 42420, "loss": 0.1824, "lr": 2.7475763895888433e-06, "epoch": 17.289014615747288, "percentage": 86.45, "elapsed_time": "2:12:47", "remaining_time": "0:20:49", "throughput": 4630.36, "total_tokens": 36892704} {"current_steps": 36675, "total_steps": 42420, "loss": 0.1245, "lr": 2.7428902080801734e-06, "epoch": 17.291371994342292, "percentage": 86.46, "elapsed_time": "2:12:48", "remaining_time": "0:20:48", "throughput": 4630.38, "total_tokens": 36897568} {"current_steps": 36680, "total_steps": 42420, "loss": 0.0762, "lr": 2.7382077943222838e-06, "epoch": 17.293729372937293, "percentage": 86.47, "elapsed_time": "2:12:49", "remaining_time": "0:20:47", "throughput": 4630.42, "total_tokens": 36903200} {"current_steps": 36685, "total_steps": 42420, "loss": 0.1815, "lr": 2.73352914910783e-06, "epoch": 17.296086751532297, "percentage": 86.48, "elapsed_time": "2:12:50", "remaining_time": "0:20:46", "throughput": 4630.47, "total_tokens": 36908928} {"current_steps": 36690, "total_steps": 42420, "loss": 0.3232, "lr": 2.7288542732288288e-06, "epoch": 17.298444130127297, "percentage": 86.49, "elapsed_time": "2:12:52", "remaining_time": "0:20:45", "throughput": 4630.49, "total_tokens": 36914752} {"current_steps": 36695, "total_steps": 42420, "loss": 0.0921, "lr": 2.7241831674766573e-06, "epoch": 17.3008015087223, "percentage": 86.5, "elapsed_time": "2:12:53", "remaining_time": "0:20:43", "throughput": 4630.51, "total_tokens": 36919136} {"current_steps": 36700, "total_steps": 42420, "loss": 0.0379, "lr": 2.719515832642053e-06, "epoch": 17.303158887317302, "percentage": 86.52, "elapsed_time": "2:12:54", "remaining_time": "0:20:42", "throughput": 4630.54, "total_tokens": 36924352} {"current_steps": 36705, "total_steps": 42420, "loss": 0.1339, "lr": 2.7148522695151167e-06, "epoch": 17.305516265912306, "percentage": 86.53, "elapsed_time": "2:12:55", "remaining_time": "0:20:41", "throughput": 4630.58, "total_tokens": 36929856} {"current_steps": 36710, "total_steps": 42420, "loss": 0.0488, "lr": 2.7101924788853124e-06, "epoch": 17.307873644507307, "percentage": 86.54, "elapsed_time": "2:12:56", "remaining_time": "0:20:40", "throughput": 4630.63, "total_tokens": 36935136} {"current_steps": 36715, "total_steps": 42420, "loss": 0.0666, "lr": 2.7055364615414635e-06, "epoch": 17.31023102310231, "percentage": 86.55, "elapsed_time": "2:12:57", "remaining_time": "0:20:39", "throughput": 4630.66, "total_tokens": 36940320} {"current_steps": 36720, "total_steps": 42420, "loss": 0.2825, "lr": 2.7008842182717514e-06, "epoch": 17.31258840169731, "percentage": 86.56, "elapsed_time": "2:12:58", "remaining_time": "0:20:38", "throughput": 4630.69, "total_tokens": 36945024} {"current_steps": 36725, "total_steps": 42420, "loss": 0.1333, "lr": 2.696235749863724e-06, "epoch": 17.314945780292316, "percentage": 86.57, "elapsed_time": "2:12:59", "remaining_time": "0:20:37", "throughput": 4630.73, "total_tokens": 36950368} {"current_steps": 36730, "total_steps": 42420, "loss": 0.0733, "lr": 2.691591057104287e-06, "epoch": 17.317303158887317, "percentage": 86.59, "elapsed_time": "2:13:00", "remaining_time": "0:20:36", "throughput": 4630.78, "total_tokens": 36956928} {"current_steps": 36735, "total_steps": 42420, "loss": 0.0601, "lr": 2.6869501407797064e-06, "epoch": 17.31966053748232, "percentage": 86.6, "elapsed_time": "2:13:01", "remaining_time": "0:20:35", "throughput": 4630.82, "total_tokens": 36962624} {"current_steps": 36740, "total_steps": 42420, "loss": 0.1124, "lr": 2.6823130016756153e-06, "epoch": 17.32201791607732, "percentage": 86.61, "elapsed_time": "2:13:02", "remaining_time": "0:20:34", "throughput": 4630.84, "total_tokens": 36967424} {"current_steps": 36745, "total_steps": 42420, "loss": 0.1017, "lr": 2.6776796405769993e-06, "epoch": 17.324375294672326, "percentage": 86.62, "elapsed_time": "2:13:03", "remaining_time": "0:20:33", "throughput": 4630.87, "total_tokens": 36972672} {"current_steps": 36750, "total_steps": 42420, "loss": 0.0656, "lr": 2.6730500582682115e-06, "epoch": 17.326732673267326, "percentage": 86.63, "elapsed_time": "2:13:05", "remaining_time": "0:20:32", "throughput": 4630.89, "total_tokens": 36979456} {"current_steps": 36755, "total_steps": 42420, "loss": 0.0982, "lr": 2.6684242555329613e-06, "epoch": 17.32909005186233, "percentage": 86.65, "elapsed_time": "2:13:06", "remaining_time": "0:20:30", "throughput": 4630.9, "total_tokens": 36984096} {"current_steps": 36760, "total_steps": 42420, "loss": 0.0975, "lr": 2.663802233154311e-06, "epoch": 17.33144743045733, "percentage": 86.66, "elapsed_time": "2:13:07", "remaining_time": "0:20:29", "throughput": 4630.93, "total_tokens": 36989696} {"current_steps": 36765, "total_steps": 42420, "loss": 0.1336, "lr": 2.659183991914696e-06, "epoch": 17.333804809052335, "percentage": 86.67, "elapsed_time": "2:13:08", "remaining_time": "0:20:28", "throughput": 4630.95, "total_tokens": 36994304} {"current_steps": 36770, "total_steps": 42420, "loss": 0.1271, "lr": 2.6545695325959046e-06, "epoch": 17.336162187647336, "percentage": 86.68, "elapsed_time": "2:13:09", "remaining_time": "0:20:27", "throughput": 4630.99, "total_tokens": 36999360} {"current_steps": 36775, "total_steps": 42420, "loss": 0.0483, "lr": 2.64995885597909e-06, "epoch": 17.33851956624234, "percentage": 86.69, "elapsed_time": "2:13:10", "remaining_time": "0:20:26", "throughput": 4630.99, "total_tokens": 37004064} {"current_steps": 36780, "total_steps": 42420, "loss": 0.0829, "lr": 2.6453519628447584e-06, "epoch": 17.34087694483734, "percentage": 86.7, "elapsed_time": "2:13:11", "remaining_time": "0:20:25", "throughput": 4631.02, "total_tokens": 37008832} {"current_steps": 36785, "total_steps": 42420, "loss": 0.2678, "lr": 2.640748853972777e-06, "epoch": 17.343234323432345, "percentage": 86.72, "elapsed_time": "2:13:12", "remaining_time": "0:20:24", "throughput": 4631.03, "total_tokens": 37013632} {"current_steps": 36790, "total_steps": 42420, "loss": 0.0216, "lr": 2.636149530142379e-06, "epoch": 17.345591702027345, "percentage": 86.73, "elapsed_time": "2:13:13", "remaining_time": "0:20:23", "throughput": 4631.06, "total_tokens": 37018848} {"current_steps": 36795, "total_steps": 42420, "loss": 0.0276, "lr": 2.631553992132152e-06, "epoch": 17.34794908062235, "percentage": 86.74, "elapsed_time": "2:13:14", "remaining_time": "0:20:22", "throughput": 4631.1, "total_tokens": 37024192} {"current_steps": 36800, "total_steps": 42420, "loss": 0.1096, "lr": 2.626962240720035e-06, "epoch": 17.35030645921735, "percentage": 86.75, "elapsed_time": "2:13:15", "remaining_time": "0:20:21", "throughput": 4631.14, "total_tokens": 37030336} {"current_steps": 36805, "total_steps": 42420, "loss": 0.1294, "lr": 2.622374276683337e-06, "epoch": 17.352663837812354, "percentage": 86.76, "elapsed_time": "2:13:16", "remaining_time": "0:20:20", "throughput": 4631.15, "total_tokens": 37034880} {"current_steps": 36810, "total_steps": 42420, "loss": 0.0225, "lr": 2.6177901007987256e-06, "epoch": 17.355021216407355, "percentage": 86.78, "elapsed_time": "2:13:18", "remaining_time": "0:20:18", "throughput": 4631.18, "total_tokens": 37040288} {"current_steps": 36815, "total_steps": 42420, "loss": 0.069, "lr": 2.613209713842221e-06, "epoch": 17.35737859500236, "percentage": 86.79, "elapsed_time": "2:13:19", "remaining_time": "0:20:17", "throughput": 4631.22, "total_tokens": 37045888} {"current_steps": 36820, "total_steps": 42420, "loss": 0.2394, "lr": 2.6086331165892043e-06, "epoch": 17.35973597359736, "percentage": 86.8, "elapsed_time": "2:13:20", "remaining_time": "0:20:16", "throughput": 4631.24, "total_tokens": 37050336} {"current_steps": 36825, "total_steps": 42420, "loss": 0.0836, "lr": 2.604060309814421e-06, "epoch": 17.36209335219236, "percentage": 86.81, "elapsed_time": "2:13:21", "remaining_time": "0:20:15", "throughput": 4631.25, "total_tokens": 37054912} {"current_steps": 36830, "total_steps": 42420, "loss": 0.1384, "lr": 2.5994912942919615e-06, "epoch": 17.364450730787365, "percentage": 86.82, "elapsed_time": "2:13:22", "remaining_time": "0:20:14", "throughput": 4631.28, "total_tokens": 37060352} {"current_steps": 36835, "total_steps": 42420, "loss": 0.2431, "lr": 2.5949260707952947e-06, "epoch": 17.366808109382365, "percentage": 86.83, "elapsed_time": "2:13:23", "remaining_time": "0:20:13", "throughput": 4631.29, "total_tokens": 37065056} {"current_steps": 36840, "total_steps": 42420, "loss": 0.0444, "lr": 2.59036464009722e-06, "epoch": 17.36916548797737, "percentage": 86.85, "elapsed_time": "2:13:24", "remaining_time": "0:20:12", "throughput": 4631.33, "total_tokens": 37070176} {"current_steps": 36845, "total_steps": 42420, "loss": 0.0699, "lr": 2.58580700296992e-06, "epoch": 17.37152286657237, "percentage": 86.86, "elapsed_time": "2:13:25", "remaining_time": "0:20:11", "throughput": 4631.35, "total_tokens": 37074752} {"current_steps": 36850, "total_steps": 42420, "loss": 0.1453, "lr": 2.581253160184924e-06, "epoch": 17.373880245167374, "percentage": 86.87, "elapsed_time": "2:13:26", "remaining_time": "0:20:10", "throughput": 4631.37, "total_tokens": 37079104} {"current_steps": 36855, "total_steps": 42420, "loss": 0.0933, "lr": 2.576703112513118e-06, "epoch": 17.376237623762375, "percentage": 86.88, "elapsed_time": "2:13:27", "remaining_time": "0:20:09", "throughput": 4631.42, "total_tokens": 37085440} {"current_steps": 36860, "total_steps": 42420, "loss": 0.1136, "lr": 2.5721568607247476e-06, "epoch": 17.37859500235738, "percentage": 86.89, "elapsed_time": "2:13:28", "remaining_time": "0:20:07", "throughput": 4631.43, "total_tokens": 37090336} {"current_steps": 36865, "total_steps": 42420, "loss": 0.1046, "lr": 2.5676144055894247e-06, "epoch": 17.38095238095238, "percentage": 86.9, "elapsed_time": "2:13:29", "remaining_time": "0:20:06", "throughput": 4631.47, "total_tokens": 37095360} {"current_steps": 36870, "total_steps": 42420, "loss": 0.0258, "lr": 2.563075747876098e-06, "epoch": 17.383309759547384, "percentage": 86.92, "elapsed_time": "2:13:30", "remaining_time": "0:20:05", "throughput": 4631.44, "total_tokens": 37099264} {"current_steps": 36875, "total_steps": 42420, "loss": 0.066, "lr": 2.5585408883530893e-06, "epoch": 17.385667138142384, "percentage": 86.93, "elapsed_time": "2:13:31", "remaining_time": "0:20:04", "throughput": 4631.46, "total_tokens": 37104064} {"current_steps": 36880, "total_steps": 42420, "loss": 0.1526, "lr": 2.554009827788073e-06, "epoch": 17.38802451673739, "percentage": 86.94, "elapsed_time": "2:13:32", "remaining_time": "0:20:03", "throughput": 4631.47, "total_tokens": 37108320} {"current_steps": 36885, "total_steps": 42420, "loss": 0.022, "lr": 2.549482566948086e-06, "epoch": 17.39038189533239, "percentage": 86.95, "elapsed_time": "2:13:33", "remaining_time": "0:20:02", "throughput": 4631.48, "total_tokens": 37112864} {"current_steps": 36890, "total_steps": 42420, "loss": 0.159, "lr": 2.5449591065995095e-06, "epoch": 17.392739273927393, "percentage": 86.96, "elapsed_time": "2:13:34", "remaining_time": "0:20:01", "throughput": 4631.48, "total_tokens": 37117376} {"current_steps": 36895, "total_steps": 42420, "loss": 0.1468, "lr": 2.540439447508089e-06, "epoch": 17.395096652522394, "percentage": 86.98, "elapsed_time": "2:13:35", "remaining_time": "0:20:00", "throughput": 4631.52, "total_tokens": 37122496} {"current_steps": 36900, "total_steps": 42420, "loss": 0.0268, "lr": 2.5359235904389324e-06, "epoch": 17.397454031117398, "percentage": 86.99, "elapsed_time": "2:13:36", "remaining_time": "0:19:59", "throughput": 4631.54, "total_tokens": 37127392} {"current_steps": 36905, "total_steps": 42420, "loss": 0.1523, "lr": 2.531411536156489e-06, "epoch": 17.3998114097124, "percentage": 87.0, "elapsed_time": "2:13:37", "remaining_time": "0:19:58", "throughput": 4631.56, "total_tokens": 37132352} {"current_steps": 36910, "total_steps": 42420, "loss": 0.1931, "lr": 2.526903285424581e-06, "epoch": 17.402168788307403, "percentage": 87.01, "elapsed_time": "2:13:38", "remaining_time": "0:19:57", "throughput": 4631.6, "total_tokens": 37138048} {"current_steps": 36915, "total_steps": 42420, "loss": 0.0717, "lr": 2.5223988390063734e-06, "epoch": 17.404526166902404, "percentage": 87.02, "elapsed_time": "2:13:39", "remaining_time": "0:19:55", "throughput": 4631.63, "total_tokens": 37142624} {"current_steps": 36920, "total_steps": 42420, "loss": 0.1573, "lr": 2.517898197664395e-06, "epoch": 17.406883545497408, "percentage": 87.03, "elapsed_time": "2:13:40", "remaining_time": "0:19:54", "throughput": 4631.6, "total_tokens": 37146976} {"current_steps": 36925, "total_steps": 42420, "loss": 0.1062, "lr": 2.5134013621605305e-06, "epoch": 17.40924092409241, "percentage": 87.05, "elapsed_time": "2:13:41", "remaining_time": "0:19:53", "throughput": 4631.63, "total_tokens": 37151712} {"current_steps": 36930, "total_steps": 42420, "loss": 0.0852, "lr": 2.508908333256013e-06, "epoch": 17.411598302687413, "percentage": 87.06, "elapsed_time": "2:13:42", "remaining_time": "0:19:52", "throughput": 4631.47, "total_tokens": 37156512} {"current_steps": 36935, "total_steps": 42420, "loss": 0.1313, "lr": 2.504419111711437e-06, "epoch": 17.413955681282413, "percentage": 87.07, "elapsed_time": "2:13:43", "remaining_time": "0:19:51", "throughput": 4631.42, "total_tokens": 37160352} {"current_steps": 36940, "total_steps": 42420, "loss": 0.0442, "lr": 2.4999336982867495e-06, "epoch": 17.416313059877417, "percentage": 87.08, "elapsed_time": "2:13:44", "remaining_time": "0:19:50", "throughput": 4631.44, "total_tokens": 37165920} {"current_steps": 36945, "total_steps": 42420, "loss": 0.0791, "lr": 2.49545209374126e-06, "epoch": 17.418670438472418, "percentage": 87.09, "elapsed_time": "2:13:45", "remaining_time": "0:19:49", "throughput": 4631.47, "total_tokens": 37171552} {"current_steps": 36950, "total_steps": 42420, "loss": 0.116, "lr": 2.490974298833626e-06, "epoch": 17.421027817067422, "percentage": 87.11, "elapsed_time": "2:13:46", "remaining_time": "0:19:48", "throughput": 4631.47, "total_tokens": 37175936} {"current_steps": 36955, "total_steps": 42420, "loss": 0.045, "lr": 2.48650031432186e-06, "epoch": 17.423385195662423, "percentage": 87.12, "elapsed_time": "2:13:47", "remaining_time": "0:19:47", "throughput": 4631.5, "total_tokens": 37180960} {"current_steps": 36960, "total_steps": 42420, "loss": 0.0277, "lr": 2.4820301409633346e-06, "epoch": 17.425742574257427, "percentage": 87.13, "elapsed_time": "2:13:49", "remaining_time": "0:19:46", "throughput": 4631.55, "total_tokens": 37187744} {"current_steps": 36965, "total_steps": 42420, "loss": 0.041, "lr": 2.4775637795147773e-06, "epoch": 17.428099952852428, "percentage": 87.14, "elapsed_time": "2:13:50", "remaining_time": "0:19:45", "throughput": 4631.59, "total_tokens": 37193376} {"current_steps": 36970, "total_steps": 42420, "loss": 0.1953, "lr": 2.4731012307322584e-06, "epoch": 17.430457331447432, "percentage": 87.15, "elapsed_time": "2:13:51", "remaining_time": "0:19:43", "throughput": 4631.64, "total_tokens": 37199424} {"current_steps": 36975, "total_steps": 42420, "loss": 0.0081, "lr": 2.4686424953712152e-06, "epoch": 17.432814710042432, "percentage": 87.16, "elapsed_time": "2:13:52", "remaining_time": "0:19:42", "throughput": 4631.67, "total_tokens": 37204896} {"current_steps": 36980, "total_steps": 42420, "loss": 0.0441, "lr": 2.464187574186436e-06, "epoch": 17.435172088637437, "percentage": 87.18, "elapsed_time": "2:13:53", "remaining_time": "0:19:41", "throughput": 4631.67, "total_tokens": 37209568} {"current_steps": 36985, "total_steps": 42420, "loss": 0.098, "lr": 2.4597364679320668e-06, "epoch": 17.437529467232437, "percentage": 87.19, "elapsed_time": "2:13:54", "remaining_time": "0:19:40", "throughput": 4631.69, "total_tokens": 37214592} {"current_steps": 36990, "total_steps": 42420, "loss": 0.1415, "lr": 2.4552891773616e-06, "epoch": 17.43988684582744, "percentage": 87.2, "elapsed_time": "2:13:55", "remaining_time": "0:19:39", "throughput": 4631.7, "total_tokens": 37219104} {"current_steps": 36995, "total_steps": 42420, "loss": 0.0919, "lr": 2.4508457032278885e-06, "epoch": 17.442244224422442, "percentage": 87.21, "elapsed_time": "2:13:56", "remaining_time": "0:19:38", "throughput": 4631.71, "total_tokens": 37223648} {"current_steps": 37000, "total_steps": 42420, "loss": 0.0986, "lr": 2.4464060462831365e-06, "epoch": 17.444601603017446, "percentage": 87.22, "elapsed_time": "2:13:57", "remaining_time": "0:19:37", "throughput": 4631.72, "total_tokens": 37229184} {"current_steps": 37005, "total_steps": 42420, "loss": 0.1359, "lr": 2.441970207278907e-06, "epoch": 17.446958981612447, "percentage": 87.23, "elapsed_time": "2:13:58", "remaining_time": "0:19:36", "throughput": 4631.74, "total_tokens": 37233824} {"current_steps": 37010, "total_steps": 42420, "loss": 0.1057, "lr": 2.437538186966104e-06, "epoch": 17.44931636020745, "percentage": 87.25, "elapsed_time": "2:13:59", "remaining_time": "0:19:35", "throughput": 4631.77, "total_tokens": 37239200} {"current_steps": 37015, "total_steps": 42420, "loss": 0.0483, "lr": 2.4331099860949973e-06, "epoch": 17.45167373880245, "percentage": 87.26, "elapsed_time": "2:14:01", "remaining_time": "0:19:34", "throughput": 4631.83, "total_tokens": 37245728} {"current_steps": 37020, "total_steps": 42420, "loss": 0.1223, "lr": 2.428685605415204e-06, "epoch": 17.454031117397456, "percentage": 87.27, "elapsed_time": "2:14:02", "remaining_time": "0:19:33", "throughput": 4631.85, "total_tokens": 37250848} {"current_steps": 37025, "total_steps": 42420, "loss": 0.0964, "lr": 2.4242650456757027e-06, "epoch": 17.456388495992456, "percentage": 87.28, "elapsed_time": "2:14:03", "remaining_time": "0:19:32", "throughput": 4631.88, "total_tokens": 37255872} {"current_steps": 37030, "total_steps": 42420, "loss": 0.1786, "lr": 2.4198483076248114e-06, "epoch": 17.458745874587457, "percentage": 87.29, "elapsed_time": "2:14:04", "remaining_time": "0:19:30", "throughput": 4631.92, "total_tokens": 37261856} {"current_steps": 37035, "total_steps": 42420, "loss": 0.1455, "lr": 2.4154353920102125e-06, "epoch": 17.46110325318246, "percentage": 87.31, "elapsed_time": "2:14:05", "remaining_time": "0:19:29", "throughput": 4631.96, "total_tokens": 37267584} {"current_steps": 37040, "total_steps": 42420, "loss": 0.0458, "lr": 2.411026299578939e-06, "epoch": 17.463460631777462, "percentage": 87.32, "elapsed_time": "2:14:07", "remaining_time": "0:19:28", "throughput": 4632.01, "total_tokens": 37274240} {"current_steps": 37045, "total_steps": 42420, "loss": 0.1788, "lr": 2.4066210310773774e-06, "epoch": 17.465818010372466, "percentage": 87.33, "elapsed_time": "2:14:08", "remaining_time": "0:19:27", "throughput": 4631.99, "total_tokens": 37278368} {"current_steps": 37050, "total_steps": 42420, "loss": 0.177, "lr": 2.402219587251259e-06, "epoch": 17.468175388967467, "percentage": 87.34, "elapsed_time": "2:14:09", "remaining_time": "0:19:26", "throughput": 4631.99, "total_tokens": 37283200} {"current_steps": 37055, "total_steps": 42420, "loss": 0.0424, "lr": 2.397821968845676e-06, "epoch": 17.47053276756247, "percentage": 87.35, "elapsed_time": "2:14:10", "remaining_time": "0:19:25", "throughput": 4631.99, "total_tokens": 37287712} {"current_steps": 37060, "total_steps": 42420, "loss": 0.1846, "lr": 2.393428176605067e-06, "epoch": 17.47289014615747, "percentage": 87.36, "elapsed_time": "2:14:11", "remaining_time": "0:19:24", "throughput": 4631.99, "total_tokens": 37292864} {"current_steps": 37065, "total_steps": 42420, "loss": 0.1471, "lr": 2.389038211273234e-06, "epoch": 17.475247524752476, "percentage": 87.38, "elapsed_time": "2:14:12", "remaining_time": "0:19:23", "throughput": 4632.02, "total_tokens": 37298400} {"current_steps": 37070, "total_steps": 42420, "loss": 0.1859, "lr": 2.384652073593316e-06, "epoch": 17.477604903347476, "percentage": 87.39, "elapsed_time": "2:14:13", "remaining_time": "0:19:22", "throughput": 4632.03, "total_tokens": 37303072} {"current_steps": 37075, "total_steps": 42420, "loss": 0.102, "lr": 2.380269764307819e-06, "epoch": 17.47996228194248, "percentage": 87.4, "elapsed_time": "2:14:14", "remaining_time": "0:19:21", "throughput": 4632.03, "total_tokens": 37307456} {"current_steps": 37080, "total_steps": 42420, "loss": 0.0942, "lr": 2.375891284158588e-06, "epoch": 17.48231966053748, "percentage": 87.41, "elapsed_time": "2:14:15", "remaining_time": "0:19:20", "throughput": 4632.07, "total_tokens": 37312640} {"current_steps": 37085, "total_steps": 42420, "loss": 0.0208, "lr": 2.3715166338868305e-06, "epoch": 17.484677039132485, "percentage": 87.42, "elapsed_time": "2:14:16", "remaining_time": "0:19:18", "throughput": 4632.11, "total_tokens": 37317920} {"current_steps": 37090, "total_steps": 42420, "loss": 0.1183, "lr": 2.3671458142330934e-06, "epoch": 17.487034417727486, "percentage": 87.44, "elapsed_time": "2:14:17", "remaining_time": "0:19:17", "throughput": 4632.14, "total_tokens": 37323168} {"current_steps": 37095, "total_steps": 42420, "loss": 0.0735, "lr": 2.3627788259372896e-06, "epoch": 17.48939179632249, "percentage": 87.45, "elapsed_time": "2:14:18", "remaining_time": "0:19:16", "throughput": 4632.17, "total_tokens": 37327808} {"current_steps": 37100, "total_steps": 42420, "loss": 0.127, "lr": 2.35841566973867e-06, "epoch": 17.49174917491749, "percentage": 87.46, "elapsed_time": "2:14:19", "remaining_time": "0:19:15", "throughput": 4632.19, "total_tokens": 37332576} {"current_steps": 37105, "total_steps": 42420, "loss": 0.0864, "lr": 2.3540563463758436e-06, "epoch": 17.494106553512495, "percentage": 87.47, "elapsed_time": "2:14:20", "remaining_time": "0:19:14", "throughput": 4632.19, "total_tokens": 37336416} {"current_steps": 37110, "total_steps": 42420, "loss": 0.1282, "lr": 2.349700856586773e-06, "epoch": 17.496463932107496, "percentage": 87.48, "elapsed_time": "2:14:21", "remaining_time": "0:19:13", "throughput": 4632.19, "total_tokens": 37340544} {"current_steps": 37115, "total_steps": 42420, "loss": 0.0668, "lr": 2.3453492011087653e-06, "epoch": 17.4988213107025, "percentage": 87.49, "elapsed_time": "2:14:21", "remaining_time": "0:19:12", "throughput": 4632.19, "total_tokens": 37344640} {"current_steps": 37120, "total_steps": 42420, "loss": 0.1042, "lr": 2.341001380678484e-06, "epoch": 17.5011786892975, "percentage": 87.51, "elapsed_time": "2:14:23", "remaining_time": "0:19:11", "throughput": 4632.21, "total_tokens": 37349792} {"current_steps": 37125, "total_steps": 42420, "loss": 0.2072, "lr": 2.3366573960319438e-06, "epoch": 17.503536067892504, "percentage": 87.52, "elapsed_time": "2:14:23", "remaining_time": "0:19:10", "throughput": 4632.21, "total_tokens": 37353824} {"current_steps": 37130, "total_steps": 42420, "loss": 0.086, "lr": 2.332317247904503e-06, "epoch": 17.505893446487505, "percentage": 87.53, "elapsed_time": "2:14:25", "remaining_time": "0:19:09", "throughput": 4632.26, "total_tokens": 37359744} {"current_steps": 37135, "total_steps": 42420, "loss": 0.2152, "lr": 2.3279809370308796e-06, "epoch": 17.50825082508251, "percentage": 87.54, "elapsed_time": "2:14:26", "remaining_time": "0:19:07", "throughput": 4632.28, "total_tokens": 37364480} {"current_steps": 37140, "total_steps": 42420, "loss": 0.119, "lr": 2.323648464145131e-06, "epoch": 17.51060820367751, "percentage": 87.55, "elapsed_time": "2:14:27", "remaining_time": "0:19:06", "throughput": 4632.3, "total_tokens": 37369184} {"current_steps": 37145, "total_steps": 42420, "loss": 0.1112, "lr": 2.3193198299806763e-06, "epoch": 17.512965582272514, "percentage": 87.56, "elapsed_time": "2:14:27", "remaining_time": "0:19:05", "throughput": 4632.33, "total_tokens": 37373440} {"current_steps": 37150, "total_steps": 42420, "loss": 0.0993, "lr": 2.3149950352702786e-06, "epoch": 17.515322960867515, "percentage": 87.58, "elapsed_time": "2:14:29", "remaining_time": "0:19:04", "throughput": 4632.36, "total_tokens": 37378816} {"current_steps": 37155, "total_steps": 42420, "loss": 0.0393, "lr": 2.3106740807460503e-06, "epoch": 17.51768033946252, "percentage": 87.59, "elapsed_time": "2:14:29", "remaining_time": "0:19:03", "throughput": 4632.36, "total_tokens": 37382688} {"current_steps": 37160, "total_steps": 42420, "loss": 0.132, "lr": 2.3063569671394584e-06, "epoch": 17.52003771805752, "percentage": 87.6, "elapsed_time": "2:14:31", "remaining_time": "0:19:02", "throughput": 4632.38, "total_tokens": 37388608} {"current_steps": 37165, "total_steps": 42420, "loss": 0.0312, "lr": 2.3020436951813133e-06, "epoch": 17.522395096652524, "percentage": 87.61, "elapsed_time": "2:14:32", "remaining_time": "0:19:01", "throughput": 4632.38, "total_tokens": 37393120} {"current_steps": 37170, "total_steps": 42420, "loss": 0.1079, "lr": 2.2977342656017836e-06, "epoch": 17.524752475247524, "percentage": 87.62, "elapsed_time": "2:14:33", "remaining_time": "0:19:00", "throughput": 4632.4, "total_tokens": 37398752} {"current_steps": 37175, "total_steps": 42420, "loss": 0.163, "lr": 2.2934286791303854e-06, "epoch": 17.52710985384253, "percentage": 87.64, "elapsed_time": "2:14:34", "remaining_time": "0:18:59", "throughput": 4632.42, "total_tokens": 37403488} {"current_steps": 37180, "total_steps": 42420, "loss": 0.0564, "lr": 2.2891269364959693e-06, "epoch": 17.52946723243753, "percentage": 87.65, "elapsed_time": "2:14:35", "remaining_time": "0:18:58", "throughput": 4632.46, "total_tokens": 37409024} {"current_steps": 37185, "total_steps": 42420, "loss": 0.086, "lr": 2.2848290384267557e-06, "epoch": 17.531824611032533, "percentage": 87.66, "elapsed_time": "2:14:36", "remaining_time": "0:18:57", "throughput": 4632.46, "total_tokens": 37414656} {"current_steps": 37190, "total_steps": 42420, "loss": 0.0967, "lr": 2.280534985650304e-06, "epoch": 17.534181989627534, "percentage": 87.67, "elapsed_time": "2:14:37", "remaining_time": "0:18:55", "throughput": 4632.47, "total_tokens": 37419264} {"current_steps": 37195, "total_steps": 42420, "loss": 0.0434, "lr": 2.2762447788935244e-06, "epoch": 17.536539368222538, "percentage": 87.68, "elapsed_time": "2:14:38", "remaining_time": "0:18:54", "throughput": 4632.46, "total_tokens": 37423776} {"current_steps": 37200, "total_steps": 42420, "loss": 0.1299, "lr": 2.2719584188826775e-06, "epoch": 17.53889674681754, "percentage": 87.69, "elapsed_time": "2:14:39", "remaining_time": "0:18:53", "throughput": 4632.47, "total_tokens": 37428480} {"current_steps": 37205, "total_steps": 42420, "loss": 0.0322, "lr": 2.2676759063433693e-06, "epoch": 17.541254125412543, "percentage": 87.71, "elapsed_time": "2:14:40", "remaining_time": "0:18:52", "throughput": 4632.49, "total_tokens": 37433344} {"current_steps": 37210, "total_steps": 42420, "loss": 0.1259, "lr": 2.2633972420005562e-06, "epoch": 17.543611504007544, "percentage": 87.72, "elapsed_time": "2:14:41", "remaining_time": "0:18:51", "throughput": 4632.53, "total_tokens": 37439104} {"current_steps": 37215, "total_steps": 42420, "loss": 0.0628, "lr": 2.2591224265785527e-06, "epoch": 17.545968882602544, "percentage": 87.73, "elapsed_time": "2:14:42", "remaining_time": "0:18:50", "throughput": 4632.56, "total_tokens": 37444192} {"current_steps": 37220, "total_steps": 42420, "loss": 0.2222, "lr": 2.254851460800997e-06, "epoch": 17.54832626119755, "percentage": 87.74, "elapsed_time": "2:14:43", "remaining_time": "0:18:49", "throughput": 4632.52, "total_tokens": 37448096} {"current_steps": 37225, "total_steps": 42420, "loss": 0.1642, "lr": 2.2505843453908963e-06, "epoch": 17.55068363979255, "percentage": 87.75, "elapsed_time": "2:14:44", "remaining_time": "0:18:48", "throughput": 4632.56, "total_tokens": 37453568} {"current_steps": 37230, "total_steps": 42420, "loss": 0.0331, "lr": 2.246321081070607e-06, "epoch": 17.553041018387553, "percentage": 87.77, "elapsed_time": "2:14:46", "remaining_time": "0:18:47", "throughput": 4632.61, "total_tokens": 37459712} {"current_steps": 37235, "total_steps": 42420, "loss": 0.0692, "lr": 2.242061668561821e-06, "epoch": 17.555398396982554, "percentage": 87.78, "elapsed_time": "2:14:47", "remaining_time": "0:18:46", "throughput": 4632.61, "total_tokens": 37464416} {"current_steps": 37240, "total_steps": 42420, "loss": 0.1388, "lr": 2.2378061085855858e-06, "epoch": 17.557755775577558, "percentage": 87.79, "elapsed_time": "2:14:48", "remaining_time": "0:18:45", "throughput": 4632.63, "total_tokens": 37469760} {"current_steps": 37245, "total_steps": 42420, "loss": 0.0713, "lr": 2.233554401862298e-06, "epoch": 17.56011315417256, "percentage": 87.8, "elapsed_time": "2:14:49", "remaining_time": "0:18:43", "throughput": 4632.65, "total_tokens": 37474816} {"current_steps": 37250, "total_steps": 42420, "loss": 0.066, "lr": 2.2293065491116956e-06, "epoch": 17.562470532767563, "percentage": 87.81, "elapsed_time": "2:14:50", "remaining_time": "0:18:42", "throughput": 4632.67, "total_tokens": 37479808} {"current_steps": 37255, "total_steps": 42420, "loss": 0.0473, "lr": 2.2250625510528785e-06, "epoch": 17.564827911362563, "percentage": 87.82, "elapsed_time": "2:14:51", "remaining_time": "0:18:41", "throughput": 4632.69, "total_tokens": 37484224} {"current_steps": 37260, "total_steps": 42420, "loss": 0.1085, "lr": 2.2208224084042663e-06, "epoch": 17.567185289957568, "percentage": 87.84, "elapsed_time": "2:14:52", "remaining_time": "0:18:40", "throughput": 4632.7, "total_tokens": 37488992} {"current_steps": 37265, "total_steps": 42420, "loss": 0.0701, "lr": 2.216586121883654e-06, "epoch": 17.569542668552568, "percentage": 87.85, "elapsed_time": "2:14:53", "remaining_time": "0:18:39", "throughput": 4632.76, "total_tokens": 37495488} {"current_steps": 37270, "total_steps": 42420, "loss": 0.0636, "lr": 2.212353692208172e-06, "epoch": 17.571900047147572, "percentage": 87.86, "elapsed_time": "2:14:54", "remaining_time": "0:18:38", "throughput": 4632.8, "total_tokens": 37501216} {"current_steps": 37275, "total_steps": 42420, "loss": 0.0823, "lr": 2.2081251200942952e-06, "epoch": 17.574257425742573, "percentage": 87.87, "elapsed_time": "2:14:55", "remaining_time": "0:18:37", "throughput": 4632.83, "total_tokens": 37506272} {"current_steps": 37280, "total_steps": 42420, "loss": 0.0345, "lr": 2.2039004062578527e-06, "epoch": 17.576614804337577, "percentage": 87.88, "elapsed_time": "2:14:56", "remaining_time": "0:18:36", "throughput": 4632.86, "total_tokens": 37511456} {"current_steps": 37285, "total_steps": 42420, "loss": 0.072, "lr": 2.199679551414016e-06, "epoch": 17.578972182932578, "percentage": 87.89, "elapsed_time": "2:14:57", "remaining_time": "0:18:35", "throughput": 4632.86, "total_tokens": 37515648} {"current_steps": 37290, "total_steps": 42420, "loss": 0.0195, "lr": 2.195462556277303e-06, "epoch": 17.581329561527582, "percentage": 87.91, "elapsed_time": "2:14:58", "remaining_time": "0:18:34", "throughput": 4632.9, "total_tokens": 37520768} {"current_steps": 37295, "total_steps": 42420, "loss": 0.1709, "lr": 2.1912494215615866e-06, "epoch": 17.583686940122583, "percentage": 87.92, "elapsed_time": "2:14:59", "remaining_time": "0:18:33", "throughput": 4632.93, "total_tokens": 37526496} {"current_steps": 37300, "total_steps": 42420, "loss": 0.1929, "lr": 2.1870401479800654e-06, "epoch": 17.586044318717587, "percentage": 87.93, "elapsed_time": "2:15:01", "remaining_time": "0:18:31", "throughput": 4632.95, "total_tokens": 37531552} {"current_steps": 37305, "total_steps": 42420, "loss": 0.1351, "lr": 2.1828347362453095e-06, "epoch": 17.588401697312587, "percentage": 87.94, "elapsed_time": "2:15:01", "remaining_time": "0:18:30", "throughput": 4632.99, "total_tokens": 37536416} {"current_steps": 37310, "total_steps": 42420, "loss": 0.0667, "lr": 2.178633187069215e-06, "epoch": 17.59075907590759, "percentage": 87.95, "elapsed_time": "2:15:02", "remaining_time": "0:18:29", "throughput": 4632.98, "total_tokens": 37540640} {"current_steps": 37315, "total_steps": 42420, "loss": 0.0238, "lr": 2.174435501163044e-06, "epoch": 17.593116454502592, "percentage": 87.97, "elapsed_time": "2:15:03", "remaining_time": "0:18:28", "throughput": 4633.0, "total_tokens": 37545632} {"current_steps": 37320, "total_steps": 42420, "loss": 0.0388, "lr": 2.170241679237381e-06, "epoch": 17.595473833097596, "percentage": 87.98, "elapsed_time": "2:15:05", "remaining_time": "0:18:27", "throughput": 4633.01, "total_tokens": 37550656} {"current_steps": 37325, "total_steps": 42420, "loss": 0.0322, "lr": 2.1660517220021742e-06, "epoch": 17.597831211692597, "percentage": 87.99, "elapsed_time": "2:15:06", "remaining_time": "0:18:26", "throughput": 4633.02, "total_tokens": 37555360} {"current_steps": 37330, "total_steps": 42420, "loss": 0.1444, "lr": 2.1618656301667122e-06, "epoch": 17.6001885902876, "percentage": 88.0, "elapsed_time": "2:15:07", "remaining_time": "0:18:25", "throughput": 4633.03, "total_tokens": 37561408} {"current_steps": 37335, "total_steps": 42420, "loss": 0.1766, "lr": 2.157683404439631e-06, "epoch": 17.602545968882602, "percentage": 88.01, "elapsed_time": "2:15:08", "remaining_time": "0:18:24", "throughput": 4633.06, "total_tokens": 37566912} {"current_steps": 37340, "total_steps": 42420, "loss": 0.151, "lr": 2.1535050455289143e-06, "epoch": 17.604903347477606, "percentage": 88.02, "elapsed_time": "2:15:09", "remaining_time": "0:18:23", "throughput": 4633.03, "total_tokens": 37571040} {"current_steps": 37345, "total_steps": 42420, "loss": 0.0976, "lr": 2.1493305541418733e-06, "epoch": 17.607260726072607, "percentage": 88.04, "elapsed_time": "2:15:10", "remaining_time": "0:18:22", "throughput": 4633.05, "total_tokens": 37576096} {"current_steps": 37350, "total_steps": 42420, "loss": 0.1015, "lr": 2.145159930985191e-06, "epoch": 17.60961810466761, "percentage": 88.05, "elapsed_time": "2:15:11", "remaining_time": "0:18:21", "throughput": 4633.04, "total_tokens": 37580640} {"current_steps": 37355, "total_steps": 42420, "loss": 0.131, "lr": 2.14099317676488e-06, "epoch": 17.61197548326261, "percentage": 88.06, "elapsed_time": "2:15:12", "remaining_time": "0:18:19", "throughput": 4633.05, "total_tokens": 37585440} {"current_steps": 37360, "total_steps": 42420, "loss": 0.0431, "lr": 2.1368302921862983e-06, "epoch": 17.614332861857616, "percentage": 88.07, "elapsed_time": "2:15:13", "remaining_time": "0:18:18", "throughput": 4633.07, "total_tokens": 37590304} {"current_steps": 37365, "total_steps": 42420, "loss": 0.1505, "lr": 2.132671277954154e-06, "epoch": 17.616690240452616, "percentage": 88.08, "elapsed_time": "2:15:14", "remaining_time": "0:18:17", "throughput": 4633.12, "total_tokens": 37596576} {"current_steps": 37370, "total_steps": 42420, "loss": 0.1697, "lr": 2.1285161347724956e-06, "epoch": 17.61904761904762, "percentage": 88.1, "elapsed_time": "2:15:15", "remaining_time": "0:18:16", "throughput": 4633.13, "total_tokens": 37601024} {"current_steps": 37375, "total_steps": 42420, "loss": 0.2597, "lr": 2.1243648633447217e-06, "epoch": 17.62140499764262, "percentage": 88.11, "elapsed_time": "2:15:16", "remaining_time": "0:18:15", "throughput": 4633.14, "total_tokens": 37605888} {"current_steps": 37380, "total_steps": 42420, "loss": 0.022, "lr": 2.120217464373575e-06, "epoch": 17.623762376237625, "percentage": 88.12, "elapsed_time": "2:15:17", "remaining_time": "0:18:14", "throughput": 4633.18, "total_tokens": 37611424} {"current_steps": 37385, "total_steps": 42420, "loss": 0.0643, "lr": 2.1160739385611306e-06, "epoch": 17.626119754832626, "percentage": 88.13, "elapsed_time": "2:15:18", "remaining_time": "0:18:13", "throughput": 4633.18, "total_tokens": 37616544} {"current_steps": 37390, "total_steps": 42420, "loss": 0.2324, "lr": 2.1119342866088186e-06, "epoch": 17.62847713342763, "percentage": 88.14, "elapsed_time": "2:15:19", "remaining_time": "0:18:12", "throughput": 4633.2, "total_tokens": 37621120} {"current_steps": 37395, "total_steps": 42420, "loss": 0.0968, "lr": 2.107798509217418e-06, "epoch": 17.63083451202263, "percentage": 88.15, "elapsed_time": "2:15:20", "remaining_time": "0:18:11", "throughput": 4633.21, "total_tokens": 37625440} {"current_steps": 37400, "total_steps": 42420, "loss": 0.2095, "lr": 2.1036666070870402e-06, "epoch": 17.633191890617635, "percentage": 88.17, "elapsed_time": "2:15:22", "remaining_time": "0:18:10", "throughput": 4633.25, "total_tokens": 37631424} {"current_steps": 37405, "total_steps": 42420, "loss": 0.0892, "lr": 2.099538580917149e-06, "epoch": 17.635549269212635, "percentage": 88.18, "elapsed_time": "2:15:23", "remaining_time": "0:18:09", "throughput": 4633.29, "total_tokens": 37636704} {"current_steps": 37410, "total_steps": 42420, "loss": 0.1593, "lr": 2.0954144314065506e-06, "epoch": 17.63790664780764, "percentage": 88.19, "elapsed_time": "2:15:24", "remaining_time": "0:18:07", "throughput": 4633.31, "total_tokens": 37641568} {"current_steps": 37415, "total_steps": 42420, "loss": 0.1159, "lr": 2.0912941592533877e-06, "epoch": 17.64026402640264, "percentage": 88.2, "elapsed_time": "2:15:25", "remaining_time": "0:18:06", "throughput": 4633.34, "total_tokens": 37646464} {"current_steps": 37420, "total_steps": 42420, "loss": 0.1056, "lr": 2.0871777651551627e-06, "epoch": 17.64262140499764, "percentage": 88.21, "elapsed_time": "2:15:26", "remaining_time": "0:18:05", "throughput": 4633.34, "total_tokens": 37650912} {"current_steps": 37425, "total_steps": 42420, "loss": 0.1252, "lr": 2.0830652498086993e-06, "epoch": 17.644978783592645, "percentage": 88.22, "elapsed_time": "2:15:27", "remaining_time": "0:18:04", "throughput": 4633.33, "total_tokens": 37655232} {"current_steps": 37430, "total_steps": 42420, "loss": 0.1623, "lr": 2.0789566139101796e-06, "epoch": 17.647336162187646, "percentage": 88.24, "elapsed_time": "2:15:28", "remaining_time": "0:18:03", "throughput": 4633.36, "total_tokens": 37660608} {"current_steps": 37435, "total_steps": 42420, "loss": 0.1365, "lr": 2.07485185815513e-06, "epoch": 17.64969354078265, "percentage": 88.25, "elapsed_time": "2:15:29", "remaining_time": "0:18:02", "throughput": 4633.4, "total_tokens": 37665760} {"current_steps": 37440, "total_steps": 42420, "loss": 0.2185, "lr": 2.0707509832384147e-06, "epoch": 17.65205091937765, "percentage": 88.26, "elapsed_time": "2:15:30", "remaining_time": "0:18:01", "throughput": 4633.39, "total_tokens": 37669952} {"current_steps": 37445, "total_steps": 42420, "loss": 0.1053, "lr": 2.066653989854242e-06, "epoch": 17.654408297972655, "percentage": 88.27, "elapsed_time": "2:15:30", "remaining_time": "0:18:00", "throughput": 4633.4, "total_tokens": 37674144} {"current_steps": 37450, "total_steps": 42420, "loss": 0.1525, "lr": 2.0625608786961596e-06, "epoch": 17.656765676567655, "percentage": 88.28, "elapsed_time": "2:15:32", "remaining_time": "0:17:59", "throughput": 4633.43, "total_tokens": 37679264} {"current_steps": 37455, "total_steps": 42420, "loss": 0.0401, "lr": 2.0584716504570667e-06, "epoch": 17.65912305516266, "percentage": 88.3, "elapsed_time": "2:15:33", "remaining_time": "0:17:58", "throughput": 4633.46, "total_tokens": 37684288} {"current_steps": 37460, "total_steps": 42420, "loss": 0.085, "lr": 2.0543863058292033e-06, "epoch": 17.66148043375766, "percentage": 88.31, "elapsed_time": "2:15:34", "remaining_time": "0:17:57", "throughput": 4633.46, "total_tokens": 37688704} {"current_steps": 37465, "total_steps": 42420, "loss": 0.0589, "lr": 2.050304845504139e-06, "epoch": 17.663837812352664, "percentage": 88.32, "elapsed_time": "2:15:35", "remaining_time": "0:17:55", "throughput": 4633.48, "total_tokens": 37693696} {"current_steps": 37470, "total_steps": 42420, "loss": 0.0782, "lr": 2.0462272701728015e-06, "epoch": 17.666195190947665, "percentage": 88.33, "elapsed_time": "2:15:36", "remaining_time": "0:17:54", "throughput": 4633.5, "total_tokens": 37698784} {"current_steps": 37475, "total_steps": 42420, "loss": 0.1709, "lr": 2.042153580525455e-06, "epoch": 17.66855256954267, "percentage": 88.34, "elapsed_time": "2:15:37", "remaining_time": "0:17:53", "throughput": 4633.53, "total_tokens": 37703968} {"current_steps": 37480, "total_steps": 42420, "loss": 0.1283, "lr": 2.038083777251704e-06, "epoch": 17.67090994813767, "percentage": 88.35, "elapsed_time": "2:15:38", "remaining_time": "0:17:52", "throughput": 4633.57, "total_tokens": 37709216} {"current_steps": 37485, "total_steps": 42420, "loss": 0.1044, "lr": 2.0340178610404965e-06, "epoch": 17.673267326732674, "percentage": 88.37, "elapsed_time": "2:15:39", "remaining_time": "0:17:51", "throughput": 4633.54, "total_tokens": 37713376} {"current_steps": 37490, "total_steps": 42420, "loss": 0.081, "lr": 2.0299558325801273e-06, "epoch": 17.675624705327674, "percentage": 88.38, "elapsed_time": "2:15:40", "remaining_time": "0:17:50", "throughput": 4633.58, "total_tokens": 37718784} {"current_steps": 37495, "total_steps": 42420, "loss": 0.2035, "lr": 2.025897692558226e-06, "epoch": 17.67798208392268, "percentage": 88.39, "elapsed_time": "2:15:41", "remaining_time": "0:17:49", "throughput": 4633.62, "total_tokens": 37723584} {"current_steps": 37500, "total_steps": 42420, "loss": 0.1117, "lr": 2.0218434416617722e-06, "epoch": 17.68033946251768, "percentage": 88.4, "elapsed_time": "2:15:42", "remaining_time": "0:17:48", "throughput": 4633.63, "total_tokens": 37728256} {"current_steps": 37505, "total_steps": 42420, "loss": 0.0968, "lr": 2.017793080577071e-06, "epoch": 17.682696841112683, "percentage": 88.41, "elapsed_time": "2:15:43", "remaining_time": "0:17:47", "throughput": 4633.64, "total_tokens": 37732544} {"current_steps": 37510, "total_steps": 42420, "loss": 0.0592, "lr": 2.0137466099897862e-06, "epoch": 17.685054219707684, "percentage": 88.43, "elapsed_time": "2:15:44", "remaining_time": "0:17:46", "throughput": 4633.68, "total_tokens": 37737536} {"current_steps": 37515, "total_steps": 42420, "loss": 0.0372, "lr": 2.0097040305849165e-06, "epoch": 17.68741159830269, "percentage": 88.44, "elapsed_time": "2:15:45", "remaining_time": "0:17:44", "throughput": 4633.68, "total_tokens": 37742080} {"current_steps": 37520, "total_steps": 42420, "loss": 0.1135, "lr": 2.0056653430468e-06, "epoch": 17.68976897689769, "percentage": 88.45, "elapsed_time": "2:15:46", "remaining_time": "0:17:43", "throughput": 4633.68, "total_tokens": 37746784} {"current_steps": 37525, "total_steps": 42420, "loss": 0.0724, "lr": 2.001630548059122e-06, "epoch": 17.692126355492693, "percentage": 88.46, "elapsed_time": "2:15:47", "remaining_time": "0:17:42", "throughput": 4633.71, "total_tokens": 37752160} {"current_steps": 37530, "total_steps": 42420, "loss": 0.1395, "lr": 1.9975996463049013e-06, "epoch": 17.694483734087694, "percentage": 88.47, "elapsed_time": "2:15:48", "remaining_time": "0:17:41", "throughput": 4633.75, "total_tokens": 37758272} {"current_steps": 37535, "total_steps": 42420, "loss": 0.0766, "lr": 1.993572638466501e-06, "epoch": 17.696841112682698, "percentage": 88.48, "elapsed_time": "2:15:49", "remaining_time": "0:17:40", "throughput": 4633.77, "total_tokens": 37762464} {"current_steps": 37540, "total_steps": 42420, "loss": 0.0563, "lr": 1.9895495252256286e-06, "epoch": 17.6991984912777, "percentage": 88.5, "elapsed_time": "2:15:50", "remaining_time": "0:17:39", "throughput": 4633.8, "total_tokens": 37768384} {"current_steps": 37545, "total_steps": 42420, "loss": 0.1166, "lr": 1.9855303072633254e-06, "epoch": 17.701555869872703, "percentage": 88.51, "elapsed_time": "2:15:51", "remaining_time": "0:17:38", "throughput": 4633.81, "total_tokens": 37773120} {"current_steps": 37550, "total_steps": 42420, "loss": 0.1408, "lr": 1.9815149852599803e-06, "epoch": 17.703913248467703, "percentage": 88.52, "elapsed_time": "2:15:52", "remaining_time": "0:17:37", "throughput": 4633.83, "total_tokens": 37777952} {"current_steps": 37555, "total_steps": 42420, "loss": 0.1353, "lr": 1.9775035598953134e-06, "epoch": 17.706270627062707, "percentage": 88.53, "elapsed_time": "2:15:53", "remaining_time": "0:17:36", "throughput": 4633.86, "total_tokens": 37782880} {"current_steps": 37560, "total_steps": 42420, "loss": 0.3658, "lr": 1.9734960318483932e-06, "epoch": 17.708628005657708, "percentage": 88.54, "elapsed_time": "2:15:54", "remaining_time": "0:17:35", "throughput": 4633.89, "total_tokens": 37788192} {"current_steps": 37565, "total_steps": 42420, "loss": 0.1171, "lr": 1.969492401797626e-06, "epoch": 17.710985384252712, "percentage": 88.55, "elapsed_time": "2:15:55", "remaining_time": "0:17:34", "throughput": 4633.92, "total_tokens": 37793056} {"current_steps": 37570, "total_steps": 42420, "loss": 0.1682, "lr": 1.9654926704207627e-06, "epoch": 17.713342762847713, "percentage": 88.57, "elapsed_time": "2:15:56", "remaining_time": "0:17:32", "throughput": 4633.93, "total_tokens": 37797600} {"current_steps": 37575, "total_steps": 42420, "loss": 0.0568, "lr": 1.961496838394883e-06, "epoch": 17.715700141442717, "percentage": 88.58, "elapsed_time": "2:15:57", "remaining_time": "0:17:31", "throughput": 4633.96, "total_tokens": 37802656} {"current_steps": 37580, "total_steps": 42420, "loss": 0.0335, "lr": 1.957504906396421e-06, "epoch": 17.718057520037718, "percentage": 88.59, "elapsed_time": "2:15:58", "remaining_time": "0:17:30", "throughput": 4633.96, "total_tokens": 37806848} {"current_steps": 37585, "total_steps": 42420, "loss": 0.0217, "lr": 1.9535168751011357e-06, "epoch": 17.720414898632722, "percentage": 88.6, "elapsed_time": "2:15:59", "remaining_time": "0:17:29", "throughput": 4633.99, "total_tokens": 37812224} {"current_steps": 37590, "total_steps": 42420, "loss": 0.0352, "lr": 1.9495327451841405e-06, "epoch": 17.722772277227723, "percentage": 88.61, "elapsed_time": "2:16:00", "remaining_time": "0:17:28", "throughput": 4634.03, "total_tokens": 37817440} {"current_steps": 37595, "total_steps": 42420, "loss": 0.0487, "lr": 1.9455525173198736e-06, "epoch": 17.725129655822727, "percentage": 88.63, "elapsed_time": "2:16:01", "remaining_time": "0:17:27", "throughput": 4634.02, "total_tokens": 37821344} {"current_steps": 37600, "total_steps": 42420, "loss": 0.1202, "lr": 1.9415761921821233e-06, "epoch": 17.727487034417727, "percentage": 88.64, "elapsed_time": "2:16:02", "remaining_time": "0:17:26", "throughput": 4634.06, "total_tokens": 37826816} {"current_steps": 37605, "total_steps": 42420, "loss": 0.1809, "lr": 1.9376037704440157e-06, "epoch": 17.72984441301273, "percentage": 88.65, "elapsed_time": "2:16:03", "remaining_time": "0:17:25", "throughput": 4634.09, "total_tokens": 37831616} {"current_steps": 37610, "total_steps": 42420, "loss": 0.0697, "lr": 1.93363525277801e-06, "epoch": 17.732201791607732, "percentage": 88.66, "elapsed_time": "2:16:04", "remaining_time": "0:17:24", "throughput": 4634.05, "total_tokens": 37834944} {"current_steps": 37615, "total_steps": 42420, "loss": 0.1628, "lr": 1.9296706398559126e-06, "epoch": 17.734559170202736, "percentage": 88.67, "elapsed_time": "2:16:05", "remaining_time": "0:17:23", "throughput": 4634.08, "total_tokens": 37839392} {"current_steps": 37620, "total_steps": 42420, "loss": 0.1059, "lr": 1.9257099323488625e-06, "epoch": 17.736916548797737, "percentage": 88.68, "elapsed_time": "2:16:06", "remaining_time": "0:17:21", "throughput": 4634.1, "total_tokens": 37843936} {"current_steps": 37625, "total_steps": 42420, "loss": 0.1941, "lr": 1.921753130927345e-06, "epoch": 17.739273927392738, "percentage": 88.7, "elapsed_time": "2:16:07", "remaining_time": "0:17:20", "throughput": 4634.12, "total_tokens": 37848416} {"current_steps": 37630, "total_steps": 42420, "loss": 0.2541, "lr": 1.9178002362611776e-06, "epoch": 17.74163130598774, "percentage": 88.71, "elapsed_time": "2:16:08", "remaining_time": "0:17:19", "throughput": 4634.16, "total_tokens": 37854016} {"current_steps": 37635, "total_steps": 42420, "loss": 0.0526, "lr": 1.913851249019513e-06, "epoch": 17.743988684582742, "percentage": 88.72, "elapsed_time": "2:16:09", "remaining_time": "0:17:18", "throughput": 4634.22, "total_tokens": 37861216} {"current_steps": 37640, "total_steps": 42420, "loss": 0.0766, "lr": 1.909906169870851e-06, "epoch": 17.746346063177747, "percentage": 88.73, "elapsed_time": "2:16:10", "remaining_time": "0:17:17", "throughput": 4634.25, "total_tokens": 37866144} {"current_steps": 37645, "total_steps": 42420, "loss": 0.066, "lr": 1.9059649994830286e-06, "epoch": 17.748703441772747, "percentage": 88.74, "elapsed_time": "2:16:12", "remaining_time": "0:17:16", "throughput": 4634.27, "total_tokens": 37871392} {"current_steps": 37650, "total_steps": 42420, "loss": 0.0828, "lr": 1.9020277385232154e-06, "epoch": 17.75106082036775, "percentage": 88.76, "elapsed_time": "2:16:13", "remaining_time": "0:17:15", "throughput": 4634.31, "total_tokens": 37876256} {"current_steps": 37655, "total_steps": 42420, "loss": 0.0211, "lr": 1.8980943876579254e-06, "epoch": 17.753418198962752, "percentage": 88.77, "elapsed_time": "2:16:14", "remaining_time": "0:17:14", "throughput": 4634.35, "total_tokens": 37881312} {"current_steps": 37660, "total_steps": 42420, "loss": 0.1645, "lr": 1.8941649475530094e-06, "epoch": 17.755775577557756, "percentage": 88.78, "elapsed_time": "2:16:15", "remaining_time": "0:17:13", "throughput": 4634.38, "total_tokens": 37887712} {"current_steps": 37665, "total_steps": 42420, "loss": 0.0466, "lr": 1.8902394188736516e-06, "epoch": 17.758132956152757, "percentage": 88.79, "elapsed_time": "2:16:16", "remaining_time": "0:17:12", "throughput": 4634.39, "total_tokens": 37892192} {"current_steps": 37670, "total_steps": 42420, "loss": 0.0963, "lr": 1.886317802284382e-06, "epoch": 17.76049033474776, "percentage": 88.8, "elapsed_time": "2:16:17", "remaining_time": "0:17:11", "throughput": 4634.38, "total_tokens": 37895904} {"current_steps": 37675, "total_steps": 42420, "loss": 0.1588, "lr": 1.882400098449058e-06, "epoch": 17.76284771334276, "percentage": 88.81, "elapsed_time": "2:16:18", "remaining_time": "0:17:09", "throughput": 4634.41, "total_tokens": 37900576} {"current_steps": 37680, "total_steps": 42420, "loss": 0.0997, "lr": 1.8784863080308828e-06, "epoch": 17.765205091937766, "percentage": 88.83, "elapsed_time": "2:16:18", "remaining_time": "0:17:08", "throughput": 4634.42, "total_tokens": 37904800} {"current_steps": 37685, "total_steps": 42420, "loss": 0.1365, "lr": 1.874576431692393e-06, "epoch": 17.767562470532766, "percentage": 88.84, "elapsed_time": "2:16:19", "remaining_time": "0:17:07", "throughput": 4634.44, "total_tokens": 37909568} {"current_steps": 37690, "total_steps": 42420, "loss": 0.134, "lr": 1.8706704700954676e-06, "epoch": 17.76991984912777, "percentage": 88.85, "elapsed_time": "2:16:21", "remaining_time": "0:17:06", "throughput": 4634.48, "total_tokens": 37917248} {"current_steps": 37695, "total_steps": 42420, "loss": 0.0625, "lr": 1.8667684239013188e-06, "epoch": 17.77227722772277, "percentage": 88.86, "elapsed_time": "2:16:22", "remaining_time": "0:17:05", "throughput": 4634.49, "total_tokens": 37922464} {"current_steps": 37700, "total_steps": 42420, "loss": 0.0441, "lr": 1.8628702937704939e-06, "epoch": 17.774634606317775, "percentage": 88.87, "elapsed_time": "2:16:23", "remaining_time": "0:17:04", "throughput": 4634.5, "total_tokens": 37927040} {"current_steps": 37705, "total_steps": 42420, "loss": 0.0151, "lr": 1.8589760803628814e-06, "epoch": 17.776991984912776, "percentage": 88.88, "elapsed_time": "2:16:24", "remaining_time": "0:17:03", "throughput": 4634.52, "total_tokens": 37931296} {"current_steps": 37710, "total_steps": 42420, "loss": 0.0372, "lr": 1.8550857843377124e-06, "epoch": 17.77934936350778, "percentage": 88.9, "elapsed_time": "2:16:25", "remaining_time": "0:17:02", "throughput": 4634.56, "total_tokens": 37936160} {"current_steps": 37715, "total_steps": 42420, "loss": 0.1087, "lr": 1.8511994063535377e-06, "epoch": 17.78170674210278, "percentage": 88.91, "elapsed_time": "2:16:26", "remaining_time": "0:17:01", "throughput": 4634.59, "total_tokens": 37941248} {"current_steps": 37720, "total_steps": 42420, "loss": 0.0574, "lr": 1.8473169470682588e-06, "epoch": 17.784064120697785, "percentage": 88.92, "elapsed_time": "2:16:27", "remaining_time": "0:17:00", "throughput": 4634.64, "total_tokens": 37947936} {"current_steps": 37725, "total_steps": 42420, "loss": 0.0883, "lr": 1.8434384071391087e-06, "epoch": 17.786421499292786, "percentage": 88.93, "elapsed_time": "2:16:28", "remaining_time": "0:16:59", "throughput": 4634.68, "total_tokens": 37953216} {"current_steps": 37730, "total_steps": 42420, "loss": 0.1464, "lr": 1.8395637872226618e-06, "epoch": 17.78877887788779, "percentage": 88.94, "elapsed_time": "2:16:29", "remaining_time": "0:16:58", "throughput": 4634.71, "total_tokens": 37957984} {"current_steps": 37735, "total_steps": 42420, "loss": 0.169, "lr": 1.835693087974824e-06, "epoch": 17.79113625648279, "percentage": 88.96, "elapsed_time": "2:16:31", "remaining_time": "0:16:56", "throughput": 4634.74, "total_tokens": 37963168} {"current_steps": 37740, "total_steps": 42420, "loss": 0.0469, "lr": 1.831826310050841e-06, "epoch": 17.793493635077795, "percentage": 88.97, "elapsed_time": "2:16:32", "remaining_time": "0:16:55", "throughput": 4634.77, "total_tokens": 37968256} {"current_steps": 37745, "total_steps": 42420, "loss": 0.1449, "lr": 1.8279634541052886e-06, "epoch": 17.795851013672795, "percentage": 88.98, "elapsed_time": "2:16:33", "remaining_time": "0:16:54", "throughput": 4634.82, "total_tokens": 37975488} {"current_steps": 37750, "total_steps": 42420, "loss": 0.1121, "lr": 1.8241045207920888e-06, "epoch": 17.7982083922678, "percentage": 88.99, "elapsed_time": "2:16:34", "remaining_time": "0:16:53", "throughput": 4634.86, "total_tokens": 37980672} {"current_steps": 37755, "total_steps": 42420, "loss": 0.0889, "lr": 1.8202495107644824e-06, "epoch": 17.8005657708628, "percentage": 89.0, "elapsed_time": "2:16:35", "remaining_time": "0:16:52", "throughput": 4634.87, "total_tokens": 37984800} {"current_steps": 37760, "total_steps": 42420, "loss": 0.0474, "lr": 1.8163984246750671e-06, "epoch": 17.802923149457804, "percentage": 89.01, "elapsed_time": "2:16:36", "remaining_time": "0:16:51", "throughput": 4634.9, "total_tokens": 37989920} {"current_steps": 37765, "total_steps": 42420, "loss": 0.2985, "lr": 1.8125512631757686e-06, "epoch": 17.805280528052805, "percentage": 89.03, "elapsed_time": "2:16:37", "remaining_time": "0:16:50", "throughput": 4634.95, "total_tokens": 37995648} {"current_steps": 37770, "total_steps": 42420, "loss": 0.0732, "lr": 1.8087080269178352e-06, "epoch": 17.80763790664781, "percentage": 89.04, "elapsed_time": "2:16:38", "remaining_time": "0:16:49", "throughput": 4634.99, "total_tokens": 38000992} {"current_steps": 37775, "total_steps": 42420, "loss": 0.0174, "lr": 1.8048687165518662e-06, "epoch": 17.80999528524281, "percentage": 89.05, "elapsed_time": "2:16:39", "remaining_time": "0:16:48", "throughput": 4634.99, "total_tokens": 38004960} {"current_steps": 37780, "total_steps": 42420, "loss": 0.1565, "lr": 1.8010333327277944e-06, "epoch": 17.812352663837814, "percentage": 89.06, "elapsed_time": "2:16:40", "remaining_time": "0:16:47", "throughput": 4635.01, "total_tokens": 38009344} {"current_steps": 37785, "total_steps": 42420, "loss": 0.0489, "lr": 1.7972018760948812e-06, "epoch": 17.814710042432814, "percentage": 89.07, "elapsed_time": "2:16:41", "remaining_time": "0:16:46", "throughput": 4635.05, "total_tokens": 38014880} {"current_steps": 37790, "total_steps": 42420, "loss": 0.1341, "lr": 1.7933743473017295e-06, "epoch": 17.81706742102782, "percentage": 89.09, "elapsed_time": "2:16:42", "remaining_time": "0:16:44", "throughput": 4635.04, "total_tokens": 38019104} {"current_steps": 37795, "total_steps": 42420, "loss": 0.0764, "lr": 1.7895507469962768e-06, "epoch": 17.81942479962282, "percentage": 89.1, "elapsed_time": "2:16:43", "remaining_time": "0:16:43", "throughput": 4635.06, "total_tokens": 38023712} {"current_steps": 37800, "total_steps": 42420, "loss": 0.0321, "lr": 1.7857310758257945e-06, "epoch": 17.821782178217823, "percentage": 89.11, "elapsed_time": "2:16:44", "remaining_time": "0:16:42", "throughput": 4635.08, "total_tokens": 38027904} {"current_steps": 37805, "total_steps": 42420, "loss": 0.1905, "lr": 1.7819153344368816e-06, "epoch": 17.824139556812824, "percentage": 89.12, "elapsed_time": "2:16:45", "remaining_time": "0:16:41", "throughput": 4635.1, "total_tokens": 38032832} {"current_steps": 37810, "total_steps": 42420, "loss": 0.0842, "lr": 1.77810352347548e-06, "epoch": 17.826496935407828, "percentage": 89.13, "elapsed_time": "2:16:46", "remaining_time": "0:16:40", "throughput": 4635.11, "total_tokens": 38037952} {"current_steps": 37815, "total_steps": 42420, "loss": 0.066, "lr": 1.774295643586868e-06, "epoch": 17.82885431400283, "percentage": 89.14, "elapsed_time": "2:16:47", "remaining_time": "0:16:39", "throughput": 4635.13, "total_tokens": 38042560} {"current_steps": 37820, "total_steps": 42420, "loss": 0.03, "lr": 1.7704916954156548e-06, "epoch": 17.831211692597833, "percentage": 89.16, "elapsed_time": "2:16:48", "remaining_time": "0:16:38", "throughput": 4635.17, "total_tokens": 38048384} {"current_steps": 37825, "total_steps": 42420, "loss": 0.032, "lr": 1.7666916796057808e-06, "epoch": 17.833569071192834, "percentage": 89.17, "elapsed_time": "2:16:49", "remaining_time": "0:16:37", "throughput": 4635.2, "total_tokens": 38053504} {"current_steps": 37830, "total_steps": 42420, "loss": 0.1019, "lr": 1.762895596800529e-06, "epoch": 17.835926449787834, "percentage": 89.18, "elapsed_time": "2:16:50", "remaining_time": "0:16:36", "throughput": 4635.23, "total_tokens": 38058592} {"current_steps": 37835, "total_steps": 42420, "loss": 0.1031, "lr": 1.7591034476425072e-06, "epoch": 17.83828382838284, "percentage": 89.19, "elapsed_time": "2:16:51", "remaining_time": "0:16:35", "throughput": 4635.25, "total_tokens": 38063264} {"current_steps": 37840, "total_steps": 42420, "loss": 0.1033, "lr": 1.755315232773666e-06, "epoch": 17.84064120697784, "percentage": 89.2, "elapsed_time": "2:16:52", "remaining_time": "0:16:34", "throughput": 4635.28, "total_tokens": 38068416} {"current_steps": 37845, "total_steps": 42420, "loss": 0.069, "lr": 1.7515309528352813e-06, "epoch": 17.842998585572843, "percentage": 89.21, "elapsed_time": "2:16:53", "remaining_time": "0:16:32", "throughput": 4635.3, "total_tokens": 38073376} {"current_steps": 37850, "total_steps": 42420, "loss": 0.1191, "lr": 1.7477506084679713e-06, "epoch": 17.845355964167844, "percentage": 89.23, "elapsed_time": "2:16:54", "remaining_time": "0:16:31", "throughput": 4635.35, "total_tokens": 38078944} {"current_steps": 37855, "total_steps": 42420, "loss": 0.2296, "lr": 1.743974200311682e-06, "epoch": 17.847713342762848, "percentage": 89.24, "elapsed_time": "2:16:55", "remaining_time": "0:16:30", "throughput": 4635.38, "total_tokens": 38083648} {"current_steps": 37860, "total_steps": 42420, "loss": 0.0471, "lr": 1.7402017290056943e-06, "epoch": 17.85007072135785, "percentage": 89.25, "elapsed_time": "2:16:56", "remaining_time": "0:16:29", "throughput": 4635.42, "total_tokens": 38089184} {"current_steps": 37865, "total_steps": 42420, "loss": 0.0616, "lr": 1.7364331951886247e-06, "epoch": 17.852428099952853, "percentage": 89.26, "elapsed_time": "2:16:57", "remaining_time": "0:16:28", "throughput": 4635.44, "total_tokens": 38093760} {"current_steps": 37870, "total_steps": 42420, "loss": 0.2448, "lr": 1.7326685994984243e-06, "epoch": 17.854785478547853, "percentage": 89.27, "elapsed_time": "2:16:58", "remaining_time": "0:16:27", "throughput": 4635.48, "total_tokens": 38098848} {"current_steps": 37875, "total_steps": 42420, "loss": 0.1608, "lr": 1.728907942572372e-06, "epoch": 17.857142857142858, "percentage": 89.29, "elapsed_time": "2:16:59", "remaining_time": "0:16:26", "throughput": 4635.52, "total_tokens": 38103904} {"current_steps": 37880, "total_steps": 42420, "loss": 0.2126, "lr": 1.7251512250470891e-06, "epoch": 17.85950023573786, "percentage": 89.3, "elapsed_time": "2:17:00", "remaining_time": "0:16:25", "throughput": 4635.54, "total_tokens": 38108320} {"current_steps": 37885, "total_steps": 42420, "loss": 0.2316, "lr": 1.7213984475585144e-06, "epoch": 17.861857614332862, "percentage": 89.31, "elapsed_time": "2:17:01", "remaining_time": "0:16:24", "throughput": 4635.58, "total_tokens": 38113728} {"current_steps": 37890, "total_steps": 42420, "loss": 0.0389, "lr": 1.7176496107419338e-06, "epoch": 17.864214992927863, "percentage": 89.32, "elapsed_time": "2:17:03", "remaining_time": "0:16:23", "throughput": 4635.61, "total_tokens": 38119360} {"current_steps": 37895, "total_steps": 42420, "loss": 0.0533, "lr": 1.713904715231962e-06, "epoch": 17.866572371522867, "percentage": 89.33, "elapsed_time": "2:17:04", "remaining_time": "0:16:22", "throughput": 4635.64, "total_tokens": 38125024} {"current_steps": 37900, "total_steps": 42420, "loss": 0.1163, "lr": 1.7101637616625503e-06, "epoch": 17.868929750117868, "percentage": 89.34, "elapsed_time": "2:17:05", "remaining_time": "0:16:20", "throughput": 4635.64, "total_tokens": 38128992} {"current_steps": 37905, "total_steps": 42420, "loss": 0.1953, "lr": 1.7064267506669702e-06, "epoch": 17.871287128712872, "percentage": 89.36, "elapsed_time": "2:17:06", "remaining_time": "0:16:19", "throughput": 4635.63, "total_tokens": 38132928} {"current_steps": 37910, "total_steps": 42420, "loss": 0.0468, "lr": 1.702693682877843e-06, "epoch": 17.873644507307873, "percentage": 89.37, "elapsed_time": "2:17:06", "remaining_time": "0:16:18", "throughput": 4635.62, "total_tokens": 38136896} {"current_steps": 37915, "total_steps": 42420, "loss": 0.0835, "lr": 1.6989645589271076e-06, "epoch": 17.876001885902877, "percentage": 89.38, "elapsed_time": "2:17:07", "remaining_time": "0:16:17", "throughput": 4635.63, "total_tokens": 38141792} {"current_steps": 37920, "total_steps": 42420, "loss": 0.0565, "lr": 1.6952393794460453e-06, "epoch": 17.878359264497877, "percentage": 89.39, "elapsed_time": "2:17:08", "remaining_time": "0:16:16", "throughput": 4635.65, "total_tokens": 38146496} {"current_steps": 37925, "total_steps": 42420, "loss": 0.13, "lr": 1.691518145065263e-06, "epoch": 17.88071664309288, "percentage": 89.4, "elapsed_time": "2:17:09", "remaining_time": "0:16:15", "throughput": 4635.68, "total_tokens": 38151136} {"current_steps": 37930, "total_steps": 42420, "loss": 0.0353, "lr": 1.6878008564147007e-06, "epoch": 17.883074021687882, "percentage": 89.42, "elapsed_time": "2:17:10", "remaining_time": "0:16:14", "throughput": 4635.7, "total_tokens": 38155968} {"current_steps": 37935, "total_steps": 42420, "loss": 0.0204, "lr": 1.6840875141236362e-06, "epoch": 17.885431400282886, "percentage": 89.43, "elapsed_time": "2:17:11", "remaining_time": "0:16:13", "throughput": 4635.72, "total_tokens": 38161088} {"current_steps": 37940, "total_steps": 42420, "loss": 0.1929, "lr": 1.6803781188206746e-06, "epoch": 17.887788778877887, "percentage": 89.44, "elapsed_time": "2:17:13", "remaining_time": "0:16:12", "throughput": 4635.77, "total_tokens": 38167360} {"current_steps": 37945, "total_steps": 42420, "loss": 0.0819, "lr": 1.6766726711337527e-06, "epoch": 17.89014615747289, "percentage": 89.45, "elapsed_time": "2:17:14", "remaining_time": "0:16:11", "throughput": 4635.81, "total_tokens": 38173088} {"current_steps": 37950, "total_steps": 42420, "loss": 0.0983, "lr": 1.6729711716901381e-06, "epoch": 17.892503536067892, "percentage": 89.46, "elapsed_time": "2:17:15", "remaining_time": "0:16:10", "throughput": 4635.85, "total_tokens": 38178336} {"current_steps": 37955, "total_steps": 42420, "loss": 0.0664, "lr": 1.669273621116435e-06, "epoch": 17.894860914662896, "percentage": 89.47, "elapsed_time": "2:17:16", "remaining_time": "0:16:08", "throughput": 4635.87, "total_tokens": 38182816} {"current_steps": 37960, "total_steps": 42420, "loss": 0.0208, "lr": 1.665580020038579e-06, "epoch": 17.897218293257897, "percentage": 89.49, "elapsed_time": "2:17:17", "remaining_time": "0:16:07", "throughput": 4635.9, "total_tokens": 38187936} {"current_steps": 37965, "total_steps": 42420, "loss": 0.074, "lr": 1.6618903690818255e-06, "epoch": 17.8995756718529, "percentage": 89.5, "elapsed_time": "2:17:18", "remaining_time": "0:16:06", "throughput": 4635.91, "total_tokens": 38192224} {"current_steps": 37970, "total_steps": 42420, "loss": 0.0975, "lr": 1.658204668870772e-06, "epoch": 17.9019330504479, "percentage": 89.51, "elapsed_time": "2:17:19", "remaining_time": "0:16:05", "throughput": 4635.88, "total_tokens": 38196032} {"current_steps": 37975, "total_steps": 42420, "loss": 0.1836, "lr": 1.65452292002935e-06, "epoch": 17.904290429042906, "percentage": 89.52, "elapsed_time": "2:17:20", "remaining_time": "0:16:04", "throughput": 4635.92, "total_tokens": 38201824} {"current_steps": 37980, "total_steps": 42420, "loss": 0.0093, "lr": 1.6508451231808109e-06, "epoch": 17.906647807637906, "percentage": 89.53, "elapsed_time": "2:17:21", "remaining_time": "0:16:03", "throughput": 4635.96, "total_tokens": 38206912} {"current_steps": 37985, "total_steps": 42420, "loss": 0.0929, "lr": 1.6471712789477484e-06, "epoch": 17.90900518623291, "percentage": 89.55, "elapsed_time": "2:17:22", "remaining_time": "0:16:02", "throughput": 4635.98, "total_tokens": 38211968} {"current_steps": 37990, "total_steps": 42420, "loss": 0.1243, "lr": 1.6435013879520844e-06, "epoch": 17.91136256482791, "percentage": 89.56, "elapsed_time": "2:17:23", "remaining_time": "0:16:01", "throughput": 4636.04, "total_tokens": 38218624} {"current_steps": 37995, "total_steps": 42420, "loss": 0.0255, "lr": 1.639835450815061e-06, "epoch": 17.913719943422915, "percentage": 89.57, "elapsed_time": "2:17:24", "remaining_time": "0:16:00", "throughput": 4636.07, "total_tokens": 38223104} {"current_steps": 38000, "total_steps": 42420, "loss": 0.0902, "lr": 1.6361734681572593e-06, "epoch": 17.916077322017916, "percentage": 89.58, "elapsed_time": "2:17:25", "remaining_time": "0:15:59", "throughput": 4636.07, "total_tokens": 38227456} {"current_steps": 38005, "total_steps": 42420, "loss": 0.0694, "lr": 1.6325154405985977e-06, "epoch": 17.91843470061292, "percentage": 89.59, "elapsed_time": "2:17:26", "remaining_time": "0:15:58", "throughput": 4636.08, "total_tokens": 38231968} {"current_steps": 38010, "total_steps": 42420, "loss": 0.1082, "lr": 1.6288613687583164e-06, "epoch": 17.92079207920792, "percentage": 89.6, "elapsed_time": "2:17:27", "remaining_time": "0:15:56", "throughput": 4636.1, "total_tokens": 38236992} {"current_steps": 38015, "total_steps": 42420, "loss": 0.0443, "lr": 1.625211253254985e-06, "epoch": 17.92314945780292, "percentage": 89.62, "elapsed_time": "2:17:28", "remaining_time": "0:15:55", "throughput": 4636.16, "total_tokens": 38243072} {"current_steps": 38020, "total_steps": 42420, "loss": 0.0527, "lr": 1.6215650947065037e-06, "epoch": 17.925506836397926, "percentage": 89.63, "elapsed_time": "2:17:29", "remaining_time": "0:15:54", "throughput": 4636.18, "total_tokens": 38247808} {"current_steps": 38025, "total_steps": 42420, "loss": 0.3327, "lr": 1.6179228937301116e-06, "epoch": 17.927864214992926, "percentage": 89.64, "elapsed_time": "2:17:31", "remaining_time": "0:15:53", "throughput": 4636.25, "total_tokens": 38254656} {"current_steps": 38030, "total_steps": 42420, "loss": 0.1888, "lr": 1.6142846509423658e-06, "epoch": 17.93022159358793, "percentage": 89.65, "elapsed_time": "2:17:32", "remaining_time": "0:15:52", "throughput": 4636.27, "total_tokens": 38259232} {"current_steps": 38035, "total_steps": 42420, "loss": 0.0187, "lr": 1.6106503669591655e-06, "epoch": 17.93257897218293, "percentage": 89.66, "elapsed_time": "2:17:33", "remaining_time": "0:15:51", "throughput": 4636.3, "total_tokens": 38264128} {"current_steps": 38040, "total_steps": 42420, "loss": 0.052, "lr": 1.6070200423957265e-06, "epoch": 17.934936350777935, "percentage": 89.67, "elapsed_time": "2:17:34", "remaining_time": "0:15:50", "throughput": 4636.32, "total_tokens": 38269312} {"current_steps": 38045, "total_steps": 42420, "loss": 0.1065, "lr": 1.6033936778666047e-06, "epoch": 17.937293729372936, "percentage": 89.69, "elapsed_time": "2:17:35", "remaining_time": "0:15:49", "throughput": 4636.33, "total_tokens": 38274144} {"current_steps": 38050, "total_steps": 42420, "loss": 0.1398, "lr": 1.599771273985684e-06, "epoch": 17.93965110796794, "percentage": 89.7, "elapsed_time": "2:17:36", "remaining_time": "0:15:48", "throughput": 4636.37, "total_tokens": 38278976} {"current_steps": 38055, "total_steps": 42420, "loss": 0.1514, "lr": 1.596152831366171e-06, "epoch": 17.94200848656294, "percentage": 89.71, "elapsed_time": "2:17:37", "remaining_time": "0:15:47", "throughput": 4636.4, "total_tokens": 38284192} {"current_steps": 38060, "total_steps": 42420, "loss": 0.267, "lr": 1.5925383506206094e-06, "epoch": 17.944365865157945, "percentage": 89.72, "elapsed_time": "2:17:38", "remaining_time": "0:15:46", "throughput": 4636.43, "total_tokens": 38289696} {"current_steps": 38065, "total_steps": 42420, "loss": 0.2702, "lr": 1.5889278323608702e-06, "epoch": 17.946723243752945, "percentage": 89.73, "elapsed_time": "2:17:39", "remaining_time": "0:15:44", "throughput": 4636.43, "total_tokens": 38293792} {"current_steps": 38070, "total_steps": 42420, "loss": 0.0434, "lr": 1.5853212771981484e-06, "epoch": 17.94908062234795, "percentage": 89.75, "elapsed_time": "2:17:40", "remaining_time": "0:15:43", "throughput": 4636.46, "total_tokens": 38299136} {"current_steps": 38075, "total_steps": 42420, "loss": 0.0257, "lr": 1.5817186857429779e-06, "epoch": 17.95143800094295, "percentage": 89.76, "elapsed_time": "2:17:41", "remaining_time": "0:15:42", "throughput": 4636.5, "total_tokens": 38304608} {"current_steps": 38080, "total_steps": 42420, "loss": 0.1999, "lr": 1.578120058605212e-06, "epoch": 17.953795379537954, "percentage": 89.77, "elapsed_time": "2:17:42", "remaining_time": "0:15:41", "throughput": 4636.56, "total_tokens": 38311200} {"current_steps": 38085, "total_steps": 42420, "loss": 0.0648, "lr": 1.5745253963940416e-06, "epoch": 17.956152758132955, "percentage": 89.78, "elapsed_time": "2:17:44", "remaining_time": "0:15:40", "throughput": 4636.61, "total_tokens": 38316928} {"current_steps": 38090, "total_steps": 42420, "loss": 0.0659, "lr": 1.5709346997179824e-06, "epoch": 17.95851013672796, "percentage": 89.79, "elapsed_time": "2:17:45", "remaining_time": "0:15:39", "throughput": 4636.63, "total_tokens": 38321888} {"current_steps": 38095, "total_steps": 42420, "loss": 0.0711, "lr": 1.5673479691848737e-06, "epoch": 17.96086751532296, "percentage": 89.8, "elapsed_time": "2:17:45", "remaining_time": "0:15:38", "throughput": 4636.65, "total_tokens": 38326496} {"current_steps": 38100, "total_steps": 42420, "loss": 0.1354, "lr": 1.5637652054018875e-06, "epoch": 17.963224893917964, "percentage": 89.82, "elapsed_time": "2:17:46", "remaining_time": "0:15:37", "throughput": 4636.65, "total_tokens": 38330976} {"current_steps": 38105, "total_steps": 42420, "loss": 0.0629, "lr": 1.560186408975528e-06, "epoch": 17.965582272512965, "percentage": 89.83, "elapsed_time": "2:17:47", "remaining_time": "0:15:36", "throughput": 4636.62, "total_tokens": 38335072} {"current_steps": 38110, "total_steps": 42420, "loss": 0.111, "lr": 1.5566115805116243e-06, "epoch": 17.96793965110797, "percentage": 89.84, "elapsed_time": "2:17:48", "remaining_time": "0:15:35", "throughput": 4636.63, "total_tokens": 38339808} {"current_steps": 38115, "total_steps": 42420, "loss": 0.0931, "lr": 1.5530407206153342e-06, "epoch": 17.97029702970297, "percentage": 89.85, "elapsed_time": "2:17:50", "remaining_time": "0:15:34", "throughput": 4636.67, "total_tokens": 38345696} {"current_steps": 38120, "total_steps": 42420, "loss": 0.0555, "lr": 1.5494738298911432e-06, "epoch": 17.972654408297974, "percentage": 89.86, "elapsed_time": "2:17:50", "remaining_time": "0:15:32", "throughput": 4636.66, "total_tokens": 38349632} {"current_steps": 38125, "total_steps": 42420, "loss": 0.1683, "lr": 1.545910908942866e-06, "epoch": 17.975011786892974, "percentage": 89.88, "elapsed_time": "2:17:51", "remaining_time": "0:15:31", "throughput": 4636.69, "total_tokens": 38354592} {"current_steps": 38130, "total_steps": 42420, "loss": 0.0512, "lr": 1.5423519583736472e-06, "epoch": 17.97736916548798, "percentage": 89.89, "elapsed_time": "2:17:53", "remaining_time": "0:15:30", "throughput": 4636.71, "total_tokens": 38359552} {"current_steps": 38135, "total_steps": 42420, "loss": 0.1685, "lr": 1.5387969787859503e-06, "epoch": 17.97972654408298, "percentage": 89.9, "elapsed_time": "2:17:53", "remaining_time": "0:15:29", "throughput": 4636.72, "total_tokens": 38363872} {"current_steps": 38140, "total_steps": 42420, "loss": 0.0553, "lr": 1.5352459707815764e-06, "epoch": 17.982083922677983, "percentage": 89.91, "elapsed_time": "2:17:55", "remaining_time": "0:15:28", "throughput": 4636.74, "total_tokens": 38369760} {"current_steps": 38145, "total_steps": 42420, "loss": 0.1845, "lr": 1.5316989349616507e-06, "epoch": 17.984441301272984, "percentage": 89.92, "elapsed_time": "2:17:56", "remaining_time": "0:15:27", "throughput": 4636.76, "total_tokens": 38375168} {"current_steps": 38150, "total_steps": 42420, "loss": 0.0623, "lr": 1.5281558719266258e-06, "epoch": 17.986798679867988, "percentage": 89.93, "elapsed_time": "2:17:57", "remaining_time": "0:15:26", "throughput": 4636.77, "total_tokens": 38379936} {"current_steps": 38155, "total_steps": 42420, "loss": 0.0628, "lr": 1.5246167822762808e-06, "epoch": 17.98915605846299, "percentage": 89.95, "elapsed_time": "2:17:58", "remaining_time": "0:15:25", "throughput": 4636.8, "total_tokens": 38385056} {"current_steps": 38160, "total_steps": 42420, "loss": 0.2301, "lr": 1.5210816666097277e-06, "epoch": 17.991513437057993, "percentage": 89.96, "elapsed_time": "2:17:59", "remaining_time": "0:15:24", "throughput": 4636.82, "total_tokens": 38390048} {"current_steps": 38165, "total_steps": 42420, "loss": 0.0948, "lr": 1.5175505255253992e-06, "epoch": 17.993870815652993, "percentage": 89.97, "elapsed_time": "2:18:00", "remaining_time": "0:15:23", "throughput": 4636.85, "total_tokens": 38395136} {"current_steps": 38170, "total_steps": 42420, "loss": 0.064, "lr": 1.5140233596210612e-06, "epoch": 17.996228194247998, "percentage": 89.98, "elapsed_time": "2:18:01", "remaining_time": "0:15:22", "throughput": 4636.84, "total_tokens": 38399520} {"current_steps": 38175, "total_steps": 42420, "loss": 0.1512, "lr": 1.5105001694937949e-06, "epoch": 17.998585572842998, "percentage": 89.99, "elapsed_time": "2:18:02", "remaining_time": "0:15:21", "throughput": 4636.89, "total_tokens": 38405632} {"current_steps": 38178, "total_steps": 42420, "eval_loss": 0.15290038287639618, "epoch": 18.0, "percentage": 90.0, "elapsed_time": "2:18:18", "remaining_time": "0:15:22", "throughput": 4628.33, "total_tokens": 38408800} {"current_steps": 38180, "total_steps": 42420, "loss": 0.1137, "lr": 1.50698095574002e-06, "epoch": 18.000942951438002, "percentage": 90.0, "elapsed_time": "2:18:20", "remaining_time": "0:15:21", "throughput": 4627.48, "total_tokens": 38410912} {"current_steps": 38185, "total_steps": 42420, "loss": 0.0959, "lr": 1.5034657189554824e-06, "epoch": 18.003300330033003, "percentage": 90.02, "elapsed_time": "2:18:22", "remaining_time": "0:15:20", "throughput": 4627.52, "total_tokens": 38418112} {"current_steps": 38190, "total_steps": 42420, "loss": 0.0534, "lr": 1.4999544597352505e-06, "epoch": 18.005657708628007, "percentage": 90.03, "elapsed_time": "2:18:23", "remaining_time": "0:15:19", "throughput": 4627.52, "total_tokens": 38423040} {"current_steps": 38195, "total_steps": 42420, "loss": 0.0248, "lr": 1.4964471786737184e-06, "epoch": 18.008015087223008, "percentage": 90.04, "elapsed_time": "2:18:24", "remaining_time": "0:15:18", "throughput": 4627.53, "total_tokens": 38427520} {"current_steps": 38200, "total_steps": 42420, "loss": 0.0336, "lr": 1.492943876364611e-06, "epoch": 18.010372465818012, "percentage": 90.05, "elapsed_time": "2:18:25", "remaining_time": "0:15:17", "throughput": 4627.54, "total_tokens": 38432032} {"current_steps": 38205, "total_steps": 42420, "loss": 0.099, "lr": 1.4894445534009816e-06, "epoch": 18.012729844413013, "percentage": 90.06, "elapsed_time": "2:18:26", "remaining_time": "0:15:16", "throughput": 4627.57, "total_tokens": 38437504} {"current_steps": 38210, "total_steps": 42420, "loss": 0.085, "lr": 1.4859492103752037e-06, "epoch": 18.015087223008017, "percentage": 90.08, "elapsed_time": "2:18:27", "remaining_time": "0:15:15", "throughput": 4627.6, "total_tokens": 38442240} {"current_steps": 38215, "total_steps": 42420, "loss": 0.0383, "lr": 1.4824578478789763e-06, "epoch": 18.017444601603017, "percentage": 90.09, "elapsed_time": "2:18:28", "remaining_time": "0:15:14", "throughput": 4627.62, "total_tokens": 38447232} {"current_steps": 38220, "total_steps": 42420, "loss": 0.1113, "lr": 1.4789704665033321e-06, "epoch": 18.019801980198018, "percentage": 90.1, "elapsed_time": "2:18:29", "remaining_time": "0:15:13", "throughput": 4627.63, "total_tokens": 38451936} {"current_steps": 38225, "total_steps": 42420, "loss": 0.0824, "lr": 1.475487066838621e-06, "epoch": 18.022159358793022, "percentage": 90.11, "elapsed_time": "2:18:30", "remaining_time": "0:15:12", "throughput": 4627.62, "total_tokens": 38456896} {"current_steps": 38230, "total_steps": 42420, "loss": 0.2471, "lr": 1.4720076494745243e-06, "epoch": 18.024516737388023, "percentage": 90.12, "elapsed_time": "2:18:31", "remaining_time": "0:15:10", "throughput": 4627.64, "total_tokens": 38461568} {"current_steps": 38235, "total_steps": 42420, "loss": 0.1113, "lr": 1.468532215000054e-06, "epoch": 18.026874115983027, "percentage": 90.13, "elapsed_time": "2:18:32", "remaining_time": "0:15:09", "throughput": 4627.65, "total_tokens": 38466080} {"current_steps": 38240, "total_steps": 42420, "loss": 0.1319, "lr": 1.4650607640035342e-06, "epoch": 18.029231494578028, "percentage": 90.15, "elapsed_time": "2:18:33", "remaining_time": "0:15:08", "throughput": 4627.67, "total_tokens": 38471296} {"current_steps": 38245, "total_steps": 42420, "loss": 0.0225, "lr": 1.4615932970726276e-06, "epoch": 18.031588873173032, "percentage": 90.16, "elapsed_time": "2:18:34", "remaining_time": "0:15:07", "throughput": 4627.7, "total_tokens": 38476608} {"current_steps": 38250, "total_steps": 42420, "loss": 0.2479, "lr": 1.4581298147943179e-06, "epoch": 18.033946251768032, "percentage": 90.17, "elapsed_time": "2:18:35", "remaining_time": "0:15:06", "throughput": 4627.73, "total_tokens": 38481888} {"current_steps": 38255, "total_steps": 42420, "loss": 0.052, "lr": 1.454670317754911e-06, "epoch": 18.036303630363037, "percentage": 90.18, "elapsed_time": "2:18:36", "remaining_time": "0:15:05", "throughput": 4627.72, "total_tokens": 38486560} {"current_steps": 38260, "total_steps": 42420, "loss": 0.0541, "lr": 1.4512148065400465e-06, "epoch": 18.038661008958037, "percentage": 90.19, "elapsed_time": "2:18:37", "remaining_time": "0:15:04", "throughput": 4627.74, "total_tokens": 38491456} {"current_steps": 38265, "total_steps": 42420, "loss": 0.1157, "lr": 1.4477632817346764e-06, "epoch": 18.04101838755304, "percentage": 90.21, "elapsed_time": "2:18:38", "remaining_time": "0:15:03", "throughput": 4627.78, "total_tokens": 38496992} {"current_steps": 38270, "total_steps": 42420, "loss": 0.3084, "lr": 1.4443157439230858e-06, "epoch": 18.043375766148042, "percentage": 90.22, "elapsed_time": "2:18:39", "remaining_time": "0:15:02", "throughput": 4627.77, "total_tokens": 38501728} {"current_steps": 38275, "total_steps": 42420, "loss": 0.0447, "lr": 1.4408721936888913e-06, "epoch": 18.045733144743046, "percentage": 90.23, "elapsed_time": "2:18:40", "remaining_time": "0:15:01", "throughput": 4627.79, "total_tokens": 38506272} {"current_steps": 38280, "total_steps": 42420, "loss": 0.0947, "lr": 1.4374326316150182e-06, "epoch": 18.048090523338047, "percentage": 90.24, "elapsed_time": "2:18:41", "remaining_time": "0:15:00", "throughput": 4627.81, "total_tokens": 38512000} {"current_steps": 38285, "total_steps": 42420, "loss": 0.1303, "lr": 1.4339970582837343e-06, "epoch": 18.05044790193305, "percentage": 90.25, "elapsed_time": "2:18:42", "remaining_time": "0:14:58", "throughput": 4627.85, "total_tokens": 38517344} {"current_steps": 38290, "total_steps": 42420, "loss": 0.1124, "lr": 1.430565474276621e-06, "epoch": 18.05280528052805, "percentage": 90.26, "elapsed_time": "2:18:43", "remaining_time": "0:14:57", "throughput": 4627.85, "total_tokens": 38521440} {"current_steps": 38295, "total_steps": 42420, "loss": 0.1681, "lr": 1.4271378801745867e-06, "epoch": 18.055162659123056, "percentage": 90.28, "elapsed_time": "2:18:44", "remaining_time": "0:14:56", "throughput": 4627.82, "total_tokens": 38525568} {"current_steps": 38300, "total_steps": 42420, "loss": 0.0516, "lr": 1.4237142765578664e-06, "epoch": 18.057520037718056, "percentage": 90.29, "elapsed_time": "2:18:45", "remaining_time": "0:14:55", "throughput": 4627.85, "total_tokens": 38530336} {"current_steps": 38305, "total_steps": 42420, "loss": 0.222, "lr": 1.4202946640060138e-06, "epoch": 18.05987741631306, "percentage": 90.3, "elapsed_time": "2:18:46", "remaining_time": "0:14:54", "throughput": 4627.87, "total_tokens": 38535264} {"current_steps": 38310, "total_steps": 42420, "loss": 0.0651, "lr": 1.4168790430979128e-06, "epoch": 18.06223479490806, "percentage": 90.31, "elapsed_time": "2:18:47", "remaining_time": "0:14:53", "throughput": 4627.89, "total_tokens": 38540064} {"current_steps": 38315, "total_steps": 42420, "loss": 0.0242, "lr": 1.4134674144117733e-06, "epoch": 18.064592173503065, "percentage": 90.32, "elapsed_time": "2:18:49", "remaining_time": "0:14:52", "throughput": 4627.94, "total_tokens": 38546976} {"current_steps": 38320, "total_steps": 42420, "loss": 0.063, "lr": 1.4100597785251217e-06, "epoch": 18.066949552098066, "percentage": 90.33, "elapsed_time": "2:18:50", "remaining_time": "0:14:51", "throughput": 4627.98, "total_tokens": 38552128} {"current_steps": 38325, "total_steps": 42420, "loss": 0.0469, "lr": 1.4066561360148167e-06, "epoch": 18.06930693069307, "percentage": 90.35, "elapsed_time": "2:18:51", "remaining_time": "0:14:50", "throughput": 4627.99, "total_tokens": 38557088} {"current_steps": 38330, "total_steps": 42420, "loss": 0.0322, "lr": 1.4032564874570359e-06, "epoch": 18.07166430928807, "percentage": 90.36, "elapsed_time": "2:18:52", "remaining_time": "0:14:49", "throughput": 4628.0, "total_tokens": 38562112} {"current_steps": 38335, "total_steps": 42420, "loss": 0.1247, "lr": 1.3998608334272829e-06, "epoch": 18.074021687883075, "percentage": 90.37, "elapsed_time": "2:18:53", "remaining_time": "0:14:47", "throughput": 4627.97, "total_tokens": 38566112} {"current_steps": 38340, "total_steps": 42420, "loss": 0.0259, "lr": 1.3964691745003867e-06, "epoch": 18.076379066478076, "percentage": 90.38, "elapsed_time": "2:18:54", "remaining_time": "0:14:46", "throughput": 4628.0, "total_tokens": 38572000} {"current_steps": 38345, "total_steps": 42420, "loss": 0.2143, "lr": 1.393081511250488e-06, "epoch": 18.07873644507308, "percentage": 90.39, "elapsed_time": "2:18:55", "remaining_time": "0:14:45", "throughput": 4628.01, "total_tokens": 38577024} {"current_steps": 38350, "total_steps": 42420, "loss": 0.0201, "lr": 1.3896978442510672e-06, "epoch": 18.08109382366808, "percentage": 90.41, "elapsed_time": "2:18:56", "remaining_time": "0:14:44", "throughput": 4628.02, "total_tokens": 38581152} {"current_steps": 38355, "total_steps": 42420, "loss": 0.1473, "lr": 1.3863181740749243e-06, "epoch": 18.083451202263085, "percentage": 90.42, "elapsed_time": "2:18:57", "remaining_time": "0:14:43", "throughput": 4628.04, "total_tokens": 38585952} {"current_steps": 38360, "total_steps": 42420, "loss": 0.0402, "lr": 1.3829425012941737e-06, "epoch": 18.085808580858085, "percentage": 90.43, "elapsed_time": "2:18:58", "remaining_time": "0:14:42", "throughput": 4628.07, "total_tokens": 38590528} {"current_steps": 38365, "total_steps": 42420, "loss": 0.0429, "lr": 1.3795708264802642e-06, "epoch": 18.08816595945309, "percentage": 90.44, "elapsed_time": "2:18:59", "remaining_time": "0:14:41", "throughput": 4628.05, "total_tokens": 38594656} {"current_steps": 38370, "total_steps": 42420, "loss": 0.0563, "lr": 1.3762031502039613e-06, "epoch": 18.09052333804809, "percentage": 90.45, "elapsed_time": "2:19:00", "remaining_time": "0:14:40", "throughput": 4628.08, "total_tokens": 38599712} {"current_steps": 38375, "total_steps": 42420, "loss": 0.2606, "lr": 1.3728394730353562e-06, "epoch": 18.092880716643094, "percentage": 90.46, "elapsed_time": "2:19:01", "remaining_time": "0:14:39", "throughput": 4628.11, "total_tokens": 38604832} {"current_steps": 38380, "total_steps": 42420, "loss": 0.0848, "lr": 1.3694797955438655e-06, "epoch": 18.095238095238095, "percentage": 90.48, "elapsed_time": "2:19:02", "remaining_time": "0:14:38", "throughput": 4628.11, "total_tokens": 38609088} {"current_steps": 38385, "total_steps": 42420, "loss": 0.1127, "lr": 1.3661241182982176e-06, "epoch": 18.0975954738331, "percentage": 90.49, "elapsed_time": "2:19:03", "remaining_time": "0:14:37", "throughput": 4628.14, "total_tokens": 38613824} {"current_steps": 38390, "total_steps": 42420, "loss": 0.1049, "lr": 1.3627724418664778e-06, "epoch": 18.0999528524281, "percentage": 90.5, "elapsed_time": "2:19:04", "remaining_time": "0:14:35", "throughput": 4628.16, "total_tokens": 38618752} {"current_steps": 38395, "total_steps": 42420, "loss": 0.1734, "lr": 1.3594247668160253e-06, "epoch": 18.102310231023104, "percentage": 90.51, "elapsed_time": "2:19:05", "remaining_time": "0:14:34", "throughput": 4628.19, "total_tokens": 38624000} {"current_steps": 38400, "total_steps": 42420, "loss": 0.0639, "lr": 1.3560810937135655e-06, "epoch": 18.104667609618105, "percentage": 90.52, "elapsed_time": "2:19:06", "remaining_time": "0:14:33", "throughput": 4628.2, "total_tokens": 38628256} {"current_steps": 38405, "total_steps": 42420, "loss": 0.2052, "lr": 1.3527414231251256e-06, "epoch": 18.10702498821311, "percentage": 90.54, "elapsed_time": "2:19:07", "remaining_time": "0:14:32", "throughput": 4628.23, "total_tokens": 38633504} {"current_steps": 38410, "total_steps": 42420, "loss": 0.1238, "lr": 1.3494057556160566e-06, "epoch": 18.10938236680811, "percentage": 90.55, "elapsed_time": "2:19:08", "remaining_time": "0:14:31", "throughput": 4628.21, "total_tokens": 38637728} {"current_steps": 38415, "total_steps": 42420, "loss": 0.0541, "lr": 1.346074091751029e-06, "epoch": 18.111739745403113, "percentage": 90.56, "elapsed_time": "2:19:09", "remaining_time": "0:14:30", "throughput": 4628.21, "total_tokens": 38642624} {"current_steps": 38420, "total_steps": 42420, "loss": 0.0856, "lr": 1.3427464320940386e-06, "epoch": 18.114097123998114, "percentage": 90.57, "elapsed_time": "2:19:10", "remaining_time": "0:14:29", "throughput": 4628.2, "total_tokens": 38647040} {"current_steps": 38425, "total_steps": 42420, "loss": 0.0855, "lr": 1.3394227772083961e-06, "epoch": 18.116454502593115, "percentage": 90.58, "elapsed_time": "2:19:11", "remaining_time": "0:14:28", "throughput": 4628.17, "total_tokens": 38650784} {"current_steps": 38430, "total_steps": 42420, "loss": 0.1547, "lr": 1.336103127656746e-06, "epoch": 18.11881188118812, "percentage": 90.59, "elapsed_time": "2:19:12", "remaining_time": "0:14:27", "throughput": 4628.19, "total_tokens": 38656224} {"current_steps": 38435, "total_steps": 42420, "loss": 0.0317, "lr": 1.332787484001044e-06, "epoch": 18.12116925978312, "percentage": 90.61, "elapsed_time": "2:19:13", "remaining_time": "0:14:26", "throughput": 4628.23, "total_tokens": 38661952} {"current_steps": 38440, "total_steps": 42420, "loss": 0.148, "lr": 1.3294758468025802e-06, "epoch": 18.123526638378124, "percentage": 90.62, "elapsed_time": "2:19:14", "remaining_time": "0:14:25", "throughput": 4628.25, "total_tokens": 38666816} {"current_steps": 38445, "total_steps": 42420, "loss": 0.0567, "lr": 1.326168216621948e-06, "epoch": 18.125884016973124, "percentage": 90.63, "elapsed_time": "2:19:15", "remaining_time": "0:14:23", "throughput": 4628.25, "total_tokens": 38670720} {"current_steps": 38450, "total_steps": 42420, "loss": 0.0456, "lr": 1.322864594019077e-06, "epoch": 18.12824139556813, "percentage": 90.64, "elapsed_time": "2:19:16", "remaining_time": "0:14:22", "throughput": 4628.28, "total_tokens": 38675168} {"current_steps": 38455, "total_steps": 42420, "loss": 0.1743, "lr": 1.3195649795532173e-06, "epoch": 18.13059877416313, "percentage": 90.65, "elapsed_time": "2:19:17", "remaining_time": "0:14:21", "throughput": 4628.3, "total_tokens": 38680512} {"current_steps": 38460, "total_steps": 42420, "loss": 0.0605, "lr": 1.3162693737829356e-06, "epoch": 18.132956152758133, "percentage": 90.66, "elapsed_time": "2:19:18", "remaining_time": "0:14:20", "throughput": 4628.32, "total_tokens": 38685248} {"current_steps": 38465, "total_steps": 42420, "loss": 0.1778, "lr": 1.312977777266125e-06, "epoch": 18.135313531353134, "percentage": 90.68, "elapsed_time": "2:19:19", "remaining_time": "0:14:19", "throughput": 4628.36, "total_tokens": 38691136} {"current_steps": 38470, "total_steps": 42420, "loss": 0.0664, "lr": 1.3096901905599895e-06, "epoch": 18.137670909948138, "percentage": 90.69, "elapsed_time": "2:19:20", "remaining_time": "0:14:18", "throughput": 4628.38, "total_tokens": 38695872} {"current_steps": 38475, "total_steps": 42420, "loss": 0.0437, "lr": 1.3064066142210673e-06, "epoch": 18.14002828854314, "percentage": 90.7, "elapsed_time": "2:19:21", "remaining_time": "0:14:17", "throughput": 4628.4, "total_tokens": 38700672} {"current_steps": 38480, "total_steps": 42420, "loss": 0.0862, "lr": 1.303127048805211e-06, "epoch": 18.142385667138143, "percentage": 90.71, "elapsed_time": "2:19:22", "remaining_time": "0:14:16", "throughput": 4628.45, "total_tokens": 38706368} {"current_steps": 38485, "total_steps": 42420, "loss": 0.0878, "lr": 1.2998514948675932e-06, "epoch": 18.144743045733144, "percentage": 90.72, "elapsed_time": "2:19:23", "remaining_time": "0:14:15", "throughput": 4628.48, "total_tokens": 38711360} {"current_steps": 38490, "total_steps": 42420, "loss": 0.1077, "lr": 1.296579952962715e-06, "epoch": 18.147100424328148, "percentage": 90.74, "elapsed_time": "2:19:24", "remaining_time": "0:14:14", "throughput": 4628.49, "total_tokens": 38715840} {"current_steps": 38495, "total_steps": 42420, "loss": 0.2678, "lr": 1.2933124236443884e-06, "epoch": 18.14945780292315, "percentage": 90.75, "elapsed_time": "2:19:25", "remaining_time": "0:14:12", "throughput": 4628.52, "total_tokens": 38720608} {"current_steps": 38500, "total_steps": 42420, "loss": 0.117, "lr": 1.2900489074657519e-06, "epoch": 18.151815181518153, "percentage": 90.76, "elapsed_time": "2:19:26", "remaining_time": "0:14:11", "throughput": 4628.55, "total_tokens": 38725440} {"current_steps": 38505, "total_steps": 42420, "loss": 0.0777, "lr": 1.2867894049792662e-06, "epoch": 18.154172560113153, "percentage": 90.77, "elapsed_time": "2:19:27", "remaining_time": "0:14:10", "throughput": 4628.53, "total_tokens": 38729376} {"current_steps": 38510, "total_steps": 42420, "loss": 0.1746, "lr": 1.2835339167367038e-06, "epoch": 18.156529938708157, "percentage": 90.78, "elapsed_time": "2:19:28", "remaining_time": "0:14:09", "throughput": 4628.56, "total_tokens": 38734816} {"current_steps": 38515, "total_steps": 42420, "loss": 0.1885, "lr": 1.2802824432891658e-06, "epoch": 18.158887317303158, "percentage": 90.79, "elapsed_time": "2:19:29", "remaining_time": "0:14:08", "throughput": 4628.61, "total_tokens": 38740800} {"current_steps": 38520, "total_steps": 42420, "loss": 0.064, "lr": 1.2770349851870727e-06, "epoch": 18.161244695898162, "percentage": 90.81, "elapsed_time": "2:19:30", "remaining_time": "0:14:07", "throughput": 4628.62, "total_tokens": 38745024} {"current_steps": 38525, "total_steps": 42420, "loss": 0.0423, "lr": 1.2737915429801628e-06, "epoch": 18.163602074493163, "percentage": 90.82, "elapsed_time": "2:19:31", "remaining_time": "0:14:06", "throughput": 4628.63, "total_tokens": 38749632} {"current_steps": 38530, "total_steps": 42420, "loss": 0.1186, "lr": 1.2705521172174994e-06, "epoch": 18.165959453088167, "percentage": 90.83, "elapsed_time": "2:19:32", "remaining_time": "0:14:05", "throughput": 4628.65, "total_tokens": 38754464} {"current_steps": 38535, "total_steps": 42420, "loss": 0.0427, "lr": 1.267316708447458e-06, "epoch": 18.168316831683168, "percentage": 90.84, "elapsed_time": "2:19:33", "remaining_time": "0:14:04", "throughput": 4628.69, "total_tokens": 38760032} {"current_steps": 38540, "total_steps": 42420, "loss": 0.0707, "lr": 1.2640853172177392e-06, "epoch": 18.17067421027817, "percentage": 90.85, "elapsed_time": "2:19:34", "remaining_time": "0:14:03", "throughput": 4628.72, "total_tokens": 38764896} {"current_steps": 38545, "total_steps": 42420, "loss": 0.0995, "lr": 1.2608579440753664e-06, "epoch": 18.173031588873172, "percentage": 90.87, "elapsed_time": "2:19:35", "remaining_time": "0:14:02", "throughput": 4628.75, "total_tokens": 38769760} {"current_steps": 38550, "total_steps": 42420, "loss": 0.1035, "lr": 1.2576345895666725e-06, "epoch": 18.175388967468177, "percentage": 90.88, "elapsed_time": "2:19:36", "remaining_time": "0:14:00", "throughput": 4628.78, "total_tokens": 38774976} {"current_steps": 38555, "total_steps": 42420, "loss": 0.0762, "lr": 1.2544152542373205e-06, "epoch": 18.177746346063177, "percentage": 90.89, "elapsed_time": "2:19:37", "remaining_time": "0:13:59", "throughput": 4628.79, "total_tokens": 38779392} {"current_steps": 38560, "total_steps": 42420, "loss": 0.0641, "lr": 1.2511999386322914e-06, "epoch": 18.18010372465818, "percentage": 90.9, "elapsed_time": "2:19:38", "remaining_time": "0:13:58", "throughput": 4628.81, "total_tokens": 38784512} {"current_steps": 38565, "total_steps": 42420, "loss": 0.1706, "lr": 1.2479886432958777e-06, "epoch": 18.182461103253182, "percentage": 90.91, "elapsed_time": "2:19:39", "remaining_time": "0:13:57", "throughput": 4628.81, "total_tokens": 38788736} {"current_steps": 38570, "total_steps": 42420, "loss": 0.0556, "lr": 1.2447813687717024e-06, "epoch": 18.184818481848186, "percentage": 90.92, "elapsed_time": "2:19:40", "remaining_time": "0:13:56", "throughput": 4628.82, "total_tokens": 38793376} {"current_steps": 38575, "total_steps": 42420, "loss": 0.0929, "lr": 1.2415781156026985e-06, "epoch": 18.187175860443187, "percentage": 90.94, "elapsed_time": "2:19:41", "remaining_time": "0:13:55", "throughput": 4628.85, "total_tokens": 38798656} {"current_steps": 38580, "total_steps": 42420, "loss": 0.0944, "lr": 1.238378884331126e-06, "epoch": 18.18953323903819, "percentage": 90.95, "elapsed_time": "2:19:42", "remaining_time": "0:13:54", "throughput": 4628.87, "total_tokens": 38803584} {"current_steps": 38585, "total_steps": 42420, "loss": 0.1231, "lr": 1.2351836754985636e-06, "epoch": 18.19189061763319, "percentage": 90.96, "elapsed_time": "2:19:43", "remaining_time": "0:13:53", "throughput": 4628.9, "total_tokens": 38808352} {"current_steps": 38590, "total_steps": 42420, "loss": 0.0884, "lr": 1.2319924896458973e-06, "epoch": 18.194247996228196, "percentage": 90.97, "elapsed_time": "2:19:45", "remaining_time": "0:13:52", "throughput": 4628.94, "total_tokens": 38813696} {"current_steps": 38595, "total_steps": 42420, "loss": 0.1087, "lr": 1.2288053273133426e-06, "epoch": 18.196605374823196, "percentage": 90.98, "elapsed_time": "2:19:46", "remaining_time": "0:13:51", "throughput": 4629.0, "total_tokens": 38819776} {"current_steps": 38600, "total_steps": 42420, "loss": 0.0214, "lr": 1.2256221890404374e-06, "epoch": 18.1989627534182, "percentage": 90.99, "elapsed_time": "2:19:47", "remaining_time": "0:13:50", "throughput": 4629.03, "total_tokens": 38825152} {"current_steps": 38605, "total_steps": 42420, "loss": 0.0234, "lr": 1.2224430753660282e-06, "epoch": 18.2013201320132, "percentage": 91.01, "elapsed_time": "2:19:48", "remaining_time": "0:13:48", "throughput": 4629.04, "total_tokens": 38829760} {"current_steps": 38610, "total_steps": 42420, "loss": 0.0265, "lr": 1.2192679868282848e-06, "epoch": 18.203677510608205, "percentage": 91.02, "elapsed_time": "2:19:49", "remaining_time": "0:13:47", "throughput": 4629.07, "total_tokens": 38834528} {"current_steps": 38615, "total_steps": 42420, "loss": 0.1471, "lr": 1.216096923964699e-06, "epoch": 18.206034889203206, "percentage": 91.03, "elapsed_time": "2:19:50", "remaining_time": "0:13:46", "throughput": 4629.09, "total_tokens": 38839296} {"current_steps": 38620, "total_steps": 42420, "loss": 0.1467, "lr": 1.2129298873120753e-06, "epoch": 18.208392267798207, "percentage": 91.04, "elapsed_time": "2:19:51", "remaining_time": "0:13:45", "throughput": 4629.12, "total_tokens": 38844192} {"current_steps": 38625, "total_steps": 42420, "loss": 0.2066, "lr": 1.2097668774065458e-06, "epoch": 18.21074964639321, "percentage": 91.05, "elapsed_time": "2:19:52", "remaining_time": "0:13:44", "throughput": 4629.14, "total_tokens": 38849440} {"current_steps": 38630, "total_steps": 42420, "loss": 0.0273, "lr": 1.206607894783543e-06, "epoch": 18.21310702498821, "percentage": 91.07, "elapsed_time": "2:19:53", "remaining_time": "0:13:43", "throughput": 4629.17, "total_tokens": 38854432} {"current_steps": 38635, "total_steps": 42420, "loss": 0.1022, "lr": 1.2034529399778365e-06, "epoch": 18.215464403583216, "percentage": 91.08, "elapsed_time": "2:19:54", "remaining_time": "0:13:42", "throughput": 4629.19, "total_tokens": 38859744} {"current_steps": 38640, "total_steps": 42420, "loss": 0.0428, "lr": 1.2003020135235021e-06, "epoch": 18.217821782178216, "percentage": 91.09, "elapsed_time": "2:19:55", "remaining_time": "0:13:41", "throughput": 4629.22, "total_tokens": 38864672} {"current_steps": 38645, "total_steps": 42420, "loss": 0.0976, "lr": 1.1971551159539434e-06, "epoch": 18.22017916077322, "percentage": 91.1, "elapsed_time": "2:19:56", "remaining_time": "0:13:40", "throughput": 4629.25, "total_tokens": 38869760} {"current_steps": 38650, "total_steps": 42420, "loss": 0.1109, "lr": 1.1940122478018734e-06, "epoch": 18.22253653936822, "percentage": 91.11, "elapsed_time": "2:19:57", "remaining_time": "0:13:39", "throughput": 4629.27, "total_tokens": 38874592} {"current_steps": 38655, "total_steps": 42420, "loss": 0.1565, "lr": 1.1908734095993274e-06, "epoch": 18.224893917963225, "percentage": 91.12, "elapsed_time": "2:19:58", "remaining_time": "0:13:38", "throughput": 4629.28, "total_tokens": 38879008} {"current_steps": 38660, "total_steps": 42420, "loss": 0.0397, "lr": 1.187738601877658e-06, "epoch": 18.227251296558226, "percentage": 91.14, "elapsed_time": "2:19:59", "remaining_time": "0:13:36", "throughput": 4629.31, "total_tokens": 38883680} {"current_steps": 38665, "total_steps": 42420, "loss": 0.1841, "lr": 1.1846078251675386e-06, "epoch": 18.22960867515323, "percentage": 91.15, "elapsed_time": "2:20:00", "remaining_time": "0:13:35", "throughput": 4629.34, "total_tokens": 38889280} {"current_steps": 38670, "total_steps": 42420, "loss": 0.0801, "lr": 1.1814810799989474e-06, "epoch": 18.23196605374823, "percentage": 91.16, "elapsed_time": "2:20:01", "remaining_time": "0:13:34", "throughput": 4629.38, "total_tokens": 38894464} {"current_steps": 38675, "total_steps": 42420, "loss": 0.2402, "lr": 1.1783583669011943e-06, "epoch": 18.234323432343235, "percentage": 91.17, "elapsed_time": "2:20:02", "remaining_time": "0:13:33", "throughput": 4629.41, "total_tokens": 38899520} {"current_steps": 38680, "total_steps": 42420, "loss": 0.1279, "lr": 1.1752396864029013e-06, "epoch": 18.236680810938235, "percentage": 91.18, "elapsed_time": "2:20:03", "remaining_time": "0:13:32", "throughput": 4629.45, "total_tokens": 38904896} {"current_steps": 38685, "total_steps": 42420, "loss": 0.1104, "lr": 1.172125039032007e-06, "epoch": 18.23903818953324, "percentage": 91.2, "elapsed_time": "2:20:04", "remaining_time": "0:13:31", "throughput": 4629.48, "total_tokens": 38910048} {"current_steps": 38690, "total_steps": 42420, "loss": 0.0703, "lr": 1.1690144253157704e-06, "epoch": 18.24139556812824, "percentage": 91.21, "elapsed_time": "2:20:05", "remaining_time": "0:13:30", "throughput": 4629.46, "total_tokens": 38913952} {"current_steps": 38695, "total_steps": 42420, "loss": 0.1583, "lr": 1.1659078457807644e-06, "epoch": 18.243752946723244, "percentage": 91.22, "elapsed_time": "2:20:07", "remaining_time": "0:13:29", "throughput": 4629.53, "total_tokens": 38921216} {"current_steps": 38700, "total_steps": 42420, "loss": 0.0849, "lr": 1.1628053009528766e-06, "epoch": 18.246110325318245, "percentage": 91.23, "elapsed_time": "2:20:08", "remaining_time": "0:13:28", "throughput": 4629.55, "total_tokens": 38925696} {"current_steps": 38705, "total_steps": 42420, "loss": 0.1707, "lr": 1.1597067913573234e-06, "epoch": 18.24846770391325, "percentage": 91.24, "elapsed_time": "2:20:09", "remaining_time": "0:13:27", "throughput": 4629.6, "total_tokens": 38932256} {"current_steps": 38710, "total_steps": 42420, "loss": 0.1796, "lr": 1.1566123175186238e-06, "epoch": 18.25082508250825, "percentage": 91.25, "elapsed_time": "2:20:10", "remaining_time": "0:13:26", "throughput": 4629.62, "total_tokens": 38937248} {"current_steps": 38715, "total_steps": 42420, "loss": 0.0563, "lr": 1.153521879960623e-06, "epoch": 18.253182461103254, "percentage": 91.27, "elapsed_time": "2:20:11", "remaining_time": "0:13:24", "throughput": 4629.66, "total_tokens": 38942720} {"current_steps": 38720, "total_steps": 42420, "loss": 0.1747, "lr": 1.150435479206477e-06, "epoch": 18.255539839698255, "percentage": 91.28, "elapsed_time": "2:20:13", "remaining_time": "0:13:23", "throughput": 4629.73, "total_tokens": 38952256} {"current_steps": 38725, "total_steps": 42420, "loss": 0.1345, "lr": 1.14735311577866e-06, "epoch": 18.25789721829326, "percentage": 91.29, "elapsed_time": "2:20:14", "remaining_time": "0:13:22", "throughput": 4629.75, "total_tokens": 38956640} {"current_steps": 38730, "total_steps": 42420, "loss": 0.1631, "lr": 1.1442747901989653e-06, "epoch": 18.26025459688826, "percentage": 91.3, "elapsed_time": "2:20:15", "remaining_time": "0:13:21", "throughput": 4629.77, "total_tokens": 38961088} {"current_steps": 38735, "total_steps": 42420, "loss": 0.095, "lr": 1.1412005029885015e-06, "epoch": 18.262611975483264, "percentage": 91.31, "elapsed_time": "2:20:16", "remaining_time": "0:13:20", "throughput": 4629.78, "total_tokens": 38965952} {"current_steps": 38740, "total_steps": 42420, "loss": 0.1468, "lr": 1.1381302546676936e-06, "epoch": 18.264969354078264, "percentage": 91.32, "elapsed_time": "2:20:17", "remaining_time": "0:13:19", "throughput": 4629.79, "total_tokens": 38970528} {"current_steps": 38745, "total_steps": 42420, "loss": 0.2125, "lr": 1.1350640457562844e-06, "epoch": 18.26732673267327, "percentage": 91.34, "elapsed_time": "2:20:18", "remaining_time": "0:13:18", "throughput": 4629.8, "total_tokens": 38974784} {"current_steps": 38750, "total_steps": 42420, "loss": 0.0359, "lr": 1.1320018767733254e-06, "epoch": 18.26968411126827, "percentage": 91.35, "elapsed_time": "2:20:19", "remaining_time": "0:13:17", "throughput": 4629.77, "total_tokens": 38978912} {"current_steps": 38755, "total_steps": 42420, "loss": 0.0374, "lr": 1.1289437482371989e-06, "epoch": 18.272041489863273, "percentage": 91.36, "elapsed_time": "2:20:20", "remaining_time": "0:13:16", "throughput": 4629.79, "total_tokens": 38983808} {"current_steps": 38760, "total_steps": 42420, "loss": 0.1974, "lr": 1.1258896606655827e-06, "epoch": 18.274398868458274, "percentage": 91.37, "elapsed_time": "2:20:21", "remaining_time": "0:13:15", "throughput": 4629.79, "total_tokens": 38988544} {"current_steps": 38765, "total_steps": 42420, "loss": 0.1034, "lr": 1.1228396145754882e-06, "epoch": 18.276756247053278, "percentage": 91.38, "elapsed_time": "2:20:22", "remaining_time": "0:13:14", "throughput": 4629.81, "total_tokens": 38993696} {"current_steps": 38770, "total_steps": 42420, "loss": 0.1283, "lr": 1.1197936104832384e-06, "epoch": 18.27911362564828, "percentage": 91.4, "elapsed_time": "2:20:23", "remaining_time": "0:13:13", "throughput": 4629.8, "total_tokens": 38998240} {"current_steps": 38775, "total_steps": 42420, "loss": 0.1337, "lr": 1.1167516489044656e-06, "epoch": 18.281471004243283, "percentage": 91.41, "elapsed_time": "2:20:24", "remaining_time": "0:13:11", "throughput": 4629.84, "total_tokens": 39004416} {"current_steps": 38780, "total_steps": 42420, "loss": 0.0329, "lr": 1.113713730354124e-06, "epoch": 18.283828382838283, "percentage": 91.42, "elapsed_time": "2:20:25", "remaining_time": "0:13:10", "throughput": 4629.86, "total_tokens": 39009440} {"current_steps": 38785, "total_steps": 42420, "loss": 0.1089, "lr": 1.1106798553464804e-06, "epoch": 18.286185761433288, "percentage": 91.43, "elapsed_time": "2:20:26", "remaining_time": "0:13:09", "throughput": 4629.86, "total_tokens": 39014016} {"current_steps": 38790, "total_steps": 42420, "loss": 0.0405, "lr": 1.107650024395121e-06, "epoch": 18.28854314002829, "percentage": 91.44, "elapsed_time": "2:20:27", "remaining_time": "0:13:08", "throughput": 4629.89, "total_tokens": 39018944} {"current_steps": 38795, "total_steps": 42420, "loss": 0.1871, "lr": 1.1046242380129495e-06, "epoch": 18.290900518623292, "percentage": 91.45, "elapsed_time": "2:20:28", "remaining_time": "0:13:07", "throughput": 4629.92, "total_tokens": 39024480} {"current_steps": 38800, "total_steps": 42420, "loss": 0.3587, "lr": 1.1016024967121674e-06, "epoch": 18.293257897218293, "percentage": 91.47, "elapsed_time": "2:20:29", "remaining_time": "0:13:06", "throughput": 4629.95, "total_tokens": 39029536} {"current_steps": 38805, "total_steps": 42420, "loss": 0.0605, "lr": 1.0985848010043126e-06, "epoch": 18.295615275813297, "percentage": 91.48, "elapsed_time": "2:20:30", "remaining_time": "0:13:05", "throughput": 4629.98, "total_tokens": 39034400} {"current_steps": 38810, "total_steps": 42420, "loss": 0.2949, "lr": 1.0955711514002265e-06, "epoch": 18.297972654408298, "percentage": 91.49, "elapsed_time": "2:20:31", "remaining_time": "0:13:04", "throughput": 4630.01, "total_tokens": 39039616} {"current_steps": 38815, "total_steps": 42420, "loss": 0.1915, "lr": 1.0925615484100704e-06, "epoch": 18.300330033003302, "percentage": 91.5, "elapsed_time": "2:20:32", "remaining_time": "0:13:03", "throughput": 4630.03, "total_tokens": 39044384} {"current_steps": 38820, "total_steps": 42420, "loss": 0.0663, "lr": 1.0895559925433201e-06, "epoch": 18.302687411598303, "percentage": 91.51, "elapsed_time": "2:20:33", "remaining_time": "0:13:02", "throughput": 4630.06, "total_tokens": 39049824} {"current_steps": 38825, "total_steps": 42420, "loss": 0.0252, "lr": 1.0865544843087634e-06, "epoch": 18.305044790193303, "percentage": 91.53, "elapsed_time": "2:20:34", "remaining_time": "0:13:01", "throughput": 4630.06, "total_tokens": 39054240} {"current_steps": 38830, "total_steps": 42420, "loss": 0.1493, "lr": 1.0835570242145071e-06, "epoch": 18.307402168788308, "percentage": 91.54, "elapsed_time": "2:20:35", "remaining_time": "0:12:59", "throughput": 4630.09, "total_tokens": 39059168} {"current_steps": 38835, "total_steps": 42420, "loss": 0.0618, "lr": 1.080563612767971e-06, "epoch": 18.309759547383308, "percentage": 91.55, "elapsed_time": "2:20:36", "remaining_time": "0:12:58", "throughput": 4630.09, "total_tokens": 39063296} {"current_steps": 38840, "total_steps": 42420, "loss": 0.0932, "lr": 1.0775742504758795e-06, "epoch": 18.312116925978312, "percentage": 91.56, "elapsed_time": "2:20:37", "remaining_time": "0:12:57", "throughput": 4630.11, "total_tokens": 39067968} {"current_steps": 38845, "total_steps": 42420, "loss": 0.0968, "lr": 1.0745889378442924e-06, "epoch": 18.314474304573313, "percentage": 91.57, "elapsed_time": "2:20:38", "remaining_time": "0:12:56", "throughput": 4630.11, "total_tokens": 39072480} {"current_steps": 38850, "total_steps": 42420, "loss": 0.0499, "lr": 1.0716076753785664e-06, "epoch": 18.316831683168317, "percentage": 91.58, "elapsed_time": "2:20:39", "remaining_time": "0:12:55", "throughput": 4630.15, "total_tokens": 39077696} {"current_steps": 38855, "total_steps": 42420, "loss": 0.0247, "lr": 1.0686304635833782e-06, "epoch": 18.319189061763318, "percentage": 91.6, "elapsed_time": "2:20:40", "remaining_time": "0:12:54", "throughput": 4630.16, "total_tokens": 39082048} {"current_steps": 38860, "total_steps": 42420, "loss": 0.1426, "lr": 1.0656573029627221e-06, "epoch": 18.321546440358322, "percentage": 91.61, "elapsed_time": "2:20:41", "remaining_time": "0:12:53", "throughput": 4630.19, "total_tokens": 39087392} {"current_steps": 38865, "total_steps": 42420, "loss": 0.093, "lr": 1.0626881940199035e-06, "epoch": 18.323903818953323, "percentage": 91.62, "elapsed_time": "2:20:42", "remaining_time": "0:12:52", "throughput": 4630.21, "total_tokens": 39091552} {"current_steps": 38870, "total_steps": 42420, "loss": 0.12, "lr": 1.0597231372575401e-06, "epoch": 18.326261197548327, "percentage": 91.63, "elapsed_time": "2:20:43", "remaining_time": "0:12:51", "throughput": 4630.24, "total_tokens": 39096448} {"current_steps": 38875, "total_steps": 42420, "loss": 0.1747, "lr": 1.0567621331775717e-06, "epoch": 18.328618576143327, "percentage": 91.64, "elapsed_time": "2:20:44", "remaining_time": "0:12:50", "throughput": 4630.23, "total_tokens": 39100480} {"current_steps": 38880, "total_steps": 42420, "loss": 0.1812, "lr": 1.0538051822812367e-06, "epoch": 18.33097595473833, "percentage": 91.65, "elapsed_time": "2:20:45", "remaining_time": "0:12:48", "throughput": 4630.26, "total_tokens": 39105664} {"current_steps": 38885, "total_steps": 42420, "loss": 0.0949, "lr": 1.0508522850691012e-06, "epoch": 18.333333333333332, "percentage": 91.67, "elapsed_time": "2:20:46", "remaining_time": "0:12:47", "throughput": 4630.3, "total_tokens": 39111104} {"current_steps": 38890, "total_steps": 42420, "loss": 0.0876, "lr": 1.0479034420410427e-06, "epoch": 18.335690711928336, "percentage": 91.68, "elapsed_time": "2:20:47", "remaining_time": "0:12:46", "throughput": 4630.3, "total_tokens": 39115680} {"current_steps": 38895, "total_steps": 42420, "loss": 0.1097, "lr": 1.0449586536962458e-06, "epoch": 18.338048090523337, "percentage": 91.69, "elapsed_time": "2:20:48", "remaining_time": "0:12:45", "throughput": 4630.33, "total_tokens": 39120992} {"current_steps": 38900, "total_steps": 42420, "loss": 0.1196, "lr": 1.0420179205332142e-06, "epoch": 18.34040546911834, "percentage": 91.7, "elapsed_time": "2:20:50", "remaining_time": "0:12:44", "throughput": 4630.37, "total_tokens": 39127104} {"current_steps": 38905, "total_steps": 42420, "loss": 0.0424, "lr": 1.0390812430497665e-06, "epoch": 18.34276284771334, "percentage": 91.71, "elapsed_time": "2:20:51", "remaining_time": "0:12:43", "throughput": 4630.39, "total_tokens": 39132256} {"current_steps": 38910, "total_steps": 42420, "loss": 0.0496, "lr": 1.0361486217430328e-06, "epoch": 18.345120226308346, "percentage": 91.73, "elapsed_time": "2:20:52", "remaining_time": "0:12:42", "throughput": 4630.4, "total_tokens": 39137504} {"current_steps": 38915, "total_steps": 42420, "loss": 0.1184, "lr": 1.0332200571094518e-06, "epoch": 18.347477604903347, "percentage": 91.74, "elapsed_time": "2:20:53", "remaining_time": "0:12:41", "throughput": 4630.41, "total_tokens": 39142368} {"current_steps": 38920, "total_steps": 42420, "loss": 0.1596, "lr": 1.030295549644783e-06, "epoch": 18.34983498349835, "percentage": 91.75, "elapsed_time": "2:20:54", "remaining_time": "0:12:40", "throughput": 4630.44, "total_tokens": 39147072} {"current_steps": 38925, "total_steps": 42420, "loss": 0.2228, "lr": 1.0273750998440996e-06, "epoch": 18.35219236209335, "percentage": 91.76, "elapsed_time": "2:20:55", "remaining_time": "0:12:39", "throughput": 4630.46, "total_tokens": 39151680} {"current_steps": 38930, "total_steps": 42420, "loss": 0.0987, "lr": 1.0244587082017753e-06, "epoch": 18.354549740688356, "percentage": 91.77, "elapsed_time": "2:20:56", "remaining_time": "0:12:38", "throughput": 4630.48, "total_tokens": 39156032} {"current_steps": 38935, "total_steps": 42420, "loss": 0.1703, "lr": 1.0215463752115101e-06, "epoch": 18.356907119283356, "percentage": 91.78, "elapsed_time": "2:20:57", "remaining_time": "0:12:37", "throughput": 4630.52, "total_tokens": 39162912} {"current_steps": 38940, "total_steps": 42420, "loss": 0.1928, "lr": 1.018638101366312e-06, "epoch": 18.35926449787836, "percentage": 91.8, "elapsed_time": "2:20:58", "remaining_time": "0:12:35", "throughput": 4630.55, "total_tokens": 39168512} {"current_steps": 38945, "total_steps": 42420, "loss": 0.0606, "lr": 1.0157338871585043e-06, "epoch": 18.36162187647336, "percentage": 91.81, "elapsed_time": "2:20:59", "remaining_time": "0:12:34", "throughput": 4630.58, "total_tokens": 39173696} {"current_steps": 38950, "total_steps": 42420, "loss": 0.0343, "lr": 1.0128337330797182e-06, "epoch": 18.363979255068365, "percentage": 91.82, "elapsed_time": "2:21:00", "remaining_time": "0:12:33", "throughput": 4630.58, "total_tokens": 39177664} {"current_steps": 38955, "total_steps": 42420, "loss": 0.1743, "lr": 1.0099376396209032e-06, "epoch": 18.366336633663366, "percentage": 91.83, "elapsed_time": "2:21:01", "remaining_time": "0:12:32", "throughput": 4630.6, "total_tokens": 39182400} {"current_steps": 38960, "total_steps": 42420, "loss": 0.122, "lr": 1.0070456072723194e-06, "epoch": 18.36869401225837, "percentage": 91.84, "elapsed_time": "2:21:02", "remaining_time": "0:12:31", "throughput": 4630.6, "total_tokens": 39186976} {"current_steps": 38965, "total_steps": 42420, "loss": 0.0136, "lr": 1.0041576365235395e-06, "epoch": 18.37105139085337, "percentage": 91.86, "elapsed_time": "2:21:03", "remaining_time": "0:12:30", "throughput": 4630.59, "total_tokens": 39190976} {"current_steps": 38970, "total_steps": 42420, "loss": 0.0671, "lr": 1.0012737278634416e-06, "epoch": 18.373408769448375, "percentage": 91.87, "elapsed_time": "2:21:04", "remaining_time": "0:12:29", "throughput": 4630.66, "total_tokens": 39197504} {"current_steps": 38975, "total_steps": 42420, "loss": 0.0333, "lr": 9.983938817802268e-07, "epoch": 18.375766148043375, "percentage": 91.88, "elapsed_time": "2:21:05", "remaining_time": "0:12:28", "throughput": 4630.69, "total_tokens": 39203104} {"current_steps": 38980, "total_steps": 42420, "loss": 0.0674, "lr": 9.955180987614026e-07, "epoch": 18.37812352663838, "percentage": 91.89, "elapsed_time": "2:21:07", "remaining_time": "0:12:27", "throughput": 4630.75, "total_tokens": 39209472} {"current_steps": 38985, "total_steps": 42420, "loss": 0.0823, "lr": 9.926463792937907e-07, "epoch": 18.38048090523338, "percentage": 91.9, "elapsed_time": "2:21:08", "remaining_time": "0:12:26", "throughput": 4630.77, "total_tokens": 39214464} {"current_steps": 38990, "total_steps": 42420, "loss": 0.0696, "lr": 9.89778723863527e-07, "epoch": 18.382838283828384, "percentage": 91.91, "elapsed_time": "2:21:09", "remaining_time": "0:12:25", "throughput": 4630.79, "total_tokens": 39219200} {"current_steps": 38995, "total_steps": 42420, "loss": 0.168, "lr": 9.869151329560565e-07, "epoch": 18.385195662423385, "percentage": 91.93, "elapsed_time": "2:21:10", "remaining_time": "0:12:23", "throughput": 4630.77, "total_tokens": 39222912} {"current_steps": 39000, "total_steps": 42420, "loss": 0.0822, "lr": 9.840556070561335e-07, "epoch": 18.38755304101839, "percentage": 91.94, "elapsed_time": "2:21:11", "remaining_time": "0:12:22", "throughput": 4630.8, "total_tokens": 39228064} {"current_steps": 39005, "total_steps": 42420, "loss": 0.1048, "lr": 9.812001466478315e-07, "epoch": 18.38991041961339, "percentage": 91.95, "elapsed_time": "2:21:12", "remaining_time": "0:12:21", "throughput": 4630.85, "total_tokens": 39233792} {"current_steps": 39010, "total_steps": 42420, "loss": 0.0651, "lr": 9.783487522145251e-07, "epoch": 18.392267798208394, "percentage": 91.96, "elapsed_time": "2:21:13", "remaining_time": "0:12:20", "throughput": 4630.83, "total_tokens": 39237568} {"current_steps": 39015, "total_steps": 42420, "loss": 0.2261, "lr": 9.755014242389115e-07, "epoch": 18.394625176803395, "percentage": 91.97, "elapsed_time": "2:21:14", "remaining_time": "0:12:19", "throughput": 4630.83, "total_tokens": 39241952} {"current_steps": 39020, "total_steps": 42420, "loss": 0.2001, "lr": 9.726581632029912e-07, "epoch": 18.396982555398395, "percentage": 91.98, "elapsed_time": "2:21:15", "remaining_time": "0:12:18", "throughput": 4630.8, "total_tokens": 39246240} {"current_steps": 39025, "total_steps": 42420, "loss": 0.0363, "lr": 9.69818969588085e-07, "epoch": 18.3993399339934, "percentage": 92.0, "elapsed_time": "2:21:16", "remaining_time": "0:12:17", "throughput": 4630.81, "total_tokens": 39250848} {"current_steps": 39030, "total_steps": 42420, "loss": 0.184, "lr": 9.669838438748192e-07, "epoch": 18.4016973125884, "percentage": 92.01, "elapsed_time": "2:21:17", "remaining_time": "0:12:16", "throughput": 4630.85, "total_tokens": 39256832} {"current_steps": 39035, "total_steps": 42420, "loss": 0.0449, "lr": 9.641527865431294e-07, "epoch": 18.404054691183404, "percentage": 92.02, "elapsed_time": "2:21:18", "remaining_time": "0:12:15", "throughput": 4630.88, "total_tokens": 39262304} {"current_steps": 39040, "total_steps": 42420, "loss": 0.1001, "lr": 9.613257980722684e-07, "epoch": 18.406412069778405, "percentage": 92.03, "elapsed_time": "2:21:19", "remaining_time": "0:12:14", "throughput": 4630.91, "total_tokens": 39267552} {"current_steps": 39045, "total_steps": 42420, "loss": 0.1903, "lr": 9.585028789408006e-07, "epoch": 18.40876944837341, "percentage": 92.04, "elapsed_time": "2:21:20", "remaining_time": "0:12:13", "throughput": 4630.94, "total_tokens": 39272832} {"current_steps": 39050, "total_steps": 42420, "loss": 0.1533, "lr": 9.556840296265884e-07, "epoch": 18.41112682696841, "percentage": 92.06, "elapsed_time": "2:21:21", "remaining_time": "0:12:11", "throughput": 4630.97, "total_tokens": 39277632} {"current_steps": 39055, "total_steps": 42420, "loss": 0.2269, "lr": 9.528692506068221e-07, "epoch": 18.413484205563414, "percentage": 92.07, "elapsed_time": "2:21:22", "remaining_time": "0:12:10", "throughput": 4631.01, "total_tokens": 39283488} {"current_steps": 39060, "total_steps": 42420, "loss": 0.1539, "lr": 9.500585423579955e-07, "epoch": 18.415841584158414, "percentage": 92.08, "elapsed_time": "2:21:23", "remaining_time": "0:12:09", "throughput": 4631.03, "total_tokens": 39288288} {"current_steps": 39065, "total_steps": 42420, "loss": 0.0909, "lr": 9.472519053559114e-07, "epoch": 18.41819896275342, "percentage": 92.09, "elapsed_time": "2:21:24", "remaining_time": "0:12:08", "throughput": 4631.07, "total_tokens": 39294432} {"current_steps": 39070, "total_steps": 42420, "loss": 0.0454, "lr": 9.444493400756871e-07, "epoch": 18.42055634134842, "percentage": 92.1, "elapsed_time": "2:21:26", "remaining_time": "0:12:07", "throughput": 4631.1, "total_tokens": 39299840} {"current_steps": 39075, "total_steps": 42420, "loss": 0.0338, "lr": 9.416508469917512e-07, "epoch": 18.422913719943423, "percentage": 92.11, "elapsed_time": "2:21:27", "remaining_time": "0:12:06", "throughput": 4631.08, "total_tokens": 39304480} {"current_steps": 39080, "total_steps": 42420, "loss": 0.0932, "lr": 9.38856426577836e-07, "epoch": 18.425271098538424, "percentage": 92.13, "elapsed_time": "2:21:27", "remaining_time": "0:12:05", "throughput": 4631.08, "total_tokens": 39308512} {"current_steps": 39085, "total_steps": 42420, "loss": 0.111, "lr": 9.360660793069992e-07, "epoch": 18.427628477133428, "percentage": 92.14, "elapsed_time": "2:21:28", "remaining_time": "0:12:04", "throughput": 4631.1, "total_tokens": 39313088} {"current_steps": 39090, "total_steps": 42420, "loss": 0.1805, "lr": 9.332798056515879e-07, "epoch": 18.42998585572843, "percentage": 92.15, "elapsed_time": "2:21:29", "remaining_time": "0:12:03", "throughput": 4631.13, "total_tokens": 39317888} {"current_steps": 39095, "total_steps": 42420, "loss": 0.4297, "lr": 9.304976060832777e-07, "epoch": 18.432343234323433, "percentage": 92.16, "elapsed_time": "2:21:30", "remaining_time": "0:12:02", "throughput": 4631.14, "total_tokens": 39322816} {"current_steps": 39100, "total_steps": 42420, "loss": 0.0357, "lr": 9.277194810730444e-07, "epoch": 18.434700612918434, "percentage": 92.17, "elapsed_time": "2:21:32", "remaining_time": "0:12:01", "throughput": 4631.17, "total_tokens": 39328032} {"current_steps": 39105, "total_steps": 42420, "loss": 0.0993, "lr": 9.249454310911787e-07, "epoch": 18.437057991513438, "percentage": 92.19, "elapsed_time": "2:21:32", "remaining_time": "0:11:59", "throughput": 4631.17, "total_tokens": 39332544} {"current_steps": 39110, "total_steps": 42420, "loss": 0.0679, "lr": 9.221754566072827e-07, "epoch": 18.43941537010844, "percentage": 92.2, "elapsed_time": "2:21:34", "remaining_time": "0:11:58", "throughput": 4631.2, "total_tokens": 39337600} {"current_steps": 39115, "total_steps": 42420, "loss": 0.0492, "lr": 9.194095580902645e-07, "epoch": 18.441772748703443, "percentage": 92.21, "elapsed_time": "2:21:35", "remaining_time": "0:11:57", "throughput": 4631.2, "total_tokens": 39342240} {"current_steps": 39120, "total_steps": 42420, "loss": 0.1008, "lr": 9.166477360083415e-07, "epoch": 18.444130127298443, "percentage": 92.22, "elapsed_time": "2:21:36", "remaining_time": "0:11:56", "throughput": 4631.24, "total_tokens": 39347872} {"current_steps": 39125, "total_steps": 42420, "loss": 0.0326, "lr": 9.138899908290421e-07, "epoch": 18.446487505893447, "percentage": 92.23, "elapsed_time": "2:21:37", "remaining_time": "0:11:55", "throughput": 4631.25, "total_tokens": 39352864} {"current_steps": 39130, "total_steps": 42420, "loss": 0.1891, "lr": 9.1113632301921e-07, "epoch": 18.448844884488448, "percentage": 92.24, "elapsed_time": "2:21:38", "remaining_time": "0:11:54", "throughput": 4631.23, "total_tokens": 39357152} {"current_steps": 39135, "total_steps": 42420, "loss": 0.0817, "lr": 9.083867330449969e-07, "epoch": 18.451202263083452, "percentage": 92.26, "elapsed_time": "2:21:39", "remaining_time": "0:11:53", "throughput": 4631.24, "total_tokens": 39362560} {"current_steps": 39140, "total_steps": 42420, "loss": 0.2691, "lr": 9.05641221371853e-07, "epoch": 18.453559641678453, "percentage": 92.27, "elapsed_time": "2:21:40", "remaining_time": "0:11:52", "throughput": 4631.26, "total_tokens": 39367296} {"current_steps": 39145, "total_steps": 42420, "loss": 0.113, "lr": 9.028997884645535e-07, "epoch": 18.455917020273457, "percentage": 92.28, "elapsed_time": "2:21:41", "remaining_time": "0:11:51", "throughput": 4631.28, "total_tokens": 39372576} {"current_steps": 39150, "total_steps": 42420, "loss": 0.1895, "lr": 9.001624347871717e-07, "epoch": 18.458274398868458, "percentage": 92.29, "elapsed_time": "2:21:42", "remaining_time": "0:11:50", "throughput": 4631.31, "total_tokens": 39378464} {"current_steps": 39155, "total_steps": 42420, "loss": 0.1012, "lr": 8.974291608030983e-07, "epoch": 18.460631777463462, "percentage": 92.3, "elapsed_time": "2:21:43", "remaining_time": "0:11:49", "throughput": 4631.32, "total_tokens": 39383392} {"current_steps": 39160, "total_steps": 42420, "loss": 0.1174, "lr": 8.946999669750294e-07, "epoch": 18.462989156058462, "percentage": 92.31, "elapsed_time": "2:21:44", "remaining_time": "0:11:47", "throughput": 4631.32, "total_tokens": 39387776} {"current_steps": 39165, "total_steps": 42420, "loss": 0.1123, "lr": 8.919748537649736e-07, "epoch": 18.465346534653467, "percentage": 92.33, "elapsed_time": "2:21:45", "remaining_time": "0:11:46", "throughput": 4631.34, "total_tokens": 39392480} {"current_steps": 39170, "total_steps": 42420, "loss": 0.1172, "lr": 8.892538216342422e-07, "epoch": 18.467703913248467, "percentage": 92.34, "elapsed_time": "2:21:46", "remaining_time": "0:11:45", "throughput": 4631.36, "total_tokens": 39397344} {"current_steps": 39175, "total_steps": 42420, "loss": 0.082, "lr": 8.86536871043464e-07, "epoch": 18.47006129184347, "percentage": 92.35, "elapsed_time": "2:21:47", "remaining_time": "0:11:44", "throughput": 4631.37, "total_tokens": 39401824} {"current_steps": 39180, "total_steps": 42420, "loss": 0.0195, "lr": 8.838240024525685e-07, "epoch": 18.472418670438472, "percentage": 92.36, "elapsed_time": "2:21:48", "remaining_time": "0:11:43", "throughput": 4631.37, "total_tokens": 39406560} {"current_steps": 39185, "total_steps": 42420, "loss": 0.0569, "lr": 8.811152163208019e-07, "epoch": 18.474776049033476, "percentage": 92.37, "elapsed_time": "2:21:49", "remaining_time": "0:11:42", "throughput": 4631.37, "total_tokens": 39410912} {"current_steps": 39190, "total_steps": 42420, "loss": 0.1619, "lr": 8.784105131067116e-07, "epoch": 18.477133427628477, "percentage": 92.39, "elapsed_time": "2:21:50", "remaining_time": "0:11:41", "throughput": 4631.37, "total_tokens": 39416096} {"current_steps": 39195, "total_steps": 42420, "loss": 0.1104, "lr": 8.75709893268159e-07, "epoch": 18.47949080622348, "percentage": 92.4, "elapsed_time": "2:21:51", "remaining_time": "0:11:40", "throughput": 4631.38, "total_tokens": 39421088} {"current_steps": 39200, "total_steps": 42420, "loss": 0.164, "lr": 8.730133572623172e-07, "epoch": 18.48184818481848, "percentage": 92.41, "elapsed_time": "2:21:52", "remaining_time": "0:11:39", "throughput": 4631.4, "total_tokens": 39426176} {"current_steps": 39205, "total_steps": 42420, "loss": 0.0605, "lr": 8.703209055456573e-07, "epoch": 18.484205563413486, "percentage": 92.42, "elapsed_time": "2:21:53", "remaining_time": "0:11:38", "throughput": 4631.42, "total_tokens": 39430848} {"current_steps": 39210, "total_steps": 42420, "loss": 0.1198, "lr": 8.676325385739731e-07, "epoch": 18.486562942008486, "percentage": 92.43, "elapsed_time": "2:21:54", "remaining_time": "0:11:37", "throughput": 4631.42, "total_tokens": 39435264} {"current_steps": 39215, "total_steps": 42420, "loss": 0.0414, "lr": 8.649482568023559e-07, "epoch": 18.48892032060349, "percentage": 92.44, "elapsed_time": "2:21:55", "remaining_time": "0:11:35", "throughput": 4631.44, "total_tokens": 39439904} {"current_steps": 39220, "total_steps": 42420, "loss": 0.0941, "lr": 8.622680606852091e-07, "epoch": 18.49127769919849, "percentage": 92.46, "elapsed_time": "2:21:56", "remaining_time": "0:11:34", "throughput": 4631.48, "total_tokens": 39445984} {"current_steps": 39225, "total_steps": 42420, "loss": 0.1217, "lr": 8.595919506762418e-07, "epoch": 18.493635077793492, "percentage": 92.47, "elapsed_time": "2:21:58", "remaining_time": "0:11:33", "throughput": 4631.52, "total_tokens": 39451360} {"current_steps": 39230, "total_steps": 42420, "loss": 0.0621, "lr": 8.569199272284778e-07, "epoch": 18.495992456388496, "percentage": 92.48, "elapsed_time": "2:21:59", "remaining_time": "0:11:32", "throughput": 4631.55, "total_tokens": 39456256} {"current_steps": 39235, "total_steps": 42420, "loss": 0.0504, "lr": 8.542519907942442e-07, "epoch": 18.498349834983497, "percentage": 92.49, "elapsed_time": "2:22:00", "remaining_time": "0:11:31", "throughput": 4631.58, "total_tokens": 39461472} {"current_steps": 39240, "total_steps": 42420, "loss": 0.1038, "lr": 8.51588141825177e-07, "epoch": 18.5007072135785, "percentage": 92.5, "elapsed_time": "2:22:01", "remaining_time": "0:11:30", "throughput": 4631.61, "total_tokens": 39466784} {"current_steps": 39245, "total_steps": 42420, "loss": 0.078, "lr": 8.489283807722182e-07, "epoch": 18.5030645921735, "percentage": 92.52, "elapsed_time": "2:22:02", "remaining_time": "0:11:29", "throughput": 4631.68, "total_tokens": 39474560} {"current_steps": 39250, "total_steps": 42420, "loss": 0.049, "lr": 8.462727080856242e-07, "epoch": 18.505421970768506, "percentage": 92.53, "elapsed_time": "2:22:03", "remaining_time": "0:11:28", "throughput": 4631.7, "total_tokens": 39480032} {"current_steps": 39255, "total_steps": 42420, "loss": 0.1415, "lr": 8.436211242149577e-07, "epoch": 18.507779349363506, "percentage": 92.54, "elapsed_time": "2:22:04", "remaining_time": "0:11:27", "throughput": 4631.73, "total_tokens": 39485088} {"current_steps": 39260, "total_steps": 42420, "loss": 0.0926, "lr": 8.409736296090792e-07, "epoch": 18.51013672795851, "percentage": 92.55, "elapsed_time": "2:22:06", "remaining_time": "0:11:26", "throughput": 4631.77, "total_tokens": 39490784} {"current_steps": 39265, "total_steps": 42420, "loss": 0.1875, "lr": 8.383302247161689e-07, "epoch": 18.51249410655351, "percentage": 92.56, "elapsed_time": "2:22:07", "remaining_time": "0:11:25", "throughput": 4631.79, "total_tokens": 39495488} {"current_steps": 39270, "total_steps": 42420, "loss": 0.2041, "lr": 8.356909099837107e-07, "epoch": 18.514851485148515, "percentage": 92.57, "elapsed_time": "2:22:08", "remaining_time": "0:11:24", "throughput": 4631.82, "total_tokens": 39500512} {"current_steps": 39275, "total_steps": 42420, "loss": 0.0673, "lr": 8.330556858584915e-07, "epoch": 18.517208863743516, "percentage": 92.59, "elapsed_time": "2:22:08", "remaining_time": "0:11:22", "throughput": 4631.77, "total_tokens": 39503840} {"current_steps": 39280, "total_steps": 42420, "loss": 0.0269, "lr": 8.304245527866156e-07, "epoch": 18.51956624233852, "percentage": 92.6, "elapsed_time": "2:22:09", "remaining_time": "0:11:21", "throughput": 4631.78, "total_tokens": 39508608} {"current_steps": 39285, "total_steps": 42420, "loss": 0.3023, "lr": 8.277975112134878e-07, "epoch": 18.52192362093352, "percentage": 92.61, "elapsed_time": "2:22:10", "remaining_time": "0:11:20", "throughput": 4631.77, "total_tokens": 39512928} {"current_steps": 39290, "total_steps": 42420, "loss": 0.1166, "lr": 8.251745615838192e-07, "epoch": 18.524280999528525, "percentage": 92.62, "elapsed_time": "2:22:11", "remaining_time": "0:11:19", "throughput": 4631.78, "total_tokens": 39517344} {"current_steps": 39295, "total_steps": 42420, "loss": 0.2468, "lr": 8.225557043416349e-07, "epoch": 18.526638378123526, "percentage": 92.63, "elapsed_time": "2:22:12", "remaining_time": "0:11:18", "throughput": 4631.8, "total_tokens": 39522656} {"current_steps": 39300, "total_steps": 42420, "loss": 0.1155, "lr": 8.199409399302582e-07, "epoch": 18.52899575671853, "percentage": 92.64, "elapsed_time": "2:22:13", "remaining_time": "0:11:17", "throughput": 4631.81, "total_tokens": 39527488} {"current_steps": 39305, "total_steps": 42420, "loss": 0.1965, "lr": 8.17330268792324e-07, "epoch": 18.53135313531353, "percentage": 92.66, "elapsed_time": "2:22:14", "remaining_time": "0:11:16", "throughput": 4631.81, "total_tokens": 39531456} {"current_steps": 39310, "total_steps": 42420, "loss": 0.043, "lr": 8.147236913697787e-07, "epoch": 18.533710513908535, "percentage": 92.67, "elapsed_time": "2:22:15", "remaining_time": "0:11:15", "throughput": 4631.83, "total_tokens": 39535968} {"current_steps": 39315, "total_steps": 42420, "loss": 0.0509, "lr": 8.121212081038721e-07, "epoch": 18.536067892503535, "percentage": 92.68, "elapsed_time": "2:22:16", "remaining_time": "0:11:14", "throughput": 4631.87, "total_tokens": 39541376} {"current_steps": 39320, "total_steps": 42420, "loss": 0.1655, "lr": 8.095228194351545e-07, "epoch": 18.53842527109854, "percentage": 92.69, "elapsed_time": "2:22:17", "remaining_time": "0:11:13", "throughput": 4631.91, "total_tokens": 39546368} {"current_steps": 39325, "total_steps": 42420, "loss": 0.0174, "lr": 8.069285258034936e-07, "epoch": 18.54078264969354, "percentage": 92.7, "elapsed_time": "2:22:18", "remaining_time": "0:11:12", "throughput": 4631.93, "total_tokens": 39551200} {"current_steps": 39330, "total_steps": 42420, "loss": 0.1291, "lr": 8.043383276480603e-07, "epoch": 18.543140028288544, "percentage": 92.72, "elapsed_time": "2:22:19", "remaining_time": "0:11:10", "throughput": 4631.96, "total_tokens": 39556736} {"current_steps": 39335, "total_steps": 42420, "loss": 0.1175, "lr": 8.017522254073289e-07, "epoch": 18.545497406883545, "percentage": 92.73, "elapsed_time": "2:22:21", "remaining_time": "0:11:09", "throughput": 4631.96, "total_tokens": 39561856} {"current_steps": 39340, "total_steps": 42420, "loss": 0.1836, "lr": 7.991702195190854e-07, "epoch": 18.54785478547855, "percentage": 92.74, "elapsed_time": "2:22:22", "remaining_time": "0:11:08", "throughput": 4631.98, "total_tokens": 39566816} {"current_steps": 39345, "total_steps": 42420, "loss": 0.1644, "lr": 7.965923104204131e-07, "epoch": 18.55021216407355, "percentage": 92.75, "elapsed_time": "2:22:23", "remaining_time": "0:11:07", "throughput": 4632.0, "total_tokens": 39571808} {"current_steps": 39350, "total_steps": 42420, "loss": 0.0728, "lr": 7.940184985477133e-07, "epoch": 18.552569542668554, "percentage": 92.76, "elapsed_time": "2:22:24", "remaining_time": "0:11:06", "throughput": 4632.02, "total_tokens": 39576544} {"current_steps": 39355, "total_steps": 42420, "loss": 0.0288, "lr": 7.914487843366874e-07, "epoch": 18.554926921263554, "percentage": 92.77, "elapsed_time": "2:22:25", "remaining_time": "0:11:05", "throughput": 4632.02, "total_tokens": 39580864} {"current_steps": 39360, "total_steps": 42420, "loss": 0.0355, "lr": 7.88883168222343e-07, "epoch": 18.55728429985856, "percentage": 92.79, "elapsed_time": "2:22:26", "remaining_time": "0:11:04", "throughput": 4632.05, "total_tokens": 39585824} {"current_steps": 39365, "total_steps": 42420, "loss": 0.1453, "lr": 7.863216506389964e-07, "epoch": 18.55964167845356, "percentage": 92.8, "elapsed_time": "2:22:27", "remaining_time": "0:11:03", "throughput": 4632.06, "total_tokens": 39591072} {"current_steps": 39370, "total_steps": 42420, "loss": 0.1876, "lr": 7.837642320202732e-07, "epoch": 18.561999057048563, "percentage": 92.81, "elapsed_time": "2:22:28", "remaining_time": "0:11:02", "throughput": 4632.06, "total_tokens": 39595616} {"current_steps": 39375, "total_steps": 42420, "loss": 0.188, "lr": 7.812109127990935e-07, "epoch": 18.564356435643564, "percentage": 92.82, "elapsed_time": "2:22:29", "remaining_time": "0:11:01", "throughput": 4632.08, "total_tokens": 39600608} {"current_steps": 39380, "total_steps": 42420, "loss": 0.1367, "lr": 7.786616934076979e-07, "epoch": 18.566713814238568, "percentage": 92.83, "elapsed_time": "2:22:30", "remaining_time": "0:11:00", "throughput": 4632.08, "total_tokens": 39604832} {"current_steps": 39385, "total_steps": 42420, "loss": 0.2744, "lr": 7.761165742776217e-07, "epoch": 18.56907119283357, "percentage": 92.85, "elapsed_time": "2:22:31", "remaining_time": "0:10:58", "throughput": 4632.08, "total_tokens": 39610144} {"current_steps": 39390, "total_steps": 42420, "loss": 0.1263, "lr": 7.73575555839709e-07, "epoch": 18.571428571428573, "percentage": 92.86, "elapsed_time": "2:22:32", "remaining_time": "0:10:57", "throughput": 4632.09, "total_tokens": 39615168} {"current_steps": 39395, "total_steps": 42420, "loss": 0.1583, "lr": 7.710386385241158e-07, "epoch": 18.573785950023574, "percentage": 92.87, "elapsed_time": "2:22:33", "remaining_time": "0:10:56", "throughput": 4632.09, "total_tokens": 39619392} {"current_steps": 39400, "total_steps": 42420, "loss": 0.0661, "lr": 7.685058227602959e-07, "epoch": 18.576143328618578, "percentage": 92.88, "elapsed_time": "2:22:34", "remaining_time": "0:10:55", "throughput": 4632.1, "total_tokens": 39623392} {"current_steps": 39405, "total_steps": 42420, "loss": 0.1325, "lr": 7.659771089770118e-07, "epoch": 18.57850070721358, "percentage": 92.89, "elapsed_time": "2:22:35", "remaining_time": "0:10:54", "throughput": 4632.08, "total_tokens": 39627456} {"current_steps": 39410, "total_steps": 42420, "loss": 0.1456, "lr": 7.634524976023349e-07, "epoch": 18.580858085808583, "percentage": 92.9, "elapsed_time": "2:22:35", "remaining_time": "0:10:53", "throughput": 4632.09, "total_tokens": 39632096} {"current_steps": 39415, "total_steps": 42420, "loss": 0.1843, "lr": 7.609319890636346e-07, "epoch": 18.583215464403583, "percentage": 92.92, "elapsed_time": "2:22:37", "remaining_time": "0:10:52", "throughput": 4632.12, "total_tokens": 39637632} {"current_steps": 39420, "total_steps": 42420, "loss": 0.1558, "lr": 7.584155837875973e-07, "epoch": 18.585572842998587, "percentage": 92.93, "elapsed_time": "2:22:38", "remaining_time": "0:10:51", "throughput": 4632.14, "total_tokens": 39642432} {"current_steps": 39425, "total_steps": 42420, "loss": 0.0229, "lr": 7.559032822001988e-07, "epoch": 18.587930221593588, "percentage": 92.94, "elapsed_time": "2:22:39", "remaining_time": "0:10:50", "throughput": 4632.16, "total_tokens": 39647808} {"current_steps": 39430, "total_steps": 42420, "loss": 0.1226, "lr": 7.533950847267351e-07, "epoch": 18.59028760018859, "percentage": 92.95, "elapsed_time": "2:22:40", "remaining_time": "0:10:49", "throughput": 4632.19, "total_tokens": 39652864} {"current_steps": 39435, "total_steps": 42420, "loss": 0.0955, "lr": 7.508909917917972e-07, "epoch": 18.592644978783593, "percentage": 92.96, "elapsed_time": "2:22:41", "remaining_time": "0:10:48", "throughput": 4632.22, "total_tokens": 39658560} {"current_steps": 39440, "total_steps": 42420, "loss": 0.0357, "lr": 7.483910038192904e-07, "epoch": 18.595002357378593, "percentage": 92.98, "elapsed_time": "2:22:42", "remaining_time": "0:10:46", "throughput": 4632.24, "total_tokens": 39663168} {"current_steps": 39445, "total_steps": 42420, "loss": 0.1306, "lr": 7.458951212324178e-07, "epoch": 18.597359735973598, "percentage": 92.99, "elapsed_time": "2:22:43", "remaining_time": "0:10:45", "throughput": 4632.25, "total_tokens": 39667712} {"current_steps": 39450, "total_steps": 42420, "loss": 0.1479, "lr": 7.434033444536886e-07, "epoch": 18.599717114568598, "percentage": 93.0, "elapsed_time": "2:22:44", "remaining_time": "0:10:44", "throughput": 4632.27, "total_tokens": 39672256} {"current_steps": 39455, "total_steps": 42420, "loss": 0.0728, "lr": 7.409156739049183e-07, "epoch": 18.602074493163602, "percentage": 93.01, "elapsed_time": "2:22:45", "remaining_time": "0:10:43", "throughput": 4632.28, "total_tokens": 39676608} {"current_steps": 39460, "total_steps": 42420, "loss": 0.0778, "lr": 7.384321100072339e-07, "epoch": 18.604431871758603, "percentage": 93.02, "elapsed_time": "2:22:46", "remaining_time": "0:10:42", "throughput": 4632.3, "total_tokens": 39680992} {"current_steps": 39465, "total_steps": 42420, "loss": 0.1383, "lr": 7.359526531810518e-07, "epoch": 18.606789250353607, "percentage": 93.03, "elapsed_time": "2:22:47", "remaining_time": "0:10:41", "throughput": 4632.31, "total_tokens": 39686048} {"current_steps": 39470, "total_steps": 42420, "loss": 0.2182, "lr": 7.334773038461056e-07, "epoch": 18.609146628948608, "percentage": 93.05, "elapsed_time": "2:22:48", "remaining_time": "0:10:40", "throughput": 4632.35, "total_tokens": 39691584} {"current_steps": 39475, "total_steps": 42420, "loss": 0.0293, "lr": 7.310060624214271e-07, "epoch": 18.611504007543612, "percentage": 93.06, "elapsed_time": "2:22:49", "remaining_time": "0:10:39", "throughput": 4632.38, "total_tokens": 39697504} {"current_steps": 39480, "total_steps": 42420, "loss": 0.0858, "lr": 7.285389293253619e-07, "epoch": 18.613861386138613, "percentage": 93.07, "elapsed_time": "2:22:50", "remaining_time": "0:10:38", "throughput": 4632.42, "total_tokens": 39702816} {"current_steps": 39485, "total_steps": 42420, "loss": 0.0385, "lr": 7.260759049755484e-07, "epoch": 18.616218764733617, "percentage": 93.08, "elapsed_time": "2:22:52", "remaining_time": "0:10:37", "throughput": 4632.48, "total_tokens": 39709792} {"current_steps": 39490, "total_steps": 42420, "loss": 0.141, "lr": 7.236169897889361e-07, "epoch": 18.618576143328617, "percentage": 93.09, "elapsed_time": "2:22:53", "remaining_time": "0:10:36", "throughput": 4632.49, "total_tokens": 39714368} {"current_steps": 39495, "total_steps": 42420, "loss": 0.0161, "lr": 7.211621841817784e-07, "epoch": 18.62093352192362, "percentage": 93.1, "elapsed_time": "2:22:54", "remaining_time": "0:10:34", "throughput": 4632.51, "total_tokens": 39719392} {"current_steps": 39500, "total_steps": 42420, "loss": 0.1927, "lr": 7.187114885696345e-07, "epoch": 18.623290900518622, "percentage": 93.12, "elapsed_time": "2:22:55", "remaining_time": "0:10:33", "throughput": 4632.5, "total_tokens": 39723904} {"current_steps": 39505, "total_steps": 42420, "loss": 0.0882, "lr": 7.162649033673585e-07, "epoch": 18.625648279113626, "percentage": 93.13, "elapsed_time": "2:22:55", "remaining_time": "0:10:32", "throughput": 4632.51, "total_tokens": 39728000} {"current_steps": 39510, "total_steps": 42420, "loss": 0.0375, "lr": 7.138224289891221e-07, "epoch": 18.628005657708627, "percentage": 93.14, "elapsed_time": "2:22:56", "remaining_time": "0:10:31", "throughput": 4632.52, "total_tokens": 39732608} {"current_steps": 39515, "total_steps": 42420, "loss": 0.0125, "lr": 7.113840658483917e-07, "epoch": 18.63036303630363, "percentage": 93.15, "elapsed_time": "2:22:58", "remaining_time": "0:10:30", "throughput": 4632.56, "total_tokens": 39738144} {"current_steps": 39520, "total_steps": 42420, "loss": 0.0554, "lr": 7.089498143579426e-07, "epoch": 18.632720414898632, "percentage": 93.16, "elapsed_time": "2:22:59", "remaining_time": "0:10:29", "throughput": 4632.58, "total_tokens": 39743456} {"current_steps": 39525, "total_steps": 42420, "loss": 0.2226, "lr": 7.065196749298508e-07, "epoch": 18.635077793493636, "percentage": 93.18, "elapsed_time": "2:23:00", "remaining_time": "0:10:28", "throughput": 4632.59, "total_tokens": 39749120} {"current_steps": 39530, "total_steps": 42420, "loss": 0.1352, "lr": 7.040936479754984e-07, "epoch": 18.637435172088637, "percentage": 93.19, "elapsed_time": "2:23:01", "remaining_time": "0:10:27", "throughput": 4632.6, "total_tokens": 39753504} {"current_steps": 39535, "total_steps": 42420, "loss": 0.02, "lr": 7.016717339055706e-07, "epoch": 18.63979255068364, "percentage": 93.2, "elapsed_time": "2:23:02", "remaining_time": "0:10:26", "throughput": 4632.62, "total_tokens": 39757984} {"current_steps": 39540, "total_steps": 42420, "loss": 0.0798, "lr": 6.99253933130059e-07, "epoch": 18.64214992927864, "percentage": 93.21, "elapsed_time": "2:23:03", "remaining_time": "0:10:25", "throughput": 4632.65, "total_tokens": 39763136} {"current_steps": 39545, "total_steps": 42420, "loss": 0.0883, "lr": 6.968402460582502e-07, "epoch": 18.644507307873646, "percentage": 93.22, "elapsed_time": "2:23:04", "remaining_time": "0:10:24", "throughput": 4632.67, "total_tokens": 39768416} {"current_steps": 39550, "total_steps": 42420, "loss": 0.0637, "lr": 6.944306730987421e-07, "epoch": 18.646864686468646, "percentage": 93.23, "elapsed_time": "2:23:05", "remaining_time": "0:10:23", "throughput": 4632.71, "total_tokens": 39774208} {"current_steps": 39555, "total_steps": 42420, "loss": 0.016, "lr": 6.920252146594364e-07, "epoch": 18.64922206506365, "percentage": 93.25, "elapsed_time": "2:23:06", "remaining_time": "0:10:21", "throughput": 4632.66, "total_tokens": 39778080} {"current_steps": 39560, "total_steps": 42420, "loss": 0.1284, "lr": 6.896238711475378e-07, "epoch": 18.65157944365865, "percentage": 93.26, "elapsed_time": "2:23:07", "remaining_time": "0:10:20", "throughput": 4632.71, "total_tokens": 39784608} {"current_steps": 39565, "total_steps": 42420, "loss": 0.1575, "lr": 6.872266429695518e-07, "epoch": 18.653936822253655, "percentage": 93.27, "elapsed_time": "2:23:08", "remaining_time": "0:10:19", "throughput": 4632.72, "total_tokens": 39788736} {"current_steps": 39570, "total_steps": 42420, "loss": 0.0156, "lr": 6.84833530531287e-07, "epoch": 18.656294200848656, "percentage": 93.28, "elapsed_time": "2:23:09", "remaining_time": "0:10:18", "throughput": 4632.74, "total_tokens": 39793600} {"current_steps": 39575, "total_steps": 42420, "loss": 0.1292, "lr": 6.824445342378583e-07, "epoch": 18.65865157944366, "percentage": 93.29, "elapsed_time": "2:23:10", "remaining_time": "0:10:17", "throughput": 4632.79, "total_tokens": 39799104} {"current_steps": 39580, "total_steps": 42420, "loss": 0.1113, "lr": 6.800596544936783e-07, "epoch": 18.66100895803866, "percentage": 93.31, "elapsed_time": "2:23:11", "remaining_time": "0:10:16", "throughput": 4632.81, "total_tokens": 39803872} {"current_steps": 39585, "total_steps": 42420, "loss": 0.3191, "lr": 6.776788917024713e-07, "epoch": 18.663366336633665, "percentage": 93.32, "elapsed_time": "2:23:12", "remaining_time": "0:10:15", "throughput": 4632.85, "total_tokens": 39809504} {"current_steps": 39590, "total_steps": 42420, "loss": 0.0296, "lr": 6.753022462672592e-07, "epoch": 18.665723715228665, "percentage": 93.33, "elapsed_time": "2:23:13", "remaining_time": "0:10:14", "throughput": 4632.85, "total_tokens": 39813664} {"current_steps": 39595, "total_steps": 42420, "loss": 0.0908, "lr": 6.729297185903677e-07, "epoch": 18.66808109382367, "percentage": 93.34, "elapsed_time": "2:23:15", "remaining_time": "0:10:13", "throughput": 4632.9, "total_tokens": 39821312} {"current_steps": 39600, "total_steps": 42420, "loss": 0.0323, "lr": 6.705613090734225e-07, "epoch": 18.67043847241867, "percentage": 93.35, "elapsed_time": "2:23:16", "remaining_time": "0:10:12", "throughput": 4632.9, "total_tokens": 39825856} {"current_steps": 39605, "total_steps": 42420, "loss": 0.0556, "lr": 6.681970181173585e-07, "epoch": 18.672795851013674, "percentage": 93.36, "elapsed_time": "2:23:17", "remaining_time": "0:10:11", "throughput": 4632.92, "total_tokens": 39830912} {"current_steps": 39610, "total_steps": 42420, "loss": 0.0655, "lr": 6.658368461224085e-07, "epoch": 18.675153229608675, "percentage": 93.38, "elapsed_time": "2:23:18", "remaining_time": "0:10:09", "throughput": 4632.95, "total_tokens": 39835936} {"current_steps": 39615, "total_steps": 42420, "loss": 0.1309, "lr": 6.634807934881082e-07, "epoch": 18.677510608203676, "percentage": 93.39, "elapsed_time": "2:23:19", "remaining_time": "0:10:08", "throughput": 4632.98, "total_tokens": 39841440} {"current_steps": 39620, "total_steps": 42420, "loss": 0.1338, "lr": 6.611288606132998e-07, "epoch": 18.67986798679868, "percentage": 93.4, "elapsed_time": "2:23:20", "remaining_time": "0:10:07", "throughput": 4633.0, "total_tokens": 39845760} {"current_steps": 39625, "total_steps": 42420, "loss": 0.3115, "lr": 6.587810478961259e-07, "epoch": 18.68222536539368, "percentage": 93.41, "elapsed_time": "2:23:21", "remaining_time": "0:10:06", "throughput": 4633.03, "total_tokens": 39850848} {"current_steps": 39630, "total_steps": 42420, "loss": 0.0286, "lr": 6.564373557340326e-07, "epoch": 18.684582743988685, "percentage": 93.42, "elapsed_time": "2:23:22", "remaining_time": "0:10:05", "throughput": 4633.07, "total_tokens": 39856384} {"current_steps": 39635, "total_steps": 42420, "loss": 0.1787, "lr": 6.540977845237606e-07, "epoch": 18.686940122583685, "percentage": 93.43, "elapsed_time": "2:23:23", "remaining_time": "0:10:04", "throughput": 4633.09, "total_tokens": 39860864} {"current_steps": 39640, "total_steps": 42420, "loss": 0.0826, "lr": 6.517623346613654e-07, "epoch": 18.68929750117869, "percentage": 93.45, "elapsed_time": "2:23:24", "remaining_time": "0:10:03", "throughput": 4633.1, "total_tokens": 39866080} {"current_steps": 39645, "total_steps": 42420, "loss": 0.245, "lr": 6.494310065421977e-07, "epoch": 18.69165487977369, "percentage": 93.46, "elapsed_time": "2:23:25", "remaining_time": "0:10:02", "throughput": 4633.15, "total_tokens": 39871936} {"current_steps": 39650, "total_steps": 42420, "loss": 0.064, "lr": 6.471038005609109e-07, "epoch": 18.694012258368694, "percentage": 93.47, "elapsed_time": "2:23:26", "remaining_time": "0:10:01", "throughput": 4633.17, "total_tokens": 39876512} {"current_steps": 39655, "total_steps": 42420, "loss": 0.0385, "lr": 6.447807171114622e-07, "epoch": 18.696369636963695, "percentage": 93.48, "elapsed_time": "2:23:27", "remaining_time": "0:10:00", "throughput": 4633.18, "total_tokens": 39880992} {"current_steps": 39660, "total_steps": 42420, "loss": 0.0616, "lr": 6.424617565871094e-07, "epoch": 18.6987270155587, "percentage": 93.49, "elapsed_time": "2:23:28", "remaining_time": "0:09:59", "throughput": 4633.2, "total_tokens": 39886208} {"current_steps": 39665, "total_steps": 42420, "loss": 0.1621, "lr": 6.401469193804133e-07, "epoch": 18.7010843941537, "percentage": 93.51, "elapsed_time": "2:23:29", "remaining_time": "0:09:58", "throughput": 4633.26, "total_tokens": 39892192} {"current_steps": 39670, "total_steps": 42420, "loss": 0.0417, "lr": 6.37836205883241e-07, "epoch": 18.703441772748704, "percentage": 93.52, "elapsed_time": "2:23:31", "remaining_time": "0:09:56", "throughput": 4633.3, "total_tokens": 39897824} {"current_steps": 39675, "total_steps": 42420, "loss": 0.2497, "lr": 6.355296164867491e-07, "epoch": 18.705799151343705, "percentage": 93.53, "elapsed_time": "2:23:32", "remaining_time": "0:09:55", "throughput": 4633.32, "total_tokens": 39903456} {"current_steps": 39680, "total_steps": 42420, "loss": 0.22, "lr": 6.332271515814087e-07, "epoch": 18.70815652993871, "percentage": 93.54, "elapsed_time": "2:23:33", "remaining_time": "0:09:54", "throughput": 4633.34, "total_tokens": 39908160} {"current_steps": 39685, "total_steps": 42420, "loss": 0.1645, "lr": 6.309288115569884e-07, "epoch": 18.71051390853371, "percentage": 93.55, "elapsed_time": "2:23:34", "remaining_time": "0:09:53", "throughput": 4633.37, "total_tokens": 39913696} {"current_steps": 39690, "total_steps": 42420, "loss": 0.1978, "lr": 6.286345968025548e-07, "epoch": 18.712871287128714, "percentage": 93.56, "elapsed_time": "2:23:35", "remaining_time": "0:09:52", "throughput": 4633.37, "total_tokens": 39918432} {"current_steps": 39695, "total_steps": 42420, "loss": 0.043, "lr": 6.263445077064833e-07, "epoch": 18.715228665723714, "percentage": 93.58, "elapsed_time": "2:23:36", "remaining_time": "0:09:51", "throughput": 4633.41, "total_tokens": 39923872} {"current_steps": 39700, "total_steps": 42420, "loss": 0.0253, "lr": 6.240585446564446e-07, "epoch": 18.71758604431872, "percentage": 93.59, "elapsed_time": "2:23:37", "remaining_time": "0:09:50", "throughput": 4633.44, "total_tokens": 39928928} {"current_steps": 39705, "total_steps": 42420, "loss": 0.0518, "lr": 6.217767080394149e-07, "epoch": 18.71994342291372, "percentage": 93.6, "elapsed_time": "2:23:38", "remaining_time": "0:09:49", "throughput": 4633.45, "total_tokens": 39933536} {"current_steps": 39710, "total_steps": 42420, "loss": 0.2999, "lr": 6.194989982416715e-07, "epoch": 18.722300801508723, "percentage": 93.61, "elapsed_time": "2:23:39", "remaining_time": "0:09:48", "throughput": 4633.46, "total_tokens": 39938048} {"current_steps": 39715, "total_steps": 42420, "loss": 0.0915, "lr": 6.172254156487894e-07, "epoch": 18.724658180103724, "percentage": 93.62, "elapsed_time": "2:23:40", "remaining_time": "0:09:47", "throughput": 4633.48, "total_tokens": 39942752} {"current_steps": 39720, "total_steps": 42420, "loss": 0.1914, "lr": 6.149559606456468e-07, "epoch": 18.727015558698728, "percentage": 93.64, "elapsed_time": "2:23:41", "remaining_time": "0:09:46", "throughput": 4633.47, "total_tokens": 39946784} {"current_steps": 39725, "total_steps": 42420, "loss": 0.0627, "lr": 6.126906336164279e-07, "epoch": 18.72937293729373, "percentage": 93.65, "elapsed_time": "2:23:42", "remaining_time": "0:09:44", "throughput": 4633.5, "total_tokens": 39952384} {"current_steps": 39730, "total_steps": 42420, "loss": 0.0264, "lr": 6.104294349446094e-07, "epoch": 18.731730315888733, "percentage": 93.66, "elapsed_time": "2:23:43", "remaining_time": "0:09:43", "throughput": 4633.53, "total_tokens": 39956672} {"current_steps": 39735, "total_steps": 42420, "loss": 0.1414, "lr": 6.081723650129767e-07, "epoch": 18.734087694483733, "percentage": 93.67, "elapsed_time": "2:23:44", "remaining_time": "0:09:42", "throughput": 4633.57, "total_tokens": 39962368} {"current_steps": 39740, "total_steps": 42420, "loss": 0.2651, "lr": 6.059194242036131e-07, "epoch": 18.736445073078738, "percentage": 93.68, "elapsed_time": "2:23:45", "remaining_time": "0:09:41", "throughput": 4633.64, "total_tokens": 39969728} {"current_steps": 39745, "total_steps": 42420, "loss": 0.1204, "lr": 6.036706128979053e-07, "epoch": 18.738802451673738, "percentage": 93.69, "elapsed_time": "2:23:46", "remaining_time": "0:09:40", "throughput": 4633.67, "total_tokens": 39974656} {"current_steps": 39750, "total_steps": 42420, "loss": 0.2363, "lr": 6.014259314765375e-07, "epoch": 18.741159830268742, "percentage": 93.71, "elapsed_time": "2:23:47", "remaining_time": "0:09:39", "throughput": 4633.67, "total_tokens": 39978976} {"current_steps": 39755, "total_steps": 42420, "loss": 0.1488, "lr": 5.991853803194919e-07, "epoch": 18.743517208863743, "percentage": 93.72, "elapsed_time": "2:23:48", "remaining_time": "0:09:38", "throughput": 4633.69, "total_tokens": 39984000} {"current_steps": 39760, "total_steps": 42420, "loss": 0.0711, "lr": 5.969489598060596e-07, "epoch": 18.745874587458747, "percentage": 93.73, "elapsed_time": "2:23:49", "remaining_time": "0:09:37", "throughput": 4633.68, "total_tokens": 39988512} {"current_steps": 39765, "total_steps": 42420, "loss": 0.2039, "lr": 5.947166703148293e-07, "epoch": 18.748231966053748, "percentage": 93.74, "elapsed_time": "2:23:50", "remaining_time": "0:09:36", "throughput": 4633.69, "total_tokens": 39992832} {"current_steps": 39770, "total_steps": 42420, "loss": 0.0441, "lr": 5.924885122236851e-07, "epoch": 18.750589344648752, "percentage": 93.75, "elapsed_time": "2:23:52", "remaining_time": "0:09:35", "throughput": 4633.74, "total_tokens": 39999072} {"current_steps": 39775, "total_steps": 42420, "loss": 0.0406, "lr": 5.90264485909825e-07, "epoch": 18.752946723243753, "percentage": 93.76, "elapsed_time": "2:23:53", "remaining_time": "0:09:34", "throughput": 4633.78, "total_tokens": 40004352} {"current_steps": 39780, "total_steps": 42420, "loss": 0.1138, "lr": 5.880445917497284e-07, "epoch": 18.755304101838757, "percentage": 93.78, "elapsed_time": "2:23:54", "remaining_time": "0:09:33", "throughput": 4633.82, "total_tokens": 40010432} {"current_steps": 39785, "total_steps": 42420, "loss": 0.2268, "lr": 5.858288301191949e-07, "epoch": 18.757661480433757, "percentage": 93.79, "elapsed_time": "2:23:55", "remaining_time": "0:09:31", "throughput": 4633.68, "total_tokens": 40015296} {"current_steps": 39790, "total_steps": 42420, "loss": 0.0311, "lr": 5.836172013933133e-07, "epoch": 18.76001885902876, "percentage": 93.8, "elapsed_time": "2:23:56", "remaining_time": "0:09:30", "throughput": 4633.72, "total_tokens": 40020960} {"current_steps": 39795, "total_steps": 42420, "loss": 0.2128, "lr": 5.814097059464702e-07, "epoch": 18.762376237623762, "percentage": 93.81, "elapsed_time": "2:23:57", "remaining_time": "0:09:29", "throughput": 4633.75, "total_tokens": 40026272} {"current_steps": 39800, "total_steps": 42420, "loss": 0.0159, "lr": 5.792063441523609e-07, "epoch": 18.764733616218766, "percentage": 93.82, "elapsed_time": "2:23:59", "remaining_time": "0:09:28", "throughput": 4633.77, "total_tokens": 40031232} {"current_steps": 39805, "total_steps": 42420, "loss": 0.1002, "lr": 5.770071163839763e-07, "epoch": 18.767090994813767, "percentage": 93.84, "elapsed_time": "2:24:00", "remaining_time": "0:09:27", "throughput": 4633.79, "total_tokens": 40036032} {"current_steps": 39810, "total_steps": 42420, "loss": 0.0968, "lr": 5.748120230136045e-07, "epoch": 18.76944837340877, "percentage": 93.85, "elapsed_time": "2:24:01", "remaining_time": "0:09:26", "throughput": 4633.81, "total_tokens": 40040832} {"current_steps": 39815, "total_steps": 42420, "loss": 0.0528, "lr": 5.726210644128427e-07, "epoch": 18.77180575200377, "percentage": 93.86, "elapsed_time": "2:24:02", "remaining_time": "0:09:25", "throughput": 4633.84, "total_tokens": 40045664} {"current_steps": 39820, "total_steps": 42420, "loss": 0.088, "lr": 5.704342409525831e-07, "epoch": 18.774163130598772, "percentage": 93.87, "elapsed_time": "2:24:03", "remaining_time": "0:09:24", "throughput": 4633.9, "total_tokens": 40053024} {"current_steps": 39825, "total_steps": 42420, "loss": 0.1828, "lr": 5.682515530030158e-07, "epoch": 18.776520509193777, "percentage": 93.88, "elapsed_time": "2:24:04", "remaining_time": "0:09:23", "throughput": 4633.9, "total_tokens": 40056928} {"current_steps": 39830, "total_steps": 42420, "loss": 0.053, "lr": 5.660730009336312e-07, "epoch": 18.778877887788777, "percentage": 93.89, "elapsed_time": "2:24:05", "remaining_time": "0:09:22", "throughput": 4633.92, "total_tokens": 40061888} {"current_steps": 39835, "total_steps": 42420, "loss": 0.0805, "lr": 5.638985851132234e-07, "epoch": 18.78123526638378, "percentage": 93.91, "elapsed_time": "2:24:06", "remaining_time": "0:09:21", "throughput": 4633.95, "total_tokens": 40067552} {"current_steps": 39840, "total_steps": 42420, "loss": 0.0252, "lr": 5.617283059098865e-07, "epoch": 18.783592644978782, "percentage": 93.92, "elapsed_time": "2:24:07", "remaining_time": "0:09:20", "throughput": 4633.99, "total_tokens": 40073280} {"current_steps": 39845, "total_steps": 42420, "loss": 0.2854, "lr": 5.595621636910075e-07, "epoch": 18.785950023573786, "percentage": 93.93, "elapsed_time": "2:24:08", "remaining_time": "0:09:18", "throughput": 4634.04, "total_tokens": 40079584} {"current_steps": 39850, "total_steps": 42420, "loss": 0.0205, "lr": 5.574001588232791e-07, "epoch": 18.788307402168787, "percentage": 93.94, "elapsed_time": "2:24:09", "remaining_time": "0:09:17", "throughput": 4634.05, "total_tokens": 40083936} {"current_steps": 39855, "total_steps": 42420, "loss": 0.106, "lr": 5.552422916726918e-07, "epoch": 18.79066478076379, "percentage": 93.95, "elapsed_time": "2:24:10", "remaining_time": "0:09:16", "throughput": 4634.04, "total_tokens": 40087936} {"current_steps": 39860, "total_steps": 42420, "loss": 0.0457, "lr": 5.53088562604534e-07, "epoch": 18.79302215935879, "percentage": 93.97, "elapsed_time": "2:24:11", "remaining_time": "0:09:15", "throughput": 4633.98, "total_tokens": 40091296} {"current_steps": 39865, "total_steps": 42420, "loss": 0.0172, "lr": 5.509389719834002e-07, "epoch": 18.795379537953796, "percentage": 93.98, "elapsed_time": "2:24:12", "remaining_time": "0:09:14", "throughput": 4634.0, "total_tokens": 40096608} {"current_steps": 39870, "total_steps": 42420, "loss": 0.1239, "lr": 5.48793520173177e-07, "epoch": 18.797736916548796, "percentage": 93.99, "elapsed_time": "2:24:13", "remaining_time": "0:09:13", "throughput": 4634.04, "total_tokens": 40101824} {"current_steps": 39875, "total_steps": 42420, "loss": 0.0354, "lr": 5.466522075370517e-07, "epoch": 18.8000942951438, "percentage": 94.0, "elapsed_time": "2:24:14", "remaining_time": "0:09:12", "throughput": 4634.05, "total_tokens": 40106432} {"current_steps": 39880, "total_steps": 42420, "loss": 0.12, "lr": 5.445150344375178e-07, "epoch": 18.8024516737388, "percentage": 94.01, "elapsed_time": "2:24:16", "remaining_time": "0:09:11", "throughput": 4634.09, "total_tokens": 40113408} {"current_steps": 39885, "total_steps": 42420, "loss": 0.0595, "lr": 5.42382001236355e-07, "epoch": 18.804809052333805, "percentage": 94.02, "elapsed_time": "2:24:17", "remaining_time": "0:09:10", "throughput": 4634.1, "total_tokens": 40117888} {"current_steps": 39890, "total_steps": 42420, "loss": 0.1484, "lr": 5.402531082946499e-07, "epoch": 18.807166430928806, "percentage": 94.04, "elapsed_time": "2:24:18", "remaining_time": "0:09:09", "throughput": 4634.14, "total_tokens": 40123360} {"current_steps": 39895, "total_steps": 42420, "loss": 0.1145, "lr": 5.381283559727945e-07, "epoch": 18.80952380952381, "percentage": 94.05, "elapsed_time": "2:24:19", "remaining_time": "0:09:08", "throughput": 4634.15, "total_tokens": 40128864} {"current_steps": 39900, "total_steps": 42420, "loss": 0.1867, "lr": 5.360077446304679e-07, "epoch": 18.81188118811881, "percentage": 94.06, "elapsed_time": "2:24:20", "remaining_time": "0:09:06", "throughput": 4634.19, "total_tokens": 40134688} {"current_steps": 39905, "total_steps": 42420, "loss": 0.0893, "lr": 5.33891274626655e-07, "epoch": 18.814238566713815, "percentage": 94.07, "elapsed_time": "2:24:21", "remaining_time": "0:09:05", "throughput": 4634.21, "total_tokens": 40139488} {"current_steps": 39910, "total_steps": 42420, "loss": 0.0409, "lr": 5.317789463196388e-07, "epoch": 18.816595945308816, "percentage": 94.08, "elapsed_time": "2:24:22", "remaining_time": "0:09:04", "throughput": 4634.24, "total_tokens": 40144320} {"current_steps": 39915, "total_steps": 42420, "loss": 0.0211, "lr": 5.296707600669998e-07, "epoch": 18.81895332390382, "percentage": 94.09, "elapsed_time": "2:24:23", "remaining_time": "0:09:03", "throughput": 4634.28, "total_tokens": 40149568} {"current_steps": 39920, "total_steps": 42420, "loss": 0.2048, "lr": 5.27566716225622e-07, "epoch": 18.82131070249882, "percentage": 94.11, "elapsed_time": "2:24:24", "remaining_time": "0:09:02", "throughput": 4634.28, "total_tokens": 40153632} {"current_steps": 39925, "total_steps": 42420, "loss": 0.075, "lr": 5.254668151516762e-07, "epoch": 18.823668081093825, "percentage": 94.12, "elapsed_time": "2:24:25", "remaining_time": "0:09:01", "throughput": 4634.33, "total_tokens": 40159296} {"current_steps": 39930, "total_steps": 42420, "loss": 0.1785, "lr": 5.233710572006473e-07, "epoch": 18.826025459688825, "percentage": 94.13, "elapsed_time": "2:24:26", "remaining_time": "0:09:00", "throughput": 4634.37, "total_tokens": 40165088} {"current_steps": 39935, "total_steps": 42420, "loss": 0.0268, "lr": 5.212794427273071e-07, "epoch": 18.82838283828383, "percentage": 94.14, "elapsed_time": "2:24:27", "remaining_time": "0:08:59", "throughput": 4634.4, "total_tokens": 40170208} {"current_steps": 39940, "total_steps": 42420, "loss": 0.137, "lr": 5.191919720857335e-07, "epoch": 18.83074021687883, "percentage": 94.15, "elapsed_time": "2:24:28", "remaining_time": "0:08:58", "throughput": 4634.4, "total_tokens": 40174336} {"current_steps": 39945, "total_steps": 42420, "loss": 0.1437, "lr": 5.171086456292967e-07, "epoch": 18.833097595473834, "percentage": 94.17, "elapsed_time": "2:24:29", "remaining_time": "0:08:57", "throughput": 4634.42, "total_tokens": 40179136} {"current_steps": 39950, "total_steps": 42420, "loss": 0.0554, "lr": 5.150294637106728e-07, "epoch": 18.835454974068835, "percentage": 94.18, "elapsed_time": "2:24:30", "remaining_time": "0:08:56", "throughput": 4634.44, "total_tokens": 40184352} {"current_steps": 39955, "total_steps": 42420, "loss": 0.0812, "lr": 5.129544266818276e-07, "epoch": 18.83781235266384, "percentage": 94.19, "elapsed_time": "2:24:31", "remaining_time": "0:08:55", "throughput": 4634.47, "total_tokens": 40189408} {"current_steps": 39960, "total_steps": 42420, "loss": 0.1997, "lr": 5.108835348940355e-07, "epoch": 18.84016973125884, "percentage": 94.2, "elapsed_time": "2:24:32", "remaining_time": "0:08:53", "throughput": 4634.5, "total_tokens": 40194400} {"current_steps": 39965, "total_steps": 42420, "loss": 0.0416, "lr": 5.088167886978579e-07, "epoch": 18.842527109853844, "percentage": 94.21, "elapsed_time": "2:24:33", "remaining_time": "0:08:52", "throughput": 4634.52, "total_tokens": 40199488} {"current_steps": 39970, "total_steps": 42420, "loss": 0.1078, "lr": 5.067541884431593e-07, "epoch": 18.844884488448844, "percentage": 94.22, "elapsed_time": "2:24:35", "remaining_time": "0:08:51", "throughput": 4634.56, "total_tokens": 40205120} {"current_steps": 39975, "total_steps": 42420, "loss": 0.1288, "lr": 5.046957344791048e-07, "epoch": 18.84724186704385, "percentage": 94.24, "elapsed_time": "2:24:36", "remaining_time": "0:08:50", "throughput": 4634.6, "total_tokens": 40211712} {"current_steps": 39980, "total_steps": 42420, "loss": 0.0691, "lr": 5.026414271541574e-07, "epoch": 18.84959924563885, "percentage": 94.25, "elapsed_time": "2:24:37", "remaining_time": "0:08:49", "throughput": 4634.63, "total_tokens": 40217152} {"current_steps": 39985, "total_steps": 42420, "loss": 0.1671, "lr": 5.005912668160723e-07, "epoch": 18.851956624233853, "percentage": 94.26, "elapsed_time": "2:24:38", "remaining_time": "0:08:48", "throughput": 4634.65, "total_tokens": 40221856} {"current_steps": 39990, "total_steps": 42420, "loss": 0.1195, "lr": 4.985452538119134e-07, "epoch": 18.854314002828854, "percentage": 94.27, "elapsed_time": "2:24:39", "remaining_time": "0:08:47", "throughput": 4634.69, "total_tokens": 40227232} {"current_steps": 39995, "total_steps": 42420, "loss": 0.0588, "lr": 4.965033884880288e-07, "epoch": 18.85667138142386, "percentage": 94.28, "elapsed_time": "2:24:40", "remaining_time": "0:08:46", "throughput": 4634.71, "total_tokens": 40231648} {"current_steps": 40000, "total_steps": 42420, "loss": 0.0151, "lr": 4.94465671190078e-07, "epoch": 18.85902876001886, "percentage": 94.3, "elapsed_time": "2:24:41", "remaining_time": "0:08:45", "throughput": 4634.72, "total_tokens": 40236128} {"current_steps": 40005, "total_steps": 42420, "loss": 0.0895, "lr": 4.924321022630074e-07, "epoch": 18.861386138613863, "percentage": 94.31, "elapsed_time": "2:24:42", "remaining_time": "0:08:44", "throughput": 4634.74, "total_tokens": 40241088} {"current_steps": 40010, "total_steps": 42420, "loss": 0.0867, "lr": 4.904026820510665e-07, "epoch": 18.863743517208864, "percentage": 94.32, "elapsed_time": "2:24:43", "remaining_time": "0:08:43", "throughput": 4634.76, "total_tokens": 40245888} {"current_steps": 40015, "total_steps": 42420, "loss": 0.0626, "lr": 4.883774108978029e-07, "epoch": 18.866100895803868, "percentage": 94.33, "elapsed_time": "2:24:44", "remaining_time": "0:08:41", "throughput": 4634.79, "total_tokens": 40250944} {"current_steps": 40020, "total_steps": 42420, "loss": 0.156, "lr": 4.863562891460588e-07, "epoch": 18.86845827439887, "percentage": 94.34, "elapsed_time": "2:24:45", "remaining_time": "0:08:40", "throughput": 4634.81, "total_tokens": 40255968} {"current_steps": 40025, "total_steps": 42420, "loss": 0.0963, "lr": 4.843393171379773e-07, "epoch": 18.87081565299387, "percentage": 94.35, "elapsed_time": "2:24:46", "remaining_time": "0:08:39", "throughput": 4634.83, "total_tokens": 40261216} {"current_steps": 40030, "total_steps": 42420, "loss": 0.0298, "lr": 4.823264952149964e-07, "epoch": 18.873173031588873, "percentage": 94.37, "elapsed_time": "2:24:47", "remaining_time": "0:08:38", "throughput": 4634.87, "total_tokens": 40267104} {"current_steps": 40035, "total_steps": 42420, "loss": 0.2027, "lr": 4.803178237178546e-07, "epoch": 18.875530410183874, "percentage": 94.38, "elapsed_time": "2:24:48", "remaining_time": "0:08:37", "throughput": 4634.9, "total_tokens": 40272576} {"current_steps": 40040, "total_steps": 42420, "loss": 0.109, "lr": 4.783133029865855e-07, "epoch": 18.877887788778878, "percentage": 94.39, "elapsed_time": "2:24:49", "remaining_time": "0:08:36", "throughput": 4634.91, "total_tokens": 40277088} {"current_steps": 40045, "total_steps": 42420, "loss": 0.0756, "lr": 4.763129333605176e-07, "epoch": 18.88024516737388, "percentage": 94.4, "elapsed_time": "2:24:50", "remaining_time": "0:08:35", "throughput": 4634.93, "total_tokens": 40282112} {"current_steps": 40050, "total_steps": 42420, "loss": 0.1001, "lr": 4.743167151782857e-07, "epoch": 18.882602545968883, "percentage": 94.41, "elapsed_time": "2:24:51", "remaining_time": "0:08:34", "throughput": 4634.95, "total_tokens": 40286528} {"current_steps": 40055, "total_steps": 42420, "loss": 0.1566, "lr": 4.7232464877780824e-07, "epoch": 18.884959924563884, "percentage": 94.42, "elapsed_time": "2:24:53", "remaining_time": "0:08:33", "throughput": 4634.99, "total_tokens": 40292384} {"current_steps": 40060, "total_steps": 42420, "loss": 0.1333, "lr": 4.703367344963128e-07, "epoch": 18.887317303158888, "percentage": 94.44, "elapsed_time": "2:24:54", "remaining_time": "0:08:32", "throughput": 4635.03, "total_tokens": 40298720} {"current_steps": 40065, "total_steps": 42420, "loss": 0.0778, "lr": 4.683529726703162e-07, "epoch": 18.88967468175389, "percentage": 94.45, "elapsed_time": "2:24:55", "remaining_time": "0:08:31", "throughput": 4635.02, "total_tokens": 40302592} {"current_steps": 40070, "total_steps": 42420, "loss": 0.1347, "lr": 4.6637336363563876e-07, "epoch": 18.892032060348892, "percentage": 94.46, "elapsed_time": "2:24:56", "remaining_time": "0:08:30", "throughput": 4635.07, "total_tokens": 40309536} {"current_steps": 40075, "total_steps": 42420, "loss": 0.269, "lr": 4.64397907727393e-07, "epoch": 18.894389438943893, "percentage": 94.47, "elapsed_time": "2:24:57", "remaining_time": "0:08:28", "throughput": 4635.09, "total_tokens": 40314560} {"current_steps": 40080, "total_steps": 42420, "loss": 0.1538, "lr": 4.6242660527999194e-07, "epoch": 18.896746817538897, "percentage": 94.48, "elapsed_time": "2:24:59", "remaining_time": "0:08:27", "throughput": 4635.12, "total_tokens": 40321152} {"current_steps": 40085, "total_steps": 42420, "loss": 0.1146, "lr": 4.6045945662714083e-07, "epoch": 18.899104196133898, "percentage": 94.5, "elapsed_time": "2:25:00", "remaining_time": "0:08:26", "throughput": 4635.12, "total_tokens": 40325920} {"current_steps": 40090, "total_steps": 42420, "loss": 0.0472, "lr": 4.5849646210184837e-07, "epoch": 18.901461574728902, "percentage": 94.51, "elapsed_time": "2:25:01", "remaining_time": "0:08:25", "throughput": 4635.14, "total_tokens": 40331072} {"current_steps": 40095, "total_steps": 42420, "loss": 0.0106, "lr": 4.565376220364126e-07, "epoch": 18.903818953323903, "percentage": 94.52, "elapsed_time": "2:25:02", "remaining_time": "0:08:24", "throughput": 4635.13, "total_tokens": 40335680} {"current_steps": 40100, "total_steps": 42420, "loss": 0.1069, "lr": 4.5458293676243214e-07, "epoch": 18.906176331918907, "percentage": 94.53, "elapsed_time": "2:25:03", "remaining_time": "0:08:23", "throughput": 4635.16, "total_tokens": 40340384} {"current_steps": 40105, "total_steps": 42420, "loss": 0.0789, "lr": 4.5263240661080344e-07, "epoch": 18.908533710513908, "percentage": 94.54, "elapsed_time": "2:25:04", "remaining_time": "0:08:22", "throughput": 4635.21, "total_tokens": 40345888} {"current_steps": 40110, "total_steps": 42420, "loss": 0.0794, "lr": 4.5068603191171786e-07, "epoch": 18.91089108910891, "percentage": 94.55, "elapsed_time": "2:25:05", "remaining_time": "0:08:21", "throughput": 4635.2, "total_tokens": 40350144} {"current_steps": 40115, "total_steps": 42420, "loss": 0.1953, "lr": 4.4874381299466475e-07, "epoch": 18.913248467703912, "percentage": 94.57, "elapsed_time": "2:25:06", "remaining_time": "0:08:20", "throughput": 4635.22, "total_tokens": 40354912} {"current_steps": 40120, "total_steps": 42420, "loss": 0.0445, "lr": 4.468057501884254e-07, "epoch": 18.915605846298917, "percentage": 94.58, "elapsed_time": "2:25:07", "remaining_time": "0:08:19", "throughput": 4635.28, "total_tokens": 40362400} {"current_steps": 40125, "total_steps": 42420, "loss": 0.0599, "lr": 4.448718438210819e-07, "epoch": 18.917963224893917, "percentage": 94.59, "elapsed_time": "2:25:09", "remaining_time": "0:08:18", "throughput": 4635.32, "total_tokens": 40369760} {"current_steps": 40130, "total_steps": 42420, "loss": 0.0339, "lr": 4.4294209422001966e-07, "epoch": 18.92032060348892, "percentage": 94.6, "elapsed_time": "2:25:10", "remaining_time": "0:08:17", "throughput": 4635.35, "total_tokens": 40374624} {"current_steps": 40135, "total_steps": 42420, "loss": 0.0931, "lr": 4.4101650171189946e-07, "epoch": 18.922677982083922, "percentage": 94.61, "elapsed_time": "2:25:11", "remaining_time": "0:08:15", "throughput": 4635.39, "total_tokens": 40380608} {"current_steps": 40140, "total_steps": 42420, "loss": 0.0337, "lr": 4.390950666226995e-07, "epoch": 18.925035360678926, "percentage": 94.63, "elapsed_time": "2:25:12", "remaining_time": "0:08:14", "throughput": 4635.4, "total_tokens": 40384992} {"current_steps": 40145, "total_steps": 42420, "loss": 0.0712, "lr": 4.371777892776846e-07, "epoch": 18.927392739273927, "percentage": 94.64, "elapsed_time": "2:25:13", "remaining_time": "0:08:13", "throughput": 4635.42, "total_tokens": 40390464} {"current_steps": 40150, "total_steps": 42420, "loss": 0.1516, "lr": 4.352646700014146e-07, "epoch": 18.92975011786893, "percentage": 94.65, "elapsed_time": "2:25:14", "remaining_time": "0:08:12", "throughput": 4635.45, "total_tokens": 40396192} {"current_steps": 40155, "total_steps": 42420, "loss": 0.039, "lr": 4.3335570911775257e-07, "epoch": 18.93210749646393, "percentage": 94.66, "elapsed_time": "2:25:15", "remaining_time": "0:08:11", "throughput": 4635.47, "total_tokens": 40401216} {"current_steps": 40160, "total_steps": 42420, "loss": 0.0622, "lr": 4.314509069498512e-07, "epoch": 18.934464875058936, "percentage": 94.67, "elapsed_time": "2:25:16", "remaining_time": "0:08:10", "throughput": 4635.49, "total_tokens": 40406432} {"current_steps": 40165, "total_steps": 42420, "loss": 0.2014, "lr": 4.2955026382016097e-07, "epoch": 18.936822253653936, "percentage": 94.68, "elapsed_time": "2:25:17", "remaining_time": "0:08:09", "throughput": 4635.53, "total_tokens": 40411776} {"current_steps": 40170, "total_steps": 42420, "loss": 0.0628, "lr": 4.276537800504299e-07, "epoch": 18.93917963224894, "percentage": 94.7, "elapsed_time": "2:25:18", "remaining_time": "0:08:08", "throughput": 4635.53, "total_tokens": 40415808} {"current_steps": 40175, "total_steps": 42420, "loss": 0.1504, "lr": 4.2576145596169845e-07, "epoch": 18.94153701084394, "percentage": 94.71, "elapsed_time": "2:25:19", "remaining_time": "0:08:07", "throughput": 4635.54, "total_tokens": 40420864} {"current_steps": 40180, "total_steps": 42420, "loss": 0.0819, "lr": 4.238732918743049e-07, "epoch": 18.943894389438945, "percentage": 94.72, "elapsed_time": "2:25:20", "remaining_time": "0:08:06", "throughput": 4635.56, "total_tokens": 40425152} {"current_steps": 40185, "total_steps": 42420, "loss": 0.1008, "lr": 4.219892881078824e-07, "epoch": 18.946251768033946, "percentage": 94.73, "elapsed_time": "2:25:21", "remaining_time": "0:08:05", "throughput": 4635.56, "total_tokens": 40429600} {"current_steps": 40190, "total_steps": 42420, "loss": 0.0987, "lr": 4.201094449813647e-07, "epoch": 18.94860914662895, "percentage": 94.74, "elapsed_time": "2:25:22", "remaining_time": "0:08:03", "throughput": 4635.58, "total_tokens": 40434272} {"current_steps": 40195, "total_steps": 42420, "loss": 0.1234, "lr": 4.182337628129751e-07, "epoch": 18.95096652522395, "percentage": 94.75, "elapsed_time": "2:25:23", "remaining_time": "0:08:02", "throughput": 4635.61, "total_tokens": 40438784} {"current_steps": 40200, "total_steps": 42420, "loss": 0.0894, "lr": 4.163622419202345e-07, "epoch": 18.953323903818955, "percentage": 94.77, "elapsed_time": "2:25:24", "remaining_time": "0:08:01", "throughput": 4635.62, "total_tokens": 40442816} {"current_steps": 40205, "total_steps": 42420, "loss": 0.052, "lr": 4.144948826199618e-07, "epoch": 18.955681282413956, "percentage": 94.78, "elapsed_time": "2:25:25", "remaining_time": "0:08:00", "throughput": 4635.65, "total_tokens": 40448384} {"current_steps": 40210, "total_steps": 42420, "loss": 0.2825, "lr": 4.1263168522826525e-07, "epoch": 18.95803866100896, "percentage": 94.79, "elapsed_time": "2:25:26", "remaining_time": "0:07:59", "throughput": 4635.69, "total_tokens": 40453888} {"current_steps": 40215, "total_steps": 42420, "loss": 0.1606, "lr": 4.1077265006055634e-07, "epoch": 18.96039603960396, "percentage": 94.8, "elapsed_time": "2:25:27", "remaining_time": "0:07:58", "throughput": 4635.7, "total_tokens": 40458560} {"current_steps": 40220, "total_steps": 42420, "loss": 0.1368, "lr": 4.0891777743153334e-07, "epoch": 18.962753418198965, "percentage": 94.81, "elapsed_time": "2:25:28", "remaining_time": "0:07:57", "throughput": 4635.74, "total_tokens": 40463520} {"current_steps": 40225, "total_steps": 42420, "loss": 0.0841, "lr": 4.0706706765520074e-07, "epoch": 18.965110796793965, "percentage": 94.83, "elapsed_time": "2:25:29", "remaining_time": "0:07:56", "throughput": 4635.78, "total_tokens": 40469408} {"current_steps": 40230, "total_steps": 42420, "loss": 0.0218, "lr": 4.0522052104484675e-07, "epoch": 18.967468175388966, "percentage": 94.84, "elapsed_time": "2:25:30", "remaining_time": "0:07:55", "throughput": 4635.79, "total_tokens": 40474240} {"current_steps": 40235, "total_steps": 42420, "loss": 0.0552, "lr": 4.033781379130658e-07, "epoch": 18.96982555398397, "percentage": 94.85, "elapsed_time": "2:25:31", "remaining_time": "0:07:54", "throughput": 4635.81, "total_tokens": 40479424} {"current_steps": 40240, "total_steps": 42420, "loss": 0.1793, "lr": 4.015399185717389e-07, "epoch": 18.97218293257897, "percentage": 94.86, "elapsed_time": "2:25:32", "remaining_time": "0:07:53", "throughput": 4635.83, "total_tokens": 40483808} {"current_steps": 40245, "total_steps": 42420, "loss": 0.1387, "lr": 3.9970586333204496e-07, "epoch": 18.974540311173975, "percentage": 94.87, "elapsed_time": "2:25:33", "remaining_time": "0:07:52", "throughput": 4635.83, "total_tokens": 40488352} {"current_steps": 40250, "total_steps": 42420, "loss": 0.0772, "lr": 3.9787597250445784e-07, "epoch": 18.976897689768975, "percentage": 94.88, "elapsed_time": "2:25:34", "remaining_time": "0:07:50", "throughput": 4635.85, "total_tokens": 40493312} {"current_steps": 40255, "total_steps": 42420, "loss": 0.0801, "lr": 3.960502463987492e-07, "epoch": 18.97925506836398, "percentage": 94.9, "elapsed_time": "2:25:35", "remaining_time": "0:07:49", "throughput": 4635.85, "total_tokens": 40498112} {"current_steps": 40260, "total_steps": 42420, "loss": 0.0248, "lr": 3.942286853239857e-07, "epoch": 18.98161244695898, "percentage": 94.91, "elapsed_time": "2:25:36", "remaining_time": "0:07:48", "throughput": 4635.87, "total_tokens": 40502784} {"current_steps": 40265, "total_steps": 42420, "loss": 0.1995, "lr": 3.924112895885207e-07, "epoch": 18.983969825553984, "percentage": 94.92, "elapsed_time": "2:25:37", "remaining_time": "0:07:47", "throughput": 4635.89, "total_tokens": 40507488} {"current_steps": 40270, "total_steps": 42420, "loss": 0.1477, "lr": 3.905980595000108e-07, "epoch": 18.986327204148985, "percentage": 94.93, "elapsed_time": "2:25:38", "remaining_time": "0:07:46", "throughput": 4635.9, "total_tokens": 40511744} {"current_steps": 40275, "total_steps": 42420, "loss": 0.0946, "lr": 3.88788995365405e-07, "epoch": 18.98868458274399, "percentage": 94.94, "elapsed_time": "2:25:39", "remaining_time": "0:07:45", "throughput": 4635.94, "total_tokens": 40517600} {"current_steps": 40280, "total_steps": 42420, "loss": 0.0613, "lr": 3.869840974909472e-07, "epoch": 18.99104196133899, "percentage": 94.96, "elapsed_time": "2:25:40", "remaining_time": "0:07:44", "throughput": 4635.95, "total_tokens": 40521856} {"current_steps": 40285, "total_steps": 42420, "loss": 0.076, "lr": 3.851833661821791e-07, "epoch": 18.993399339933994, "percentage": 94.97, "elapsed_time": "2:25:41", "remaining_time": "0:07:43", "throughput": 4635.98, "total_tokens": 40527104} {"current_steps": 40290, "total_steps": 42420, "loss": 0.0429, "lr": 3.8338680174392906e-07, "epoch": 18.995756718528995, "percentage": 94.98, "elapsed_time": "2:25:43", "remaining_time": "0:07:42", "throughput": 4636.03, "total_tokens": 40532960} {"current_steps": 40295, "total_steps": 42420, "loss": 0.0632, "lr": 3.815944044803288e-07, "epoch": 18.998114097124, "percentage": 94.99, "elapsed_time": "2:25:44", "remaining_time": "0:07:41", "throughput": 4636.07, "total_tokens": 40538112} {"current_steps": 40299, "total_steps": 42420, "eval_loss": 0.15307621657848358, "epoch": 19.0, "percentage": 95.0, "elapsed_time": "2:26:00", "remaining_time": "0:07:41", "throughput": 4627.95, "total_tokens": 40541312} {"current_steps": 40300, "total_steps": 42420, "loss": 0.1769, "lr": 3.7980617469479953e-07, "epoch": 19.000471475719, "percentage": 95.0, "elapsed_time": "2:26:01", "remaining_time": "0:07:40", "throughput": 4627.07, "total_tokens": 40542240} {"current_steps": 40305, "total_steps": 42420, "loss": 0.1543, "lr": 3.780221126900574e-07, "epoch": 19.002828854314004, "percentage": 95.01, "elapsed_time": "2:26:02", "remaining_time": "0:07:39", "throughput": 4627.04, "total_tokens": 40546560} {"current_steps": 40310, "total_steps": 42420, "loss": 0.0701, "lr": 3.762422187681136e-07, "epoch": 19.005186232909004, "percentage": 95.03, "elapsed_time": "2:26:04", "remaining_time": "0:07:38", "throughput": 4627.06, "total_tokens": 40551680} {"current_steps": 40315, "total_steps": 42420, "loss": 0.1493, "lr": 3.744664932302744e-07, "epoch": 19.00754361150401, "percentage": 95.04, "elapsed_time": "2:26:05", "remaining_time": "0:07:37", "throughput": 4627.05, "total_tokens": 40556544} {"current_steps": 40320, "total_steps": 42420, "loss": 0.112, "lr": 3.7269493637714094e-07, "epoch": 19.00990099009901, "percentage": 95.05, "elapsed_time": "2:26:06", "remaining_time": "0:07:36", "throughput": 4627.07, "total_tokens": 40561440} {"current_steps": 40325, "total_steps": 42420, "loss": 0.0449, "lr": 3.709275485086039e-07, "epoch": 19.012258368694013, "percentage": 95.06, "elapsed_time": "2:26:07", "remaining_time": "0:07:35", "throughput": 4627.06, "total_tokens": 40566048} {"current_steps": 40330, "total_steps": 42420, "loss": 0.0798, "lr": 3.691643299238573e-07, "epoch": 19.014615747289014, "percentage": 95.07, "elapsed_time": "2:26:08", "remaining_time": "0:07:34", "throughput": 4627.06, "total_tokens": 40570432} {"current_steps": 40335, "total_steps": 42420, "loss": 0.139, "lr": 3.674052809213818e-07, "epoch": 19.016973125884018, "percentage": 95.08, "elapsed_time": "2:26:08", "remaining_time": "0:07:33", "throughput": 4627.03, "total_tokens": 40574432} {"current_steps": 40340, "total_steps": 42420, "loss": 0.0067, "lr": 3.656504017989587e-07, "epoch": 19.01933050447902, "percentage": 95.1, "elapsed_time": "2:26:09", "remaining_time": "0:07:32", "throughput": 4627.05, "total_tokens": 40579040} {"current_steps": 40345, "total_steps": 42420, "loss": 0.0121, "lr": 3.6389969285365036e-07, "epoch": 19.021687883074023, "percentage": 95.11, "elapsed_time": "2:26:11", "remaining_time": "0:07:31", "throughput": 4627.08, "total_tokens": 40584672} {"current_steps": 40350, "total_steps": 42420, "loss": 0.1155, "lr": 3.6215315438182795e-07, "epoch": 19.024045261669023, "percentage": 95.12, "elapsed_time": "2:26:12", "remaining_time": "0:07:30", "throughput": 4627.11, "total_tokens": 40590208} {"current_steps": 40355, "total_steps": 42420, "loss": 0.0943, "lr": 3.604107866791495e-07, "epoch": 19.026402640264028, "percentage": 95.13, "elapsed_time": "2:26:13", "remaining_time": "0:07:28", "throughput": 4627.18, "total_tokens": 40597152} {"current_steps": 40360, "total_steps": 42420, "loss": 0.0741, "lr": 3.5867259004056795e-07, "epoch": 19.02876001885903, "percentage": 95.14, "elapsed_time": "2:26:14", "remaining_time": "0:07:27", "throughput": 4627.22, "total_tokens": 40602656} {"current_steps": 40365, "total_steps": 42420, "loss": 0.0814, "lr": 3.569385647603313e-07, "epoch": 19.031117397454032, "percentage": 95.16, "elapsed_time": "2:26:15", "remaining_time": "0:07:26", "throughput": 4627.22, "total_tokens": 40607008} {"current_steps": 40370, "total_steps": 42420, "loss": 0.0178, "lr": 3.5520871113197964e-07, "epoch": 19.033474776049033, "percentage": 95.17, "elapsed_time": "2:26:16", "remaining_time": "0:07:25", "throughput": 4627.24, "total_tokens": 40611328} {"current_steps": 40375, "total_steps": 42420, "loss": 0.2212, "lr": 3.5348302944834824e-07, "epoch": 19.035832154644037, "percentage": 95.18, "elapsed_time": "2:26:17", "remaining_time": "0:07:24", "throughput": 4627.3, "total_tokens": 40618432} {"current_steps": 40380, "total_steps": 42420, "loss": 0.0117, "lr": 3.5176152000157006e-07, "epoch": 19.038189533239038, "percentage": 95.19, "elapsed_time": "2:26:18", "remaining_time": "0:07:23", "throughput": 4627.34, "total_tokens": 40623296} {"current_steps": 40385, "total_steps": 42420, "loss": 0.2193, "lr": 3.500441830830592e-07, "epoch": 19.040546911834042, "percentage": 95.2, "elapsed_time": "2:26:20", "remaining_time": "0:07:22", "throughput": 4627.36, "total_tokens": 40629184} {"current_steps": 40390, "total_steps": 42420, "loss": 0.0175, "lr": 3.4833101898353594e-07, "epoch": 19.042904290429043, "percentage": 95.21, "elapsed_time": "2:26:21", "remaining_time": "0:07:21", "throughput": 4627.38, "total_tokens": 40634112} {"current_steps": 40395, "total_steps": 42420, "loss": 0.0117, "lr": 3.4662202799300993e-07, "epoch": 19.045261669024047, "percentage": 95.23, "elapsed_time": "2:26:22", "remaining_time": "0:07:20", "throughput": 4627.43, "total_tokens": 40640448} {"current_steps": 40400, "total_steps": 42420, "loss": 0.0238, "lr": 3.4491721040078305e-07, "epoch": 19.047619047619047, "percentage": 95.24, "elapsed_time": "2:26:23", "remaining_time": "0:07:19", "throughput": 4627.44, "total_tokens": 40644992} {"current_steps": 40405, "total_steps": 42420, "loss": 0.1355, "lr": 3.432165664954551e-07, "epoch": 19.04997642621405, "percentage": 95.25, "elapsed_time": "2:26:24", "remaining_time": "0:07:18", "throughput": 4627.47, "total_tokens": 40650016} {"current_steps": 40410, "total_steps": 42420, "loss": 0.1723, "lr": 3.4152009656491235e-07, "epoch": 19.052333804809052, "percentage": 95.26, "elapsed_time": "2:26:25", "remaining_time": "0:07:16", "throughput": 4627.49, "total_tokens": 40654976} {"current_steps": 40415, "total_steps": 42420, "loss": 0.0887, "lr": 3.398278008963418e-07, "epoch": 19.054691183404056, "percentage": 95.27, "elapsed_time": "2:26:26", "remaining_time": "0:07:15", "throughput": 4627.51, "total_tokens": 40659296} {"current_steps": 40420, "total_steps": 42420, "loss": 0.1047, "lr": 3.3813967977621986e-07, "epoch": 19.057048561999057, "percentage": 95.29, "elapsed_time": "2:26:27", "remaining_time": "0:07:14", "throughput": 4627.56, "total_tokens": 40665504} {"current_steps": 40425, "total_steps": 42420, "loss": 0.0933, "lr": 3.3645573349031234e-07, "epoch": 19.059405940594058, "percentage": 95.3, "elapsed_time": "2:26:28", "remaining_time": "0:07:13", "throughput": 4627.57, "total_tokens": 40670560} {"current_steps": 40430, "total_steps": 42420, "loss": 0.2101, "lr": 3.3477596232368845e-07, "epoch": 19.061763319189062, "percentage": 95.31, "elapsed_time": "2:26:29", "remaining_time": "0:07:12", "throughput": 4627.59, "total_tokens": 40674816} {"current_steps": 40435, "total_steps": 42420, "loss": 0.0504, "lr": 3.3310036656070134e-07, "epoch": 19.064120697784062, "percentage": 95.32, "elapsed_time": "2:26:30", "remaining_time": "0:07:11", "throughput": 4627.62, "total_tokens": 40679520} {"current_steps": 40440, "total_steps": 42420, "loss": 0.1672, "lr": 3.314289464850018e-07, "epoch": 19.066478076379067, "percentage": 95.33, "elapsed_time": "2:26:31", "remaining_time": "0:07:10", "throughput": 4627.63, "total_tokens": 40683712} {"current_steps": 40445, "total_steps": 42420, "loss": 0.1064, "lr": 3.2976170237953295e-07, "epoch": 19.068835454974067, "percentage": 95.34, "elapsed_time": "2:26:32", "remaining_time": "0:07:09", "throughput": 4627.66, "total_tokens": 40689344} {"current_steps": 40450, "total_steps": 42420, "loss": 0.1711, "lr": 3.28098634526533e-07, "epoch": 19.07119283356907, "percentage": 95.36, "elapsed_time": "2:26:33", "remaining_time": "0:07:08", "throughput": 4627.68, "total_tokens": 40694240} {"current_steps": 40455, "total_steps": 42420, "loss": 0.0409, "lr": 3.264397432075267e-07, "epoch": 19.073550212164072, "percentage": 95.37, "elapsed_time": "2:26:34", "remaining_time": "0:07:07", "throughput": 4627.72, "total_tokens": 40699616} {"current_steps": 40460, "total_steps": 42420, "loss": 0.0365, "lr": 3.247850287033422e-07, "epoch": 19.075907590759076, "percentage": 95.38, "elapsed_time": "2:26:35", "remaining_time": "0:07:06", "throughput": 4627.75, "total_tokens": 40705344} {"current_steps": 40465, "total_steps": 42420, "loss": 0.075, "lr": 3.2313449129408867e-07, "epoch": 19.078264969354077, "percentage": 95.39, "elapsed_time": "2:26:36", "remaining_time": "0:07:05", "throughput": 4627.77, "total_tokens": 40710112} {"current_steps": 40470, "total_steps": 42420, "loss": 0.0659, "lr": 3.214881312591761e-07, "epoch": 19.08062234794908, "percentage": 95.4, "elapsed_time": "2:26:37", "remaining_time": "0:07:03", "throughput": 4627.79, "total_tokens": 40714944} {"current_steps": 40475, "total_steps": 42420, "loss": 0.1025, "lr": 3.1984594887730645e-07, "epoch": 19.08297972654408, "percentage": 95.41, "elapsed_time": "2:26:38", "remaining_time": "0:07:02", "throughput": 4627.82, "total_tokens": 40720000} {"current_steps": 40480, "total_steps": 42420, "loss": 0.1574, "lr": 3.182079444264713e-07, "epoch": 19.085337105139086, "percentage": 95.43, "elapsed_time": "2:26:40", "remaining_time": "0:07:01", "throughput": 4627.86, "total_tokens": 40727136} {"current_steps": 40485, "total_steps": 42420, "loss": 0.0957, "lr": 3.165741181839571e-07, "epoch": 19.087694483734087, "percentage": 95.44, "elapsed_time": "2:26:41", "remaining_time": "0:07:00", "throughput": 4627.86, "total_tokens": 40731520} {"current_steps": 40490, "total_steps": 42420, "loss": 0.0815, "lr": 3.1494447042634546e-07, "epoch": 19.09005186232909, "percentage": 95.45, "elapsed_time": "2:26:42", "remaining_time": "0:06:59", "throughput": 4627.89, "total_tokens": 40736672} {"current_steps": 40495, "total_steps": 42420, "loss": 0.1372, "lr": 3.133190014295073e-07, "epoch": 19.09240924092409, "percentage": 95.46, "elapsed_time": "2:26:43", "remaining_time": "0:06:58", "throughput": 4627.92, "total_tokens": 40741664} {"current_steps": 40500, "total_steps": 42420, "loss": 0.1499, "lr": 3.116977114686059e-07, "epoch": 19.094766619519095, "percentage": 95.47, "elapsed_time": "2:26:44", "remaining_time": "0:06:57", "throughput": 4627.92, "total_tokens": 40746240} {"current_steps": 40505, "total_steps": 42420, "loss": 0.0476, "lr": 3.100806008180995e-07, "epoch": 19.097123998114096, "percentage": 95.49, "elapsed_time": "2:26:45", "remaining_time": "0:06:56", "throughput": 4627.95, "total_tokens": 40751776} {"current_steps": 40510, "total_steps": 42420, "loss": 0.0811, "lr": 3.084676697517358e-07, "epoch": 19.0994813767091, "percentage": 95.5, "elapsed_time": "2:26:46", "remaining_time": "0:06:55", "throughput": 4627.97, "total_tokens": 40757024} {"current_steps": 40515, "total_steps": 42420, "loss": 0.109, "lr": 3.0685891854255745e-07, "epoch": 19.1018387553041, "percentage": 95.51, "elapsed_time": "2:26:47", "remaining_time": "0:06:54", "throughput": 4627.98, "total_tokens": 40762592} {"current_steps": 40520, "total_steps": 42420, "loss": 0.016, "lr": 3.0525434746289663e-07, "epoch": 19.104196133899105, "percentage": 95.52, "elapsed_time": "2:26:48", "remaining_time": "0:06:53", "throughput": 4627.99, "total_tokens": 40767264} {"current_steps": 40525, "total_steps": 42420, "loss": 0.1039, "lr": 3.0365395678438327e-07, "epoch": 19.106553512494106, "percentage": 95.53, "elapsed_time": "2:26:49", "remaining_time": "0:06:51", "throughput": 4628.0, "total_tokens": 40772256} {"current_steps": 40530, "total_steps": 42420, "loss": 0.0175, "lr": 3.02057746777934e-07, "epoch": 19.10891089108911, "percentage": 95.54, "elapsed_time": "2:26:51", "remaining_time": "0:06:50", "throughput": 4628.03, "total_tokens": 40777888} {"current_steps": 40535, "total_steps": 42420, "loss": 0.0827, "lr": 3.0046571771376043e-07, "epoch": 19.11126826968411, "percentage": 95.56, "elapsed_time": "2:26:52", "remaining_time": "0:06:49", "throughput": 4628.07, "total_tokens": 40783200} {"current_steps": 40540, "total_steps": 42420, "loss": 0.0355, "lr": 2.9887786986136923e-07, "epoch": 19.113625648279115, "percentage": 95.57, "elapsed_time": "2:26:53", "remaining_time": "0:06:48", "throughput": 4628.09, "total_tokens": 40788704} {"current_steps": 40545, "total_steps": 42420, "loss": 0.0449, "lr": 2.9729420348955093e-07, "epoch": 19.115983026874115, "percentage": 95.58, "elapsed_time": "2:26:54", "remaining_time": "0:06:47", "throughput": 4628.1, "total_tokens": 40793824} {"current_steps": 40550, "total_steps": 42420, "loss": 0.0888, "lr": 2.9571471886639946e-07, "epoch": 19.11834040546912, "percentage": 95.59, "elapsed_time": "2:26:55", "remaining_time": "0:06:46", "throughput": 4628.14, "total_tokens": 40799168} {"current_steps": 40555, "total_steps": 42420, "loss": 0.1884, "lr": 2.9413941625928696e-07, "epoch": 19.12069778406412, "percentage": 95.6, "elapsed_time": "2:26:56", "remaining_time": "0:06:45", "throughput": 4628.16, "total_tokens": 40804320} {"current_steps": 40560, "total_steps": 42420, "loss": 0.1341, "lr": 2.925682959348919e-07, "epoch": 19.123055162659124, "percentage": 95.62, "elapsed_time": "2:26:57", "remaining_time": "0:06:44", "throughput": 4628.18, "total_tokens": 40808864} {"current_steps": 40565, "total_steps": 42420, "loss": 0.0189, "lr": 2.910013581591764e-07, "epoch": 19.125412541254125, "percentage": 95.63, "elapsed_time": "2:26:58", "remaining_time": "0:06:43", "throughput": 4628.2, "total_tokens": 40813504} {"current_steps": 40570, "total_steps": 42420, "loss": 0.1071, "lr": 2.8943860319739504e-07, "epoch": 19.12776991984913, "percentage": 95.64, "elapsed_time": "2:26:59", "remaining_time": "0:06:42", "throughput": 4628.23, "total_tokens": 40819232} {"current_steps": 40575, "total_steps": 42420, "loss": 0.0126, "lr": 2.8788003131409444e-07, "epoch": 19.13012729844413, "percentage": 95.65, "elapsed_time": "2:27:00", "remaining_time": "0:06:41", "throughput": 4628.26, "total_tokens": 40824192} {"current_steps": 40580, "total_steps": 42420, "loss": 0.0622, "lr": 2.8632564277311923e-07, "epoch": 19.132484677039134, "percentage": 95.66, "elapsed_time": "2:27:01", "remaining_time": "0:06:39", "throughput": 4628.24, "total_tokens": 40828224} {"current_steps": 40585, "total_steps": 42420, "loss": 0.025, "lr": 2.847754378376005e-07, "epoch": 19.134842055634135, "percentage": 95.67, "elapsed_time": "2:27:02", "remaining_time": "0:06:38", "throughput": 4628.27, "total_tokens": 40833152} {"current_steps": 40590, "total_steps": 42420, "loss": 0.1669, "lr": 2.8322941676995615e-07, "epoch": 19.13719943422914, "percentage": 95.69, "elapsed_time": "2:27:03", "remaining_time": "0:06:37", "throughput": 4628.28, "total_tokens": 40838208} {"current_steps": 40595, "total_steps": 42420, "loss": 0.2121, "lr": 2.816875798319074e-07, "epoch": 19.13955681282414, "percentage": 95.7, "elapsed_time": "2:27:05", "remaining_time": "0:06:36", "throughput": 4628.32, "total_tokens": 40845152} {"current_steps": 40600, "total_steps": 42420, "loss": 0.0517, "lr": 2.8014992728445656e-07, "epoch": 19.141914191419144, "percentage": 95.71, "elapsed_time": "2:27:06", "remaining_time": "0:06:35", "throughput": 4628.33, "total_tokens": 40849760} {"current_steps": 40605, "total_steps": 42420, "loss": 0.0234, "lr": 2.786164593879037e-07, "epoch": 19.144271570014144, "percentage": 95.72, "elapsed_time": "2:27:07", "remaining_time": "0:06:34", "throughput": 4628.32, "total_tokens": 40854336} {"current_steps": 40610, "total_steps": 42420, "loss": 0.0266, "lr": 2.7708717640183844e-07, "epoch": 19.14662894860915, "percentage": 95.73, "elapsed_time": "2:27:08", "remaining_time": "0:06:33", "throughput": 4628.34, "total_tokens": 40859264} {"current_steps": 40615, "total_steps": 42420, "loss": 0.0984, "lr": 2.755620785851426e-07, "epoch": 19.14898632720415, "percentage": 95.74, "elapsed_time": "2:27:08", "remaining_time": "0:06:32", "throughput": 4628.35, "total_tokens": 40863168} {"current_steps": 40620, "total_steps": 42420, "loss": 0.1369, "lr": 2.74041166195993e-07, "epoch": 19.15134370579915, "percentage": 95.76, "elapsed_time": "2:27:09", "remaining_time": "0:06:31", "throughput": 4628.35, "total_tokens": 40867360} {"current_steps": 40625, "total_steps": 42420, "loss": 0.0575, "lr": 2.7252443949185024e-07, "epoch": 19.153701084394154, "percentage": 95.77, "elapsed_time": "2:27:10", "remaining_time": "0:06:30", "throughput": 4628.35, "total_tokens": 40871968} {"current_steps": 40630, "total_steps": 42420, "loss": 0.0675, "lr": 2.7101189872947017e-07, "epoch": 19.156058462989154, "percentage": 95.78, "elapsed_time": "2:27:11", "remaining_time": "0:06:29", "throughput": 4628.37, "total_tokens": 40877312} {"current_steps": 40635, "total_steps": 42420, "loss": 0.1266, "lr": 2.6950354416490076e-07, "epoch": 19.15841584158416, "percentage": 95.79, "elapsed_time": "2:27:12", "remaining_time": "0:06:28", "throughput": 4628.39, "total_tokens": 40882336} {"current_steps": 40640, "total_steps": 42420, "loss": 0.0732, "lr": 2.679993760534821e-07, "epoch": 19.16077322017916, "percentage": 95.8, "elapsed_time": "2:27:13", "remaining_time": "0:06:26", "throughput": 4628.41, "total_tokens": 40887072} {"current_steps": 40645, "total_steps": 42420, "loss": 0.09, "lr": 2.66499394649844e-07, "epoch": 19.163130598774163, "percentage": 95.82, "elapsed_time": "2:27:14", "remaining_time": "0:06:25", "throughput": 4628.41, "total_tokens": 40891680} {"current_steps": 40650, "total_steps": 42420, "loss": 0.0107, "lr": 2.650036002079054e-07, "epoch": 19.165487977369164, "percentage": 95.83, "elapsed_time": "2:27:15", "remaining_time": "0:06:24", "throughput": 4628.4, "total_tokens": 40895744} {"current_steps": 40655, "total_steps": 42420, "loss": 0.0977, "lr": 2.6351199298088325e-07, "epoch": 19.167845355964168, "percentage": 95.84, "elapsed_time": "2:27:16", "remaining_time": "0:06:23", "throughput": 4628.43, "total_tokens": 40900512} {"current_steps": 40660, "total_steps": 42420, "loss": 0.1371, "lr": 2.620245732212784e-07, "epoch": 19.17020273455917, "percentage": 95.85, "elapsed_time": "2:27:17", "remaining_time": "0:06:22", "throughput": 4628.45, "total_tokens": 40905664} {"current_steps": 40665, "total_steps": 42420, "loss": 0.3984, "lr": 2.6054134118088656e-07, "epoch": 19.172560113154173, "percentage": 95.86, "elapsed_time": "2:27:18", "remaining_time": "0:06:21", "throughput": 4628.46, "total_tokens": 40910176} {"current_steps": 40670, "total_steps": 42420, "loss": 0.2394, "lr": 2.590622971107931e-07, "epoch": 19.174917491749174, "percentage": 95.87, "elapsed_time": "2:27:19", "remaining_time": "0:06:20", "throughput": 4628.48, "total_tokens": 40915232} {"current_steps": 40675, "total_steps": 42420, "loss": 0.1941, "lr": 2.575874412613782e-07, "epoch": 19.177274870344178, "percentage": 95.89, "elapsed_time": "2:27:21", "remaining_time": "0:06:19", "throughput": 4628.53, "total_tokens": 40922592} {"current_steps": 40680, "total_steps": 42420, "loss": 0.1501, "lr": 2.561167738823034e-07, "epoch": 19.17963224893918, "percentage": 95.9, "elapsed_time": "2:27:22", "remaining_time": "0:06:18", "throughput": 4628.55, "total_tokens": 40928096} {"current_steps": 40685, "total_steps": 42420, "loss": 0.0433, "lr": 2.5465029522253327e-07, "epoch": 19.181989627534183, "percentage": 95.91, "elapsed_time": "2:27:23", "remaining_time": "0:06:17", "throughput": 4628.6, "total_tokens": 40934912} {"current_steps": 40690, "total_steps": 42420, "loss": 0.0623, "lr": 2.531880055303165e-07, "epoch": 19.184347006129183, "percentage": 95.92, "elapsed_time": "2:27:24", "remaining_time": "0:06:16", "throughput": 4628.58, "total_tokens": 40939680} {"current_steps": 40695, "total_steps": 42420, "loss": 0.0276, "lr": 2.5172990505319406e-07, "epoch": 19.186704384724187, "percentage": 95.93, "elapsed_time": "2:27:25", "remaining_time": "0:06:14", "throughput": 4628.57, "total_tokens": 40943744} {"current_steps": 40700, "total_steps": 42420, "loss": 0.1037, "lr": 2.502759940379934e-07, "epoch": 19.189061763319188, "percentage": 95.95, "elapsed_time": "2:27:27", "remaining_time": "0:06:13", "throughput": 4628.61, "total_tokens": 40949344} {"current_steps": 40705, "total_steps": 42420, "loss": 0.1412, "lr": 2.488262727308427e-07, "epoch": 19.191419141914192, "percentage": 95.96, "elapsed_time": "2:27:27", "remaining_time": "0:06:12", "throughput": 4628.63, "total_tokens": 40954048} {"current_steps": 40710, "total_steps": 42420, "loss": 0.2777, "lr": 2.4738074137715394e-07, "epoch": 19.193776520509193, "percentage": 95.97, "elapsed_time": "2:27:29", "remaining_time": "0:06:11", "throughput": 4628.63, "total_tokens": 40958848} {"current_steps": 40715, "total_steps": 42420, "loss": 0.1787, "lr": 2.459394002216314e-07, "epoch": 19.196133899104197, "percentage": 95.98, "elapsed_time": "2:27:29", "remaining_time": "0:06:10", "throughput": 4628.64, "total_tokens": 40963296} {"current_steps": 40720, "total_steps": 42420, "loss": 0.0368, "lr": 2.4450224950826604e-07, "epoch": 19.198491277699198, "percentage": 95.99, "elapsed_time": "2:27:31", "remaining_time": "0:06:09", "throughput": 4628.64, "total_tokens": 40968128} {"current_steps": 40725, "total_steps": 42420, "loss": 0.1523, "lr": 2.430692894803438e-07, "epoch": 19.200848656294202, "percentage": 96.0, "elapsed_time": "2:27:32", "remaining_time": "0:06:08", "throughput": 4628.62, "total_tokens": 40972832} {"current_steps": 40730, "total_steps": 42420, "loss": 0.1449, "lr": 2.416405203804456e-07, "epoch": 19.203206034889202, "percentage": 96.02, "elapsed_time": "2:27:33", "remaining_time": "0:06:07", "throughput": 4628.67, "total_tokens": 40978976} {"current_steps": 40735, "total_steps": 42420, "loss": 0.0396, "lr": 2.402159424504308e-07, "epoch": 19.205563413484207, "percentage": 96.03, "elapsed_time": "2:27:34", "remaining_time": "0:06:06", "throughput": 4628.67, "total_tokens": 40982912} {"current_steps": 40740, "total_steps": 42420, "loss": 0.0957, "lr": 2.38795555931462e-07, "epoch": 19.207920792079207, "percentage": 96.04, "elapsed_time": "2:27:35", "remaining_time": "0:06:05", "throughput": 4628.69, "total_tokens": 40988160} {"current_steps": 40745, "total_steps": 42420, "loss": 0.081, "lr": 2.3737936106398295e-07, "epoch": 19.21027817067421, "percentage": 96.05, "elapsed_time": "2:27:36", "remaining_time": "0:06:04", "throughput": 4628.71, "total_tokens": 40993184} {"current_steps": 40750, "total_steps": 42420, "loss": 0.1504, "lr": 2.359673580877325e-07, "epoch": 19.212635549269212, "percentage": 96.06, "elapsed_time": "2:27:37", "remaining_time": "0:06:02", "throughput": 4628.71, "total_tokens": 40997600} {"current_steps": 40755, "total_steps": 42420, "loss": 0.2533, "lr": 2.3455954724174167e-07, "epoch": 19.214992927864216, "percentage": 96.07, "elapsed_time": "2:27:38", "remaining_time": "0:06:01", "throughput": 4628.72, "total_tokens": 41002528} {"current_steps": 40760, "total_steps": 42420, "loss": 0.0818, "lr": 2.3315592876432535e-07, "epoch": 19.217350306459217, "percentage": 96.09, "elapsed_time": "2:27:39", "remaining_time": "0:06:00", "throughput": 4628.73, "total_tokens": 41007328} {"current_steps": 40765, "total_steps": 42420, "loss": 0.146, "lr": 2.3175650289309348e-07, "epoch": 19.21970768505422, "percentage": 96.1, "elapsed_time": "2:27:40", "remaining_time": "0:05:59", "throughput": 4628.73, "total_tokens": 41011584} {"current_steps": 40770, "total_steps": 42420, "loss": 0.1495, "lr": 2.3036126986494267e-07, "epoch": 19.22206506364922, "percentage": 96.11, "elapsed_time": "2:27:41", "remaining_time": "0:05:58", "throughput": 4628.73, "total_tokens": 41016544} {"current_steps": 40775, "total_steps": 42420, "loss": 0.0501, "lr": 2.2897022991606455e-07, "epoch": 19.224422442244226, "percentage": 96.12, "elapsed_time": "2:27:42", "remaining_time": "0:05:57", "throughput": 4628.72, "total_tokens": 41021056} {"current_steps": 40780, "total_steps": 42420, "loss": 0.1426, "lr": 2.2758338328194018e-07, "epoch": 19.226779820839226, "percentage": 96.13, "elapsed_time": "2:27:43", "remaining_time": "0:05:56", "throughput": 4628.72, "total_tokens": 41025504} {"current_steps": 40785, "total_steps": 42420, "loss": 0.0509, "lr": 2.2620073019733734e-07, "epoch": 19.22913719943423, "percentage": 96.15, "elapsed_time": "2:27:44", "remaining_time": "0:05:55", "throughput": 4628.75, "total_tokens": 41030944} {"current_steps": 40790, "total_steps": 42420, "loss": 0.0318, "lr": 2.2482227089631324e-07, "epoch": 19.23149457802923, "percentage": 96.16, "elapsed_time": "2:27:45", "remaining_time": "0:05:54", "throughput": 4628.77, "total_tokens": 41037408} {"current_steps": 40795, "total_steps": 42420, "loss": 0.1292, "lr": 2.234480056122229e-07, "epoch": 19.233851956624235, "percentage": 96.17, "elapsed_time": "2:27:46", "remaining_time": "0:05:53", "throughput": 4628.77, "total_tokens": 41041824} {"current_steps": 40800, "total_steps": 42420, "loss": 0.1273, "lr": 2.2207793457770242e-07, "epoch": 19.236209335219236, "percentage": 96.18, "elapsed_time": "2:27:47", "remaining_time": "0:05:52", "throughput": 4628.77, "total_tokens": 41046080} {"current_steps": 40805, "total_steps": 42420, "loss": 0.0581, "lr": 2.2071205802468299e-07, "epoch": 19.23856671381424, "percentage": 96.19, "elapsed_time": "2:27:48", "remaining_time": "0:05:51", "throughput": 4628.79, "total_tokens": 41051200} {"current_steps": 40810, "total_steps": 42420, "loss": 0.1902, "lr": 2.1935037618438237e-07, "epoch": 19.24092409240924, "percentage": 96.2, "elapsed_time": "2:27:49", "remaining_time": "0:05:49", "throughput": 4628.83, "total_tokens": 41057696} {"current_steps": 40815, "total_steps": 42420, "loss": 0.032, "lr": 2.1799288928731064e-07, "epoch": 19.243281471004245, "percentage": 96.22, "elapsed_time": "2:27:50", "remaining_time": "0:05:48", "throughput": 4628.84, "total_tokens": 41062048} {"current_steps": 40820, "total_steps": 42420, "loss": 0.3194, "lr": 2.1663959756327011e-07, "epoch": 19.245638849599246, "percentage": 96.23, "elapsed_time": "2:27:51", "remaining_time": "0:05:47", "throughput": 4628.88, "total_tokens": 41067104} {"current_steps": 40825, "total_steps": 42420, "loss": 0.0608, "lr": 2.1529050124134699e-07, "epoch": 19.247996228194246, "percentage": 96.24, "elapsed_time": "2:27:52", "remaining_time": "0:05:46", "throughput": 4628.84, "total_tokens": 41071392} {"current_steps": 40830, "total_steps": 42420, "loss": 0.2536, "lr": 2.139456005499224e-07, "epoch": 19.25035360678925, "percentage": 96.25, "elapsed_time": "2:27:53", "remaining_time": "0:05:45", "throughput": 4628.86, "total_tokens": 41076288} {"current_steps": 40835, "total_steps": 42420, "loss": 0.0556, "lr": 2.126048957166671e-07, "epoch": 19.25271098538425, "percentage": 96.26, "elapsed_time": "2:27:54", "remaining_time": "0:05:44", "throughput": 4628.86, "total_tokens": 41081056} {"current_steps": 40840, "total_steps": 42420, "loss": 0.2117, "lr": 2.112683869685328e-07, "epoch": 19.255068363979255, "percentage": 96.28, "elapsed_time": "2:27:56", "remaining_time": "0:05:43", "throughput": 4628.88, "total_tokens": 41086080} {"current_steps": 40845, "total_steps": 42420, "loss": 0.1554, "lr": 2.0993607453177465e-07, "epoch": 19.257425742574256, "percentage": 96.29, "elapsed_time": "2:27:57", "remaining_time": "0:05:42", "throughput": 4628.91, "total_tokens": 41091616} {"current_steps": 40850, "total_steps": 42420, "loss": 0.0161, "lr": 2.0860795863192617e-07, "epoch": 19.25978312116926, "percentage": 96.3, "elapsed_time": "2:27:58", "remaining_time": "0:05:41", "throughput": 4628.93, "total_tokens": 41096192} {"current_steps": 40855, "total_steps": 42420, "loss": 0.2479, "lr": 2.0728403949381582e-07, "epoch": 19.26214049976426, "percentage": 96.31, "elapsed_time": "2:27:59", "remaining_time": "0:05:40", "throughput": 4628.92, "total_tokens": 41100384} {"current_steps": 40860, "total_steps": 42420, "loss": 0.143, "lr": 2.0596431734156153e-07, "epoch": 19.264497878359265, "percentage": 96.32, "elapsed_time": "2:28:00", "remaining_time": "0:05:39", "throughput": 4628.93, "total_tokens": 41105632} {"current_steps": 40865, "total_steps": 42420, "loss": 0.0435, "lr": 2.046487923985707e-07, "epoch": 19.266855256954265, "percentage": 96.33, "elapsed_time": "2:28:01", "remaining_time": "0:05:37", "throughput": 4628.95, "total_tokens": 41111040} {"current_steps": 40870, "total_steps": 42420, "loss": 0.0722, "lr": 2.0333746488753746e-07, "epoch": 19.26921263554927, "percentage": 96.35, "elapsed_time": "2:28:02", "remaining_time": "0:05:36", "throughput": 4628.98, "total_tokens": 41115968} {"current_steps": 40875, "total_steps": 42420, "loss": 0.1785, "lr": 2.020303350304481e-07, "epoch": 19.27157001414427, "percentage": 96.36, "elapsed_time": "2:28:04", "remaining_time": "0:05:35", "throughput": 4629.04, "total_tokens": 41124576} {"current_steps": 40880, "total_steps": 42420, "loss": 0.0423, "lr": 2.007274030485784e-07, "epoch": 19.273927392739274, "percentage": 96.37, "elapsed_time": "2:28:05", "remaining_time": "0:05:34", "throughput": 4629.05, "total_tokens": 41129952} {"current_steps": 40885, "total_steps": 42420, "loss": 0.1036, "lr": 1.994286691624908e-07, "epoch": 19.276284771334275, "percentage": 96.38, "elapsed_time": "2:28:06", "remaining_time": "0:05:33", "throughput": 4629.04, "total_tokens": 41134080} {"current_steps": 40890, "total_steps": 42420, "loss": 0.0623, "lr": 1.9813413359204003e-07, "epoch": 19.27864214992928, "percentage": 96.39, "elapsed_time": "2:28:07", "remaining_time": "0:05:32", "throughput": 4629.05, "total_tokens": 41138496} {"current_steps": 40895, "total_steps": 42420, "loss": 0.0723, "lr": 1.968437965563674e-07, "epoch": 19.28099952852428, "percentage": 96.4, "elapsed_time": "2:28:07", "remaining_time": "0:05:31", "throughput": 4629.06, "total_tokens": 41142944} {"current_steps": 40900, "total_steps": 42420, "loss": 0.1165, "lr": 1.9555765827390937e-07, "epoch": 19.283356907119284, "percentage": 96.42, "elapsed_time": "2:28:08", "remaining_time": "0:05:30", "throughput": 4629.05, "total_tokens": 41147168} {"current_steps": 40905, "total_steps": 42420, "loss": 0.0436, "lr": 1.9427571896238062e-07, "epoch": 19.285714285714285, "percentage": 96.43, "elapsed_time": "2:28:09", "remaining_time": "0:05:29", "throughput": 4629.06, "total_tokens": 41152384} {"current_steps": 40910, "total_steps": 42420, "loss": 0.0393, "lr": 1.9299797883879922e-07, "epoch": 19.28807166430929, "percentage": 96.44, "elapsed_time": "2:28:11", "remaining_time": "0:05:28", "throughput": 4629.1, "total_tokens": 41157504} {"current_steps": 40915, "total_steps": 42420, "loss": 0.1263, "lr": 1.9172443811945883e-07, "epoch": 19.29042904290429, "percentage": 96.45, "elapsed_time": "2:28:11", "remaining_time": "0:05:27", "throughput": 4629.08, "total_tokens": 41161664} {"current_steps": 40920, "total_steps": 42420, "loss": 0.0415, "lr": 1.904550970199509e-07, "epoch": 19.292786421499294, "percentage": 96.46, "elapsed_time": "2:28:12", "remaining_time": "0:05:25", "throughput": 4629.09, "total_tokens": 41166304} {"current_steps": 40925, "total_steps": 42420, "loss": 0.04, "lr": 1.8918995575515352e-07, "epoch": 19.295143800094294, "percentage": 96.48, "elapsed_time": "2:28:13", "remaining_time": "0:05:24", "throughput": 4629.1, "total_tokens": 41170816} {"current_steps": 40930, "total_steps": 42420, "loss": 0.0793, "lr": 1.879290145392343e-07, "epoch": 19.2975011786893, "percentage": 96.49, "elapsed_time": "2:28:14", "remaining_time": "0:05:23", "throughput": 4629.12, "total_tokens": 41175904} {"current_steps": 40935, "total_steps": 42420, "loss": 0.1983, "lr": 1.8667227358564464e-07, "epoch": 19.2998585572843, "percentage": 96.5, "elapsed_time": "2:28:16", "remaining_time": "0:05:22", "throughput": 4629.15, "total_tokens": 41182112} {"current_steps": 40940, "total_steps": 42420, "loss": 0.0501, "lr": 1.854197331071339e-07, "epoch": 19.302215935879303, "percentage": 96.51, "elapsed_time": "2:28:17", "remaining_time": "0:05:21", "throughput": 4629.18, "total_tokens": 41187200} {"current_steps": 40945, "total_steps": 42420, "loss": 0.2106, "lr": 1.841713933157352e-07, "epoch": 19.304573314474304, "percentage": 96.52, "elapsed_time": "2:28:18", "remaining_time": "0:05:20", "throughput": 4629.2, "total_tokens": 41192256} {"current_steps": 40950, "total_steps": 42420, "loss": 0.029, "lr": 1.8292725442277114e-07, "epoch": 19.306930693069308, "percentage": 96.53, "elapsed_time": "2:28:19", "remaining_time": "0:05:19", "throughput": 4629.2, "total_tokens": 41197120} {"current_steps": 40955, "total_steps": 42420, "loss": 0.1374, "lr": 1.8168731663885108e-07, "epoch": 19.30928807166431, "percentage": 96.55, "elapsed_time": "2:28:20", "remaining_time": "0:05:18", "throughput": 4629.21, "total_tokens": 41202016} {"current_steps": 40960, "total_steps": 42420, "loss": 0.3278, "lr": 1.804515801738793e-07, "epoch": 19.311645450259313, "percentage": 96.56, "elapsed_time": "2:28:21", "remaining_time": "0:05:17", "throughput": 4629.2, "total_tokens": 41206304} {"current_steps": 40965, "total_steps": 42420, "loss": 0.2318, "lr": 1.7922004523704407e-07, "epoch": 19.314002828854314, "percentage": 96.57, "elapsed_time": "2:28:22", "remaining_time": "0:05:16", "throughput": 4629.17, "total_tokens": 41210304} {"current_steps": 40970, "total_steps": 42420, "loss": 0.1904, "lr": 1.7799271203682022e-07, "epoch": 19.316360207449318, "percentage": 96.58, "elapsed_time": "2:28:23", "remaining_time": "0:05:15", "throughput": 4629.21, "total_tokens": 41215520} {"current_steps": 40975, "total_steps": 42420, "loss": 0.0779, "lr": 1.7676958078097772e-07, "epoch": 19.31871758604432, "percentage": 96.59, "elapsed_time": "2:28:24", "remaining_time": "0:05:14", "throughput": 4629.2, "total_tokens": 41220160} {"current_steps": 40980, "total_steps": 42420, "loss": 0.1231, "lr": 1.7555065167657036e-07, "epoch": 19.321074964639323, "percentage": 96.61, "elapsed_time": "2:28:25", "remaining_time": "0:05:12", "throughput": 4629.24, "total_tokens": 41225504} {"current_steps": 40985, "total_steps": 42420, "loss": 0.3679, "lr": 1.7433592492994143e-07, "epoch": 19.323432343234323, "percentage": 96.62, "elapsed_time": "2:28:26", "remaining_time": "0:05:11", "throughput": 4629.21, "total_tokens": 41229888} {"current_steps": 40990, "total_steps": 42420, "loss": 0.0813, "lr": 1.7312540074672646e-07, "epoch": 19.325789721829327, "percentage": 96.63, "elapsed_time": "2:28:27", "remaining_time": "0:05:10", "throughput": 4629.24, "total_tokens": 41234880} {"current_steps": 40995, "total_steps": 42420, "loss": 0.0495, "lr": 1.7191907933184203e-07, "epoch": 19.328147100424328, "percentage": 96.64, "elapsed_time": "2:28:28", "remaining_time": "0:05:09", "throughput": 4629.24, "total_tokens": 41239392} {"current_steps": 41000, "total_steps": 42420, "loss": 0.1059, "lr": 1.7071696088950262e-07, "epoch": 19.330504479019332, "percentage": 96.65, "elapsed_time": "2:28:29", "remaining_time": "0:05:08", "throughput": 4629.25, "total_tokens": 41244672} {"current_steps": 41005, "total_steps": 42420, "loss": 0.0744, "lr": 1.6951904562320653e-07, "epoch": 19.332861857614333, "percentage": 96.66, "elapsed_time": "2:28:30", "remaining_time": "0:05:07", "throughput": 4629.28, "total_tokens": 41249440} {"current_steps": 41010, "total_steps": 42420, "loss": 0.0585, "lr": 1.68325333735736e-07, "epoch": 19.335219236209337, "percentage": 96.68, "elapsed_time": "2:28:31", "remaining_time": "0:05:06", "throughput": 4629.3, "total_tokens": 41254944} {"current_steps": 41015, "total_steps": 42420, "loss": 0.1658, "lr": 1.6713582542916827e-07, "epoch": 19.337576614804338, "percentage": 96.69, "elapsed_time": "2:28:32", "remaining_time": "0:05:05", "throughput": 4629.34, "total_tokens": 41260416} {"current_steps": 41020, "total_steps": 42420, "loss": 0.0751, "lr": 1.6595052090486728e-07, "epoch": 19.33993399339934, "percentage": 96.7, "elapsed_time": "2:28:33", "remaining_time": "0:05:04", "throughput": 4629.36, "total_tokens": 41265216} {"current_steps": 41025, "total_steps": 42420, "loss": 0.2311, "lr": 1.6476942036348643e-07, "epoch": 19.342291371994342, "percentage": 96.71, "elapsed_time": "2:28:34", "remaining_time": "0:05:03", "throughput": 4629.38, "total_tokens": 41270048} {"current_steps": 41030, "total_steps": 42420, "loss": 0.0591, "lr": 1.6359252400496295e-07, "epoch": 19.344648750589343, "percentage": 96.72, "elapsed_time": "2:28:35", "remaining_time": "0:05:02", "throughput": 4629.4, "total_tokens": 41274944} {"current_steps": 41035, "total_steps": 42420, "loss": 0.0276, "lr": 1.624198320285264e-07, "epoch": 19.347006129184347, "percentage": 96.74, "elapsed_time": "2:28:36", "remaining_time": "0:05:00", "throughput": 4629.38, "total_tokens": 41278752} {"current_steps": 41040, "total_steps": 42420, "loss": 0.0639, "lr": 1.6125134463269576e-07, "epoch": 19.349363507779348, "percentage": 96.75, "elapsed_time": "2:28:37", "remaining_time": "0:04:59", "throughput": 4629.4, "total_tokens": 41283776} {"current_steps": 41045, "total_steps": 42420, "loss": 0.2, "lr": 1.6008706201527667e-07, "epoch": 19.351720886374352, "percentage": 96.76, "elapsed_time": "2:28:38", "remaining_time": "0:04:58", "throughput": 4629.41, "total_tokens": 41288896} {"current_steps": 41050, "total_steps": 42420, "loss": 0.2704, "lr": 1.5892698437335595e-07, "epoch": 19.354078264969353, "percentage": 96.77, "elapsed_time": "2:28:39", "remaining_time": "0:04:57", "throughput": 4629.43, "total_tokens": 41294048} {"current_steps": 41055, "total_steps": 42420, "loss": 0.181, "lr": 1.5777111190332096e-07, "epoch": 19.356435643564357, "percentage": 96.78, "elapsed_time": "2:28:41", "remaining_time": "0:04:56", "throughput": 4629.45, "total_tokens": 41299488} {"current_steps": 41060, "total_steps": 42420, "loss": 0.083, "lr": 1.5661944480084011e-07, "epoch": 19.358793022159357, "percentage": 96.79, "elapsed_time": "2:28:42", "remaining_time": "0:04:55", "throughput": 4629.49, "total_tokens": 41304928} {"current_steps": 41065, "total_steps": 42420, "loss": 0.0402, "lr": 1.5547198326087143e-07, "epoch": 19.36115040075436, "percentage": 96.81, "elapsed_time": "2:28:43", "remaining_time": "0:04:54", "throughput": 4629.51, "total_tokens": 41309600} {"current_steps": 41070, "total_steps": 42420, "loss": 0.0771, "lr": 1.5432872747765948e-07, "epoch": 19.363507779349362, "percentage": 96.82, "elapsed_time": "2:28:44", "remaining_time": "0:04:53", "throughput": 4629.5, "total_tokens": 41314208} {"current_steps": 41075, "total_steps": 42420, "loss": 0.1108, "lr": 1.5318967764473557e-07, "epoch": 19.365865157944366, "percentage": 96.83, "elapsed_time": "2:28:45", "remaining_time": "0:04:52", "throughput": 4629.53, "total_tokens": 41319200} {"current_steps": 41080, "total_steps": 42420, "loss": 0.0314, "lr": 1.5205483395492882e-07, "epoch": 19.368222536539367, "percentage": 96.84, "elapsed_time": "2:28:46", "remaining_time": "0:04:51", "throughput": 4629.57, "total_tokens": 41324928} {"current_steps": 41085, "total_steps": 42420, "loss": 0.0908, "lr": 1.5092419660034384e-07, "epoch": 19.37057991513437, "percentage": 96.85, "elapsed_time": "2:28:47", "remaining_time": "0:04:50", "throughput": 4629.57, "total_tokens": 41329024} {"current_steps": 41090, "total_steps": 42420, "loss": 0.1869, "lr": 1.4979776577237758e-07, "epoch": 19.372937293729372, "percentage": 96.86, "elapsed_time": "2:28:48", "remaining_time": "0:04:48", "throughput": 4629.59, "total_tokens": 41334368} {"current_steps": 41095, "total_steps": 42420, "loss": 0.0737, "lr": 1.4867554166171638e-07, "epoch": 19.375294672324376, "percentage": 96.88, "elapsed_time": "2:28:49", "remaining_time": "0:04:47", "throughput": 4629.59, "total_tokens": 41338560} {"current_steps": 41100, "total_steps": 42420, "loss": 0.1549, "lr": 1.4755752445833604e-07, "epoch": 19.377652050919377, "percentage": 96.89, "elapsed_time": "2:28:50", "remaining_time": "0:04:46", "throughput": 4629.58, "total_tokens": 41342720} {"current_steps": 41105, "total_steps": 42420, "loss": 0.1517, "lr": 1.4644371435149629e-07, "epoch": 19.38000942951438, "percentage": 96.9, "elapsed_time": "2:28:51", "remaining_time": "0:04:45", "throughput": 4629.6, "total_tokens": 41347488} {"current_steps": 41110, "total_steps": 42420, "loss": 0.2377, "lr": 1.453341115297435e-07, "epoch": 19.38236680810938, "percentage": 96.91, "elapsed_time": "2:28:52", "remaining_time": "0:04:44", "throughput": 4629.62, "total_tokens": 41352320} {"current_steps": 41115, "total_steps": 42420, "loss": 0.0963, "lr": 1.4422871618092194e-07, "epoch": 19.384724186704386, "percentage": 96.92, "elapsed_time": "2:28:53", "remaining_time": "0:04:43", "throughput": 4629.64, "total_tokens": 41357792} {"current_steps": 41120, "total_steps": 42420, "loss": 0.2354, "lr": 1.431275284921485e-07, "epoch": 19.387081565299386, "percentage": 96.94, "elapsed_time": "2:28:54", "remaining_time": "0:04:42", "throughput": 4629.65, "total_tokens": 41362240} {"current_steps": 41125, "total_steps": 42420, "loss": 0.0264, "lr": 1.4203054864984078e-07, "epoch": 19.38943894389439, "percentage": 96.95, "elapsed_time": "2:28:55", "remaining_time": "0:04:41", "throughput": 4629.67, "total_tokens": 41367936} {"current_steps": 41130, "total_steps": 42420, "loss": 0.1862, "lr": 1.4093777683969745e-07, "epoch": 19.39179632248939, "percentage": 96.96, "elapsed_time": "2:28:56", "remaining_time": "0:04:40", "throughput": 4629.7, "total_tokens": 41373888} {"current_steps": 41135, "total_steps": 42420, "loss": 0.1647, "lr": 1.3984921324670385e-07, "epoch": 19.394153701084395, "percentage": 96.97, "elapsed_time": "2:28:57", "remaining_time": "0:04:39", "throughput": 4629.71, "total_tokens": 41378240} {"current_steps": 41140, "total_steps": 42420, "loss": 0.0186, "lr": 1.387648580551376e-07, "epoch": 19.396511079679396, "percentage": 96.98, "elapsed_time": "2:28:58", "remaining_time": "0:04:38", "throughput": 4629.7, "total_tokens": 41382976} {"current_steps": 41145, "total_steps": 42420, "loss": 0.0914, "lr": 1.376847114485602e-07, "epoch": 19.3988684582744, "percentage": 96.99, "elapsed_time": "2:28:59", "remaining_time": "0:04:37", "throughput": 4629.75, "total_tokens": 41388960} {"current_steps": 41150, "total_steps": 42420, "loss": 0.0631, "lr": 1.3660877360982537e-07, "epoch": 19.4012258368694, "percentage": 97.01, "elapsed_time": "2:29:01", "remaining_time": "0:04:35", "throughput": 4629.79, "total_tokens": 41395040} {"current_steps": 41155, "total_steps": 42420, "loss": 0.0269, "lr": 1.355370447210652e-07, "epoch": 19.403583215464405, "percentage": 97.02, "elapsed_time": "2:29:01", "remaining_time": "0:04:34", "throughput": 4629.81, "total_tokens": 41399488} {"current_steps": 41160, "total_steps": 42420, "loss": 0.1394, "lr": 1.3446952496371235e-07, "epoch": 19.405940594059405, "percentage": 97.03, "elapsed_time": "2:29:02", "remaining_time": "0:04:33", "throughput": 4629.8, "total_tokens": 41404192} {"current_steps": 41165, "total_steps": 42420, "loss": 0.0736, "lr": 1.3340621451847501e-07, "epoch": 19.40829797265441, "percentage": 97.04, "elapsed_time": "2:29:03", "remaining_time": "0:04:32", "throughput": 4629.83, "total_tokens": 41409184} {"current_steps": 41170, "total_steps": 42420, "loss": 0.2021, "lr": 1.3234711356535368e-07, "epoch": 19.41065535124941, "percentage": 97.05, "elapsed_time": "2:29:05", "remaining_time": "0:04:31", "throughput": 4629.87, "total_tokens": 41414848} {"current_steps": 41175, "total_steps": 42420, "loss": 0.1032, "lr": 1.3129222228363824e-07, "epoch": 19.413012729844414, "percentage": 97.07, "elapsed_time": "2:29:06", "remaining_time": "0:04:30", "throughput": 4629.91, "total_tokens": 41420864} {"current_steps": 41180, "total_steps": 42420, "loss": 0.1029, "lr": 1.3024154085190533e-07, "epoch": 19.415370108439415, "percentage": 97.08, "elapsed_time": "2:29:07", "remaining_time": "0:04:29", "throughput": 4629.94, "total_tokens": 41426400} {"current_steps": 41185, "total_steps": 42420, "loss": 0.1041, "lr": 1.2919506944801264e-07, "epoch": 19.41772748703442, "percentage": 97.09, "elapsed_time": "2:29:08", "remaining_time": "0:04:28", "throughput": 4629.97, "total_tokens": 41431488} {"current_steps": 41190, "total_steps": 42420, "loss": 0.109, "lr": 1.2815280824911013e-07, "epoch": 19.42008486562942, "percentage": 97.1, "elapsed_time": "2:29:09", "remaining_time": "0:04:27", "throughput": 4629.99, "total_tokens": 41436192} {"current_steps": 41195, "total_steps": 42420, "loss": 0.0936, "lr": 1.2711475743164002e-07, "epoch": 19.422442244224424, "percentage": 97.11, "elapsed_time": "2:29:10", "remaining_time": "0:04:26", "throughput": 4629.99, "total_tokens": 41441280} {"current_steps": 41200, "total_steps": 42420, "loss": 0.0868, "lr": 1.2608091717132564e-07, "epoch": 19.424799622819425, "percentage": 97.12, "elapsed_time": "2:29:11", "remaining_time": "0:04:25", "throughput": 4630.03, "total_tokens": 41447328} {"current_steps": 41205, "total_steps": 42420, "loss": 0.1796, "lr": 1.250512876431742e-07, "epoch": 19.42715700141443, "percentage": 97.14, "elapsed_time": "2:29:12", "remaining_time": "0:04:23", "throughput": 4630.06, "total_tokens": 41452736} {"current_steps": 41210, "total_steps": 42420, "loss": 0.1226, "lr": 1.2402586902148793e-07, "epoch": 19.42951438000943, "percentage": 97.15, "elapsed_time": "2:29:14", "remaining_time": "0:04:22", "throughput": 4630.11, "total_tokens": 41458432} {"current_steps": 41215, "total_steps": 42420, "loss": 0.1382, "lr": 1.23004661479853e-07, "epoch": 19.431871758604434, "percentage": 97.16, "elapsed_time": "2:29:15", "remaining_time": "0:04:21", "throughput": 4630.13, "total_tokens": 41463328} {"current_steps": 41220, "total_steps": 42420, "loss": 0.049, "lr": 1.2198766519113947e-07, "epoch": 19.434229137199434, "percentage": 97.17, "elapsed_time": "2:29:15", "remaining_time": "0:04:20", "throughput": 4630.13, "total_tokens": 41467424} {"current_steps": 41225, "total_steps": 42420, "loss": 0.0379, "lr": 1.2097488032750957e-07, "epoch": 19.436586515794435, "percentage": 97.18, "elapsed_time": "2:29:17", "remaining_time": "0:04:19", "throughput": 4630.15, "total_tokens": 41474112} {"current_steps": 41230, "total_steps": 42420, "loss": 0.101, "lr": 1.1996630706041235e-07, "epoch": 19.43894389438944, "percentage": 97.19, "elapsed_time": "2:29:18", "remaining_time": "0:04:18", "throughput": 4630.19, "total_tokens": 41480256} {"current_steps": 41235, "total_steps": 42420, "loss": 0.1044, "lr": 1.189619455605806e-07, "epoch": 19.44130127298444, "percentage": 97.21, "elapsed_time": "2:29:19", "remaining_time": "0:04:17", "throughput": 4630.2, "total_tokens": 41484544} {"current_steps": 41240, "total_steps": 42420, "loss": 0.0504, "lr": 1.1796179599803391e-07, "epoch": 19.443658651579444, "percentage": 97.22, "elapsed_time": "2:29:20", "remaining_time": "0:04:16", "throughput": 4630.23, "total_tokens": 41489152} {"current_steps": 41245, "total_steps": 42420, "loss": 0.0986, "lr": 1.169658585420813e-07, "epoch": 19.446016030174444, "percentage": 97.23, "elapsed_time": "2:29:21", "remaining_time": "0:04:15", "throughput": 4630.26, "total_tokens": 41495808} {"current_steps": 41250, "total_steps": 42420, "loss": 0.0535, "lr": 1.1597413336132124e-07, "epoch": 19.44837340876945, "percentage": 97.24, "elapsed_time": "2:29:23", "remaining_time": "0:04:14", "throughput": 4630.27, "total_tokens": 41501248} {"current_steps": 41255, "total_steps": 42420, "loss": 0.0614, "lr": 1.149866206236333e-07, "epoch": 19.45073078736445, "percentage": 97.25, "elapsed_time": "2:29:23", "remaining_time": "0:04:13", "throughput": 4630.26, "total_tokens": 41505504} {"current_steps": 41260, "total_steps": 42420, "loss": 0.1233, "lr": 1.1400332049618933e-07, "epoch": 19.453088165959453, "percentage": 97.27, "elapsed_time": "2:29:25", "remaining_time": "0:04:12", "throughput": 4630.26, "total_tokens": 41510400} {"current_steps": 41265, "total_steps": 42420, "loss": 0.1813, "lr": 1.1302423314543953e-07, "epoch": 19.455445544554454, "percentage": 97.28, "elapsed_time": "2:29:26", "remaining_time": "0:04:10", "throughput": 4630.29, "total_tokens": 41515584} {"current_steps": 41270, "total_steps": 42420, "loss": 0.1143, "lr": 1.1204935873713185e-07, "epoch": 19.45780292314946, "percentage": 97.29, "elapsed_time": "2:29:27", "remaining_time": "0:04:09", "throughput": 4630.32, "total_tokens": 41521632} {"current_steps": 41275, "total_steps": 42420, "loss": 0.0776, "lr": 1.1107869743629263e-07, "epoch": 19.46016030174446, "percentage": 97.3, "elapsed_time": "2:29:28", "remaining_time": "0:04:08", "throughput": 4630.32, "total_tokens": 41525824} {"current_steps": 41280, "total_steps": 42420, "loss": 0.1815, "lr": 1.1011224940724041e-07, "epoch": 19.462517680339463, "percentage": 97.31, "elapsed_time": "2:29:29", "remaining_time": "0:04:07", "throughput": 4630.35, "total_tokens": 41530432} {"current_steps": 41285, "total_steps": 42420, "loss": 0.0301, "lr": 1.0915001481358045e-07, "epoch": 19.464875058934464, "percentage": 97.32, "elapsed_time": "2:29:30", "remaining_time": "0:04:06", "throughput": 4630.35, "total_tokens": 41534944} {"current_steps": 41290, "total_steps": 42420, "loss": 0.0927, "lr": 1.0819199381819634e-07, "epoch": 19.467232437529468, "percentage": 97.34, "elapsed_time": "2:29:31", "remaining_time": "0:04:05", "throughput": 4630.38, "total_tokens": 41540224} {"current_steps": 41295, "total_steps": 42420, "loss": 0.0857, "lr": 1.07238186583275e-07, "epoch": 19.46958981612447, "percentage": 97.35, "elapsed_time": "2:29:32", "remaining_time": "0:04:04", "throughput": 4630.39, "total_tokens": 41545184} {"current_steps": 41300, "total_steps": 42420, "loss": 0.0767, "lr": 1.0628859327026786e-07, "epoch": 19.471947194719473, "percentage": 97.36, "elapsed_time": "2:29:33", "remaining_time": "0:04:03", "throughput": 4630.4, "total_tokens": 41549888} {"current_steps": 41305, "total_steps": 42420, "loss": 0.0711, "lr": 1.0534321403993242e-07, "epoch": 19.474304573314473, "percentage": 97.37, "elapsed_time": "2:29:34", "remaining_time": "0:04:02", "throughput": 4630.43, "total_tokens": 41555232} {"current_steps": 41310, "total_steps": 42420, "loss": 0.078, "lr": 1.0440204905230455e-07, "epoch": 19.476661951909477, "percentage": 97.38, "elapsed_time": "2:29:35", "remaining_time": "0:04:01", "throughput": 4630.47, "total_tokens": 41560832} {"current_steps": 41315, "total_steps": 42420, "loss": 0.0761, "lr": 1.0346509846670682e-07, "epoch": 19.479019330504478, "percentage": 97.4, "elapsed_time": "2:29:36", "remaining_time": "0:04:00", "throughput": 4630.46, "total_tokens": 41565664} {"current_steps": 41320, "total_steps": 42420, "loss": 0.0678, "lr": 1.0253236244174846e-07, "epoch": 19.481376709099482, "percentage": 97.41, "elapsed_time": "2:29:37", "remaining_time": "0:03:58", "throughput": 4630.49, "total_tokens": 41570752} {"current_steps": 41325, "total_steps": 42420, "loss": 0.015, "lr": 1.0160384113532539e-07, "epoch": 19.483734087694483, "percentage": 97.42, "elapsed_time": "2:29:38", "remaining_time": "0:03:57", "throughput": 4630.5, "total_tokens": 41575200} {"current_steps": 41330, "total_steps": 42420, "loss": 0.0761, "lr": 1.0067953470462022e-07, "epoch": 19.486091466289487, "percentage": 97.43, "elapsed_time": "2:29:39", "remaining_time": "0:03:56", "throughput": 4630.49, "total_tokens": 41579328} {"current_steps": 41335, "total_steps": 42420, "loss": 0.0672, "lr": 9.975944330610776e-08, "epoch": 19.488448844884488, "percentage": 97.44, "elapsed_time": "2:29:40", "remaining_time": "0:03:55", "throughput": 4630.48, "total_tokens": 41583840} {"current_steps": 41340, "total_steps": 42420, "loss": 0.0516, "lr": 9.884356709553565e-08, "epoch": 19.490806223479492, "percentage": 97.45, "elapsed_time": "2:29:41", "remaining_time": "0:03:54", "throughput": 4630.49, "total_tokens": 41588640} {"current_steps": 41345, "total_steps": 42420, "loss": 0.1054, "lr": 9.793190622795211e-08, "epoch": 19.493163602074493, "percentage": 97.47, "elapsed_time": "2:29:42", "remaining_time": "0:03:53", "throughput": 4630.54, "total_tokens": 41594080} {"current_steps": 41350, "total_steps": 42420, "loss": 0.0476, "lr": 9.702446085768092e-08, "epoch": 19.495520980669497, "percentage": 97.48, "elapsed_time": "2:29:43", "remaining_time": "0:03:52", "throughput": 4630.55, "total_tokens": 41598976} {"current_steps": 41355, "total_steps": 42420, "loss": 0.1374, "lr": 9.61212311383436e-08, "epoch": 19.497878359264497, "percentage": 97.49, "elapsed_time": "2:29:44", "remaining_time": "0:03:51", "throughput": 4630.58, "total_tokens": 41603776} {"current_steps": 41360, "total_steps": 42420, "loss": 0.1554, "lr": 9.522221722283453e-08, "epoch": 19.5002357378595, "percentage": 97.5, "elapsed_time": "2:29:45", "remaining_time": "0:03:50", "throughput": 4630.6, "total_tokens": 41608672} {"current_steps": 41365, "total_steps": 42420, "loss": 0.0622, "lr": 9.432741926334865e-08, "epoch": 19.502593116454502, "percentage": 97.51, "elapsed_time": "2:29:46", "remaining_time": "0:03:49", "throughput": 4630.63, "total_tokens": 41613920} {"current_steps": 41370, "total_steps": 42420, "loss": 0.1713, "lr": 9.343683741135645e-08, "epoch": 19.504950495049506, "percentage": 97.52, "elapsed_time": "2:29:47", "remaining_time": "0:03:48", "throughput": 4630.66, "total_tokens": 41618688} {"current_steps": 41375, "total_steps": 42420, "loss": 0.0739, "lr": 9.255047181761512e-08, "epoch": 19.507307873644507, "percentage": 97.54, "elapsed_time": "2:29:48", "remaining_time": "0:03:47", "throughput": 4630.67, "total_tokens": 41623200} {"current_steps": 41380, "total_steps": 42420, "loss": 0.1483, "lr": 9.166832263217683e-08, "epoch": 19.50966525223951, "percentage": 97.55, "elapsed_time": "2:29:49", "remaining_time": "0:03:45", "throughput": 4630.7, "total_tokens": 41628352} {"current_steps": 41385, "total_steps": 42420, "loss": 0.4373, "lr": 9.079039000437218e-08, "epoch": 19.51202263083451, "percentage": 97.56, "elapsed_time": "2:29:50", "remaining_time": "0:03:44", "throughput": 4630.7, "total_tokens": 41632672} {"current_steps": 41390, "total_steps": 42420, "loss": 0.047, "lr": 8.991667408281835e-08, "epoch": 19.514380009429516, "percentage": 97.57, "elapsed_time": "2:29:51", "remaining_time": "0:03:43", "throughput": 4630.7, "total_tokens": 41637056} {"current_steps": 41395, "total_steps": 42420, "loss": 0.0142, "lr": 8.904717501542204e-08, "epoch": 19.516737388024517, "percentage": 97.58, "elapsed_time": "2:29:52", "remaining_time": "0:03:42", "throughput": 4630.75, "total_tokens": 41643520} {"current_steps": 41400, "total_steps": 42420, "loss": 0.1343, "lr": 8.818189294937662e-08, "epoch": 19.51909476661952, "percentage": 97.6, "elapsed_time": "2:29:53", "remaining_time": "0:03:41", "throughput": 4630.79, "total_tokens": 41649056} {"current_steps": 41405, "total_steps": 42420, "loss": 0.15, "lr": 8.732082803115938e-08, "epoch": 19.52145214521452, "percentage": 97.61, "elapsed_time": "2:29:54", "remaining_time": "0:03:40", "throughput": 4630.78, "total_tokens": 41653312} {"current_steps": 41410, "total_steps": 42420, "loss": 0.0161, "lr": 8.646398040653147e-08, "epoch": 19.523809523809526, "percentage": 97.62, "elapsed_time": "2:29:55", "remaining_time": "0:03:39", "throughput": 4630.81, "total_tokens": 41658304} {"current_steps": 41415, "total_steps": 42420, "loss": 0.2903, "lr": 8.561135022054357e-08, "epoch": 19.526166902404526, "percentage": 97.63, "elapsed_time": "2:29:56", "remaining_time": "0:03:38", "throughput": 4630.85, "total_tokens": 41663616} {"current_steps": 41420, "total_steps": 42420, "loss": 0.1742, "lr": 8.476293761753296e-08, "epoch": 19.528524280999527, "percentage": 97.64, "elapsed_time": "2:29:57", "remaining_time": "0:03:37", "throughput": 4630.88, "total_tokens": 41668480} {"current_steps": 41425, "total_steps": 42420, "loss": 0.0805, "lr": 8.391874274111811e-08, "epoch": 19.53088165959453, "percentage": 97.65, "elapsed_time": "2:29:58", "remaining_time": "0:03:36", "throughput": 4630.88, "total_tokens": 41672480} {"current_steps": 41430, "total_steps": 42420, "loss": 0.073, "lr": 8.30787657342097e-08, "epoch": 19.53323903818953, "percentage": 97.67, "elapsed_time": "2:29:59", "remaining_time": "0:03:35", "throughput": 4630.88, "total_tokens": 41676640} {"current_steps": 41435, "total_steps": 42420, "loss": 0.1992, "lr": 8.224300673900231e-08, "epoch": 19.535596416784536, "percentage": 97.68, "elapsed_time": "2:30:00", "remaining_time": "0:03:33", "throughput": 4630.9, "total_tokens": 41681952} {"current_steps": 41440, "total_steps": 42420, "loss": 0.0529, "lr": 8.141146589697445e-08, "epoch": 19.537953795379536, "percentage": 97.69, "elapsed_time": "2:30:01", "remaining_time": "0:03:32", "throughput": 4630.94, "total_tokens": 41687520} {"current_steps": 41445, "total_steps": 42420, "loss": 0.0966, "lr": 8.05841433488913e-08, "epoch": 19.54031117397454, "percentage": 97.7, "elapsed_time": "2:30:02", "remaining_time": "0:03:31", "throughput": 4630.97, "total_tokens": 41692352} {"current_steps": 41450, "total_steps": 42420, "loss": 0.1139, "lr": 7.976103923480471e-08, "epoch": 19.54266855256954, "percentage": 97.71, "elapsed_time": "2:30:04", "remaining_time": "0:03:30", "throughput": 4630.99, "total_tokens": 41697728} {"current_steps": 41455, "total_steps": 42420, "loss": 0.0961, "lr": 7.894215369405322e-08, "epoch": 19.545025931164545, "percentage": 97.73, "elapsed_time": "2:30:05", "remaining_time": "0:03:29", "throughput": 4631.0, "total_tokens": 41702272} {"current_steps": 41460, "total_steps": 42420, "loss": 0.0965, "lr": 7.812748686525928e-08, "epoch": 19.547383309759546, "percentage": 97.74, "elapsed_time": "2:30:06", "remaining_time": "0:03:28", "throughput": 4631.03, "total_tokens": 41707424} {"current_steps": 41465, "total_steps": 42420, "loss": 0.0929, "lr": 7.731703888633202e-08, "epoch": 19.54974068835455, "percentage": 97.75, "elapsed_time": "2:30:07", "remaining_time": "0:03:27", "throughput": 4631.05, "total_tokens": 41712224} {"current_steps": 41470, "total_steps": 42420, "loss": 0.1109, "lr": 7.651080989447002e-08, "epoch": 19.55209806694955, "percentage": 97.76, "elapsed_time": "2:30:08", "remaining_time": "0:03:26", "throughput": 4631.08, "total_tokens": 41717536} {"current_steps": 41475, "total_steps": 42420, "loss": 0.0829, "lr": 7.570880002614744e-08, "epoch": 19.554455445544555, "percentage": 97.77, "elapsed_time": "2:30:09", "remaining_time": "0:03:25", "throughput": 4631.11, "total_tokens": 41722336} {"current_steps": 41480, "total_steps": 42420, "loss": 0.2108, "lr": 7.491100941713625e-08, "epoch": 19.556812824139556, "percentage": 97.78, "elapsed_time": "2:30:10", "remaining_time": "0:03:24", "throughput": 4631.13, "total_tokens": 41727328} {"current_steps": 41485, "total_steps": 42420, "loss": 0.0448, "lr": 7.411743820248674e-08, "epoch": 19.55917020273456, "percentage": 97.8, "elapsed_time": "2:30:11", "remaining_time": "0:03:23", "throughput": 4631.19, "total_tokens": 41733664} {"current_steps": 41490, "total_steps": 42420, "loss": 0.1179, "lr": 7.332808651653867e-08, "epoch": 19.56152758132956, "percentage": 97.81, "elapsed_time": "2:30:12", "remaining_time": "0:03:22", "throughput": 4631.21, "total_tokens": 41737888} {"current_steps": 41495, "total_steps": 42420, "loss": 0.2842, "lr": 7.254295449291293e-08, "epoch": 19.563884959924565, "percentage": 97.82, "elapsed_time": "2:30:13", "remaining_time": "0:03:20", "throughput": 4631.2, "total_tokens": 41742240} {"current_steps": 41500, "total_steps": 42420, "loss": 0.1313, "lr": 7.176204226452266e-08, "epoch": 19.566242338519565, "percentage": 97.83, "elapsed_time": "2:30:14", "remaining_time": "0:03:19", "throughput": 4631.24, "total_tokens": 41747872} {"current_steps": 41505, "total_steps": 42420, "loss": 0.0909, "lr": 7.098534996355933e-08, "epoch": 19.56859971711457, "percentage": 97.84, "elapsed_time": "2:30:15", "remaining_time": "0:03:18", "throughput": 4631.29, "total_tokens": 41754144} {"current_steps": 41510, "total_steps": 42420, "loss": 0.1994, "lr": 7.021287772150665e-08, "epoch": 19.57095709570957, "percentage": 97.85, "elapsed_time": "2:30:16", "remaining_time": "0:03:17", "throughput": 4631.29, "total_tokens": 41758528} {"current_steps": 41515, "total_steps": 42420, "loss": 0.1044, "lr": 6.944462566912945e-08, "epoch": 19.573314474304574, "percentage": 97.87, "elapsed_time": "2:30:17", "remaining_time": "0:03:16", "throughput": 4631.26, "total_tokens": 41762880} {"current_steps": 41520, "total_steps": 42420, "loss": 0.1143, "lr": 6.868059393648207e-08, "epoch": 19.575671852899575, "percentage": 97.88, "elapsed_time": "2:30:18", "remaining_time": "0:03:15", "throughput": 4631.23, "total_tokens": 41766464} {"current_steps": 41525, "total_steps": 42420, "loss": 0.0948, "lr": 6.792078265289991e-08, "epoch": 19.57802923149458, "percentage": 97.89, "elapsed_time": "2:30:19", "remaining_time": "0:03:14", "throughput": 4631.25, "total_tokens": 41770784} {"current_steps": 41530, "total_steps": 42420, "loss": 0.065, "lr": 6.716519194700511e-08, "epoch": 19.58038661008958, "percentage": 97.9, "elapsed_time": "2:30:20", "remaining_time": "0:03:13", "throughput": 4631.28, "total_tokens": 41776000} {"current_steps": 41535, "total_steps": 42420, "loss": 0.076, "lr": 6.64138219467092e-08, "epoch": 19.582743988684584, "percentage": 97.91, "elapsed_time": "2:30:21", "remaining_time": "0:03:12", "throughput": 4631.3, "total_tokens": 41780672} {"current_steps": 41540, "total_steps": 42420, "loss": 0.1318, "lr": 6.566667277920491e-08, "epoch": 19.585101367279584, "percentage": 97.93, "elapsed_time": "2:30:22", "remaining_time": "0:03:11", "throughput": 4631.3, "total_tokens": 41785792} {"current_steps": 41545, "total_steps": 42420, "loss": 0.0611, "lr": 6.492374457097161e-08, "epoch": 19.58745874587459, "percentage": 97.94, "elapsed_time": "2:30:23", "remaining_time": "0:03:10", "throughput": 4631.29, "total_tokens": 41789504} {"current_steps": 41550, "total_steps": 42420, "loss": 0.3012, "lr": 6.418503744777538e-08, "epoch": 19.58981612446959, "percentage": 97.95, "elapsed_time": "2:30:24", "remaining_time": "0:03:08", "throughput": 4631.29, "total_tokens": 41794048} {"current_steps": 41555, "total_steps": 42420, "loss": 0.106, "lr": 6.345055153466616e-08, "epoch": 19.592173503064593, "percentage": 97.96, "elapsed_time": "2:30:25", "remaining_time": "0:03:07", "throughput": 4631.32, "total_tokens": 41799136} {"current_steps": 41560, "total_steps": 42420, "loss": 0.1107, "lr": 6.272028695598064e-08, "epoch": 19.594530881659594, "percentage": 97.97, "elapsed_time": "2:30:26", "remaining_time": "0:03:06", "throughput": 4631.34, "total_tokens": 41803680} {"current_steps": 41565, "total_steps": 42420, "loss": 0.0975, "lr": 6.199424383533937e-08, "epoch": 19.596888260254598, "percentage": 97.98, "elapsed_time": "2:30:27", "remaining_time": "0:03:05", "throughput": 4631.37, "total_tokens": 41808512} {"current_steps": 41570, "total_steps": 42420, "loss": 0.0805, "lr": 6.127242229564956e-08, "epoch": 19.5992456388496, "percentage": 98.0, "elapsed_time": "2:30:28", "remaining_time": "0:03:04", "throughput": 4631.4, "total_tokens": 41813920} {"current_steps": 41575, "total_steps": 42420, "loss": 0.0343, "lr": 6.055482245910238e-08, "epoch": 19.601603017444603, "percentage": 98.01, "elapsed_time": "2:30:29", "remaining_time": "0:03:03", "throughput": 4631.43, "total_tokens": 41819616} {"current_steps": 41580, "total_steps": 42420, "loss": 0.0543, "lr": 5.984144444717565e-08, "epoch": 19.603960396039604, "percentage": 98.02, "elapsed_time": "2:30:30", "remaining_time": "0:03:02", "throughput": 4631.48, "total_tokens": 41824928} {"current_steps": 41585, "total_steps": 42420, "loss": 0.2093, "lr": 5.913228838063389e-08, "epoch": 19.606317774634608, "percentage": 98.03, "elapsed_time": "2:30:31", "remaining_time": "0:03:01", "throughput": 4631.49, "total_tokens": 41829184} {"current_steps": 41590, "total_steps": 42420, "loss": 0.1008, "lr": 5.842735437952274e-08, "epoch": 19.60867515322961, "percentage": 98.04, "elapsed_time": "2:30:32", "remaining_time": "0:03:00", "throughput": 4631.53, "total_tokens": 41834976} {"current_steps": 41595, "total_steps": 42420, "loss": 0.0228, "lr": 5.772664256317728e-08, "epoch": 19.611032531824613, "percentage": 98.06, "elapsed_time": "2:30:33", "remaining_time": "0:02:59", "throughput": 4631.54, "total_tokens": 41839936} {"current_steps": 41600, "total_steps": 42420, "loss": 0.0738, "lr": 5.703015305021653e-08, "epoch": 19.613389910419613, "percentage": 98.07, "elapsed_time": "2:30:34", "remaining_time": "0:02:58", "throughput": 4631.57, "total_tokens": 41845408} {"current_steps": 41605, "total_steps": 42420, "loss": 0.0713, "lr": 5.633788595854062e-08, "epoch": 19.615747289014617, "percentage": 98.08, "elapsed_time": "2:30:36", "remaining_time": "0:02:57", "throughput": 4631.61, "total_tokens": 41851200} {"current_steps": 41610, "total_steps": 42420, "loss": 0.2838, "lr": 5.564984140534468e-08, "epoch": 19.618104667609618, "percentage": 98.09, "elapsed_time": "2:30:37", "remaining_time": "0:02:55", "throughput": 4631.62, "total_tokens": 41856256} {"current_steps": 41615, "total_steps": 42420, "loss": 0.158, "lr": 5.4966019507096676e-08, "epoch": 19.620462046204622, "percentage": 98.1, "elapsed_time": "2:30:38", "remaining_time": "0:02:54", "throughput": 4631.65, "total_tokens": 41861408} {"current_steps": 41620, "total_steps": 42420, "loss": 0.0532, "lr": 5.4286420379559555e-08, "epoch": 19.622819424799623, "percentage": 98.11, "elapsed_time": "2:30:39", "remaining_time": "0:02:53", "throughput": 4631.65, "total_tokens": 41865824} {"current_steps": 41625, "total_steps": 42420, "loss": 0.1778, "lr": 5.36110441377774e-08, "epoch": 19.625176803394623, "percentage": 98.13, "elapsed_time": "2:30:40", "remaining_time": "0:02:52", "throughput": 4631.68, "total_tokens": 41870720} {"current_steps": 41630, "total_steps": 42420, "loss": 0.0789, "lr": 5.293989089608098e-08, "epoch": 19.627534181989628, "percentage": 98.14, "elapsed_time": "2:30:41", "remaining_time": "0:02:51", "throughput": 4631.7, "total_tokens": 41876192} {"current_steps": 41635, "total_steps": 42420, "loss": 0.1392, "lr": 5.2272960768084965e-08, "epoch": 19.62989156058463, "percentage": 98.15, "elapsed_time": "2:30:42", "remaining_time": "0:02:50", "throughput": 4631.72, "total_tokens": 41880672} {"current_steps": 41640, "total_steps": 42420, "loss": 0.2382, "lr": 5.161025386668794e-08, "epoch": 19.632248939179632, "percentage": 98.16, "elapsed_time": "2:30:43", "remaining_time": "0:02:49", "throughput": 4631.74, "total_tokens": 41885472} {"current_steps": 41645, "total_steps": 42420, "loss": 0.0369, "lr": 5.0951770304072385e-08, "epoch": 19.634606317774633, "percentage": 98.17, "elapsed_time": "2:30:44", "remaining_time": "0:02:48", "throughput": 4631.77, "total_tokens": 41891712} {"current_steps": 41650, "total_steps": 42420, "loss": 0.0715, "lr": 5.0297510191713024e-08, "epoch": 19.636963696369637, "percentage": 98.18, "elapsed_time": "2:30:45", "remaining_time": "0:02:47", "throughput": 4631.8, "total_tokens": 41897184} {"current_steps": 41655, "total_steps": 42420, "loss": 0.1345, "lr": 4.9647473640365706e-08, "epoch": 19.639321074964638, "percentage": 98.2, "elapsed_time": "2:30:46", "remaining_time": "0:02:46", "throughput": 4631.82, "total_tokens": 41902016} {"current_steps": 41660, "total_steps": 42420, "loss": 0.0215, "lr": 4.900166076006463e-08, "epoch": 19.641678453559642, "percentage": 98.21, "elapsed_time": "2:30:47", "remaining_time": "0:02:45", "throughput": 4631.84, "total_tokens": 41907104} {"current_steps": 41665, "total_steps": 42420, "loss": 0.0591, "lr": 4.836007166014178e-08, "epoch": 19.644035832154643, "percentage": 98.22, "elapsed_time": "2:30:48", "remaining_time": "0:02:43", "throughput": 4631.87, "total_tokens": 41911904} {"current_steps": 41670, "total_steps": 42420, "loss": 0.1307, "lr": 4.772270644920196e-08, "epoch": 19.646393210749647, "percentage": 98.23, "elapsed_time": "2:30:49", "remaining_time": "0:02:42", "throughput": 4631.87, "total_tokens": 41916352} {"current_steps": 41675, "total_steps": 42420, "loss": 0.0295, "lr": 4.708956523514496e-08, "epoch": 19.648750589344647, "percentage": 98.24, "elapsed_time": "2:30:50", "remaining_time": "0:02:41", "throughput": 4631.9, "total_tokens": 41921632} {"current_steps": 41680, "total_steps": 42420, "loss": 0.147, "lr": 4.646064812514617e-08, "epoch": 19.65110796793965, "percentage": 98.26, "elapsed_time": "2:30:51", "remaining_time": "0:02:40", "throughput": 4631.95, "total_tokens": 41927520} {"current_steps": 41685, "total_steps": 42420, "loss": 0.0229, "lr": 4.583595522567041e-08, "epoch": 19.653465346534652, "percentage": 98.27, "elapsed_time": "2:30:52", "remaining_time": "0:02:39", "throughput": 4631.97, "total_tokens": 41932416} {"current_steps": 41690, "total_steps": 42420, "loss": 0.1017, "lr": 4.5215486642471997e-08, "epoch": 19.655822725129656, "percentage": 98.28, "elapsed_time": "2:30:53", "remaining_time": "0:02:38", "throughput": 4631.98, "total_tokens": 41937152} {"current_steps": 41695, "total_steps": 42420, "loss": 0.0307, "lr": 4.4599242480586336e-08, "epoch": 19.658180103724657, "percentage": 98.29, "elapsed_time": "2:30:54", "remaining_time": "0:02:37", "throughput": 4632.0, "total_tokens": 41942016} {"current_steps": 41700, "total_steps": 42420, "loss": 0.2828, "lr": 4.398722284432721e-08, "epoch": 19.66053748231966, "percentage": 98.3, "elapsed_time": "2:30:55", "remaining_time": "0:02:36", "throughput": 4632.0, "total_tokens": 41946464} {"current_steps": 41705, "total_steps": 42420, "loss": 0.0391, "lr": 4.3379427837300646e-08, "epoch": 19.662894860914662, "percentage": 98.31, "elapsed_time": "2:30:56", "remaining_time": "0:02:35", "throughput": 4632.03, "total_tokens": 41951904} {"current_steps": 41710, "total_steps": 42420, "loss": 0.0357, "lr": 4.27758575624021e-08, "epoch": 19.665252239509666, "percentage": 98.33, "elapsed_time": "2:30:57", "remaining_time": "0:02:34", "throughput": 4632.04, "total_tokens": 41956608} {"current_steps": 41715, "total_steps": 42420, "loss": 0.0422, "lr": 4.217651212179985e-08, "epoch": 19.667609618104667, "percentage": 98.34, "elapsed_time": "2:30:58", "remaining_time": "0:02:33", "throughput": 4632.07, "total_tokens": 41961728} {"current_steps": 41720, "total_steps": 42420, "loss": 0.1041, "lr": 4.1581391616951623e-08, "epoch": 19.66996699669967, "percentage": 98.35, "elapsed_time": "2:30:59", "remaining_time": "0:02:32", "throughput": 4632.09, "total_tokens": 41966528} {"current_steps": 41725, "total_steps": 42420, "loss": 0.2226, "lr": 4.0990496148607395e-08, "epoch": 19.67232437529467, "percentage": 98.36, "elapsed_time": "2:31:00", "remaining_time": "0:02:30", "throughput": 4632.12, "total_tokens": 41971616} {"current_steps": 41730, "total_steps": 42420, "loss": 0.1611, "lr": 4.0403825816789917e-08, "epoch": 19.674681753889676, "percentage": 98.37, "elapsed_time": "2:31:01", "remaining_time": "0:02:29", "throughput": 4632.14, "total_tokens": 41976032} {"current_steps": 41735, "total_steps": 42420, "loss": 0.1717, "lr": 3.982138072081698e-08, "epoch": 19.677039132484676, "percentage": 98.39, "elapsed_time": "2:31:02", "remaining_time": "0:02:28", "throughput": 4632.16, "total_tokens": 41981216} {"current_steps": 41740, "total_steps": 42420, "loss": 0.0279, "lr": 3.924316095928193e-08, "epoch": 19.67939651107968, "percentage": 98.4, "elapsed_time": "2:31:04", "remaining_time": "0:02:27", "throughput": 4632.18, "total_tokens": 41986368} {"current_steps": 41745, "total_steps": 42420, "loss": 0.1581, "lr": 3.866916663007314e-08, "epoch": 19.68175388967468, "percentage": 98.41, "elapsed_time": "2:31:05", "remaining_time": "0:02:26", "throughput": 4632.2, "total_tokens": 41991040} {"current_steps": 41750, "total_steps": 42420, "loss": 0.1176, "lr": 3.8099397830354544e-08, "epoch": 19.684111268269685, "percentage": 98.42, "elapsed_time": "2:31:06", "remaining_time": "0:02:25", "throughput": 4632.24, "total_tokens": 41996864} {"current_steps": 41755, "total_steps": 42420, "loss": 0.1415, "lr": 3.753385465657677e-08, "epoch": 19.686468646864686, "percentage": 98.43, "elapsed_time": "2:31:07", "remaining_time": "0:02:24", "throughput": 4632.24, "total_tokens": 42001440} {"current_steps": 41760, "total_steps": 42420, "loss": 0.1977, "lr": 3.6972537204479905e-08, "epoch": 19.68882602545969, "percentage": 98.44, "elapsed_time": "2:31:08", "remaining_time": "0:02:23", "throughput": 4632.24, "total_tokens": 42005696} {"current_steps": 41765, "total_steps": 42420, "loss": 0.0968, "lr": 3.641544556908516e-08, "epoch": 19.69118340405469, "percentage": 98.46, "elapsed_time": "2:31:09", "remaining_time": "0:02:22", "throughput": 4632.28, "total_tokens": 42011680} {"current_steps": 41770, "total_steps": 42420, "loss": 0.2247, "lr": 3.5862579844697654e-08, "epoch": 19.693540782649695, "percentage": 98.47, "elapsed_time": "2:31:10", "remaining_time": "0:02:21", "throughput": 4632.29, "total_tokens": 42016608} {"current_steps": 41775, "total_steps": 42420, "loss": 0.0201, "lr": 3.5313940124909184e-08, "epoch": 19.695898161244696, "percentage": 98.48, "elapsed_time": "2:31:11", "remaining_time": "0:02:20", "throughput": 4632.29, "total_tokens": 42021312} {"current_steps": 41780, "total_steps": 42420, "loss": 0.4068, "lr": 3.4769526502592684e-08, "epoch": 19.6982555398397, "percentage": 98.49, "elapsed_time": "2:31:12", "remaining_time": "0:02:18", "throughput": 4632.31, "total_tokens": 42026016} {"current_steps": 41785, "total_steps": 42420, "loss": 0.0376, "lr": 3.4229339069910546e-08, "epoch": 19.7006129184347, "percentage": 98.5, "elapsed_time": "2:31:13", "remaining_time": "0:02:17", "throughput": 4632.33, "total_tokens": 42030976} {"current_steps": 41790, "total_steps": 42420, "loss": 0.166, "lr": 3.369337791830629e-08, "epoch": 19.702970297029704, "percentage": 98.51, "elapsed_time": "2:31:14", "remaining_time": "0:02:16", "throughput": 4632.34, "total_tokens": 42035328} {"current_steps": 41795, "total_steps": 42420, "loss": 0.0386, "lr": 3.3161643138510115e-08, "epoch": 19.705327675624705, "percentage": 98.53, "elapsed_time": "2:31:15", "remaining_time": "0:02:15", "throughput": 4632.37, "total_tokens": 42040640} {"current_steps": 41800, "total_steps": 42420, "loss": 0.0464, "lr": 3.2634134820536125e-08, "epoch": 19.70768505421971, "percentage": 98.54, "elapsed_time": "2:31:16", "remaining_time": "0:02:14", "throughput": 4632.38, "total_tokens": 42045120} {"current_steps": 41805, "total_steps": 42420, "loss": 0.0933, "lr": 3.211085305367956e-08, "epoch": 19.71004243281471, "percentage": 98.55, "elapsed_time": "2:31:17", "remaining_time": "0:02:13", "throughput": 4632.38, "total_tokens": 42050624} {"current_steps": 41810, "total_steps": 42420, "loss": 0.1601, "lr": 3.159179792652511e-08, "epoch": 19.712399811409714, "percentage": 98.56, "elapsed_time": "2:31:18", "remaining_time": "0:02:12", "throughput": 4632.42, "total_tokens": 42056000} {"current_steps": 41815, "total_steps": 42420, "loss": 0.1556, "lr": 3.107696952694139e-08, "epoch": 19.714757190004715, "percentage": 98.57, "elapsed_time": "2:31:19", "remaining_time": "0:02:11", "throughput": 4632.45, "total_tokens": 42060832} {"current_steps": 41820, "total_steps": 42420, "loss": 0.0524, "lr": 3.056636794207812e-08, "epoch": 19.71711456859972, "percentage": 98.59, "elapsed_time": "2:31:20", "remaining_time": "0:02:10", "throughput": 4632.44, "total_tokens": 42065600} {"current_steps": 41825, "total_steps": 42420, "loss": 0.0971, "lr": 3.0059993258368945e-08, "epoch": 19.71947194719472, "percentage": 98.6, "elapsed_time": "2:31:21", "remaining_time": "0:02:09", "throughput": 4632.46, "total_tokens": 42070656} {"current_steps": 41830, "total_steps": 42420, "loss": 0.0987, "lr": 2.955784556153973e-08, "epoch": 19.72182932578972, "percentage": 98.61, "elapsed_time": "2:31:22", "remaining_time": "0:02:08", "throughput": 4632.49, "total_tokens": 42076512} {"current_steps": 41835, "total_steps": 42420, "loss": 0.0832, "lr": 2.9059924936594706e-08, "epoch": 19.724186704384724, "percentage": 98.62, "elapsed_time": "2:31:24", "remaining_time": "0:02:07", "throughput": 4632.54, "total_tokens": 42082368} {"current_steps": 41840, "total_steps": 42420, "loss": 0.0707, "lr": 2.8566231467819228e-08, "epoch": 19.726544082979725, "percentage": 98.63, "elapsed_time": "2:31:25", "remaining_time": "0:02:05", "throughput": 4632.56, "total_tokens": 42087136} {"current_steps": 41845, "total_steps": 42420, "loss": 0.0152, "lr": 2.807676523879088e-08, "epoch": 19.72890146157473, "percentage": 98.64, "elapsed_time": "2:31:26", "remaining_time": "0:02:04", "throughput": 4632.58, "total_tokens": 42092192} {"current_steps": 41850, "total_steps": 42420, "loss": 0.0563, "lr": 2.759152633236839e-08, "epoch": 19.73125884016973, "percentage": 98.66, "elapsed_time": "2:31:26", "remaining_time": "0:02:03", "throughput": 4632.57, "total_tokens": 42096096} {"current_steps": 41855, "total_steps": 42420, "loss": 0.1297, "lr": 2.71105148306916e-08, "epoch": 19.733616218764734, "percentage": 98.67, "elapsed_time": "2:31:27", "remaining_time": "0:02:02", "throughput": 4632.59, "total_tokens": 42100800} {"current_steps": 41860, "total_steps": 42420, "loss": 0.1482, "lr": 2.6633730815189828e-08, "epoch": 19.735973597359735, "percentage": 98.68, "elapsed_time": "2:31:29", "remaining_time": "0:02:01", "throughput": 4632.64, "total_tokens": 42106720} {"current_steps": 41865, "total_steps": 42420, "loss": 0.0151, "lr": 2.6161174366573504e-08, "epoch": 19.73833097595474, "percentage": 98.69, "elapsed_time": "2:31:30", "remaining_time": "0:02:00", "throughput": 4632.65, "total_tokens": 42111520} {"current_steps": 41870, "total_steps": 42420, "loss": 0.1066, "lr": 2.5692845564839753e-08, "epoch": 19.74068835454974, "percentage": 98.7, "elapsed_time": "2:31:31", "remaining_time": "0:01:59", "throughput": 4632.67, "total_tokens": 42116064} {"current_steps": 41875, "total_steps": 42420, "loss": 0.0447, "lr": 2.522874448926682e-08, "epoch": 19.743045733144744, "percentage": 98.72, "elapsed_time": "2:31:32", "remaining_time": "0:01:58", "throughput": 4632.7, "total_tokens": 42121632} {"current_steps": 41880, "total_steps": 42420, "loss": 0.1091, "lr": 2.476887121841964e-08, "epoch": 19.745403111739744, "percentage": 98.73, "elapsed_time": "2:31:33", "remaining_time": "0:01:57", "throughput": 4632.74, "total_tokens": 42127360} {"current_steps": 41885, "total_steps": 42420, "loss": 0.0841, "lr": 2.4313225830147057e-08, "epoch": 19.74776049033475, "percentage": 98.74, "elapsed_time": "2:31:34", "remaining_time": "0:01:56", "throughput": 4632.76, "total_tokens": 42131616} {"current_steps": 41890, "total_steps": 42420, "loss": 0.1859, "lr": 2.3861808401581808e-08, "epoch": 19.75011786892975, "percentage": 98.75, "elapsed_time": "2:31:35", "remaining_time": "0:01:55", "throughput": 4632.76, "total_tokens": 42136096} {"current_steps": 41895, "total_steps": 42420, "loss": 0.3167, "lr": 2.3414619009143323e-08, "epoch": 19.752475247524753, "percentage": 98.76, "elapsed_time": "2:31:36", "remaining_time": "0:01:53", "throughput": 4632.78, "total_tokens": 42141120} {"current_steps": 41900, "total_steps": 42420, "loss": 0.2085, "lr": 2.297165772853216e-08, "epoch": 19.754832626119754, "percentage": 98.77, "elapsed_time": "2:31:37", "remaining_time": "0:01:52", "throughput": 4632.79, "total_tokens": 42145856} {"current_steps": 41905, "total_steps": 42420, "loss": 0.163, "lr": 2.2532924634732778e-08, "epoch": 19.757190004714758, "percentage": 98.79, "elapsed_time": "2:31:38", "remaining_time": "0:01:51", "throughput": 4632.82, "total_tokens": 42150848} {"current_steps": 41910, "total_steps": 42420, "loss": 0.0939, "lr": 2.2098419802013548e-08, "epoch": 19.75954738330976, "percentage": 98.8, "elapsed_time": "2:31:39", "remaining_time": "0:01:50", "throughput": 4632.85, "total_tokens": 42155744} {"current_steps": 41915, "total_steps": 42420, "loss": 0.0163, "lr": 2.1668143303935074e-08, "epoch": 19.761904761904763, "percentage": 98.81, "elapsed_time": "2:31:40", "remaining_time": "0:01:49", "throughput": 4632.88, "total_tokens": 42161920} {"current_steps": 41920, "total_steps": 42420, "loss": 0.1788, "lr": 2.1242095213327984e-08, "epoch": 19.764262140499763, "percentage": 98.82, "elapsed_time": "2:31:41", "remaining_time": "0:01:48", "throughput": 4632.9, "total_tokens": 42166688} {"current_steps": 41925, "total_steps": 42420, "loss": 0.0328, "lr": 2.082027560232347e-08, "epoch": 19.766619519094768, "percentage": 98.83, "elapsed_time": "2:31:42", "remaining_time": "0:01:47", "throughput": 4632.93, "total_tokens": 42172000} {"current_steps": 41930, "total_steps": 42420, "loss": 0.013, "lr": 2.040268454231997e-08, "epoch": 19.768976897689768, "percentage": 98.84, "elapsed_time": "2:31:43", "remaining_time": "0:01:46", "throughput": 4632.96, "total_tokens": 42176800} {"current_steps": 41935, "total_steps": 42420, "loss": 0.218, "lr": 1.9989322104013718e-08, "epoch": 19.771334276284772, "percentage": 98.86, "elapsed_time": "2:31:44", "remaining_time": "0:01:45", "throughput": 4632.98, "total_tokens": 42181920} {"current_steps": 41940, "total_steps": 42420, "loss": 0.2405, "lr": 1.9580188357379292e-08, "epoch": 19.773691654879773, "percentage": 98.87, "elapsed_time": "2:31:46", "remaining_time": "0:01:44", "throughput": 4633.03, "total_tokens": 42189568} {"current_steps": 41945, "total_steps": 42420, "loss": 0.0318, "lr": 1.9175283371675178e-08, "epoch": 19.776049033474777, "percentage": 98.88, "elapsed_time": "2:31:47", "remaining_time": "0:01:43", "throughput": 4633.08, "total_tokens": 42195712} {"current_steps": 41950, "total_steps": 42420, "loss": 0.0231, "lr": 1.877460721544655e-08, "epoch": 19.778406412069778, "percentage": 98.89, "elapsed_time": "2:31:48", "remaining_time": "0:01:42", "throughput": 4633.11, "total_tokens": 42201280} {"current_steps": 41955, "total_steps": 42420, "loss": 0.1151, "lr": 1.8378159956519703e-08, "epoch": 19.780763790664782, "percentage": 98.9, "elapsed_time": "2:31:49", "remaining_time": "0:01:40", "throughput": 4633.12, "total_tokens": 42206144} {"current_steps": 41960, "total_steps": 42420, "loss": 0.0308, "lr": 1.7985941662004848e-08, "epoch": 19.783121169259783, "percentage": 98.92, "elapsed_time": "2:31:50", "remaining_time": "0:01:39", "throughput": 4633.14, "total_tokens": 42210624} {"current_steps": 41965, "total_steps": 42420, "loss": 0.1858, "lr": 1.7597952398301644e-08, "epoch": 19.785478547854787, "percentage": 98.93, "elapsed_time": "2:31:51", "remaining_time": "0:01:38", "throughput": 4633.15, "total_tokens": 42215488} {"current_steps": 41970, "total_steps": 42420, "loss": 0.2158, "lr": 1.721419223108811e-08, "epoch": 19.787835926449787, "percentage": 98.94, "elapsed_time": "2:31:52", "remaining_time": "0:01:37", "throughput": 4633.12, "total_tokens": 42219488} {"current_steps": 41975, "total_steps": 42420, "loss": 0.069, "lr": 1.6834661225326175e-08, "epoch": 19.79019330504479, "percentage": 98.95, "elapsed_time": "2:31:53", "remaining_time": "0:01:36", "throughput": 4633.13, "total_tokens": 42224064} {"current_steps": 41980, "total_steps": 42420, "loss": 0.2329, "lr": 1.6459359445267218e-08, "epoch": 19.792550683639792, "percentage": 98.96, "elapsed_time": "2:31:54", "remaining_time": "0:01:35", "throughput": 4633.15, "total_tokens": 42229920} {"current_steps": 41985, "total_steps": 42420, "loss": 0.0885, "lr": 1.6088286954443753e-08, "epoch": 19.794908062234796, "percentage": 98.97, "elapsed_time": "2:31:55", "remaining_time": "0:01:34", "throughput": 4633.16, "total_tokens": 42235136} {"current_steps": 41990, "total_steps": 42420, "loss": 0.0247, "lr": 1.5721443815666647e-08, "epoch": 19.797265440829797, "percentage": 98.99, "elapsed_time": "2:31:56", "remaining_time": "0:01:33", "throughput": 4633.19, "total_tokens": 42240480} {"current_steps": 41995, "total_steps": 42420, "loss": 0.1072, "lr": 1.535883009104455e-08, "epoch": 19.7996228194248, "percentage": 99.0, "elapsed_time": "2:31:58", "remaining_time": "0:01:32", "throughput": 4633.22, "total_tokens": 42245920} {"current_steps": 42000, "total_steps": 42420, "loss": 0.0666, "lr": 1.5000445841956144e-08, "epoch": 19.801980198019802, "percentage": 99.01, "elapsed_time": "2:31:59", "remaining_time": "0:01:31", "throughput": 4633.24, "total_tokens": 42250656} {"current_steps": 42005, "total_steps": 42420, "loss": 0.03, "lr": 1.4646291129069566e-08, "epoch": 19.804337576614806, "percentage": 99.02, "elapsed_time": "2:32:00", "remaining_time": "0:01:30", "throughput": 4633.27, "total_tokens": 42255776} {"current_steps": 42010, "total_steps": 42420, "loss": 0.0775, "lr": 1.4296366012339634e-08, "epoch": 19.806694955209807, "percentage": 99.03, "elapsed_time": "2:32:01", "remaining_time": "0:01:29", "throughput": 4633.27, "total_tokens": 42260288} {"current_steps": 42015, "total_steps": 42420, "loss": 0.0487, "lr": 1.3950670551002298e-08, "epoch": 19.809052333804807, "percentage": 99.05, "elapsed_time": "2:32:02", "remaining_time": "0:01:27", "throughput": 4633.29, "total_tokens": 42264960} {"current_steps": 42020, "total_steps": 42420, "loss": 0.1439, "lr": 1.3609204803577413e-08, "epoch": 19.81140971239981, "percentage": 99.06, "elapsed_time": "2:32:03", "remaining_time": "0:01:26", "throughput": 4633.32, "total_tokens": 42270496} {"current_steps": 42025, "total_steps": 42420, "loss": 0.1057, "lr": 1.3271968827868742e-08, "epoch": 19.813767090994816, "percentage": 99.07, "elapsed_time": "2:32:04", "remaining_time": "0:01:25", "throughput": 4633.35, "total_tokens": 42275904} {"current_steps": 42030, "total_steps": 42420, "loss": 0.2943, "lr": 1.2938962680966727e-08, "epoch": 19.816124469589816, "percentage": 99.08, "elapsed_time": "2:32:05", "remaining_time": "0:01:24", "throughput": 4633.38, "total_tokens": 42281504} {"current_steps": 42035, "total_steps": 42420, "loss": 0.041, "lr": 1.2610186419240166e-08, "epoch": 19.818481848184817, "percentage": 99.09, "elapsed_time": "2:32:06", "remaining_time": "0:01:23", "throughput": 4633.39, "total_tokens": 42285600} {"current_steps": 42040, "total_steps": 42420, "loss": 0.1159, "lr": 1.2285640098347317e-08, "epoch": 19.82083922677982, "percentage": 99.1, "elapsed_time": "2:32:07", "remaining_time": "0:01:22", "throughput": 4633.4, "total_tokens": 42290784} {"current_steps": 42045, "total_steps": 42420, "loss": 0.0373, "lr": 1.1965323773230342e-08, "epoch": 19.82319660537482, "percentage": 99.12, "elapsed_time": "2:32:08", "remaining_time": "0:01:21", "throughput": 4633.41, "total_tokens": 42295744} {"current_steps": 42050, "total_steps": 42420, "loss": 0.0541, "lr": 1.1649237498109755e-08, "epoch": 19.825553983969826, "percentage": 99.13, "elapsed_time": "2:32:09", "remaining_time": "0:01:20", "throughput": 4633.43, "total_tokens": 42300608} {"current_steps": 42055, "total_steps": 42420, "loss": 0.0804, "lr": 1.1337381326495533e-08, "epoch": 19.827911362564826, "percentage": 99.14, "elapsed_time": "2:32:10", "remaining_time": "0:01:19", "throughput": 4633.44, "total_tokens": 42305120} {"current_steps": 42060, "total_steps": 42420, "loss": 0.0989, "lr": 1.1029755311181556e-08, "epoch": 19.83026874115983, "percentage": 99.15, "elapsed_time": "2:32:11", "remaining_time": "0:01:18", "throughput": 4633.44, "total_tokens": 42309056} {"current_steps": 42065, "total_steps": 42420, "loss": 0.0764, "lr": 1.0726359504240058e-08, "epoch": 19.83262611975483, "percentage": 99.16, "elapsed_time": "2:32:12", "remaining_time": "0:01:17", "throughput": 4633.48, "total_tokens": 42314624} {"current_steps": 42070, "total_steps": 42420, "loss": 0.0499, "lr": 1.0427193957029958e-08, "epoch": 19.834983498349835, "percentage": 99.17, "elapsed_time": "2:32:13", "remaining_time": "0:01:15", "throughput": 4633.5, "total_tokens": 42319488} {"current_steps": 42075, "total_steps": 42420, "loss": 0.1208, "lr": 1.0132258720199627e-08, "epoch": 19.837340876944836, "percentage": 99.19, "elapsed_time": "2:32:14", "remaining_time": "0:01:14", "throughput": 4633.56, "total_tokens": 42327296} {"current_steps": 42080, "total_steps": 42420, "loss": 0.0791, "lr": 9.841553843673023e-09, "epoch": 19.83969825553984, "percentage": 99.2, "elapsed_time": "2:32:15", "remaining_time": "0:01:13", "throughput": 4633.54, "total_tokens": 42331232} {"current_steps": 42085, "total_steps": 42420, "loss": 0.188, "lr": 9.555079376663556e-09, "epoch": 19.84205563413484, "percentage": 99.21, "elapsed_time": "2:32:16", "remaining_time": "0:01:12", "throughput": 4633.53, "total_tokens": 42335200} {"current_steps": 42090, "total_steps": 42420, "loss": 0.244, "lr": 9.27283536766299e-09, "epoch": 19.844413012729845, "percentage": 99.22, "elapsed_time": "2:32:17", "remaining_time": "0:01:11", "throughput": 4633.56, "total_tokens": 42340512} {"current_steps": 42095, "total_steps": 42420, "loss": 0.1904, "lr": 8.994821864455328e-09, "epoch": 19.846770391324846, "percentage": 99.23, "elapsed_time": "2:32:18", "remaining_time": "0:01:10", "throughput": 4633.58, "total_tokens": 42345344} {"current_steps": 42100, "total_steps": 42420, "loss": 0.0472, "lr": 8.721038914100144e-09, "epoch": 19.84912776991985, "percentage": 99.25, "elapsed_time": "2:32:19", "remaining_time": "0:01:09", "throughput": 4633.62, "total_tokens": 42350784} {"current_steps": 42105, "total_steps": 42420, "loss": 0.0871, "lr": 8.451486562946476e-09, "epoch": 19.85148514851485, "percentage": 99.26, "elapsed_time": "2:32:20", "remaining_time": "0:01:08", "throughput": 4633.6, "total_tokens": 42354688} {"current_steps": 42110, "total_steps": 42420, "loss": 0.2348, "lr": 8.18616485662449e-09, "epoch": 19.853842527109855, "percentage": 99.27, "elapsed_time": "2:32:21", "remaining_time": "0:01:07", "throughput": 4633.61, "total_tokens": 42359936} {"current_steps": 42115, "total_steps": 42420, "loss": 0.0361, "lr": 7.925073840045483e-09, "epoch": 19.856199905704855, "percentage": 99.28, "elapsed_time": "2:32:22", "remaining_time": "0:01:06", "throughput": 4633.62, "total_tokens": 42365056} {"current_steps": 42120, "total_steps": 42420, "loss": 0.1854, "lr": 7.668213557410209e-09, "epoch": 19.85855728429986, "percentage": 99.29, "elapsed_time": "2:32:23", "remaining_time": "0:01:05", "throughput": 4633.6, "total_tokens": 42369248} {"current_steps": 42125, "total_steps": 42420, "loss": 0.0206, "lr": 7.4155840522033285e-09, "epoch": 19.86091466289486, "percentage": 99.3, "elapsed_time": "2:32:24", "remaining_time": "0:01:04", "throughput": 4633.58, "total_tokens": 42374016} {"current_steps": 42130, "total_steps": 42420, "loss": 0.0815, "lr": 7.167185367187856e-09, "epoch": 19.863272041489864, "percentage": 99.32, "elapsed_time": "2:32:25", "remaining_time": "0:01:02", "throughput": 4633.6, "total_tokens": 42378560} {"current_steps": 42135, "total_steps": 42420, "loss": 0.0156, "lr": 6.923017544410715e-09, "epoch": 19.865629420084865, "percentage": 99.33, "elapsed_time": "2:32:27", "remaining_time": "0:01:01", "throughput": 4633.63, "total_tokens": 42384704} {"current_steps": 42140, "total_steps": 42420, "loss": 0.2035, "lr": 6.6830806252110574e-09, "epoch": 19.86798679867987, "percentage": 99.34, "elapsed_time": "2:32:28", "remaining_time": "0:01:00", "throughput": 4633.61, "total_tokens": 42388992} {"current_steps": 42145, "total_steps": 42420, "loss": 0.0869, "lr": 6.447374650203619e-09, "epoch": 19.87034417727487, "percentage": 99.35, "elapsed_time": "2:32:29", "remaining_time": "0:00:59", "throughput": 4633.62, "total_tokens": 42393888} {"current_steps": 42150, "total_steps": 42420, "loss": 0.0239, "lr": 6.215899659287039e-09, "epoch": 19.872701555869874, "percentage": 99.36, "elapsed_time": "2:32:30", "remaining_time": "0:00:58", "throughput": 4633.65, "total_tokens": 42399168} {"current_steps": 42155, "total_steps": 42420, "loss": 0.0961, "lr": 5.988655691649414e-09, "epoch": 19.875058934464874, "percentage": 99.38, "elapsed_time": "2:32:31", "remaining_time": "0:00:57", "throughput": 4633.67, "total_tokens": 42404096} {"current_steps": 42160, "total_steps": 42420, "loss": 0.1537, "lr": 5.765642785759973e-09, "epoch": 19.87741631305988, "percentage": 99.39, "elapsed_time": "2:32:32", "remaining_time": "0:00:56", "throughput": 4633.7, "total_tokens": 42408864} {"current_steps": 42165, "total_steps": 42420, "loss": 0.1442, "lr": 5.546860979366298e-09, "epoch": 19.87977369165488, "percentage": 99.4, "elapsed_time": "2:32:33", "remaining_time": "0:00:55", "throughput": 4633.74, "total_tokens": 42414944} {"current_steps": 42170, "total_steps": 42420, "loss": 0.3212, "lr": 5.33231030951098e-09, "epoch": 19.882131070249883, "percentage": 99.41, "elapsed_time": "2:32:34", "remaining_time": "0:00:54", "throughput": 4633.75, "total_tokens": 42419424} {"current_steps": 42175, "total_steps": 42420, "loss": 0.1096, "lr": 5.121990812506638e-09, "epoch": 19.884488448844884, "percentage": 99.42, "elapsed_time": "2:32:35", "remaining_time": "0:00:53", "throughput": 4633.76, "total_tokens": 42424640} {"current_steps": 42180, "total_steps": 42420, "loss": 0.0654, "lr": 4.915902523960902e-09, "epoch": 19.88684582743989, "percentage": 99.43, "elapsed_time": "2:32:36", "remaining_time": "0:00:52", "throughput": 4633.78, "total_tokens": 42429824} {"current_steps": 42185, "total_steps": 42420, "loss": 0.067, "lr": 4.7140454787625295e-09, "epoch": 19.88920320603489, "percentage": 99.45, "elapsed_time": "2:32:37", "remaining_time": "0:00:51", "throughput": 4633.8, "total_tokens": 42435008} {"current_steps": 42190, "total_steps": 42420, "loss": 0.0189, "lr": 4.5164197110786346e-09, "epoch": 19.891560584629893, "percentage": 99.46, "elapsed_time": "2:32:38", "remaining_time": "0:00:49", "throughput": 4633.81, "total_tokens": 42439328} {"current_steps": 42195, "total_steps": 42420, "loss": 0.0754, "lr": 4.323025254368562e-09, "epoch": 19.893917963224894, "percentage": 99.47, "elapsed_time": "2:32:39", "remaining_time": "0:00:48", "throughput": 4633.85, "total_tokens": 42444672} {"current_steps": 42200, "total_steps": 42420, "loss": 0.0755, "lr": 4.133862141364464e-09, "epoch": 19.896275341819898, "percentage": 99.48, "elapsed_time": "2:32:41", "remaining_time": "0:00:47", "throughput": 4633.88, "total_tokens": 42451552} {"current_steps": 42205, "total_steps": 42420, "loss": 0.0902, "lr": 3.948930404093498e-09, "epoch": 19.8986327204149, "percentage": 99.49, "elapsed_time": "2:32:42", "remaining_time": "0:00:46", "throughput": 4633.9, "total_tokens": 42456704} {"current_steps": 42210, "total_steps": 42420, "loss": 0.0517, "lr": 3.768230073861179e-09, "epoch": 19.900990099009903, "percentage": 99.5, "elapsed_time": "2:32:43", "remaining_time": "0:00:45", "throughput": 4633.91, "total_tokens": 42460960} {"current_steps": 42215, "total_steps": 42420, "loss": 0.1933, "lr": 3.591761181251374e-09, "epoch": 19.903347477604903, "percentage": 99.52, "elapsed_time": "2:32:44", "remaining_time": "0:00:44", "throughput": 4633.91, "total_tokens": 42465344} {"current_steps": 42220, "total_steps": 42420, "loss": 0.0237, "lr": 3.419523756145737e-09, "epoch": 19.905704856199904, "percentage": 99.53, "elapsed_time": "2:32:45", "remaining_time": "0:00:43", "throughput": 4633.94, "total_tokens": 42471168} {"current_steps": 42225, "total_steps": 42420, "loss": 0.0227, "lr": 3.2515178276959492e-09, "epoch": 19.908062234794908, "percentage": 99.54, "elapsed_time": "2:32:46", "remaining_time": "0:00:42", "throughput": 4633.94, "total_tokens": 42475520} {"current_steps": 42230, "total_steps": 42420, "loss": 0.062, "lr": 3.087743424343148e-09, "epoch": 19.91041961338991, "percentage": 99.55, "elapsed_time": "2:32:47", "remaining_time": "0:00:41", "throughput": 4633.98, "total_tokens": 42482592} {"current_steps": 42235, "total_steps": 42420, "loss": 0.0593, "lr": 2.928200573809603e-09, "epoch": 19.912776991984913, "percentage": 99.56, "elapsed_time": "2:32:48", "remaining_time": "0:00:40", "throughput": 4634.02, "total_tokens": 42488896} {"current_steps": 42240, "total_steps": 42420, "loss": 0.0169, "lr": 2.772889303109816e-09, "epoch": 19.915134370579914, "percentage": 99.58, "elapsed_time": "2:32:49", "remaining_time": "0:00:39", "throughput": 4634.02, "total_tokens": 42493728} {"current_steps": 42245, "total_steps": 42420, "loss": 0.0251, "lr": 2.6218096385283164e-09, "epoch": 19.917491749174918, "percentage": 99.59, "elapsed_time": "2:32:51", "remaining_time": "0:00:37", "throughput": 4634.02, "total_tokens": 42498976} {"current_steps": 42250, "total_steps": 42420, "loss": 0.066, "lr": 2.4749616056446433e-09, "epoch": 19.91984912776992, "percentage": 99.6, "elapsed_time": "2:32:51", "remaining_time": "0:00:36", "throughput": 4633.96, "total_tokens": 42502400} {"current_steps": 42255, "total_steps": 42420, "loss": 0.0596, "lr": 2.3323452293139147e-09, "epoch": 19.922206506364923, "percentage": 99.61, "elapsed_time": "2:32:53", "remaining_time": "0:00:35", "throughput": 4633.98, "total_tokens": 42507712} {"current_steps": 42260, "total_steps": 42420, "loss": 0.1051, "lr": 2.193960533683481e-09, "epoch": 19.924563884959923, "percentage": 99.62, "elapsed_time": "2:32:53", "remaining_time": "0:00:34", "throughput": 4633.97, "total_tokens": 42511584} {"current_steps": 42265, "total_steps": 42420, "loss": 0.0778, "lr": 2.059807542176273e-09, "epoch": 19.926921263554927, "percentage": 99.63, "elapsed_time": "2:32:54", "remaining_time": "0:00:33", "throughput": 4633.99, "total_tokens": 42516384} {"current_steps": 42270, "total_steps": 42420, "loss": 0.0808, "lr": 1.9298862775019024e-09, "epoch": 19.929278642149928, "percentage": 99.65, "elapsed_time": "2:32:55", "remaining_time": "0:00:32", "throughput": 4634.0, "total_tokens": 42520928} {"current_steps": 42275, "total_steps": 42420, "loss": 0.1167, "lr": 1.8041967616566623e-09, "epoch": 19.931636020744932, "percentage": 99.66, "elapsed_time": "2:32:56", "remaining_time": "0:00:31", "throughput": 4634.03, "total_tokens": 42525888} {"current_steps": 42280, "total_steps": 42420, "loss": 0.1305, "lr": 1.6827390159124267e-09, "epoch": 19.933993399339933, "percentage": 99.67, "elapsed_time": "2:32:58", "remaining_time": "0:00:30", "throughput": 4634.04, "total_tokens": 42532128} {"current_steps": 42285, "total_steps": 42420, "loss": 0.0612, "lr": 1.5655130608360768e-09, "epoch": 19.936350777934937, "percentage": 99.68, "elapsed_time": "2:32:59", "remaining_time": "0:00:29", "throughput": 4634.06, "total_tokens": 42537344} {"current_steps": 42290, "total_steps": 42420, "loss": 0.119, "lr": 1.452518916267298e-09, "epoch": 19.938708156529938, "percentage": 99.69, "elapsed_time": "2:33:00", "remaining_time": "0:00:28", "throughput": 4634.1, "total_tokens": 42542688} {"current_steps": 42295, "total_steps": 42420, "loss": 0.1853, "lr": 1.3437566013380088e-09, "epoch": 19.94106553512494, "percentage": 99.71, "elapsed_time": "2:33:01", "remaining_time": "0:00:27", "throughput": 4634.13, "total_tokens": 42548480} {"current_steps": 42300, "total_steps": 42420, "loss": 0.1631, "lr": 1.2392261344557066e-09, "epoch": 19.943422913719942, "percentage": 99.72, "elapsed_time": "2:33:02", "remaining_time": "0:00:26", "throughput": 4634.15, "total_tokens": 42553120} {"current_steps": 42305, "total_steps": 42420, "loss": 0.0843, "lr": 1.1389275333173465e-09, "epoch": 19.945780292314947, "percentage": 99.73, "elapsed_time": "2:33:03", "remaining_time": "0:00:24", "throughput": 4634.15, "total_tokens": 42557344} {"current_steps": 42310, "total_steps": 42420, "loss": 0.1801, "lr": 1.0428608149037899e-09, "epoch": 19.948137670909947, "percentage": 99.74, "elapsed_time": "2:33:04", "remaining_time": "0:00:23", "throughput": 4634.17, "total_tokens": 42563232} {"current_steps": 42315, "total_steps": 42420, "loss": 0.2503, "lr": 9.510259954742529e-10, "epoch": 19.95049504950495, "percentage": 99.75, "elapsed_time": "2:33:05", "remaining_time": "0:00:22", "throughput": 4634.2, "total_tokens": 42568800} {"current_steps": 42320, "total_steps": 42420, "loss": 0.0576, "lr": 8.634230905774088e-10, "epoch": 19.952852428099952, "percentage": 99.76, "elapsed_time": "2:33:06", "remaining_time": "0:00:21", "throughput": 4634.21, "total_tokens": 42574432} {"current_steps": 42325, "total_steps": 42420, "loss": 0.1897, "lr": 7.800521150430617e-10, "epoch": 19.955209806694956, "percentage": 99.78, "elapsed_time": "2:33:08", "remaining_time": "0:00:20", "throughput": 4634.24, "total_tokens": 42580352} {"current_steps": 42330, "total_steps": 42420, "loss": 0.0891, "lr": 7.009130829793709e-10, "epoch": 19.957567185289957, "percentage": 99.79, "elapsed_time": "2:33:09", "remaining_time": "0:00:19", "throughput": 4634.25, "total_tokens": 42584992} {"current_steps": 42335, "total_steps": 42420, "loss": 0.2233, "lr": 6.260060077922791e-10, "epoch": 19.95992456388496, "percentage": 99.8, "elapsed_time": "2:33:10", "remaining_time": "0:00:18", "throughput": 4634.27, "total_tokens": 42589920} {"current_steps": 42340, "total_steps": 42420, "loss": 0.1514, "lr": 5.553309021522069e-10, "epoch": 19.96228194247996, "percentage": 99.81, "elapsed_time": "2:33:11", "remaining_time": "0:00:17", "throughput": 4634.3, "total_tokens": 42595488} {"current_steps": 42345, "total_steps": 42420, "loss": 0.0627, "lr": 4.888877780301338e-10, "epoch": 19.964639321074966, "percentage": 99.82, "elapsed_time": "2:33:12", "remaining_time": "0:00:16", "throughput": 4634.27, "total_tokens": 42599520} {"current_steps": 42350, "total_steps": 42420, "loss": 0.2122, "lr": 4.266766466726191e-10, "epoch": 19.966996699669966, "percentage": 99.83, "elapsed_time": "2:33:13", "remaining_time": "0:00:15", "throughput": 4634.27, "total_tokens": 42604736} {"current_steps": 42355, "total_steps": 42420, "loss": 0.0457, "lr": 3.6869751861012827e-10, "epoch": 19.96935407826497, "percentage": 99.85, "elapsed_time": "2:33:14", "remaining_time": "0:00:14", "throughput": 4634.3, "total_tokens": 42610496} {"current_steps": 42360, "total_steps": 42420, "loss": 0.0513, "lr": 3.1495040365703275e-10, "epoch": 19.97171145685997, "percentage": 99.86, "elapsed_time": "2:33:15", "remaining_time": "0:00:13", "throughput": 4634.33, "total_tokens": 42616320} {"current_steps": 42365, "total_steps": 42420, "loss": 0.0555, "lr": 2.6543531091161033e-10, "epoch": 19.974068835454975, "percentage": 99.87, "elapsed_time": "2:33:16", "remaining_time": "0:00:11", "throughput": 4634.34, "total_tokens": 42621120} {"current_steps": 42370, "total_steps": 42420, "loss": 0.1259, "lr": 2.2015224875882035e-10, "epoch": 19.976426214049976, "percentage": 99.88, "elapsed_time": "2:33:17", "remaining_time": "0:00:10", "throughput": 4634.35, "total_tokens": 42625920} {"current_steps": 42375, "total_steps": 42420, "loss": 0.19, "lr": 1.7910122485920167e-10, "epoch": 19.97878359264498, "percentage": 99.89, "elapsed_time": "2:33:18", "remaining_time": "0:00:09", "throughput": 4634.34, "total_tokens": 42629920} {"current_steps": 42380, "total_steps": 42420, "loss": 0.0506, "lr": 1.4228224616830154e-10, "epoch": 19.98114097123998, "percentage": 99.91, "elapsed_time": "2:33:19", "remaining_time": "0:00:08", "throughput": 4634.36, "total_tokens": 42634688} {"current_steps": 42385, "total_steps": 42420, "loss": 0.1243, "lr": 1.0969531891447115e-10, "epoch": 19.983498349834985, "percentage": 99.92, "elapsed_time": "2:33:20", "remaining_time": "0:00:07", "throughput": 4634.41, "total_tokens": 42641056} {"current_steps": 42390, "total_steps": 42420, "loss": 0.1045, "lr": 8.134044861274337e-11, "epoch": 19.985855728429986, "percentage": 99.93, "elapsed_time": "2:33:22", "remaining_time": "0:00:06", "throughput": 4634.42, "total_tokens": 42646016} {"current_steps": 42395, "total_steps": 42420, "loss": 0.1725, "lr": 5.7217640067608326e-11, "epoch": 19.98821310702499, "percentage": 99.94, "elapsed_time": "2:33:23", "remaining_time": "0:00:05", "throughput": 4634.46, "total_tokens": 42651232} {"current_steps": 42400, "total_steps": 42420, "loss": 0.1962, "lr": 3.7326897361911197e-11, "epoch": 19.99057048561999, "percentage": 99.95, "elapsed_time": "2:33:24", "remaining_time": "0:00:04", "throughput": 4634.49, "total_tokens": 42656512} {"current_steps": 42405, "total_steps": 42420, "loss": 0.0387, "lr": 2.1668223859627744e-11, "epoch": 19.992927864214995, "percentage": 99.96, "elapsed_time": "2:33:25", "remaining_time": "0:00:03", "throughput": 4634.5, "total_tokens": 42661088} {"current_steps": 42410, "total_steps": 42420, "loss": 0.0857, "lr": 1.0241622214191005e-11, "epoch": 19.995285242809995, "percentage": 99.98, "elapsed_time": "2:33:26", "remaining_time": "0:00:02", "throughput": 4634.53, "total_tokens": 42666496} {"current_steps": 42415, "total_steps": 42420, "loss": 0.1275, "lr": 3.0470943573890354e-12, "epoch": 19.997642621405, "percentage": 99.99, "elapsed_time": "2:33:27", "remaining_time": "0:00:01", "throughput": 4634.56, "total_tokens": 42673888} {"current_steps": 42420, "total_steps": 42420, "loss": 0.0778, "lr": 8.464151046716495e-14, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "2:33:28", "remaining_time": "0:00:00", "throughput": 4634.5, "total_tokens": 42678144} {"current_steps": 42420, "total_steps": 42420, "eval_loss": 0.15385045111179352, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "2:33:43", "remaining_time": "0:00:00", "throughput": 4626.86, "total_tokens": 42678144} {"current_steps": 42420, "total_steps": 42420, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "2:33:45", "remaining_time": "0:00:00", "throughput": 4626.13, "total_tokens": 42678144}