{"current_steps": 5, "total_steps": 38160, "loss": 1.2588, "lr": 5.241090146750525e-08, "epoch": 0.002620545073375262, "percentage": 0.01, "elapsed_time": "0:00:01", "remaining_time": "3:47:08", "throughput": 1648.41, "total_tokens": 2944} {"current_steps": 10, "total_steps": 38160, "loss": 1.1171, "lr": 1.1792452830188679e-07, "epoch": 0.005241090146750524, "percentage": 0.03, "elapsed_time": "0:00:02", "remaining_time": "3:03:15", "throughput": 2364.94, "total_tokens": 6816} {"current_steps": 15, "total_steps": 38160, "loss": 1.2245, "lr": 1.8343815513626837e-07, "epoch": 0.007861635220125786, "percentage": 0.04, "elapsed_time": "0:00:03", "remaining_time": "2:48:08", "throughput": 2460.2, "total_tokens": 9760} {"current_steps": 20, "total_steps": 38160, "loss": 1.1659, "lr": 2.489517819706499e-07, "epoch": 0.010482180293501049, "percentage": 0.05, "elapsed_time": "0:00:05", "remaining_time": "2:42:06", "throughput": 2641.35, "total_tokens": 13472} {"current_steps": 25, "total_steps": 38160, "loss": 1.2366, "lr": 3.144654088050315e-07, "epoch": 0.01310272536687631, "percentage": 0.07, "elapsed_time": "0:00:06", "remaining_time": "2:38:30", "throughput": 2704.77, "total_tokens": 16864} {"current_steps": 30, "total_steps": 38160, "loss": 1.3587, "lr": 3.79979035639413e-07, "epoch": 0.015723270440251572, "percentage": 0.08, "elapsed_time": "0:00:07", "remaining_time": "2:35:49", "throughput": 2766.76, "total_tokens": 20352} {"current_steps": 35, "total_steps": 38160, "loss": 1.3345, "lr": 4.454926624737945e-07, "epoch": 0.018343815513626835, "percentage": 0.09, "elapsed_time": "0:00:08", "remaining_time": "2:32:05", "throughput": 2746.29, "total_tokens": 23008} {"current_steps": 40, "total_steps": 38160, "loss": 1.0766, "lr": 5.110062893081761e-07, "epoch": 0.020964360587002098, "percentage": 0.1, "elapsed_time": "0:00:09", "remaining_time": "2:29:21", "throughput": 2756.55, "total_tokens": 25920} {"current_steps": 45, "total_steps": 38160, "loss": 1.2347, "lr": 5.765199161425577e-07, "epoch": 0.02358490566037736, "percentage": 0.12, "elapsed_time": "0:00:10", "remaining_time": "2:27:53", "throughput": 2736.97, "total_tokens": 28672} {"current_steps": 50, "total_steps": 38160, "loss": 1.0794, "lr": 6.420335429769392e-07, "epoch": 0.02620545073375262, "percentage": 0.13, "elapsed_time": "0:00:11", "remaining_time": "2:25:53", "throughput": 2741.93, "total_tokens": 31488} {"current_steps": 55, "total_steps": 38160, "loss": 1.2162, "lr": 7.075471698113208e-07, "epoch": 0.028825995807127882, "percentage": 0.14, "elapsed_time": "0:00:12", "remaining_time": "2:25:18", "throughput": 2741.31, "total_tokens": 34496} {"current_steps": 60, "total_steps": 38160, "loss": 1.2939, "lr": 7.730607966457024e-07, "epoch": 0.031446540880503145, "percentage": 0.16, "elapsed_time": "0:00:13", "remaining_time": "2:25:03", "throughput": 2780.6, "total_tokens": 38112} {"current_steps": 65, "total_steps": 38160, "loss": 1.3709, "lr": 8.38574423480084e-07, "epoch": 0.034067085953878404, "percentage": 0.17, "elapsed_time": "0:00:14", "remaining_time": "2:24:11", "throughput": 2768.31, "total_tokens": 40864} {"current_steps": 70, "total_steps": 38160, "loss": 1.2814, "lr": 9.040880503144654e-07, "epoch": 0.03668763102725367, "percentage": 0.18, "elapsed_time": "0:00:15", "remaining_time": "2:23:44", "throughput": 2788.05, "total_tokens": 44192} {"current_steps": 75, "total_steps": 38160, "loss": 1.407, "lr": 9.69601677148847e-07, "epoch": 0.03930817610062893, "percentage": 0.2, "elapsed_time": "0:00:16", "remaining_time": "2:22:31", "throughput": 2777.94, "total_tokens": 46784} {"current_steps": 80, "total_steps": 38160, "loss": 1.3949, "lr": 1.0351153039832286e-06, "epoch": 0.041928721174004195, "percentage": 0.21, "elapsed_time": "0:00:17", "remaining_time": "2:22:21", "throughput": 2796.1, "total_tokens": 50176} {"current_steps": 85, "total_steps": 38160, "loss": 1.0891, "lr": 1.10062893081761e-06, "epoch": 0.044549266247379454, "percentage": 0.22, "elapsed_time": "0:00:19", "remaining_time": "2:22:22", "throughput": 2852.57, "total_tokens": 54400} {"current_steps": 90, "total_steps": 38160, "loss": 1.4374, "lr": 1.1661425576519918e-06, "epoch": 0.04716981132075472, "percentage": 0.24, "elapsed_time": "0:00:20", "remaining_time": "2:21:38", "throughput": 2836.68, "total_tokens": 56992} {"current_steps": 95, "total_steps": 38160, "loss": 1.0148, "lr": 1.2316561844863732e-06, "epoch": 0.04979035639412998, "percentage": 0.25, "elapsed_time": "0:00:21", "remaining_time": "2:22:14", "throughput": 2859.1, "total_tokens": 60896} {"current_steps": 100, "total_steps": 38160, "loss": 1.1486, "lr": 1.2971698113207548e-06, "epoch": 0.05241090146750524, "percentage": 0.26, "elapsed_time": "0:00:22", "remaining_time": "2:22:00", "throughput": 2884.5, "total_tokens": 64576} {"current_steps": 105, "total_steps": 38160, "loss": 1.3761, "lr": 1.3626834381551364e-06, "epoch": 0.055031446540880505, "percentage": 0.28, "elapsed_time": "0:00:23", "remaining_time": "2:21:28", "throughput": 2886.92, "total_tokens": 67616} {"current_steps": 110, "total_steps": 38160, "loss": 1.0211, "lr": 1.4281970649895177e-06, "epoch": 0.057651991614255764, "percentage": 0.29, "elapsed_time": "0:00:24", "remaining_time": "2:22:41", "throughput": 2931.01, "total_tokens": 72544} {"current_steps": 115, "total_steps": 38160, "loss": 1.2894, "lr": 1.4937106918238995e-06, "epoch": 0.06027253668763103, "percentage": 0.3, "elapsed_time": "0:00:25", "remaining_time": "2:22:25", "throughput": 2928.73, "total_tokens": 75648} {"current_steps": 120, "total_steps": 38160, "loss": 1.3719, "lr": 1.559224318658281e-06, "epoch": 0.06289308176100629, "percentage": 0.31, "elapsed_time": "0:00:26", "remaining_time": "2:21:36", "throughput": 2924.03, "total_tokens": 78368} {"current_steps": 125, "total_steps": 38160, "loss": 1.221, "lr": 1.6247379454926625e-06, "epoch": 0.06551362683438156, "percentage": 0.33, "elapsed_time": "0:00:27", "remaining_time": "2:21:28", "throughput": 2937.75, "total_tokens": 81952} {"current_steps": 130, "total_steps": 38160, "loss": 1.1627, "lr": 1.690251572327044e-06, "epoch": 0.06813417190775681, "percentage": 0.34, "elapsed_time": "0:00:28", "remaining_time": "2:20:51", "throughput": 2940.95, "total_tokens": 84960} {"current_steps": 135, "total_steps": 38160, "loss": 1.2821, "lr": 1.7557651991614257e-06, "epoch": 0.07075471698113207, "percentage": 0.35, "elapsed_time": "0:00:29", "remaining_time": "2:20:45", "throughput": 2954.02, "total_tokens": 88576} {"current_steps": 140, "total_steps": 38160, "loss": 0.9797, "lr": 1.821278825995807e-06, "epoch": 0.07337526205450734, "percentage": 0.37, "elapsed_time": "0:00:31", "remaining_time": "2:20:30", "throughput": 2968.69, "total_tokens": 92160} {"current_steps": 145, "total_steps": 38160, "loss": 1.0781, "lr": 1.8867924528301887e-06, "epoch": 0.0759958071278826, "percentage": 0.38, "elapsed_time": "0:00:32", "remaining_time": "2:20:17", "throughput": 2985.18, "total_tokens": 95840} {"current_steps": 150, "total_steps": 38160, "loss": 1.1061, "lr": 1.9523060796645703e-06, "epoch": 0.07861635220125786, "percentage": 0.39, "elapsed_time": "0:00:33", "remaining_time": "2:19:55", "throughput": 2982.66, "total_tokens": 98816} {"current_steps": 155, "total_steps": 38160, "loss": 0.9152, "lr": 2.017819706498952e-06, "epoch": 0.08123689727463312, "percentage": 0.41, "elapsed_time": "0:00:34", "remaining_time": "2:19:57", "throughput": 3003.75, "total_tokens": 102880} {"current_steps": 160, "total_steps": 38160, "loss": 1.0812, "lr": 2.0833333333333334e-06, "epoch": 0.08385744234800839, "percentage": 0.42, "elapsed_time": "0:00:35", "remaining_time": "2:19:23", "throughput": 3007.96, "total_tokens": 105920} {"current_steps": 165, "total_steps": 38160, "loss": 1.2431, "lr": 2.148846960167715e-06, "epoch": 0.08647798742138364, "percentage": 0.43, "elapsed_time": "0:00:36", "remaining_time": "2:19:11", "throughput": 3000.04, "total_tokens": 108800} {"current_steps": 170, "total_steps": 38160, "loss": 0.9619, "lr": 2.2143605870020966e-06, "epoch": 0.08909853249475891, "percentage": 0.45, "elapsed_time": "0:00:37", "remaining_time": "2:18:40", "throughput": 3007.3, "total_tokens": 111968} {"current_steps": 175, "total_steps": 38160, "loss": 1.0127, "lr": 2.279874213836478e-06, "epoch": 0.09171907756813417, "percentage": 0.46, "elapsed_time": "0:00:38", "remaining_time": "2:18:22", "throughput": 3005.89, "total_tokens": 114976} {"current_steps": 180, "total_steps": 38160, "loss": 1.16, "lr": 2.34538784067086e-06, "epoch": 0.09433962264150944, "percentage": 0.47, "elapsed_time": "0:00:39", "remaining_time": "2:18:03", "throughput": 2994.6, "total_tokens": 117568} {"current_steps": 185, "total_steps": 38160, "loss": 0.8258, "lr": 2.410901467505241e-06, "epoch": 0.09696016771488469, "percentage": 0.48, "elapsed_time": "0:00:40", "remaining_time": "2:17:39", "throughput": 2991.7, "total_tokens": 120384} {"current_steps": 190, "total_steps": 38160, "loss": 0.8277, "lr": 2.476415094339623e-06, "epoch": 0.09958071278825996, "percentage": 0.5, "elapsed_time": "0:00:41", "remaining_time": "2:17:20", "throughput": 2999.25, "total_tokens": 123680} {"current_steps": 195, "total_steps": 38160, "loss": 0.9592, "lr": 2.5419287211740044e-06, "epoch": 0.10220125786163523, "percentage": 0.51, "elapsed_time": "0:00:42", "remaining_time": "2:17:16", "throughput": 3005.8, "total_tokens": 127168} {"current_steps": 200, "total_steps": 38160, "loss": 0.7008, "lr": 2.6074423480083857e-06, "epoch": 0.10482180293501048, "percentage": 0.52, "elapsed_time": "0:00:43", "remaining_time": "2:16:56", "throughput": 3007.15, "total_tokens": 130176} {"current_steps": 205, "total_steps": 38160, "loss": 0.8399, "lr": 2.6729559748427675e-06, "epoch": 0.10744234800838574, "percentage": 0.54, "elapsed_time": "0:00:44", "remaining_time": "2:16:36", "throughput": 3005.61, "total_tokens": 133056} {"current_steps": 210, "total_steps": 38160, "loss": 0.665, "lr": 2.738469601677149e-06, "epoch": 0.11006289308176101, "percentage": 0.55, "elapsed_time": "0:00:45", "remaining_time": "2:16:56", "throughput": 3010.04, "total_tokens": 136864} {"current_steps": 215, "total_steps": 38160, "loss": 0.9658, "lr": 2.8039832285115303e-06, "epoch": 0.11268343815513626, "percentage": 0.56, "elapsed_time": "0:00:46", "remaining_time": "2:16:49", "throughput": 3011.22, "total_tokens": 140064} {"current_steps": 220, "total_steps": 38160, "loss": 0.7364, "lr": 2.869496855345912e-06, "epoch": 0.11530398322851153, "percentage": 0.58, "elapsed_time": "0:00:47", "remaining_time": "2:16:39", "throughput": 3022.47, "total_tokens": 143712} {"current_steps": 225, "total_steps": 38160, "loss": 0.7104, "lr": 2.935010482180294e-06, "epoch": 0.1179245283018868, "percentage": 0.59, "elapsed_time": "0:00:48", "remaining_time": "2:16:36", "throughput": 3021.39, "total_tokens": 146880} {"current_steps": 230, "total_steps": 38160, "loss": 0.6654, "lr": 3.0005241090146753e-06, "epoch": 0.12054507337526206, "percentage": 0.6, "elapsed_time": "0:00:49", "remaining_time": "2:16:34", "throughput": 3029.92, "total_tokens": 150560} {"current_steps": 235, "total_steps": 38160, "loss": 0.8498, "lr": 3.0660377358490567e-06, "epoch": 0.12316561844863731, "percentage": 0.62, "elapsed_time": "0:00:50", "remaining_time": "2:16:29", "throughput": 3028.03, "total_tokens": 153664} {"current_steps": 240, "total_steps": 38160, "loss": 0.5954, "lr": 3.131551362683438e-06, "epoch": 0.12578616352201258, "percentage": 0.63, "elapsed_time": "0:00:51", "remaining_time": "2:16:25", "throughput": 3041.49, "total_tokens": 157568} {"current_steps": 245, "total_steps": 38160, "loss": 0.6299, "lr": 3.1970649895178203e-06, "epoch": 0.12840670859538783, "percentage": 0.64, "elapsed_time": "0:00:52", "remaining_time": "2:16:20", "throughput": 3036.43, "total_tokens": 160512} {"current_steps": 250, "total_steps": 38160, "loss": 0.5946, "lr": 3.2625786163522012e-06, "epoch": 0.1310272536687631, "percentage": 0.66, "elapsed_time": "0:00:54", "remaining_time": "2:16:30", "throughput": 3045.71, "total_tokens": 164512} {"current_steps": 255, "total_steps": 38160, "loss": 0.562, "lr": 3.3280922431865826e-06, "epoch": 0.13364779874213836, "percentage": 0.67, "elapsed_time": "0:00:55", "remaining_time": "2:16:17", "throughput": 3039.15, "total_tokens": 167200} {"current_steps": 260, "total_steps": 38160, "loss": 0.6459, "lr": 3.393605870020965e-06, "epoch": 0.13626834381551362, "percentage": 0.68, "elapsed_time": "0:00:56", "remaining_time": "2:16:15", "throughput": 3030.73, "total_tokens": 169984} {"current_steps": 265, "total_steps": 38160, "loss": 0.5688, "lr": 3.459119496855346e-06, "epoch": 0.1388888888888889, "percentage": 0.69, "elapsed_time": "0:00:57", "remaining_time": "2:16:23", "throughput": 3037.92, "total_tokens": 173856} {"current_steps": 270, "total_steps": 38160, "loss": 0.662, "lr": 3.524633123689727e-06, "epoch": 0.14150943396226415, "percentage": 0.71, "elapsed_time": "0:00:58", "remaining_time": "2:16:15", "throughput": 3024.41, "total_tokens": 176192} {"current_steps": 275, "total_steps": 38160, "loss": 0.4491, "lr": 3.5901467505241094e-06, "epoch": 0.1441299790356394, "percentage": 0.72, "elapsed_time": "0:00:59", "remaining_time": "2:16:19", "throughput": 3028.89, "total_tokens": 179840} {"current_steps": 280, "total_steps": 38160, "loss": 0.5351, "lr": 3.6556603773584908e-06, "epoch": 0.14675052410901468, "percentage": 0.73, "elapsed_time": "0:01:00", "remaining_time": "2:16:08", "throughput": 3030.6, "total_tokens": 182976} {"current_steps": 285, "total_steps": 38160, "loss": 0.5822, "lr": 3.7211740041928726e-06, "epoch": 0.14937106918238993, "percentage": 0.75, "elapsed_time": "0:01:01", "remaining_time": "2:15:59", "throughput": 3035.82, "total_tokens": 186400} {"current_steps": 290, "total_steps": 38160, "loss": 0.5798, "lr": 3.786687631027254e-06, "epoch": 0.1519916142557652, "percentage": 0.76, "elapsed_time": "0:01:02", "remaining_time": "2:16:04", "throughput": 3041.15, "total_tokens": 190144} {"current_steps": 295, "total_steps": 38160, "loss": 0.6191, "lr": 3.852201257861635e-06, "epoch": 0.15461215932914046, "percentage": 0.77, "elapsed_time": "0:01:03", "remaining_time": "2:16:12", "throughput": 3036.62, "total_tokens": 193344} {"current_steps": 300, "total_steps": 38160, "loss": 0.4113, "lr": 3.917714884696017e-06, "epoch": 0.15723270440251572, "percentage": 0.79, "elapsed_time": "0:01:04", "remaining_time": "2:16:09", "throughput": 3026.21, "total_tokens": 195904} {"current_steps": 305, "total_steps": 38160, "loss": 0.5717, "lr": 3.9832285115303985e-06, "epoch": 0.159853249475891, "percentage": 0.8, "elapsed_time": "0:01:05", "remaining_time": "2:16:01", "throughput": 3025.4, "total_tokens": 198944} {"current_steps": 310, "total_steps": 38160, "loss": 0.5535, "lr": 4.04874213836478e-06, "epoch": 0.16247379454926625, "percentage": 0.81, "elapsed_time": "0:01:06", "remaining_time": "2:15:55", "throughput": 3020.9, "total_tokens": 201792} {"current_steps": 315, "total_steps": 38160, "loss": 0.5157, "lr": 4.114255765199162e-06, "epoch": 0.1650943396226415, "percentage": 0.83, "elapsed_time": "0:01:07", "remaining_time": "2:16:02", "throughput": 3033.28, "total_tokens": 206080} {"current_steps": 320, "total_steps": 38160, "loss": 0.6303, "lr": 4.1797693920335435e-06, "epoch": 0.16771488469601678, "percentage": 0.84, "elapsed_time": "0:01:08", "remaining_time": "2:15:55", "throughput": 3035.98, "total_tokens": 209376} {"current_steps": 325, "total_steps": 38160, "loss": 0.6296, "lr": 4.245283018867925e-06, "epoch": 0.17033542976939203, "percentage": 0.85, "elapsed_time": "0:01:09", "remaining_time": "2:15:43", "throughput": 3033.05, "total_tokens": 212160} {"current_steps": 330, "total_steps": 38160, "loss": 0.5717, "lr": 4.310796645702306e-06, "epoch": 0.17295597484276728, "percentage": 0.86, "elapsed_time": "0:01:11", "remaining_time": "2:15:39", "throughput": 3043.79, "total_tokens": 216128} {"current_steps": 335, "total_steps": 38160, "loss": 0.7549, "lr": 4.376310272536688e-06, "epoch": 0.17557651991614256, "percentage": 0.88, "elapsed_time": "0:01:12", "remaining_time": "2:15:30", "throughput": 3044.65, "total_tokens": 219232} {"current_steps": 340, "total_steps": 38160, "loss": 0.489, "lr": 4.441823899371069e-06, "epoch": 0.17819706498951782, "percentage": 0.89, "elapsed_time": "0:01:13", "remaining_time": "2:15:36", "throughput": 3041.44, "total_tokens": 222464} {"current_steps": 345, "total_steps": 38160, "loss": 0.7478, "lr": 4.507337526205451e-06, "epoch": 0.18081761006289307, "percentage": 0.9, "elapsed_time": "0:01:14", "remaining_time": "2:15:31", "throughput": 3035.45, "total_tokens": 225184} {"current_steps": 350, "total_steps": 38160, "loss": 0.5011, "lr": 4.572851153039833e-06, "epoch": 0.18343815513626835, "percentage": 0.92, "elapsed_time": "0:01:15", "remaining_time": "2:15:29", "throughput": 3029.68, "total_tokens": 228000} {"current_steps": 355, "total_steps": 38160, "loss": 0.4632, "lr": 4.638364779874214e-06, "epoch": 0.1860587002096436, "percentage": 0.93, "elapsed_time": "0:01:16", "remaining_time": "2:15:22", "throughput": 3027.96, "total_tokens": 230944} {"current_steps": 360, "total_steps": 38160, "loss": 0.4807, "lr": 4.703878406708595e-06, "epoch": 0.18867924528301888, "percentage": 0.94, "elapsed_time": "0:01:17", "remaining_time": "2:15:11", "throughput": 3025.6, "total_tokens": 233728} {"current_steps": 365, "total_steps": 38160, "loss": 0.509, "lr": 4.769392033542977e-06, "epoch": 0.19129979035639413, "percentage": 0.96, "elapsed_time": "0:01:18", "remaining_time": "2:15:04", "throughput": 3021.39, "total_tokens": 236480} {"current_steps": 370, "total_steps": 38160, "loss": 0.5022, "lr": 4.834905660377359e-06, "epoch": 0.19392033542976939, "percentage": 0.97, "elapsed_time": "0:01:19", "remaining_time": "2:15:00", "throughput": 3019.46, "total_tokens": 239488} {"current_steps": 375, "total_steps": 38160, "loss": 0.6116, "lr": 4.90041928721174e-06, "epoch": 0.19654088050314467, "percentage": 0.98, "elapsed_time": "0:01:20", "remaining_time": "2:14:54", "throughput": 3014.05, "total_tokens": 242144} {"current_steps": 380, "total_steps": 38160, "loss": 0.5404, "lr": 4.965932914046122e-06, "epoch": 0.19916142557651992, "percentage": 1.0, "elapsed_time": "0:01:21", "remaining_time": "2:14:47", "throughput": 3014.44, "total_tokens": 245216} {"current_steps": 385, "total_steps": 38160, "loss": 0.6767, "lr": 5.031446540880504e-06, "epoch": 0.20178197064989517, "percentage": 1.01, "elapsed_time": "0:01:22", "remaining_time": "2:14:56", "throughput": 3025.3, "total_tokens": 249632} {"current_steps": 390, "total_steps": 38160, "loss": 0.5798, "lr": 5.096960167714885e-06, "epoch": 0.20440251572327045, "percentage": 1.02, "elapsed_time": "0:01:23", "remaining_time": "2:14:57", "throughput": 3029.71, "total_tokens": 253312} {"current_steps": 395, "total_steps": 38160, "loss": 0.5217, "lr": 5.162473794549266e-06, "epoch": 0.2070230607966457, "percentage": 1.04, "elapsed_time": "0:01:24", "remaining_time": "2:14:48", "throughput": 3030.44, "total_tokens": 256384} {"current_steps": 400, "total_steps": 38160, "loss": 0.5806, "lr": 5.227987421383648e-06, "epoch": 0.20964360587002095, "percentage": 1.05, "elapsed_time": "0:01:25", "remaining_time": "2:14:57", "throughput": 3028.11, "total_tokens": 259744} {"current_steps": 405, "total_steps": 38160, "loss": 0.7239, "lr": 5.2935010482180295e-06, "epoch": 0.21226415094339623, "percentage": 1.06, "elapsed_time": "0:01:26", "remaining_time": "2:14:52", "throughput": 3034.87, "total_tokens": 263456} {"current_steps": 410, "total_steps": 38160, "loss": 0.5317, "lr": 5.359014675052411e-06, "epoch": 0.2148846960167715, "percentage": 1.07, "elapsed_time": "0:01:27", "remaining_time": "2:14:45", "throughput": 3034.74, "total_tokens": 266496} {"current_steps": 415, "total_steps": 38160, "loss": 0.6346, "lr": 5.424528301886793e-06, "epoch": 0.21750524109014674, "percentage": 1.09, "elapsed_time": "0:01:28", "remaining_time": "2:14:36", "throughput": 3036.19, "total_tokens": 269600} {"current_steps": 420, "total_steps": 38160, "loss": 0.5527, "lr": 5.4900419287211744e-06, "epoch": 0.22012578616352202, "percentage": 1.1, "elapsed_time": "0:01:29", "remaining_time": "2:14:36", "throughput": 3039.1, "total_tokens": 273152} {"current_steps": 425, "total_steps": 38160, "loss": 0.7132, "lr": 5.555555555555556e-06, "epoch": 0.22274633123689727, "percentage": 1.11, "elapsed_time": "0:01:31", "remaining_time": "2:14:42", "throughput": 3042.64, "total_tokens": 276992} {"current_steps": 430, "total_steps": 38160, "loss": 0.6571, "lr": 5.621069182389937e-06, "epoch": 0.22536687631027252, "percentage": 1.13, "elapsed_time": "0:01:32", "remaining_time": "2:14:32", "throughput": 3035.68, "total_tokens": 279296} {"current_steps": 435, "total_steps": 38160, "loss": 0.4393, "lr": 5.686582809224319e-06, "epoch": 0.2279874213836478, "percentage": 1.14, "elapsed_time": "0:01:33", "remaining_time": "2:14:36", "throughput": 3041.94, "total_tokens": 283296} {"current_steps": 440, "total_steps": 38160, "loss": 0.729, "lr": 5.752096436058701e-06, "epoch": 0.23060796645702306, "percentage": 1.15, "elapsed_time": "0:01:34", "remaining_time": "2:14:26", "throughput": 3039.68, "total_tokens": 286016} {"current_steps": 445, "total_steps": 38160, "loss": 0.5834, "lr": 5.817610062893082e-06, "epoch": 0.23322851153039834, "percentage": 1.17, "elapsed_time": "0:01:35", "remaining_time": "2:14:22", "throughput": 3040.44, "total_tokens": 289248} {"current_steps": 450, "total_steps": 38160, "loss": 0.6264, "lr": 5.8831236897274636e-06, "epoch": 0.2358490566037736, "percentage": 1.18, "elapsed_time": "0:01:36", "remaining_time": "2:14:17", "throughput": 3038.69, "total_tokens": 292160} {"current_steps": 455, "total_steps": 38160, "loss": 0.5522, "lr": 5.948637316561846e-06, "epoch": 0.23846960167714884, "percentage": 1.19, "elapsed_time": "0:01:37", "remaining_time": "2:14:06", "throughput": 3041.18, "total_tokens": 295296} {"current_steps": 460, "total_steps": 38160, "loss": 0.6081, "lr": 6.014150943396227e-06, "epoch": 0.24109014675052412, "percentage": 1.21, "elapsed_time": "0:01:38", "remaining_time": "2:14:08", "throughput": 3048.14, "total_tokens": 299360} {"current_steps": 465, "total_steps": 38160, "loss": 0.5023, "lr": 6.079664570230608e-06, "epoch": 0.24371069182389937, "percentage": 1.22, "elapsed_time": "0:01:39", "remaining_time": "2:14:06", "throughput": 3053.22, "total_tokens": 303072} {"current_steps": 470, "total_steps": 38160, "loss": 0.4862, "lr": 6.14517819706499e-06, "epoch": 0.24633123689727462, "percentage": 1.23, "elapsed_time": "0:01:40", "remaining_time": "2:14:16", "throughput": 3061.77, "total_tokens": 307616} {"current_steps": 475, "total_steps": 38160, "loss": 0.5074, "lr": 6.210691823899371e-06, "epoch": 0.2489517819706499, "percentage": 1.24, "elapsed_time": "0:01:41", "remaining_time": "2:14:10", "throughput": 3056.06, "total_tokens": 310112} {"current_steps": 480, "total_steps": 38160, "loss": 0.4848, "lr": 6.2762054507337535e-06, "epoch": 0.25157232704402516, "percentage": 1.26, "elapsed_time": "0:01:42", "remaining_time": "2:14:06", "throughput": 3057.99, "total_tokens": 313472} {"current_steps": 485, "total_steps": 38160, "loss": 0.5105, "lr": 6.341719077568134e-06, "epoch": 0.25419287211740044, "percentage": 1.27, "elapsed_time": "0:01:43", "remaining_time": "2:14:01", "throughput": 3053.96, "total_tokens": 316128} {"current_steps": 490, "total_steps": 38160, "loss": 0.475, "lr": 6.407232704402516e-06, "epoch": 0.25681341719077566, "percentage": 1.28, "elapsed_time": "0:01:44", "remaining_time": "2:14:01", "throughput": 3055.13, "total_tokens": 319584} {"current_steps": 495, "total_steps": 38160, "loss": 0.5692, "lr": 6.472746331236898e-06, "epoch": 0.25943396226415094, "percentage": 1.3, "elapsed_time": "0:01:45", "remaining_time": "2:13:53", "throughput": 3054.45, "total_tokens": 322496} {"current_steps": 500, "total_steps": 38160, "loss": 0.8498, "lr": 6.538259958071278e-06, "epoch": 0.2620545073375262, "percentage": 1.31, "elapsed_time": "0:01:46", "remaining_time": "2:13:44", "throughput": 3051.57, "total_tokens": 325120} {"current_steps": 505, "total_steps": 38160, "loss": 0.6094, "lr": 6.60377358490566e-06, "epoch": 0.26467505241090145, "percentage": 1.32, "elapsed_time": "0:01:47", "remaining_time": "2:13:36", "throughput": 3049.53, "total_tokens": 327840} {"current_steps": 510, "total_steps": 38160, "loss": 0.4201, "lr": 6.669287211740043e-06, "epoch": 0.2672955974842767, "percentage": 1.34, "elapsed_time": "0:01:48", "remaining_time": "2:13:34", "throughput": 3055.88, "total_tokens": 331776} {"current_steps": 515, "total_steps": 38160, "loss": 0.5139, "lr": 6.734800838574423e-06, "epoch": 0.269916142557652, "percentage": 1.35, "elapsed_time": "0:01:49", "remaining_time": "2:14:00", "throughput": 3059.67, "total_tokens": 336544} {"current_steps": 520, "total_steps": 38160, "loss": 0.6796, "lr": 6.800314465408805e-06, "epoch": 0.27253668763102723, "percentage": 1.36, "elapsed_time": "0:01:51", "remaining_time": "2:14:03", "throughput": 3066.44, "total_tokens": 340768} {"current_steps": 525, "total_steps": 38160, "loss": 0.6693, "lr": 6.865828092243188e-06, "epoch": 0.2751572327044025, "percentage": 1.38, "elapsed_time": "0:01:52", "remaining_time": "2:14:00", "throughput": 3060.65, "total_tokens": 343296} {"current_steps": 530, "total_steps": 38160, "loss": 0.3967, "lr": 6.931341719077568e-06, "epoch": 0.2777777777777778, "percentage": 1.39, "elapsed_time": "0:01:53", "remaining_time": "2:13:55", "throughput": 3064.69, "total_tokens": 346848} {"current_steps": 535, "total_steps": 38160, "loss": 0.5686, "lr": 6.9968553459119495e-06, "epoch": 0.280398322851153, "percentage": 1.4, "elapsed_time": "0:01:54", "remaining_time": "2:13:55", "throughput": 3060.09, "total_tokens": 349632} {"current_steps": 540, "total_steps": 38160, "loss": 0.5291, "lr": 7.062368972746332e-06, "epoch": 0.2830188679245283, "percentage": 1.42, "elapsed_time": "0:01:55", "remaining_time": "2:13:53", "throughput": 3061.52, "total_tokens": 353024} {"current_steps": 545, "total_steps": 38160, "loss": 0.5171, "lr": 7.127882599580712e-06, "epoch": 0.2856394129979036, "percentage": 1.43, "elapsed_time": "0:01:56", "remaining_time": "2:13:51", "throughput": 3055.25, "total_tokens": 355552} {"current_steps": 550, "total_steps": 38160, "loss": 0.4898, "lr": 7.1933962264150945e-06, "epoch": 0.2882599580712788, "percentage": 1.44, "elapsed_time": "0:01:57", "remaining_time": "2:13:59", "throughput": 3063.33, "total_tokens": 360128} {"current_steps": 555, "total_steps": 38160, "loss": 0.5362, "lr": 7.258909853249477e-06, "epoch": 0.2908805031446541, "percentage": 1.45, "elapsed_time": "0:01:58", "remaining_time": "2:13:53", "throughput": 3064.64, "total_tokens": 363360} {"current_steps": 560, "total_steps": 38160, "loss": 0.5338, "lr": 7.324423480083858e-06, "epoch": 0.29350104821802936, "percentage": 1.47, "elapsed_time": "0:01:59", "remaining_time": "2:13:47", "throughput": 3062.61, "total_tokens": 366144} {"current_steps": 565, "total_steps": 38160, "loss": 0.5507, "lr": 7.3899371069182395e-06, "epoch": 0.29612159329140464, "percentage": 1.48, "elapsed_time": "0:02:00", "remaining_time": "2:13:46", "throughput": 3060.93, "total_tokens": 369216} {"current_steps": 570, "total_steps": 38160, "loss": 0.6116, "lr": 7.455450733752621e-06, "epoch": 0.29874213836477986, "percentage": 1.49, "elapsed_time": "0:02:01", "remaining_time": "2:13:39", "throughput": 3063.15, "total_tokens": 372512} {"current_steps": 575, "total_steps": 38160, "loss": 0.5496, "lr": 7.520964360587003e-06, "epoch": 0.30136268343815514, "percentage": 1.51, "elapsed_time": "0:02:02", "remaining_time": "2:13:41", "throughput": 3055.51, "total_tokens": 374976} {"current_steps": 580, "total_steps": 38160, "loss": 0.4374, "lr": 7.586477987421384e-06, "epoch": 0.3039832285115304, "percentage": 1.52, "elapsed_time": "0:02:03", "remaining_time": "2:13:40", "throughput": 3050.76, "total_tokens": 377632} {"current_steps": 585, "total_steps": 38160, "loss": 0.6749, "lr": 7.651991614255765e-06, "epoch": 0.30660377358490565, "percentage": 1.53, "elapsed_time": "0:02:04", "remaining_time": "2:13:39", "throughput": 3049.87, "total_tokens": 380768} {"current_steps": 590, "total_steps": 38160, "loss": 0.5122, "lr": 7.717505241090148e-06, "epoch": 0.30922431865828093, "percentage": 1.55, "elapsed_time": "0:02:05", "remaining_time": "2:13:35", "throughput": 3046.97, "total_tokens": 383520} {"current_steps": 595, "total_steps": 38160, "loss": 0.7816, "lr": 7.783018867924528e-06, "epoch": 0.3118448637316562, "percentage": 1.56, "elapsed_time": "0:02:06", "remaining_time": "2:13:32", "throughput": 3045.35, "total_tokens": 386496} {"current_steps": 600, "total_steps": 38160, "loss": 0.5949, "lr": 7.848532494758911e-06, "epoch": 0.31446540880503143, "percentage": 1.57, "elapsed_time": "0:02:08", "remaining_time": "2:13:36", "throughput": 3049.22, "total_tokens": 390464} {"current_steps": 605, "total_steps": 38160, "loss": 0.4512, "lr": 7.914046121593292e-06, "epoch": 0.3170859538784067, "percentage": 1.59, "elapsed_time": "0:02:09", "remaining_time": "2:13:32", "throughput": 3048.17, "total_tokens": 393440} {"current_steps": 610, "total_steps": 38160, "loss": 0.461, "lr": 7.979559748427674e-06, "epoch": 0.319706498951782, "percentage": 1.6, "elapsed_time": "0:02:10", "remaining_time": "2:13:46", "throughput": 3055.1, "total_tokens": 398336} {"current_steps": 615, "total_steps": 38160, "loss": 0.4246, "lr": 8.045073375262055e-06, "epoch": 0.3223270440251572, "percentage": 1.61, "elapsed_time": "0:02:11", "remaining_time": "2:13:48", "throughput": 3053.16, "total_tokens": 401504} {"current_steps": 620, "total_steps": 38160, "loss": 0.5048, "lr": 8.110587002096436e-06, "epoch": 0.3249475890985325, "percentage": 1.62, "elapsed_time": "0:02:12", "remaining_time": "2:13:48", "throughput": 3053.22, "total_tokens": 404864} {"current_steps": 625, "total_steps": 38160, "loss": 0.5725, "lr": 8.176100628930818e-06, "epoch": 0.3275681341719078, "percentage": 1.64, "elapsed_time": "0:02:13", "remaining_time": "2:14:00", "throughput": 3055.16, "total_tokens": 409056} {"current_steps": 630, "total_steps": 38160, "loss": 0.5641, "lr": 8.241614255765199e-06, "epoch": 0.330188679245283, "percentage": 1.65, "elapsed_time": "0:02:14", "remaining_time": "2:13:59", "throughput": 3057.0, "total_tokens": 412544} {"current_steps": 635, "total_steps": 38160, "loss": 0.5394, "lr": 8.307127882599582e-06, "epoch": 0.3328092243186583, "percentage": 1.66, "elapsed_time": "0:02:16", "remaining_time": "2:13:57", "throughput": 3054.91, "total_tokens": 415520} {"current_steps": 640, "total_steps": 38160, "loss": 0.9309, "lr": 8.372641509433962e-06, "epoch": 0.33542976939203356, "percentage": 1.68, "elapsed_time": "0:02:17", "remaining_time": "2:13:57", "throughput": 3047.25, "total_tokens": 417760} {"current_steps": 645, "total_steps": 38160, "loss": 0.5685, "lr": 8.438155136268345e-06, "epoch": 0.3380503144654088, "percentage": 1.69, "elapsed_time": "0:02:18", "remaining_time": "2:14:00", "throughput": 3050.58, "total_tokens": 421728} {"current_steps": 650, "total_steps": 38160, "loss": 0.5014, "lr": 8.503668763102726e-06, "epoch": 0.34067085953878407, "percentage": 1.7, "elapsed_time": "0:02:19", "remaining_time": "2:14:02", "throughput": 3054.44, "total_tokens": 425664} {"current_steps": 655, "total_steps": 38160, "loss": 0.4649, "lr": 8.569182389937106e-06, "epoch": 0.34329140461215935, "percentage": 1.72, "elapsed_time": "0:02:20", "remaining_time": "2:13:59", "throughput": 3054.72, "total_tokens": 428896} {"current_steps": 660, "total_steps": 38160, "loss": 0.5261, "lr": 8.634696016771489e-06, "epoch": 0.34591194968553457, "percentage": 1.73, "elapsed_time": "0:02:21", "remaining_time": "2:13:53", "throughput": 3053.48, "total_tokens": 431744} {"current_steps": 665, "total_steps": 38160, "loss": 0.5443, "lr": 8.70020964360587e-06, "epoch": 0.34853249475890985, "percentage": 1.74, "elapsed_time": "0:02:22", "remaining_time": "2:13:50", "throughput": 3057.67, "total_tokens": 435520} {"current_steps": 670, "total_steps": 38160, "loss": 0.4883, "lr": 8.765723270440252e-06, "epoch": 0.35115303983228513, "percentage": 1.76, "elapsed_time": "0:02:23", "remaining_time": "2:13:46", "throughput": 3057.4, "total_tokens": 438592} {"current_steps": 675, "total_steps": 38160, "loss": 0.5312, "lr": 8.831236897274633e-06, "epoch": 0.35377358490566035, "percentage": 1.77, "elapsed_time": "0:02:24", "remaining_time": "2:13:46", "throughput": 3055.68, "total_tokens": 441664} {"current_steps": 680, "total_steps": 38160, "loss": 0.59, "lr": 8.896750524109015e-06, "epoch": 0.35639412997903563, "percentage": 1.78, "elapsed_time": "0:02:25", "remaining_time": "2:13:44", "throughput": 3055.27, "total_tokens": 444832} {"current_steps": 685, "total_steps": 38160, "loss": 0.6046, "lr": 8.962264150943396e-06, "epoch": 0.3590146750524109, "percentage": 1.8, "elapsed_time": "0:02:26", "remaining_time": "2:13:41", "throughput": 3051.3, "total_tokens": 447392} {"current_steps": 690, "total_steps": 38160, "loss": 0.5575, "lr": 9.027777777777777e-06, "epoch": 0.36163522012578614, "percentage": 1.81, "elapsed_time": "0:02:27", "remaining_time": "2:13:39", "throughput": 3050.66, "total_tokens": 450528} {"current_steps": 695, "total_steps": 38160, "loss": 0.4183, "lr": 9.09329140461216e-06, "epoch": 0.3642557651991614, "percentage": 1.82, "elapsed_time": "0:02:28", "remaining_time": "2:13:37", "throughput": 3049.03, "total_tokens": 453504} {"current_steps": 700, "total_steps": 38160, "loss": 0.6326, "lr": 9.15880503144654e-06, "epoch": 0.3668763102725367, "percentage": 1.83, "elapsed_time": "0:02:29", "remaining_time": "2:13:37", "throughput": 3045.76, "total_tokens": 456288} {"current_steps": 705, "total_steps": 38160, "loss": 0.4041, "lr": 9.224318658280923e-06, "epoch": 0.3694968553459119, "percentage": 1.85, "elapsed_time": "0:02:30", "remaining_time": "2:13:34", "throughput": 3048.34, "total_tokens": 459840} {"current_steps": 710, "total_steps": 38160, "loss": 0.4243, "lr": 9.289832285115305e-06, "epoch": 0.3721174004192872, "percentage": 1.86, "elapsed_time": "0:02:31", "remaining_time": "2:13:31", "throughput": 3049.49, "total_tokens": 463168} {"current_steps": 715, "total_steps": 38160, "loss": 0.4882, "lr": 9.355345911949686e-06, "epoch": 0.3747379454926625, "percentage": 1.87, "elapsed_time": "0:02:32", "remaining_time": "2:13:27", "throughput": 3048.61, "total_tokens": 466112} {"current_steps": 720, "total_steps": 38160, "loss": 0.6441, "lr": 9.420859538784067e-06, "epoch": 0.37735849056603776, "percentage": 1.89, "elapsed_time": "0:02:33", "remaining_time": "2:13:25", "throughput": 3049.95, "total_tokens": 469568} {"current_steps": 725, "total_steps": 38160, "loss": 0.4169, "lr": 9.486373165618449e-06, "epoch": 0.379979035639413, "percentage": 1.9, "elapsed_time": "0:02:35", "remaining_time": "2:13:26", "throughput": 3049.86, "total_tokens": 472896} {"current_steps": 730, "total_steps": 38160, "loss": 0.3374, "lr": 9.551886792452832e-06, "epoch": 0.38259958071278827, "percentage": 1.91, "elapsed_time": "0:02:36", "remaining_time": "2:13:22", "throughput": 3048.12, "total_tokens": 475744} {"current_steps": 735, "total_steps": 38160, "loss": 0.5299, "lr": 9.617400419287211e-06, "epoch": 0.38522012578616355, "percentage": 1.93, "elapsed_time": "0:02:37", "remaining_time": "2:13:52", "throughput": 3050.62, "total_tokens": 481216} {"current_steps": 740, "total_steps": 38160, "loss": 0.5329, "lr": 9.682914046121595e-06, "epoch": 0.38784067085953877, "percentage": 1.94, "elapsed_time": "0:02:38", "remaining_time": "2:13:48", "throughput": 3045.29, "total_tokens": 483488} {"current_steps": 745, "total_steps": 38160, "loss": 0.5875, "lr": 9.748427672955976e-06, "epoch": 0.39046121593291405, "percentage": 1.95, "elapsed_time": "0:02:39", "remaining_time": "2:13:48", "throughput": 3046.68, "total_tokens": 487072} {"current_steps": 750, "total_steps": 38160, "loss": 0.5249, "lr": 9.813941299790357e-06, "epoch": 0.39308176100628933, "percentage": 1.97, "elapsed_time": "0:02:40", "remaining_time": "2:13:47", "throughput": 3047.81, "total_tokens": 490496} {"current_steps": 755, "total_steps": 38160, "loss": 0.4644, "lr": 9.879454926624739e-06, "epoch": 0.39570230607966456, "percentage": 1.98, "elapsed_time": "0:02:41", "remaining_time": "2:13:43", "throughput": 3049.42, "total_tokens": 493824} {"current_steps": 760, "total_steps": 38160, "loss": 0.6809, "lr": 9.94496855345912e-06, "epoch": 0.39832285115303984, "percentage": 1.99, "elapsed_time": "0:02:42", "remaining_time": "2:13:40", "throughput": 3044.44, "total_tokens": 496192} {"current_steps": 765, "total_steps": 38160, "loss": 0.5845, "lr": 1.0010482180293501e-05, "epoch": 0.4009433962264151, "percentage": 2.0, "elapsed_time": "0:02:44", "remaining_time": "2:13:39", "throughput": 3041.06, "total_tokens": 498880} {"current_steps": 770, "total_steps": 38160, "loss": 0.5155, "lr": 1.0075995807127883e-05, "epoch": 0.40356394129979034, "percentage": 2.02, "elapsed_time": "0:02:45", "remaining_time": "2:13:36", "throughput": 3040.72, "total_tokens": 502016} {"current_steps": 775, "total_steps": 38160, "loss": 0.5233, "lr": 1.0141509433962266e-05, "epoch": 0.4061844863731656, "percentage": 2.03, "elapsed_time": "0:02:46", "remaining_time": "2:13:34", "throughput": 3040.34, "total_tokens": 505120} {"current_steps": 780, "total_steps": 38160, "loss": 0.5054, "lr": 1.0207023060796646e-05, "epoch": 0.4088050314465409, "percentage": 2.04, "elapsed_time": "0:02:47", "remaining_time": "2:13:33", "throughput": 3039.7, "total_tokens": 508256} {"current_steps": 785, "total_steps": 38160, "loss": 0.5066, "lr": 1.0272536687631027e-05, "epoch": 0.4114255765199161, "percentage": 2.06, "elapsed_time": "0:02:48", "remaining_time": "2:13:31", "throughput": 3041.48, "total_tokens": 511776} {"current_steps": 790, "total_steps": 38160, "loss": 0.4976, "lr": 1.033805031446541e-05, "epoch": 0.4140461215932914, "percentage": 2.07, "elapsed_time": "0:02:49", "remaining_time": "2:13:25", "throughput": 3039.89, "total_tokens": 514464} {"current_steps": 795, "total_steps": 38160, "loss": 0.5012, "lr": 1.040356394129979e-05, "epoch": 0.4166666666666667, "percentage": 2.08, "elapsed_time": "0:02:50", "remaining_time": "2:13:24", "throughput": 3042.21, "total_tokens": 518144} {"current_steps": 800, "total_steps": 38160, "loss": 0.5248, "lr": 1.0469077568134173e-05, "epoch": 0.4192872117400419, "percentage": 2.1, "elapsed_time": "0:02:51", "remaining_time": "2:13:19", "throughput": 3040.19, "total_tokens": 520768} {"current_steps": 805, "total_steps": 38160, "loss": 0.6468, "lr": 1.0534591194968554e-05, "epoch": 0.4219077568134172, "percentage": 2.11, "elapsed_time": "0:02:52", "remaining_time": "2:13:16", "throughput": 3039.59, "total_tokens": 523808} {"current_steps": 810, "total_steps": 38160, "loss": 0.3761, "lr": 1.0600104821802936e-05, "epoch": 0.42452830188679247, "percentage": 2.12, "elapsed_time": "0:02:53", "remaining_time": "2:13:13", "throughput": 3040.99, "total_tokens": 527136} {"current_steps": 815, "total_steps": 38160, "loss": 0.6178, "lr": 1.0665618448637317e-05, "epoch": 0.4271488469601677, "percentage": 2.14, "elapsed_time": "0:02:54", "remaining_time": "2:13:08", "throughput": 3041.54, "total_tokens": 530240} {"current_steps": 820, "total_steps": 38160, "loss": 0.5103, "lr": 1.0731132075471698e-05, "epoch": 0.429769392033543, "percentage": 2.15, "elapsed_time": "0:02:55", "remaining_time": "2:13:13", "throughput": 3044.75, "total_tokens": 534496} {"current_steps": 825, "total_steps": 38160, "loss": 0.539, "lr": 1.079664570230608e-05, "epoch": 0.43238993710691825, "percentage": 2.16, "elapsed_time": "0:02:56", "remaining_time": "2:13:20", "throughput": 3046.66, "total_tokens": 538624} {"current_steps": 830, "total_steps": 38160, "loss": 0.5068, "lr": 1.0862159329140461e-05, "epoch": 0.4350104821802935, "percentage": 2.18, "elapsed_time": "0:02:57", "remaining_time": "2:13:21", "throughput": 3047.19, "total_tokens": 542112} {"current_steps": 835, "total_steps": 38160, "loss": 0.6292, "lr": 1.0927672955974844e-05, "epoch": 0.43763102725366876, "percentage": 2.19, "elapsed_time": "0:02:58", "remaining_time": "2:13:17", "throughput": 3048.54, "total_tokens": 545408} {"current_steps": 840, "total_steps": 38160, "loss": 0.5048, "lr": 1.0993186582809224e-05, "epoch": 0.44025157232704404, "percentage": 2.2, "elapsed_time": "0:02:59", "remaining_time": "2:13:12", "throughput": 3048.64, "total_tokens": 548416} {"current_steps": 845, "total_steps": 38160, "loss": 0.5326, "lr": 1.1058700209643607e-05, "epoch": 0.44287211740041926, "percentage": 2.21, "elapsed_time": "0:03:00", "remaining_time": "2:13:08", "throughput": 3047.48, "total_tokens": 551264} {"current_steps": 850, "total_steps": 38160, "loss": 0.4212, "lr": 1.1124213836477988e-05, "epoch": 0.44549266247379454, "percentage": 2.23, "elapsed_time": "0:03:01", "remaining_time": "2:13:06", "throughput": 3048.19, "total_tokens": 554592} {"current_steps": 855, "total_steps": 38160, "loss": 0.382, "lr": 1.118972746331237e-05, "epoch": 0.4481132075471698, "percentage": 2.24, "elapsed_time": "0:03:02", "remaining_time": "2:13:01", "throughput": 3051.98, "total_tokens": 558304} {"current_steps": 860, "total_steps": 38160, "loss": 0.5466, "lr": 1.1255241090146751e-05, "epoch": 0.45073375262054505, "percentage": 2.25, "elapsed_time": "0:03:03", "remaining_time": "2:12:56", "throughput": 3051.76, "total_tokens": 561248} {"current_steps": 865, "total_steps": 38160, "loss": 0.3604, "lr": 1.1320754716981132e-05, "epoch": 0.4533542976939203, "percentage": 2.27, "elapsed_time": "0:03:04", "remaining_time": "2:12:52", "throughput": 3051.92, "total_tokens": 564352} {"current_steps": 870, "total_steps": 38160, "loss": 0.482, "lr": 1.1386268343815514e-05, "epoch": 0.4559748427672956, "percentage": 2.28, "elapsed_time": "0:03:05", "remaining_time": "2:12:49", "throughput": 3053.3, "total_tokens": 567712} {"current_steps": 875, "total_steps": 38160, "loss": 0.5337, "lr": 1.1451781970649895e-05, "epoch": 0.4585953878406709, "percentage": 2.29, "elapsed_time": "0:03:06", "remaining_time": "2:12:45", "throughput": 3050.59, "total_tokens": 570240} {"current_steps": 880, "total_steps": 38160, "loss": 0.5573, "lr": 1.1517295597484278e-05, "epoch": 0.4612159329140461, "percentage": 2.31, "elapsed_time": "0:03:07", "remaining_time": "2:12:40", "throughput": 3048.08, "total_tokens": 572768} {"current_steps": 885, "total_steps": 38160, "loss": 0.5539, "lr": 1.158280922431866e-05, "epoch": 0.4638364779874214, "percentage": 2.32, "elapsed_time": "0:03:08", "remaining_time": "2:12:40", "throughput": 3050.39, "total_tokens": 576512} {"current_steps": 890, "total_steps": 38160, "loss": 0.5497, "lr": 1.164832285115304e-05, "epoch": 0.46645702306079667, "percentage": 2.33, "elapsed_time": "0:03:10", "remaining_time": "2:12:37", "throughput": 3048.25, "total_tokens": 579264} {"current_steps": 895, "total_steps": 38160, "loss": 0.5296, "lr": 1.1713836477987422e-05, "epoch": 0.4690775681341719, "percentage": 2.35, "elapsed_time": "0:03:11", "remaining_time": "2:12:35", "throughput": 3042.93, "total_tokens": 581440} {"current_steps": 900, "total_steps": 38160, "loss": 0.3596, "lr": 1.1779350104821804e-05, "epoch": 0.4716981132075472, "percentage": 2.36, "elapsed_time": "0:03:12", "remaining_time": "2:12:33", "throughput": 3042.87, "total_tokens": 584544} {"current_steps": 905, "total_steps": 38160, "loss": 0.5314, "lr": 1.1844863731656185e-05, "epoch": 0.47431865828092246, "percentage": 2.37, "elapsed_time": "0:03:13", "remaining_time": "2:12:30", "throughput": 3045.36, "total_tokens": 588160} {"current_steps": 910, "total_steps": 38160, "loss": 0.4694, "lr": 1.1910377358490566e-05, "epoch": 0.4769392033542977, "percentage": 2.38, "elapsed_time": "0:03:14", "remaining_time": "2:12:25", "throughput": 3041.5, "total_tokens": 590400} {"current_steps": 915, "total_steps": 38160, "loss": 0.4481, "lr": 1.197589098532495e-05, "epoch": 0.47955974842767296, "percentage": 2.4, "elapsed_time": "0:03:15", "remaining_time": "2:12:22", "throughput": 3041.24, "total_tokens": 593440} {"current_steps": 920, "total_steps": 38160, "loss": 0.4679, "lr": 1.204140461215933e-05, "epoch": 0.48218029350104824, "percentage": 2.41, "elapsed_time": "0:03:16", "remaining_time": "2:12:22", "throughput": 3039.93, "total_tokens": 596480} {"current_steps": 925, "total_steps": 38160, "loss": 0.4598, "lr": 1.210691823899371e-05, "epoch": 0.48480083857442346, "percentage": 2.42, "elapsed_time": "0:03:17", "remaining_time": "2:12:20", "throughput": 3038.6, "total_tokens": 599392} {"current_steps": 930, "total_steps": 38160, "loss": 0.4062, "lr": 1.2172431865828094e-05, "epoch": 0.48742138364779874, "percentage": 2.44, "elapsed_time": "0:03:18", "remaining_time": "2:12:18", "throughput": 3037.92, "total_tokens": 602432} {"current_steps": 935, "total_steps": 38160, "loss": 0.4458, "lr": 1.2237945492662473e-05, "epoch": 0.490041928721174, "percentage": 2.45, "elapsed_time": "0:03:19", "remaining_time": "2:12:15", "throughput": 3032.89, "total_tokens": 604512} {"current_steps": 940, "total_steps": 38160, "loss": 0.4398, "lr": 1.2303459119496856e-05, "epoch": 0.49266247379454925, "percentage": 2.46, "elapsed_time": "0:03:20", "remaining_time": "2:12:17", "throughput": 3037.22, "total_tokens": 608864} {"current_steps": 945, "total_steps": 38160, "loss": 0.504, "lr": 1.2368972746331238e-05, "epoch": 0.49528301886792453, "percentage": 2.48, "elapsed_time": "0:03:21", "remaining_time": "2:12:18", "throughput": 3038.22, "total_tokens": 612448} {"current_steps": 950, "total_steps": 38160, "loss": 0.4647, "lr": 1.243448637316562e-05, "epoch": 0.4979035639412998, "percentage": 2.49, "elapsed_time": "0:03:22", "remaining_time": "2:12:18", "throughput": 3034.15, "total_tokens": 614944} {"current_steps": 955, "total_steps": 38160, "loss": 0.4782, "lr": 1.25e-05, "epoch": 0.500524109014675, "percentage": 2.5, "elapsed_time": "0:03:23", "remaining_time": "2:12:15", "throughput": 3031.49, "total_tokens": 617472} {"current_steps": 960, "total_steps": 38160, "loss": 0.431, "lr": 1.2565513626834382e-05, "epoch": 0.5031446540880503, "percentage": 2.52, "elapsed_time": "0:03:24", "remaining_time": "2:12:12", "throughput": 3029.43, "total_tokens": 620192} {"current_steps": 965, "total_steps": 38160, "loss": 0.5388, "lr": 1.2631027253668765e-05, "epoch": 0.5057651991614256, "percentage": 2.53, "elapsed_time": "0:03:25", "remaining_time": "2:12:11", "throughput": 3028.69, "total_tokens": 623232} {"current_steps": 970, "total_steps": 38160, "loss": 0.642, "lr": 1.2696540880503146e-05, "epoch": 0.5083857442348009, "percentage": 2.54, "elapsed_time": "0:03:26", "remaining_time": "2:12:10", "throughput": 3026.57, "total_tokens": 626016} {"current_steps": 975, "total_steps": 38160, "loss": 0.4599, "lr": 1.2762054507337526e-05, "epoch": 0.5110062893081762, "percentage": 2.56, "elapsed_time": "0:03:27", "remaining_time": "2:12:10", "throughput": 3027.32, "total_tokens": 629472} {"current_steps": 980, "total_steps": 38160, "loss": 0.5402, "lr": 1.2827568134171907e-05, "epoch": 0.5136268343815513, "percentage": 2.57, "elapsed_time": "0:03:28", "remaining_time": "2:12:05", "throughput": 3028.12, "total_tokens": 632608} {"current_steps": 985, "total_steps": 38160, "loss": 0.393, "lr": 1.289308176100629e-05, "epoch": 0.5162473794549266, "percentage": 2.58, "elapsed_time": "0:03:29", "remaining_time": "2:12:03", "throughput": 3030.29, "total_tokens": 636192} {"current_steps": 990, "total_steps": 38160, "loss": 0.4694, "lr": 1.2958595387840672e-05, "epoch": 0.5188679245283019, "percentage": 2.59, "elapsed_time": "0:03:31", "remaining_time": "2:12:06", "throughput": 3033.88, "total_tokens": 640544} {"current_steps": 995, "total_steps": 38160, "loss": 0.459, "lr": 1.3024109014675053e-05, "epoch": 0.5214884696016772, "percentage": 2.61, "elapsed_time": "0:03:32", "remaining_time": "2:12:09", "throughput": 3035.82, "total_tokens": 644448} {"current_steps": 1000, "total_steps": 38160, "loss": 0.4476, "lr": 1.3089622641509436e-05, "epoch": 0.5241090146750524, "percentage": 2.62, "elapsed_time": "0:03:33", "remaining_time": "2:12:08", "throughput": 3038.53, "total_tokens": 648288} {"current_steps": 1005, "total_steps": 38160, "loss": 0.6344, "lr": 1.3155136268343814e-05, "epoch": 0.5267295597484277, "percentage": 2.63, "elapsed_time": "0:03:34", "remaining_time": "2:12:05", "throughput": 3038.11, "total_tokens": 651296} {"current_steps": 1010, "total_steps": 38160, "loss": 0.3945, "lr": 1.3220649895178197e-05, "epoch": 0.5293501048218029, "percentage": 2.65, "elapsed_time": "0:03:35", "remaining_time": "2:12:02", "throughput": 3037.17, "total_tokens": 654176} {"current_steps": 1015, "total_steps": 38160, "loss": 0.5206, "lr": 1.3286163522012579e-05, "epoch": 0.5319706498951782, "percentage": 2.66, "elapsed_time": "0:03:36", "remaining_time": "2:11:59", "throughput": 3038.88, "total_tokens": 657664} {"current_steps": 1020, "total_steps": 38160, "loss": 0.5941, "lr": 1.3351677148846962e-05, "epoch": 0.5345911949685535, "percentage": 2.67, "elapsed_time": "0:03:37", "remaining_time": "2:11:56", "throughput": 3036.13, "total_tokens": 660064} {"current_steps": 1025, "total_steps": 38160, "loss": 0.5872, "lr": 1.3417190775681343e-05, "epoch": 0.5372117400419287, "percentage": 2.69, "elapsed_time": "0:03:38", "remaining_time": "2:11:53", "throughput": 3034.95, "total_tokens": 662880} {"current_steps": 1030, "total_steps": 38160, "loss": 0.428, "lr": 1.3482704402515725e-05, "epoch": 0.539832285115304, "percentage": 2.7, "elapsed_time": "0:03:39", "remaining_time": "2:11:50", "throughput": 3034.44, "total_tokens": 665920} {"current_steps": 1035, "total_steps": 38160, "loss": 0.4367, "lr": 1.3548218029350104e-05, "epoch": 0.5424528301886793, "percentage": 2.71, "elapsed_time": "0:03:40", "remaining_time": "2:11:48", "throughput": 3033.49, "total_tokens": 668864} {"current_steps": 1040, "total_steps": 38160, "loss": 0.4442, "lr": 1.3613731656184486e-05, "epoch": 0.5450733752620545, "percentage": 2.73, "elapsed_time": "0:03:41", "remaining_time": "2:11:46", "throughput": 3032.48, "total_tokens": 671776} {"current_steps": 1045, "total_steps": 38160, "loss": 0.5206, "lr": 1.3679245283018869e-05, "epoch": 0.5476939203354297, "percentage": 2.74, "elapsed_time": "0:03:42", "remaining_time": "2:11:44", "throughput": 3032.67, "total_tokens": 674912} {"current_steps": 1050, "total_steps": 38160, "loss": 0.3837, "lr": 1.374475890985325e-05, "epoch": 0.550314465408805, "percentage": 2.75, "elapsed_time": "0:03:43", "remaining_time": "2:11:41", "throughput": 3034.12, "total_tokens": 678368} {"current_steps": 1055, "total_steps": 38160, "loss": 0.5459, "lr": 1.3810272536687632e-05, "epoch": 0.5529350104821803, "percentage": 2.76, "elapsed_time": "0:03:44", "remaining_time": "2:11:43", "throughput": 3036.27, "total_tokens": 682336} {"current_steps": 1060, "total_steps": 38160, "loss": 0.4788, "lr": 1.3875786163522015e-05, "epoch": 0.5555555555555556, "percentage": 2.78, "elapsed_time": "0:03:45", "remaining_time": "2:11:43", "throughput": 3037.0, "total_tokens": 685760} {"current_steps": 1065, "total_steps": 38160, "loss": 0.416, "lr": 1.3941299790356394e-05, "epoch": 0.5581761006289309, "percentage": 2.79, "elapsed_time": "0:03:46", "remaining_time": "2:11:39", "throughput": 3035.59, "total_tokens": 688480} {"current_steps": 1070, "total_steps": 38160, "loss": 0.5682, "lr": 1.4006813417190776e-05, "epoch": 0.560796645702306, "percentage": 2.8, "elapsed_time": "0:03:47", "remaining_time": "2:11:38", "throughput": 3037.4, "total_tokens": 692064} {"current_steps": 1075, "total_steps": 38160, "loss": 0.5657, "lr": 1.4072327044025157e-05, "epoch": 0.5634171907756813, "percentage": 2.82, "elapsed_time": "0:03:48", "remaining_time": "2:11:34", "throughput": 3034.74, "total_tokens": 694464} {"current_steps": 1080, "total_steps": 38160, "loss": 0.4907, "lr": 1.413784067085954e-05, "epoch": 0.5660377358490566, "percentage": 2.83, "elapsed_time": "0:03:49", "remaining_time": "2:11:31", "throughput": 3033.97, "total_tokens": 697344} {"current_steps": 1085, "total_steps": 38160, "loss": 0.4683, "lr": 1.4203354297693922e-05, "epoch": 0.5686582809224319, "percentage": 2.84, "elapsed_time": "0:03:50", "remaining_time": "2:11:29", "throughput": 3032.92, "total_tokens": 700256} {"current_steps": 1090, "total_steps": 38160, "loss": 0.4493, "lr": 1.4268867924528303e-05, "epoch": 0.5712788259958071, "percentage": 2.86, "elapsed_time": "0:03:51", "remaining_time": "2:11:29", "throughput": 3034.71, "total_tokens": 703968} {"current_steps": 1095, "total_steps": 38160, "loss": 0.4699, "lr": 1.4334381551362683e-05, "epoch": 0.5738993710691824, "percentage": 2.87, "elapsed_time": "0:03:53", "remaining_time": "2:11:33", "throughput": 3036.79, "total_tokens": 708160} {"current_steps": 1100, "total_steps": 38160, "loss": 0.6817, "lr": 1.4399895178197064e-05, "epoch": 0.5765199161425576, "percentage": 2.88, "elapsed_time": "0:03:54", "remaining_time": "2:11:29", "throughput": 3036.07, "total_tokens": 710976} {"current_steps": 1105, "total_steps": 38160, "loss": 0.5854, "lr": 1.4465408805031447e-05, "epoch": 0.5791404612159329, "percentage": 2.9, "elapsed_time": "0:03:55", "remaining_time": "2:11:26", "throughput": 3034.82, "total_tokens": 713696} {"current_steps": 1110, "total_steps": 38160, "loss": 0.4378, "lr": 1.4530922431865828e-05, "epoch": 0.5817610062893082, "percentage": 2.91, "elapsed_time": "0:03:56", "remaining_time": "2:11:24", "throughput": 3033.74, "total_tokens": 716608} {"current_steps": 1115, "total_steps": 38160, "loss": 0.4786, "lr": 1.4596436058700211e-05, "epoch": 0.5843815513626834, "percentage": 2.92, "elapsed_time": "0:03:57", "remaining_time": "2:11:21", "throughput": 3033.02, "total_tokens": 719488} {"current_steps": 1120, "total_steps": 38160, "loss": 0.384, "lr": 1.4661949685534593e-05, "epoch": 0.5870020964360587, "percentage": 2.94, "elapsed_time": "0:03:58", "remaining_time": "2:11:19", "throughput": 3031.68, "total_tokens": 722304} {"current_steps": 1125, "total_steps": 38160, "loss": 0.4055, "lr": 1.4727463312368974e-05, "epoch": 0.589622641509434, "percentage": 2.95, "elapsed_time": "0:03:59", "remaining_time": "2:11:16", "throughput": 3032.11, "total_tokens": 725472} {"current_steps": 1130, "total_steps": 38160, "loss": 0.3555, "lr": 1.4792976939203354e-05, "epoch": 0.5922431865828093, "percentage": 2.96, "elapsed_time": "0:04:00", "remaining_time": "2:11:16", "throughput": 3032.54, "total_tokens": 728896} {"current_steps": 1135, "total_steps": 38160, "loss": 0.3984, "lr": 1.4858490566037735e-05, "epoch": 0.5948637316561844, "percentage": 2.97, "elapsed_time": "0:04:01", "remaining_time": "2:11:15", "throughput": 3032.19, "total_tokens": 732000} {"current_steps": 1140, "total_steps": 38160, "loss": 0.5477, "lr": 1.4924004192872118e-05, "epoch": 0.5974842767295597, "percentage": 2.99, "elapsed_time": "0:04:02", "remaining_time": "2:11:12", "throughput": 3033.11, "total_tokens": 735328} {"current_steps": 1145, "total_steps": 38160, "loss": 0.3414, "lr": 1.49895178197065e-05, "epoch": 0.600104821802935, "percentage": 3.0, "elapsed_time": "0:04:03", "remaining_time": "2:11:09", "throughput": 3033.75, "total_tokens": 738528} {"current_steps": 1150, "total_steps": 38160, "loss": 0.5687, "lr": 1.5055031446540883e-05, "epoch": 0.6027253668763103, "percentage": 3.01, "elapsed_time": "0:04:04", "remaining_time": "2:11:07", "throughput": 3032.74, "total_tokens": 741376} {"current_steps": 1155, "total_steps": 38160, "loss": 0.4994, "lr": 1.5120545073375264e-05, "epoch": 0.6053459119496856, "percentage": 3.03, "elapsed_time": "0:04:05", "remaining_time": "2:11:04", "throughput": 3030.5, "total_tokens": 743872} {"current_steps": 1160, "total_steps": 38160, "loss": 0.5136, "lr": 1.5186058700209644e-05, "epoch": 0.6079664570230608, "percentage": 3.04, "elapsed_time": "0:04:06", "remaining_time": "2:11:03", "throughput": 3029.0, "total_tokens": 746720} {"current_steps": 1165, "total_steps": 38160, "loss": 0.5449, "lr": 1.5251572327044025e-05, "epoch": 0.610587002096436, "percentage": 3.05, "elapsed_time": "0:04:07", "remaining_time": "2:11:01", "throughput": 3030.46, "total_tokens": 750240} {"current_steps": 1170, "total_steps": 38160, "loss": 0.4796, "lr": 1.5317085953878407e-05, "epoch": 0.6132075471698113, "percentage": 3.07, "elapsed_time": "0:04:08", "remaining_time": "2:11:00", "throughput": 3029.9, "total_tokens": 753344} {"current_steps": 1175, "total_steps": 38160, "loss": 0.4529, "lr": 1.538259958071279e-05, "epoch": 0.6158280922431866, "percentage": 3.08, "elapsed_time": "0:04:09", "remaining_time": "2:10:58", "throughput": 3028.14, "total_tokens": 755968} {"current_steps": 1180, "total_steps": 38160, "loss": 0.5571, "lr": 1.5448113207547173e-05, "epoch": 0.6184486373165619, "percentage": 3.09, "elapsed_time": "0:04:10", "remaining_time": "2:10:56", "throughput": 3029.49, "total_tokens": 759520} {"current_steps": 1185, "total_steps": 38160, "loss": 0.4795, "lr": 1.5513626834381552e-05, "epoch": 0.6210691823899371, "percentage": 3.11, "elapsed_time": "0:04:11", "remaining_time": "2:10:53", "throughput": 3027.6, "total_tokens": 762048} {"current_steps": 1190, "total_steps": 38160, "loss": 0.5803, "lr": 1.5579140461215932e-05, "epoch": 0.6236897274633124, "percentage": 3.12, "elapsed_time": "0:04:12", "remaining_time": "2:10:52", "throughput": 3028.43, "total_tokens": 765504} {"current_steps": 1195, "total_steps": 38160, "loss": 0.4512, "lr": 1.5644654088050315e-05, "epoch": 0.6263102725366876, "percentage": 3.13, "elapsed_time": "0:04:13", "remaining_time": "2:10:51", "throughput": 3026.53, "total_tokens": 768192} {"current_steps": 1200, "total_steps": 38160, "loss": 0.4972, "lr": 1.5710167714884695e-05, "epoch": 0.6289308176100629, "percentage": 3.14, "elapsed_time": "0:04:14", "remaining_time": "2:10:48", "throughput": 3026.2, "total_tokens": 771168} {"current_steps": 1205, "total_steps": 38160, "loss": 0.2978, "lr": 1.5775681341719078e-05, "epoch": 0.6315513626834381, "percentage": 3.16, "elapsed_time": "0:04:16", "remaining_time": "2:11:08", "throughput": 3030.5, "total_tokens": 777504} {"current_steps": 1210, "total_steps": 38160, "loss": 0.4441, "lr": 1.584119496855346e-05, "epoch": 0.6341719077568134, "percentage": 3.17, "elapsed_time": "0:04:17", "remaining_time": "2:11:06", "throughput": 3029.96, "total_tokens": 780512} {"current_steps": 1215, "total_steps": 38160, "loss": 0.5078, "lr": 1.5906708595387844e-05, "epoch": 0.6367924528301887, "percentage": 3.18, "elapsed_time": "0:04:18", "remaining_time": "2:11:06", "throughput": 3031.4, "total_tokens": 784192} {"current_steps": 1220, "total_steps": 38160, "loss": 0.5606, "lr": 1.597222222222222e-05, "epoch": 0.639412997903564, "percentage": 3.2, "elapsed_time": "0:04:19", "remaining_time": "2:11:03", "throughput": 3032.44, "total_tokens": 787552} {"current_steps": 1225, "total_steps": 38160, "loss": 0.6115, "lr": 1.6037735849056604e-05, "epoch": 0.6420335429769392, "percentage": 3.21, "elapsed_time": "0:04:20", "remaining_time": "2:11:02", "throughput": 3032.21, "total_tokens": 790720} {"current_steps": 1230, "total_steps": 38160, "loss": 0.5549, "lr": 1.6103249475890987e-05, "epoch": 0.6446540880503144, "percentage": 3.22, "elapsed_time": "0:04:21", "remaining_time": "2:10:59", "throughput": 3032.19, "total_tokens": 793696} {"current_steps": 1235, "total_steps": 38160, "loss": 0.5344, "lr": 1.6168763102725366e-05, "epoch": 0.6472746331236897, "percentage": 3.24, "elapsed_time": "0:04:22", "remaining_time": "2:10:57", "throughput": 3031.37, "total_tokens": 796640} {"current_steps": 1240, "total_steps": 38160, "loss": 0.5081, "lr": 1.623427672955975e-05, "epoch": 0.649895178197065, "percentage": 3.25, "elapsed_time": "0:04:23", "remaining_time": "2:10:54", "throughput": 3031.06, "total_tokens": 799648} {"current_steps": 1245, "total_steps": 38160, "loss": 0.3392, "lr": 1.6299790356394132e-05, "epoch": 0.6525157232704403, "percentage": 3.26, "elapsed_time": "0:04:24", "remaining_time": "2:10:51", "throughput": 3030.4, "total_tokens": 802496} {"current_steps": 1250, "total_steps": 38160, "loss": 0.5154, "lr": 1.6365303983228512e-05, "epoch": 0.6551362683438156, "percentage": 3.28, "elapsed_time": "0:04:25", "remaining_time": "2:10:51", "throughput": 3030.2, "total_tokens": 805760} {"current_steps": 1255, "total_steps": 38160, "loss": 0.5182, "lr": 1.6430817610062892e-05, "epoch": 0.6577568134171907, "percentage": 3.29, "elapsed_time": "0:04:26", "remaining_time": "2:10:49", "throughput": 3030.08, "total_tokens": 808832} {"current_steps": 1260, "total_steps": 38160, "loss": 0.4409, "lr": 1.6496331236897275e-05, "epoch": 0.660377358490566, "percentage": 3.3, "elapsed_time": "0:04:28", "remaining_time": "2:10:50", "throughput": 3030.21, "total_tokens": 812256} {"current_steps": 1265, "total_steps": 38160, "loss": 0.4542, "lr": 1.6561844863731658e-05, "epoch": 0.6629979035639413, "percentage": 3.31, "elapsed_time": "0:04:29", "remaining_time": "2:10:47", "throughput": 3031.38, "total_tokens": 815680} {"current_steps": 1270, "total_steps": 38160, "loss": 0.3576, "lr": 1.6627358490566038e-05, "epoch": 0.6656184486373166, "percentage": 3.33, "elapsed_time": "0:04:30", "remaining_time": "2:10:46", "throughput": 3029.83, "total_tokens": 818400} {"current_steps": 1275, "total_steps": 38160, "loss": 0.5443, "lr": 1.669287211740042e-05, "epoch": 0.6682389937106918, "percentage": 3.34, "elapsed_time": "0:04:31", "remaining_time": "2:10:44", "throughput": 3029.77, "total_tokens": 821536} {"current_steps": 1280, "total_steps": 38160, "loss": 0.4665, "lr": 1.6758385744234804e-05, "epoch": 0.6708595387840671, "percentage": 3.35, "elapsed_time": "0:04:32", "remaining_time": "2:10:44", "throughput": 3030.27, "total_tokens": 825024} {"current_steps": 1285, "total_steps": 38160, "loss": 0.4445, "lr": 1.6823899371069183e-05, "epoch": 0.6734800838574424, "percentage": 3.37, "elapsed_time": "0:04:33", "remaining_time": "2:10:46", "throughput": 3032.71, "total_tokens": 829248} {"current_steps": 1290, "total_steps": 38160, "loss": 0.4157, "lr": 1.6889412997903563e-05, "epoch": 0.6761006289308176, "percentage": 3.38, "elapsed_time": "0:04:34", "remaining_time": "2:10:47", "throughput": 3029.75, "total_tokens": 831872} {"current_steps": 1295, "total_steps": 38160, "loss": 0.5771, "lr": 1.6954926624737946e-05, "epoch": 0.6787211740041929, "percentage": 3.39, "elapsed_time": "0:04:35", "remaining_time": "2:10:45", "throughput": 3029.29, "total_tokens": 834880} {"current_steps": 1300, "total_steps": 38160, "loss": 0.5613, "lr": 1.702044025157233e-05, "epoch": 0.6813417190775681, "percentage": 3.41, "elapsed_time": "0:04:36", "remaining_time": "2:10:43", "throughput": 3028.59, "total_tokens": 837824} {"current_steps": 1305, "total_steps": 38160, "loss": 0.498, "lr": 1.708595387840671e-05, "epoch": 0.6839622641509434, "percentage": 3.42, "elapsed_time": "0:04:37", "remaining_time": "2:10:43", "throughput": 3027.73, "total_tokens": 840896} {"current_steps": 1310, "total_steps": 38160, "loss": 0.6692, "lr": 1.7151467505241092e-05, "epoch": 0.6865828092243187, "percentage": 3.43, "elapsed_time": "0:04:38", "remaining_time": "2:10:41", "throughput": 3027.56, "total_tokens": 844000} {"current_steps": 1315, "total_steps": 38160, "loss": 0.4513, "lr": 1.7216981132075472e-05, "epoch": 0.689203354297694, "percentage": 3.45, "elapsed_time": "0:04:39", "remaining_time": "2:10:39", "throughput": 3030.08, "total_tokens": 847840} {"current_steps": 1320, "total_steps": 38160, "loss": 0.5656, "lr": 1.7282494758909855e-05, "epoch": 0.6918238993710691, "percentage": 3.46, "elapsed_time": "0:04:40", "remaining_time": "2:10:38", "throughput": 3029.82, "total_tokens": 850976} {"current_steps": 1325, "total_steps": 38160, "loss": 0.4261, "lr": 1.7348008385744234e-05, "epoch": 0.6944444444444444, "percentage": 3.47, "elapsed_time": "0:04:42", "remaining_time": "2:10:41", "throughput": 3033.3, "total_tokens": 855616} {"current_steps": 1330, "total_steps": 38160, "loss": 0.3071, "lr": 1.7413522012578618e-05, "epoch": 0.6970649895178197, "percentage": 3.49, "elapsed_time": "0:04:43", "remaining_time": "2:10:38", "throughput": 3032.98, "total_tokens": 858528} {"current_steps": 1335, "total_steps": 38160, "loss": 0.4918, "lr": 1.7479035639413e-05, "epoch": 0.699685534591195, "percentage": 3.5, "elapsed_time": "0:04:44", "remaining_time": "2:10:36", "throughput": 3034.81, "total_tokens": 862144} {"current_steps": 1340, "total_steps": 38160, "loss": 0.5737, "lr": 1.754454926624738e-05, "epoch": 0.7023060796645703, "percentage": 3.51, "elapsed_time": "0:04:45", "remaining_time": "2:10:33", "throughput": 3035.6, "total_tokens": 865440} {"current_steps": 1345, "total_steps": 38160, "loss": 0.5072, "lr": 1.761006289308176e-05, "epoch": 0.7049266247379455, "percentage": 3.52, "elapsed_time": "0:04:46", "remaining_time": "2:10:30", "throughput": 3037.47, "total_tokens": 868992} {"current_steps": 1350, "total_steps": 38160, "loss": 0.4759, "lr": 1.7675576519916143e-05, "epoch": 0.7075471698113207, "percentage": 3.54, "elapsed_time": "0:04:47", "remaining_time": "2:10:28", "throughput": 3037.15, "total_tokens": 871968} {"current_steps": 1355, "total_steps": 38160, "loss": 0.4704, "lr": 1.7741090146750526e-05, "epoch": 0.710167714884696, "percentage": 3.55, "elapsed_time": "0:04:48", "remaining_time": "2:10:26", "throughput": 3036.31, "total_tokens": 874912} {"current_steps": 1360, "total_steps": 38160, "loss": 0.5088, "lr": 1.7806603773584906e-05, "epoch": 0.7127882599580713, "percentage": 3.56, "elapsed_time": "0:04:49", "remaining_time": "2:10:27", "throughput": 3035.66, "total_tokens": 878112} {"current_steps": 1365, "total_steps": 38160, "loss": 0.4872, "lr": 1.787211740041929e-05, "epoch": 0.7154088050314465, "percentage": 3.58, "elapsed_time": "0:04:50", "remaining_time": "2:10:25", "throughput": 3034.67, "total_tokens": 880928} {"current_steps": 1370, "total_steps": 38160, "loss": 0.5104, "lr": 1.7937631027253672e-05, "epoch": 0.7180293501048218, "percentage": 3.59, "elapsed_time": "0:04:51", "remaining_time": "2:10:23", "throughput": 3037.21, "total_tokens": 884832} {"current_steps": 1375, "total_steps": 38160, "loss": 0.471, "lr": 1.8003144654088048e-05, "epoch": 0.7206498951781971, "percentage": 3.6, "elapsed_time": "0:04:52", "remaining_time": "2:10:24", "throughput": 3038.86, "total_tokens": 888800} {"current_steps": 1380, "total_steps": 38160, "loss": 0.4773, "lr": 1.806865828092243e-05, "epoch": 0.7232704402515723, "percentage": 3.62, "elapsed_time": "0:04:53", "remaining_time": "2:10:22", "throughput": 3040.62, "total_tokens": 892416} {"current_steps": 1385, "total_steps": 38160, "loss": 0.5645, "lr": 1.8134171907756814e-05, "epoch": 0.7258909853249476, "percentage": 3.63, "elapsed_time": "0:04:54", "remaining_time": "2:10:19", "throughput": 3041.93, "total_tokens": 895840} {"current_steps": 1390, "total_steps": 38160, "loss": 0.5095, "lr": 1.8199685534591197e-05, "epoch": 0.7285115303983228, "percentage": 3.64, "elapsed_time": "0:04:55", "remaining_time": "2:10:16", "throughput": 3043.64, "total_tokens": 899392} {"current_steps": 1395, "total_steps": 38160, "loss": 0.4463, "lr": 1.8265199161425577e-05, "epoch": 0.7311320754716981, "percentage": 3.66, "elapsed_time": "0:04:56", "remaining_time": "2:10:14", "throughput": 3046.28, "total_tokens": 903264} {"current_steps": 1400, "total_steps": 38160, "loss": 0.4499, "lr": 1.833071278825996e-05, "epoch": 0.7337526205450734, "percentage": 3.67, "elapsed_time": "0:04:57", "remaining_time": "2:10:11", "throughput": 3045.48, "total_tokens": 906016} {"current_steps": 1405, "total_steps": 38160, "loss": 0.5893, "lr": 1.839622641509434e-05, "epoch": 0.7363731656184487, "percentage": 3.68, "elapsed_time": "0:04:58", "remaining_time": "2:10:09", "throughput": 3045.63, "total_tokens": 909152} {"current_steps": 1410, "total_steps": 38160, "loss": 0.5345, "lr": 1.846174004192872e-05, "epoch": 0.7389937106918238, "percentage": 3.69, "elapsed_time": "0:04:59", "remaining_time": "2:10:08", "throughput": 3045.51, "total_tokens": 912416} {"current_steps": 1415, "total_steps": 38160, "loss": 0.6131, "lr": 1.8527253668763103e-05, "epoch": 0.7416142557651991, "percentage": 3.71, "elapsed_time": "0:05:00", "remaining_time": "2:10:06", "throughput": 3045.61, "total_tokens": 915616} {"current_steps": 1420, "total_steps": 38160, "loss": 0.5128, "lr": 1.8592767295597486e-05, "epoch": 0.7442348008385744, "percentage": 3.72, "elapsed_time": "0:05:02", "remaining_time": "2:10:21", "throughput": 3048.58, "total_tokens": 921568} {"current_steps": 1425, "total_steps": 38160, "loss": 0.4479, "lr": 1.865828092243187e-05, "epoch": 0.7468553459119497, "percentage": 3.73, "elapsed_time": "0:05:03", "remaining_time": "2:10:20", "throughput": 3048.8, "total_tokens": 924864} {"current_steps": 1430, "total_steps": 38160, "loss": 0.5181, "lr": 1.872379454926625e-05, "epoch": 0.749475890985325, "percentage": 3.75, "elapsed_time": "0:05:04", "remaining_time": "2:10:18", "throughput": 3048.72, "total_tokens": 927968} {"current_steps": 1435, "total_steps": 38160, "loss": 0.5011, "lr": 1.878930817610063e-05, "epoch": 0.7520964360587002, "percentage": 3.76, "elapsed_time": "0:05:05", "remaining_time": "2:10:17", "throughput": 3049.83, "total_tokens": 931584} {"current_steps": 1440, "total_steps": 38160, "loss": 0.4637, "lr": 1.885482180293501e-05, "epoch": 0.7547169811320755, "percentage": 3.77, "elapsed_time": "0:05:06", "remaining_time": "2:10:16", "throughput": 3049.59, "total_tokens": 934816} {"current_steps": 1445, "total_steps": 38160, "loss": 0.5268, "lr": 1.892033542976939e-05, "epoch": 0.7573375262054507, "percentage": 3.79, "elapsed_time": "0:05:07", "remaining_time": "2:10:13", "throughput": 3049.6, "total_tokens": 937856} {"current_steps": 1450, "total_steps": 38160, "loss": 0.5022, "lr": 1.8985849056603774e-05, "epoch": 0.759958071278826, "percentage": 3.8, "elapsed_time": "0:05:09", "remaining_time": "2:10:36", "throughput": 3055.16, "total_tokens": 945632} {"current_steps": 1455, "total_steps": 38160, "loss": 0.5428, "lr": 1.9051362683438157e-05, "epoch": 0.7625786163522013, "percentage": 3.81, "elapsed_time": "0:05:10", "remaining_time": "2:10:33", "throughput": 3054.87, "total_tokens": 948608} {"current_steps": 1460, "total_steps": 38160, "loss": 0.4075, "lr": 1.9116876310272537e-05, "epoch": 0.7651991614255765, "percentage": 3.83, "elapsed_time": "0:05:11", "remaining_time": "2:10:31", "throughput": 3054.12, "total_tokens": 951488} {"current_steps": 1465, "total_steps": 38160, "loss": 0.4967, "lr": 1.918238993710692e-05, "epoch": 0.7678197064989518, "percentage": 3.84, "elapsed_time": "0:05:12", "remaining_time": "2:10:28", "throughput": 3055.85, "total_tokens": 955072} {"current_steps": 1470, "total_steps": 38160, "loss": 0.5655, "lr": 1.92479035639413e-05, "epoch": 0.7704402515723271, "percentage": 3.85, "elapsed_time": "0:05:13", "remaining_time": "2:10:25", "throughput": 3056.31, "total_tokens": 958272} {"current_steps": 1475, "total_steps": 38160, "loss": 0.6418, "lr": 1.9313417190775683e-05, "epoch": 0.7730607966457023, "percentage": 3.87, "elapsed_time": "0:05:14", "remaining_time": "2:10:27", "throughput": 3056.49, "total_tokens": 961888} {"current_steps": 1480, "total_steps": 38160, "loss": 0.6758, "lr": 1.9378930817610062e-05, "epoch": 0.7756813417190775, "percentage": 3.88, "elapsed_time": "0:05:15", "remaining_time": "2:10:25", "throughput": 3054.01, "total_tokens": 964256} {"current_steps": 1485, "total_steps": 38160, "loss": 0.5108, "lr": 1.9444444444444445e-05, "epoch": 0.7783018867924528, "percentage": 3.89, "elapsed_time": "0:05:16", "remaining_time": "2:10:24", "throughput": 3056.24, "total_tokens": 968224} {"current_steps": 1490, "total_steps": 38160, "loss": 0.475, "lr": 1.950995807127883e-05, "epoch": 0.7809224318658281, "percentage": 3.9, "elapsed_time": "0:05:17", "remaining_time": "2:10:20", "throughput": 3056.12, "total_tokens": 971136} {"current_steps": 1495, "total_steps": 38160, "loss": 0.4917, "lr": 1.9575471698113208e-05, "epoch": 0.7835429769392034, "percentage": 3.92, "elapsed_time": "0:05:19", "remaining_time": "2:10:23", "throughput": 3059.31, "total_tokens": 975936} {"current_steps": 1500, "total_steps": 38160, "loss": 0.5177, "lr": 1.9640985324947588e-05, "epoch": 0.7861635220125787, "percentage": 3.93, "elapsed_time": "0:05:20", "remaining_time": "2:10:21", "throughput": 3060.25, "total_tokens": 979360} {"current_steps": 1505, "total_steps": 38160, "loss": 0.4446, "lr": 1.970649895178197e-05, "epoch": 0.7887840670859538, "percentage": 3.94, "elapsed_time": "0:05:21", "remaining_time": "2:10:23", "throughput": 3062.14, "total_tokens": 983616} {"current_steps": 1510, "total_steps": 38160, "loss": 0.4569, "lr": 1.9772012578616354e-05, "epoch": 0.7914046121593291, "percentage": 3.96, "elapsed_time": "0:05:22", "remaining_time": "2:10:20", "throughput": 3062.88, "total_tokens": 986944} {"current_steps": 1515, "total_steps": 38160, "loss": 0.4822, "lr": 1.9837526205450734e-05, "epoch": 0.7940251572327044, "percentage": 3.97, "elapsed_time": "0:05:23", "remaining_time": "2:10:18", "throughput": 3062.41, "total_tokens": 989888} {"current_steps": 1520, "total_steps": 38160, "loss": 0.4896, "lr": 1.9903039832285117e-05, "epoch": 0.7966457023060797, "percentage": 3.98, "elapsed_time": "0:05:24", "remaining_time": "2:10:16", "throughput": 3061.42, "total_tokens": 992768} {"current_steps": 1525, "total_steps": 38160, "loss": 0.3721, "lr": 1.99685534591195e-05, "epoch": 0.799266247379455, "percentage": 4.0, "elapsed_time": "0:05:25", "remaining_time": "2:10:18", "throughput": 3062.89, "total_tokens": 996896} {"current_steps": 1530, "total_steps": 38160, "loss": 0.5259, "lr": 2.003406708595388e-05, "epoch": 0.8018867924528302, "percentage": 4.01, "elapsed_time": "0:05:26", "remaining_time": "2:10:16", "throughput": 3062.6, "total_tokens": 999840} {"current_steps": 1535, "total_steps": 38160, "loss": 0.4143, "lr": 2.009958071278826e-05, "epoch": 0.8045073375262054, "percentage": 4.02, "elapsed_time": "0:05:27", "remaining_time": "2:10:16", "throughput": 3063.86, "total_tokens": 1003680} {"current_steps": 1540, "total_steps": 38160, "loss": 0.4451, "lr": 2.0165094339622642e-05, "epoch": 0.8071278825995807, "percentage": 4.04, "elapsed_time": "0:05:28", "remaining_time": "2:10:13", "throughput": 3063.47, "total_tokens": 1006656} {"current_steps": 1545, "total_steps": 38160, "loss": 0.3915, "lr": 2.0230607966457025e-05, "epoch": 0.809748427672956, "percentage": 4.05, "elapsed_time": "0:05:29", "remaining_time": "2:10:10", "throughput": 3060.68, "total_tokens": 1008768} {"current_steps": 1550, "total_steps": 38160, "loss": 0.4305, "lr": 2.0296121593291405e-05, "epoch": 0.8123689727463312, "percentage": 4.06, "elapsed_time": "0:05:30", "remaining_time": "2:10:08", "throughput": 3061.17, "total_tokens": 1011968} {"current_steps": 1555, "total_steps": 38160, "loss": 0.4702, "lr": 2.0361635220125788e-05, "epoch": 0.8149895178197065, "percentage": 4.07, "elapsed_time": "0:05:32", "remaining_time": "2:10:26", "throughput": 3064.12, "total_tokens": 1018784} {"current_steps": 1560, "total_steps": 38160, "loss": 0.3471, "lr": 2.0427148846960168e-05, "epoch": 0.8176100628930818, "percentage": 4.09, "elapsed_time": "0:05:33", "remaining_time": "2:10:32", "throughput": 3065.74, "total_tokens": 1023520} {"current_steps": 1565, "total_steps": 38160, "loss": 0.455, "lr": 2.049266247379455e-05, "epoch": 0.820230607966457, "percentage": 4.1, "elapsed_time": "0:05:34", "remaining_time": "2:10:30", "throughput": 3067.24, "total_tokens": 1027200} {"current_steps": 1570, "total_steps": 38160, "loss": 0.7732, "lr": 2.055817610062893e-05, "epoch": 0.8228511530398323, "percentage": 4.11, "elapsed_time": "0:05:35", "remaining_time": "2:10:30", "throughput": 3068.03, "total_tokens": 1030848} {"current_steps": 1575, "total_steps": 38160, "loss": 0.5356, "lr": 2.0623689727463314e-05, "epoch": 0.8254716981132075, "percentage": 4.13, "elapsed_time": "0:05:37", "remaining_time": "2:10:31", "throughput": 3070.63, "total_tokens": 1035232} {"current_steps": 1580, "total_steps": 38160, "loss": 0.4918, "lr": 2.0689203354297697e-05, "epoch": 0.8280922431865828, "percentage": 4.14, "elapsed_time": "0:05:38", "remaining_time": "2:10:29", "throughput": 3070.09, "total_tokens": 1038176} {"current_steps": 1585, "total_steps": 38160, "loss": 0.3933, "lr": 2.0754716981132076e-05, "epoch": 0.8307127882599581, "percentage": 4.15, "elapsed_time": "0:05:39", "remaining_time": "2:10:28", "throughput": 3069.21, "total_tokens": 1041216} {"current_steps": 1590, "total_steps": 38160, "loss": 0.5113, "lr": 2.0820230607966456e-05, "epoch": 0.8333333333333334, "percentage": 4.17, "elapsed_time": "0:05:40", "remaining_time": "2:10:25", "throughput": 3067.82, "total_tokens": 1043840} {"current_steps": 1595, "total_steps": 38160, "loss": 0.3991, "lr": 2.088574423480084e-05, "epoch": 0.8359538784067087, "percentage": 4.18, "elapsed_time": "0:05:41", "remaining_time": "2:10:22", "throughput": 3067.18, "total_tokens": 1046656} {"current_steps": 1600, "total_steps": 38160, "loss": 0.4215, "lr": 2.0951257861635222e-05, "epoch": 0.8385744234800838, "percentage": 4.19, "elapsed_time": "0:05:42", "remaining_time": "2:10:27", "throughput": 3069.85, "total_tokens": 1051616} {"current_steps": 1605, "total_steps": 38160, "loss": 0.5972, "lr": 2.1016771488469602e-05, "epoch": 0.8411949685534591, "percentage": 4.21, "elapsed_time": "0:05:43", "remaining_time": "2:10:24", "throughput": 3067.3, "total_tokens": 1053824} {"current_steps": 1610, "total_steps": 38160, "loss": 0.4508, "lr": 2.1082285115303985e-05, "epoch": 0.8438155136268344, "percentage": 4.22, "elapsed_time": "0:05:44", "remaining_time": "2:10:21", "throughput": 3066.39, "total_tokens": 1056512} {"current_steps": 1615, "total_steps": 38160, "loss": 0.4772, "lr": 2.1147798742138368e-05, "epoch": 0.8464360587002097, "percentage": 4.23, "elapsed_time": "0:05:45", "remaining_time": "2:10:19", "throughput": 3067.86, "total_tokens": 1060160} {"current_steps": 1620, "total_steps": 38160, "loss": 0.6068, "lr": 2.1213312368972748e-05, "epoch": 0.8490566037735849, "percentage": 4.25, "elapsed_time": "0:05:46", "remaining_time": "2:10:16", "throughput": 3067.03, "total_tokens": 1062880} {"current_steps": 1625, "total_steps": 38160, "loss": 0.5661, "lr": 2.1278825995807127e-05, "epoch": 0.8516771488469602, "percentage": 4.26, "elapsed_time": "0:05:47", "remaining_time": "2:10:15", "throughput": 3068.25, "total_tokens": 1066528} {"current_steps": 1630, "total_steps": 38160, "loss": 0.3973, "lr": 2.134433962264151e-05, "epoch": 0.8542976939203354, "percentage": 4.27, "elapsed_time": "0:05:48", "remaining_time": "2:10:11", "throughput": 3068.24, "total_tokens": 1069472} {"current_steps": 1635, "total_steps": 38160, "loss": 0.4902, "lr": 2.1409853249475894e-05, "epoch": 0.8569182389937107, "percentage": 4.28, "elapsed_time": "0:05:49", "remaining_time": "2:10:15", "throughput": 3070.9, "total_tokens": 1074304} {"current_steps": 1640, "total_steps": 38160, "loss": 0.4232, "lr": 2.1475366876310273e-05, "epoch": 0.859538784067086, "percentage": 4.3, "elapsed_time": "0:05:50", "remaining_time": "2:10:11", "throughput": 3071.11, "total_tokens": 1077376} {"current_steps": 1645, "total_steps": 38160, "loss": 0.4957, "lr": 2.1540880503144656e-05, "epoch": 0.8621593291404612, "percentage": 4.31, "elapsed_time": "0:05:51", "remaining_time": "2:10:08", "throughput": 3072.04, "total_tokens": 1080672} {"current_steps": 1650, "total_steps": 38160, "loss": 0.5266, "lr": 2.160639412997904e-05, "epoch": 0.8647798742138365, "percentage": 4.32, "elapsed_time": "0:05:52", "remaining_time": "2:10:07", "throughput": 3072.8, "total_tokens": 1084224} {"current_steps": 1655, "total_steps": 38160, "loss": 0.6544, "lr": 2.1671907756813416e-05, "epoch": 0.8674004192872118, "percentage": 4.34, "elapsed_time": "0:05:53", "remaining_time": "2:10:04", "throughput": 3071.85, "total_tokens": 1086912} {"current_steps": 1660, "total_steps": 38160, "loss": 0.581, "lr": 2.17374213836478e-05, "epoch": 0.870020964360587, "percentage": 4.35, "elapsed_time": "0:05:54", "remaining_time": "2:10:01", "throughput": 3071.09, "total_tokens": 1089696} {"current_steps": 1665, "total_steps": 38160, "loss": 0.4278, "lr": 2.1802935010482182e-05, "epoch": 0.8726415094339622, "percentage": 4.36, "elapsed_time": "0:05:55", "remaining_time": "2:09:58", "throughput": 3070.94, "total_tokens": 1092608} {"current_steps": 1670, "total_steps": 38160, "loss": 0.6558, "lr": 2.186844863731656e-05, "epoch": 0.8752620545073375, "percentage": 4.38, "elapsed_time": "0:05:56", "remaining_time": "2:09:56", "throughput": 3071.16, "total_tokens": 1095808} {"current_steps": 1675, "total_steps": 38160, "loss": 0.5447, "lr": 2.1933962264150945e-05, "epoch": 0.8778825995807128, "percentage": 4.39, "elapsed_time": "0:05:57", "remaining_time": "2:09:53", "throughput": 3071.06, "total_tokens": 1098816} {"current_steps": 1680, "total_steps": 38160, "loss": 0.5563, "lr": 2.1999475890985328e-05, "epoch": 0.8805031446540881, "percentage": 4.4, "elapsed_time": "0:05:58", "remaining_time": "2:09:54", "throughput": 3073.26, "total_tokens": 1103136} {"current_steps": 1685, "total_steps": 38160, "loss": 0.439, "lr": 2.2064989517819707e-05, "epoch": 0.8831236897274634, "percentage": 4.42, "elapsed_time": "0:06:00", "remaining_time": "2:09:56", "throughput": 3075.91, "total_tokens": 1107872} {"current_steps": 1690, "total_steps": 38160, "loss": 0.6202, "lr": 2.2130503144654087e-05, "epoch": 0.8857442348008385, "percentage": 4.43, "elapsed_time": "0:06:01", "remaining_time": "2:09:53", "throughput": 3076.5, "total_tokens": 1111072} {"current_steps": 1695, "total_steps": 38160, "loss": 0.5386, "lr": 2.219601677148847e-05, "epoch": 0.8883647798742138, "percentage": 4.44, "elapsed_time": "0:06:02", "remaining_time": "2:09:50", "throughput": 3075.57, "total_tokens": 1113792} {"current_steps": 1700, "total_steps": 38160, "loss": 0.4305, "lr": 2.2261530398322853e-05, "epoch": 0.8909853249475891, "percentage": 4.45, "elapsed_time": "0:06:03", "remaining_time": "2:09:48", "throughput": 3074.31, "total_tokens": 1116384} {"current_steps": 1705, "total_steps": 38160, "loss": 0.4326, "lr": 2.2327044025157233e-05, "epoch": 0.8936058700209644, "percentage": 4.47, "elapsed_time": "0:06:04", "remaining_time": "2:09:46", "throughput": 3073.56, "total_tokens": 1119296} {"current_steps": 1710, "total_steps": 38160, "loss": 0.5935, "lr": 2.2392557651991616e-05, "epoch": 0.8962264150943396, "percentage": 4.48, "elapsed_time": "0:06:05", "remaining_time": "2:09:45", "throughput": 3073.85, "total_tokens": 1122720} {"current_steps": 1715, "total_steps": 38160, "loss": 0.5462, "lr": 2.2458071278825996e-05, "epoch": 0.8988469601677149, "percentage": 4.49, "elapsed_time": "0:06:06", "remaining_time": "2:09:43", "throughput": 3071.66, "total_tokens": 1125088} {"current_steps": 1720, "total_steps": 38160, "loss": 0.6149, "lr": 2.252358490566038e-05, "epoch": 0.9014675052410901, "percentage": 4.51, "elapsed_time": "0:06:07", "remaining_time": "2:09:40", "throughput": 3072.15, "total_tokens": 1128288} {"current_steps": 1725, "total_steps": 38160, "loss": 0.5371, "lr": 2.258909853249476e-05, "epoch": 0.9040880503144654, "percentage": 4.52, "elapsed_time": "0:06:08", "remaining_time": "2:09:38", "throughput": 3071.09, "total_tokens": 1131040} {"current_steps": 1730, "total_steps": 38160, "loss": 0.5138, "lr": 2.265461215932914e-05, "epoch": 0.9067085953878407, "percentage": 4.53, "elapsed_time": "0:06:09", "remaining_time": "2:09:40", "throughput": 3072.31, "total_tokens": 1135136} {"current_steps": 1735, "total_steps": 38160, "loss": 0.6284, "lr": 2.2720125786163524e-05, "epoch": 0.9093291404612159, "percentage": 4.55, "elapsed_time": "0:06:10", "remaining_time": "2:09:40", "throughput": 3073.57, "total_tokens": 1139008} {"current_steps": 1740, "total_steps": 38160, "loss": 0.4604, "lr": 2.2785639412997904e-05, "epoch": 0.9119496855345912, "percentage": 4.56, "elapsed_time": "0:06:11", "remaining_time": "2:09:38", "throughput": 3072.87, "total_tokens": 1141920} {"current_steps": 1745, "total_steps": 38160, "loss": 0.4338, "lr": 2.2851153039832284e-05, "epoch": 0.9145702306079665, "percentage": 4.57, "elapsed_time": "0:06:12", "remaining_time": "2:09:36", "throughput": 3072.68, "total_tokens": 1144960} {"current_steps": 1750, "total_steps": 38160, "loss": 0.5337, "lr": 2.2916666666666667e-05, "epoch": 0.9171907756813418, "percentage": 4.59, "elapsed_time": "0:06:13", "remaining_time": "2:09:33", "throughput": 3071.84, "total_tokens": 1147712} {"current_steps": 1755, "total_steps": 38160, "loss": 0.5192, "lr": 2.298218029350105e-05, "epoch": 0.9198113207547169, "percentage": 4.6, "elapsed_time": "0:06:14", "remaining_time": "2:09:30", "throughput": 3071.18, "total_tokens": 1150528} {"current_steps": 1760, "total_steps": 38160, "loss": 0.5521, "lr": 2.304769392033543e-05, "epoch": 0.9224318658280922, "percentage": 4.61, "elapsed_time": "0:06:15", "remaining_time": "2:09:29", "throughput": 3072.74, "total_tokens": 1154272} {"current_steps": 1765, "total_steps": 38160, "loss": 0.4363, "lr": 2.3113207547169813e-05, "epoch": 0.9250524109014675, "percentage": 4.63, "elapsed_time": "0:06:16", "remaining_time": "2:09:26", "throughput": 3072.17, "total_tokens": 1157088} {"current_steps": 1770, "total_steps": 38160, "loss": 0.6102, "lr": 2.3178721174004196e-05, "epoch": 0.9276729559748428, "percentage": 4.64, "elapsed_time": "0:06:17", "remaining_time": "2:09:25", "throughput": 3071.73, "total_tokens": 1160192} {"current_steps": 1775, "total_steps": 38160, "loss": 0.5305, "lr": 2.3244234800838576e-05, "epoch": 0.9302935010482181, "percentage": 4.65, "elapsed_time": "0:06:18", "remaining_time": "2:09:23", "throughput": 3071.78, "total_tokens": 1163424} {"current_steps": 1780, "total_steps": 38160, "loss": 0.5788, "lr": 2.3309748427672955e-05, "epoch": 0.9329140461215933, "percentage": 4.66, "elapsed_time": "0:06:19", "remaining_time": "2:09:21", "throughput": 3073.41, "total_tokens": 1167104} {"current_steps": 1785, "total_steps": 38160, "loss": 0.4842, "lr": 2.3375262054507338e-05, "epoch": 0.9355345911949685, "percentage": 4.68, "elapsed_time": "0:06:20", "remaining_time": "2:09:20", "throughput": 3073.28, "total_tokens": 1170368} {"current_steps": 1790, "total_steps": 38160, "loss": 0.5968, "lr": 2.344077568134172e-05, "epoch": 0.9381551362683438, "percentage": 4.69, "elapsed_time": "0:06:21", "remaining_time": "2:09:17", "throughput": 3074.45, "total_tokens": 1173888} {"current_steps": 1795, "total_steps": 38160, "loss": 0.4947, "lr": 2.35062893081761e-05, "epoch": 0.9407756813417191, "percentage": 4.7, "elapsed_time": "0:06:22", "remaining_time": "2:09:16", "throughput": 3075.43, "total_tokens": 1177408} {"current_steps": 1800, "total_steps": 38160, "loss": 0.4773, "lr": 2.3571802935010484e-05, "epoch": 0.9433962264150944, "percentage": 4.72, "elapsed_time": "0:06:23", "remaining_time": "2:09:15", "throughput": 3076.1, "total_tokens": 1181056} {"current_steps": 1805, "total_steps": 38160, "loss": 0.6613, "lr": 2.3637316561844867e-05, "epoch": 0.9460167714884696, "percentage": 4.73, "elapsed_time": "0:06:25", "remaining_time": "2:09:14", "throughput": 3075.83, "total_tokens": 1184256} {"current_steps": 1810, "total_steps": 38160, "loss": 0.42, "lr": 2.3702830188679247e-05, "epoch": 0.9486373165618449, "percentage": 4.74, "elapsed_time": "0:06:26", "remaining_time": "2:09:12", "throughput": 3075.3, "total_tokens": 1187168} {"current_steps": 1815, "total_steps": 38160, "loss": 0.4466, "lr": 2.3768343815513627e-05, "epoch": 0.9512578616352201, "percentage": 4.76, "elapsed_time": "0:06:27", "remaining_time": "2:09:10", "throughput": 3076.59, "total_tokens": 1190784} {"current_steps": 1820, "total_steps": 38160, "loss": 0.5457, "lr": 2.383385744234801e-05, "epoch": 0.9538784067085954, "percentage": 4.77, "elapsed_time": "0:06:28", "remaining_time": "2:09:08", "throughput": 3075.17, "total_tokens": 1193312} {"current_steps": 1825, "total_steps": 38160, "loss": 0.4782, "lr": 2.3899371069182393e-05, "epoch": 0.9564989517819706, "percentage": 4.78, "elapsed_time": "0:06:29", "remaining_time": "2:09:07", "throughput": 3075.13, "total_tokens": 1196608} {"current_steps": 1830, "total_steps": 38160, "loss": 0.5531, "lr": 2.3964884696016772e-05, "epoch": 0.9591194968553459, "percentage": 4.8, "elapsed_time": "0:06:30", "remaining_time": "2:09:06", "throughput": 3075.91, "total_tokens": 1200160} {"current_steps": 1835, "total_steps": 38160, "loss": 0.4034, "lr": 2.4030398322851155e-05, "epoch": 0.9617400419287212, "percentage": 4.81, "elapsed_time": "0:06:31", "remaining_time": "2:09:03", "throughput": 3075.45, "total_tokens": 1203040} {"current_steps": 1840, "total_steps": 38160, "loss": 0.3753, "lr": 2.4095911949685535e-05, "epoch": 0.9643605870020965, "percentage": 4.82, "elapsed_time": "0:06:32", "remaining_time": "2:09:01", "throughput": 3073.62, "total_tokens": 1205408} {"current_steps": 1845, "total_steps": 38160, "loss": 0.3536, "lr": 2.4161425576519918e-05, "epoch": 0.9669811320754716, "percentage": 4.83, "elapsed_time": "0:06:33", "remaining_time": "2:09:00", "throughput": 3074.13, "total_tokens": 1208896} {"current_steps": 1850, "total_steps": 38160, "loss": 0.4694, "lr": 2.4226939203354298e-05, "epoch": 0.9696016771488469, "percentage": 4.85, "elapsed_time": "0:06:34", "remaining_time": "2:08:58", "throughput": 3075.4, "total_tokens": 1212576} {"current_steps": 1855, "total_steps": 38160, "loss": 0.4708, "lr": 2.429245283018868e-05, "epoch": 0.9722222222222222, "percentage": 4.86, "elapsed_time": "0:06:35", "remaining_time": "2:08:57", "throughput": 3075.65, "total_tokens": 1215872} {"current_steps": 1860, "total_steps": 38160, "loss": 0.4543, "lr": 2.4357966457023064e-05, "epoch": 0.9748427672955975, "percentage": 4.87, "elapsed_time": "0:06:36", "remaining_time": "2:08:58", "throughput": 3076.86, "total_tokens": 1219968} {"current_steps": 1865, "total_steps": 38160, "loss": 0.4885, "lr": 2.4423480083857444e-05, "epoch": 0.9774633123689728, "percentage": 4.89, "elapsed_time": "0:06:37", "remaining_time": "2:08:55", "throughput": 3074.34, "total_tokens": 1222048} {"current_steps": 1870, "total_steps": 38160, "loss": 0.5155, "lr": 2.4488993710691823e-05, "epoch": 0.980083857442348, "percentage": 4.9, "elapsed_time": "0:06:38", "remaining_time": "2:08:53", "throughput": 3074.31, "total_tokens": 1225120} {"current_steps": 1875, "total_steps": 38160, "loss": 0.5146, "lr": 2.4554507337526206e-05, "epoch": 0.9827044025157232, "percentage": 4.91, "elapsed_time": "0:06:39", "remaining_time": "2:08:52", "throughput": 3075.77, "total_tokens": 1229056} {"current_steps": 1880, "total_steps": 38160, "loss": 0.3727, "lr": 2.4620020964360586e-05, "epoch": 0.9853249475890985, "percentage": 4.93, "elapsed_time": "0:06:40", "remaining_time": "2:08:51", "throughput": 3074.63, "total_tokens": 1231776} {"current_steps": 1885, "total_steps": 38160, "loss": 0.4574, "lr": 2.468553459119497e-05, "epoch": 0.9879454926624738, "percentage": 4.94, "elapsed_time": "0:06:41", "remaining_time": "2:08:50", "throughput": 3074.56, "total_tokens": 1235040} {"current_steps": 1890, "total_steps": 38160, "loss": 0.3966, "lr": 2.4751048218029352e-05, "epoch": 0.9905660377358491, "percentage": 4.95, "elapsed_time": "0:06:42", "remaining_time": "2:08:48", "throughput": 3074.24, "total_tokens": 1238048} {"current_steps": 1895, "total_steps": 38160, "loss": 0.5253, "lr": 2.4816561844863735e-05, "epoch": 0.9931865828092243, "percentage": 4.97, "elapsed_time": "0:06:43", "remaining_time": "2:08:45", "throughput": 3075.01, "total_tokens": 1241344} {"current_steps": 1900, "total_steps": 38160, "loss": 0.3521, "lr": 2.488207547169811e-05, "epoch": 0.9958071278825996, "percentage": 4.98, "elapsed_time": "0:06:44", "remaining_time": "2:08:43", "throughput": 3073.61, "total_tokens": 1243840} {"current_steps": 1905, "total_steps": 38160, "loss": 0.5856, "lr": 2.4947589098532495e-05, "epoch": 0.9984276729559748, "percentage": 4.99, "elapsed_time": "0:06:45", "remaining_time": "2:08:40", "throughput": 3073.66, "total_tokens": 1246816} {"current_steps": 1908, "total_steps": 38160, "eval_loss": 0.4838300049304962, "epoch": 1.0, "percentage": 5.0, "elapsed_time": "0:06:58", "remaining_time": "2:12:24", "throughput": 2985.36, "total_tokens": 1248304} {"current_steps": 1910, "total_steps": 38160, "loss": 0.4641, "lr": 2.5013102725366878e-05, "epoch": 1.00104821802935, "percentage": 5.01, "elapsed_time": "0:07:04", "remaining_time": "2:14:18", "throughput": 2942.05, "total_tokens": 1249200} {"current_steps": 1915, "total_steps": 38160, "loss": 0.4516, "lr": 2.507861635220126e-05, "epoch": 1.0036687631027255, "percentage": 5.02, "elapsed_time": "0:07:05", "remaining_time": "2:14:17", "throughput": 2940.24, "total_tokens": 1251664} {"current_steps": 1920, "total_steps": 38160, "loss": 0.4514, "lr": 2.514412997903564e-05, "epoch": 1.0062893081761006, "percentage": 5.03, "elapsed_time": "0:07:06", "remaining_time": "2:14:16", "throughput": 2940.24, "total_tokens": 1254928} {"current_steps": 1925, "total_steps": 38160, "loss": 0.3823, "lr": 2.520964360587002e-05, "epoch": 1.0089098532494758, "percentage": 5.04, "elapsed_time": "0:07:07", "remaining_time": "2:14:15", "throughput": 2939.11, "total_tokens": 1257744} {"current_steps": 1930, "total_steps": 38160, "loss": 0.4171, "lr": 2.5275157232704407e-05, "epoch": 1.0115303983228512, "percentage": 5.06, "elapsed_time": "0:07:09", "remaining_time": "2:14:14", "throughput": 2941.14, "total_tokens": 1261904} {"current_steps": 1935, "total_steps": 38160, "loss": 0.3906, "lr": 2.5340670859538783e-05, "epoch": 1.0141509433962264, "percentage": 5.07, "elapsed_time": "0:07:10", "remaining_time": "2:14:12", "throughput": 2939.7, "total_tokens": 1264432} {"current_steps": 1940, "total_steps": 38160, "loss": 0.5223, "lr": 2.540618448637317e-05, "epoch": 1.0167714884696017, "percentage": 5.08, "elapsed_time": "0:07:11", "remaining_time": "2:14:10", "throughput": 2941.57, "total_tokens": 1268400} {"current_steps": 1945, "total_steps": 38160, "loss": 0.4031, "lr": 2.547169811320755e-05, "epoch": 1.019392033542977, "percentage": 5.1, "elapsed_time": "0:07:12", "remaining_time": "2:14:10", "throughput": 2943.68, "total_tokens": 1272752} {"current_steps": 1950, "total_steps": 38160, "loss": 0.5506, "lr": 2.553721174004193e-05, "epoch": 1.0220125786163523, "percentage": 5.11, "elapsed_time": "0:07:13", "remaining_time": "2:14:07", "throughput": 2943.22, "total_tokens": 1275568} {"current_steps": 1955, "total_steps": 38160, "loss": 0.5376, "lr": 2.5602725366876312e-05, "epoch": 1.0246331236897275, "percentage": 5.12, "elapsed_time": "0:07:14", "remaining_time": "2:14:04", "throughput": 2942.27, "total_tokens": 1278160} {"current_steps": 1960, "total_steps": 38160, "loss": 0.4488, "lr": 2.566823899371069e-05, "epoch": 1.0272536687631026, "percentage": 5.14, "elapsed_time": "0:07:15", "remaining_time": "2:14:03", "throughput": 2942.57, "total_tokens": 1281424} {"current_steps": 1965, "total_steps": 38160, "loss": 0.4486, "lr": 2.5733752620545075e-05, "epoch": 1.029874213836478, "percentage": 5.15, "elapsed_time": "0:07:16", "remaining_time": "2:14:00", "throughput": 2941.43, "total_tokens": 1283920} {"current_steps": 1970, "total_steps": 38160, "loss": 0.4141, "lr": 2.5799266247379454e-05, "epoch": 1.0324947589098532, "percentage": 5.16, "elapsed_time": "0:07:17", "remaining_time": "2:13:59", "throughput": 2942.79, "total_tokens": 1287920} {"current_steps": 1975, "total_steps": 38160, "loss": 0.5047, "lr": 2.586477987421384e-05, "epoch": 1.0351153039832286, "percentage": 5.18, "elapsed_time": "0:07:18", "remaining_time": "2:13:58", "throughput": 2942.23, "total_tokens": 1290960} {"current_steps": 1980, "total_steps": 38160, "loss": 0.3531, "lr": 2.593029350104822e-05, "epoch": 1.0377358490566038, "percentage": 5.19, "elapsed_time": "0:07:19", "remaining_time": "2:13:58", "throughput": 2942.87, "total_tokens": 1294544} {"current_steps": 1985, "total_steps": 38160, "loss": 0.6244, "lr": 2.59958071278826e-05, "epoch": 1.040356394129979, "percentage": 5.2, "elapsed_time": "0:07:21", "remaining_time": "2:13:58", "throughput": 2942.98, "total_tokens": 1298160} {"current_steps": 1990, "total_steps": 38160, "loss": 0.4623, "lr": 2.6061320754716983e-05, "epoch": 1.0429769392033543, "percentage": 5.21, "elapsed_time": "0:07:22", "remaining_time": "2:13:56", "throughput": 2940.98, "total_tokens": 1300368} {"current_steps": 1995, "total_steps": 38160, "loss": 0.4071, "lr": 2.6126834381551363e-05, "epoch": 1.0455974842767295, "percentage": 5.23, "elapsed_time": "0:07:23", "remaining_time": "2:14:07", "throughput": 2944.6, "total_tokens": 1307184} {"current_steps": 2000, "total_steps": 38160, "loss": 0.7226, "lr": 2.6192348008385746e-05, "epoch": 1.0482180293501049, "percentage": 5.24, "elapsed_time": "0:07:25", "remaining_time": "2:14:05", "throughput": 2943.33, "total_tokens": 1309840} {"current_steps": 2005, "total_steps": 38160, "loss": 0.4379, "lr": 2.6257861635220126e-05, "epoch": 1.05083857442348, "percentage": 5.25, "elapsed_time": "0:07:26", "remaining_time": "2:14:08", "throughput": 2943.17, "total_tokens": 1313648} {"current_steps": 2010, "total_steps": 38160, "loss": 0.4673, "lr": 2.6323375262054505e-05, "epoch": 1.0534591194968554, "percentage": 5.27, "elapsed_time": "0:07:27", "remaining_time": "2:14:06", "throughput": 2942.57, "total_tokens": 1316496} {"current_steps": 2015, "total_steps": 38160, "loss": 0.4763, "lr": 2.6388888888888892e-05, "epoch": 1.0560796645702306, "percentage": 5.28, "elapsed_time": "0:07:28", "remaining_time": "2:14:04", "throughput": 2943.16, "total_tokens": 1319952} {"current_steps": 2020, "total_steps": 38160, "loss": 0.4267, "lr": 2.645440251572327e-05, "epoch": 1.0587002096436058, "percentage": 5.29, "elapsed_time": "0:07:29", "remaining_time": "2:14:03", "throughput": 2943.37, "total_tokens": 1323344} {"current_steps": 2025, "total_steps": 38160, "loss": 0.5222, "lr": 2.6519916142557655e-05, "epoch": 1.0613207547169812, "percentage": 5.31, "elapsed_time": "0:07:30", "remaining_time": "2:14:02", "throughput": 2943.78, "total_tokens": 1326704} {"current_steps": 2030, "total_steps": 38160, "loss": 0.451, "lr": 2.6585429769392034e-05, "epoch": 1.0639412997903563, "percentage": 5.32, "elapsed_time": "0:07:31", "remaining_time": "2:14:00", "throughput": 2944.29, "total_tokens": 1330128} {"current_steps": 2035, "total_steps": 38160, "loss": 0.4127, "lr": 2.6650943396226417e-05, "epoch": 1.0665618448637317, "percentage": 5.33, "elapsed_time": "0:07:32", "remaining_time": "2:13:58", "throughput": 2943.67, "total_tokens": 1333040} {"current_steps": 2040, "total_steps": 38160, "loss": 0.4762, "lr": 2.6716457023060797e-05, "epoch": 1.069182389937107, "percentage": 5.35, "elapsed_time": "0:07:33", "remaining_time": "2:13:56", "throughput": 2942.35, "total_tokens": 1335504} {"current_steps": 2045, "total_steps": 38160, "loss": 0.5059, "lr": 2.6781970649895177e-05, "epoch": 1.0718029350104823, "percentage": 5.36, "elapsed_time": "0:07:34", "remaining_time": "2:13:55", "throughput": 2943.57, "total_tokens": 1339280} {"current_steps": 2050, "total_steps": 38160, "loss": 0.5321, "lr": 2.6847484276729563e-05, "epoch": 1.0744234800838575, "percentage": 5.37, "elapsed_time": "0:07:36", "remaining_time": "2:13:53", "throughput": 2943.9, "total_tokens": 1342576} {"current_steps": 2055, "total_steps": 38160, "loss": 0.4618, "lr": 2.6912997903563943e-05, "epoch": 1.0770440251572326, "percentage": 5.39, "elapsed_time": "0:07:37", "remaining_time": "2:13:52", "throughput": 2944.55, "total_tokens": 1346256} {"current_steps": 2060, "total_steps": 38160, "loss": 0.5555, "lr": 2.6978511530398326e-05, "epoch": 1.079664570230608, "percentage": 5.4, "elapsed_time": "0:07:38", "remaining_time": "2:13:50", "throughput": 2943.84, "total_tokens": 1349008} {"current_steps": 2065, "total_steps": 38160, "loss": 0.5261, "lr": 2.7044025157232706e-05, "epoch": 1.0822851153039832, "percentage": 5.41, "elapsed_time": "0:07:39", "remaining_time": "2:13:52", "throughput": 2945.58, "total_tokens": 1353552} {"current_steps": 2070, "total_steps": 38160, "loss": 0.4301, "lr": 2.710953878406709e-05, "epoch": 1.0849056603773586, "percentage": 5.42, "elapsed_time": "0:07:40", "remaining_time": "2:13:50", "throughput": 2945.01, "total_tokens": 1356400} {"current_steps": 2075, "total_steps": 38160, "loss": 0.4783, "lr": 2.717505241090147e-05, "epoch": 1.0875262054507338, "percentage": 5.44, "elapsed_time": "0:07:41", "remaining_time": "2:13:50", "throughput": 2947.36, "total_tokens": 1361008} {"current_steps": 2080, "total_steps": 38160, "loss": 0.5299, "lr": 2.7240566037735848e-05, "epoch": 1.090146750524109, "percentage": 5.45, "elapsed_time": "0:07:42", "remaining_time": "2:13:48", "throughput": 2945.26, "total_tokens": 1363184} {"current_steps": 2085, "total_steps": 38160, "loss": 0.4511, "lr": 2.7306079664570235e-05, "epoch": 1.0927672955974843, "percentage": 5.46, "elapsed_time": "0:07:43", "remaining_time": "2:13:47", "throughput": 2943.95, "total_tokens": 1365872} {"current_steps": 2090, "total_steps": 38160, "loss": 0.519, "lr": 2.737159329140461e-05, "epoch": 1.0953878406708595, "percentage": 5.48, "elapsed_time": "0:07:45", "remaining_time": "2:13:45", "throughput": 2944.33, "total_tokens": 1369168} {"current_steps": 2095, "total_steps": 38160, "loss": 0.4588, "lr": 2.7437106918238997e-05, "epoch": 1.0980083857442349, "percentage": 5.49, "elapsed_time": "0:07:46", "remaining_time": "2:13:43", "throughput": 2944.18, "total_tokens": 1372208} {"current_steps": 2100, "total_steps": 38160, "loss": 0.3748, "lr": 2.7502620545073377e-05, "epoch": 1.10062893081761, "percentage": 5.5, "elapsed_time": "0:07:47", "remaining_time": "2:13:47", "throughput": 2946.33, "total_tokens": 1377360} {"current_steps": 2105, "total_steps": 38160, "loss": 0.402, "lr": 2.7568134171907757e-05, "epoch": 1.1032494758909852, "percentage": 5.52, "elapsed_time": "0:07:48", "remaining_time": "2:13:45", "throughput": 2946.06, "total_tokens": 1380400} {"current_steps": 2110, "total_steps": 38160, "loss": 0.4416, "lr": 2.763364779874214e-05, "epoch": 1.1058700209643606, "percentage": 5.53, "elapsed_time": "0:07:49", "remaining_time": "2:13:44", "throughput": 2944.61, "total_tokens": 1383056} {"current_steps": 2115, "total_steps": 38160, "loss": 0.5296, "lr": 2.769916142557652e-05, "epoch": 1.1084905660377358, "percentage": 5.54, "elapsed_time": "0:07:50", "remaining_time": "2:13:42", "throughput": 2944.57, "total_tokens": 1386160} {"current_steps": 2120, "total_steps": 38160, "loss": 0.4361, "lr": 2.7764675052410906e-05, "epoch": 1.1111111111111112, "percentage": 5.56, "elapsed_time": "0:07:51", "remaining_time": "2:13:41", "throughput": 2944.24, "total_tokens": 1389232} {"current_steps": 2125, "total_steps": 38160, "loss": 0.5491, "lr": 2.7830188679245282e-05, "epoch": 1.1137316561844863, "percentage": 5.57, "elapsed_time": "0:07:53", "remaining_time": "2:13:41", "throughput": 2945.54, "total_tokens": 1393328} {"current_steps": 2130, "total_steps": 38160, "loss": 0.4165, "lr": 2.789570230607967e-05, "epoch": 1.1163522012578617, "percentage": 5.58, "elapsed_time": "0:07:54", "remaining_time": "2:13:39", "throughput": 2946.26, "total_tokens": 1396816} {"current_steps": 2135, "total_steps": 38160, "loss": 0.4049, "lr": 2.796121593291405e-05, "epoch": 1.118972746331237, "percentage": 5.59, "elapsed_time": "0:07:55", "remaining_time": "2:13:38", "throughput": 2946.45, "total_tokens": 1400176} {"current_steps": 2140, "total_steps": 38160, "loss": 0.5527, "lr": 2.8026729559748428e-05, "epoch": 1.121593291404612, "percentage": 5.61, "elapsed_time": "0:07:56", "remaining_time": "2:13:36", "throughput": 2946.65, "total_tokens": 1403408} {"current_steps": 2145, "total_steps": 38160, "loss": 0.4044, "lr": 2.809224318658281e-05, "epoch": 1.1242138364779874, "percentage": 5.62, "elapsed_time": "0:07:57", "remaining_time": "2:13:35", "throughput": 2946.17, "total_tokens": 1406448} {"current_steps": 2150, "total_steps": 38160, "loss": 0.4915, "lr": 2.815775681341719e-05, "epoch": 1.1268343815513626, "percentage": 5.63, "elapsed_time": "0:07:58", "remaining_time": "2:13:34", "throughput": 2945.67, "total_tokens": 1409584} {"current_steps": 2155, "total_steps": 38160, "loss": 0.4745, "lr": 2.8223270440251577e-05, "epoch": 1.129454926624738, "percentage": 5.65, "elapsed_time": "0:07:59", "remaining_time": "2:13:35", "throughput": 2947.2, "total_tokens": 1413872} {"current_steps": 2160, "total_steps": 38160, "loss": 0.6167, "lr": 2.8288784067085954e-05, "epoch": 1.1320754716981132, "percentage": 5.66, "elapsed_time": "0:08:00", "remaining_time": "2:13:32", "throughput": 2946.35, "total_tokens": 1416528} {"current_steps": 2165, "total_steps": 38160, "loss": 0.4867, "lr": 2.8354297693920333e-05, "epoch": 1.1346960167714886, "percentage": 5.67, "elapsed_time": "0:08:01", "remaining_time": "2:13:30", "throughput": 2944.87, "total_tokens": 1418896} {"current_steps": 2170, "total_steps": 38160, "loss": 0.516, "lr": 2.841981132075472e-05, "epoch": 1.1373165618448637, "percentage": 5.69, "elapsed_time": "0:08:02", "remaining_time": "2:13:28", "throughput": 2944.2, "total_tokens": 1421712} {"current_steps": 2175, "total_steps": 38160, "loss": 0.4498, "lr": 2.84853249475891e-05, "epoch": 1.139937106918239, "percentage": 5.7, "elapsed_time": "0:08:03", "remaining_time": "2:13:27", "throughput": 2944.42, "total_tokens": 1425072} {"current_steps": 2180, "total_steps": 38160, "loss": 0.6512, "lr": 2.8550838574423482e-05, "epoch": 1.1425576519916143, "percentage": 5.71, "elapsed_time": "0:08:05", "remaining_time": "2:13:28", "throughput": 2944.62, "total_tokens": 1428848} {"current_steps": 2185, "total_steps": 38160, "loss": 0.4974, "lr": 2.8616352201257862e-05, "epoch": 1.1451781970649895, "percentage": 5.73, "elapsed_time": "0:08:06", "remaining_time": "2:13:29", "throughput": 2944.64, "total_tokens": 1432432} {"current_steps": 2190, "total_steps": 38160, "loss": 0.6417, "lr": 2.868186582809225e-05, "epoch": 1.1477987421383649, "percentage": 5.74, "elapsed_time": "0:08:07", "remaining_time": "2:13:28", "throughput": 2945.23, "total_tokens": 1436048} {"current_steps": 2195, "total_steps": 38160, "loss": 0.6179, "lr": 2.8747379454926625e-05, "epoch": 1.15041928721174, "percentage": 5.75, "elapsed_time": "0:08:08", "remaining_time": "2:13:29", "throughput": 2946.21, "total_tokens": 1440144} {"current_steps": 2200, "total_steps": 38160, "loss": 0.5435, "lr": 2.8812893081761005e-05, "epoch": 1.1530398322851152, "percentage": 5.77, "elapsed_time": "0:08:09", "remaining_time": "2:13:27", "throughput": 2947.07, "total_tokens": 1443760} {"current_steps": 2205, "total_steps": 38160, "loss": 0.7429, "lr": 2.887840670859539e-05, "epoch": 1.1556603773584906, "percentage": 5.78, "elapsed_time": "0:08:11", "remaining_time": "2:13:26", "throughput": 2946.69, "total_tokens": 1446864} {"current_steps": 2210, "total_steps": 38160, "loss": 0.3158, "lr": 2.894392033542977e-05, "epoch": 1.1582809224318658, "percentage": 5.79, "elapsed_time": "0:08:12", "remaining_time": "2:13:25", "throughput": 2945.29, "total_tokens": 1449456} {"current_steps": 2215, "total_steps": 38160, "loss": 0.5315, "lr": 2.9009433962264154e-05, "epoch": 1.1609014675052411, "percentage": 5.8, "elapsed_time": "0:08:13", "remaining_time": "2:13:24", "throughput": 2945.8, "total_tokens": 1452944} {"current_steps": 2220, "total_steps": 38160, "loss": 0.4458, "lr": 2.9074947589098533e-05, "epoch": 1.1635220125786163, "percentage": 5.82, "elapsed_time": "0:08:14", "remaining_time": "2:13:22", "throughput": 2945.51, "total_tokens": 1455952} {"current_steps": 2225, "total_steps": 38160, "loss": 0.5714, "lr": 2.9140461215932913e-05, "epoch": 1.1661425576519917, "percentage": 5.83, "elapsed_time": "0:08:15", "remaining_time": "2:13:20", "throughput": 2945.88, "total_tokens": 1459376} {"current_steps": 2230, "total_steps": 38160, "loss": 0.4568, "lr": 2.9205974842767296e-05, "epoch": 1.1687631027253669, "percentage": 5.84, "elapsed_time": "0:08:16", "remaining_time": "2:13:19", "throughput": 2945.5, "total_tokens": 1462352} {"current_steps": 2235, "total_steps": 38160, "loss": 0.55, "lr": 2.9271488469601676e-05, "epoch": 1.171383647798742, "percentage": 5.86, "elapsed_time": "0:08:17", "remaining_time": "2:13:16", "throughput": 2944.92, "total_tokens": 1465104} {"current_steps": 2240, "total_steps": 38160, "loss": 0.5201, "lr": 2.9337002096436062e-05, "epoch": 1.1740041928721174, "percentage": 5.87, "elapsed_time": "0:08:18", "remaining_time": "2:13:17", "throughput": 2944.65, "total_tokens": 1468624} {"current_steps": 2245, "total_steps": 38160, "loss": 0.4042, "lr": 2.9402515723270442e-05, "epoch": 1.1766247379454926, "percentage": 5.88, "elapsed_time": "0:08:20", "remaining_time": "2:13:29", "throughput": 2946.57, "total_tokens": 1475184} {"current_steps": 2250, "total_steps": 38160, "loss": 0.3685, "lr": 2.9468029350104825e-05, "epoch": 1.179245283018868, "percentage": 5.9, "elapsed_time": "0:08:21", "remaining_time": "2:13:28", "throughput": 2946.79, "total_tokens": 1478640} {"current_steps": 2255, "total_steps": 38160, "loss": 0.5231, "lr": 2.9533542976939205e-05, "epoch": 1.1818658280922432, "percentage": 5.91, "elapsed_time": "0:08:22", "remaining_time": "2:13:26", "throughput": 2946.27, "total_tokens": 1481552} {"current_steps": 2260, "total_steps": 38160, "loss": 0.4235, "lr": 2.9599056603773584e-05, "epoch": 1.1844863731656186, "percentage": 5.92, "elapsed_time": "0:08:23", "remaining_time": "2:13:25", "throughput": 2946.84, "total_tokens": 1485104} {"current_steps": 2265, "total_steps": 38160, "loss": 0.498, "lr": 2.9664570230607968e-05, "epoch": 1.1871069182389937, "percentage": 5.94, "elapsed_time": "0:08:25", "remaining_time": "2:13:23", "throughput": 2945.84, "total_tokens": 1487728} {"current_steps": 2270, "total_steps": 38160, "loss": 0.436, "lr": 2.9730083857442347e-05, "epoch": 1.189727463312369, "percentage": 5.95, "elapsed_time": "0:08:26", "remaining_time": "2:13:23", "throughput": 2946.16, "total_tokens": 1491312} {"current_steps": 2275, "total_steps": 38160, "loss": 0.4977, "lr": 2.9795597484276734e-05, "epoch": 1.1923480083857443, "percentage": 5.96, "elapsed_time": "0:08:27", "remaining_time": "2:13:21", "throughput": 2945.68, "total_tokens": 1494192} {"current_steps": 2280, "total_steps": 38160, "loss": 0.6157, "lr": 2.9861111111111113e-05, "epoch": 1.1949685534591195, "percentage": 5.97, "elapsed_time": "0:08:28", "remaining_time": "2:13:18", "throughput": 2945.53, "total_tokens": 1497168} {"current_steps": 2285, "total_steps": 38160, "loss": 0.482, "lr": 2.9926624737945496e-05, "epoch": 1.1975890985324948, "percentage": 5.99, "elapsed_time": "0:08:29", "remaining_time": "2:13:21", "throughput": 2947.21, "total_tokens": 1501936} {"current_steps": 2290, "total_steps": 38160, "loss": 0.4034, "lr": 2.9992138364779876e-05, "epoch": 1.20020964360587, "percentage": 6.0, "elapsed_time": "0:08:30", "remaining_time": "2:13:19", "throughput": 2947.18, "total_tokens": 1505040} {"current_steps": 2295, "total_steps": 38160, "loss": 0.6102, "lr": 3.0057651991614256e-05, "epoch": 1.2028301886792452, "percentage": 6.01, "elapsed_time": "0:08:31", "remaining_time": "2:13:17", "throughput": 2946.57, "total_tokens": 1507856} {"current_steps": 2300, "total_steps": 38160, "loss": 0.4575, "lr": 3.012316561844864e-05, "epoch": 1.2054507337526206, "percentage": 6.03, "elapsed_time": "0:08:32", "remaining_time": "2:13:15", "throughput": 2946.19, "total_tokens": 1510768} {"current_steps": 2305, "total_steps": 38160, "loss": 0.5981, "lr": 3.018867924528302e-05, "epoch": 1.2080712788259957, "percentage": 6.04, "elapsed_time": "0:08:33", "remaining_time": "2:13:12", "throughput": 2946.12, "total_tokens": 1513808} {"current_steps": 2310, "total_steps": 38160, "loss": 0.4365, "lr": 3.0254192872117405e-05, "epoch": 1.2106918238993711, "percentage": 6.05, "elapsed_time": "0:08:34", "remaining_time": "2:13:11", "throughput": 2946.94, "total_tokens": 1517392} {"current_steps": 2315, "total_steps": 38160, "loss": 0.4805, "lr": 3.0319706498951785e-05, "epoch": 1.2133123689727463, "percentage": 6.07, "elapsed_time": "0:08:36", "remaining_time": "2:13:11", "throughput": 2948.2, "total_tokens": 1521648} {"current_steps": 2320, "total_steps": 38160, "loss": 0.4232, "lr": 3.038522012578616e-05, "epoch": 1.2159329140461215, "percentage": 6.08, "elapsed_time": "0:08:37", "remaining_time": "2:13:09", "throughput": 2947.61, "total_tokens": 1524496} {"current_steps": 2325, "total_steps": 38160, "loss": 0.4965, "lr": 3.0450733752620547e-05, "epoch": 1.2185534591194969, "percentage": 6.09, "elapsed_time": "0:08:38", "remaining_time": "2:13:09", "throughput": 2948.15, "total_tokens": 1528144} {"current_steps": 2330, "total_steps": 38160, "loss": 0.4556, "lr": 3.0516247379454927e-05, "epoch": 1.221174004192872, "percentage": 6.11, "elapsed_time": "0:08:39", "remaining_time": "2:13:07", "throughput": 2948.75, "total_tokens": 1531664} {"current_steps": 2335, "total_steps": 38160, "loss": 0.5805, "lr": 3.0581761006289314e-05, "epoch": 1.2237945492662474, "percentage": 6.12, "elapsed_time": "0:08:40", "remaining_time": "2:13:06", "throughput": 2949.68, "total_tokens": 1535408} {"current_steps": 2340, "total_steps": 38160, "loss": 0.4774, "lr": 3.064727463312369e-05, "epoch": 1.2264150943396226, "percentage": 6.13, "elapsed_time": "0:08:41", "remaining_time": "2:13:04", "throughput": 2949.65, "total_tokens": 1538448} {"current_steps": 2345, "total_steps": 38160, "loss": 0.5075, "lr": 3.071278825995807e-05, "epoch": 1.229035639412998, "percentage": 6.15, "elapsed_time": "0:08:42", "remaining_time": "2:13:02", "throughput": 2950.41, "total_tokens": 1541968} {"current_steps": 2350, "total_steps": 38160, "loss": 0.5195, "lr": 3.0778301886792456e-05, "epoch": 1.2316561844863732, "percentage": 6.16, "elapsed_time": "0:08:43", "remaining_time": "2:13:01", "throughput": 2949.03, "total_tokens": 1544560} {"current_steps": 2355, "total_steps": 38160, "loss": 0.4779, "lr": 3.084381551362683e-05, "epoch": 1.2342767295597485, "percentage": 6.17, "elapsed_time": "0:08:44", "remaining_time": "2:12:59", "throughput": 2949.48, "total_tokens": 1548080} {"current_steps": 2360, "total_steps": 38160, "loss": 0.4238, "lr": 3.0909329140461215e-05, "epoch": 1.2368972746331237, "percentage": 6.18, "elapsed_time": "0:08:45", "remaining_time": "2:12:57", "throughput": 2950.02, "total_tokens": 1551472} {"current_steps": 2365, "total_steps": 38160, "loss": 0.5382, "lr": 3.09748427672956e-05, "epoch": 1.2395178197064989, "percentage": 6.2, "elapsed_time": "0:08:47", "remaining_time": "2:12:56", "throughput": 2948.57, "total_tokens": 1553904} {"current_steps": 2370, "total_steps": 38160, "loss": 0.4235, "lr": 3.104035639412998e-05, "epoch": 1.2421383647798743, "percentage": 6.21, "elapsed_time": "0:08:48", "remaining_time": "2:12:57", "throughput": 2949.96, "total_tokens": 1558352} {"current_steps": 2375, "total_steps": 38160, "loss": 0.3753, "lr": 3.1105870020964365e-05, "epoch": 1.2447589098532494, "percentage": 6.22, "elapsed_time": "0:08:49", "remaining_time": "2:12:56", "throughput": 2949.74, "total_tokens": 1561616} {"current_steps": 2380, "total_steps": 38160, "loss": 0.3546, "lr": 3.117138364779874e-05, "epoch": 1.2473794549266248, "percentage": 6.24, "elapsed_time": "0:08:50", "remaining_time": "2:12:58", "throughput": 2950.78, "total_tokens": 1566000} {"current_steps": 2385, "total_steps": 38160, "loss": 0.4834, "lr": 3.1236897274633124e-05, "epoch": 1.25, "percentage": 6.25, "elapsed_time": "0:08:51", "remaining_time": "2:12:59", "throughput": 2950.93, "total_tokens": 1569776} {"current_steps": 2390, "total_steps": 38160, "loss": 0.5438, "lr": 3.130241090146751e-05, "epoch": 1.2526205450733752, "percentage": 6.26, "elapsed_time": "0:08:53", "remaining_time": "2:12:57", "throughput": 2949.29, "total_tokens": 1572112} {"current_steps": 2395, "total_steps": 38160, "loss": 0.4919, "lr": 3.136792452830189e-05, "epoch": 1.2552410901467506, "percentage": 6.28, "elapsed_time": "0:08:54", "remaining_time": "2:12:55", "throughput": 2949.55, "total_tokens": 1575312} {"current_steps": 2400, "total_steps": 38160, "loss": 0.5564, "lr": 3.1433438155136266e-05, "epoch": 1.2578616352201257, "percentage": 6.29, "elapsed_time": "0:08:55", "remaining_time": "2:12:53", "throughput": 2949.16, "total_tokens": 1578256} {"current_steps": 2405, "total_steps": 38160, "loss": 0.6539, "lr": 3.1498951781970656e-05, "epoch": 1.2604821802935011, "percentage": 6.3, "elapsed_time": "0:08:56", "remaining_time": "2:12:52", "throughput": 2948.91, "total_tokens": 1581328} {"current_steps": 2410, "total_steps": 38160, "loss": 0.5064, "lr": 3.156446540880503e-05, "epoch": 1.2631027253668763, "percentage": 6.32, "elapsed_time": "0:08:57", "remaining_time": "2:12:50", "throughput": 2948.1, "total_tokens": 1583952} {"current_steps": 2415, "total_steps": 38160, "loss": 0.4849, "lr": 3.162997903563941e-05, "epoch": 1.2657232704402515, "percentage": 6.33, "elapsed_time": "0:08:58", "remaining_time": "2:12:48", "throughput": 2948.5, "total_tokens": 1587472} {"current_steps": 2420, "total_steps": 38160, "loss": 0.4261, "lr": 3.16954926624738e-05, "epoch": 1.2683438155136268, "percentage": 6.34, "elapsed_time": "0:08:59", "remaining_time": "2:12:46", "throughput": 2948.24, "total_tokens": 1590384} {"current_steps": 2425, "total_steps": 38160, "loss": 0.442, "lr": 3.1761006289308175e-05, "epoch": 1.270964360587002, "percentage": 6.35, "elapsed_time": "0:09:00", "remaining_time": "2:12:45", "throughput": 2947.6, "total_tokens": 1593264} {"current_steps": 2430, "total_steps": 38160, "loss": 0.4205, "lr": 3.182651991614256e-05, "epoch": 1.2735849056603774, "percentage": 6.37, "elapsed_time": "0:09:01", "remaining_time": "2:12:46", "throughput": 2948.8, "total_tokens": 1597680} {"current_steps": 2435, "total_steps": 38160, "loss": 0.5132, "lr": 3.189203354297694e-05, "epoch": 1.2762054507337526, "percentage": 6.38, "elapsed_time": "0:09:02", "remaining_time": "2:12:44", "throughput": 2948.92, "total_tokens": 1600912} {"current_steps": 2440, "total_steps": 38160, "loss": 0.4129, "lr": 3.1957547169811324e-05, "epoch": 1.2788259958071277, "percentage": 6.39, "elapsed_time": "0:09:03", "remaining_time": "2:12:42", "throughput": 2947.88, "total_tokens": 1603472} {"current_steps": 2445, "total_steps": 38160, "loss": 0.4372, "lr": 3.202306079664571e-05, "epoch": 1.2814465408805031, "percentage": 6.41, "elapsed_time": "0:09:05", "remaining_time": "2:12:41", "throughput": 2947.43, "total_tokens": 1606384} {"current_steps": 2450, "total_steps": 38160, "loss": 0.465, "lr": 3.2088574423480084e-05, "epoch": 1.2840670859538785, "percentage": 6.42, "elapsed_time": "0:09:06", "remaining_time": "2:12:39", "throughput": 2947.1, "total_tokens": 1609360} {"current_steps": 2455, "total_steps": 38160, "loss": 0.4905, "lr": 3.215408805031447e-05, "epoch": 1.2866876310272537, "percentage": 6.43, "elapsed_time": "0:09:07", "remaining_time": "2:12:37", "throughput": 2946.77, "total_tokens": 1612336} {"current_steps": 2460, "total_steps": 38160, "loss": 0.3954, "lr": 3.221960167714885e-05, "epoch": 1.2893081761006289, "percentage": 6.45, "elapsed_time": "0:09:08", "remaining_time": "2:12:35", "throughput": 2947.76, "total_tokens": 1616048} {"current_steps": 2465, "total_steps": 38160, "loss": 0.3752, "lr": 3.228511530398323e-05, "epoch": 1.2919287211740043, "percentage": 6.46, "elapsed_time": "0:09:09", "remaining_time": "2:12:34", "throughput": 2947.4, "total_tokens": 1618960} {"current_steps": 2470, "total_steps": 38160, "loss": 0.336, "lr": 3.235062893081761e-05, "epoch": 1.2945492662473794, "percentage": 6.47, "elapsed_time": "0:09:10", "remaining_time": "2:12:33", "throughput": 2947.8, "total_tokens": 1622544} {"current_steps": 2475, "total_steps": 38160, "loss": 0.4439, "lr": 3.241614255765199e-05, "epoch": 1.2971698113207548, "percentage": 6.49, "elapsed_time": "0:09:11", "remaining_time": "2:12:31", "throughput": 2948.24, "total_tokens": 1625872} {"current_steps": 2480, "total_steps": 38160, "loss": 0.4674, "lr": 3.2481656184486375e-05, "epoch": 1.29979035639413, "percentage": 6.5, "elapsed_time": "0:09:12", "remaining_time": "2:12:30", "throughput": 2948.63, "total_tokens": 1629456} {"current_steps": 2485, "total_steps": 38160, "loss": 0.5714, "lr": 3.254716981132075e-05, "epoch": 1.3024109014675052, "percentage": 6.51, "elapsed_time": "0:09:13", "remaining_time": "2:12:27", "throughput": 2948.6, "total_tokens": 1632432} {"current_steps": 2490, "total_steps": 38160, "loss": 0.446, "lr": 3.261268343815514e-05, "epoch": 1.3050314465408805, "percentage": 6.53, "elapsed_time": "0:09:14", "remaining_time": "2:12:25", "throughput": 2949.68, "total_tokens": 1636080} {"current_steps": 2495, "total_steps": 38160, "loss": 0.4648, "lr": 3.267819706498952e-05, "epoch": 1.3076519916142557, "percentage": 6.54, "elapsed_time": "0:09:15", "remaining_time": "2:12:23", "throughput": 2949.47, "total_tokens": 1638960} {"current_steps": 2500, "total_steps": 38160, "loss": 0.4534, "lr": 3.27437106918239e-05, "epoch": 1.310272536687631, "percentage": 6.55, "elapsed_time": "0:09:16", "remaining_time": "2:12:21", "throughput": 2951.1, "total_tokens": 1643120} {"current_steps": 2505, "total_steps": 38160, "loss": 0.385, "lr": 3.2809224318658284e-05, "epoch": 1.3128930817610063, "percentage": 6.56, "elapsed_time": "0:09:17", "remaining_time": "2:12:20", "throughput": 2951.87, "total_tokens": 1646768} {"current_steps": 2510, "total_steps": 38160, "loss": 0.4922, "lr": 3.287473794549266e-05, "epoch": 1.3155136268343814, "percentage": 6.58, "elapsed_time": "0:09:18", "remaining_time": "2:12:19", "throughput": 2952.23, "total_tokens": 1650256} {"current_steps": 2515, "total_steps": 38160, "loss": 0.4953, "lr": 3.294025157232704e-05, "epoch": 1.3181341719077568, "percentage": 6.59, "elapsed_time": "0:09:20", "remaining_time": "2:12:17", "throughput": 2951.4, "total_tokens": 1652912} {"current_steps": 2520, "total_steps": 38160, "loss": 0.4725, "lr": 3.3005765199161426e-05, "epoch": 1.320754716981132, "percentage": 6.6, "elapsed_time": "0:09:21", "remaining_time": "2:12:17", "throughput": 2951.57, "total_tokens": 1656432} {"current_steps": 2525, "total_steps": 38160, "loss": 0.3954, "lr": 3.307127882599581e-05, "epoch": 1.3233752620545074, "percentage": 6.62, "elapsed_time": "0:09:22", "remaining_time": "2:12:15", "throughput": 2951.28, "total_tokens": 1659472} {"current_steps": 2530, "total_steps": 38160, "loss": 0.4958, "lr": 3.313679245283019e-05, "epoch": 1.3259958071278826, "percentage": 6.63, "elapsed_time": "0:09:23", "remaining_time": "2:12:13", "throughput": 2951.19, "total_tokens": 1662480} {"current_steps": 2535, "total_steps": 38160, "loss": 0.5204, "lr": 3.320230607966457e-05, "epoch": 1.3286163522012577, "percentage": 6.64, "elapsed_time": "0:09:24", "remaining_time": "2:12:11", "throughput": 2950.84, "total_tokens": 1665424} {"current_steps": 2540, "total_steps": 38160, "loss": 0.53, "lr": 3.326781970649895e-05, "epoch": 1.3312368972746331, "percentage": 6.66, "elapsed_time": "0:09:25", "remaining_time": "2:12:09", "throughput": 2949.55, "total_tokens": 1667760} {"current_steps": 2545, "total_steps": 38160, "loss": 0.3832, "lr": 3.3333333333333335e-05, "epoch": 1.3338574423480085, "percentage": 6.67, "elapsed_time": "0:09:26", "remaining_time": "2:12:07", "throughput": 2949.25, "total_tokens": 1670800} {"current_steps": 2550, "total_steps": 38160, "loss": 0.509, "lr": 3.339884696016772e-05, "epoch": 1.3364779874213837, "percentage": 6.68, "elapsed_time": "0:09:27", "remaining_time": "2:12:09", "throughput": 2951.17, "total_tokens": 1675760} {"current_steps": 2555, "total_steps": 38160, "loss": 0.5548, "lr": 3.3464360587002094e-05, "epoch": 1.3390985324947589, "percentage": 6.7, "elapsed_time": "0:09:28", "remaining_time": "2:12:07", "throughput": 2949.58, "total_tokens": 1677936} {"current_steps": 2560, "total_steps": 38160, "loss": 0.5665, "lr": 3.3529874213836484e-05, "epoch": 1.3417190775681342, "percentage": 6.71, "elapsed_time": "0:09:30", "remaining_time": "2:12:18", "throughput": 2951.55, "total_tokens": 1685008} {"current_steps": 2565, "total_steps": 38160, "loss": 0.5916, "lr": 3.359538784067086e-05, "epoch": 1.3443396226415094, "percentage": 6.72, "elapsed_time": "0:09:31", "remaining_time": "2:12:17", "throughput": 2951.74, "total_tokens": 1688240} {"current_steps": 2570, "total_steps": 38160, "loss": 0.6286, "lr": 3.3660901467505244e-05, "epoch": 1.3469601677148848, "percentage": 6.73, "elapsed_time": "0:09:33", "remaining_time": "2:12:15", "throughput": 2950.8, "total_tokens": 1690832} {"current_steps": 2575, "total_steps": 38160, "loss": 0.6035, "lr": 3.3726415094339627e-05, "epoch": 1.34958071278826, "percentage": 6.75, "elapsed_time": "0:09:34", "remaining_time": "2:12:16", "throughput": 2951.87, "total_tokens": 1695248} {"current_steps": 2580, "total_steps": 38160, "loss": 0.4751, "lr": 3.3791928721174e-05, "epoch": 1.3522012578616351, "percentage": 6.76, "elapsed_time": "0:09:35", "remaining_time": "2:12:16", "throughput": 2952.22, "total_tokens": 1698896} {"current_steps": 2585, "total_steps": 38160, "loss": 0.5938, "lr": 3.3857442348008386e-05, "epoch": 1.3548218029350105, "percentage": 6.77, "elapsed_time": "0:09:36", "remaining_time": "2:12:14", "throughput": 2950.95, "total_tokens": 1701296} {"current_steps": 2590, "total_steps": 38160, "loss": 0.352, "lr": 3.392295597484277e-05, "epoch": 1.3574423480083857, "percentage": 6.79, "elapsed_time": "0:09:37", "remaining_time": "2:12:12", "throughput": 2952.09, "total_tokens": 1705136} {"current_steps": 2595, "total_steps": 38160, "loss": 0.4463, "lr": 3.398846960167715e-05, "epoch": 1.360062893081761, "percentage": 6.8, "elapsed_time": "0:09:38", "remaining_time": "2:12:10", "throughput": 2951.61, "total_tokens": 1708016} {"current_steps": 2600, "total_steps": 38160, "loss": 0.604, "lr": 3.4053983228511535e-05, "epoch": 1.3626834381551363, "percentage": 6.81, "elapsed_time": "0:09:39", "remaining_time": "2:12:08", "throughput": 2951.21, "total_tokens": 1710864} {"current_steps": 2605, "total_steps": 38160, "loss": 0.3936, "lr": 3.411949685534591e-05, "epoch": 1.3653039832285114, "percentage": 6.83, "elapsed_time": "0:09:40", "remaining_time": "2:12:06", "throughput": 2950.61, "total_tokens": 1713552} {"current_steps": 2610, "total_steps": 38160, "loss": 0.4097, "lr": 3.4185010482180295e-05, "epoch": 1.3679245283018868, "percentage": 6.84, "elapsed_time": "0:09:41", "remaining_time": "2:12:04", "throughput": 2950.47, "total_tokens": 1716528} {"current_steps": 2615, "total_steps": 38160, "loss": 0.4288, "lr": 3.425052410901468e-05, "epoch": 1.370545073375262, "percentage": 6.85, "elapsed_time": "0:09:42", "remaining_time": "2:12:02", "throughput": 2949.73, "total_tokens": 1719216} {"current_steps": 2620, "total_steps": 38160, "loss": 0.5054, "lr": 3.431603773584906e-05, "epoch": 1.3731656184486374, "percentage": 6.87, "elapsed_time": "0:09:43", "remaining_time": "2:12:00", "throughput": 2949.68, "total_tokens": 1722384} {"current_steps": 2625, "total_steps": 38160, "loss": 0.4267, "lr": 3.438155136268344e-05, "epoch": 1.3757861635220126, "percentage": 6.88, "elapsed_time": "0:09:45", "remaining_time": "2:11:59", "throughput": 2948.78, "total_tokens": 1725104} {"current_steps": 2630, "total_steps": 38160, "loss": 0.4437, "lr": 3.444706498951782e-05, "epoch": 1.3784067085953877, "percentage": 6.89, "elapsed_time": "0:09:46", "remaining_time": "2:11:58", "throughput": 2948.41, "total_tokens": 1728112} {"current_steps": 2635, "total_steps": 38160, "loss": 0.4852, "lr": 3.45125786163522e-05, "epoch": 1.381027253668763, "percentage": 6.91, "elapsed_time": "0:09:47", "remaining_time": "2:11:56", "throughput": 2948.76, "total_tokens": 1731536} {"current_steps": 2640, "total_steps": 38160, "loss": 0.5252, "lr": 3.457809224318658e-05, "epoch": 1.3836477987421385, "percentage": 6.92, "elapsed_time": "0:09:48", "remaining_time": "2:11:55", "throughput": 2949.05, "total_tokens": 1734896} {"current_steps": 2645, "total_steps": 38160, "loss": 0.4861, "lr": 3.464360587002097e-05, "epoch": 1.3862683438155137, "percentage": 6.93, "elapsed_time": "0:09:49", "remaining_time": "2:11:53", "throughput": 2948.36, "total_tokens": 1737584} {"current_steps": 2650, "total_steps": 38160, "loss": 0.5482, "lr": 3.4709119496855346e-05, "epoch": 1.3888888888888888, "percentage": 6.94, "elapsed_time": "0:09:50", "remaining_time": "2:11:51", "throughput": 2948.35, "total_tokens": 1740720} {"current_steps": 2655, "total_steps": 38160, "loss": 0.3392, "lr": 3.477463312368973e-05, "epoch": 1.3915094339622642, "percentage": 6.96, "elapsed_time": "0:09:51", "remaining_time": "2:11:49", "throughput": 2947.24, "total_tokens": 1743216} {"current_steps": 2660, "total_steps": 38160, "loss": 0.5271, "lr": 3.484014675052411e-05, "epoch": 1.3941299790356394, "percentage": 6.97, "elapsed_time": "0:09:52", "remaining_time": "2:11:47", "throughput": 2946.82, "total_tokens": 1746000} {"current_steps": 2665, "total_steps": 38160, "loss": 0.392, "lr": 3.490566037735849e-05, "epoch": 1.3967505241090148, "percentage": 6.98, "elapsed_time": "0:09:53", "remaining_time": "2:11:45", "throughput": 2945.88, "total_tokens": 1748560} {"current_steps": 2670, "total_steps": 38160, "loss": 0.542, "lr": 3.497117400419288e-05, "epoch": 1.39937106918239, "percentage": 7.0, "elapsed_time": "0:09:54", "remaining_time": "2:11:43", "throughput": 2945.56, "total_tokens": 1751504} {"current_steps": 2675, "total_steps": 38160, "loss": 0.4536, "lr": 3.5036687631027254e-05, "epoch": 1.4019916142557651, "percentage": 7.01, "elapsed_time": "0:09:55", "remaining_time": "2:11:41", "throughput": 2946.0, "total_tokens": 1754864} {"current_steps": 2680, "total_steps": 38160, "loss": 0.4715, "lr": 3.510220125786164e-05, "epoch": 1.4046121593291405, "percentage": 7.02, "elapsed_time": "0:09:56", "remaining_time": "2:11:40", "throughput": 2945.27, "total_tokens": 1757648} {"current_steps": 2685, "total_steps": 38160, "loss": 0.4695, "lr": 3.516771488469602e-05, "epoch": 1.4072327044025157, "percentage": 7.04, "elapsed_time": "0:09:57", "remaining_time": "2:11:38", "throughput": 2944.81, "total_tokens": 1760432} {"current_steps": 2690, "total_steps": 38160, "loss": 0.4834, "lr": 3.5233228511530397e-05, "epoch": 1.409853249475891, "percentage": 7.05, "elapsed_time": "0:09:58", "remaining_time": "2:11:37", "throughput": 2944.72, "total_tokens": 1763664} {"current_steps": 2695, "total_steps": 38160, "loss": 0.4001, "lr": 3.529874213836478e-05, "epoch": 1.4124737945492662, "percentage": 7.06, "elapsed_time": "0:10:00", "remaining_time": "2:11:36", "throughput": 2944.22, "total_tokens": 1766640} {"current_steps": 2700, "total_steps": 38160, "loss": 0.4683, "lr": 3.536425576519916e-05, "epoch": 1.4150943396226414, "percentage": 7.08, "elapsed_time": "0:10:01", "remaining_time": "2:11:34", "throughput": 2944.29, "total_tokens": 1769776} {"current_steps": 2705, "total_steps": 38160, "loss": 0.513, "lr": 3.5429769392033546e-05, "epoch": 1.4177148846960168, "percentage": 7.09, "elapsed_time": "0:10:02", "remaining_time": "2:11:33", "throughput": 2942.71, "total_tokens": 1772112} {"current_steps": 2710, "total_steps": 38160, "loss": 0.4658, "lr": 3.549528301886792e-05, "epoch": 1.420335429769392, "percentage": 7.1, "elapsed_time": "0:10:03", "remaining_time": "2:11:31", "throughput": 2942.77, "total_tokens": 1775312} {"current_steps": 2715, "total_steps": 38160, "loss": 0.5959, "lr": 3.556079664570231e-05, "epoch": 1.4229559748427674, "percentage": 7.11, "elapsed_time": "0:10:04", "remaining_time": "2:11:32", "throughput": 2943.44, "total_tokens": 1779504} {"current_steps": 2720, "total_steps": 38160, "loss": 0.4338, "lr": 3.562631027253669e-05, "epoch": 1.4255765199161425, "percentage": 7.13, "elapsed_time": "0:10:05", "remaining_time": "2:11:32", "throughput": 2943.91, "total_tokens": 1783248} {"current_steps": 2725, "total_steps": 38160, "loss": 0.3472, "lr": 3.569182389937107e-05, "epoch": 1.4281970649895177, "percentage": 7.14, "elapsed_time": "0:10:07", "remaining_time": "2:11:38", "throughput": 2945.76, "total_tokens": 1789168} {"current_steps": 2730, "total_steps": 38160, "loss": 0.4474, "lr": 3.5757337526205454e-05, "epoch": 1.430817610062893, "percentage": 7.15, "elapsed_time": "0:10:08", "remaining_time": "2:11:36", "throughput": 2946.01, "total_tokens": 1792592} {"current_steps": 2735, "total_steps": 38160, "loss": 0.4904, "lr": 3.582285115303983e-05, "epoch": 1.4334381551362683, "percentage": 7.17, "elapsed_time": "0:10:09", "remaining_time": "2:11:34", "throughput": 2945.82, "total_tokens": 1795536} {"current_steps": 2740, "total_steps": 38160, "loss": 0.4282, "lr": 3.588836477987422e-05, "epoch": 1.4360587002096437, "percentage": 7.18, "elapsed_time": "0:10:10", "remaining_time": "2:11:33", "throughput": 2944.73, "total_tokens": 1798064} {"current_steps": 2745, "total_steps": 38160, "loss": 0.4659, "lr": 3.59538784067086e-05, "epoch": 1.4386792452830188, "percentage": 7.19, "elapsed_time": "0:10:11", "remaining_time": "2:11:31", "throughput": 2945.21, "total_tokens": 1801392} {"current_steps": 2750, "total_steps": 38160, "loss": 0.5285, "lr": 3.601939203354298e-05, "epoch": 1.441299790356394, "percentage": 7.21, "elapsed_time": "0:10:12", "remaining_time": "2:11:29", "throughput": 2944.96, "total_tokens": 1804368} {"current_steps": 2755, "total_steps": 38160, "loss": 0.5262, "lr": 3.608490566037736e-05, "epoch": 1.4439203354297694, "percentage": 7.22, "elapsed_time": "0:10:13", "remaining_time": "2:11:27", "throughput": 2944.99, "total_tokens": 1807504} {"current_steps": 2760, "total_steps": 38160, "loss": 0.3596, "lr": 3.615041928721174e-05, "epoch": 1.4465408805031448, "percentage": 7.23, "elapsed_time": "0:10:14", "remaining_time": "2:11:25", "throughput": 2944.37, "total_tokens": 1810160} {"current_steps": 2765, "total_steps": 38160, "loss": 0.4683, "lr": 3.621593291404612e-05, "epoch": 1.44916142557652, "percentage": 7.25, "elapsed_time": "0:10:15", "remaining_time": "2:11:24", "throughput": 2944.66, "total_tokens": 1813616} {"current_steps": 2770, "total_steps": 38160, "loss": 0.4432, "lr": 3.6281446540880505e-05, "epoch": 1.4517819706498951, "percentage": 7.26, "elapsed_time": "0:10:16", "remaining_time": "2:11:22", "throughput": 2944.66, "total_tokens": 1816752} {"current_steps": 2775, "total_steps": 38160, "loss": 0.4461, "lr": 3.634696016771489e-05, "epoch": 1.4544025157232705, "percentage": 7.27, "elapsed_time": "0:10:18", "remaining_time": "2:11:25", "throughput": 2944.16, "total_tokens": 1820784} {"current_steps": 2780, "total_steps": 38160, "loss": 0.3938, "lr": 3.6412473794549265e-05, "epoch": 1.4570230607966457, "percentage": 7.29, "elapsed_time": "0:10:19", "remaining_time": "2:11:24", "throughput": 2942.58, "total_tokens": 1823024} {"current_steps": 2785, "total_steps": 38160, "loss": 0.5382, "lr": 3.647798742138365e-05, "epoch": 1.459643605870021, "percentage": 7.3, "elapsed_time": "0:10:20", "remaining_time": "2:11:26", "throughput": 2944.03, "total_tokens": 1828016} {"current_steps": 2790, "total_steps": 38160, "loss": 0.5113, "lr": 3.654350104821803e-05, "epoch": 1.4622641509433962, "percentage": 7.31, "elapsed_time": "0:10:21", "remaining_time": "2:11:25", "throughput": 2944.2, "total_tokens": 1831280} {"current_steps": 2795, "total_steps": 38160, "loss": 0.4139, "lr": 3.6609014675052414e-05, "epoch": 1.4648846960167714, "percentage": 7.32, "elapsed_time": "0:10:23", "remaining_time": "2:11:23", "throughput": 2944.98, "total_tokens": 1834896} {"current_steps": 2800, "total_steps": 38160, "loss": 0.4414, "lr": 3.66745283018868e-05, "epoch": 1.4675052410901468, "percentage": 7.34, "elapsed_time": "0:10:24", "remaining_time": "2:11:21", "throughput": 2944.11, "total_tokens": 1837488} {"current_steps": 2805, "total_steps": 38160, "loss": 0.5171, "lr": 3.6740041928721173e-05, "epoch": 1.470125786163522, "percentage": 7.35, "elapsed_time": "0:10:25", "remaining_time": "2:11:21", "throughput": 2945.13, "total_tokens": 1841584} {"current_steps": 2810, "total_steps": 38160, "loss": 0.5345, "lr": 3.6805555555555556e-05, "epoch": 1.4727463312368974, "percentage": 7.36, "elapsed_time": "0:10:26", "remaining_time": "2:11:19", "throughput": 2945.13, "total_tokens": 1844688} {"current_steps": 2815, "total_steps": 38160, "loss": 0.4745, "lr": 3.687106918238994e-05, "epoch": 1.4753668763102725, "percentage": 7.38, "elapsed_time": "0:10:27", "remaining_time": "2:11:17", "throughput": 2944.52, "total_tokens": 1847472} {"current_steps": 2820, "total_steps": 38160, "loss": 0.682, "lr": 3.6936582809224316e-05, "epoch": 1.4779874213836477, "percentage": 7.39, "elapsed_time": "0:10:28", "remaining_time": "2:11:16", "throughput": 2945.04, "total_tokens": 1851088} {"current_steps": 2825, "total_steps": 38160, "loss": 0.4793, "lr": 3.7002096436058706e-05, "epoch": 1.480607966457023, "percentage": 7.4, "elapsed_time": "0:10:29", "remaining_time": "2:11:17", "throughput": 2945.58, "total_tokens": 1855216} {"current_steps": 2830, "total_steps": 38160, "loss": 0.4007, "lr": 3.706761006289308e-05, "epoch": 1.4832285115303983, "percentage": 7.42, "elapsed_time": "0:10:30", "remaining_time": "2:11:16", "throughput": 2944.53, "total_tokens": 1857744} {"current_steps": 2835, "total_steps": 38160, "loss": 0.4102, "lr": 3.7133123689727465e-05, "epoch": 1.4858490566037736, "percentage": 7.43, "elapsed_time": "0:10:31", "remaining_time": "2:11:14", "throughput": 2943.8, "total_tokens": 1860400} {"current_steps": 2840, "total_steps": 38160, "loss": 0.521, "lr": 3.719863731656185e-05, "epoch": 1.4884696016771488, "percentage": 7.44, "elapsed_time": "0:10:33", "remaining_time": "2:11:13", "throughput": 2943.0, "total_tokens": 1863248} {"current_steps": 2845, "total_steps": 38160, "loss": 0.4603, "lr": 3.7264150943396224e-05, "epoch": 1.491090146750524, "percentage": 7.46, "elapsed_time": "0:10:34", "remaining_time": "2:11:12", "throughput": 2943.14, "total_tokens": 1866576} {"current_steps": 2850, "total_steps": 38160, "loss": 0.4304, "lr": 3.732966457023061e-05, "epoch": 1.4937106918238994, "percentage": 7.47, "elapsed_time": "0:10:35", "remaining_time": "2:11:10", "throughput": 2943.51, "total_tokens": 1869840} {"current_steps": 2855, "total_steps": 38160, "loss": 0.5746, "lr": 3.739517819706499e-05, "epoch": 1.4963312368972748, "percentage": 7.48, "elapsed_time": "0:10:36", "remaining_time": "2:11:08", "throughput": 2942.89, "total_tokens": 1872624} {"current_steps": 2860, "total_steps": 38160, "loss": 0.4636, "lr": 3.7460691823899374e-05, "epoch": 1.49895178197065, "percentage": 7.49, "elapsed_time": "0:10:37", "remaining_time": "2:11:07", "throughput": 2943.24, "total_tokens": 1876016} {"current_steps": 2865, "total_steps": 38160, "loss": 0.4003, "lr": 3.752620545073376e-05, "epoch": 1.501572327044025, "percentage": 7.51, "elapsed_time": "0:10:38", "remaining_time": "2:11:10", "throughput": 2944.14, "total_tokens": 1880976} {"current_steps": 2870, "total_steps": 38160, "loss": 0.5604, "lr": 3.759171907756814e-05, "epoch": 1.5041928721174003, "percentage": 7.52, "elapsed_time": "0:10:39", "remaining_time": "2:11:08", "throughput": 2943.36, "total_tokens": 1883568} {"current_steps": 2875, "total_steps": 38160, "loss": 0.4581, "lr": 3.7657232704402516e-05, "epoch": 1.5068134171907757, "percentage": 7.53, "elapsed_time": "0:10:41", "remaining_time": "2:11:07", "throughput": 2943.32, "total_tokens": 1886800} {"current_steps": 2880, "total_steps": 38160, "loss": 0.4358, "lr": 3.77227463312369e-05, "epoch": 1.509433962264151, "percentage": 7.55, "elapsed_time": "0:10:42", "remaining_time": "2:11:06", "throughput": 2944.41, "total_tokens": 1890672} {"current_steps": 2885, "total_steps": 38160, "loss": 0.3561, "lr": 3.778825995807128e-05, "epoch": 1.5120545073375262, "percentage": 7.56, "elapsed_time": "0:10:43", "remaining_time": "2:11:04", "throughput": 2943.9, "total_tokens": 1893456} {"current_steps": 2890, "total_steps": 38160, "loss": 0.4757, "lr": 3.785377358490566e-05, "epoch": 1.5146750524109014, "percentage": 7.57, "elapsed_time": "0:10:44", "remaining_time": "2:11:02", "throughput": 2944.13, "total_tokens": 1896752} {"current_steps": 2895, "total_steps": 38160, "loss": 0.4013, "lr": 3.791928721174005e-05, "epoch": 1.5172955974842768, "percentage": 7.59, "elapsed_time": "0:10:45", "remaining_time": "2:11:00", "throughput": 2943.82, "total_tokens": 1899664} {"current_steps": 2900, "total_steps": 38160, "loss": 0.3692, "lr": 3.7984800838574425e-05, "epoch": 1.519916142557652, "percentage": 7.6, "elapsed_time": "0:10:46", "remaining_time": "2:10:58", "throughput": 2943.17, "total_tokens": 1902320} {"current_steps": 2905, "total_steps": 38160, "loss": 0.5233, "lr": 3.805031446540881e-05, "epoch": 1.5225366876310273, "percentage": 7.61, "elapsed_time": "0:10:47", "remaining_time": "2:10:56", "throughput": 2943.27, "total_tokens": 1905488} {"current_steps": 2910, "total_steps": 38160, "loss": 0.4443, "lr": 3.811582809224319e-05, "epoch": 1.5251572327044025, "percentage": 7.63, "elapsed_time": "0:10:48", "remaining_time": "2:10:54", "throughput": 2942.64, "total_tokens": 1908144} {"current_steps": 2915, "total_steps": 38160, "loss": 0.4354, "lr": 3.818134171907757e-05, "epoch": 1.5277777777777777, "percentage": 7.64, "elapsed_time": "0:10:49", "remaining_time": "2:10:54", "throughput": 2942.42, "total_tokens": 1911536} {"current_steps": 2920, "total_steps": 38160, "loss": 0.4494, "lr": 3.824685534591195e-05, "epoch": 1.530398322851153, "percentage": 7.65, "elapsed_time": "0:10:50", "remaining_time": "2:10:55", "throughput": 2944.01, "total_tokens": 1916176} {"current_steps": 2925, "total_steps": 38160, "loss": 0.4567, "lr": 3.831236897274633e-05, "epoch": 1.5330188679245285, "percentage": 7.67, "elapsed_time": "0:10:52", "remaining_time": "2:10:54", "throughput": 2945.68, "total_tokens": 1920592} {"current_steps": 2930, "total_steps": 38160, "loss": 0.4435, "lr": 3.8377882599580716e-05, "epoch": 1.5356394129979036, "percentage": 7.68, "elapsed_time": "0:10:53", "remaining_time": "2:10:52", "throughput": 2944.71, "total_tokens": 1923152} {"current_steps": 2935, "total_steps": 38160, "loss": 0.4956, "lr": 3.844339622641509e-05, "epoch": 1.5382599580712788, "percentage": 7.69, "elapsed_time": "0:10:54", "remaining_time": "2:10:51", "throughput": 2944.08, "total_tokens": 1926000} {"current_steps": 2940, "total_steps": 38160, "loss": 0.5237, "lr": 3.8508909853249476e-05, "epoch": 1.540880503144654, "percentage": 7.7, "elapsed_time": "0:10:55", "remaining_time": "2:10:49", "throughput": 2944.01, "total_tokens": 1929072} {"current_steps": 2945, "total_steps": 38160, "loss": 0.3307, "lr": 3.857442348008386e-05, "epoch": 1.5435010482180294, "percentage": 7.72, "elapsed_time": "0:10:56", "remaining_time": "2:10:47", "throughput": 2944.06, "total_tokens": 1932208} {"current_steps": 2950, "total_steps": 38160, "loss": 0.6308, "lr": 3.863993710691824e-05, "epoch": 1.5461215932914047, "percentage": 7.73, "elapsed_time": "0:10:57", "remaining_time": "2:10:46", "throughput": 2943.74, "total_tokens": 1935152} {"current_steps": 2955, "total_steps": 38160, "loss": 0.5213, "lr": 3.8705450733752625e-05, "epoch": 1.54874213836478, "percentage": 7.74, "elapsed_time": "0:10:58", "remaining_time": "2:10:44", "throughput": 2944.22, "total_tokens": 1938704} {"current_steps": 2960, "total_steps": 38160, "loss": 0.5464, "lr": 3.8770964360587e-05, "epoch": 1.551362683438155, "percentage": 7.76, "elapsed_time": "0:10:59", "remaining_time": "2:10:43", "throughput": 2944.56, "total_tokens": 1942192} {"current_steps": 2965, "total_steps": 38160, "loss": 0.4301, "lr": 3.883647798742139e-05, "epoch": 1.5539832285115303, "percentage": 7.77, "elapsed_time": "0:11:00", "remaining_time": "2:10:42", "throughput": 2944.85, "total_tokens": 1945744} {"current_steps": 2970, "total_steps": 38160, "loss": 0.456, "lr": 3.890199161425577e-05, "epoch": 1.5566037735849056, "percentage": 7.78, "elapsed_time": "0:11:01", "remaining_time": "2:10:41", "throughput": 2944.92, "total_tokens": 1948944} {"current_steps": 2975, "total_steps": 38160, "loss": 0.4307, "lr": 3.8967505241090144e-05, "epoch": 1.559224318658281, "percentage": 7.8, "elapsed_time": "0:11:02", "remaining_time": "2:10:39", "throughput": 2944.62, "total_tokens": 1951792} {"current_steps": 2980, "total_steps": 38160, "loss": 0.5099, "lr": 3.9033018867924534e-05, "epoch": 1.5618448637316562, "percentage": 7.81, "elapsed_time": "0:11:03", "remaining_time": "2:10:38", "throughput": 2945.06, "total_tokens": 1955376} {"current_steps": 2985, "total_steps": 38160, "loss": 0.4855, "lr": 3.909853249475891e-05, "epoch": 1.5644654088050314, "percentage": 7.82, "elapsed_time": "0:11:05", "remaining_time": "2:10:37", "throughput": 2945.73, "total_tokens": 1959120} {"current_steps": 2990, "total_steps": 38160, "loss": 0.3743, "lr": 3.916404612159329e-05, "epoch": 1.5670859538784065, "percentage": 7.84, "elapsed_time": "0:11:06", "remaining_time": "2:10:37", "throughput": 2948.06, "total_tokens": 1964304} {"current_steps": 2995, "total_steps": 38160, "loss": 0.5761, "lr": 3.9229559748427676e-05, "epoch": 1.569706498951782, "percentage": 7.85, "elapsed_time": "0:11:07", "remaining_time": "2:10:35", "throughput": 2947.07, "total_tokens": 1966832} {"current_steps": 3000, "total_steps": 38160, "loss": 0.5471, "lr": 3.929507337526205e-05, "epoch": 1.5723270440251573, "percentage": 7.86, "elapsed_time": "0:11:08", "remaining_time": "2:10:35", "throughput": 2947.08, "total_tokens": 1970224} {"current_steps": 3005, "total_steps": 38160, "loss": 0.4731, "lr": 3.9360587002096435e-05, "epoch": 1.5749475890985325, "percentage": 7.87, "elapsed_time": "0:11:09", "remaining_time": "2:10:34", "throughput": 2948.11, "total_tokens": 1974288} {"current_steps": 3010, "total_steps": 38160, "loss": 0.4063, "lr": 3.942610062893082e-05, "epoch": 1.5775681341719077, "percentage": 7.89, "elapsed_time": "0:11:10", "remaining_time": "2:10:32", "throughput": 2949.11, "total_tokens": 1978064} {"current_steps": 3015, "total_steps": 38160, "loss": 0.5022, "lr": 3.94916142557652e-05, "epoch": 1.580188679245283, "percentage": 7.9, "elapsed_time": "0:11:11", "remaining_time": "2:10:31", "throughput": 2949.78, "total_tokens": 1981744} {"current_steps": 3020, "total_steps": 38160, "loss": 0.4914, "lr": 3.9557127882599585e-05, "epoch": 1.5828092243186582, "percentage": 7.91, "elapsed_time": "0:11:12", "remaining_time": "2:10:28", "throughput": 2948.73, "total_tokens": 1984016} {"current_steps": 3025, "total_steps": 38160, "loss": 0.3403, "lr": 3.962264150943397e-05, "epoch": 1.5854297693920336, "percentage": 7.93, "elapsed_time": "0:11:13", "remaining_time": "2:10:27", "throughput": 2948.64, "total_tokens": 1987056} {"current_steps": 3030, "total_steps": 38160, "loss": 0.5119, "lr": 3.9688155136268344e-05, "epoch": 1.5880503144654088, "percentage": 7.94, "elapsed_time": "0:11:15", "remaining_time": "2:10:27", "throughput": 2950.42, "total_tokens": 1992048} {"current_steps": 3035, "total_steps": 38160, "loss": 0.6167, "lr": 3.975366876310273e-05, "epoch": 1.590670859538784, "percentage": 7.95, "elapsed_time": "0:11:16", "remaining_time": "2:10:26", "throughput": 2950.93, "total_tokens": 1995472} {"current_steps": 3040, "total_steps": 38160, "loss": 0.3579, "lr": 3.981918238993711e-05, "epoch": 1.5932914046121593, "percentage": 7.97, "elapsed_time": "0:11:17", "remaining_time": "2:10:25", "throughput": 2951.49, "total_tokens": 1999152} {"current_steps": 3045, "total_steps": 38160, "loss": 0.4982, "lr": 3.9884696016771486e-05, "epoch": 1.5959119496855347, "percentage": 7.98, "elapsed_time": "0:11:18", "remaining_time": "2:10:23", "throughput": 2950.68, "total_tokens": 2001744} {"current_steps": 3050, "total_steps": 38160, "loss": 0.5746, "lr": 3.9950209643605876e-05, "epoch": 1.59853249475891, "percentage": 7.99, "elapsed_time": "0:11:19", "remaining_time": "2:10:21", "throughput": 2950.68, "total_tokens": 2004848} {"current_steps": 3055, "total_steps": 38160, "loss": 0.5147, "lr": 4.001572327044025e-05, "epoch": 1.601153039832285, "percentage": 8.01, "elapsed_time": "0:11:20", "remaining_time": "2:10:19", "throughput": 2950.74, "total_tokens": 2007920} {"current_steps": 3060, "total_steps": 38160, "loss": 0.4407, "lr": 4.0081236897274636e-05, "epoch": 1.6037735849056602, "percentage": 8.02, "elapsed_time": "0:11:21", "remaining_time": "2:10:17", "throughput": 2951.0, "total_tokens": 2011152} {"current_steps": 3065, "total_steps": 38160, "loss": 0.5602, "lr": 4.014675052410902e-05, "epoch": 1.6063941299790356, "percentage": 8.03, "elapsed_time": "0:11:22", "remaining_time": "2:10:15", "throughput": 2950.6, "total_tokens": 2013968} {"current_steps": 3070, "total_steps": 38160, "loss": 0.5073, "lr": 4.0212264150943395e-05, "epoch": 1.609014675052411, "percentage": 8.05, "elapsed_time": "0:11:23", "remaining_time": "2:10:15", "throughput": 2951.18, "total_tokens": 2017936} {"current_steps": 3075, "total_steps": 38160, "loss": 0.416, "lr": 4.027777777777778e-05, "epoch": 1.6116352201257862, "percentage": 8.06, "elapsed_time": "0:11:24", "remaining_time": "2:10:13", "throughput": 2950.34, "total_tokens": 2020528} {"current_steps": 3080, "total_steps": 38160, "loss": 0.6204, "lr": 4.034329140461216e-05, "epoch": 1.6142557651991614, "percentage": 8.07, "elapsed_time": "0:11:25", "remaining_time": "2:10:12", "throughput": 2950.43, "total_tokens": 2023792} {"current_steps": 3085, "total_steps": 38160, "loss": 0.5078, "lr": 4.0408805031446544e-05, "epoch": 1.6168763102725365, "percentage": 8.08, "elapsed_time": "0:11:27", "remaining_time": "2:10:11", "throughput": 2950.67, "total_tokens": 2027152} {"current_steps": 3090, "total_steps": 38160, "loss": 0.3421, "lr": 4.047431865828093e-05, "epoch": 1.619496855345912, "percentage": 8.1, "elapsed_time": "0:11:28", "remaining_time": "2:10:09", "throughput": 2950.26, "total_tokens": 2029968} {"current_steps": 3095, "total_steps": 38160, "loss": 0.4268, "lr": 4.0539832285115304e-05, "epoch": 1.6221174004192873, "percentage": 8.11, "elapsed_time": "0:11:29", "remaining_time": "2:10:08", "throughput": 2950.42, "total_tokens": 2033488} {"current_steps": 3100, "total_steps": 38160, "loss": 0.5312, "lr": 4.0605345911949687e-05, "epoch": 1.6247379454926625, "percentage": 8.12, "elapsed_time": "0:11:30", "remaining_time": "2:10:07", "throughput": 2950.86, "total_tokens": 2037136} {"current_steps": 3105, "total_steps": 38160, "loss": 0.4617, "lr": 4.067085953878407e-05, "epoch": 1.6273584905660377, "percentage": 8.14, "elapsed_time": "0:11:31", "remaining_time": "2:10:06", "throughput": 2950.1, "total_tokens": 2039888} {"current_steps": 3110, "total_steps": 38160, "loss": 0.6456, "lr": 4.073637316561845e-05, "epoch": 1.629979035639413, "percentage": 8.15, "elapsed_time": "0:11:32", "remaining_time": "2:10:05", "throughput": 2950.03, "total_tokens": 2043024} {"current_steps": 3115, "total_steps": 38160, "loss": 0.3562, "lr": 4.080188679245283e-05, "epoch": 1.6325995807127882, "percentage": 8.16, "elapsed_time": "0:11:33", "remaining_time": "2:10:04", "throughput": 2950.94, "total_tokens": 2047056} {"current_steps": 3120, "total_steps": 38160, "loss": 0.5273, "lr": 4.086740041928722e-05, "epoch": 1.6352201257861636, "percentage": 8.18, "elapsed_time": "0:11:34", "remaining_time": "2:10:02", "throughput": 2950.74, "total_tokens": 2050000} {"current_steps": 3125, "total_steps": 38160, "loss": 0.467, "lr": 4.0932914046121595e-05, "epoch": 1.6378406708595388, "percentage": 8.19, "elapsed_time": "0:11:35", "remaining_time": "2:10:01", "throughput": 2951.92, "total_tokens": 2054032} {"current_steps": 3130, "total_steps": 38160, "loss": 0.4806, "lr": 4.099842767295597e-05, "epoch": 1.640461215932914, "percentage": 8.2, "elapsed_time": "0:11:36", "remaining_time": "2:09:59", "throughput": 2951.72, "total_tokens": 2057072} {"current_steps": 3135, "total_steps": 38160, "loss": 0.4452, "lr": 4.106394129979036e-05, "epoch": 1.6430817610062893, "percentage": 8.22, "elapsed_time": "0:11:37", "remaining_time": "2:09:58", "throughput": 2952.28, "total_tokens": 2060656} {"current_steps": 3140, "total_steps": 38160, "loss": 0.5115, "lr": 4.112945492662474e-05, "epoch": 1.6457023060796647, "percentage": 8.23, "elapsed_time": "0:11:39", "remaining_time": "2:09:56", "throughput": 2951.96, "total_tokens": 2063568} {"current_steps": 3145, "total_steps": 38160, "loss": 0.3865, "lr": 4.119496855345912e-05, "epoch": 1.64832285115304, "percentage": 8.24, "elapsed_time": "0:11:40", "remaining_time": "2:09:55", "throughput": 2952.15, "total_tokens": 2066960} {"current_steps": 3150, "total_steps": 38160, "loss": 0.468, "lr": 4.1260482180293504e-05, "epoch": 1.650943396226415, "percentage": 8.25, "elapsed_time": "0:11:41", "remaining_time": "2:09:53", "throughput": 2952.12, "total_tokens": 2070096} {"current_steps": 3155, "total_steps": 38160, "loss": 0.4648, "lr": 4.132599580712788e-05, "epoch": 1.6535639412997902, "percentage": 8.27, "elapsed_time": "0:11:42", "remaining_time": "2:09:52", "throughput": 2951.86, "total_tokens": 2073072} {"current_steps": 3160, "total_steps": 38160, "loss": 0.4387, "lr": 4.139150943396227e-05, "epoch": 1.6561844863731656, "percentage": 8.28, "elapsed_time": "0:11:43", "remaining_time": "2:09:50", "throughput": 2951.16, "total_tokens": 2075632} {"current_steps": 3165, "total_steps": 38160, "loss": 0.3975, "lr": 4.1457023060796646e-05, "epoch": 1.658805031446541, "percentage": 8.29, "elapsed_time": "0:11:44", "remaining_time": "2:09:48", "throughput": 2951.51, "total_tokens": 2079024} {"current_steps": 3170, "total_steps": 38160, "loss": 0.6084, "lr": 4.152253668763103e-05, "epoch": 1.6614255765199162, "percentage": 8.31, "elapsed_time": "0:11:45", "remaining_time": "2:09:46", "throughput": 2951.05, "total_tokens": 2081744} {"current_steps": 3175, "total_steps": 38160, "loss": 0.5043, "lr": 4.158805031446541e-05, "epoch": 1.6640461215932913, "percentage": 8.32, "elapsed_time": "0:11:46", "remaining_time": "2:09:44", "throughput": 2951.13, "total_tokens": 2084784} {"current_steps": 3180, "total_steps": 38160, "loss": 0.4022, "lr": 4.1653563941299795e-05, "epoch": 1.6666666666666665, "percentage": 8.33, "elapsed_time": "0:11:47", "remaining_time": "2:09:42", "throughput": 2951.2, "total_tokens": 2087984} {"current_steps": 3185, "total_steps": 38160, "loss": 0.4352, "lr": 4.171907756813417e-05, "epoch": 1.669287211740042, "percentage": 8.35, "elapsed_time": "0:11:48", "remaining_time": "2:09:40", "throughput": 2951.58, "total_tokens": 2091344} {"current_steps": 3190, "total_steps": 38160, "loss": 0.4085, "lr": 4.1784591194968555e-05, "epoch": 1.6719077568134173, "percentage": 8.36, "elapsed_time": "0:11:49", "remaining_time": "2:09:39", "throughput": 2952.61, "total_tokens": 2095312} {"current_steps": 3195, "total_steps": 38160, "loss": 0.3947, "lr": 4.185010482180294e-05, "epoch": 1.6745283018867925, "percentage": 8.37, "elapsed_time": "0:11:50", "remaining_time": "2:09:38", "throughput": 2953.0, "total_tokens": 2098832} {"current_steps": 3200, "total_steps": 38160, "loss": 0.5665, "lr": 4.1915618448637314e-05, "epoch": 1.6771488469601676, "percentage": 8.39, "elapsed_time": "0:11:51", "remaining_time": "2:09:36", "throughput": 2952.02, "total_tokens": 2101168} {"current_steps": 3205, "total_steps": 38160, "loss": 0.6716, "lr": 4.1981132075471704e-05, "epoch": 1.679769392033543, "percentage": 8.4, "elapsed_time": "0:11:52", "remaining_time": "2:09:34", "throughput": 2952.56, "total_tokens": 2104816} {"current_steps": 3210, "total_steps": 38160, "loss": 0.4636, "lr": 4.204664570230608e-05, "epoch": 1.6823899371069182, "percentage": 8.41, "elapsed_time": "0:11:53", "remaining_time": "2:09:33", "throughput": 2952.16, "total_tokens": 2107728} {"current_steps": 3215, "total_steps": 38160, "loss": 0.6681, "lr": 4.2112159329140463e-05, "epoch": 1.6850104821802936, "percentage": 8.43, "elapsed_time": "0:11:54", "remaining_time": "2:09:31", "throughput": 2952.5, "total_tokens": 2110992} {"current_steps": 3220, "total_steps": 38160, "loss": 0.4322, "lr": 4.2177672955974846e-05, "epoch": 1.6876310272536688, "percentage": 8.44, "elapsed_time": "0:11:56", "remaining_time": "2:09:29", "throughput": 2952.23, "total_tokens": 2113840} {"current_steps": 3225, "total_steps": 38160, "loss": 0.4824, "lr": 4.224318658280922e-05, "epoch": 1.690251572327044, "percentage": 8.45, "elapsed_time": "0:11:57", "remaining_time": "2:09:27", "throughput": 2952.12, "total_tokens": 2116784} {"current_steps": 3230, "total_steps": 38160, "loss": 0.6238, "lr": 4.2308700209643606e-05, "epoch": 1.6928721174004193, "percentage": 8.46, "elapsed_time": "0:11:58", "remaining_time": "2:09:25", "throughput": 2951.76, "total_tokens": 2119696} {"current_steps": 3235, "total_steps": 38160, "loss": 0.531, "lr": 4.237421383647799e-05, "epoch": 1.6954926624737947, "percentage": 8.48, "elapsed_time": "0:11:59", "remaining_time": "2:09:24", "throughput": 2951.47, "total_tokens": 2122608} {"current_steps": 3240, "total_steps": 38160, "loss": 0.4474, "lr": 4.243972746331237e-05, "epoch": 1.6981132075471699, "percentage": 8.49, "elapsed_time": "0:12:00", "remaining_time": "2:09:22", "throughput": 2951.55, "total_tokens": 2125808} {"current_steps": 3245, "total_steps": 38160, "loss": 0.4034, "lr": 4.2505241090146755e-05, "epoch": 1.700733752620545, "percentage": 8.5, "elapsed_time": "0:12:01", "remaining_time": "2:09:21", "throughput": 2952.31, "total_tokens": 2129584} {"current_steps": 3250, "total_steps": 38160, "loss": 0.4304, "lr": 4.257075471698113e-05, "epoch": 1.7033542976939202, "percentage": 8.52, "elapsed_time": "0:12:02", "remaining_time": "2:09:19", "throughput": 2951.81, "total_tokens": 2132208} {"current_steps": 3255, "total_steps": 38160, "loss": 0.4093, "lr": 4.2636268343815514e-05, "epoch": 1.7059748427672956, "percentage": 8.53, "elapsed_time": "0:12:03", "remaining_time": "2:09:17", "throughput": 2952.35, "total_tokens": 2135632} {"current_steps": 3260, "total_steps": 38160, "loss": 0.6695, "lr": 4.27017819706499e-05, "epoch": 1.708595387840671, "percentage": 8.54, "elapsed_time": "0:12:04", "remaining_time": "2:09:16", "throughput": 2953.2, "total_tokens": 2139760} {"current_steps": 3265, "total_steps": 38160, "loss": 0.4462, "lr": 4.276729559748428e-05, "epoch": 1.7112159329140462, "percentage": 8.56, "elapsed_time": "0:12:05", "remaining_time": "2:09:15", "throughput": 2953.72, "total_tokens": 2143280} {"current_steps": 3270, "total_steps": 38160, "loss": 0.4259, "lr": 4.283280922431866e-05, "epoch": 1.7138364779874213, "percentage": 8.57, "elapsed_time": "0:12:06", "remaining_time": "2:09:12", "throughput": 2952.88, "total_tokens": 2145648} {"current_steps": 3275, "total_steps": 38160, "loss": 0.4551, "lr": 4.289832285115305e-05, "epoch": 1.7164570230607965, "percentage": 8.58, "elapsed_time": "0:12:07", "remaining_time": "2:09:11", "throughput": 2953.12, "total_tokens": 2149040} {"current_steps": 3280, "total_steps": 38160, "loss": 0.5064, "lr": 4.296383647798742e-05, "epoch": 1.719077568134172, "percentage": 8.6, "elapsed_time": "0:12:08", "remaining_time": "2:09:09", "throughput": 2952.65, "total_tokens": 2151792} {"current_steps": 3285, "total_steps": 38160, "loss": 0.4366, "lr": 4.3029350104821806e-05, "epoch": 1.7216981132075473, "percentage": 8.61, "elapsed_time": "0:12:09", "remaining_time": "2:09:08", "throughput": 2953.57, "total_tokens": 2155600} {"current_steps": 3290, "total_steps": 38160, "loss": 0.3938, "lr": 4.309486373165619e-05, "epoch": 1.7243186582809225, "percentage": 8.62, "elapsed_time": "0:12:10", "remaining_time": "2:09:06", "throughput": 2954.06, "total_tokens": 2159088} {"current_steps": 3295, "total_steps": 38160, "loss": 0.3509, "lr": 4.3160377358490565e-05, "epoch": 1.7269392033542976, "percentage": 8.63, "elapsed_time": "0:12:12", "remaining_time": "2:09:05", "throughput": 2954.62, "total_tokens": 2162800} {"current_steps": 3300, "total_steps": 38160, "loss": 0.5302, "lr": 4.322589098532495e-05, "epoch": 1.7295597484276728, "percentage": 8.65, "elapsed_time": "0:12:13", "remaining_time": "2:09:03", "throughput": 2954.51, "total_tokens": 2165872} {"current_steps": 3305, "total_steps": 38160, "loss": 0.5392, "lr": 4.329140461215933e-05, "epoch": 1.7321802935010482, "percentage": 8.66, "elapsed_time": "0:12:14", "remaining_time": "2:09:02", "throughput": 2955.15, "total_tokens": 2169456} {"current_steps": 3310, "total_steps": 38160, "loss": 0.4633, "lr": 4.335691823899371e-05, "epoch": 1.7348008385744236, "percentage": 8.67, "elapsed_time": "0:12:15", "remaining_time": "2:09:00", "throughput": 2954.7, "total_tokens": 2172368} {"current_steps": 3315, "total_steps": 38160, "loss": 0.5658, "lr": 4.34224318658281e-05, "epoch": 1.7374213836477987, "percentage": 8.69, "elapsed_time": "0:12:16", "remaining_time": "2:08:58", "throughput": 2954.88, "total_tokens": 2175504} {"current_steps": 3320, "total_steps": 38160, "loss": 0.476, "lr": 4.3487945492662474e-05, "epoch": 1.740041928721174, "percentage": 8.7, "elapsed_time": "0:12:17", "remaining_time": "2:08:58", "throughput": 2955.65, "total_tokens": 2179440} {"current_steps": 3325, "total_steps": 38160, "loss": 0.5656, "lr": 4.355345911949686e-05, "epoch": 1.7426624737945493, "percentage": 8.71, "elapsed_time": "0:12:18", "remaining_time": "2:08:55", "throughput": 2954.93, "total_tokens": 2181904} {"current_steps": 3330, "total_steps": 38160, "loss": 0.3872, "lr": 4.361897274633124e-05, "epoch": 1.7452830188679245, "percentage": 8.73, "elapsed_time": "0:12:19", "remaining_time": "2:08:54", "throughput": 2954.74, "total_tokens": 2184816} {"current_steps": 3335, "total_steps": 38160, "loss": 0.5502, "lr": 4.368448637316562e-05, "epoch": 1.7479035639412999, "percentage": 8.74, "elapsed_time": "0:12:20", "remaining_time": "2:08:52", "throughput": 2954.8, "total_tokens": 2187920} {"current_steps": 3340, "total_steps": 38160, "loss": 0.4816, "lr": 4.375e-05, "epoch": 1.750524109014675, "percentage": 8.75, "elapsed_time": "0:12:21", "remaining_time": "2:08:50", "throughput": 2955.12, "total_tokens": 2191216} {"current_steps": 3345, "total_steps": 38160, "loss": 0.4202, "lr": 4.381551362683438e-05, "epoch": 1.7531446540880502, "percentage": 8.77, "elapsed_time": "0:12:22", "remaining_time": "2:08:48", "throughput": 2954.39, "total_tokens": 2193744} {"current_steps": 3350, "total_steps": 38160, "loss": 0.4245, "lr": 4.3881027253668766e-05, "epoch": 1.7557651991614256, "percentage": 8.78, "elapsed_time": "0:12:23", "remaining_time": "2:08:46", "throughput": 2953.9, "total_tokens": 2196368} {"current_steps": 3355, "total_steps": 38160, "loss": 0.3615, "lr": 4.394654088050314e-05, "epoch": 1.758385744234801, "percentage": 8.79, "elapsed_time": "0:12:24", "remaining_time": "2:08:44", "throughput": 2954.04, "total_tokens": 2199632} {"current_steps": 3360, "total_steps": 38160, "loss": 0.4848, "lr": 4.401205450733753e-05, "epoch": 1.7610062893081762, "percentage": 8.81, "elapsed_time": "0:12:25", "remaining_time": "2:08:43", "throughput": 2953.76, "total_tokens": 2202704} {"current_steps": 3365, "total_steps": 38160, "loss": 0.6286, "lr": 4.407756813417191e-05, "epoch": 1.7636268343815513, "percentage": 8.82, "elapsed_time": "0:12:26", "remaining_time": "2:08:42", "throughput": 2953.22, "total_tokens": 2205616} {"current_steps": 3370, "total_steps": 38160, "loss": 0.416, "lr": 4.414308176100629e-05, "epoch": 1.7662473794549265, "percentage": 8.83, "elapsed_time": "0:12:27", "remaining_time": "2:08:41", "throughput": 2953.47, "total_tokens": 2209008} {"current_steps": 3375, "total_steps": 38160, "loss": 0.4054, "lr": 4.4208595387840674e-05, "epoch": 1.7688679245283019, "percentage": 8.84, "elapsed_time": "0:12:29", "remaining_time": "2:08:39", "throughput": 2953.02, "total_tokens": 2211824} {"current_steps": 3380, "total_steps": 38160, "loss": 0.453, "lr": 4.427410901467505e-05, "epoch": 1.7714884696016773, "percentage": 8.86, "elapsed_time": "0:12:30", "remaining_time": "2:08:38", "throughput": 2953.77, "total_tokens": 2215632} {"current_steps": 3385, "total_steps": 38160, "loss": 0.4194, "lr": 4.433962264150944e-05, "epoch": 1.7741090146750524, "percentage": 8.87, "elapsed_time": "0:12:31", "remaining_time": "2:08:37", "throughput": 2953.21, "total_tokens": 2218512} {"current_steps": 3390, "total_steps": 38160, "loss": 0.3741, "lr": 4.440513626834382e-05, "epoch": 1.7767295597484276, "percentage": 8.88, "elapsed_time": "0:12:32", "remaining_time": "2:08:36", "throughput": 2953.25, "total_tokens": 2221776} {"current_steps": 3395, "total_steps": 38160, "loss": 0.3794, "lr": 4.44706498951782e-05, "epoch": 1.7793501048218028, "percentage": 8.9, "elapsed_time": "0:12:33", "remaining_time": "2:08:34", "throughput": 2953.16, "total_tokens": 2224784} {"current_steps": 3400, "total_steps": 38160, "loss": 0.46, "lr": 4.453616352201258e-05, "epoch": 1.7819706498951782, "percentage": 8.91, "elapsed_time": "0:12:34", "remaining_time": "2:08:32", "throughput": 2952.52, "total_tokens": 2227408} {"current_steps": 3405, "total_steps": 38160, "loss": 0.4317, "lr": 4.460167714884696e-05, "epoch": 1.7845911949685536, "percentage": 8.92, "elapsed_time": "0:12:35", "remaining_time": "2:08:31", "throughput": 2951.74, "total_tokens": 2230064} {"current_steps": 3410, "total_steps": 38160, "loss": 0.3442, "lr": 4.466719077568134e-05, "epoch": 1.7872117400419287, "percentage": 8.94, "elapsed_time": "0:12:36", "remaining_time": "2:08:31", "throughput": 2952.69, "total_tokens": 2234288} {"current_steps": 3415, "total_steps": 38160, "loss": 0.3477, "lr": 4.4732704402515725e-05, "epoch": 1.789832285115304, "percentage": 8.95, "elapsed_time": "0:12:37", "remaining_time": "2:08:29", "throughput": 2952.15, "total_tokens": 2237072} {"current_steps": 3420, "total_steps": 38160, "loss": 0.3449, "lr": 4.479821802935011e-05, "epoch": 1.7924528301886793, "percentage": 8.96, "elapsed_time": "0:12:38", "remaining_time": "2:08:28", "throughput": 2951.62, "total_tokens": 2240016} {"current_steps": 3425, "total_steps": 38160, "loss": 0.433, "lr": 4.4863731656184485e-05, "epoch": 1.7950733752620545, "percentage": 8.98, "elapsed_time": "0:12:39", "remaining_time": "2:08:27", "throughput": 2951.22, "total_tokens": 2242800} {"current_steps": 3430, "total_steps": 38160, "loss": 0.4742, "lr": 4.4929245283018875e-05, "epoch": 1.7976939203354299, "percentage": 8.99, "elapsed_time": "0:12:41", "remaining_time": "2:08:25", "throughput": 2950.89, "total_tokens": 2245680} {"current_steps": 3435, "total_steps": 38160, "loss": 0.4996, "lr": 4.499475890985325e-05, "epoch": 1.800314465408805, "percentage": 9.0, "elapsed_time": "0:12:42", "remaining_time": "2:08:23", "throughput": 2950.19, "total_tokens": 2248272} {"current_steps": 3440, "total_steps": 38160, "loss": 0.3095, "lr": 4.5060272536687634e-05, "epoch": 1.8029350104821802, "percentage": 9.01, "elapsed_time": "0:12:43", "remaining_time": "2:08:23", "throughput": 2949.86, "total_tokens": 2251376} {"current_steps": 3445, "total_steps": 38160, "loss": 0.5099, "lr": 4.512578616352202e-05, "epoch": 1.8055555555555556, "percentage": 9.03, "elapsed_time": "0:12:44", "remaining_time": "2:08:21", "throughput": 2949.56, "total_tokens": 2254256} {"current_steps": 3450, "total_steps": 38160, "loss": 0.5393, "lr": 4.519129979035639e-05, "epoch": 1.808176100628931, "percentage": 9.04, "elapsed_time": "0:12:45", "remaining_time": "2:08:19", "throughput": 2949.26, "total_tokens": 2257104} {"current_steps": 3455, "total_steps": 38160, "loss": 0.4933, "lr": 4.525681341719078e-05, "epoch": 1.8107966457023061, "percentage": 9.05, "elapsed_time": "0:12:46", "remaining_time": "2:08:17", "throughput": 2948.94, "total_tokens": 2259920} {"current_steps": 3460, "total_steps": 38160, "loss": 0.3662, "lr": 4.532232704402516e-05, "epoch": 1.8134171907756813, "percentage": 9.07, "elapsed_time": "0:12:47", "remaining_time": "2:08:16", "throughput": 2948.5, "total_tokens": 2262736} {"current_steps": 3465, "total_steps": 38160, "loss": 0.4145, "lr": 4.5387840670859536e-05, "epoch": 1.8160377358490565, "percentage": 9.08, "elapsed_time": "0:12:48", "remaining_time": "2:08:15", "throughput": 2949.34, "total_tokens": 2266864} {"current_steps": 3470, "total_steps": 38160, "loss": 0.6449, "lr": 4.5453354297693926e-05, "epoch": 1.8186582809224319, "percentage": 9.09, "elapsed_time": "0:12:49", "remaining_time": "2:08:14", "throughput": 2948.9, "total_tokens": 2269584} {"current_steps": 3475, "total_steps": 38160, "loss": 0.4216, "lr": 4.55188679245283e-05, "epoch": 1.8212788259958073, "percentage": 9.11, "elapsed_time": "0:12:50", "remaining_time": "2:08:12", "throughput": 2948.97, "total_tokens": 2272720} {"current_steps": 3480, "total_steps": 38160, "loss": 0.5554, "lr": 4.5584381551362685e-05, "epoch": 1.8238993710691824, "percentage": 9.12, "elapsed_time": "0:12:51", "remaining_time": "2:08:11", "throughput": 2950.08, "total_tokens": 2276880} {"current_steps": 3485, "total_steps": 38160, "loss": 0.4312, "lr": 4.564989517819707e-05, "epoch": 1.8265199161425576, "percentage": 9.13, "elapsed_time": "0:12:52", "remaining_time": "2:08:09", "throughput": 2950.05, "total_tokens": 2280016} {"current_steps": 3490, "total_steps": 38160, "loss": 0.4464, "lr": 4.571540880503145e-05, "epoch": 1.8291404612159328, "percentage": 9.15, "elapsed_time": "0:12:53", "remaining_time": "2:08:08", "throughput": 2949.3, "total_tokens": 2282640} {"current_steps": 3495, "total_steps": 38160, "loss": 0.4123, "lr": 4.578092243186583e-05, "epoch": 1.8317610062893082, "percentage": 9.16, "elapsed_time": "0:12:55", "remaining_time": "2:08:07", "throughput": 2949.52, "total_tokens": 2286032} {"current_steps": 3500, "total_steps": 38160, "loss": 0.5222, "lr": 4.584643605870021e-05, "epoch": 1.8343815513626835, "percentage": 9.17, "elapsed_time": "0:12:56", "remaining_time": "2:08:05", "throughput": 2949.59, "total_tokens": 2289136} {"current_steps": 3505, "total_steps": 38160, "loss": 0.3612, "lr": 4.5911949685534594e-05, "epoch": 1.8370020964360587, "percentage": 9.19, "elapsed_time": "0:12:57", "remaining_time": "2:08:04", "throughput": 2950.34, "total_tokens": 2292944} {"current_steps": 3510, "total_steps": 38160, "loss": 0.4369, "lr": 4.5977463312368977e-05, "epoch": 1.8396226415094339, "percentage": 9.2, "elapsed_time": "0:12:58", "remaining_time": "2:08:02", "throughput": 2950.58, "total_tokens": 2296240} {"current_steps": 3515, "total_steps": 38160, "loss": 0.4386, "lr": 4.604297693920336e-05, "epoch": 1.8422431865828093, "percentage": 9.21, "elapsed_time": "0:12:59", "remaining_time": "2:08:01", "throughput": 2950.11, "total_tokens": 2299088} {"current_steps": 3520, "total_steps": 38160, "loss": 0.4892, "lr": 4.6108490566037736e-05, "epoch": 1.8448637316561844, "percentage": 9.22, "elapsed_time": "0:13:00", "remaining_time": "2:08:00", "throughput": 2950.43, "total_tokens": 2302736} {"current_steps": 3525, "total_steps": 38160, "loss": 0.5232, "lr": 4.617400419287212e-05, "epoch": 1.8474842767295598, "percentage": 9.24, "elapsed_time": "0:13:01", "remaining_time": "2:08:00", "throughput": 2950.85, "total_tokens": 2306640} {"current_steps": 3530, "total_steps": 38160, "loss": 0.5344, "lr": 4.62395178197065e-05, "epoch": 1.850104821802935, "percentage": 9.25, "elapsed_time": "0:13:02", "remaining_time": "2:07:58", "throughput": 2951.05, "total_tokens": 2309840} {"current_steps": 3535, "total_steps": 38160, "loss": 0.4911, "lr": 4.630503144654088e-05, "epoch": 1.8527253668763102, "percentage": 9.26, "elapsed_time": "0:13:03", "remaining_time": "2:07:57", "throughput": 2949.81, "total_tokens": 2312208} {"current_steps": 3540, "total_steps": 38160, "loss": 0.574, "lr": 4.637054507337527e-05, "epoch": 1.8553459119496856, "percentage": 9.28, "elapsed_time": "0:13:04", "remaining_time": "2:07:55", "throughput": 2949.62, "total_tokens": 2315088} {"current_steps": 3545, "total_steps": 38160, "loss": 0.4905, "lr": 4.6436058700209645e-05, "epoch": 1.857966457023061, "percentage": 9.29, "elapsed_time": "0:13:05", "remaining_time": "2:07:54", "throughput": 2949.59, "total_tokens": 2318224} {"current_steps": 3550, "total_steps": 38160, "loss": 0.3959, "lr": 4.650157232704403e-05, "epoch": 1.8605870020964361, "percentage": 9.3, "elapsed_time": "0:13:07", "remaining_time": "2:07:54", "throughput": 2950.68, "total_tokens": 2322800} {"current_steps": 3555, "total_steps": 38160, "loss": 0.3209, "lr": 4.656708595387841e-05, "epoch": 1.8632075471698113, "percentage": 9.32, "elapsed_time": "0:13:08", "remaining_time": "2:07:59", "throughput": 2952.05, "total_tokens": 2329008} {"current_steps": 3560, "total_steps": 38160, "loss": 0.6168, "lr": 4.663259958071279e-05, "epoch": 1.8658280922431865, "percentage": 9.33, "elapsed_time": "0:13:10", "remaining_time": "2:07:58", "throughput": 2950.95, "total_tokens": 2331344} {"current_steps": 3565, "total_steps": 38160, "loss": 0.4587, "lr": 4.669811320754717e-05, "epoch": 1.8684486373165619, "percentage": 9.34, "elapsed_time": "0:13:11", "remaining_time": "2:07:57", "throughput": 2950.58, "total_tokens": 2334352} {"current_steps": 3570, "total_steps": 38160, "loss": 0.5249, "lr": 4.676362683438155e-05, "epoch": 1.8710691823899372, "percentage": 9.36, "elapsed_time": "0:13:12", "remaining_time": "2:07:56", "throughput": 2951.67, "total_tokens": 2338512} {"current_steps": 3575, "total_steps": 38160, "loss": 0.5512, "lr": 4.6829140461215936e-05, "epoch": 1.8736897274633124, "percentage": 9.37, "elapsed_time": "0:13:13", "remaining_time": "2:07:54", "throughput": 2952.44, "total_tokens": 2342224} {"current_steps": 3580, "total_steps": 38160, "loss": 0.4382, "lr": 4.689465408805032e-05, "epoch": 1.8763102725366876, "percentage": 9.38, "elapsed_time": "0:13:14", "remaining_time": "2:07:53", "throughput": 2952.74, "total_tokens": 2345808} {"current_steps": 3585, "total_steps": 38160, "loss": 0.5077, "lr": 4.69601677148847e-05, "epoch": 1.8789308176100628, "percentage": 9.39, "elapsed_time": "0:13:15", "remaining_time": "2:07:51", "throughput": 2952.36, "total_tokens": 2348560} {"current_steps": 3590, "total_steps": 38160, "loss": 0.3608, "lr": 4.702568134171908e-05, "epoch": 1.8815513626834381, "percentage": 9.41, "elapsed_time": "0:13:16", "remaining_time": "2:07:50", "throughput": 2952.64, "total_tokens": 2351824} {"current_steps": 3595, "total_steps": 38160, "loss": 0.3704, "lr": 4.709119496855346e-05, "epoch": 1.8841719077568135, "percentage": 9.42, "elapsed_time": "0:13:17", "remaining_time": "2:07:49", "throughput": 2953.35, "total_tokens": 2355696} {"current_steps": 3600, "total_steps": 38160, "loss": 0.3994, "lr": 4.7156708595387845e-05, "epoch": 1.8867924528301887, "percentage": 9.43, "elapsed_time": "0:13:18", "remaining_time": "2:07:47", "throughput": 2952.87, "total_tokens": 2358352} {"current_steps": 3605, "total_steps": 38160, "loss": 0.3964, "lr": 4.722222222222222e-05, "epoch": 1.8894129979035639, "percentage": 9.45, "elapsed_time": "0:13:19", "remaining_time": "2:07:45", "throughput": 2953.28, "total_tokens": 2361776} {"current_steps": 3610, "total_steps": 38160, "loss": 0.5221, "lr": 4.728773584905661e-05, "epoch": 1.892033542976939, "percentage": 9.46, "elapsed_time": "0:13:20", "remaining_time": "2:07:43", "throughput": 2953.85, "total_tokens": 2365264} {"current_steps": 3615, "total_steps": 38160, "loss": 0.6779, "lr": 4.735324947589099e-05, "epoch": 1.8946540880503144, "percentage": 9.47, "elapsed_time": "0:13:21", "remaining_time": "2:07:41", "throughput": 2953.53, "total_tokens": 2368080} {"current_steps": 3620, "total_steps": 38160, "loss": 0.4686, "lr": 4.7418763102725364e-05, "epoch": 1.8972746331236898, "percentage": 9.49, "elapsed_time": "0:13:22", "remaining_time": "2:07:41", "throughput": 2953.83, "total_tokens": 2371696} {"current_steps": 3625, "total_steps": 38160, "loss": 0.4475, "lr": 4.7484276729559753e-05, "epoch": 1.899895178197065, "percentage": 9.5, "elapsed_time": "0:13:23", "remaining_time": "2:07:39", "throughput": 2953.08, "total_tokens": 2374160} {"current_steps": 3630, "total_steps": 38160, "loss": 0.3802, "lr": 4.754979035639413e-05, "epoch": 1.9025157232704402, "percentage": 9.51, "elapsed_time": "0:13:25", "remaining_time": "2:07:37", "throughput": 2952.32, "total_tokens": 2376656} {"current_steps": 3635, "total_steps": 38160, "loss": 0.4462, "lr": 4.761530398322851e-05, "epoch": 1.9051362683438156, "percentage": 9.53, "elapsed_time": "0:13:26", "remaining_time": "2:07:36", "throughput": 2952.38, "total_tokens": 2379856} {"current_steps": 3640, "total_steps": 38160, "loss": 0.5343, "lr": 4.7680817610062896e-05, "epoch": 1.9077568134171907, "percentage": 9.54, "elapsed_time": "0:13:27", "remaining_time": "2:07:34", "throughput": 2952.01, "total_tokens": 2382736} {"current_steps": 3645, "total_steps": 38160, "loss": 0.4241, "lr": 4.774633123689728e-05, "epoch": 1.9103773584905661, "percentage": 9.55, "elapsed_time": "0:13:28", "remaining_time": "2:07:34", "throughput": 2952.4, "total_tokens": 2386672} {"current_steps": 3650, "total_steps": 38160, "loss": 0.3796, "lr": 4.7811844863731655e-05, "epoch": 1.9129979035639413, "percentage": 9.56, "elapsed_time": "0:13:29", "remaining_time": "2:07:33", "throughput": 2951.81, "total_tokens": 2389296} {"current_steps": 3655, "total_steps": 38160, "loss": 0.544, "lr": 4.787735849056604e-05, "epoch": 1.9156184486373165, "percentage": 9.58, "elapsed_time": "0:13:30", "remaining_time": "2:07:31", "throughput": 2951.53, "total_tokens": 2392080} {"current_steps": 3660, "total_steps": 38160, "loss": 0.387, "lr": 4.794287211740042e-05, "epoch": 1.9182389937106918, "percentage": 9.59, "elapsed_time": "0:13:31", "remaining_time": "2:07:30", "throughput": 2951.96, "total_tokens": 2395952} {"current_steps": 3665, "total_steps": 38160, "loss": 0.3813, "lr": 4.8008385744234804e-05, "epoch": 1.9208595387840672, "percentage": 9.6, "elapsed_time": "0:13:32", "remaining_time": "2:07:28", "throughput": 2951.44, "total_tokens": 2398512} {"current_steps": 3670, "total_steps": 38160, "loss": 0.524, "lr": 4.807389937106919e-05, "epoch": 1.9234800838574424, "percentage": 9.62, "elapsed_time": "0:13:33", "remaining_time": "2:07:27", "throughput": 2951.8, "total_tokens": 2401904} {"current_steps": 3675, "total_steps": 38160, "loss": 0.4899, "lr": 4.8139412997903564e-05, "epoch": 1.9261006289308176, "percentage": 9.63, "elapsed_time": "0:13:34", "remaining_time": "2:07:26", "throughput": 2951.97, "total_tokens": 2405584} {"current_steps": 3680, "total_steps": 38160, "loss": 0.5407, "lr": 4.8204926624737954e-05, "epoch": 1.9287211740041927, "percentage": 9.64, "elapsed_time": "0:13:36", "remaining_time": "2:07:26", "throughput": 2952.78, "total_tokens": 2409712} {"current_steps": 3685, "total_steps": 38160, "loss": 0.6036, "lr": 4.827044025157233e-05, "epoch": 1.9313417190775681, "percentage": 9.66, "elapsed_time": "0:13:37", "remaining_time": "2:07:25", "throughput": 2951.95, "total_tokens": 2412240} {"current_steps": 3690, "total_steps": 38160, "loss": 0.3927, "lr": 4.8335953878406706e-05, "epoch": 1.9339622641509435, "percentage": 9.67, "elapsed_time": "0:13:38", "remaining_time": "2:07:23", "throughput": 2951.49, "total_tokens": 2415056} {"current_steps": 3695, "total_steps": 38160, "loss": 0.4418, "lr": 4.8401467505241096e-05, "epoch": 1.9365828092243187, "percentage": 9.68, "elapsed_time": "0:13:39", "remaining_time": "2:07:22", "throughput": 2952.51, "total_tokens": 2419184} {"current_steps": 3700, "total_steps": 38160, "loss": 0.503, "lr": 4.846698113207547e-05, "epoch": 1.9392033542976939, "percentage": 9.7, "elapsed_time": "0:13:40", "remaining_time": "2:07:21", "throughput": 2952.64, "total_tokens": 2422512} {"current_steps": 3705, "total_steps": 38160, "loss": 0.4436, "lr": 4.8532494758909855e-05, "epoch": 1.941823899371069, "percentage": 9.71, "elapsed_time": "0:13:41", "remaining_time": "2:07:20", "throughput": 2952.71, "total_tokens": 2425936} {"current_steps": 3710, "total_steps": 38160, "loss": 0.5833, "lr": 4.859800838574424e-05, "epoch": 1.9444444444444444, "percentage": 9.72, "elapsed_time": "0:13:42", "remaining_time": "2:07:18", "throughput": 2952.55, "total_tokens": 2428944} {"current_steps": 3715, "total_steps": 38160, "loss": 0.365, "lr": 4.8663522012578615e-05, "epoch": 1.9470649895178198, "percentage": 9.74, "elapsed_time": "0:13:43", "remaining_time": "2:07:17", "throughput": 2952.54, "total_tokens": 2432080} {"current_steps": 3720, "total_steps": 38160, "loss": 0.4142, "lr": 4.8729035639413e-05, "epoch": 1.949685534591195, "percentage": 9.75, "elapsed_time": "0:13:44", "remaining_time": "2:07:15", "throughput": 2952.15, "total_tokens": 2434864} {"current_steps": 3725, "total_steps": 38160, "loss": 0.4185, "lr": 4.879454926624738e-05, "epoch": 1.9523060796645701, "percentage": 9.76, "elapsed_time": "0:13:45", "remaining_time": "2:07:14", "throughput": 2951.0, "total_tokens": 2437104} {"current_steps": 3730, "total_steps": 38160, "loss": 0.6277, "lr": 4.8860062893081764e-05, "epoch": 1.9549266247379455, "percentage": 9.77, "elapsed_time": "0:13:46", "remaining_time": "2:07:12", "throughput": 2950.5, "total_tokens": 2439792} {"current_steps": 3735, "total_steps": 38160, "loss": 0.6071, "lr": 4.892557651991615e-05, "epoch": 1.9575471698113207, "percentage": 9.79, "elapsed_time": "0:13:48", "remaining_time": "2:07:11", "throughput": 2949.6, "total_tokens": 2442320} {"current_steps": 3740, "total_steps": 38160, "loss": 0.3889, "lr": 4.899109014675053e-05, "epoch": 1.960167714884696, "percentage": 9.8, "elapsed_time": "0:13:49", "remaining_time": "2:07:10", "throughput": 2949.17, "total_tokens": 2445136} {"current_steps": 3745, "total_steps": 38160, "loss": 0.44, "lr": 4.9056603773584906e-05, "epoch": 1.9627882599580713, "percentage": 9.81, "elapsed_time": "0:13:50", "remaining_time": "2:07:08", "throughput": 2948.89, "total_tokens": 2448080} {"current_steps": 3750, "total_steps": 38160, "loss": 0.4922, "lr": 4.912211740041929e-05, "epoch": 1.9654088050314464, "percentage": 9.83, "elapsed_time": "0:13:51", "remaining_time": "2:07:08", "throughput": 2948.78, "total_tokens": 2451376} {"current_steps": 3755, "total_steps": 38160, "loss": 0.5474, "lr": 4.918763102725367e-05, "epoch": 1.9680293501048218, "percentage": 9.84, "elapsed_time": "0:13:52", "remaining_time": "2:07:07", "throughput": 2948.8, "total_tokens": 2454672} {"current_steps": 3760, "total_steps": 38160, "loss": 0.4184, "lr": 4.925314465408805e-05, "epoch": 1.9706498951781972, "percentage": 9.85, "elapsed_time": "0:13:53", "remaining_time": "2:07:06", "throughput": 2948.48, "total_tokens": 2457712} {"current_steps": 3765, "total_steps": 38160, "loss": 0.447, "lr": 4.931865828092244e-05, "epoch": 1.9732704402515724, "percentage": 9.87, "elapsed_time": "0:13:54", "remaining_time": "2:07:05", "throughput": 2949.39, "total_tokens": 2461936} {"current_steps": 3770, "total_steps": 38160, "loss": 0.3721, "lr": 4.9384171907756815e-05, "epoch": 1.9758909853249476, "percentage": 9.88, "elapsed_time": "0:13:55", "remaining_time": "2:07:03", "throughput": 2949.69, "total_tokens": 2465296} {"current_steps": 3775, "total_steps": 38160, "loss": 0.472, "lr": 4.944968553459119e-05, "epoch": 1.9785115303983227, "percentage": 9.89, "elapsed_time": "0:13:56", "remaining_time": "2:07:03", "throughput": 2950.95, "total_tokens": 2469872} {"current_steps": 3780, "total_steps": 38160, "loss": 0.3511, "lr": 4.951519916142558e-05, "epoch": 1.9811320754716981, "percentage": 9.91, "elapsed_time": "0:13:58", "remaining_time": "2:07:03", "throughput": 2951.57, "total_tokens": 2473840} {"current_steps": 3785, "total_steps": 38160, "loss": 0.464, "lr": 4.958071278825996e-05, "epoch": 1.9837526205450735, "percentage": 9.92, "elapsed_time": "0:13:59", "remaining_time": "2:07:01", "throughput": 2951.59, "total_tokens": 2476944} {"current_steps": 3790, "total_steps": 38160, "loss": 0.4406, "lr": 4.964622641509434e-05, "epoch": 1.9863731656184487, "percentage": 9.93, "elapsed_time": "0:14:07", "remaining_time": "2:08:05", "throughput": 2926.0, "total_tokens": 2479792} {"current_steps": 3795, "total_steps": 38160, "loss": 0.5654, "lr": 4.9711740041928724e-05, "epoch": 1.9889937106918238, "percentage": 9.94, "elapsed_time": "0:14:08", "remaining_time": "2:08:06", "throughput": 2926.77, "total_tokens": 2484464} {"current_steps": 3800, "total_steps": 38160, "loss": 0.4222, "lr": 4.977725366876311e-05, "epoch": 1.991614255765199, "percentage": 9.96, "elapsed_time": "0:14:09", "remaining_time": "2:08:04", "throughput": 2926.56, "total_tokens": 2487312} {"current_steps": 3805, "total_steps": 38160, "loss": 0.4526, "lr": 4.984276729559749e-05, "epoch": 1.9942348008385744, "percentage": 9.97, "elapsed_time": "0:14:10", "remaining_time": "2:08:03", "throughput": 2926.41, "total_tokens": 2490288} {"current_steps": 3810, "total_steps": 38160, "loss": 0.4912, "lr": 4.9908280922431866e-05, "epoch": 1.9968553459119498, "percentage": 9.98, "elapsed_time": "0:14:12", "remaining_time": "2:08:02", "throughput": 2927.02, "total_tokens": 2494128} {"current_steps": 3815, "total_steps": 38160, "loss": 0.4289, "lr": 4.997379454926625e-05, "epoch": 1.999475890985325, "percentage": 10.0, "elapsed_time": "0:14:13", "remaining_time": "2:08:00", "throughput": 2926.68, "total_tokens": 2496848} {"current_steps": 3816, "total_steps": 38160, "eval_loss": 0.47038066387176514, "epoch": 2.0, "percentage": 10.0, "elapsed_time": "0:14:28", "remaining_time": "2:10:17", "throughput": 2874.55, "total_tokens": 2497016} {"current_steps": 3820, "total_steps": 38160, "loss": 0.3389, "lr": 4.999999905865133e-05, "epoch": 2.0020964360587, "percentage": 10.01, "elapsed_time": "0:14:33", "remaining_time": "2:10:48", "throughput": 2862.78, "total_tokens": 2499256} {"current_steps": 3825, "total_steps": 38160, "loss": 0.4151, "lr": 4.999999330596526e-05, "epoch": 2.0047169811320753, "percentage": 10.02, "elapsed_time": "0:14:34", "remaining_time": "2:10:46", "throughput": 2862.44, "total_tokens": 2502200} {"current_steps": 3830, "total_steps": 38160, "loss": 0.5725, "lr": 4.9999982323565806e-05, "epoch": 2.007337526205451, "percentage": 10.04, "elapsed_time": "0:14:35", "remaining_time": "2:10:44", "throughput": 2862.24, "total_tokens": 2505080} {"current_steps": 3835, "total_steps": 38160, "loss": 0.4507, "lr": 4.999996611145527e-05, "epoch": 2.009958071278826, "percentage": 10.05, "elapsed_time": "0:14:36", "remaining_time": "2:10:43", "throughput": 2862.27, "total_tokens": 2508216} {"current_steps": 3840, "total_steps": 38160, "loss": 0.3412, "lr": 4.9999944669637024e-05, "epoch": 2.0125786163522013, "percentage": 10.06, "elapsed_time": "0:14:37", "remaining_time": "2:10:41", "throughput": 2862.14, "total_tokens": 2511128} {"current_steps": 3845, "total_steps": 38160, "loss": 0.4649, "lr": 4.999991799811557e-05, "epoch": 2.0151991614255764, "percentage": 10.08, "elapsed_time": "0:14:38", "remaining_time": "2:10:40", "throughput": 2862.6, "total_tokens": 2514776} {"current_steps": 3850, "total_steps": 38160, "loss": 0.5657, "lr": 4.99998860968965e-05, "epoch": 2.0178197064989516, "percentage": 10.09, "elapsed_time": "0:14:39", "remaining_time": "2:10:38", "throughput": 2862.16, "total_tokens": 2517528} {"current_steps": 3855, "total_steps": 38160, "loss": 0.4971, "lr": 4.999984896598646e-05, "epoch": 2.020440251572327, "percentage": 10.1, "elapsed_time": "0:14:41", "remaining_time": "2:10:40", "throughput": 2863.78, "total_tokens": 2523032} {"current_steps": 3860, "total_steps": 38160, "loss": 0.4144, "lr": 4.999980660539323e-05, "epoch": 2.0230607966457024, "percentage": 10.12, "elapsed_time": "0:14:42", "remaining_time": "2:10:38", "throughput": 2863.95, "total_tokens": 2526200} {"current_steps": 3865, "total_steps": 38160, "loss": 0.5622, "lr": 4.999975901512567e-05, "epoch": 2.0256813417190775, "percentage": 10.13, "elapsed_time": "0:14:43", "remaining_time": "2:10:43", "throughput": 2865.37, "total_tokens": 2532760} {"current_steps": 3870, "total_steps": 38160, "loss": 0.3706, "lr": 4.999970619519374e-05, "epoch": 2.0283018867924527, "percentage": 10.14, "elapsed_time": "0:14:44", "remaining_time": "2:10:41", "throughput": 2865.18, "total_tokens": 2535640} {"current_steps": 3875, "total_steps": 38160, "loss": 0.4037, "lr": 4.999964814560849e-05, "epoch": 2.030922431865828, "percentage": 10.15, "elapsed_time": "0:14:46", "remaining_time": "2:10:40", "throughput": 2865.66, "total_tokens": 2539288} {"current_steps": 3880, "total_steps": 38160, "loss": 0.4996, "lr": 4.999958486638205e-05, "epoch": 2.0335429769392035, "percentage": 10.17, "elapsed_time": "0:14:47", "remaining_time": "2:10:38", "throughput": 2865.1, "total_tokens": 2541880} {"current_steps": 3885, "total_steps": 38160, "loss": 0.4264, "lr": 4.999951635752767e-05, "epoch": 2.0361635220125787, "percentage": 10.18, "elapsed_time": "0:14:48", "remaining_time": "2:10:36", "throughput": 2865.3, "total_tokens": 2545080} {"current_steps": 3890, "total_steps": 38160, "loss": 0.3304, "lr": 4.999944261905968e-05, "epoch": 2.038784067085954, "percentage": 10.19, "elapsed_time": "0:14:49", "remaining_time": "2:10:34", "throughput": 2865.47, "total_tokens": 2548376} {"current_steps": 3895, "total_steps": 38160, "loss": 0.3764, "lr": 4.99993636509935e-05, "epoch": 2.041404612159329, "percentage": 10.21, "elapsed_time": "0:14:50", "remaining_time": "2:10:33", "throughput": 2864.34, "total_tokens": 2550616} {"current_steps": 3900, "total_steps": 38160, "loss": 0.5286, "lr": 4.999927945334565e-05, "epoch": 2.0440251572327046, "percentage": 10.22, "elapsed_time": "0:14:51", "remaining_time": "2:10:32", "throughput": 2865.54, "total_tokens": 2555000} {"current_steps": 3905, "total_steps": 38160, "loss": 0.4319, "lr": 4.9999190026133745e-05, "epoch": 2.04664570230608, "percentage": 10.23, "elapsed_time": "0:14:52", "remaining_time": "2:10:30", "throughput": 2865.78, "total_tokens": 2558328} {"current_steps": 3910, "total_steps": 38160, "loss": 0.5278, "lr": 4.9999095369376506e-05, "epoch": 2.049266247379455, "percentage": 10.25, "elapsed_time": "0:14:53", "remaining_time": "2:10:29", "throughput": 2866.06, "total_tokens": 2561592} {"current_steps": 3915, "total_steps": 38160, "loss": 0.3109, "lr": 4.99989954830937e-05, "epoch": 2.05188679245283, "percentage": 10.26, "elapsed_time": "0:14:54", "remaining_time": "2:10:26", "throughput": 2866.05, "total_tokens": 2564472} {"current_steps": 3920, "total_steps": 38160, "loss": 0.4202, "lr": 4.9998890367306255e-05, "epoch": 2.0545073375262053, "percentage": 10.27, "elapsed_time": "0:14:55", "remaining_time": "2:10:24", "throughput": 2866.0, "total_tokens": 2567352} {"current_steps": 3925, "total_steps": 38160, "loss": 0.3268, "lr": 4.999878002203614e-05, "epoch": 2.057127882599581, "percentage": 10.29, "elapsed_time": "0:14:56", "remaining_time": "2:10:23", "throughput": 2866.95, "total_tokens": 2571448} {"current_steps": 3930, "total_steps": 38160, "loss": 0.3625, "lr": 4.999866444730645e-05, "epoch": 2.059748427672956, "percentage": 10.3, "elapsed_time": "0:14:57", "remaining_time": "2:10:20", "throughput": 2866.88, "total_tokens": 2574264} {"current_steps": 3935, "total_steps": 38160, "loss": 0.5308, "lr": 4.999854364314136e-05, "epoch": 2.0623689727463312, "percentage": 10.31, "elapsed_time": "0:14:58", "remaining_time": "2:10:18", "throughput": 2867.28, "total_tokens": 2577592} {"current_steps": 3940, "total_steps": 38160, "loss": 0.4623, "lr": 4.999841760956614e-05, "epoch": 2.0649895178197064, "percentage": 10.32, "elapsed_time": "0:15:00", "remaining_time": "2:10:17", "throughput": 2868.06, "total_tokens": 2581624} {"current_steps": 3945, "total_steps": 38160, "loss": 0.446, "lr": 4.999828634660715e-05, "epoch": 2.0676100628930816, "percentage": 10.34, "elapsed_time": "0:15:01", "remaining_time": "2:10:16", "throughput": 2868.19, "total_tokens": 2584888} {"current_steps": 3950, "total_steps": 38160, "loss": 0.4612, "lr": 4.9998149854291856e-05, "epoch": 2.070230607966457, "percentage": 10.35, "elapsed_time": "0:15:02", "remaining_time": "2:10:14", "throughput": 2868.06, "total_tokens": 2587672} {"current_steps": 3955, "total_steps": 38160, "loss": 0.439, "lr": 4.99980081326488e-05, "epoch": 2.0728511530398324, "percentage": 10.36, "elapsed_time": "0:15:03", "remaining_time": "2:10:11", "throughput": 2867.57, "total_tokens": 2590136} {"current_steps": 3960, "total_steps": 38160, "loss": 0.428, "lr": 4.999786118170763e-05, "epoch": 2.0754716981132075, "percentage": 10.38, "elapsed_time": "0:15:04", "remaining_time": "2:10:10", "throughput": 2868.17, "total_tokens": 2593976} {"current_steps": 3965, "total_steps": 38160, "loss": 0.9195, "lr": 4.99977090014991e-05, "epoch": 2.0780922431865827, "percentage": 10.39, "elapsed_time": "0:15:05", "remaining_time": "2:10:09", "throughput": 2868.17, "total_tokens": 2597208} {"current_steps": 3970, "total_steps": 38160, "loss": 0.4443, "lr": 4.9997551592055034e-05, "epoch": 2.080712788259958, "percentage": 10.4, "elapsed_time": "0:15:06", "remaining_time": "2:10:07", "throughput": 2868.49, "total_tokens": 2600536} {"current_steps": 3975, "total_steps": 38160, "loss": 0.3721, "lr": 4.999738895340836e-05, "epoch": 2.0833333333333335, "percentage": 10.42, "elapsed_time": "0:15:07", "remaining_time": "2:10:05", "throughput": 2868.64, "total_tokens": 2603608} {"current_steps": 3980, "total_steps": 38160, "loss": 0.4331, "lr": 4.999722108559311e-05, "epoch": 2.0859538784067087, "percentage": 10.43, "elapsed_time": "0:15:08", "remaining_time": "2:10:04", "throughput": 2869.19, "total_tokens": 2607288} {"current_steps": 3985, "total_steps": 38160, "loss": 0.5572, "lr": 4.9997047988644385e-05, "epoch": 2.088574423480084, "percentage": 10.44, "elapsed_time": "0:15:09", "remaining_time": "2:10:02", "throughput": 2869.28, "total_tokens": 2610392} {"current_steps": 3990, "total_steps": 38160, "loss": 0.5387, "lr": 4.99968696625984e-05, "epoch": 2.091194968553459, "percentage": 10.46, "elapsed_time": "0:15:10", "remaining_time": "2:10:00", "throughput": 2869.09, "total_tokens": 2613208} {"current_steps": 3995, "total_steps": 38160, "loss": 0.5622, "lr": 4.999668610749246e-05, "epoch": 2.0938155136268346, "percentage": 10.47, "elapsed_time": "0:15:11", "remaining_time": "2:09:58", "throughput": 2869.35, "total_tokens": 2616472} {"current_steps": 4000, "total_steps": 38160, "loss": 0.4319, "lr": 4.999649732336498e-05, "epoch": 2.0964360587002098, "percentage": 10.48, "elapsed_time": "0:15:13", "remaining_time": "2:09:57", "throughput": 2870.21, "total_tokens": 2620504} {"current_steps": 4005, "total_steps": 38160, "loss": 0.5043, "lr": 4.999630331025542e-05, "epoch": 2.099056603773585, "percentage": 10.5, "elapsed_time": "0:15:14", "remaining_time": "2:09:55", "throughput": 2871.11, "total_tokens": 2624632} {"current_steps": 4010, "total_steps": 38160, "loss": 0.4347, "lr": 4.9996104068204385e-05, "epoch": 2.10167714884696, "percentage": 10.51, "elapsed_time": "0:15:15", "remaining_time": "2:09:53", "throughput": 2871.12, "total_tokens": 2627608} {"current_steps": 4015, "total_steps": 38160, "loss": 0.3505, "lr": 4.999589959725355e-05, "epoch": 2.1042976939203353, "percentage": 10.52, "elapsed_time": "0:15:16", "remaining_time": "2:09:51", "throughput": 2870.75, "total_tokens": 2630232} {"current_steps": 4020, "total_steps": 38160, "loss": 0.3729, "lr": 4.999568989744568e-05, "epoch": 2.106918238993711, "percentage": 10.53, "elapsed_time": "0:15:17", "remaining_time": "2:09:50", "throughput": 2870.93, "total_tokens": 2633624} {"current_steps": 4025, "total_steps": 38160, "loss": 0.4648, "lr": 4.999547496882466e-05, "epoch": 2.109538784067086, "percentage": 10.55, "elapsed_time": "0:15:18", "remaining_time": "2:09:48", "throughput": 2870.52, "total_tokens": 2636280} {"current_steps": 4030, "total_steps": 38160, "loss": 0.4535, "lr": 4.999525481143543e-05, "epoch": 2.1121593291404612, "percentage": 10.56, "elapsed_time": "0:15:19", "remaining_time": "2:09:47", "throughput": 2871.19, "total_tokens": 2640152} {"current_steps": 4035, "total_steps": 38160, "loss": 0.4344, "lr": 4.999502942532406e-05, "epoch": 2.1147798742138364, "percentage": 10.57, "elapsed_time": "0:15:20", "remaining_time": "2:09:46", "throughput": 2871.58, "total_tokens": 2643800} {"current_steps": 4040, "total_steps": 38160, "loss": 0.4133, "lr": 4.999479881053769e-05, "epoch": 2.1174004192872116, "percentage": 10.59, "elapsed_time": "0:15:21", "remaining_time": "2:09:44", "throughput": 2872.41, "total_tokens": 2647608} {"current_steps": 4045, "total_steps": 38160, "loss": 0.5022, "lr": 4.999456296712457e-05, "epoch": 2.120020964360587, "percentage": 10.6, "elapsed_time": "0:15:22", "remaining_time": "2:09:42", "throughput": 2872.0, "total_tokens": 2650200} {"current_steps": 4050, "total_steps": 38160, "loss": 0.5608, "lr": 4.9994321895134025e-05, "epoch": 2.1226415094339623, "percentage": 10.61, "elapsed_time": "0:15:23", "remaining_time": "2:09:40", "throughput": 2872.55, "total_tokens": 2653784} {"current_steps": 4055, "total_steps": 38160, "loss": 0.451, "lr": 4.999407559461649e-05, "epoch": 2.1252620545073375, "percentage": 10.63, "elapsed_time": "0:15:25", "remaining_time": "2:09:40", "throughput": 2873.52, "total_tokens": 2658104} {"current_steps": 4060, "total_steps": 38160, "loss": 0.3862, "lr": 4.999382406562349e-05, "epoch": 2.1278825995807127, "percentage": 10.64, "elapsed_time": "0:15:26", "remaining_time": "2:09:38", "throughput": 2873.53, "total_tokens": 2661080} {"current_steps": 4065, "total_steps": 38160, "loss": 0.3793, "lr": 4.999356730820765e-05, "epoch": 2.130503144654088, "percentage": 10.65, "elapsed_time": "0:15:27", "remaining_time": "2:09:36", "throughput": 2873.71, "total_tokens": 2664312} {"current_steps": 4070, "total_steps": 38160, "loss": 0.4855, "lr": 4.999330532242266e-05, "epoch": 2.1331236897274635, "percentage": 10.67, "elapsed_time": "0:15:28", "remaining_time": "2:09:34", "throughput": 2874.05, "total_tokens": 2667704} {"current_steps": 4075, "total_steps": 38160, "loss": 0.364, "lr": 4.999303810832333e-05, "epoch": 2.1357442348008386, "percentage": 10.68, "elapsed_time": "0:15:29", "remaining_time": "2:09:33", "throughput": 2874.06, "total_tokens": 2671160} {"current_steps": 4080, "total_steps": 38160, "loss": 0.4804, "lr": 4.999276566596557e-05, "epoch": 2.138364779874214, "percentage": 10.69, "elapsed_time": "0:15:30", "remaining_time": "2:09:33", "throughput": 2874.84, "total_tokens": 2675544} {"current_steps": 4085, "total_steps": 38160, "loss": 0.4501, "lr": 4.9992487995406364e-05, "epoch": 2.140985324947589, "percentage": 10.7, "elapsed_time": "0:15:31", "remaining_time": "2:09:32", "throughput": 2874.45, "total_tokens": 2678264} {"current_steps": 4090, "total_steps": 38160, "loss": 0.3918, "lr": 4.9992205096703806e-05, "epoch": 2.1436058700209646, "percentage": 10.72, "elapsed_time": "0:15:33", "remaining_time": "2:09:36", "throughput": 2875.35, "total_tokens": 2684120} {"current_steps": 4095, "total_steps": 38160, "loss": 0.6037, "lr": 4.9991916969917054e-05, "epoch": 2.1462264150943398, "percentage": 10.73, "elapsed_time": "0:15:34", "remaining_time": "2:09:34", "throughput": 2875.05, "total_tokens": 2686872} {"current_steps": 4100, "total_steps": 38160, "loss": 0.3965, "lr": 4.99916236151064e-05, "epoch": 2.148846960167715, "percentage": 10.74, "elapsed_time": "0:15:35", "remaining_time": "2:09:32", "throughput": 2875.5, "total_tokens": 2690456} {"current_steps": 4105, "total_steps": 38160, "loss": 0.429, "lr": 4.999132503233321e-05, "epoch": 2.15146750524109, "percentage": 10.76, "elapsed_time": "0:15:36", "remaining_time": "2:09:30", "throughput": 2874.83, "total_tokens": 2692824} {"current_steps": 4110, "total_steps": 38160, "loss": 0.5383, "lr": 4.999102122165994e-05, "epoch": 2.1540880503144653, "percentage": 10.77, "elapsed_time": "0:15:37", "remaining_time": "2:09:28", "throughput": 2874.75, "total_tokens": 2695704} {"current_steps": 4115, "total_steps": 38160, "loss": 0.4282, "lr": 4.9990712183150135e-05, "epoch": 2.156708595387841, "percentage": 10.78, "elapsed_time": "0:15:38", "remaining_time": "2:09:27", "throughput": 2875.43, "total_tokens": 2699480} {"current_steps": 4120, "total_steps": 38160, "loss": 0.5051, "lr": 4.9990397916868456e-05, "epoch": 2.159329140461216, "percentage": 10.8, "elapsed_time": "0:15:40", "remaining_time": "2:09:26", "throughput": 2876.4, "total_tokens": 2703960} {"current_steps": 4125, "total_steps": 38160, "loss": 0.386, "lr": 4.999007842288064e-05, "epoch": 2.161949685534591, "percentage": 10.81, "elapsed_time": "0:15:41", "remaining_time": "2:09:25", "throughput": 2875.87, "total_tokens": 2706552} {"current_steps": 4130, "total_steps": 38160, "loss": 0.4764, "lr": 4.9989753701253514e-05, "epoch": 2.1645702306079664, "percentage": 10.82, "elapsed_time": "0:15:42", "remaining_time": "2:09:23", "throughput": 2875.66, "total_tokens": 2709368} {"current_steps": 4135, "total_steps": 38160, "loss": 0.4906, "lr": 4.998942375205502e-05, "epoch": 2.1671907756813416, "percentage": 10.84, "elapsed_time": "0:15:43", "remaining_time": "2:09:21", "throughput": 2875.52, "total_tokens": 2712248} {"current_steps": 4140, "total_steps": 38160, "loss": 0.3979, "lr": 4.998908857535416e-05, "epoch": 2.169811320754717, "percentage": 10.85, "elapsed_time": "0:15:44", "remaining_time": "2:09:19", "throughput": 2875.67, "total_tokens": 2715448} {"current_steps": 4145, "total_steps": 38160, "loss": 0.3575, "lr": 4.9988748171221065e-05, "epoch": 2.1724318658280923, "percentage": 10.86, "elapsed_time": "0:15:45", "remaining_time": "2:09:18", "throughput": 2875.94, "total_tokens": 2719064} {"current_steps": 4150, "total_steps": 38160, "loss": 0.4105, "lr": 4.998840253972695e-05, "epoch": 2.1750524109014675, "percentage": 10.88, "elapsed_time": "0:15:46", "remaining_time": "2:09:16", "throughput": 2876.36, "total_tokens": 2722488} {"current_steps": 4155, "total_steps": 38160, "loss": 0.3513, "lr": 4.9988051680944094e-05, "epoch": 2.1776729559748427, "percentage": 10.89, "elapsed_time": "0:15:47", "remaining_time": "2:09:15", "throughput": 2876.33, "total_tokens": 2725528} {"current_steps": 4160, "total_steps": 38160, "loss": 0.3805, "lr": 4.998769559494591e-05, "epoch": 2.180293501048218, "percentage": 10.9, "elapsed_time": "0:15:48", "remaining_time": "2:09:13", "throughput": 2876.54, "total_tokens": 2728824} {"current_steps": 4165, "total_steps": 38160, "loss": 0.5394, "lr": 4.998733428180689e-05, "epoch": 2.1829140461215935, "percentage": 10.91, "elapsed_time": "0:15:49", "remaining_time": "2:09:11", "throughput": 2877.24, "total_tokens": 2732472} {"current_steps": 4170, "total_steps": 38160, "loss": 0.4475, "lr": 4.998696774160259e-05, "epoch": 2.1855345911949686, "percentage": 10.93, "elapsed_time": "0:15:50", "remaining_time": "2:09:09", "throughput": 2877.22, "total_tokens": 2735544} {"current_steps": 4175, "total_steps": 38160, "loss": 0.4558, "lr": 4.9986595974409714e-05, "epoch": 2.188155136268344, "percentage": 10.94, "elapsed_time": "0:15:51", "remaining_time": "2:09:07", "throughput": 2877.74, "total_tokens": 2739032} {"current_steps": 4180, "total_steps": 38160, "loss": 0.5546, "lr": 4.998621898030603e-05, "epoch": 2.190775681341719, "percentage": 10.95, "elapsed_time": "0:15:52", "remaining_time": "2:09:06", "throughput": 2878.06, "total_tokens": 2742456} {"current_steps": 4185, "total_steps": 38160, "loss": 0.3929, "lr": 4.998583675937039e-05, "epoch": 2.1933962264150946, "percentage": 10.97, "elapsed_time": "0:15:53", "remaining_time": "2:09:04", "throughput": 2877.38, "total_tokens": 2744888} {"current_steps": 4190, "total_steps": 38160, "loss": 0.5136, "lr": 4.998544931168274e-05, "epoch": 2.1960167714884697, "percentage": 10.98, "elapsed_time": "0:15:55", "remaining_time": "2:09:02", "throughput": 2876.94, "total_tokens": 2747512} {"current_steps": 4195, "total_steps": 38160, "loss": 0.4675, "lr": 4.9985056637324154e-05, "epoch": 2.198637316561845, "percentage": 10.99, "elapsed_time": "0:15:56", "remaining_time": "2:09:00", "throughput": 2876.99, "total_tokens": 2750648} {"current_steps": 4200, "total_steps": 38160, "loss": 0.3467, "lr": 4.998465873637677e-05, "epoch": 2.20125786163522, "percentage": 11.01, "elapsed_time": "0:15:57", "remaining_time": "2:08:59", "throughput": 2876.68, "total_tokens": 2753368} {"current_steps": 4205, "total_steps": 38160, "loss": 0.4023, "lr": 4.9984255608923806e-05, "epoch": 2.2038784067085953, "percentage": 11.02, "elapsed_time": "0:15:58", "remaining_time": "2:08:57", "throughput": 2877.02, "total_tokens": 2756696} {"current_steps": 4210, "total_steps": 38160, "loss": 0.4653, "lr": 4.998384725504961e-05, "epoch": 2.2064989517819704, "percentage": 11.03, "elapsed_time": "0:15:59", "remaining_time": "2:08:55", "throughput": 2876.5, "total_tokens": 2759256} {"current_steps": 4215, "total_steps": 38160, "loss": 0.4922, "lr": 4.9983433674839596e-05, "epoch": 2.209119496855346, "percentage": 11.05, "elapsed_time": "0:16:00", "remaining_time": "2:08:53", "throughput": 2876.49, "total_tokens": 2762296} {"current_steps": 4220, "total_steps": 38160, "loss": 0.4311, "lr": 4.998301486838028e-05, "epoch": 2.211740041928721, "percentage": 11.06, "elapsed_time": "0:16:01", "remaining_time": "2:08:51", "throughput": 2876.57, "total_tokens": 2765400} {"current_steps": 4225, "total_steps": 38160, "loss": 0.421, "lr": 4.998259083575929e-05, "epoch": 2.2143605870020964, "percentage": 11.07, "elapsed_time": "0:16:02", "remaining_time": "2:08:50", "throughput": 2876.16, "total_tokens": 2768120} {"current_steps": 4230, "total_steps": 38160, "loss": 0.4891, "lr": 4.99821615770653e-05, "epoch": 2.2169811320754715, "percentage": 11.08, "elapsed_time": "0:16:03", "remaining_time": "2:08:48", "throughput": 2876.02, "total_tokens": 2771096} {"current_steps": 4235, "total_steps": 38160, "loss": 0.4958, "lr": 4.998172709238813e-05, "epoch": 2.219601677148847, "percentage": 11.1, "elapsed_time": "0:16:04", "remaining_time": "2:08:46", "throughput": 2876.2, "total_tokens": 2774328} {"current_steps": 4240, "total_steps": 38160, "loss": 0.4986, "lr": 4.9981287381818654e-05, "epoch": 2.2222222222222223, "percentage": 11.11, "elapsed_time": "0:16:05", "remaining_time": "2:08:45", "throughput": 2876.65, "total_tokens": 2778008} {"current_steps": 4245, "total_steps": 38160, "loss": 0.4494, "lr": 4.9980842445448856e-05, "epoch": 2.2248427672955975, "percentage": 11.12, "elapsed_time": "0:16:06", "remaining_time": "2:08:44", "throughput": 2875.71, "total_tokens": 2780216} {"current_steps": 4250, "total_steps": 38160, "loss": 0.4213, "lr": 4.9980392283371815e-05, "epoch": 2.2274633123689727, "percentage": 11.14, "elapsed_time": "0:16:07", "remaining_time": "2:08:42", "throughput": 2876.42, "total_tokens": 2784088} {"current_steps": 4255, "total_steps": 38160, "loss": 0.3528, "lr": 4.99799368956817e-05, "epoch": 2.230083857442348, "percentage": 11.15, "elapsed_time": "0:16:08", "remaining_time": "2:08:41", "throughput": 2875.64, "total_tokens": 2786488} {"current_steps": 4260, "total_steps": 38160, "loss": 0.358, "lr": 4.997947628247378e-05, "epoch": 2.2327044025157234, "percentage": 11.16, "elapsed_time": "0:16:10", "remaining_time": "2:08:39", "throughput": 2875.07, "total_tokens": 2788920} {"current_steps": 4265, "total_steps": 38160, "loss": 0.5976, "lr": 4.9979010443844395e-05, "epoch": 2.2353249475890986, "percentage": 11.18, "elapsed_time": "0:16:11", "remaining_time": "2:08:37", "throughput": 2874.75, "total_tokens": 2791640} {"current_steps": 4270, "total_steps": 38160, "loss": 0.3367, "lr": 4.9978539379891e-05, "epoch": 2.237945492662474, "percentage": 11.19, "elapsed_time": "0:16:12", "remaining_time": "2:08:36", "throughput": 2874.87, "total_tokens": 2794904} {"current_steps": 4275, "total_steps": 38160, "loss": 0.3873, "lr": 4.997806309071214e-05, "epoch": 2.240566037735849, "percentage": 11.2, "elapsed_time": "0:16:13", "remaining_time": "2:08:35", "throughput": 2875.4, "total_tokens": 2798840} {"current_steps": 4280, "total_steps": 38160, "loss": 0.4851, "lr": 4.997758157640745e-05, "epoch": 2.243186582809224, "percentage": 11.22, "elapsed_time": "0:16:14", "remaining_time": "2:08:33", "throughput": 2876.08, "total_tokens": 2802616} {"current_steps": 4285, "total_steps": 38160, "loss": 0.4272, "lr": 4.997709483707765e-05, "epoch": 2.2458071278825997, "percentage": 11.23, "elapsed_time": "0:16:15", "remaining_time": "2:08:31", "throughput": 2875.83, "total_tokens": 2805432} {"current_steps": 4290, "total_steps": 38160, "loss": 0.4791, "lr": 4.997660287282456e-05, "epoch": 2.248427672955975, "percentage": 11.24, "elapsed_time": "0:16:16", "remaining_time": "2:08:30", "throughput": 2876.03, "total_tokens": 2808696} {"current_steps": 4295, "total_steps": 38160, "loss": 0.3892, "lr": 4.99761056837511e-05, "epoch": 2.25104821802935, "percentage": 11.26, "elapsed_time": "0:16:17", "remaining_time": "2:08:28", "throughput": 2876.04, "total_tokens": 2811640} {"current_steps": 4300, "total_steps": 38160, "loss": 0.3882, "lr": 4.997560326996128e-05, "epoch": 2.2536687631027252, "percentage": 11.27, "elapsed_time": "0:16:18", "remaining_time": "2:08:27", "throughput": 2876.24, "total_tokens": 2815224} {"current_steps": 4305, "total_steps": 38160, "loss": 0.4639, "lr": 4.997509563156018e-05, "epoch": 2.2562893081761004, "percentage": 11.28, "elapsed_time": "0:16:19", "remaining_time": "2:08:25", "throughput": 2875.66, "total_tokens": 2817688} {"current_steps": 4310, "total_steps": 38160, "loss": 0.3621, "lr": 4.997458276865401e-05, "epoch": 2.258909853249476, "percentage": 11.29, "elapsed_time": "0:16:20", "remaining_time": "2:08:23", "throughput": 2875.93, "total_tokens": 2821016} {"current_steps": 4315, "total_steps": 38160, "loss": 0.5344, "lr": 4.997406468135005e-05, "epoch": 2.261530398322851, "percentage": 11.31, "elapsed_time": "0:16:21", "remaining_time": "2:08:22", "throughput": 2875.49, "total_tokens": 2823608} {"current_steps": 4320, "total_steps": 38160, "loss": 0.3816, "lr": 4.9973541369756686e-05, "epoch": 2.2641509433962264, "percentage": 11.32, "elapsed_time": "0:16:23", "remaining_time": "2:08:21", "throughput": 2876.5, "total_tokens": 2828248} {"current_steps": 4325, "total_steps": 38160, "loss": 0.4859, "lr": 4.9973012833983365e-05, "epoch": 2.2667714884696015, "percentage": 11.33, "elapsed_time": "0:16:24", "remaining_time": "2:08:21", "throughput": 2877.02, "total_tokens": 2832344} {"current_steps": 4330, "total_steps": 38160, "loss": 0.3901, "lr": 4.9972479074140684e-05, "epoch": 2.269392033542977, "percentage": 11.35, "elapsed_time": "0:16:25", "remaining_time": "2:08:20", "throughput": 2877.78, "total_tokens": 2836408} {"current_steps": 4335, "total_steps": 38160, "loss": 0.4844, "lr": 4.9971940090340276e-05, "epoch": 2.2720125786163523, "percentage": 11.36, "elapsed_time": "0:16:26", "remaining_time": "2:08:18", "throughput": 2877.63, "total_tokens": 2839320} {"current_steps": 4340, "total_steps": 38160, "loss": 0.4903, "lr": 4.997139588269489e-05, "epoch": 2.2746331236897275, "percentage": 11.37, "elapsed_time": "0:16:27", "remaining_time": "2:08:16", "throughput": 2877.81, "total_tokens": 2842456} {"current_steps": 4345, "total_steps": 38160, "loss": 0.558, "lr": 4.997084645131838e-05, "epoch": 2.2772536687631026, "percentage": 11.39, "elapsed_time": "0:16:28", "remaining_time": "2:08:15", "throughput": 2877.76, "total_tokens": 2845432} {"current_steps": 4350, "total_steps": 38160, "loss": 0.4951, "lr": 4.9970291796325666e-05, "epoch": 2.279874213836478, "percentage": 11.4, "elapsed_time": "0:16:29", "remaining_time": "2:08:13", "throughput": 2877.84, "total_tokens": 2848536} {"current_steps": 4355, "total_steps": 38160, "loss": 0.5409, "lr": 4.996973191783279e-05, "epoch": 2.2824947589098534, "percentage": 11.41, "elapsed_time": "0:16:30", "remaining_time": "2:08:12", "throughput": 2877.47, "total_tokens": 2851544} {"current_steps": 4360, "total_steps": 38160, "loss": 0.4345, "lr": 4.996916681595687e-05, "epoch": 2.2851153039832286, "percentage": 11.43, "elapsed_time": "0:16:32", "remaining_time": "2:08:11", "throughput": 2877.13, "total_tokens": 2854392} {"current_steps": 4365, "total_steps": 38160, "loss": 0.3644, "lr": 4.996859649081611e-05, "epoch": 2.2877358490566038, "percentage": 11.44, "elapsed_time": "0:16:33", "remaining_time": "2:08:10", "throughput": 2877.59, "total_tokens": 2858424} {"current_steps": 4370, "total_steps": 38160, "loss": 0.4631, "lr": 4.996802094252983e-05, "epoch": 2.290356394129979, "percentage": 11.45, "elapsed_time": "0:16:34", "remaining_time": "2:08:08", "throughput": 2877.55, "total_tokens": 2861368} {"current_steps": 4375, "total_steps": 38160, "loss": 0.4406, "lr": 4.996744017121841e-05, "epoch": 2.2929769392033545, "percentage": 11.46, "elapsed_time": "0:16:35", "remaining_time": "2:08:06", "throughput": 2877.2, "total_tokens": 2863960} {"current_steps": 4380, "total_steps": 38160, "loss": 0.5256, "lr": 4.9966854177003355e-05, "epoch": 2.2955974842767297, "percentage": 11.48, "elapsed_time": "0:16:36", "remaining_time": "2:08:05", "throughput": 2877.44, "total_tokens": 2867352} {"current_steps": 4385, "total_steps": 38160, "loss": 0.4958, "lr": 4.996626296000724e-05, "epoch": 2.298218029350105, "percentage": 11.49, "elapsed_time": "0:16:37", "remaining_time": "2:08:05", "throughput": 2878.37, "total_tokens": 2871992} {"current_steps": 4390, "total_steps": 38160, "loss": 0.4011, "lr": 4.996566652035374e-05, "epoch": 2.30083857442348, "percentage": 11.5, "elapsed_time": "0:16:38", "remaining_time": "2:08:03", "throughput": 2877.98, "total_tokens": 2874680} {"current_steps": 4395, "total_steps": 38160, "loss": 0.3292, "lr": 4.996506485816763e-05, "epoch": 2.3034591194968552, "percentage": 11.52, "elapsed_time": "0:16:39", "remaining_time": "2:08:01", "throughput": 2877.92, "total_tokens": 2877688} {"current_steps": 4400, "total_steps": 38160, "loss": 0.5187, "lr": 4.996445797357477e-05, "epoch": 2.3060796645702304, "percentage": 11.53, "elapsed_time": "0:16:41", "remaining_time": "2:08:07", "throughput": 2880.16, "total_tokens": 2885528} {"current_steps": 4405, "total_steps": 38160, "loss": 0.5683, "lr": 4.996384586670211e-05, "epoch": 2.308700209643606, "percentage": 11.54, "elapsed_time": "0:16:42", "remaining_time": "2:08:05", "throughput": 2880.86, "total_tokens": 2889464} {"current_steps": 4410, "total_steps": 38160, "loss": 0.3406, "lr": 4.99632285376777e-05, "epoch": 2.311320754716981, "percentage": 11.56, "elapsed_time": "0:16:44", "remaining_time": "2:08:04", "throughput": 2881.63, "total_tokens": 2893464} {"current_steps": 4415, "total_steps": 38160, "loss": 0.4799, "lr": 4.9962605986630674e-05, "epoch": 2.3139412997903563, "percentage": 11.57, "elapsed_time": "0:16:45", "remaining_time": "2:08:02", "throughput": 2881.97, "total_tokens": 2896792} {"current_steps": 4420, "total_steps": 38160, "loss": 0.4286, "lr": 4.996197821369126e-05, "epoch": 2.3165618448637315, "percentage": 11.58, "elapsed_time": "0:16:46", "remaining_time": "2:08:01", "throughput": 2882.55, "total_tokens": 2900664} {"current_steps": 4425, "total_steps": 38160, "loss": 0.4927, "lr": 4.9961345218990796e-05, "epoch": 2.319182389937107, "percentage": 11.6, "elapsed_time": "0:16:47", "remaining_time": "2:08:00", "throughput": 2882.71, "total_tokens": 2904152} {"current_steps": 4430, "total_steps": 38160, "loss": 0.4479, "lr": 4.996070700266168e-05, "epoch": 2.3218029350104823, "percentage": 11.61, "elapsed_time": "0:16:48", "remaining_time": "2:07:58", "throughput": 2882.35, "total_tokens": 2906776} {"current_steps": 4435, "total_steps": 38160, "loss": 0.4619, "lr": 4.9960063564837424e-05, "epoch": 2.3244234800838575, "percentage": 11.62, "elapsed_time": "0:16:49", "remaining_time": "2:07:56", "throughput": 2882.22, "total_tokens": 2909720} {"current_steps": 4440, "total_steps": 38160, "loss": 0.3218, "lr": 4.995941490565262e-05, "epoch": 2.3270440251572326, "percentage": 11.64, "elapsed_time": "0:16:51", "remaining_time": "2:08:00", "throughput": 2884.07, "total_tokens": 2916536} {"current_steps": 4445, "total_steps": 38160, "loss": 0.51, "lr": 4.995876102524299e-05, "epoch": 2.329664570230608, "percentage": 11.65, "elapsed_time": "0:16:52", "remaining_time": "2:07:58", "throughput": 2884.12, "total_tokens": 2919608} {"current_steps": 4450, "total_steps": 38160, "loss": 0.5754, "lr": 4.995810192374529e-05, "epoch": 2.3322851153039834, "percentage": 11.66, "elapsed_time": "0:16:53", "remaining_time": "2:07:56", "throughput": 2884.86, "total_tokens": 2923352} {"current_steps": 4455, "total_steps": 38160, "loss": 0.4214, "lr": 4.99574376012974e-05, "epoch": 2.3349056603773586, "percentage": 11.67, "elapsed_time": "0:16:54", "remaining_time": "2:07:54", "throughput": 2884.66, "total_tokens": 2926232} {"current_steps": 4460, "total_steps": 38160, "loss": 0.4127, "lr": 4.995676805803829e-05, "epoch": 2.3375262054507338, "percentage": 11.69, "elapsed_time": "0:16:55", "remaining_time": "2:07:53", "throughput": 2884.93, "total_tokens": 2929656} {"current_steps": 4465, "total_steps": 38160, "loss": 0.5086, "lr": 4.995609329410804e-05, "epoch": 2.340146750524109, "percentage": 11.7, "elapsed_time": "0:16:56", "remaining_time": "2:07:51", "throughput": 2884.53, "total_tokens": 2932344} {"current_steps": 4470, "total_steps": 38160, "loss": 0.3639, "lr": 4.9955413309647776e-05, "epoch": 2.342767295597484, "percentage": 11.71, "elapsed_time": "0:16:57", "remaining_time": "2:07:50", "throughput": 2884.92, "total_tokens": 2936152} {"current_steps": 4475, "total_steps": 38160, "loss": 0.3987, "lr": 4.9954728104799756e-05, "epoch": 2.3453878406708597, "percentage": 11.73, "elapsed_time": "0:16:58", "remaining_time": "2:07:48", "throughput": 2885.04, "total_tokens": 2939224} {"current_steps": 4480, "total_steps": 38160, "loss": 0.3561, "lr": 4.995403767970731e-05, "epoch": 2.348008385744235, "percentage": 11.74, "elapsed_time": "0:16:59", "remaining_time": "2:07:47", "throughput": 2884.68, "total_tokens": 2941912} {"current_steps": 4485, "total_steps": 38160, "loss": 0.377, "lr": 4.995334203451488e-05, "epoch": 2.35062893081761, "percentage": 11.75, "elapsed_time": "0:17:00", "remaining_time": "2:07:44", "throughput": 2884.43, "total_tokens": 2944568} {"current_steps": 4490, "total_steps": 38160, "loss": 0.3407, "lr": 4.995264116936798e-05, "epoch": 2.353249475890985, "percentage": 11.77, "elapsed_time": "0:17:01", "remaining_time": "2:07:42", "throughput": 2884.46, "total_tokens": 2947480} {"current_steps": 4495, "total_steps": 38160, "loss": 0.4776, "lr": 4.995193508441322e-05, "epoch": 2.3558700209643604, "percentage": 11.78, "elapsed_time": "0:17:03", "remaining_time": "2:07:41", "throughput": 2884.84, "total_tokens": 2951192} {"current_steps": 4500, "total_steps": 38160, "loss": 0.4402, "lr": 4.99512237797983e-05, "epoch": 2.358490566037736, "percentage": 11.79, "elapsed_time": "0:17:04", "remaining_time": "2:07:39", "throughput": 2885.25, "total_tokens": 2954648} {"current_steps": 4505, "total_steps": 38160, "loss": 0.3605, "lr": 4.995050725567203e-05, "epoch": 2.361111111111111, "percentage": 11.81, "elapsed_time": "0:17:05", "remaining_time": "2:07:39", "throughput": 2885.45, "total_tokens": 2958552} {"current_steps": 4510, "total_steps": 38160, "loss": 0.3739, "lr": 4.994978551218429e-05, "epoch": 2.3637316561844863, "percentage": 11.82, "elapsed_time": "0:17:06", "remaining_time": "2:07:38", "throughput": 2885.6, "total_tokens": 2962040} {"current_steps": 4515, "total_steps": 38160, "loss": 0.4411, "lr": 4.9949058549486066e-05, "epoch": 2.3663522012578615, "percentage": 11.83, "elapsed_time": "0:17:07", "remaining_time": "2:07:36", "throughput": 2885.42, "total_tokens": 2964824} {"current_steps": 4520, "total_steps": 38160, "loss": 0.4106, "lr": 4.994832636772943e-05, "epoch": 2.368972746331237, "percentage": 11.84, "elapsed_time": "0:17:08", "remaining_time": "2:07:35", "throughput": 2885.04, "total_tokens": 2967448} {"current_steps": 4525, "total_steps": 38160, "loss": 0.5136, "lr": 4.994758896706754e-05, "epoch": 2.3715932914046123, "percentage": 11.86, "elapsed_time": "0:17:09", "remaining_time": "2:07:33", "throughput": 2885.34, "total_tokens": 2971000} {"current_steps": 4530, "total_steps": 38160, "loss": 0.4434, "lr": 4.994684634765465e-05, "epoch": 2.3742138364779874, "percentage": 11.87, "elapsed_time": "0:17:10", "remaining_time": "2:07:32", "throughput": 2884.88, "total_tokens": 2973592} {"current_steps": 4535, "total_steps": 38160, "loss": 0.5156, "lr": 4.9946098509646125e-05, "epoch": 2.3768343815513626, "percentage": 11.88, "elapsed_time": "0:17:11", "remaining_time": "2:07:30", "throughput": 2885.55, "total_tokens": 2977560} {"current_steps": 4540, "total_steps": 38160, "loss": 0.4274, "lr": 4.994534545319838e-05, "epoch": 2.379454926624738, "percentage": 11.9, "elapsed_time": "0:17:12", "remaining_time": "2:07:29", "throughput": 2885.29, "total_tokens": 2980280} {"current_steps": 4545, "total_steps": 38160, "loss": 0.4071, "lr": 4.994458717846896e-05, "epoch": 2.3820754716981134, "percentage": 11.91, "elapsed_time": "0:17:13", "remaining_time": "2:07:27", "throughput": 2885.44, "total_tokens": 2983352} {"current_steps": 4550, "total_steps": 38160, "loss": 0.4867, "lr": 4.9943823685616485e-05, "epoch": 2.3846960167714886, "percentage": 11.92, "elapsed_time": "0:17:15", "remaining_time": "2:07:25", "throughput": 2885.55, "total_tokens": 2986648} {"current_steps": 4555, "total_steps": 38160, "loss": 0.4157, "lr": 4.994305497480067e-05, "epoch": 2.3873165618448637, "percentage": 11.94, "elapsed_time": "0:17:16", "remaining_time": "2:07:23", "throughput": 2885.71, "total_tokens": 2989880} {"current_steps": 4560, "total_steps": 38160, "loss": 0.4143, "lr": 4.994228104618233e-05, "epoch": 2.389937106918239, "percentage": 11.95, "elapsed_time": "0:17:17", "remaining_time": "2:07:22", "throughput": 2885.32, "total_tokens": 2992536} {"current_steps": 4565, "total_steps": 38160, "loss": 0.4589, "lr": 4.994150189992334e-05, "epoch": 2.392557651991614, "percentage": 11.96, "elapsed_time": "0:17:18", "remaining_time": "2:07:20", "throughput": 2885.77, "total_tokens": 2996152} {"current_steps": 4570, "total_steps": 38160, "loss": 0.4263, "lr": 4.99407175361867e-05, "epoch": 2.3951781970649897, "percentage": 11.98, "elapsed_time": "0:17:19", "remaining_time": "2:07:18", "throughput": 2885.89, "total_tokens": 2999288} {"current_steps": 4575, "total_steps": 38160, "loss": 0.3369, "lr": 4.99399279551365e-05, "epoch": 2.397798742138365, "percentage": 11.99, "elapsed_time": "0:17:20", "remaining_time": "2:07:17", "throughput": 2886.08, "total_tokens": 3002520} {"current_steps": 4580, "total_steps": 38160, "loss": 0.5275, "lr": 4.9939133156937886e-05, "epoch": 2.40041928721174, "percentage": 12.0, "elapsed_time": "0:17:21", "remaining_time": "2:07:15", "throughput": 2886.28, "total_tokens": 3005752} {"current_steps": 4585, "total_steps": 38160, "loss": 0.4477, "lr": 4.993833314175716e-05, "epoch": 2.403039832285115, "percentage": 12.02, "elapsed_time": "0:17:22", "remaining_time": "2:07:13", "throughput": 2887.01, "total_tokens": 3009432} {"current_steps": 4590, "total_steps": 38160, "loss": 0.4782, "lr": 4.993752790976163e-05, "epoch": 2.4056603773584904, "percentage": 12.03, "elapsed_time": "0:17:23", "remaining_time": "2:07:12", "throughput": 2888.1, "total_tokens": 3014136} {"current_steps": 4595, "total_steps": 38160, "loss": 0.4699, "lr": 4.993671746111977e-05, "epoch": 2.408280922431866, "percentage": 12.04, "elapsed_time": "0:17:24", "remaining_time": "2:07:11", "throughput": 2888.07, "total_tokens": 3017144} {"current_steps": 4600, "total_steps": 38160, "loss": 0.4822, "lr": 4.993590179600111e-05, "epoch": 2.410901467505241, "percentage": 12.05, "elapsed_time": "0:17:25", "remaining_time": "2:07:09", "throughput": 2887.31, "total_tokens": 3019448} {"current_steps": 4605, "total_steps": 38160, "loss": 0.3375, "lr": 4.9935080914576284e-05, "epoch": 2.4135220125786163, "percentage": 12.07, "elapsed_time": "0:17:26", "remaining_time": "2:07:07", "throughput": 2886.96, "total_tokens": 3022104} {"current_steps": 4610, "total_steps": 38160, "loss": 0.4857, "lr": 4.9934254817016995e-05, "epoch": 2.4161425576519915, "percentage": 12.08, "elapsed_time": "0:17:27", "remaining_time": "2:07:06", "throughput": 2887.42, "total_tokens": 3025688} {"current_steps": 4615, "total_steps": 38160, "loss": 0.3226, "lr": 4.993342350349607e-05, "epoch": 2.418763102725367, "percentage": 12.09, "elapsed_time": "0:17:29", "remaining_time": "2:07:05", "throughput": 2888.15, "total_tokens": 3029816} {"current_steps": 4620, "total_steps": 38160, "loss": 0.3179, "lr": 4.9932586974187404e-05, "epoch": 2.4213836477987423, "percentage": 12.11, "elapsed_time": "0:17:30", "remaining_time": "2:07:03", "throughput": 2888.14, "total_tokens": 3032824} {"current_steps": 4625, "total_steps": 38160, "loss": 0.5591, "lr": 4.9931745229265986e-05, "epoch": 2.4240041928721174, "percentage": 12.12, "elapsed_time": "0:17:31", "remaining_time": "2:07:02", "throughput": 2888.66, "total_tokens": 3036632} {"current_steps": 4630, "total_steps": 38160, "loss": 0.4713, "lr": 4.99308982689079e-05, "epoch": 2.4266247379454926, "percentage": 12.13, "elapsed_time": "0:17:32", "remaining_time": "2:07:00", "throughput": 2888.3, "total_tokens": 3039384} {"current_steps": 4635, "total_steps": 38160, "loss": 0.4353, "lr": 4.993004609329033e-05, "epoch": 2.4292452830188678, "percentage": 12.15, "elapsed_time": "0:17:33", "remaining_time": "2:06:58", "throughput": 2888.25, "total_tokens": 3042296} {"current_steps": 4640, "total_steps": 38160, "loss": 0.3997, "lr": 4.992918870259153e-05, "epoch": 2.431865828092243, "percentage": 12.16, "elapsed_time": "0:17:34", "remaining_time": "2:06:56", "throughput": 2888.28, "total_tokens": 3045304} {"current_steps": 4645, "total_steps": 38160, "loss": 0.3549, "lr": 4.992832609699086e-05, "epoch": 2.4344863731656186, "percentage": 12.17, "elapsed_time": "0:17:35", "remaining_time": "2:06:55", "throughput": 2888.75, "total_tokens": 3048824} {"current_steps": 4650, "total_steps": 38160, "loss": 0.4795, "lr": 4.992745827666877e-05, "epoch": 2.4371069182389937, "percentage": 12.19, "elapsed_time": "0:17:36", "remaining_time": "2:06:53", "throughput": 2888.78, "total_tokens": 3052120} {"current_steps": 4655, "total_steps": 38160, "loss": 0.4332, "lr": 4.99265852418068e-05, "epoch": 2.439727463312369, "percentage": 12.2, "elapsed_time": "0:17:37", "remaining_time": "2:06:52", "throughput": 2888.97, "total_tokens": 3055384} {"current_steps": 4660, "total_steps": 38160, "loss": 0.3382, "lr": 4.992570699258757e-05, "epoch": 2.442348008385744, "percentage": 12.21, "elapsed_time": "0:17:38", "remaining_time": "2:06:50", "throughput": 2888.86, "total_tokens": 3058328} {"current_steps": 4665, "total_steps": 38160, "loss": 0.4733, "lr": 4.99248235291948e-05, "epoch": 2.4449685534591197, "percentage": 12.22, "elapsed_time": "0:17:40", "remaining_time": "2:06:50", "throughput": 2890.08, "total_tokens": 3063512} {"current_steps": 4670, "total_steps": 38160, "loss": 0.475, "lr": 4.9923934851813314e-05, "epoch": 2.447589098532495, "percentage": 12.24, "elapsed_time": "0:17:41", "remaining_time": "2:06:50", "throughput": 2890.84, "total_tokens": 3068056} {"current_steps": 4675, "total_steps": 38160, "loss": 0.3915, "lr": 4.9923040960628996e-05, "epoch": 2.45020964360587, "percentage": 12.25, "elapsed_time": "0:17:42", "remaining_time": "2:06:49", "throughput": 2891.29, "total_tokens": 3071608} {"current_steps": 4680, "total_steps": 38160, "loss": 0.4795, "lr": 4.9922141855828856e-05, "epoch": 2.452830188679245, "percentage": 12.26, "elapsed_time": "0:17:43", "remaining_time": "2:06:47", "throughput": 2891.45, "total_tokens": 3074872} {"current_steps": 4685, "total_steps": 38160, "loss": 0.3723, "lr": 4.992123753760096e-05, "epoch": 2.4554507337526204, "percentage": 12.28, "elapsed_time": "0:17:44", "remaining_time": "2:06:45", "throughput": 2891.28, "total_tokens": 3077720} {"current_steps": 4690, "total_steps": 38160, "loss": 0.5298, "lr": 4.9920328006134484e-05, "epoch": 2.458071278825996, "percentage": 12.29, "elapsed_time": "0:17:45", "remaining_time": "2:06:44", "throughput": 2891.16, "total_tokens": 3080664} {"current_steps": 4695, "total_steps": 38160, "loss": 0.4358, "lr": 4.991941326161971e-05, "epoch": 2.460691823899371, "percentage": 12.3, "elapsed_time": "0:17:46", "remaining_time": "2:06:44", "throughput": 2891.22, "total_tokens": 3084408} {"current_steps": 4700, "total_steps": 38160, "loss": 0.4825, "lr": 4.991849330424796e-05, "epoch": 2.4633123689727463, "percentage": 12.32, "elapsed_time": "0:17:47", "remaining_time": "2:06:42", "throughput": 2891.42, "total_tokens": 3087640} {"current_steps": 4705, "total_steps": 38160, "loss": 0.4955, "lr": 4.9917568134211703e-05, "epoch": 2.4659329140461215, "percentage": 12.33, "elapsed_time": "0:17:48", "remaining_time": "2:06:40", "throughput": 2891.26, "total_tokens": 3090520} {"current_steps": 4710, "total_steps": 38160, "loss": 0.3951, "lr": 4.991663775170447e-05, "epoch": 2.468553459119497, "percentage": 12.34, "elapsed_time": "0:17:49", "remaining_time": "2:06:38", "throughput": 2891.31, "total_tokens": 3093624} {"current_steps": 4715, "total_steps": 38160, "loss": 0.4022, "lr": 4.991570215692088e-05, "epoch": 2.4711740041928723, "percentage": 12.36, "elapsed_time": "0:17:51", "remaining_time": "2:06:37", "throughput": 2890.89, "total_tokens": 3096184} {"current_steps": 4720, "total_steps": 38160, "loss": 0.5277, "lr": 4.991476135005665e-05, "epoch": 2.4737945492662474, "percentage": 12.37, "elapsed_time": "0:17:52", "remaining_time": "2:06:35", "throughput": 2891.42, "total_tokens": 3099928} {"current_steps": 4725, "total_steps": 38160, "loss": 0.4247, "lr": 4.991381533130859e-05, "epoch": 2.4764150943396226, "percentage": 12.38, "elapsed_time": "0:17:53", "remaining_time": "2:06:33", "throughput": 2891.01, "total_tokens": 3102456} {"current_steps": 4730, "total_steps": 38160, "loss": 0.4826, "lr": 4.99128641008746e-05, "epoch": 2.4790356394129978, "percentage": 12.4, "elapsed_time": "0:17:54", "remaining_time": "2:06:31", "throughput": 2890.33, "total_tokens": 3104728} {"current_steps": 4735, "total_steps": 38160, "loss": 0.3893, "lr": 4.9911907658953664e-05, "epoch": 2.481656184486373, "percentage": 12.41, "elapsed_time": "0:17:55", "remaining_time": "2:06:30", "throughput": 2890.27, "total_tokens": 3107704} {"current_steps": 4740, "total_steps": 38160, "loss": 0.3769, "lr": 4.991094600574584e-05, "epoch": 2.4842767295597485, "percentage": 12.42, "elapsed_time": "0:17:56", "remaining_time": "2:06:28", "throughput": 2889.89, "total_tokens": 3110328} {"current_steps": 4745, "total_steps": 38160, "loss": 0.4645, "lr": 4.9909979141452324e-05, "epoch": 2.4868972746331237, "percentage": 12.43, "elapsed_time": "0:17:57", "remaining_time": "2:06:27", "throughput": 2889.71, "total_tokens": 3113464} {"current_steps": 4750, "total_steps": 38160, "loss": 0.3848, "lr": 4.9909007066275346e-05, "epoch": 2.489517819706499, "percentage": 12.45, "elapsed_time": "0:17:58", "remaining_time": "2:06:26", "throughput": 2890.1, "total_tokens": 3117112} {"current_steps": 4755, "total_steps": 38160, "loss": 0.3909, "lr": 4.990802978041828e-05, "epoch": 2.492138364779874, "percentage": 12.46, "elapsed_time": "0:17:59", "remaining_time": "2:06:24", "throughput": 2890.14, "total_tokens": 3120280} {"current_steps": 4760, "total_steps": 38160, "loss": 0.4243, "lr": 4.990704728408555e-05, "epoch": 2.4947589098532497, "percentage": 12.47, "elapsed_time": "0:18:00", "remaining_time": "2:06:23", "throughput": 2890.65, "total_tokens": 3123928} {"current_steps": 4765, "total_steps": 38160, "loss": 0.3691, "lr": 4.990605957748268e-05, "epoch": 2.497379454926625, "percentage": 12.49, "elapsed_time": "0:18:01", "remaining_time": "2:06:21", "throughput": 2890.27, "total_tokens": 3126584} {"current_steps": 4770, "total_steps": 38160, "loss": 0.5382, "lr": 4.990506666081628e-05, "epoch": 2.5, "percentage": 12.5, "elapsed_time": "0:18:02", "remaining_time": "2:06:19", "throughput": 2889.95, "total_tokens": 3129368} {"current_steps": 4775, "total_steps": 38160, "loss": 0.5259, "lr": 4.990406853429408e-05, "epoch": 2.502620545073375, "percentage": 12.51, "elapsed_time": "0:18:03", "remaining_time": "2:06:18", "throughput": 2889.56, "total_tokens": 3132248} {"current_steps": 4780, "total_steps": 38160, "loss": 0.3254, "lr": 4.990306519812485e-05, "epoch": 2.5052410901467503, "percentage": 12.53, "elapsed_time": "0:18:05", "remaining_time": "2:06:17", "throughput": 2889.54, "total_tokens": 3135320} {"current_steps": 4785, "total_steps": 38160, "loss": 0.6554, "lr": 4.99020566525185e-05, "epoch": 2.507861635220126, "percentage": 12.54, "elapsed_time": "0:18:06", "remaining_time": "2:06:16", "throughput": 2889.64, "total_tokens": 3139032} {"current_steps": 4790, "total_steps": 38160, "loss": 0.5826, "lr": 4.9901042897685996e-05, "epoch": 2.510482180293501, "percentage": 12.55, "elapsed_time": "0:18:07", "remaining_time": "2:06:15", "throughput": 2889.51, "total_tokens": 3141944} {"current_steps": 4795, "total_steps": 38160, "loss": 0.435, "lr": 4.99000239338394e-05, "epoch": 2.5131027253668763, "percentage": 12.57, "elapsed_time": "0:18:08", "remaining_time": "2:06:13", "throughput": 2889.92, "total_tokens": 3145400} {"current_steps": 4800, "total_steps": 38160, "loss": 0.5247, "lr": 4.989899976119187e-05, "epoch": 2.5157232704402515, "percentage": 12.58, "elapsed_time": "0:18:09", "remaining_time": "2:06:12", "throughput": 2890.65, "total_tokens": 3149496} {"current_steps": 4805, "total_steps": 38160, "loss": 0.5381, "lr": 4.989797037995766e-05, "epoch": 2.518343815513627, "percentage": 12.59, "elapsed_time": "0:18:10", "remaining_time": "2:06:10", "throughput": 2890.51, "total_tokens": 3152344} {"current_steps": 4810, "total_steps": 38160, "loss": 0.3746, "lr": 4.989693579035209e-05, "epoch": 2.5209643605870022, "percentage": 12.6, "elapsed_time": "0:18:11", "remaining_time": "2:06:08", "throughput": 2890.33, "total_tokens": 3155192} {"current_steps": 4815, "total_steps": 38160, "loss": 0.3534, "lr": 4.989589599259159e-05, "epoch": 2.5235849056603774, "percentage": 12.62, "elapsed_time": "0:18:12", "remaining_time": "2:06:07", "throughput": 2889.86, "total_tokens": 3157688} {"current_steps": 4820, "total_steps": 38160, "loss": 0.4294, "lr": 4.9894850986893685e-05, "epoch": 2.5262054507337526, "percentage": 12.63, "elapsed_time": "0:18:13", "remaining_time": "2:06:05", "throughput": 2890.41, "total_tokens": 3161592} {"current_steps": 4825, "total_steps": 38160, "loss": 0.4231, "lr": 4.9893800773476965e-05, "epoch": 2.5288259958071277, "percentage": 12.64, "elapsed_time": "0:18:14", "remaining_time": "2:06:04", "throughput": 2889.78, "total_tokens": 3164024} {"current_steps": 4830, "total_steps": 38160, "loss": 0.3493, "lr": 4.9892745352561134e-05, "epoch": 2.531446540880503, "percentage": 12.66, "elapsed_time": "0:18:15", "remaining_time": "2:06:02", "throughput": 2889.25, "total_tokens": 3166424} {"current_steps": 4835, "total_steps": 38160, "loss": 0.6008, "lr": 4.9891684724366955e-05, "epoch": 2.5340670859538785, "percentage": 12.67, "elapsed_time": "0:18:17", "remaining_time": "2:06:01", "throughput": 2888.97, "total_tokens": 3169240} {"current_steps": 4840, "total_steps": 38160, "loss": 0.4471, "lr": 4.989061888911631e-05, "epoch": 2.5366876310272537, "percentage": 12.68, "elapsed_time": "0:18:18", "remaining_time": "2:05:59", "throughput": 2888.77, "total_tokens": 3172088} {"current_steps": 4845, "total_steps": 38160, "loss": 0.4462, "lr": 4.988954784703217e-05, "epoch": 2.539308176100629, "percentage": 12.7, "elapsed_time": "0:18:19", "remaining_time": "2:05:58", "throughput": 2888.82, "total_tokens": 3175480} {"current_steps": 4850, "total_steps": 38160, "loss": 0.4832, "lr": 4.9888471598338574e-05, "epoch": 2.541928721174004, "percentage": 12.71, "elapsed_time": "0:18:20", "remaining_time": "2:05:57", "throughput": 2889.46, "total_tokens": 3179480} {"current_steps": 4855, "total_steps": 38160, "loss": 0.4175, "lr": 4.988739014326066e-05, "epoch": 2.5445492662473796, "percentage": 12.72, "elapsed_time": "0:18:21", "remaining_time": "2:05:55", "throughput": 2889.53, "total_tokens": 3182520} {"current_steps": 4860, "total_steps": 38160, "loss": 0.4599, "lr": 4.9886303482024656e-05, "epoch": 2.547169811320755, "percentage": 12.74, "elapsed_time": "0:18:22", "remaining_time": "2:05:53", "throughput": 2889.62, "total_tokens": 3185560} {"current_steps": 4865, "total_steps": 38160, "loss": 0.4535, "lr": 4.988521161485789e-05, "epoch": 2.54979035639413, "percentage": 12.75, "elapsed_time": "0:18:23", "remaining_time": "2:05:52", "throughput": 2890.38, "total_tokens": 3189592} {"current_steps": 4870, "total_steps": 38160, "loss": 0.3929, "lr": 4.9884114541988747e-05, "epoch": 2.552410901467505, "percentage": 12.76, "elapsed_time": "0:18:24", "remaining_time": "2:05:50", "throughput": 2890.48, "total_tokens": 3192760} {"current_steps": 4875, "total_steps": 38160, "loss": 0.3692, "lr": 4.988301226364674e-05, "epoch": 2.5550314465408803, "percentage": 12.78, "elapsed_time": "0:18:25", "remaining_time": "2:05:49", "throughput": 2890.6, "total_tokens": 3195992} {"current_steps": 4880, "total_steps": 38160, "loss": 0.449, "lr": 4.988190478006245e-05, "epoch": 2.5576519916142555, "percentage": 12.79, "elapsed_time": "0:18:26", "remaining_time": "2:05:47", "throughput": 2889.75, "total_tokens": 3198200} {"current_steps": 4885, "total_steps": 38160, "loss": 0.4249, "lr": 4.988079209146754e-05, "epoch": 2.560272536687631, "percentage": 12.8, "elapsed_time": "0:18:27", "remaining_time": "2:05:46", "throughput": 2890.01, "total_tokens": 3201848} {"current_steps": 4890, "total_steps": 38160, "loss": 0.6002, "lr": 4.9879674198094794e-05, "epoch": 2.5628930817610063, "percentage": 12.81, "elapsed_time": "0:18:28", "remaining_time": "2:05:45", "throughput": 2889.59, "total_tokens": 3204504} {"current_steps": 4895, "total_steps": 38160, "loss": 0.5539, "lr": 4.987855110017804e-05, "epoch": 2.5655136268343814, "percentage": 12.83, "elapsed_time": "0:18:30", "remaining_time": "2:05:43", "throughput": 2889.42, "total_tokens": 3207320} {"current_steps": 4900, "total_steps": 38160, "loss": 0.4039, "lr": 4.9877422797952224e-05, "epoch": 2.568134171907757, "percentage": 12.84, "elapsed_time": "0:18:31", "remaining_time": "2:05:41", "throughput": 2889.62, "total_tokens": 3210584} {"current_steps": 4905, "total_steps": 38160, "loss": 0.334, "lr": 4.987628929165338e-05, "epoch": 2.5707547169811322, "percentage": 12.85, "elapsed_time": "0:18:32", "remaining_time": "2:05:40", "throughput": 2889.5, "total_tokens": 3213496} {"current_steps": 4910, "total_steps": 38160, "loss": 0.4272, "lr": 4.9875150581518615e-05, "epoch": 2.5733752620545074, "percentage": 12.87, "elapsed_time": "0:18:33", "remaining_time": "2:05:39", "throughput": 2889.67, "total_tokens": 3217016} {"current_steps": 4915, "total_steps": 38160, "loss": 0.5422, "lr": 4.987400666778614e-05, "epoch": 2.5759958071278826, "percentage": 12.88, "elapsed_time": "0:18:34", "remaining_time": "2:05:37", "throughput": 2889.48, "total_tokens": 3219800} {"current_steps": 4920, "total_steps": 38160, "loss": 0.4277, "lr": 4.987285755069524e-05, "epoch": 2.5786163522012577, "percentage": 12.89, "elapsed_time": "0:18:35", "remaining_time": "2:05:35", "throughput": 2889.15, "total_tokens": 3222424} {"current_steps": 4925, "total_steps": 38160, "loss": 0.4643, "lr": 4.987170323048632e-05, "epoch": 2.581236897274633, "percentage": 12.91, "elapsed_time": "0:18:36", "remaining_time": "2:05:33", "throughput": 2888.94, "total_tokens": 3225272} {"current_steps": 4930, "total_steps": 38160, "loss": 0.3968, "lr": 4.987054370740083e-05, "epoch": 2.5838574423480085, "percentage": 12.92, "elapsed_time": "0:18:37", "remaining_time": "2:05:32", "throughput": 2888.68, "total_tokens": 3228088} {"current_steps": 4935, "total_steps": 38160, "loss": 0.447, "lr": 4.986937898168134e-05, "epoch": 2.5864779874213837, "percentage": 12.93, "elapsed_time": "0:18:38", "remaining_time": "2:05:30", "throughput": 2888.75, "total_tokens": 3231096} {"current_steps": 4940, "total_steps": 38160, "loss": 0.5202, "lr": 4.986820905357148e-05, "epoch": 2.589098532494759, "percentage": 12.95, "elapsed_time": "0:18:39", "remaining_time": "2:05:28", "throughput": 2889.04, "total_tokens": 3234552} {"current_steps": 4945, "total_steps": 38160, "loss": 0.358, "lr": 4.9867033923315995e-05, "epoch": 2.591719077568134, "percentage": 12.96, "elapsed_time": "0:18:40", "remaining_time": "2:05:27", "throughput": 2889.23, "total_tokens": 3238072} {"current_steps": 4950, "total_steps": 38160, "loss": 0.4983, "lr": 4.9865853591160724e-05, "epoch": 2.5943396226415096, "percentage": 12.97, "elapsed_time": "0:18:41", "remaining_time": "2:05:26", "throughput": 2889.44, "total_tokens": 3241624} {"current_steps": 4955, "total_steps": 38160, "loss": 0.7068, "lr": 4.9864668057352556e-05, "epoch": 2.596960167714885, "percentage": 12.98, "elapsed_time": "0:18:42", "remaining_time": "2:05:25", "throughput": 2889.76, "total_tokens": 3245080} {"current_steps": 4960, "total_steps": 38160, "loss": 0.4869, "lr": 4.9863477322139517e-05, "epoch": 2.59958071278826, "percentage": 13.0, "elapsed_time": "0:18:44", "remaining_time": "2:05:23", "throughput": 2889.41, "total_tokens": 3247800} {"current_steps": 4965, "total_steps": 38160, "loss": 0.3364, "lr": 4.986228138577067e-05, "epoch": 2.602201257861635, "percentage": 13.01, "elapsed_time": "0:18:45", "remaining_time": "2:05:22", "throughput": 2889.34, "total_tokens": 3251000} {"current_steps": 4970, "total_steps": 38160, "loss": 0.3908, "lr": 4.986108024849619e-05, "epoch": 2.6048218029350103, "percentage": 13.02, "elapsed_time": "0:18:46", "remaining_time": "2:05:21", "throughput": 2889.92, "total_tokens": 3254872} {"current_steps": 4975, "total_steps": 38160, "loss": 0.468, "lr": 4.985987391056737e-05, "epoch": 2.6074423480083855, "percentage": 13.04, "elapsed_time": "0:18:47", "remaining_time": "2:05:20", "throughput": 2890.36, "total_tokens": 3258520} {"current_steps": 4980, "total_steps": 38160, "loss": 0.4843, "lr": 4.9858662372236544e-05, "epoch": 2.610062893081761, "percentage": 13.05, "elapsed_time": "0:18:48", "remaining_time": "2:05:18", "throughput": 2890.54, "total_tokens": 3261944} {"current_steps": 4985, "total_steps": 38160, "loss": 0.4995, "lr": 4.985744563375714e-05, "epoch": 2.6126834381551363, "percentage": 13.06, "elapsed_time": "0:18:49", "remaining_time": "2:05:17", "throughput": 2890.67, "total_tokens": 3265432} {"current_steps": 4990, "total_steps": 38160, "loss": 0.465, "lr": 4.985622369538371e-05, "epoch": 2.6153039832285114, "percentage": 13.08, "elapsed_time": "0:18:50", "remaining_time": "2:05:16", "throughput": 2890.73, "total_tokens": 3268632} {"current_steps": 4995, "total_steps": 38160, "loss": 0.4106, "lr": 4.985499655737185e-05, "epoch": 2.617924528301887, "percentage": 13.09, "elapsed_time": "0:18:51", "remaining_time": "2:05:14", "throughput": 2890.59, "total_tokens": 3271416} {"current_steps": 5000, "total_steps": 38160, "loss": 0.3272, "lr": 4.985376421997827e-05, "epoch": 2.620545073375262, "percentage": 13.1, "elapsed_time": "0:18:52", "remaining_time": "2:05:13", "throughput": 2890.41, "total_tokens": 3274424} {"current_steps": 5005, "total_steps": 38160, "loss": 0.4604, "lr": 4.985252668346076e-05, "epoch": 2.6231656184486374, "percentage": 13.12, "elapsed_time": "0:18:53", "remaining_time": "2:05:11", "throughput": 2890.7, "total_tokens": 3277688} {"current_steps": 5010, "total_steps": 38160, "loss": 0.3491, "lr": 4.9851283948078206e-05, "epoch": 2.6257861635220126, "percentage": 13.13, "elapsed_time": "0:18:54", "remaining_time": "2:05:09", "throughput": 2890.45, "total_tokens": 3280440} {"current_steps": 5015, "total_steps": 38160, "loss": 0.6238, "lr": 4.985003601409057e-05, "epoch": 2.6284067085953877, "percentage": 13.14, "elapsed_time": "0:18:55", "remaining_time": "2:05:07", "throughput": 2890.75, "total_tokens": 3283704} {"current_steps": 5020, "total_steps": 38160, "loss": 0.4068, "lr": 4.9848782881758906e-05, "epoch": 2.631027253668763, "percentage": 13.16, "elapsed_time": "0:18:57", "remaining_time": "2:05:06", "throughput": 2890.76, "total_tokens": 3286808} {"current_steps": 5025, "total_steps": 38160, "loss": 0.5344, "lr": 4.9847524551345345e-05, "epoch": 2.6336477987421385, "percentage": 13.17, "elapsed_time": "0:18:58", "remaining_time": "2:05:04", "throughput": 2890.66, "total_tokens": 3289592} {"current_steps": 5030, "total_steps": 38160, "loss": 0.45, "lr": 4.984626102311313e-05, "epoch": 2.6362683438155137, "percentage": 13.18, "elapsed_time": "0:18:59", "remaining_time": "2:05:02", "throughput": 2890.74, "total_tokens": 3292696} {"current_steps": 5035, "total_steps": 38160, "loss": 0.3045, "lr": 4.984499229732656e-05, "epoch": 2.638888888888889, "percentage": 13.19, "elapsed_time": "0:19:00", "remaining_time": "2:05:00", "throughput": 2891.4, "total_tokens": 3296632} {"current_steps": 5040, "total_steps": 38160, "loss": 0.3675, "lr": 4.984371837425106e-05, "epoch": 2.641509433962264, "percentage": 13.21, "elapsed_time": "0:19:01", "remaining_time": "2:04:59", "throughput": 2892.09, "total_tokens": 3300536} {"current_steps": 5045, "total_steps": 38160, "loss": 0.4386, "lr": 4.9842439254153106e-05, "epoch": 2.6441299790356396, "percentage": 13.22, "elapsed_time": "0:19:02", "remaining_time": "2:04:58", "throughput": 2892.87, "total_tokens": 3304728} {"current_steps": 5050, "total_steps": 38160, "loss": 0.4884, "lr": 4.984115493730027e-05, "epoch": 2.646750524109015, "percentage": 13.23, "elapsed_time": "0:19:03", "remaining_time": "2:04:57", "throughput": 2892.84, "total_tokens": 3307928} {"current_steps": 5055, "total_steps": 38160, "loss": 0.5561, "lr": 4.983986542396123e-05, "epoch": 2.64937106918239, "percentage": 13.25, "elapsed_time": "0:19:04", "remaining_time": "2:04:55", "throughput": 2892.53, "total_tokens": 3310552} {"current_steps": 5060, "total_steps": 38160, "loss": 0.5572, "lr": 4.983857071440573e-05, "epoch": 2.651991614255765, "percentage": 13.26, "elapsed_time": "0:19:05", "remaining_time": "2:04:54", "throughput": 2893.46, "total_tokens": 3314904} {"current_steps": 5065, "total_steps": 38160, "loss": 0.4288, "lr": 4.9837270808904616e-05, "epoch": 2.6546121593291403, "percentage": 13.27, "elapsed_time": "0:19:07", "remaining_time": "2:04:55", "throughput": 2894.32, "total_tokens": 3320184} {"current_steps": 5070, "total_steps": 38160, "loss": 0.3961, "lr": 4.9835965707729807e-05, "epoch": 2.6572327044025155, "percentage": 13.29, "elapsed_time": "0:19:08", "remaining_time": "2:04:53", "throughput": 2894.09, "total_tokens": 3322904} {"current_steps": 5075, "total_steps": 38160, "loss": 0.3829, "lr": 4.983465541115431e-05, "epoch": 2.659853249475891, "percentage": 13.3, "elapsed_time": "0:19:09", "remaining_time": "2:04:52", "throughput": 2893.92, "total_tokens": 3325784} {"current_steps": 5080, "total_steps": 38160, "loss": 0.4909, "lr": 4.983333991945223e-05, "epoch": 2.6624737945492662, "percentage": 13.31, "elapsed_time": "0:19:10", "remaining_time": "2:04:50", "throughput": 2893.91, "total_tokens": 3328760} {"current_steps": 5085, "total_steps": 38160, "loss": 0.4575, "lr": 4.983201923289875e-05, "epoch": 2.6650943396226414, "percentage": 13.33, "elapsed_time": "0:19:11", "remaining_time": "2:04:48", "throughput": 2893.66, "total_tokens": 3331576} {"current_steps": 5090, "total_steps": 38160, "loss": 0.5024, "lr": 4.983069335177014e-05, "epoch": 2.667714884696017, "percentage": 13.34, "elapsed_time": "0:19:12", "remaining_time": "2:04:46", "throughput": 2893.1, "total_tokens": 3333880} {"current_steps": 5095, "total_steps": 38160, "loss": 0.465, "lr": 4.982936227634378e-05, "epoch": 2.670335429769392, "percentage": 13.35, "elapsed_time": "0:19:13", "remaining_time": "2:04:45", "throughput": 2893.85, "total_tokens": 3337880} {"current_steps": 5100, "total_steps": 38160, "loss": 0.4417, "lr": 4.982802600689809e-05, "epoch": 2.6729559748427674, "percentage": 13.36, "elapsed_time": "0:19:14", "remaining_time": "2:04:43", "throughput": 2893.85, "total_tokens": 3340920} {"current_steps": 5105, "total_steps": 38160, "loss": 0.4077, "lr": 4.982668454371261e-05, "epoch": 2.6755765199161425, "percentage": 13.38, "elapsed_time": "0:19:15", "remaining_time": "2:04:42", "throughput": 2893.83, "total_tokens": 3344312} {"current_steps": 5110, "total_steps": 38160, "loss": 0.3881, "lr": 4.9825337887067966e-05, "epoch": 2.6781970649895177, "percentage": 13.39, "elapsed_time": "0:19:16", "remaining_time": "2:04:41", "throughput": 2894.09, "total_tokens": 3347672} {"current_steps": 5115, "total_steps": 38160, "loss": 0.4637, "lr": 4.982398603724586e-05, "epoch": 2.680817610062893, "percentage": 13.4, "elapsed_time": "0:19:17", "remaining_time": "2:04:39", "throughput": 2894.42, "total_tokens": 3351032} {"current_steps": 5120, "total_steps": 38160, "loss": 0.5954, "lr": 4.982262899452909e-05, "epoch": 2.6834381551362685, "percentage": 13.42, "elapsed_time": "0:19:18", "remaining_time": "2:04:37", "throughput": 2894.21, "total_tokens": 3353752} {"current_steps": 5125, "total_steps": 38160, "loss": 0.4021, "lr": 4.982126675920151e-05, "epoch": 2.6860587002096437, "percentage": 13.43, "elapsed_time": "0:19:19", "remaining_time": "2:04:36", "throughput": 2894.06, "total_tokens": 3356600} {"current_steps": 5130, "total_steps": 38160, "loss": 0.5022, "lr": 4.98198993315481e-05, "epoch": 2.688679245283019, "percentage": 13.44, "elapsed_time": "0:19:20", "remaining_time": "2:04:34", "throughput": 2894.49, "total_tokens": 3360280} {"current_steps": 5135, "total_steps": 38160, "loss": 0.5653, "lr": 4.981852671185492e-05, "epoch": 2.691299790356394, "percentage": 13.46, "elapsed_time": "0:19:21", "remaining_time": "2:04:33", "throughput": 2894.82, "total_tokens": 3363768} {"current_steps": 5140, "total_steps": 38160, "loss": 0.3921, "lr": 4.9817148900409093e-05, "epoch": 2.6939203354297696, "percentage": 13.47, "elapsed_time": "0:19:23", "remaining_time": "2:04:32", "throughput": 2895.21, "total_tokens": 3367480} {"current_steps": 5145, "total_steps": 38160, "loss": 0.4467, "lr": 4.981576589749885e-05, "epoch": 2.6965408805031448, "percentage": 13.48, "elapsed_time": "0:19:24", "remaining_time": "2:04:30", "throughput": 2895.25, "total_tokens": 3370520} {"current_steps": 5150, "total_steps": 38160, "loss": 0.3898, "lr": 4.981437770341348e-05, "epoch": 2.69916142557652, "percentage": 13.5, "elapsed_time": "0:19:25", "remaining_time": "2:04:28", "throughput": 2894.84, "total_tokens": 3372984} {"current_steps": 5155, "total_steps": 38160, "loss": 0.4428, "lr": 4.9812984318443414e-05, "epoch": 2.701781970649895, "percentage": 13.51, "elapsed_time": "0:19:26", "remaining_time": "2:04:26", "throughput": 2894.21, "total_tokens": 3375288} {"current_steps": 5160, "total_steps": 38160, "loss": 0.3542, "lr": 4.98115857428801e-05, "epoch": 2.7044025157232703, "percentage": 13.52, "elapsed_time": "0:19:27", "remaining_time": "2:04:25", "throughput": 2894.26, "total_tokens": 3378488} {"current_steps": 5165, "total_steps": 38160, "loss": 0.3907, "lr": 4.9810181977016104e-05, "epoch": 2.7070230607966455, "percentage": 13.54, "elapsed_time": "0:19:28", "remaining_time": "2:04:23", "throughput": 2894.23, "total_tokens": 3381368} {"current_steps": 5170, "total_steps": 38160, "loss": 0.4584, "lr": 4.9808773021145096e-05, "epoch": 2.709643605870021, "percentage": 13.55, "elapsed_time": "0:19:29", "remaining_time": "2:04:21", "throughput": 2894.76, "total_tokens": 3385016} {"current_steps": 5175, "total_steps": 38160, "loss": 0.4599, "lr": 4.98073588755618e-05, "epoch": 2.7122641509433962, "percentage": 13.56, "elapsed_time": "0:19:30", "remaining_time": "2:04:20", "throughput": 2894.65, "total_tokens": 3387992} {"current_steps": 5180, "total_steps": 38160, "loss": 0.4445, "lr": 4.980593954056205e-05, "epoch": 2.7148846960167714, "percentage": 13.57, "elapsed_time": "0:19:31", "remaining_time": "2:04:18", "throughput": 2894.45, "total_tokens": 3390872} {"current_steps": 5185, "total_steps": 38160, "loss": 0.4775, "lr": 4.9804515016442754e-05, "epoch": 2.717505241090147, "percentage": 13.59, "elapsed_time": "0:19:32", "remaining_time": "2:04:16", "throughput": 2894.15, "total_tokens": 3393496} {"current_steps": 5190, "total_steps": 38160, "loss": 0.6623, "lr": 4.9803085303501896e-05, "epoch": 2.720125786163522, "percentage": 13.6, "elapsed_time": "0:19:33", "remaining_time": "2:04:15", "throughput": 2893.75, "total_tokens": 3395992} {"current_steps": 5195, "total_steps": 38160, "loss": 0.5397, "lr": 4.9801650402038555e-05, "epoch": 2.7227463312368974, "percentage": 13.61, "elapsed_time": "0:19:34", "remaining_time": "2:04:13", "throughput": 2893.68, "total_tokens": 3399160} {"current_steps": 5200, "total_steps": 38160, "loss": 0.417, "lr": 4.980021031235291e-05, "epoch": 2.7253668763102725, "percentage": 13.63, "elapsed_time": "0:19:35", "remaining_time": "2:04:12", "throughput": 2893.65, "total_tokens": 3402072} {"current_steps": 5205, "total_steps": 38160, "loss": 0.4275, "lr": 4.9798765034746206e-05, "epoch": 2.7279874213836477, "percentage": 13.64, "elapsed_time": "0:19:36", "remaining_time": "2:04:10", "throughput": 2893.01, "total_tokens": 3404344} {"current_steps": 5210, "total_steps": 38160, "loss": 0.4265, "lr": 4.979731456952077e-05, "epoch": 2.730607966457023, "percentage": 13.65, "elapsed_time": "0:19:37", "remaining_time": "2:04:08", "throughput": 2893.2, "total_tokens": 3407640} {"current_steps": 5215, "total_steps": 38160, "loss": 0.3483, "lr": 4.9795858916980034e-05, "epoch": 2.7332285115303985, "percentage": 13.67, "elapsed_time": "0:19:38", "remaining_time": "2:04:07", "throughput": 2892.86, "total_tokens": 3410200} {"current_steps": 5220, "total_steps": 38160, "loss": 0.3636, "lr": 4.9794398077428495e-05, "epoch": 2.7358490566037736, "percentage": 13.68, "elapsed_time": "0:19:39", "remaining_time": "2:04:05", "throughput": 2892.48, "total_tokens": 3412856} {"current_steps": 5225, "total_steps": 38160, "loss": 0.4296, "lr": 4.979293205117175e-05, "epoch": 2.738469601677149, "percentage": 13.69, "elapsed_time": "0:19:40", "remaining_time": "2:04:04", "throughput": 2892.42, "total_tokens": 3415864} {"current_steps": 5230, "total_steps": 38160, "loss": 0.4685, "lr": 4.979146083851647e-05, "epoch": 2.741090146750524, "percentage": 13.71, "elapsed_time": "0:19:42", "remaining_time": "2:04:02", "throughput": 2892.63, "total_tokens": 3419224} {"current_steps": 5235, "total_steps": 38160, "loss": 0.4034, "lr": 4.978998443977042e-05, "epoch": 2.7437106918238996, "percentage": 13.72, "elapsed_time": "0:19:43", "remaining_time": "2:04:01", "throughput": 2892.84, "total_tokens": 3422520} {"current_steps": 5240, "total_steps": 38160, "loss": 0.4276, "lr": 4.9788502855242436e-05, "epoch": 2.7463312368972748, "percentage": 13.73, "elapsed_time": "0:19:44", "remaining_time": "2:03:59", "throughput": 2893.2, "total_tokens": 3425976} {"current_steps": 5245, "total_steps": 38160, "loss": 0.4508, "lr": 4.978701608524247e-05, "epoch": 2.74895178197065, "percentage": 13.74, "elapsed_time": "0:19:45", "remaining_time": "2:03:57", "throughput": 2893.55, "total_tokens": 3429368} {"current_steps": 5250, "total_steps": 38160, "loss": 0.4941, "lr": 4.978552413008152e-05, "epoch": 2.751572327044025, "percentage": 13.76, "elapsed_time": "0:19:46", "remaining_time": "2:03:57", "throughput": 2894.72, "total_tokens": 3434680} {"current_steps": 5255, "total_steps": 38160, "loss": 0.5186, "lr": 4.9784026990071687e-05, "epoch": 2.7541928721174003, "percentage": 13.77, "elapsed_time": "0:19:47", "remaining_time": "2:03:56", "throughput": 2894.63, "total_tokens": 3437752} {"current_steps": 5260, "total_steps": 38160, "loss": 0.5331, "lr": 4.978252466552615e-05, "epoch": 2.7568134171907754, "percentage": 13.78, "elapsed_time": "0:19:48", "remaining_time": "2:03:54", "throughput": 2894.69, "total_tokens": 3440760} {"current_steps": 5265, "total_steps": 38160, "loss": 0.4741, "lr": 4.9781017156759205e-05, "epoch": 2.759433962264151, "percentage": 13.8, "elapsed_time": "0:19:49", "remaining_time": "2:03:53", "throughput": 2894.64, "total_tokens": 3443736} {"current_steps": 5270, "total_steps": 38160, "loss": 0.5603, "lr": 4.977950446408618e-05, "epoch": 2.762054507337526, "percentage": 13.81, "elapsed_time": "0:19:50", "remaining_time": "2:03:51", "throughput": 2894.74, "total_tokens": 3446904} {"current_steps": 5275, "total_steps": 38160, "loss": 0.3821, "lr": 4.9777986587823523e-05, "epoch": 2.7646750524109014, "percentage": 13.82, "elapsed_time": "0:19:51", "remaining_time": "2:03:49", "throughput": 2894.94, "total_tokens": 3450104} {"current_steps": 5280, "total_steps": 38160, "loss": 0.5846, "lr": 4.977646352828875e-05, "epoch": 2.767295597484277, "percentage": 13.84, "elapsed_time": "0:19:52", "remaining_time": "2:03:48", "throughput": 2895.31, "total_tokens": 3453592} {"current_steps": 5285, "total_steps": 38160, "loss": 0.4386, "lr": 4.9774935285800476e-05, "epoch": 2.769916142557652, "percentage": 13.85, "elapsed_time": "0:19:53", "remaining_time": "2:03:46", "throughput": 2895.46, "total_tokens": 3456824} {"current_steps": 5290, "total_steps": 38160, "loss": 0.4751, "lr": 4.977340186067838e-05, "epoch": 2.7725366876310273, "percentage": 13.86, "elapsed_time": "0:19:55", "remaining_time": "2:03:45", "throughput": 2895.98, "total_tokens": 3460792} {"current_steps": 5295, "total_steps": 38160, "loss": 0.4896, "lr": 4.977186325324325e-05, "epoch": 2.7751572327044025, "percentage": 13.88, "elapsed_time": "0:19:56", "remaining_time": "2:03:44", "throughput": 2896.25, "total_tokens": 3464280} {"current_steps": 5300, "total_steps": 38160, "loss": 0.5583, "lr": 4.977031946381694e-05, "epoch": 2.7777777777777777, "percentage": 13.89, "elapsed_time": "0:19:57", "remaining_time": "2:03:42", "throughput": 2896.2, "total_tokens": 3467320} {"current_steps": 5305, "total_steps": 38160, "loss": 0.4221, "lr": 4.9768770492722394e-05, "epoch": 2.780398322851153, "percentage": 13.9, "elapsed_time": "0:19:58", "remaining_time": "2:03:40", "throughput": 2896.4, "total_tokens": 3470520} {"current_steps": 5310, "total_steps": 38160, "loss": 0.4543, "lr": 4.976721634028363e-05, "epoch": 2.7830188679245285, "percentage": 13.92, "elapsed_time": "0:19:59", "remaining_time": "2:03:39", "throughput": 2896.56, "total_tokens": 3474008} {"current_steps": 5315, "total_steps": 38160, "loss": 0.3872, "lr": 4.976565700682578e-05, "epoch": 2.7856394129979036, "percentage": 13.93, "elapsed_time": "0:20:00", "remaining_time": "2:03:38", "throughput": 2896.55, "total_tokens": 3477208} {"current_steps": 5320, "total_steps": 38160, "loss": 0.4653, "lr": 4.976409249267502e-05, "epoch": 2.788259958071279, "percentage": 13.94, "elapsed_time": "0:20:01", "remaining_time": "2:03:36", "throughput": 2896.45, "total_tokens": 3480088} {"current_steps": 5325, "total_steps": 38160, "loss": 0.4278, "lr": 4.976252279815863e-05, "epoch": 2.790880503144654, "percentage": 13.95, "elapsed_time": "0:20:02", "remaining_time": "2:03:36", "throughput": 2896.93, "total_tokens": 3484504} {"current_steps": 5330, "total_steps": 38160, "loss": 0.3993, "lr": 4.976094792360498e-05, "epoch": 2.7935010482180296, "percentage": 13.97, "elapsed_time": "0:20:03", "remaining_time": "2:03:35", "throughput": 2896.38, "total_tokens": 3487000} {"current_steps": 5335, "total_steps": 38160, "loss": 0.3937, "lr": 4.975936786934351e-05, "epoch": 2.7961215932914047, "percentage": 13.98, "elapsed_time": "0:20:05", "remaining_time": "2:03:34", "throughput": 2896.82, "total_tokens": 3490712} {"current_steps": 5340, "total_steps": 38160, "loss": 0.4735, "lr": 4.975778263570475e-05, "epoch": 2.79874213836478, "percentage": 13.99, "elapsed_time": "0:20:06", "remaining_time": "2:03:32", "throughput": 2897.21, "total_tokens": 3494296} {"current_steps": 5345, "total_steps": 38160, "loss": 0.3891, "lr": 4.975619222302032e-05, "epoch": 2.801362683438155, "percentage": 14.01, "elapsed_time": "0:20:07", "remaining_time": "2:03:31", "throughput": 2897.77, "total_tokens": 3498232} {"current_steps": 5350, "total_steps": 38160, "loss": 0.434, "lr": 4.975459663162291e-05, "epoch": 2.8039832285115303, "percentage": 14.02, "elapsed_time": "0:20:08", "remaining_time": "2:03:30", "throughput": 2897.55, "total_tokens": 3501080} {"current_steps": 5355, "total_steps": 38160, "loss": 0.3474, "lr": 4.9752995861846296e-05, "epoch": 2.8066037735849054, "percentage": 14.03, "elapsed_time": "0:20:09", "remaining_time": "2:03:28", "throughput": 2897.29, "total_tokens": 3504024} {"current_steps": 5360, "total_steps": 38160, "loss": 0.3568, "lr": 4.975138991402535e-05, "epoch": 2.809224318658281, "percentage": 14.05, "elapsed_time": "0:20:10", "remaining_time": "2:03:27", "throughput": 2897.37, "total_tokens": 3507256} {"current_steps": 5365, "total_steps": 38160, "loss": 0.491, "lr": 4.974977878849601e-05, "epoch": 2.811844863731656, "percentage": 14.06, "elapsed_time": "0:20:11", "remaining_time": "2:03:26", "throughput": 2897.17, "total_tokens": 3510392} {"current_steps": 5370, "total_steps": 38160, "loss": 0.481, "lr": 4.9748162485595303e-05, "epoch": 2.8144654088050314, "percentage": 14.07, "elapsed_time": "0:20:12", "remaining_time": "2:03:25", "throughput": 2896.87, "total_tokens": 3513272} {"current_steps": 5375, "total_steps": 38160, "loss": 0.4533, "lr": 4.974654100566135e-05, "epoch": 2.8170859538784065, "percentage": 14.09, "elapsed_time": "0:20:13", "remaining_time": "2:03:23", "throughput": 2896.8, "total_tokens": 3516312} {"current_steps": 5380, "total_steps": 38160, "loss": 0.4743, "lr": 4.974491434903335e-05, "epoch": 2.819706498951782, "percentage": 14.1, "elapsed_time": "0:20:14", "remaining_time": "2:03:22", "throughput": 2896.58, "total_tokens": 3519032} {"current_steps": 5385, "total_steps": 38160, "loss": 0.3452, "lr": 4.9743282516051556e-05, "epoch": 2.8223270440251573, "percentage": 14.11, "elapsed_time": "0:20:15", "remaining_time": "2:03:20", "throughput": 2896.37, "total_tokens": 3521720} {"current_steps": 5390, "total_steps": 38160, "loss": 0.3994, "lr": 4.974164550705736e-05, "epoch": 2.8249475890985325, "percentage": 14.12, "elapsed_time": "0:20:16", "remaining_time": "2:03:18", "throughput": 2896.53, "total_tokens": 3524888} {"current_steps": 5395, "total_steps": 38160, "loss": 0.3753, "lr": 4.974000332239319e-05, "epoch": 2.8275681341719077, "percentage": 14.14, "elapsed_time": "0:20:18", "remaining_time": "2:03:18", "throughput": 2897.46, "total_tokens": 3529688} {"current_steps": 5400, "total_steps": 38160, "loss": 0.4667, "lr": 4.973835596240257e-05, "epoch": 2.830188679245283, "percentage": 14.15, "elapsed_time": "0:20:19", "remaining_time": "2:03:16", "throughput": 2897.17, "total_tokens": 3532440} {"current_steps": 5405, "total_steps": 38160, "loss": 0.4387, "lr": 4.9736703427430114e-05, "epoch": 2.832809224318658, "percentage": 14.16, "elapsed_time": "0:20:20", "remaining_time": "2:03:15", "throughput": 2897.07, "total_tokens": 3535288} {"current_steps": 5410, "total_steps": 38160, "loss": 0.4647, "lr": 4.9735045717821514e-05, "epoch": 2.8354297693920336, "percentage": 14.18, "elapsed_time": "0:20:21", "remaining_time": "2:03:13", "throughput": 2897.37, "total_tokens": 3538840} {"current_steps": 5415, "total_steps": 38160, "loss": 0.3331, "lr": 4.973338283392354e-05, "epoch": 2.838050314465409, "percentage": 14.19, "elapsed_time": "0:20:22", "remaining_time": "2:03:12", "throughput": 2897.33, "total_tokens": 3541880} {"current_steps": 5420, "total_steps": 38160, "loss": 0.4807, "lr": 4.9731714776084046e-05, "epoch": 2.840670859538784, "percentage": 14.2, "elapsed_time": "0:20:23", "remaining_time": "2:03:11", "throughput": 2897.44, "total_tokens": 3545208} {"current_steps": 5425, "total_steps": 38160, "loss": 0.3838, "lr": 4.973004154465198e-05, "epoch": 2.8432914046121596, "percentage": 14.22, "elapsed_time": "0:20:24", "remaining_time": "2:03:09", "throughput": 2897.27, "total_tokens": 3548120} {"current_steps": 5430, "total_steps": 38160, "loss": 0.4421, "lr": 4.972836313997736e-05, "epoch": 2.8459119496855347, "percentage": 14.23, "elapsed_time": "0:20:25", "remaining_time": "2:03:08", "throughput": 2897.5, "total_tokens": 3551512} {"current_steps": 5435, "total_steps": 38160, "loss": 0.3668, "lr": 4.9726679562411285e-05, "epoch": 2.84853249475891, "percentage": 14.24, "elapsed_time": "0:20:26", "remaining_time": "2:03:06", "throughput": 2897.45, "total_tokens": 3554520} {"current_steps": 5440, "total_steps": 38160, "loss": 0.5025, "lr": 4.972499081230595e-05, "epoch": 2.851153039832285, "percentage": 14.26, "elapsed_time": "0:20:27", "remaining_time": "2:03:05", "throughput": 2897.0, "total_tokens": 3557208} {"current_steps": 5445, "total_steps": 38160, "loss": 0.6034, "lr": 4.9723296890014605e-05, "epoch": 2.8537735849056602, "percentage": 14.27, "elapsed_time": "0:20:28", "remaining_time": "2:03:03", "throughput": 2897.25, "total_tokens": 3560600} {"current_steps": 5450, "total_steps": 38160, "loss": 0.4106, "lr": 4.9721597795891605e-05, "epoch": 2.8563941299790354, "percentage": 14.28, "elapsed_time": "0:20:30", "remaining_time": "2:03:04", "throughput": 2898.05, "total_tokens": 3565752} {"current_steps": 5455, "total_steps": 38160, "loss": 0.3677, "lr": 4.9719893530292396e-05, "epoch": 2.859014675052411, "percentage": 14.3, "elapsed_time": "0:20:31", "remaining_time": "2:03:03", "throughput": 2898.4, "total_tokens": 3569400} {"current_steps": 5460, "total_steps": 38160, "loss": 0.3945, "lr": 4.9718184093573475e-05, "epoch": 2.861635220125786, "percentage": 14.31, "elapsed_time": "0:20:32", "remaining_time": "2:03:01", "throughput": 2898.14, "total_tokens": 3572088} {"current_steps": 5465, "total_steps": 38160, "loss": 0.5252, "lr": 4.9716469486092435e-05, "epoch": 2.8642557651991614, "percentage": 14.32, "elapsed_time": "0:20:33", "remaining_time": "2:03:00", "throughput": 2897.96, "total_tokens": 3575032} {"current_steps": 5470, "total_steps": 38160, "loss": 0.4184, "lr": 4.971474970820797e-05, "epoch": 2.8668763102725365, "percentage": 14.33, "elapsed_time": "0:20:34", "remaining_time": "2:02:59", "throughput": 2897.95, "total_tokens": 3578232} {"current_steps": 5475, "total_steps": 38160, "loss": 0.4599, "lr": 4.971302476027982e-05, "epoch": 2.869496855345912, "percentage": 14.35, "elapsed_time": "0:20:35", "remaining_time": "2:02:57", "throughput": 2897.92, "total_tokens": 3581304} {"current_steps": 5480, "total_steps": 38160, "loss": 0.3561, "lr": 4.971129464266884e-05, "epoch": 2.8721174004192873, "percentage": 14.36, "elapsed_time": "0:20:36", "remaining_time": "2:02:56", "throughput": 2897.93, "total_tokens": 3584664} {"current_steps": 5485, "total_steps": 38160, "loss": 0.5177, "lr": 4.970955935573693e-05, "epoch": 2.8747379454926625, "percentage": 14.37, "elapsed_time": "0:20:38", "remaining_time": "2:02:54", "throughput": 2897.85, "total_tokens": 3587544} {"current_steps": 5490, "total_steps": 38160, "loss": 0.4722, "lr": 4.9707818899847106e-05, "epoch": 2.8773584905660377, "percentage": 14.39, "elapsed_time": "0:20:39", "remaining_time": "2:02:53", "throughput": 2897.73, "total_tokens": 3590360} {"current_steps": 5495, "total_steps": 38160, "loss": 0.3771, "lr": 4.970607327536346e-05, "epoch": 2.879979035639413, "percentage": 14.4, "elapsed_time": "0:20:40", "remaining_time": "2:02:57", "throughput": 2898.68, "total_tokens": 3597208} {"current_steps": 5500, "total_steps": 38160, "loss": 0.3601, "lr": 4.970432248265114e-05, "epoch": 2.882599580712788, "percentage": 14.41, "elapsed_time": "0:20:42", "remaining_time": "2:02:55", "throughput": 2898.73, "total_tokens": 3600568} {"current_steps": 5505, "total_steps": 38160, "loss": 0.422, "lr": 4.97025665220764e-05, "epoch": 2.8852201257861636, "percentage": 14.43, "elapsed_time": "0:20:43", "remaining_time": "2:02:54", "throughput": 2898.45, "total_tokens": 3603480} {"current_steps": 5510, "total_steps": 38160, "loss": 0.4958, "lr": 4.970080539400656e-05, "epoch": 2.8878406708595388, "percentage": 14.44, "elapsed_time": "0:20:44", "remaining_time": "2:02:53", "throughput": 2898.32, "total_tokens": 3606360} {"current_steps": 5515, "total_steps": 38160, "loss": 0.4084, "lr": 4.969903909881004e-05, "epoch": 2.890461215932914, "percentage": 14.45, "elapsed_time": "0:20:45", "remaining_time": "2:02:51", "throughput": 2897.82, "total_tokens": 3608856} {"current_steps": 5520, "total_steps": 38160, "loss": 0.3629, "lr": 4.9697267636856317e-05, "epoch": 2.8930817610062896, "percentage": 14.47, "elapsed_time": "0:20:46", "remaining_time": "2:02:49", "throughput": 2897.47, "total_tokens": 3611384} {"current_steps": 5525, "total_steps": 38160, "loss": 0.6605, "lr": 4.969549100851597e-05, "epoch": 2.8957023060796647, "percentage": 14.48, "elapsed_time": "0:20:47", "remaining_time": "2:02:48", "throughput": 2897.44, "total_tokens": 3614488} {"current_steps": 5530, "total_steps": 38160, "loss": 0.4238, "lr": 4.9693709214160645e-05, "epoch": 2.89832285115304, "percentage": 14.49, "elapsed_time": "0:20:48", "remaining_time": "2:02:47", "throughput": 2897.01, "total_tokens": 3617080} {"current_steps": 5535, "total_steps": 38160, "loss": 0.5431, "lr": 4.969192225416307e-05, "epoch": 2.900943396226415, "percentage": 14.5, "elapsed_time": "0:20:49", "remaining_time": "2:02:46", "throughput": 2897.26, "total_tokens": 3620728} {"current_steps": 5540, "total_steps": 38160, "loss": 0.4894, "lr": 4.969013012889706e-05, "epoch": 2.9035639412997902, "percentage": 14.52, "elapsed_time": "0:20:50", "remaining_time": "2:02:44", "throughput": 2897.5, "total_tokens": 3624184} {"current_steps": 5545, "total_steps": 38160, "loss": 0.3807, "lr": 4.9688332838737504e-05, "epoch": 2.9061844863731654, "percentage": 14.53, "elapsed_time": "0:20:52", "remaining_time": "2:02:44", "throughput": 2898.15, "total_tokens": 3628856} {"current_steps": 5550, "total_steps": 38160, "loss": 0.5035, "lr": 4.9686530384060386e-05, "epoch": 2.908805031446541, "percentage": 14.54, "elapsed_time": "0:20:53", "remaining_time": "2:02:43", "throughput": 2897.99, "total_tokens": 3631800} {"current_steps": 5555, "total_steps": 38160, "loss": 0.4302, "lr": 4.968472276524275e-05, "epoch": 2.911425576519916, "percentage": 14.56, "elapsed_time": "0:20:54", "remaining_time": "2:02:41", "throughput": 2897.9, "total_tokens": 3634680} {"current_steps": 5560, "total_steps": 38160, "loss": 0.371, "lr": 4.9682909982662725e-05, "epoch": 2.9140461215932913, "percentage": 14.57, "elapsed_time": "0:20:55", "remaining_time": "2:02:40", "throughput": 2898.32, "total_tokens": 3638264} {"current_steps": 5565, "total_steps": 38160, "loss": 0.3847, "lr": 4.968109203669953e-05, "epoch": 2.9166666666666665, "percentage": 14.58, "elapsed_time": "0:20:56", "remaining_time": "2:02:38", "throughput": 2898.33, "total_tokens": 3641240} {"current_steps": 5570, "total_steps": 38160, "loss": 0.4821, "lr": 4.967926892773346e-05, "epoch": 2.919287211740042, "percentage": 14.6, "elapsed_time": "0:20:57", "remaining_time": "2:02:36", "throughput": 2897.88, "total_tokens": 3643640} {"current_steps": 5575, "total_steps": 38160, "loss": 0.4486, "lr": 4.967744065614588e-05, "epoch": 2.9219077568134173, "percentage": 14.61, "elapsed_time": "0:20:58", "remaining_time": "2:02:36", "throughput": 2898.62, "total_tokens": 3648088} {"current_steps": 5580, "total_steps": 38160, "loss": 0.4027, "lr": 4.9675607222319255e-05, "epoch": 2.9245283018867925, "percentage": 14.62, "elapsed_time": "0:20:59", "remaining_time": "2:02:34", "throughput": 2898.83, "total_tokens": 3651352} {"current_steps": 5585, "total_steps": 38160, "loss": 0.4693, "lr": 4.967376862663711e-05, "epoch": 2.9271488469601676, "percentage": 14.64, "elapsed_time": "0:21:00", "remaining_time": "2:02:32", "throughput": 2899.48, "total_tokens": 3655288} {"current_steps": 5590, "total_steps": 38160, "loss": 0.4107, "lr": 4.9671924869484064e-05, "epoch": 2.929769392033543, "percentage": 14.65, "elapsed_time": "0:21:01", "remaining_time": "2:02:31", "throughput": 2898.92, "total_tokens": 3657624} {"current_steps": 5595, "total_steps": 38160, "loss": 0.3594, "lr": 4.967007595124581e-05, "epoch": 2.932389937106918, "percentage": 14.66, "elapsed_time": "0:21:02", "remaining_time": "2:02:29", "throughput": 2898.79, "total_tokens": 3660472} {"current_steps": 5600, "total_steps": 38160, "loss": 0.5024, "lr": 4.966822187230911e-05, "epoch": 2.9350104821802936, "percentage": 14.68, "elapsed_time": "0:21:03", "remaining_time": "2:02:28", "throughput": 2899.09, "total_tokens": 3663992} {"current_steps": 5605, "total_steps": 38160, "loss": 0.4662, "lr": 4.966636263306183e-05, "epoch": 2.9376310272536688, "percentage": 14.69, "elapsed_time": "0:21:04", "remaining_time": "2:02:26", "throughput": 2898.58, "total_tokens": 3666424} {"current_steps": 5610, "total_steps": 38160, "loss": 0.5109, "lr": 4.9664498233892895e-05, "epoch": 2.940251572327044, "percentage": 14.7, "elapsed_time": "0:21:05", "remaining_time": "2:02:25", "throughput": 2898.52, "total_tokens": 3669400} {"current_steps": 5615, "total_steps": 38160, "loss": 0.5768, "lr": 4.966262867519232e-05, "epoch": 2.9428721174004195, "percentage": 14.71, "elapsed_time": "0:21:07", "remaining_time": "2:02:23", "throughput": 2898.47, "total_tokens": 3672440} {"current_steps": 5620, "total_steps": 38160, "loss": 0.3352, "lr": 4.966075395735119e-05, "epoch": 2.9454926624737947, "percentage": 14.73, "elapsed_time": "0:21:08", "remaining_time": "2:02:22", "throughput": 2898.55, "total_tokens": 3675704} {"current_steps": 5625, "total_steps": 38160, "loss": 0.5829, "lr": 4.965887408076167e-05, "epoch": 2.94811320754717, "percentage": 14.74, "elapsed_time": "0:21:09", "remaining_time": "2:02:21", "throughput": 2898.8, "total_tokens": 3679160} {"current_steps": 5630, "total_steps": 38160, "loss": 0.4235, "lr": 4.965698904581703e-05, "epoch": 2.950733752620545, "percentage": 14.75, "elapsed_time": "0:21:10", "remaining_time": "2:02:19", "throughput": 2898.96, "total_tokens": 3682328} {"current_steps": 5635, "total_steps": 38160, "loss": 0.4137, "lr": 4.965509885291157e-05, "epoch": 2.95335429769392, "percentage": 14.77, "elapsed_time": "0:21:11", "remaining_time": "2:02:17", "throughput": 2898.91, "total_tokens": 3685240} {"current_steps": 5640, "total_steps": 38160, "loss": 0.5825, "lr": 4.9653203502440716e-05, "epoch": 2.9559748427672954, "percentage": 14.78, "elapsed_time": "0:21:12", "remaining_time": "2:02:15", "throughput": 2898.71, "total_tokens": 3687960} {"current_steps": 5645, "total_steps": 38160, "loss": 0.3604, "lr": 4.965130299480095e-05, "epoch": 2.958595387840671, "percentage": 14.79, "elapsed_time": "0:21:13", "remaining_time": "2:02:14", "throughput": 2899.07, "total_tokens": 3691704} {"current_steps": 5650, "total_steps": 38160, "loss": 0.4874, "lr": 4.9649397330389834e-05, "epoch": 2.961215932914046, "percentage": 14.81, "elapsed_time": "0:21:14", "remaining_time": "2:02:13", "throughput": 2899.57, "total_tokens": 3695416} {"current_steps": 5655, "total_steps": 38160, "loss": 0.4225, "lr": 4.964748650960601e-05, "epoch": 2.9638364779874213, "percentage": 14.82, "elapsed_time": "0:21:15", "remaining_time": "2:02:11", "throughput": 2899.31, "total_tokens": 3698168} {"current_steps": 5660, "total_steps": 38160, "loss": 0.5698, "lr": 4.96455705328492e-05, "epoch": 2.9664570230607965, "percentage": 14.83, "elapsed_time": "0:21:16", "remaining_time": "2:02:10", "throughput": 2899.11, "total_tokens": 3700984} {"current_steps": 5665, "total_steps": 38160, "loss": 0.6134, "lr": 4.964364940052021e-05, "epoch": 2.969077568134172, "percentage": 14.85, "elapsed_time": "0:21:17", "remaining_time": "2:02:09", "throughput": 2899.09, "total_tokens": 3704472} {"current_steps": 5670, "total_steps": 38160, "loss": 0.3615, "lr": 4.964172311302091e-05, "epoch": 2.9716981132075473, "percentage": 14.86, "elapsed_time": "0:21:18", "remaining_time": "2:02:08", "throughput": 2899.43, "total_tokens": 3707960} {"current_steps": 5675, "total_steps": 38160, "loss": 0.455, "lr": 4.9639791670754265e-05, "epoch": 2.9743186582809225, "percentage": 14.87, "elapsed_time": "0:21:19", "remaining_time": "2:02:06", "throughput": 2899.09, "total_tokens": 3710520} {"current_steps": 5680, "total_steps": 38160, "loss": 0.455, "lr": 4.9637855074124305e-05, "epoch": 2.9769392033542976, "percentage": 14.88, "elapsed_time": "0:21:20", "remaining_time": "2:02:04", "throughput": 2899.16, "total_tokens": 3713688} {"current_steps": 5685, "total_steps": 38160, "loss": 0.4238, "lr": 4.963591332353615e-05, "epoch": 2.979559748427673, "percentage": 14.9, "elapsed_time": "0:21:22", "remaining_time": "2:02:05", "throughput": 2898.86, "total_tokens": 3717304} {"current_steps": 5690, "total_steps": 38160, "loss": 0.5001, "lr": 4.9633966419396e-05, "epoch": 2.982180293501048, "percentage": 14.91, "elapsed_time": "0:21:23", "remaining_time": "2:02:04", "throughput": 2899.06, "total_tokens": 3720888} {"current_steps": 5695, "total_steps": 38160, "loss": 0.4824, "lr": 4.96320143621111e-05, "epoch": 2.9848008385744236, "percentage": 14.92, "elapsed_time": "0:21:24", "remaining_time": "2:02:03", "throughput": 2899.31, "total_tokens": 3724888} {"current_steps": 5700, "total_steps": 38160, "loss": 0.3644, "lr": 4.963005715208981e-05, "epoch": 2.9874213836477987, "percentage": 14.94, "elapsed_time": "0:21:25", "remaining_time": "2:02:02", "throughput": 2898.73, "total_tokens": 3727288} {"current_steps": 5705, "total_steps": 38160, "loss": 0.4945, "lr": 4.962809478974157e-05, "epoch": 2.990041928721174, "percentage": 14.95, "elapsed_time": "0:21:26", "remaining_time": "2:02:01", "throughput": 2898.6, "total_tokens": 3730328} {"current_steps": 5710, "total_steps": 38160, "loss": 0.3857, "lr": 4.962612727547686e-05, "epoch": 2.9926624737945495, "percentage": 14.96, "elapsed_time": "0:21:28", "remaining_time": "2:02:00", "throughput": 2898.76, "total_tokens": 3733912} {"current_steps": 5715, "total_steps": 38160, "loss": 0.4194, "lr": 4.962415460970728e-05, "epoch": 2.9952830188679247, "percentage": 14.98, "elapsed_time": "0:21:29", "remaining_time": "2:01:59", "throughput": 2898.92, "total_tokens": 3737464} {"current_steps": 5720, "total_steps": 38160, "loss": 0.4096, "lr": 4.962217679284548e-05, "epoch": 2.9979035639413, "percentage": 14.99, "elapsed_time": "0:21:30", "remaining_time": "2:01:57", "throughput": 2898.66, "total_tokens": 3740152} {"current_steps": 5724, "total_steps": 38160, "eval_loss": 0.4691515564918518, "epoch": 3.0, "percentage": 15.0, "elapsed_time": "0:21:42", "remaining_time": "2:03:03", "throughput": 2872.28, "total_tokens": 3742552} {"current_steps": 5725, "total_steps": 38160, "loss": 0.3653, "lr": 4.962019382530521e-05, "epoch": 3.000524109014675, "percentage": 15.0, "elapsed_time": "0:21:46", "remaining_time": "2:03:22", "throughput": 2864.79, "total_tokens": 3742968} {"current_steps": 5730, "total_steps": 38160, "loss": 0.4309, "lr": 4.9618205707501256e-05, "epoch": 3.00314465408805, "percentage": 15.02, "elapsed_time": "0:21:47", "remaining_time": "2:03:20", "throughput": 2864.56, "total_tokens": 3745880} {"current_steps": 5735, "total_steps": 38160, "loss": 0.442, "lr": 4.961621243984954e-05, "epoch": 3.0057651991614254, "percentage": 15.03, "elapsed_time": "0:21:48", "remaining_time": "2:03:20", "throughput": 2864.68, "total_tokens": 3749464} {"current_steps": 5740, "total_steps": 38160, "loss": 0.3473, "lr": 4.9614214022767014e-05, "epoch": 3.008385744234801, "percentage": 15.04, "elapsed_time": "0:21:49", "remaining_time": "2:03:18", "throughput": 2864.39, "total_tokens": 3752248} {"current_steps": 5745, "total_steps": 38160, "loss": 0.4173, "lr": 4.9612210456671735e-05, "epoch": 3.011006289308176, "percentage": 15.06, "elapsed_time": "0:21:51", "remaining_time": "2:03:17", "throughput": 2864.28, "total_tokens": 3755480} {"current_steps": 5750, "total_steps": 38160, "loss": 0.3776, "lr": 4.961020174198281e-05, "epoch": 3.0136268343815513, "percentage": 15.07, "elapsed_time": "0:21:52", "remaining_time": "2:03:16", "throughput": 2863.79, "total_tokens": 3758040} {"current_steps": 5755, "total_steps": 38160, "loss": 0.3944, "lr": 4.9608187879120454e-05, "epoch": 3.0162473794549265, "percentage": 15.08, "elapsed_time": "0:21:53", "remaining_time": "2:03:15", "throughput": 2863.9, "total_tokens": 3761368} {"current_steps": 5760, "total_steps": 38160, "loss": 0.3949, "lr": 4.9606168868505936e-05, "epoch": 3.018867924528302, "percentage": 15.09, "elapsed_time": "0:21:54", "remaining_time": "2:03:14", "throughput": 2864.03, "total_tokens": 3764824} {"current_steps": 5765, "total_steps": 38160, "loss": 0.3229, "lr": 4.9604144710561616e-05, "epoch": 3.0214884696016773, "percentage": 15.11, "elapsed_time": "0:21:55", "remaining_time": "2:03:12", "throughput": 2864.02, "total_tokens": 3768056} {"current_steps": 5770, "total_steps": 38160, "loss": 0.4283, "lr": 4.960211540571092e-05, "epoch": 3.0241090146750524, "percentage": 15.12, "elapsed_time": "0:21:56", "remaining_time": "2:03:11", "throughput": 2863.27, "total_tokens": 3770168} {"current_steps": 5775, "total_steps": 38160, "loss": 0.4203, "lr": 4.960008095437836e-05, "epoch": 3.0267295597484276, "percentage": 15.13, "elapsed_time": "0:21:57", "remaining_time": "2:03:10", "throughput": 2863.17, "total_tokens": 3773112} {"current_steps": 5780, "total_steps": 38160, "loss": 0.4486, "lr": 4.959804135698951e-05, "epoch": 3.029350104821803, "percentage": 15.15, "elapsed_time": "0:21:58", "remaining_time": "2:03:08", "throughput": 2863.39, "total_tokens": 3776568} {"current_steps": 5785, "total_steps": 38160, "loss": 0.5663, "lr": 4.959599661397104e-05, "epoch": 3.0319706498951784, "percentage": 15.16, "elapsed_time": "0:22:00", "remaining_time": "2:03:08", "throughput": 2863.96, "total_tokens": 3780920} {"current_steps": 5790, "total_steps": 38160, "loss": 0.4622, "lr": 4.959394672575068e-05, "epoch": 3.0345911949685536, "percentage": 15.17, "elapsed_time": "0:22:01", "remaining_time": "2:03:06", "throughput": 2863.85, "total_tokens": 3783960} {"current_steps": 5795, "total_steps": 38160, "loss": 0.3683, "lr": 4.959189169275725e-05, "epoch": 3.0372117400419287, "percentage": 15.19, "elapsed_time": "0:22:02", "remaining_time": "2:03:04", "throughput": 2863.94, "total_tokens": 3786968} {"current_steps": 5800, "total_steps": 38160, "loss": 0.4642, "lr": 4.958983151542065e-05, "epoch": 3.039832285115304, "percentage": 15.2, "elapsed_time": "0:22:03", "remaining_time": "2:03:03", "throughput": 2864.51, "total_tokens": 3790808} {"current_steps": 5805, "total_steps": 38160, "loss": 0.4103, "lr": 4.958776619417182e-05, "epoch": 3.042452830188679, "percentage": 15.21, "elapsed_time": "0:22:04", "remaining_time": "2:03:01", "throughput": 2864.89, "total_tokens": 3794264} {"current_steps": 5810, "total_steps": 38160, "loss": 0.4381, "lr": 4.9585695729442814e-05, "epoch": 3.0450733752620547, "percentage": 15.23, "elapsed_time": "0:22:05", "remaining_time": "2:02:59", "throughput": 2865.1, "total_tokens": 3797496} {"current_steps": 5815, "total_steps": 38160, "loss": 0.5496, "lr": 4.9583620121666754e-05, "epoch": 3.04769392033543, "percentage": 15.24, "elapsed_time": "0:22:06", "remaining_time": "2:02:58", "throughput": 2865.32, "total_tokens": 3800888} {"current_steps": 5820, "total_steps": 38160, "loss": 0.3588, "lr": 4.958153937127783e-05, "epoch": 3.050314465408805, "percentage": 15.25, "elapsed_time": "0:22:07", "remaining_time": "2:02:56", "throughput": 2865.07, "total_tokens": 3803512} {"current_steps": 5825, "total_steps": 38160, "loss": 0.4768, "lr": 4.95794534787113e-05, "epoch": 3.05293501048218, "percentage": 15.26, "elapsed_time": "0:22:08", "remaining_time": "2:02:55", "throughput": 2865.03, "total_tokens": 3806552} {"current_steps": 5830, "total_steps": 38160, "loss": 0.4564, "lr": 4.957736244440353e-05, "epoch": 3.0555555555555554, "percentage": 15.28, "elapsed_time": "0:22:09", "remaining_time": "2:02:54", "throughput": 2865.4, "total_tokens": 3810648} {"current_steps": 5835, "total_steps": 38160, "loss": 0.345, "lr": 4.957526626879193e-05, "epoch": 3.058176100628931, "percentage": 15.29, "elapsed_time": "0:22:10", "remaining_time": "2:02:53", "throughput": 2865.5, "total_tokens": 3813976} {"current_steps": 5840, "total_steps": 38160, "loss": 0.4392, "lr": 4.957316495231499e-05, "epoch": 3.060796645702306, "percentage": 15.3, "elapsed_time": "0:22:12", "remaining_time": "2:02:51", "throughput": 2865.34, "total_tokens": 3816824} {"current_steps": 5845, "total_steps": 38160, "loss": 0.4857, "lr": 4.9571058495412294e-05, "epoch": 3.0634171907756813, "percentage": 15.32, "elapsed_time": "0:22:13", "remaining_time": "2:02:50", "throughput": 2865.51, "total_tokens": 3820376} {"current_steps": 5850, "total_steps": 38160, "loss": 0.3612, "lr": 4.9568946898524485e-05, "epoch": 3.0660377358490565, "percentage": 15.33, "elapsed_time": "0:22:14", "remaining_time": "2:02:49", "throughput": 2865.68, "total_tokens": 3823736} {"current_steps": 5855, "total_steps": 38160, "loss": 0.5631, "lr": 4.956683016209327e-05, "epoch": 3.068658280922432, "percentage": 15.34, "elapsed_time": "0:22:15", "remaining_time": "2:02:47", "throughput": 2865.2, "total_tokens": 3826104} {"current_steps": 5860, "total_steps": 38160, "loss": 0.4481, "lr": 4.956470828656147e-05, "epoch": 3.0712788259958073, "percentage": 15.36, "elapsed_time": "0:22:16", "remaining_time": "2:02:46", "throughput": 2864.81, "total_tokens": 3828632} {"current_steps": 5865, "total_steps": 38160, "loss": 0.2636, "lr": 4.956258127237294e-05, "epoch": 3.0738993710691824, "percentage": 15.37, "elapsed_time": "0:22:17", "remaining_time": "2:02:44", "throughput": 2864.79, "total_tokens": 3831576} {"current_steps": 5870, "total_steps": 38160, "loss": 0.3099, "lr": 4.956044911997263e-05, "epoch": 3.0765199161425576, "percentage": 15.38, "elapsed_time": "0:22:18", "remaining_time": "2:02:43", "throughput": 2864.63, "total_tokens": 3834392} {"current_steps": 5875, "total_steps": 38160, "loss": 0.4683, "lr": 4.955831182980657e-05, "epoch": 3.0791404612159328, "percentage": 15.4, "elapsed_time": "0:22:19", "remaining_time": "2:02:41", "throughput": 2864.42, "total_tokens": 3837144} {"current_steps": 5880, "total_steps": 38160, "loss": 0.4522, "lr": 4.955616940232185e-05, "epoch": 3.0817610062893084, "percentage": 15.41, "elapsed_time": "0:22:20", "remaining_time": "2:02:40", "throughput": 2864.5, "total_tokens": 3840504} {"current_steps": 5885, "total_steps": 38160, "loss": 0.4518, "lr": 4.9554021837966636e-05, "epoch": 3.0843815513626835, "percentage": 15.42, "elapsed_time": "0:22:21", "remaining_time": "2:02:38", "throughput": 2865.07, "total_tokens": 3844408} {"current_steps": 5890, "total_steps": 38160, "loss": 0.4484, "lr": 4.955186913719019e-05, "epoch": 3.0870020964360587, "percentage": 15.44, "elapsed_time": "0:22:22", "remaining_time": "2:02:37", "throughput": 2865.23, "total_tokens": 3847736} {"current_steps": 5895, "total_steps": 38160, "loss": 0.4123, "lr": 4.954971130044281e-05, "epoch": 3.089622641509434, "percentage": 15.45, "elapsed_time": "0:22:23", "remaining_time": "2:02:36", "throughput": 2864.86, "total_tokens": 3850360} {"current_steps": 5900, "total_steps": 38160, "loss": 0.3925, "lr": 4.954754832817592e-05, "epoch": 3.092243186582809, "percentage": 15.46, "elapsed_time": "0:22:25", "remaining_time": "2:02:34", "throughput": 2865.09, "total_tokens": 3853624} {"current_steps": 5905, "total_steps": 38160, "loss": 0.3107, "lr": 4.954538022084196e-05, "epoch": 3.0948637316561847, "percentage": 15.47, "elapsed_time": "0:22:26", "remaining_time": "2:02:32", "throughput": 2865.17, "total_tokens": 3856664} {"current_steps": 5910, "total_steps": 38160, "loss": 0.4519, "lr": 4.9543206978894496e-05, "epoch": 3.09748427672956, "percentage": 15.49, "elapsed_time": "0:22:27", "remaining_time": "2:02:30", "throughput": 2865.24, "total_tokens": 3859640} {"current_steps": 5915, "total_steps": 38160, "loss": 0.3291, "lr": 4.954102860278813e-05, "epoch": 3.100104821802935, "percentage": 15.5, "elapsed_time": "0:22:28", "remaining_time": "2:02:29", "throughput": 2865.31, "total_tokens": 3862712} {"current_steps": 5920, "total_steps": 38160, "loss": 0.3965, "lr": 4.9538845092978567e-05, "epoch": 3.10272536687631, "percentage": 15.51, "elapsed_time": "0:22:29", "remaining_time": "2:02:28", "throughput": 2865.51, "total_tokens": 3866328} {"current_steps": 5925, "total_steps": 38160, "loss": 0.3726, "lr": 4.953665644992256e-05, "epoch": 3.1053459119496853, "percentage": 15.53, "elapsed_time": "0:22:30", "remaining_time": "2:02:26", "throughput": 2865.56, "total_tokens": 3869592} {"current_steps": 5930, "total_steps": 38160, "loss": 0.3228, "lr": 4.953446267407795e-05, "epoch": 3.107966457023061, "percentage": 15.54, "elapsed_time": "0:22:31", "remaining_time": "2:02:27", "throughput": 2866.45, "total_tokens": 3875032} {"current_steps": 5935, "total_steps": 38160, "loss": 0.465, "lr": 4.953226376590365e-05, "epoch": 3.110587002096436, "percentage": 15.55, "elapsed_time": "0:22:33", "remaining_time": "2:02:26", "throughput": 2867.16, "total_tokens": 3879288} {"current_steps": 5940, "total_steps": 38160, "loss": 0.2998, "lr": 4.953005972585965e-05, "epoch": 3.1132075471698113, "percentage": 15.57, "elapsed_time": "0:22:34", "remaining_time": "2:02:24", "throughput": 2867.56, "total_tokens": 3882936} {"current_steps": 5945, "total_steps": 38160, "loss": 0.4337, "lr": 4.952785055440701e-05, "epoch": 3.1158280922431865, "percentage": 15.58, "elapsed_time": "0:22:35", "remaining_time": "2:02:23", "throughput": 2867.8, "total_tokens": 3886296} {"current_steps": 5950, "total_steps": 38160, "loss": 0.394, "lr": 4.9525636252007864e-05, "epoch": 3.1184486373165616, "percentage": 15.59, "elapsed_time": "0:22:36", "remaining_time": "2:02:22", "throughput": 2867.99, "total_tokens": 3889816} {"current_steps": 5955, "total_steps": 38160, "loss": 0.3279, "lr": 4.9523416819125425e-05, "epoch": 3.1210691823899372, "percentage": 15.61, "elapsed_time": "0:22:37", "remaining_time": "2:02:20", "throughput": 2867.97, "total_tokens": 3892888} {"current_steps": 5960, "total_steps": 38160, "loss": 0.4827, "lr": 4.952119225622396e-05, "epoch": 3.1236897274633124, "percentage": 15.62, "elapsed_time": "0:22:38", "remaining_time": "2:02:19", "throughput": 2867.86, "total_tokens": 3896152} {"current_steps": 5965, "total_steps": 38160, "loss": 0.2892, "lr": 4.951896256376882e-05, "epoch": 3.1263102725366876, "percentage": 15.63, "elapsed_time": "0:22:39", "remaining_time": "2:02:18", "throughput": 2867.54, "total_tokens": 3898776} {"current_steps": 5970, "total_steps": 38160, "loss": 0.4066, "lr": 4.9516727742226444e-05, "epoch": 3.1289308176100628, "percentage": 15.64, "elapsed_time": "0:22:40", "remaining_time": "2:02:16", "throughput": 2867.66, "total_tokens": 3901912} {"current_steps": 5975, "total_steps": 38160, "loss": 0.4755, "lr": 4.9514487792064323e-05, "epoch": 3.131551362683438, "percentage": 15.66, "elapsed_time": "0:22:41", "remaining_time": "2:02:15", "throughput": 2868.07, "total_tokens": 3905688} {"current_steps": 5980, "total_steps": 38160, "loss": 0.4183, "lr": 4.951224271375104e-05, "epoch": 3.1341719077568135, "percentage": 15.67, "elapsed_time": "0:22:42", "remaining_time": "2:02:13", "throughput": 2868.21, "total_tokens": 3908888} {"current_steps": 5985, "total_steps": 38160, "loss": 0.3486, "lr": 4.950999250775623e-05, "epoch": 3.1367924528301887, "percentage": 15.68, "elapsed_time": "0:22:43", "remaining_time": "2:02:12", "throughput": 2868.46, "total_tokens": 3912280} {"current_steps": 5990, "total_steps": 38160, "loss": 0.363, "lr": 4.950773717455061e-05, "epoch": 3.139412997903564, "percentage": 15.7, "elapsed_time": "0:22:45", "remaining_time": "2:02:11", "throughput": 2868.21, "total_tokens": 3915256} {"current_steps": 5995, "total_steps": 38160, "loss": 0.3716, "lr": 4.950547671460596e-05, "epoch": 3.142033542976939, "percentage": 15.71, "elapsed_time": "0:22:46", "remaining_time": "2:02:09", "throughput": 2867.92, "total_tokens": 3917912} {"current_steps": 6000, "total_steps": 38160, "loss": 0.4402, "lr": 4.950321112839517e-05, "epoch": 3.1446540880503147, "percentage": 15.72, "elapsed_time": "0:22:47", "remaining_time": "2:02:08", "throughput": 2867.75, "total_tokens": 3920824} {"current_steps": 6005, "total_steps": 38160, "loss": 0.3489, "lr": 4.9500940416392156e-05, "epoch": 3.14727463312369, "percentage": 15.74, "elapsed_time": "0:22:48", "remaining_time": "2:02:06", "throughput": 2867.63, "total_tokens": 3923736} {"current_steps": 6010, "total_steps": 38160, "loss": 0.4663, "lr": 4.949866457907193e-05, "epoch": 3.149895178197065, "percentage": 15.75, "elapsed_time": "0:22:49", "remaining_time": "2:02:05", "throughput": 2867.48, "total_tokens": 3926584} {"current_steps": 6015, "total_steps": 38160, "loss": 0.5519, "lr": 4.9496383616910565e-05, "epoch": 3.15251572327044, "percentage": 15.76, "elapsed_time": "0:22:50", "remaining_time": "2:02:03", "throughput": 2867.33, "total_tokens": 3929432} {"current_steps": 6020, "total_steps": 38160, "loss": 0.4338, "lr": 4.949409753038522e-05, "epoch": 3.1551362683438153, "percentage": 15.78, "elapsed_time": "0:22:51", "remaining_time": "2:02:02", "throughput": 2867.03, "total_tokens": 3932088} {"current_steps": 6025, "total_steps": 38160, "loss": 0.3634, "lr": 4.949180631997411e-05, "epoch": 3.157756813417191, "percentage": 15.79, "elapsed_time": "0:22:52", "remaining_time": "2:02:00", "throughput": 2867.09, "total_tokens": 3935384} {"current_steps": 6030, "total_steps": 38160, "loss": 0.3952, "lr": 4.948950998615654e-05, "epoch": 3.160377358490566, "percentage": 15.8, "elapsed_time": "0:22:53", "remaining_time": "2:01:59", "throughput": 2867.12, "total_tokens": 3938424} {"current_steps": 6035, "total_steps": 38160, "loss": 0.4435, "lr": 4.9487208529412876e-05, "epoch": 3.1629979035639413, "percentage": 15.81, "elapsed_time": "0:22:54", "remaining_time": "2:01:57", "throughput": 2866.78, "total_tokens": 3940984} {"current_steps": 6040, "total_steps": 38160, "loss": 0.3919, "lr": 4.9484901950224546e-05, "epoch": 3.1656184486373165, "percentage": 15.83, "elapsed_time": "0:22:55", "remaining_time": "2:01:56", "throughput": 2867.42, "total_tokens": 3945144} {"current_steps": 6045, "total_steps": 38160, "loss": 0.3984, "lr": 4.948259024907407e-05, "epoch": 3.1682389937106916, "percentage": 15.84, "elapsed_time": "0:22:56", "remaining_time": "2:01:55", "throughput": 2867.49, "total_tokens": 3948344} {"current_steps": 6050, "total_steps": 38160, "loss": 0.4742, "lr": 4.948027342644502e-05, "epoch": 3.1708595387840672, "percentage": 15.85, "elapsed_time": "0:22:58", "remaining_time": "2:01:53", "throughput": 2867.19, "total_tokens": 3951000} {"current_steps": 6055, "total_steps": 38160, "loss": 0.3849, "lr": 4.947795148282206e-05, "epoch": 3.1734800838574424, "percentage": 15.87, "elapsed_time": "0:22:59", "remaining_time": "2:01:52", "throughput": 2867.6, "total_tokens": 3954584} {"current_steps": 6060, "total_steps": 38160, "loss": 0.271, "lr": 4.947562441869091e-05, "epoch": 3.1761006289308176, "percentage": 15.88, "elapsed_time": "0:23:00", "remaining_time": "2:01:50", "throughput": 2867.7, "total_tokens": 3957944} {"current_steps": 6065, "total_steps": 38160, "loss": 0.3544, "lr": 4.947329223453836e-05, "epoch": 3.1787211740041927, "percentage": 15.89, "elapsed_time": "0:23:01", "remaining_time": "2:01:49", "throughput": 2868.32, "total_tokens": 3961816} {"current_steps": 6070, "total_steps": 38160, "loss": 0.4257, "lr": 4.947095493085229e-05, "epoch": 3.181341719077568, "percentage": 15.91, "elapsed_time": "0:23:02", "remaining_time": "2:01:47", "throughput": 2868.35, "total_tokens": 3964824} {"current_steps": 6075, "total_steps": 38160, "loss": 0.3228, "lr": 4.9468612508121616e-05, "epoch": 3.1839622641509435, "percentage": 15.92, "elapsed_time": "0:23:03", "remaining_time": "2:01:46", "throughput": 2868.44, "total_tokens": 3968056} {"current_steps": 6080, "total_steps": 38160, "loss": 0.3893, "lr": 4.9466264966836365e-05, "epoch": 3.1865828092243187, "percentage": 15.93, "elapsed_time": "0:23:04", "remaining_time": "2:01:44", "throughput": 2867.97, "total_tokens": 3970424} {"current_steps": 6085, "total_steps": 38160, "loss": 0.3751, "lr": 4.94639123074876e-05, "epoch": 3.189203354297694, "percentage": 15.95, "elapsed_time": "0:23:05", "remaining_time": "2:01:42", "throughput": 2867.81, "total_tokens": 3973208} {"current_steps": 6090, "total_steps": 38160, "loss": 0.4302, "lr": 4.946155453056749e-05, "epoch": 3.191823899371069, "percentage": 15.96, "elapsed_time": "0:23:06", "remaining_time": "2:01:41", "throughput": 2867.78, "total_tokens": 3976216} {"current_steps": 6095, "total_steps": 38160, "loss": 0.4785, "lr": 4.945919163656923e-05, "epoch": 3.1944444444444446, "percentage": 15.97, "elapsed_time": "0:23:07", "remaining_time": "2:01:40", "throughput": 2868.52, "total_tokens": 3980824} {"current_steps": 6100, "total_steps": 38160, "loss": 0.4607, "lr": 4.945682362598715e-05, "epoch": 3.19706498951782, "percentage": 15.99, "elapsed_time": "0:23:09", "remaining_time": "2:01:43", "throughput": 2869.4, "total_tokens": 3987480} {"current_steps": 6105, "total_steps": 38160, "loss": 0.3952, "lr": 4.945445049931656e-05, "epoch": 3.199685534591195, "percentage": 16.0, "elapsed_time": "0:23:10", "remaining_time": "2:01:42", "throughput": 2869.95, "total_tokens": 3991288} {"current_steps": 6110, "total_steps": 38160, "loss": 0.4676, "lr": 4.945207225705393e-05, "epoch": 3.20230607966457, "percentage": 16.01, "elapsed_time": "0:23:11", "remaining_time": "2:01:40", "throughput": 2869.64, "total_tokens": 3993848} {"current_steps": 6115, "total_steps": 38160, "loss": 0.4151, "lr": 4.944968889969674e-05, "epoch": 3.2049266247379453, "percentage": 16.02, "elapsed_time": "0:23:12", "remaining_time": "2:01:38", "throughput": 2870.37, "total_tokens": 3997848} {"current_steps": 6120, "total_steps": 38160, "loss": 0.3466, "lr": 4.944730042774358e-05, "epoch": 3.207547169811321, "percentage": 16.04, "elapsed_time": "0:23:13", "remaining_time": "2:01:37", "throughput": 2870.82, "total_tokens": 4001784} {"current_steps": 6125, "total_steps": 38160, "loss": 0.4212, "lr": 4.944490684169408e-05, "epoch": 3.210167714884696, "percentage": 16.05, "elapsed_time": "0:23:14", "remaining_time": "2:01:36", "throughput": 2871.03, "total_tokens": 4005048} {"current_steps": 6130, "total_steps": 38160, "loss": 0.4376, "lr": 4.9442508142048945e-05, "epoch": 3.2127882599580713, "percentage": 16.06, "elapsed_time": "0:23:16", "remaining_time": "2:01:34", "throughput": 2870.91, "total_tokens": 4007864} {"current_steps": 6135, "total_steps": 38160, "loss": 0.4366, "lr": 4.9440104329309956e-05, "epoch": 3.2154088050314464, "percentage": 16.08, "elapsed_time": "0:23:17", "remaining_time": "2:01:32", "throughput": 2871.52, "total_tokens": 4011832} {"current_steps": 6140, "total_steps": 38160, "loss": 0.3964, "lr": 4.943769540397998e-05, "epoch": 3.2180293501048216, "percentage": 16.09, "elapsed_time": "0:23:18", "remaining_time": "2:01:31", "throughput": 2871.65, "total_tokens": 4015032} {"current_steps": 6145, "total_steps": 38160, "loss": 0.548, "lr": 4.943528136656292e-05, "epoch": 3.220649895178197, "percentage": 16.1, "elapsed_time": "0:23:19", "remaining_time": "2:01:29", "throughput": 2871.19, "total_tokens": 4017432} {"current_steps": 6150, "total_steps": 38160, "loss": 0.3397, "lr": 4.943286221756377e-05, "epoch": 3.2232704402515724, "percentage": 16.12, "elapsed_time": "0:23:20", "remaining_time": "2:01:28", "throughput": 2871.05, "total_tokens": 4020216} {"current_steps": 6155, "total_steps": 38160, "loss": 0.4598, "lr": 4.9430437957488586e-05, "epoch": 3.2258909853249476, "percentage": 16.13, "elapsed_time": "0:23:21", "remaining_time": "2:01:26", "throughput": 2870.98, "total_tokens": 4023096} {"current_steps": 6160, "total_steps": 38160, "loss": 0.288, "lr": 4.94280085868445e-05, "epoch": 3.2285115303983227, "percentage": 16.14, "elapsed_time": "0:23:22", "remaining_time": "2:01:25", "throughput": 2871.25, "total_tokens": 4026712} {"current_steps": 6165, "total_steps": 38160, "loss": 0.4527, "lr": 4.942557410613972e-05, "epoch": 3.231132075471698, "percentage": 16.16, "elapsed_time": "0:23:23", "remaining_time": "2:01:24", "throughput": 2871.78, "total_tokens": 4030872} {"current_steps": 6170, "total_steps": 38160, "loss": 0.3841, "lr": 4.942313451588348e-05, "epoch": 3.2337526205450735, "percentage": 16.17, "elapsed_time": "0:23:24", "remaining_time": "2:01:23", "throughput": 2872.23, "total_tokens": 4034744} {"current_steps": 6175, "total_steps": 38160, "loss": 0.3802, "lr": 4.942068981658614e-05, "epoch": 3.2363731656184487, "percentage": 16.18, "elapsed_time": "0:23:25", "remaining_time": "2:01:21", "throughput": 2872.24, "total_tokens": 4037752} {"current_steps": 6180, "total_steps": 38160, "loss": 0.3363, "lr": 4.9418240008759097e-05, "epoch": 3.238993710691824, "percentage": 16.19, "elapsed_time": "0:23:26", "remaining_time": "2:01:20", "throughput": 2872.4, "total_tokens": 4041048} {"current_steps": 6185, "total_steps": 38160, "loss": 0.4944, "lr": 4.9415785092914826e-05, "epoch": 3.241614255765199, "percentage": 16.21, "elapsed_time": "0:23:27", "remaining_time": "2:01:18", "throughput": 2872.16, "total_tokens": 4043832} {"current_steps": 6190, "total_steps": 38160, "loss": 0.354, "lr": 4.941332506956686e-05, "epoch": 3.2442348008385746, "percentage": 16.22, "elapsed_time": "0:23:29", "remaining_time": "2:01:17", "throughput": 2872.46, "total_tokens": 4047512} {"current_steps": 6195, "total_steps": 38160, "loss": 0.4302, "lr": 4.941085993922981e-05, "epoch": 3.24685534591195, "percentage": 16.23, "elapsed_time": "0:23:30", "remaining_time": "2:01:16", "throughput": 2872.41, "total_tokens": 4050584} {"current_steps": 6200, "total_steps": 38160, "loss": 0.3208, "lr": 4.9408389702419354e-05, "epoch": 3.249475890985325, "percentage": 16.25, "elapsed_time": "0:23:31", "remaining_time": "2:01:14", "throughput": 2872.53, "total_tokens": 4053752} {"current_steps": 6205, "total_steps": 38160, "loss": 0.4292, "lr": 4.940591435965224e-05, "epoch": 3.2520964360587, "percentage": 16.26, "elapsed_time": "0:23:32", "remaining_time": "2:01:13", "throughput": 2872.53, "total_tokens": 4056824} {"current_steps": 6210, "total_steps": 38160, "loss": 0.5357, "lr": 4.9403433911446285e-05, "epoch": 3.2547169811320753, "percentage": 16.27, "elapsed_time": "0:23:33", "remaining_time": "2:01:11", "throughput": 2872.51, "total_tokens": 4059864} {"current_steps": 6215, "total_steps": 38160, "loss": 0.3757, "lr": 4.9400948358320356e-05, "epoch": 3.257337526205451, "percentage": 16.29, "elapsed_time": "0:23:34", "remaining_time": "2:01:10", "throughput": 2872.87, "total_tokens": 4063416} {"current_steps": 6220, "total_steps": 38160, "loss": 0.354, "lr": 4.939845770079442e-05, "epoch": 3.259958071278826, "percentage": 16.3, "elapsed_time": "0:23:35", "remaining_time": "2:01:08", "throughput": 2872.71, "total_tokens": 4066264} {"current_steps": 6225, "total_steps": 38160, "loss": 0.4171, "lr": 4.9395961939389475e-05, "epoch": 3.2625786163522013, "percentage": 16.31, "elapsed_time": "0:23:36", "remaining_time": "2:01:07", "throughput": 2872.24, "total_tokens": 4068664} {"current_steps": 6230, "total_steps": 38160, "loss": 0.6004, "lr": 4.939346107462762e-05, "epoch": 3.2651991614255764, "percentage": 16.33, "elapsed_time": "0:23:37", "remaining_time": "2:01:05", "throughput": 2872.55, "total_tokens": 4072088} {"current_steps": 6235, "total_steps": 38160, "loss": 0.5474, "lr": 4.9390955107032e-05, "epoch": 3.2678197064989516, "percentage": 16.34, "elapsed_time": "0:23:38", "remaining_time": "2:01:03", "throughput": 2872.53, "total_tokens": 4075064} {"current_steps": 6240, "total_steps": 38160, "loss": 0.4212, "lr": 4.938844403712685e-05, "epoch": 3.270440251572327, "percentage": 16.35, "elapsed_time": "0:23:39", "remaining_time": "2:01:02", "throughput": 2872.34, "total_tokens": 4077752} {"current_steps": 6245, "total_steps": 38160, "loss": 0.4218, "lr": 4.938592786543743e-05, "epoch": 3.2730607966457024, "percentage": 16.37, "elapsed_time": "0:23:40", "remaining_time": "2:01:00", "throughput": 2872.02, "total_tokens": 4080472} {"current_steps": 6250, "total_steps": 38160, "loss": 0.317, "lr": 4.938340659249012e-05, "epoch": 3.2756813417190775, "percentage": 16.38, "elapsed_time": "0:23:41", "remaining_time": "2:00:59", "throughput": 2871.98, "total_tokens": 4083384} {"current_steps": 6255, "total_steps": 38160, "loss": 0.4453, "lr": 4.938088021881233e-05, "epoch": 3.2783018867924527, "percentage": 16.39, "elapsed_time": "0:23:42", "remaining_time": "2:00:57", "throughput": 2872.07, "total_tokens": 4086488} {"current_steps": 6260, "total_steps": 38160, "loss": 0.2871, "lr": 4.937834874493255e-05, "epoch": 3.280922431865828, "percentage": 16.4, "elapsed_time": "0:23:43", "remaining_time": "2:00:56", "throughput": 2871.87, "total_tokens": 4089464} {"current_steps": 6265, "total_steps": 38160, "loss": 0.4575, "lr": 4.9375812171380334e-05, "epoch": 3.2835429769392035, "percentage": 16.42, "elapsed_time": "0:23:45", "remaining_time": "2:00:55", "throughput": 2871.5, "total_tokens": 4092088} {"current_steps": 6270, "total_steps": 38160, "loss": 0.3867, "lr": 4.9373270498686306e-05, "epoch": 3.2861635220125787, "percentage": 16.43, "elapsed_time": "0:23:46", "remaining_time": "2:00:54", "throughput": 2871.48, "total_tokens": 4095544} {"current_steps": 6275, "total_steps": 38160, "loss": 0.4252, "lr": 4.937072372738216e-05, "epoch": 3.288784067085954, "percentage": 16.44, "elapsed_time": "0:23:47", "remaining_time": "2:00:52", "throughput": 2871.27, "total_tokens": 4098264} {"current_steps": 6280, "total_steps": 38160, "loss": 0.3939, "lr": 4.9368171858000635e-05, "epoch": 3.291404612159329, "percentage": 16.46, "elapsed_time": "0:23:48", "remaining_time": "2:00:51", "throughput": 2870.82, "total_tokens": 4100792} {"current_steps": 6285, "total_steps": 38160, "loss": 0.3711, "lr": 4.9365614891075576e-05, "epoch": 3.2940251572327046, "percentage": 16.47, "elapsed_time": "0:23:49", "remaining_time": "2:00:50", "throughput": 2870.79, "total_tokens": 4103896} {"current_steps": 6290, "total_steps": 38160, "loss": 0.3177, "lr": 4.936305282714185e-05, "epoch": 3.29664570230608, "percentage": 16.48, "elapsed_time": "0:23:50", "remaining_time": "2:00:48", "throughput": 2870.75, "total_tokens": 4106968} {"current_steps": 6295, "total_steps": 38160, "loss": 0.475, "lr": 4.936048566673542e-05, "epoch": 3.299266247379455, "percentage": 16.5, "elapsed_time": "0:23:51", "remaining_time": "2:00:47", "throughput": 2870.72, "total_tokens": 4110040} {"current_steps": 6300, "total_steps": 38160, "loss": 0.3578, "lr": 4.935791341039332e-05, "epoch": 3.30188679245283, "percentage": 16.51, "elapsed_time": "0:23:52", "remaining_time": "2:00:45", "throughput": 2870.38, "total_tokens": 4112664} {"current_steps": 6305, "total_steps": 38160, "loss": 0.3982, "lr": 4.935533605865361e-05, "epoch": 3.3045073375262053, "percentage": 16.52, "elapsed_time": "0:23:53", "remaining_time": "2:00:44", "throughput": 2870.34, "total_tokens": 4115832} {"current_steps": 6310, "total_steps": 38160, "loss": 0.3742, "lr": 4.935275361205547e-05, "epoch": 3.307127882599581, "percentage": 16.54, "elapsed_time": "0:23:55", "remaining_time": "2:00:43", "throughput": 2870.25, "total_tokens": 4119160} {"current_steps": 6315, "total_steps": 38160, "loss": 0.7292, "lr": 4.93501660711391e-05, "epoch": 3.309748427672956, "percentage": 16.55, "elapsed_time": "0:23:56", "remaining_time": "2:00:42", "throughput": 2870.31, "total_tokens": 4122520} {"current_steps": 6320, "total_steps": 38160, "loss": 0.3988, "lr": 4.934757343644578e-05, "epoch": 3.3123689727463312, "percentage": 16.56, "elapsed_time": "0:23:57", "remaining_time": "2:00:41", "throughput": 2869.81, "total_tokens": 4124888} {"current_steps": 6325, "total_steps": 38160, "loss": 0.4502, "lr": 4.934497570851788e-05, "epoch": 3.3149895178197064, "percentage": 16.57, "elapsed_time": "0:23:58", "remaining_time": "2:00:39", "throughput": 2869.65, "total_tokens": 4127832} {"current_steps": 6330, "total_steps": 38160, "loss": 0.5136, "lr": 4.9342372887898804e-05, "epoch": 3.3176100628930816, "percentage": 16.59, "elapsed_time": "0:23:59", "remaining_time": "2:00:38", "throughput": 2869.22, "total_tokens": 4130232} {"current_steps": 6335, "total_steps": 38160, "loss": 0.3492, "lr": 4.9339764975133026e-05, "epoch": 3.320230607966457, "percentage": 16.6, "elapsed_time": "0:24:00", "remaining_time": "2:00:36", "throughput": 2869.06, "total_tokens": 4133080} {"current_steps": 6340, "total_steps": 38160, "loss": 0.3495, "lr": 4.93371519707661e-05, "epoch": 3.3228511530398324, "percentage": 16.61, "elapsed_time": "0:24:01", "remaining_time": "2:00:36", "throughput": 2869.0, "total_tokens": 4136536} {"current_steps": 6345, "total_steps": 38160, "loss": 0.3661, "lr": 4.933453387534464e-05, "epoch": 3.3254716981132075, "percentage": 16.63, "elapsed_time": "0:24:02", "remaining_time": "2:00:35", "throughput": 2868.9, "total_tokens": 4139608} {"current_steps": 6350, "total_steps": 38160, "loss": 0.5084, "lr": 4.933191068941631e-05, "epoch": 3.3280922431865827, "percentage": 16.64, "elapsed_time": "0:24:03", "remaining_time": "2:00:33", "throughput": 2868.6, "total_tokens": 4142200} {"current_steps": 6355, "total_steps": 38160, "loss": 0.7439, "lr": 4.932928241352987e-05, "epoch": 3.330712788259958, "percentage": 16.65, "elapsed_time": "0:24:05", "remaining_time": "2:00:32", "throughput": 2868.93, "total_tokens": 4146200} {"current_steps": 6360, "total_steps": 38160, "loss": 0.328, "lr": 4.9326649048235095e-05, "epoch": 3.3333333333333335, "percentage": 16.67, "elapsed_time": "0:24:06", "remaining_time": "2:00:31", "throughput": 2869.09, "total_tokens": 4149464} {"current_steps": 6365, "total_steps": 38160, "loss": 0.4662, "lr": 4.932401059408287e-05, "epoch": 3.3359538784067087, "percentage": 16.68, "elapsed_time": "0:24:07", "remaining_time": "2:00:29", "throughput": 2868.74, "total_tokens": 4151992} {"current_steps": 6370, "total_steps": 38160, "loss": 0.4256, "lr": 4.932136705162514e-05, "epoch": 3.338574423480084, "percentage": 16.69, "elapsed_time": "0:24:08", "remaining_time": "2:00:28", "throughput": 2868.95, "total_tokens": 4155576} {"current_steps": 6375, "total_steps": 38160, "loss": 0.5054, "lr": 4.93187184214149e-05, "epoch": 3.341194968553459, "percentage": 16.71, "elapsed_time": "0:24:09", "remaining_time": "2:00:27", "throughput": 2869.53, "total_tokens": 4159672} {"current_steps": 6380, "total_steps": 38160, "loss": 0.3153, "lr": 4.9316064704006205e-05, "epoch": 3.3438155136268346, "percentage": 16.72, "elapsed_time": "0:24:10", "remaining_time": "2:00:26", "throughput": 2869.19, "total_tokens": 4162360} {"current_steps": 6385, "total_steps": 38160, "loss": 0.4083, "lr": 4.931340589995419e-05, "epoch": 3.3464360587002098, "percentage": 16.73, "elapsed_time": "0:24:11", "remaining_time": "2:00:25", "throughput": 2868.99, "total_tokens": 4165304} {"current_steps": 6390, "total_steps": 38160, "loss": 0.3706, "lr": 4.9310742009815035e-05, "epoch": 3.349056603773585, "percentage": 16.75, "elapsed_time": "0:24:12", "remaining_time": "2:00:23", "throughput": 2869.21, "total_tokens": 4168728} {"current_steps": 6395, "total_steps": 38160, "loss": 0.314, "lr": 4.930807303414601e-05, "epoch": 3.35167714884696, "percentage": 16.76, "elapsed_time": "0:24:14", "remaining_time": "2:00:22", "throughput": 2869.24, "total_tokens": 4171960} {"current_steps": 6400, "total_steps": 38160, "loss": 0.3934, "lr": 4.930539897350542e-05, "epoch": 3.3542976939203353, "percentage": 16.77, "elapsed_time": "0:24:15", "remaining_time": "2:00:21", "throughput": 2869.49, "total_tokens": 4175544} {"current_steps": 6405, "total_steps": 38160, "loss": 0.3132, "lr": 4.930271982845266e-05, "epoch": 3.3569182389937104, "percentage": 16.78, "elapsed_time": "0:24:16", "remaining_time": "2:00:19", "throughput": 2869.26, "total_tokens": 4178264} {"current_steps": 6410, "total_steps": 38160, "loss": 0.4461, "lr": 4.930003559954817e-05, "epoch": 3.359538784067086, "percentage": 16.8, "elapsed_time": "0:24:17", "remaining_time": "2:00:18", "throughput": 2869.05, "total_tokens": 4180984} {"current_steps": 6415, "total_steps": 38160, "loss": 0.488, "lr": 4.929734628735346e-05, "epoch": 3.3621593291404612, "percentage": 16.81, "elapsed_time": "0:24:18", "remaining_time": "2:00:16", "throughput": 2868.92, "total_tokens": 4183768} {"current_steps": 6420, "total_steps": 38160, "loss": 0.3503, "lr": 4.9294651892431115e-05, "epoch": 3.3647798742138364, "percentage": 16.82, "elapsed_time": "0:24:19", "remaining_time": "2:00:14", "throughput": 2869.07, "total_tokens": 4187000} {"current_steps": 6425, "total_steps": 38160, "loss": 0.4009, "lr": 4.929195241534476e-05, "epoch": 3.3674004192872116, "percentage": 16.84, "elapsed_time": "0:24:20", "remaining_time": "2:00:13", "throughput": 2868.6, "total_tokens": 4189304} {"current_steps": 6430, "total_steps": 38160, "loss": 0.4293, "lr": 4.9289247856659095e-05, "epoch": 3.370020964360587, "percentage": 16.85, "elapsed_time": "0:24:21", "remaining_time": "2:00:12", "throughput": 2869.01, "total_tokens": 4193080} {"current_steps": 6435, "total_steps": 38160, "loss": 0.4196, "lr": 4.9286538216939883e-05, "epoch": 3.3726415094339623, "percentage": 16.86, "elapsed_time": "0:24:22", "remaining_time": "2:00:10", "throughput": 2868.72, "total_tokens": 4195608} {"current_steps": 6440, "total_steps": 38160, "loss": 0.3269, "lr": 4.9283823496753944e-05, "epoch": 3.3752620545073375, "percentage": 16.88, "elapsed_time": "0:24:23", "remaining_time": "2:00:08", "throughput": 2868.84, "total_tokens": 4198744} {"current_steps": 6445, "total_steps": 38160, "loss": 0.6344, "lr": 4.928110369666918e-05, "epoch": 3.3778825995807127, "percentage": 16.89, "elapsed_time": "0:24:24", "remaining_time": "2:00:07", "throughput": 2869.25, "total_tokens": 4202680} {"current_steps": 6450, "total_steps": 38160, "loss": 0.3989, "lr": 4.927837881725455e-05, "epoch": 3.380503144654088, "percentage": 16.9, "elapsed_time": "0:24:25", "remaining_time": "2:00:06", "throughput": 2868.87, "total_tokens": 4205144} {"current_steps": 6455, "total_steps": 38160, "loss": 0.3733, "lr": 4.927564885908003e-05, "epoch": 3.3831236897274635, "percentage": 16.92, "elapsed_time": "0:24:26", "remaining_time": "2:00:05", "throughput": 2869.27, "total_tokens": 4209112} {"current_steps": 6460, "total_steps": 38160, "loss": 0.3858, "lr": 4.9272913822716735e-05, "epoch": 3.3857442348008386, "percentage": 16.93, "elapsed_time": "0:24:28", "remaining_time": "2:00:04", "throughput": 2869.69, "total_tokens": 4213048} {"current_steps": 6465, "total_steps": 38160, "loss": 0.3902, "lr": 4.927017370873678e-05, "epoch": 3.388364779874214, "percentage": 16.94, "elapsed_time": "0:24:29", "remaining_time": "2:00:02", "throughput": 2869.94, "total_tokens": 4216472} {"current_steps": 6470, "total_steps": 38160, "loss": 0.377, "lr": 4.926742851771338e-05, "epoch": 3.390985324947589, "percentage": 16.95, "elapsed_time": "0:24:30", "remaining_time": "2:00:01", "throughput": 2870.1, "total_tokens": 4219672} {"current_steps": 6475, "total_steps": 38160, "loss": 0.4357, "lr": 4.926467825022079e-05, "epoch": 3.3936058700209646, "percentage": 16.97, "elapsed_time": "0:24:31", "remaining_time": "1:59:59", "throughput": 2870.11, "total_tokens": 4222872} {"current_steps": 6480, "total_steps": 38160, "loss": 0.4628, "lr": 4.926192290683434e-05, "epoch": 3.3962264150943398, "percentage": 16.98, "elapsed_time": "0:24:32", "remaining_time": "1:59:58", "throughput": 2869.82, "total_tokens": 4225528} {"current_steps": 6485, "total_steps": 38160, "loss": 0.3622, "lr": 4.9259162488130404e-05, "epoch": 3.398846960167715, "percentage": 16.99, "elapsed_time": "0:24:33", "remaining_time": "1:59:57", "throughput": 2869.9, "total_tokens": 4229144} {"current_steps": 6490, "total_steps": 38160, "loss": 0.4356, "lr": 4.925639699468645e-05, "epoch": 3.40146750524109, "percentage": 17.01, "elapsed_time": "0:24:34", "remaining_time": "1:59:56", "throughput": 2870.28, "total_tokens": 4232792} {"current_steps": 6495, "total_steps": 38160, "loss": 0.3783, "lr": 4.925362642708097e-05, "epoch": 3.4040880503144653, "percentage": 17.02, "elapsed_time": "0:24:35", "remaining_time": "1:59:54", "throughput": 2870.79, "total_tokens": 4236600} {"current_steps": 6500, "total_steps": 38160, "loss": 0.5304, "lr": 4.9250850785893536e-05, "epoch": 3.4067085953878404, "percentage": 17.03, "elapsed_time": "0:24:36", "remaining_time": "1:59:53", "throughput": 2870.84, "total_tokens": 4239896} {"current_steps": 6505, "total_steps": 38160, "loss": 0.4421, "lr": 4.924807007170479e-05, "epoch": 3.409329140461216, "percentage": 17.05, "elapsed_time": "0:24:37", "remaining_time": "1:59:52", "throughput": 2871.33, "total_tokens": 4243640} {"current_steps": 6510, "total_steps": 38160, "loss": 0.4698, "lr": 4.924528428509643e-05, "epoch": 3.411949685534591, "percentage": 17.06, "elapsed_time": "0:24:38", "remaining_time": "1:59:50", "throughput": 2871.66, "total_tokens": 4247160} {"current_steps": 6515, "total_steps": 38160, "loss": 0.5015, "lr": 4.9242493426651196e-05, "epoch": 3.4145702306079664, "percentage": 17.07, "elapsed_time": "0:24:40", "remaining_time": "1:59:49", "throughput": 2872.18, "total_tokens": 4251032} {"current_steps": 6520, "total_steps": 38160, "loss": 0.471, "lr": 4.92396974969529e-05, "epoch": 3.4171907756813416, "percentage": 17.09, "elapsed_time": "0:24:41", "remaining_time": "1:59:47", "throughput": 2872.43, "total_tokens": 4254680} {"current_steps": 6525, "total_steps": 38160, "loss": 0.3531, "lr": 4.923689649658644e-05, "epoch": 3.419811320754717, "percentage": 17.1, "elapsed_time": "0:24:42", "remaining_time": "1:59:46", "throughput": 2872.39, "total_tokens": 4257720} {"current_steps": 6530, "total_steps": 38160, "loss": 0.4235, "lr": 4.923409042613774e-05, "epoch": 3.4224318658280923, "percentage": 17.11, "elapsed_time": "0:24:43", "remaining_time": "1:59:45", "throughput": 2872.34, "total_tokens": 4260696} {"current_steps": 6535, "total_steps": 38160, "loss": 0.3607, "lr": 4.92312792861938e-05, "epoch": 3.4250524109014675, "percentage": 17.13, "elapsed_time": "0:24:44", "remaining_time": "1:59:43", "throughput": 2872.11, "total_tokens": 4263416} {"current_steps": 6540, "total_steps": 38160, "loss": 0.5026, "lr": 4.922846307734268e-05, "epoch": 3.4276729559748427, "percentage": 17.14, "elapsed_time": "0:24:45", "remaining_time": "1:59:42", "throughput": 2871.94, "total_tokens": 4266232} {"current_steps": 6545, "total_steps": 38160, "loss": 0.3427, "lr": 4.9225641800173496e-05, "epoch": 3.430293501048218, "percentage": 17.15, "elapsed_time": "0:24:46", "remaining_time": "1:59:40", "throughput": 2871.96, "total_tokens": 4269400} {"current_steps": 6550, "total_steps": 38160, "loss": 0.403, "lr": 4.922281545527643e-05, "epoch": 3.4329140461215935, "percentage": 17.16, "elapsed_time": "0:24:47", "remaining_time": "1:59:39", "throughput": 2871.63, "total_tokens": 4271896} {"current_steps": 6555, "total_steps": 38160, "loss": 0.5797, "lr": 4.9219984043242715e-05, "epoch": 3.4355345911949686, "percentage": 17.18, "elapsed_time": "0:24:48", "remaining_time": "1:59:38", "throughput": 2871.76, "total_tokens": 4275416} {"current_steps": 6560, "total_steps": 38160, "loss": 0.3839, "lr": 4.921714756466466e-05, "epoch": 3.438155136268344, "percentage": 17.19, "elapsed_time": "0:24:49", "remaining_time": "1:59:36", "throughput": 2872.03, "total_tokens": 4278936} {"current_steps": 6565, "total_steps": 38160, "loss": 0.3977, "lr": 4.921430602013561e-05, "epoch": 3.440775681341719, "percentage": 17.2, "elapsed_time": "0:24:51", "remaining_time": "1:59:35", "throughput": 2872.41, "total_tokens": 4282808} {"current_steps": 6570, "total_steps": 38160, "loss": 0.4348, "lr": 4.9211459410249995e-05, "epoch": 3.4433962264150946, "percentage": 17.22, "elapsed_time": "0:24:52", "remaining_time": "1:59:34", "throughput": 2872.12, "total_tokens": 4285400} {"current_steps": 6575, "total_steps": 38160, "loss": 0.3247, "lr": 4.92086077356033e-05, "epoch": 3.4460167714884697, "percentage": 17.23, "elapsed_time": "0:24:53", "remaining_time": "1:59:32", "throughput": 2871.93, "total_tokens": 4288280} {"current_steps": 6580, "total_steps": 38160, "loss": 0.4282, "lr": 4.920575099679204e-05, "epoch": 3.448637316561845, "percentage": 17.24, "elapsed_time": "0:24:54", "remaining_time": "1:59:31", "throughput": 2872.08, "total_tokens": 4291576} {"current_steps": 6585, "total_steps": 38160, "loss": 0.3889, "lr": 4.920288919441383e-05, "epoch": 3.45125786163522, "percentage": 17.26, "elapsed_time": "0:24:55", "remaining_time": "1:59:30", "throughput": 2872.31, "total_tokens": 4295288} {"current_steps": 6590, "total_steps": 38160, "loss": 0.4433, "lr": 4.9200022329067316e-05, "epoch": 3.4538784067085953, "percentage": 17.27, "elapsed_time": "0:24:56", "remaining_time": "1:59:29", "throughput": 2872.54, "total_tokens": 4298808} {"current_steps": 6595, "total_steps": 38160, "loss": 0.3306, "lr": 4.9197150401352224e-05, "epoch": 3.4564989517819704, "percentage": 17.28, "elapsed_time": "0:24:58", "remaining_time": "1:59:29", "throughput": 2873.29, "total_tokens": 4304280} {"current_steps": 6600, "total_steps": 38160, "loss": 0.5716, "lr": 4.919427341186933e-05, "epoch": 3.459119496855346, "percentage": 17.3, "elapsed_time": "0:24:59", "remaining_time": "1:59:28", "throughput": 2872.88, "total_tokens": 4306616} {"current_steps": 6605, "total_steps": 38160, "loss": 0.4066, "lr": 4.919139136122045e-05, "epoch": 3.461740041928721, "percentage": 17.31, "elapsed_time": "0:25:00", "remaining_time": "1:59:26", "throughput": 2872.57, "total_tokens": 4309112} {"current_steps": 6610, "total_steps": 38160, "loss": 0.4827, "lr": 4.918850425000849e-05, "epoch": 3.4643605870020964, "percentage": 17.32, "elapsed_time": "0:25:01", "remaining_time": "1:59:25", "throughput": 2872.39, "total_tokens": 4311832} {"current_steps": 6615, "total_steps": 38160, "loss": 0.3836, "lr": 4.918561207883741e-05, "epoch": 3.4669811320754715, "percentage": 17.33, "elapsed_time": "0:25:02", "remaining_time": "1:59:26", "throughput": 2873.39, "total_tokens": 4318328} {"current_steps": 6620, "total_steps": 38160, "loss": 0.3631, "lr": 4.9182714848312195e-05, "epoch": 3.469601677148847, "percentage": 17.35, "elapsed_time": "0:25:03", "remaining_time": "1:59:25", "throughput": 2873.68, "total_tokens": 4321848} {"current_steps": 6625, "total_steps": 38160, "loss": 0.2934, "lr": 4.917981255903893e-05, "epoch": 3.4722222222222223, "percentage": 17.36, "elapsed_time": "0:25:05", "remaining_time": "1:59:23", "throughput": 2873.71, "total_tokens": 4324984} {"current_steps": 6630, "total_steps": 38160, "loss": 0.3577, "lr": 4.917690521162474e-05, "epoch": 3.4748427672955975, "percentage": 17.37, "elapsed_time": "0:25:06", "remaining_time": "1:59:22", "throughput": 2873.54, "total_tokens": 4327704} {"current_steps": 6635, "total_steps": 38160, "loss": 0.3415, "lr": 4.9173992806677796e-05, "epoch": 3.4774633123689727, "percentage": 17.39, "elapsed_time": "0:25:07", "remaining_time": "1:59:20", "throughput": 2873.59, "total_tokens": 4330904} {"current_steps": 6640, "total_steps": 38160, "loss": 0.4546, "lr": 4.917107534480735e-05, "epoch": 3.480083857442348, "percentage": 17.4, "elapsed_time": "0:25:08", "remaining_time": "1:59:19", "throughput": 2873.35, "total_tokens": 4333592} {"current_steps": 6645, "total_steps": 38160, "loss": 0.3721, "lr": 4.916815282662369e-05, "epoch": 3.4827044025157234, "percentage": 17.41, "elapsed_time": "0:25:09", "remaining_time": "1:59:18", "throughput": 2873.35, "total_tokens": 4336696} {"current_steps": 6650, "total_steps": 38160, "loss": 0.6161, "lr": 4.91652252527382e-05, "epoch": 3.4853249475890986, "percentage": 17.43, "elapsed_time": "0:25:10", "remaining_time": "1:59:16", "throughput": 2873.61, "total_tokens": 4340088} {"current_steps": 6655, "total_steps": 38160, "loss": 0.4818, "lr": 4.9162292623763275e-05, "epoch": 3.487945492662474, "percentage": 17.44, "elapsed_time": "0:25:11", "remaining_time": "1:59:15", "throughput": 2873.68, "total_tokens": 4343640} {"current_steps": 6660, "total_steps": 38160, "loss": 0.3988, "lr": 4.9159354940312386e-05, "epoch": 3.490566037735849, "percentage": 17.45, "elapsed_time": "0:25:12", "remaining_time": "1:59:15", "throughput": 2874.54, "total_tokens": 4348568} {"current_steps": 6665, "total_steps": 38160, "loss": 0.3676, "lr": 4.915641220300007e-05, "epoch": 3.4931865828092246, "percentage": 17.47, "elapsed_time": "0:25:13", "remaining_time": "1:59:13", "throughput": 2874.88, "total_tokens": 4352376} {"current_steps": 6670, "total_steps": 38160, "loss": 0.429, "lr": 4.9153464412441915e-05, "epoch": 3.4958071278825997, "percentage": 17.48, "elapsed_time": "0:25:15", "remaining_time": "1:59:12", "throughput": 2875.28, "total_tokens": 4356120} {"current_steps": 6675, "total_steps": 38160, "loss": 0.3968, "lr": 4.915051156925456e-05, "epoch": 3.498427672955975, "percentage": 17.49, "elapsed_time": "0:25:16", "remaining_time": "1:59:11", "throughput": 2875.5, "total_tokens": 4359448} {"current_steps": 6680, "total_steps": 38160, "loss": 0.2927, "lr": 4.91475536740557e-05, "epoch": 3.50104821802935, "percentage": 17.51, "elapsed_time": "0:25:17", "remaining_time": "1:59:09", "throughput": 2875.67, "total_tokens": 4362936} {"current_steps": 6685, "total_steps": 38160, "loss": 0.3627, "lr": 4.914459072746411e-05, "epoch": 3.5036687631027252, "percentage": 17.52, "elapsed_time": "0:25:18", "remaining_time": "1:59:08", "throughput": 2876.2, "total_tokens": 4366968} {"current_steps": 6690, "total_steps": 38160, "loss": 0.3103, "lr": 4.91416227300996e-05, "epoch": 3.5062893081761004, "percentage": 17.53, "elapsed_time": "0:25:19", "remaining_time": "1:59:07", "throughput": 2876.25, "total_tokens": 4370264} {"current_steps": 6695, "total_steps": 38160, "loss": 0.2771, "lr": 4.913864968258303e-05, "epoch": 3.508909853249476, "percentage": 17.54, "elapsed_time": "0:25:20", "remaining_time": "1:59:06", "throughput": 2876.25, "total_tokens": 4373432} {"current_steps": 6700, "total_steps": 38160, "loss": 0.5368, "lr": 4.913567158553634e-05, "epoch": 3.511530398322851, "percentage": 17.56, "elapsed_time": "0:25:21", "remaining_time": "1:59:04", "throughput": 2876.38, "total_tokens": 4376824} {"current_steps": 6705, "total_steps": 38160, "loss": 0.4578, "lr": 4.9132688439582505e-05, "epoch": 3.5141509433962264, "percentage": 17.57, "elapsed_time": "0:25:22", "remaining_time": "1:59:03", "throughput": 2876.62, "total_tokens": 4380504} {"current_steps": 6710, "total_steps": 38160, "loss": 0.4107, "lr": 4.9129700245345565e-05, "epoch": 3.5167714884696015, "percentage": 17.58, "elapsed_time": "0:25:23", "remaining_time": "1:59:02", "throughput": 2876.72, "total_tokens": 4383704} {"current_steps": 6715, "total_steps": 38160, "loss": 0.5407, "lr": 4.912670700345063e-05, "epoch": 3.519392033542977, "percentage": 17.6, "elapsed_time": "0:25:24", "remaining_time": "1:59:01", "throughput": 2876.84, "total_tokens": 4387128} {"current_steps": 6720, "total_steps": 38160, "loss": 0.3991, "lr": 4.912370871452383e-05, "epoch": 3.5220125786163523, "percentage": 17.61, "elapsed_time": "0:25:26", "remaining_time": "1:58:59", "throughput": 2876.95, "total_tokens": 4390296} {"current_steps": 6725, "total_steps": 38160, "loss": 0.4621, "lr": 4.91207053791924e-05, "epoch": 3.5246331236897275, "percentage": 17.62, "elapsed_time": "0:25:27", "remaining_time": "1:58:58", "throughput": 2877.1, "total_tokens": 4393624} {"current_steps": 6730, "total_steps": 38160, "loss": 0.3631, "lr": 4.911769699808457e-05, "epoch": 3.5272536687631026, "percentage": 17.64, "elapsed_time": "0:25:28", "remaining_time": "1:58:57", "throughput": 2877.72, "total_tokens": 4397944} {"current_steps": 6735, "total_steps": 38160, "loss": 0.3825, "lr": 4.911468357182969e-05, "epoch": 3.529874213836478, "percentage": 17.65, "elapsed_time": "0:25:29", "remaining_time": "1:58:55", "throughput": 2877.58, "total_tokens": 4400696} {"current_steps": 6740, "total_steps": 38160, "loss": 0.4048, "lr": 4.9111665101058116e-05, "epoch": 3.532494758909853, "percentage": 17.66, "elapsed_time": "0:25:30", "remaining_time": "1:58:54", "throughput": 2877.38, "total_tokens": 4403416} {"current_steps": 6745, "total_steps": 38160, "loss": 0.3632, "lr": 4.910864158640128e-05, "epoch": 3.5351153039832286, "percentage": 17.68, "elapsed_time": "0:25:31", "remaining_time": "1:58:52", "throughput": 2877.88, "total_tokens": 4407320} {"current_steps": 6750, "total_steps": 38160, "loss": 0.3561, "lr": 4.910561302849168e-05, "epoch": 3.5377358490566038, "percentage": 17.69, "elapsed_time": "0:25:32", "remaining_time": "1:58:51", "throughput": 2877.47, "total_tokens": 4409848} {"current_steps": 6755, "total_steps": 38160, "loss": 0.4142, "lr": 4.910257942796284e-05, "epoch": 3.540356394129979, "percentage": 17.7, "elapsed_time": "0:25:33", "remaining_time": "1:58:50", "throughput": 2877.42, "total_tokens": 4412920} {"current_steps": 6760, "total_steps": 38160, "loss": 0.3168, "lr": 4.909954078544936e-05, "epoch": 3.5429769392033545, "percentage": 17.71, "elapsed_time": "0:25:34", "remaining_time": "1:58:48", "throughput": 2877.06, "total_tokens": 4415384} {"current_steps": 6765, "total_steps": 38160, "loss": 0.3186, "lr": 4.909649710158689e-05, "epoch": 3.5455974842767297, "percentage": 17.73, "elapsed_time": "0:25:35", "remaining_time": "1:58:46", "throughput": 2876.86, "total_tokens": 4418040} {"current_steps": 6770, "total_steps": 38160, "loss": 0.3908, "lr": 4.909344837701214e-05, "epoch": 3.548218029350105, "percentage": 17.74, "elapsed_time": "0:25:36", "remaining_time": "1:58:45", "throughput": 2877.07, "total_tokens": 4421464} {"current_steps": 6775, "total_steps": 38160, "loss": 0.4231, "lr": 4.909039461236285e-05, "epoch": 3.55083857442348, "percentage": 17.75, "elapsed_time": "0:25:37", "remaining_time": "1:58:44", "throughput": 2876.5, "total_tokens": 4423672} {"current_steps": 6780, "total_steps": 38160, "loss": 0.3664, "lr": 4.908733580827786e-05, "epoch": 3.5534591194968552, "percentage": 17.77, "elapsed_time": "0:25:38", "remaining_time": "1:58:42", "throughput": 2876.45, "total_tokens": 4426648} {"current_steps": 6785, "total_steps": 38160, "loss": 0.4278, "lr": 4.9084271965397014e-05, "epoch": 3.5560796645702304, "percentage": 17.78, "elapsed_time": "0:25:40", "remaining_time": "1:58:41", "throughput": 2876.45, "total_tokens": 4429752} {"current_steps": 6790, "total_steps": 38160, "loss": 0.5002, "lr": 4.908120308436124e-05, "epoch": 3.558700209643606, "percentage": 17.79, "elapsed_time": "0:25:41", "remaining_time": "1:58:40", "throughput": 2876.86, "total_tokens": 4433784} {"current_steps": 6795, "total_steps": 38160, "loss": 0.3853, "lr": 4.907812916581251e-05, "epoch": 3.561320754716981, "percentage": 17.81, "elapsed_time": "0:25:42", "remaining_time": "1:58:39", "throughput": 2876.42, "total_tokens": 4436376} {"current_steps": 6800, "total_steps": 38160, "loss": 0.3428, "lr": 4.907505021039386e-05, "epoch": 3.5639412997903563, "percentage": 17.82, "elapsed_time": "0:25:43", "remaining_time": "1:58:37", "throughput": 2876.33, "total_tokens": 4439384} {"current_steps": 6805, "total_steps": 38160, "loss": 0.4275, "lr": 4.907196621874937e-05, "epoch": 3.5665618448637315, "percentage": 17.83, "elapsed_time": "0:25:44", "remaining_time": "1:58:36", "throughput": 2876.37, "total_tokens": 4442712} {"current_steps": 6810, "total_steps": 38160, "loss": 0.4434, "lr": 4.9068877191524176e-05, "epoch": 3.569182389937107, "percentage": 17.85, "elapsed_time": "0:25:45", "remaining_time": "1:58:35", "throughput": 2877.0, "total_tokens": 4446936} {"current_steps": 6815, "total_steps": 38160, "loss": 0.4695, "lr": 4.906578312936446e-05, "epoch": 3.5718029350104823, "percentage": 17.86, "elapsed_time": "0:25:46", "remaining_time": "1:58:33", "throughput": 2877.31, "total_tokens": 4450328} {"current_steps": 6820, "total_steps": 38160, "loss": 0.341, "lr": 4.906268403291747e-05, "epoch": 3.5744234800838575, "percentage": 17.87, "elapsed_time": "0:25:47", "remaining_time": "1:58:32", "throughput": 2877.58, "total_tokens": 4453816} {"current_steps": 6825, "total_steps": 38160, "loss": 0.339, "lr": 4.905957990283151e-05, "epoch": 3.5770440251572326, "percentage": 17.89, "elapsed_time": "0:25:48", "remaining_time": "1:58:31", "throughput": 2878.06, "total_tokens": 4458072} {"current_steps": 6830, "total_steps": 38160, "loss": 0.3644, "lr": 4.905647073975592e-05, "epoch": 3.579664570230608, "percentage": 17.9, "elapsed_time": "0:25:50", "remaining_time": "1:58:30", "throughput": 2878.07, "total_tokens": 4461144} {"current_steps": 6835, "total_steps": 38160, "loss": 0.2973, "lr": 4.9053356544341095e-05, "epoch": 3.582285115303983, "percentage": 17.91, "elapsed_time": "0:25:51", "remaining_time": "1:58:28", "throughput": 2877.96, "total_tokens": 4463928} {"current_steps": 6840, "total_steps": 38160, "loss": 0.3969, "lr": 4.90502373172385e-05, "epoch": 3.5849056603773586, "percentage": 17.92, "elapsed_time": "0:25:52", "remaining_time": "1:58:26", "throughput": 2877.72, "total_tokens": 4466488} {"current_steps": 6845, "total_steps": 38160, "loss": 0.3383, "lr": 4.9047113059100635e-05, "epoch": 3.5875262054507338, "percentage": 17.94, "elapsed_time": "0:25:53", "remaining_time": "1:58:25", "throughput": 2878.07, "total_tokens": 4470104} {"current_steps": 6850, "total_steps": 38160, "loss": 0.4681, "lr": 4.904398377058106e-05, "epoch": 3.590146750524109, "percentage": 17.95, "elapsed_time": "0:25:54", "remaining_time": "1:58:23", "throughput": 2877.52, "total_tokens": 4472184} {"current_steps": 6855, "total_steps": 38160, "loss": 0.4152, "lr": 4.90408494523344e-05, "epoch": 3.5927672955974845, "percentage": 17.96, "elapsed_time": "0:25:55", "remaining_time": "1:58:22", "throughput": 2877.29, "total_tokens": 4474840} {"current_steps": 6860, "total_steps": 38160, "loss": 0.4297, "lr": 4.90377101050163e-05, "epoch": 3.5953878406708597, "percentage": 17.98, "elapsed_time": "0:25:56", "remaining_time": "1:58:20", "throughput": 2877.3, "total_tokens": 4477816} {"current_steps": 6865, "total_steps": 38160, "loss": 0.4855, "lr": 4.903456572928348e-05, "epoch": 3.598008385744235, "percentage": 17.99, "elapsed_time": "0:25:57", "remaining_time": "1:58:19", "throughput": 2877.76, "total_tokens": 4481816} {"current_steps": 6870, "total_steps": 38160, "loss": 0.3266, "lr": 4.903141632579371e-05, "epoch": 3.60062893081761, "percentage": 18.0, "elapsed_time": "0:25:58", "remaining_time": "1:58:18", "throughput": 2877.94, "total_tokens": 4485464} {"current_steps": 6875, "total_steps": 38160, "loss": 0.3361, "lr": 4.902826189520581e-05, "epoch": 3.603249475890985, "percentage": 18.02, "elapsed_time": "0:25:59", "remaining_time": "1:58:18", "throughput": 2878.7, "total_tokens": 4490392} {"current_steps": 6880, "total_steps": 38160, "loss": 0.417, "lr": 4.9025102438179656e-05, "epoch": 3.6058700209643604, "percentage": 18.03, "elapsed_time": "0:26:01", "remaining_time": "1:58:17", "throughput": 2879.2, "total_tokens": 4494712} {"current_steps": 6885, "total_steps": 38160, "loss": 0.4482, "lr": 4.902193795537616e-05, "epoch": 3.608490566037736, "percentage": 18.04, "elapsed_time": "0:26:02", "remaining_time": "1:58:15", "throughput": 2879.1, "total_tokens": 4497528} {"current_steps": 6890, "total_steps": 38160, "loss": 0.3159, "lr": 4.90187684474573e-05, "epoch": 3.611111111111111, "percentage": 18.06, "elapsed_time": "0:26:03", "remaining_time": "1:58:14", "throughput": 2879.13, "total_tokens": 4500536} {"current_steps": 6895, "total_steps": 38160, "loss": 0.4245, "lr": 4.901559391508611e-05, "epoch": 3.6137316561844863, "percentage": 18.07, "elapsed_time": "0:26:04", "remaining_time": "1:58:13", "throughput": 2879.27, "total_tokens": 4504056} {"current_steps": 6900, "total_steps": 38160, "loss": 0.3965, "lr": 4.9012414358926644e-05, "epoch": 3.6163522012578615, "percentage": 18.08, "elapsed_time": "0:26:05", "remaining_time": "1:58:11", "throughput": 2879.19, "total_tokens": 4506936} {"current_steps": 6905, "total_steps": 38160, "loss": 0.319, "lr": 4.900922977964405e-05, "epoch": 3.618972746331237, "percentage": 18.09, "elapsed_time": "0:26:06", "remaining_time": "1:58:10", "throughput": 2878.98, "total_tokens": 4509560} {"current_steps": 6910, "total_steps": 38160, "loss": 0.4013, "lr": 4.90060401779045e-05, "epoch": 3.6215932914046123, "percentage": 18.11, "elapsed_time": "0:26:07", "remaining_time": "1:58:08", "throughput": 2879.26, "total_tokens": 4513240} {"current_steps": 6915, "total_steps": 38160, "loss": 0.3945, "lr": 4.900284555437521e-05, "epoch": 3.6242138364779874, "percentage": 18.12, "elapsed_time": "0:26:08", "remaining_time": "1:58:07", "throughput": 2878.9, "total_tokens": 4515640} {"current_steps": 6920, "total_steps": 38160, "loss": 0.3647, "lr": 4.899964590972448e-05, "epoch": 3.6268343815513626, "percentage": 18.13, "elapsed_time": "0:26:09", "remaining_time": "1:58:07", "throughput": 2879.75, "total_tokens": 4520824} {"current_steps": 6925, "total_steps": 38160, "loss": 0.4331, "lr": 4.899644124462163e-05, "epoch": 3.629454926624738, "percentage": 18.15, "elapsed_time": "0:26:10", "remaining_time": "1:58:05", "throughput": 2879.69, "total_tokens": 4523896} {"current_steps": 6930, "total_steps": 38160, "loss": 0.5143, "lr": 4.8993231559737026e-05, "epoch": 3.632075471698113, "percentage": 18.16, "elapsed_time": "0:26:11", "remaining_time": "1:58:04", "throughput": 2879.77, "total_tokens": 4527000} {"current_steps": 6935, "total_steps": 38160, "loss": 0.5001, "lr": 4.8990016855742114e-05, "epoch": 3.6346960167714886, "percentage": 18.17, "elapsed_time": "0:26:13", "remaining_time": "1:58:02", "throughput": 2879.67, "total_tokens": 4529912} {"current_steps": 6940, "total_steps": 38160, "loss": 0.356, "lr": 4.898679713330937e-05, "epoch": 3.6373165618448637, "percentage": 18.19, "elapsed_time": "0:26:14", "remaining_time": "1:58:01", "throughput": 2879.94, "total_tokens": 4533336} {"current_steps": 6945, "total_steps": 38160, "loss": 0.3953, "lr": 4.898357239311232e-05, "epoch": 3.639937106918239, "percentage": 18.2, "elapsed_time": "0:26:15", "remaining_time": "1:57:59", "throughput": 2879.89, "total_tokens": 4536344} {"current_steps": 6950, "total_steps": 38160, "loss": 0.3353, "lr": 4.898034263582554e-05, "epoch": 3.6425576519916145, "percentage": 18.21, "elapsed_time": "0:26:16", "remaining_time": "1:57:59", "throughput": 2880.08, "total_tokens": 4540152} {"current_steps": 6955, "total_steps": 38160, "loss": 0.3132, "lr": 4.897710786212467e-05, "epoch": 3.6451781970649897, "percentage": 18.23, "elapsed_time": "0:26:17", "remaining_time": "1:57:57", "throughput": 2879.99, "total_tokens": 4543032} {"current_steps": 6960, "total_steps": 38160, "loss": 0.3857, "lr": 4.897386807268638e-05, "epoch": 3.647798742138365, "percentage": 18.24, "elapsed_time": "0:26:18", "remaining_time": "1:57:57", "throughput": 2880.18, "total_tokens": 4547064} {"current_steps": 6965, "total_steps": 38160, "loss": 0.4235, "lr": 4.897062326818839e-05, "epoch": 3.65041928721174, "percentage": 18.25, "elapsed_time": "0:26:19", "remaining_time": "1:57:55", "throughput": 2880.62, "total_tokens": 4551000} {"current_steps": 6970, "total_steps": 38160, "loss": 0.464, "lr": 4.8967373449309495e-05, "epoch": 3.653039832285115, "percentage": 18.27, "elapsed_time": "0:26:21", "remaining_time": "1:57:54", "throughput": 2881.07, "total_tokens": 4555000} {"current_steps": 6975, "total_steps": 38160, "loss": 0.3556, "lr": 4.89641186167295e-05, "epoch": 3.6556603773584904, "percentage": 18.28, "elapsed_time": "0:26:22", "remaining_time": "1:57:53", "throughput": 2881.38, "total_tokens": 4558680} {"current_steps": 6980, "total_steps": 38160, "loss": 0.3831, "lr": 4.8960858771129294e-05, "epoch": 3.658280922431866, "percentage": 18.29, "elapsed_time": "0:26:23", "remaining_time": "1:57:52", "throughput": 2881.08, "total_tokens": 4561336} {"current_steps": 6985, "total_steps": 38160, "loss": 0.4184, "lr": 4.895759391319079e-05, "epoch": 3.660901467505241, "percentage": 18.3, "elapsed_time": "0:26:24", "remaining_time": "1:57:50", "throughput": 2881.18, "total_tokens": 4564568} {"current_steps": 6990, "total_steps": 38160, "loss": 0.383, "lr": 4.8954324043596954e-05, "epoch": 3.6635220125786163, "percentage": 18.32, "elapsed_time": "0:26:25", "remaining_time": "1:57:49", "throughput": 2881.1, "total_tokens": 4567448} {"current_steps": 6995, "total_steps": 38160, "loss": 0.4665, "lr": 4.8951049163031826e-05, "epoch": 3.6661425576519915, "percentage": 18.33, "elapsed_time": "0:26:26", "remaining_time": "1:57:47", "throughput": 2880.86, "total_tokens": 4570136} {"current_steps": 7000, "total_steps": 38160, "loss": 0.4093, "lr": 4.894776927218045e-05, "epoch": 3.668763102725367, "percentage": 18.34, "elapsed_time": "0:26:27", "remaining_time": "1:57:46", "throughput": 2881.02, "total_tokens": 4573624} {"current_steps": 7005, "total_steps": 38160, "loss": 0.3498, "lr": 4.894448437172896e-05, "epoch": 3.6713836477987423, "percentage": 18.36, "elapsed_time": "0:26:28", "remaining_time": "1:57:45", "throughput": 2881.16, "total_tokens": 4577048} {"current_steps": 7010, "total_steps": 38160, "loss": 0.432, "lr": 4.894119446236452e-05, "epoch": 3.6740041928721174, "percentage": 18.37, "elapsed_time": "0:26:29", "remaining_time": "1:57:43", "throughput": 2881.19, "total_tokens": 4580088} {"current_steps": 7015, "total_steps": 38160, "loss": 0.3451, "lr": 4.893789954477532e-05, "epoch": 3.6766247379454926, "percentage": 18.38, "elapsed_time": "0:26:30", "remaining_time": "1:57:42", "throughput": 2881.35, "total_tokens": 4583480} {"current_steps": 7020, "total_steps": 38160, "loss": 0.5333, "lr": 4.893459961965063e-05, "epoch": 3.6792452830188678, "percentage": 18.4, "elapsed_time": "0:26:31", "remaining_time": "1:57:41", "throughput": 2881.12, "total_tokens": 4586168} {"current_steps": 7025, "total_steps": 38160, "loss": 0.3462, "lr": 4.8931294687680775e-05, "epoch": 3.681865828092243, "percentage": 18.41, "elapsed_time": "0:26:32", "remaining_time": "1:57:39", "throughput": 2881.21, "total_tokens": 4589592} {"current_steps": 7030, "total_steps": 38160, "loss": 0.4498, "lr": 4.8927984749557086e-05, "epoch": 3.6844863731656186, "percentage": 18.42, "elapsed_time": "0:26:33", "remaining_time": "1:57:38", "throughput": 2881.16, "total_tokens": 4592440} {"current_steps": 7035, "total_steps": 38160, "loss": 0.3004, "lr": 4.892466980597198e-05, "epoch": 3.6871069182389937, "percentage": 18.44, "elapsed_time": "0:26:35", "remaining_time": "1:57:36", "throughput": 2880.81, "total_tokens": 4594904} {"current_steps": 7040, "total_steps": 38160, "loss": 0.4361, "lr": 4.892134985761889e-05, "epoch": 3.689727463312369, "percentage": 18.45, "elapsed_time": "0:26:36", "remaining_time": "1:57:35", "throughput": 2880.68, "total_tokens": 4597624} {"current_steps": 7045, "total_steps": 38160, "loss": 0.4839, "lr": 4.891802490519232e-05, "epoch": 3.6923480083857445, "percentage": 18.46, "elapsed_time": "0:26:37", "remaining_time": "1:57:33", "throughput": 2880.21, "total_tokens": 4599928} {"current_steps": 7050, "total_steps": 38160, "loss": 0.4114, "lr": 4.891469494938781e-05, "epoch": 3.6949685534591197, "percentage": 18.47, "elapsed_time": "0:26:38", "remaining_time": "1:57:32", "throughput": 2879.79, "total_tokens": 4602328} {"current_steps": 7055, "total_steps": 38160, "loss": 0.4193, "lr": 4.891135999090195e-05, "epoch": 3.697589098532495, "percentage": 18.49, "elapsed_time": "0:26:39", "remaining_time": "1:57:31", "throughput": 2880.02, "total_tokens": 4606328} {"current_steps": 7060, "total_steps": 38160, "loss": 0.3344, "lr": 4.890802003043238e-05, "epoch": 3.70020964360587, "percentage": 18.5, "elapsed_time": "0:26:40", "remaining_time": "1:57:30", "throughput": 2879.91, "total_tokens": 4609176} {"current_steps": 7065, "total_steps": 38160, "loss": 0.5001, "lr": 4.890467506867777e-05, "epoch": 3.702830188679245, "percentage": 18.51, "elapsed_time": "0:26:41", "remaining_time": "1:57:28", "throughput": 2879.78, "total_tokens": 4612056} {"current_steps": 7070, "total_steps": 38160, "loss": 0.5097, "lr": 4.890132510633786e-05, "epoch": 3.7054507337526204, "percentage": 18.53, "elapsed_time": "0:26:42", "remaining_time": "1:57:27", "throughput": 2879.77, "total_tokens": 4615320} {"current_steps": 7075, "total_steps": 38160, "loss": 0.4571, "lr": 4.8897970144113416e-05, "epoch": 3.708071278825996, "percentage": 18.54, "elapsed_time": "0:26:43", "remaining_time": "1:57:26", "throughput": 2879.66, "total_tokens": 4618200} {"current_steps": 7080, "total_steps": 38160, "loss": 0.2902, "lr": 4.889461018270626e-05, "epoch": 3.710691823899371, "percentage": 18.55, "elapsed_time": "0:26:44", "remaining_time": "1:57:24", "throughput": 2879.72, "total_tokens": 4621368} {"current_steps": 7085, "total_steps": 38160, "loss": 0.4131, "lr": 4.889124522281926e-05, "epoch": 3.7133123689727463, "percentage": 18.57, "elapsed_time": "0:26:45", "remaining_time": "1:57:23", "throughput": 2879.5, "total_tokens": 4624088} {"current_steps": 7090, "total_steps": 38160, "loss": 0.5462, "lr": 4.888787526515632e-05, "epoch": 3.7159329140461215, "percentage": 18.58, "elapsed_time": "0:26:46", "remaining_time": "1:57:22", "throughput": 2880.25, "total_tokens": 4628568} {"current_steps": 7095, "total_steps": 38160, "loss": 0.4391, "lr": 4.8884500310422406e-05, "epoch": 3.718553459119497, "percentage": 18.59, "elapsed_time": "0:26:48", "remaining_time": "1:57:20", "throughput": 2880.1, "total_tokens": 4631288} {"current_steps": 7100, "total_steps": 38160, "loss": 0.3402, "lr": 4.8881120359323516e-05, "epoch": 3.7211740041928723, "percentage": 18.61, "elapsed_time": "0:26:49", "remaining_time": "1:57:19", "throughput": 2880.56, "total_tokens": 4635224} {"current_steps": 7105, "total_steps": 38160, "loss": 0.5845, "lr": 4.887773541256669e-05, "epoch": 3.7237945492662474, "percentage": 18.62, "elapsed_time": "0:26:50", "remaining_time": "1:57:18", "throughput": 2880.68, "total_tokens": 4638648} {"current_steps": 7110, "total_steps": 38160, "loss": 0.3181, "lr": 4.887434547086004e-05, "epoch": 3.7264150943396226, "percentage": 18.63, "elapsed_time": "0:26:51", "remaining_time": "1:57:16", "throughput": 2880.82, "total_tokens": 4641848} {"current_steps": 7115, "total_steps": 38160, "loss": 0.4089, "lr": 4.887095053491269e-05, "epoch": 3.7290356394129978, "percentage": 18.65, "elapsed_time": "0:26:52", "remaining_time": "1:57:14", "throughput": 2880.6, "total_tokens": 4644408} {"current_steps": 7120, "total_steps": 38160, "loss": 0.5302, "lr": 4.8867550605434806e-05, "epoch": 3.731656184486373, "percentage": 18.66, "elapsed_time": "0:26:53", "remaining_time": "1:57:13", "throughput": 2880.47, "total_tokens": 4647096} {"current_steps": 7125, "total_steps": 38160, "loss": 0.4189, "lr": 4.8864145683137644e-05, "epoch": 3.7342767295597485, "percentage": 18.67, "elapsed_time": "0:26:54", "remaining_time": "1:57:11", "throughput": 2879.96, "total_tokens": 4649176} {"current_steps": 7130, "total_steps": 38160, "loss": 0.4384, "lr": 4.886073576873346e-05, "epoch": 3.7368972746331237, "percentage": 18.68, "elapsed_time": "0:26:55", "remaining_time": "1:57:10", "throughput": 2880.29, "total_tokens": 4653144} {"current_steps": 7135, "total_steps": 38160, "loss": 0.2894, "lr": 4.885732086293556e-05, "epoch": 3.739517819706499, "percentage": 18.7, "elapsed_time": "0:26:56", "remaining_time": "1:57:09", "throughput": 2880.16, "total_tokens": 4655864} {"current_steps": 7140, "total_steps": 38160, "loss": 0.4185, "lr": 4.8853900966458335e-05, "epoch": 3.742138364779874, "percentage": 18.71, "elapsed_time": "0:26:57", "remaining_time": "1:57:07", "throughput": 2880.26, "total_tokens": 4659000} {"current_steps": 7145, "total_steps": 38160, "loss": 0.447, "lr": 4.8850476080017146e-05, "epoch": 3.7447589098532497, "percentage": 18.72, "elapsed_time": "0:26:58", "remaining_time": "1:57:05", "throughput": 2880.11, "total_tokens": 4661720} {"current_steps": 7150, "total_steps": 38160, "loss": 0.4025, "lr": 4.884704620432848e-05, "epoch": 3.747379454926625, "percentage": 18.74, "elapsed_time": "0:26:59", "remaining_time": "1:57:05", "throughput": 2880.85, "total_tokens": 4666584} {"current_steps": 7155, "total_steps": 38160, "loss": 0.3756, "lr": 4.8843611340109794e-05, "epoch": 3.75, "percentage": 18.75, "elapsed_time": "0:27:00", "remaining_time": "1:57:03", "throughput": 2880.69, "total_tokens": 4669272} {"current_steps": 7160, "total_steps": 38160, "loss": 0.414, "lr": 4.884017148807965e-05, "epoch": 3.752620545073375, "percentage": 18.76, "elapsed_time": "0:27:01", "remaining_time": "1:57:02", "throughput": 2880.74, "total_tokens": 4672280} {"current_steps": 7165, "total_steps": 38160, "loss": 0.3233, "lr": 4.883672664895761e-05, "epoch": 3.7552410901467503, "percentage": 18.78, "elapsed_time": "0:27:02", "remaining_time": "1:57:00", "throughput": 2880.63, "total_tokens": 4675032} {"current_steps": 7170, "total_steps": 38160, "loss": 0.3855, "lr": 4.8833276823464296e-05, "epoch": 3.757861635220126, "percentage": 18.79, "elapsed_time": "0:27:03", "remaining_time": "1:56:58", "throughput": 2880.86, "total_tokens": 4678360} {"current_steps": 7175, "total_steps": 38160, "loss": 0.4053, "lr": 4.882982201232138e-05, "epoch": 3.760482180293501, "percentage": 18.8, "elapsed_time": "0:27:04", "remaining_time": "1:56:57", "throughput": 2880.78, "total_tokens": 4681208} {"current_steps": 7180, "total_steps": 38160, "loss": 0.4204, "lr": 4.882636221625156e-05, "epoch": 3.7631027253668763, "percentage": 18.82, "elapsed_time": "0:27:06", "remaining_time": "1:56:56", "throughput": 2880.45, "total_tokens": 4683768} {"current_steps": 7185, "total_steps": 38160, "loss": 0.4121, "lr": 4.8822897435978586e-05, "epoch": 3.7657232704402515, "percentage": 18.83, "elapsed_time": "0:27:07", "remaining_time": "1:56:54", "throughput": 2880.54, "total_tokens": 4686872} {"current_steps": 7190, "total_steps": 38160, "loss": 0.4003, "lr": 4.8819427672227264e-05, "epoch": 3.768343815513627, "percentage": 18.84, "elapsed_time": "0:27:08", "remaining_time": "1:56:53", "throughput": 2880.83, "total_tokens": 4690424} {"current_steps": 7195, "total_steps": 38160, "loss": 0.436, "lr": 4.881595292572341e-05, "epoch": 3.7709643605870022, "percentage": 18.85, "elapsed_time": "0:27:09", "remaining_time": "1:56:51", "throughput": 2880.41, "total_tokens": 4692824} {"current_steps": 7200, "total_steps": 38160, "loss": 0.4574, "lr": 4.881247319719392e-05, "epoch": 3.7735849056603774, "percentage": 18.87, "elapsed_time": "0:27:10", "remaining_time": "1:56:50", "throughput": 2880.66, "total_tokens": 4696440} {"current_steps": 7205, "total_steps": 38160, "loss": 0.3708, "lr": 4.88089884873667e-05, "epoch": 3.7762054507337526, "percentage": 18.88, "elapsed_time": "0:27:11", "remaining_time": "1:56:49", "throughput": 2881.08, "total_tokens": 4700440} {"current_steps": 7210, "total_steps": 38160, "loss": 0.3679, "lr": 4.880549879697071e-05, "epoch": 3.7788259958071277, "percentage": 18.89, "elapsed_time": "0:27:12", "remaining_time": "1:56:47", "throughput": 2880.97, "total_tokens": 4703320} {"current_steps": 7215, "total_steps": 38160, "loss": 0.5033, "lr": 4.8802004126735965e-05, "epoch": 3.781446540880503, "percentage": 18.91, "elapsed_time": "0:27:13", "remaining_time": "1:56:46", "throughput": 2881.02, "total_tokens": 4706552} {"current_steps": 7220, "total_steps": 38160, "loss": 0.3384, "lr": 4.87985044773935e-05, "epoch": 3.7840670859538785, "percentage": 18.92, "elapsed_time": "0:27:14", "remaining_time": "1:56:45", "throughput": 2880.95, "total_tokens": 4709592} {"current_steps": 7225, "total_steps": 38160, "loss": 0.4831, "lr": 4.879499984967541e-05, "epoch": 3.7866876310272537, "percentage": 18.93, "elapsed_time": "0:27:15", "remaining_time": "1:56:44", "throughput": 2880.71, "total_tokens": 4712344} {"current_steps": 7230, "total_steps": 38160, "loss": 0.4243, "lr": 4.8791490244314824e-05, "epoch": 3.789308176100629, "percentage": 18.95, "elapsed_time": "0:27:16", "remaining_time": "1:56:42", "throughput": 2880.46, "total_tokens": 4715000} {"current_steps": 7235, "total_steps": 38160, "loss": 0.3807, "lr": 4.8787975662045904e-05, "epoch": 3.791928721174004, "percentage": 18.96, "elapsed_time": "0:27:18", "remaining_time": "1:56:41", "throughput": 2880.7, "total_tokens": 4718904} {"current_steps": 7240, "total_steps": 38160, "loss": 0.4805, "lr": 4.878445610360386e-05, "epoch": 3.7945492662473796, "percentage": 18.97, "elapsed_time": "0:27:19", "remaining_time": "1:56:40", "throughput": 2880.5, "total_tokens": 4721656} {"current_steps": 7245, "total_steps": 38160, "loss": 0.4882, "lr": 4.878093156972494e-05, "epoch": 3.797169811320755, "percentage": 18.99, "elapsed_time": "0:27:20", "remaining_time": "1:56:40", "throughput": 2880.87, "total_tokens": 4726264} {"current_steps": 7250, "total_steps": 38160, "loss": 0.3399, "lr": 4.877740206114645e-05, "epoch": 3.79979035639413, "percentage": 19.0, "elapsed_time": "0:27:21", "remaining_time": "1:56:39", "throughput": 2880.7, "total_tokens": 4729112} {"current_steps": 7255, "total_steps": 38160, "loss": 0.4651, "lr": 4.8773867578606716e-05, "epoch": 3.802410901467505, "percentage": 19.01, "elapsed_time": "0:27:22", "remaining_time": "1:56:37", "throughput": 2880.51, "total_tokens": 4731832} {"current_steps": 7260, "total_steps": 38160, "loss": 0.4882, "lr": 4.877032812284511e-05, "epoch": 3.8050314465408803, "percentage": 19.03, "elapsed_time": "0:27:24", "remaining_time": "1:56:39", "throughput": 2881.21, "total_tokens": 4738136} {"current_steps": 7265, "total_steps": 38160, "loss": 0.3604, "lr": 4.876678369460205e-05, "epoch": 3.8076519916142555, "percentage": 19.04, "elapsed_time": "0:27:25", "remaining_time": "1:56:38", "throughput": 2881.05, "total_tokens": 4741080} {"current_steps": 7270, "total_steps": 38160, "loss": 0.3004, "lr": 4.8763234294618985e-05, "epoch": 3.810272536687631, "percentage": 19.05, "elapsed_time": "0:27:26", "remaining_time": "1:56:36", "throughput": 2881.24, "total_tokens": 4744472} {"current_steps": 7275, "total_steps": 38160, "loss": 0.3479, "lr": 4.875967992363841e-05, "epoch": 3.8128930817610063, "percentage": 19.06, "elapsed_time": "0:27:27", "remaining_time": "1:56:35", "throughput": 2881.66, "total_tokens": 4748664} {"current_steps": 7280, "total_steps": 38160, "loss": 0.4161, "lr": 4.875612058240386e-05, "epoch": 3.8155136268343814, "percentage": 19.08, "elapsed_time": "0:27:28", "remaining_time": "1:56:34", "throughput": 2881.59, "total_tokens": 4751704} {"current_steps": 7285, "total_steps": 38160, "loss": 0.4083, "lr": 4.875255627165991e-05, "epoch": 3.818134171907757, "percentage": 19.09, "elapsed_time": "0:27:30", "remaining_time": "1:56:33", "throughput": 2881.15, "total_tokens": 4754104} {"current_steps": 7290, "total_steps": 38160, "loss": 0.3665, "lr": 4.874898699215217e-05, "epoch": 3.8207547169811322, "percentage": 19.1, "elapsed_time": "0:27:31", "remaining_time": "1:56:31", "throughput": 2881.37, "total_tokens": 4757528} {"current_steps": 7295, "total_steps": 38160, "loss": 0.5335, "lr": 4.8745412744627296e-05, "epoch": 3.8233752620545074, "percentage": 19.12, "elapsed_time": "0:27:32", "remaining_time": "1:56:30", "throughput": 2881.7, "total_tokens": 4761208} {"current_steps": 7300, "total_steps": 38160, "loss": 0.3948, "lr": 4.874183352983297e-05, "epoch": 3.8259958071278826, "percentage": 19.13, "elapsed_time": "0:27:33", "remaining_time": "1:56:29", "throughput": 2881.56, "total_tokens": 4764088} {"current_steps": 7305, "total_steps": 38160, "loss": 0.4663, "lr": 4.873824934851794e-05, "epoch": 3.8286163522012577, "percentage": 19.14, "elapsed_time": "0:27:34", "remaining_time": "1:56:27", "throughput": 2881.58, "total_tokens": 4767352} {"current_steps": 7310, "total_steps": 38160, "loss": 0.4121, "lr": 4.873466020143196e-05, "epoch": 3.831236897274633, "percentage": 19.16, "elapsed_time": "0:27:35", "remaining_time": "1:56:26", "throughput": 2881.63, "total_tokens": 4770648} {"current_steps": 7315, "total_steps": 38160, "loss": 0.3929, "lr": 4.873106608932585e-05, "epoch": 3.8338574423480085, "percentage": 19.17, "elapsed_time": "0:27:37", "remaining_time": "1:56:29", "throughput": 2882.33, "total_tokens": 4777624} {"current_steps": 7320, "total_steps": 38160, "loss": 0.491, "lr": 4.872746701295145e-05, "epoch": 3.8364779874213837, "percentage": 19.18, "elapsed_time": "0:27:38", "remaining_time": "1:56:27", "throughput": 2882.16, "total_tokens": 4780376} {"current_steps": 7325, "total_steps": 38160, "loss": 0.3859, "lr": 4.872386297306165e-05, "epoch": 3.839098532494759, "percentage": 19.2, "elapsed_time": "0:27:39", "remaining_time": "1:56:26", "throughput": 2881.96, "total_tokens": 4783096} {"current_steps": 7330, "total_steps": 38160, "loss": 0.2904, "lr": 4.872025397041037e-05, "epoch": 3.841719077568134, "percentage": 19.21, "elapsed_time": "0:27:40", "remaining_time": "1:56:25", "throughput": 2882.43, "total_tokens": 4787000} {"current_steps": 7335, "total_steps": 38160, "loss": 0.4253, "lr": 4.871664000575258e-05, "epoch": 3.8443396226415096, "percentage": 19.22, "elapsed_time": "0:27:41", "remaining_time": "1:56:23", "throughput": 2882.51, "total_tokens": 4790168} {"current_steps": 7340, "total_steps": 38160, "loss": 0.464, "lr": 4.871302107984427e-05, "epoch": 3.846960167714885, "percentage": 19.23, "elapsed_time": "0:27:42", "remaining_time": "1:56:22", "throughput": 2882.83, "total_tokens": 4793944} {"current_steps": 7345, "total_steps": 38160, "loss": 0.3362, "lr": 4.8709397193442474e-05, "epoch": 3.84958071278826, "percentage": 19.25, "elapsed_time": "0:27:43", "remaining_time": "1:56:20", "throughput": 2882.88, "total_tokens": 4797016} {"current_steps": 7350, "total_steps": 38160, "loss": 0.4235, "lr": 4.870576834730529e-05, "epoch": 3.852201257861635, "percentage": 19.26, "elapsed_time": "0:27:45", "remaining_time": "1:56:19", "throughput": 2883.0, "total_tokens": 4800216} {"current_steps": 7355, "total_steps": 38160, "loss": 0.326, "lr": 4.8702134542191816e-05, "epoch": 3.8548218029350103, "percentage": 19.27, "elapsed_time": "0:27:46", "remaining_time": "1:56:18", "throughput": 2883.4, "total_tokens": 4803992} {"current_steps": 7360, "total_steps": 38160, "loss": 0.3882, "lr": 4.86984957788622e-05, "epoch": 3.8574423480083855, "percentage": 19.29, "elapsed_time": "0:27:47", "remaining_time": "1:56:16", "throughput": 2883.32, "total_tokens": 4806872} {"current_steps": 7365, "total_steps": 38160, "loss": 0.263, "lr": 4.869485205807763e-05, "epoch": 3.860062893081761, "percentage": 19.3, "elapsed_time": "0:27:48", "remaining_time": "1:56:15", "throughput": 2883.35, "total_tokens": 4809912} {"current_steps": 7370, "total_steps": 38160, "loss": 0.2857, "lr": 4.869120338060034e-05, "epoch": 3.8626834381551363, "percentage": 19.31, "elapsed_time": "0:27:49", "remaining_time": "1:56:16", "throughput": 2884.6, "total_tokens": 4816984} {"current_steps": 7375, "total_steps": 38160, "loss": 0.4676, "lr": 4.8687549747193585e-05, "epoch": 3.8653039832285114, "percentage": 19.33, "elapsed_time": "0:27:50", "remaining_time": "1:56:15", "throughput": 2884.27, "total_tokens": 4819608} {"current_steps": 7380, "total_steps": 38160, "loss": 0.3482, "lr": 4.868389115862166e-05, "epoch": 3.867924528301887, "percentage": 19.34, "elapsed_time": "0:27:52", "remaining_time": "1:56:13", "throughput": 2884.62, "total_tokens": 4823448} {"current_steps": 7385, "total_steps": 38160, "loss": 0.4186, "lr": 4.868022761564991e-05, "epoch": 3.870545073375262, "percentage": 19.35, "elapsed_time": "0:27:53", "remaining_time": "1:56:12", "throughput": 2884.49, "total_tokens": 4826328} {"current_steps": 7390, "total_steps": 38160, "loss": 0.4321, "lr": 4.8676559119044696e-05, "epoch": 3.8731656184486374, "percentage": 19.37, "elapsed_time": "0:27:54", "remaining_time": "1:56:11", "throughput": 2884.25, "total_tokens": 4829048} {"current_steps": 7395, "total_steps": 38160, "loss": 0.3703, "lr": 4.867288566957344e-05, "epoch": 3.8757861635220126, "percentage": 19.38, "elapsed_time": "0:27:55", "remaining_time": "1:56:10", "throughput": 2884.49, "total_tokens": 4833048} {"current_steps": 7400, "total_steps": 38160, "loss": 0.354, "lr": 4.866920726800457e-05, "epoch": 3.8784067085953877, "percentage": 19.39, "elapsed_time": "0:27:56", "remaining_time": "1:56:09", "throughput": 2884.39, "total_tokens": 4836184} {"current_steps": 7405, "total_steps": 38160, "loss": 0.4082, "lr": 4.8665523915107576e-05, "epoch": 3.881027253668763, "percentage": 19.41, "elapsed_time": "0:27:57", "remaining_time": "1:56:08", "throughput": 2884.68, "total_tokens": 4839896} {"current_steps": 7410, "total_steps": 38160, "loss": 0.3487, "lr": 4.866183561165296e-05, "epoch": 3.8836477987421385, "percentage": 19.42, "elapsed_time": "0:27:58", "remaining_time": "1:56:07", "throughput": 2884.54, "total_tokens": 4842936} {"current_steps": 7415, "total_steps": 38160, "loss": 0.5048, "lr": 4.86581423584123e-05, "epoch": 3.8862683438155137, "percentage": 19.43, "elapsed_time": "0:28:00", "remaining_time": "1:56:06", "throughput": 2884.57, "total_tokens": 4846200} {"current_steps": 7420, "total_steps": 38160, "loss": 0.4174, "lr": 4.8654444156158154e-05, "epoch": 3.888888888888889, "percentage": 19.44, "elapsed_time": "0:28:01", "remaining_time": "1:56:04", "throughput": 2884.57, "total_tokens": 4849336} {"current_steps": 7425, "total_steps": 38160, "loss": 0.4052, "lr": 4.865074100566415e-05, "epoch": 3.891509433962264, "percentage": 19.46, "elapsed_time": "0:28:02", "remaining_time": "1:56:03", "throughput": 2884.69, "total_tokens": 4852632} {"current_steps": 7430, "total_steps": 38160, "loss": 0.4161, "lr": 4.864703290770495e-05, "epoch": 3.8941299790356396, "percentage": 19.47, "elapsed_time": "0:28:03", "remaining_time": "1:56:01", "throughput": 2884.53, "total_tokens": 4855384} {"current_steps": 7435, "total_steps": 38160, "loss": 0.442, "lr": 4.864331986305626e-05, "epoch": 3.896750524109015, "percentage": 19.48, "elapsed_time": "0:28:04", "remaining_time": "1:56:00", "throughput": 2884.87, "total_tokens": 4858936} {"current_steps": 7440, "total_steps": 38160, "loss": 0.4409, "lr": 4.8639601872494775e-05, "epoch": 3.89937106918239, "percentage": 19.5, "elapsed_time": "0:28:05", "remaining_time": "1:55:59", "throughput": 2885.05, "total_tokens": 4862488} {"current_steps": 7445, "total_steps": 38160, "loss": 0.3731, "lr": 4.8635878936798287e-05, "epoch": 3.901991614255765, "percentage": 19.51, "elapsed_time": "0:28:06", "remaining_time": "1:55:57", "throughput": 2884.93, "total_tokens": 4865240} {"current_steps": 7450, "total_steps": 38160, "loss": 0.3726, "lr": 4.863215105674557e-05, "epoch": 3.9046121593291403, "percentage": 19.52, "elapsed_time": "0:28:07", "remaining_time": "1:55:56", "throughput": 2884.8, "total_tokens": 4868152} {"current_steps": 7455, "total_steps": 38160, "loss": 0.2984, "lr": 4.8628418233116457e-05, "epoch": 3.9072327044025155, "percentage": 19.54, "elapsed_time": "0:28:08", "remaining_time": "1:55:54", "throughput": 2884.6, "total_tokens": 4870808} {"current_steps": 7460, "total_steps": 38160, "loss": 0.377, "lr": 4.8624680466691824e-05, "epoch": 3.909853249475891, "percentage": 19.55, "elapsed_time": "0:28:09", "remaining_time": "1:55:53", "throughput": 2884.7, "total_tokens": 4873944} {"current_steps": 7465, "total_steps": 38160, "loss": 0.46, "lr": 4.862093775825356e-05, "epoch": 3.9124737945492662, "percentage": 19.56, "elapsed_time": "0:28:10", "remaining_time": "1:55:51", "throughput": 2884.94, "total_tokens": 4877528} {"current_steps": 7470, "total_steps": 38160, "loss": 0.3559, "lr": 4.86171901085846e-05, "epoch": 3.9150943396226414, "percentage": 19.58, "elapsed_time": "0:28:11", "remaining_time": "1:55:50", "throughput": 2884.92, "total_tokens": 4880504} {"current_steps": 7475, "total_steps": 38160, "loss": 0.3706, "lr": 4.861343751846891e-05, "epoch": 3.917714884696017, "percentage": 19.59, "elapsed_time": "0:28:12", "remaining_time": "1:55:49", "throughput": 2885.25, "total_tokens": 4884312} {"current_steps": 7480, "total_steps": 38160, "loss": 0.3292, "lr": 4.860967998869148e-05, "epoch": 3.920335429769392, "percentage": 19.6, "elapsed_time": "0:28:13", "remaining_time": "1:55:47", "throughput": 2885.11, "total_tokens": 4887032} {"current_steps": 7485, "total_steps": 38160, "loss": 0.462, "lr": 4.860591752003836e-05, "epoch": 3.9229559748427674, "percentage": 19.61, "elapsed_time": "0:28:14", "remaining_time": "1:55:46", "throughput": 2884.96, "total_tokens": 4889976} {"current_steps": 7490, "total_steps": 38160, "loss": 0.5028, "lr": 4.8602150113296596e-05, "epoch": 3.9255765199161425, "percentage": 19.63, "elapsed_time": "0:28:16", "remaining_time": "1:55:45", "throughput": 2884.69, "total_tokens": 4892600} {"current_steps": 7495, "total_steps": 38160, "loss": 0.3919, "lr": 4.8598377769254305e-05, "epoch": 3.9281970649895177, "percentage": 19.64, "elapsed_time": "0:28:17", "remaining_time": "1:55:43", "throughput": 2884.69, "total_tokens": 4895640} {"current_steps": 7500, "total_steps": 38160, "loss": 0.3326, "lr": 4.85946004887006e-05, "epoch": 3.930817610062893, "percentage": 19.65, "elapsed_time": "0:28:18", "remaining_time": "1:55:42", "throughput": 2884.44, "total_tokens": 4898200} {"current_steps": 7505, "total_steps": 38160, "loss": 0.3464, "lr": 4.859081827242566e-05, "epoch": 3.9334381551362685, "percentage": 19.67, "elapsed_time": "0:28:19", "remaining_time": "1:55:40", "throughput": 2884.29, "total_tokens": 4901080} {"current_steps": 7510, "total_steps": 38160, "loss": 0.4483, "lr": 4.858703112122068e-05, "epoch": 3.9360587002096437, "percentage": 19.68, "elapsed_time": "0:28:20", "remaining_time": "1:55:39", "throughput": 2884.38, "total_tokens": 4904280} {"current_steps": 7515, "total_steps": 38160, "loss": 0.5917, "lr": 4.8583239035877876e-05, "epoch": 3.938679245283019, "percentage": 19.69, "elapsed_time": "0:28:21", "remaining_time": "1:55:37", "throughput": 2884.72, "total_tokens": 4907832} {"current_steps": 7520, "total_steps": 38160, "loss": 0.5315, "lr": 4.8579442017190526e-05, "epoch": 3.941299790356394, "percentage": 19.71, "elapsed_time": "0:28:22", "remaining_time": "1:55:36", "throughput": 2884.91, "total_tokens": 4911320} {"current_steps": 7525, "total_steps": 38160, "loss": 0.3883, "lr": 4.8575640065952905e-05, "epoch": 3.9439203354297696, "percentage": 19.72, "elapsed_time": "0:28:23", "remaining_time": "1:55:34", "throughput": 2884.77, "total_tokens": 4914072} {"current_steps": 7530, "total_steps": 38160, "loss": 0.4361, "lr": 4.857183318296035e-05, "epoch": 3.9465408805031448, "percentage": 19.73, "elapsed_time": "0:28:24", "remaining_time": "1:55:34", "throughput": 2885.24, "total_tokens": 4918584} {"current_steps": 7535, "total_steps": 38160, "loss": 0.3783, "lr": 4.856802136900922e-05, "epoch": 3.94916142557652, "percentage": 19.75, "elapsed_time": "0:28:25", "remaining_time": "1:55:32", "throughput": 2885.18, "total_tokens": 4921496} {"current_steps": 7540, "total_steps": 38160, "loss": 0.4312, "lr": 4.856420462489689e-05, "epoch": 3.951781970649895, "percentage": 19.76, "elapsed_time": "0:28:26", "remaining_time": "1:55:31", "throughput": 2885.2, "total_tokens": 4924600} {"current_steps": 7545, "total_steps": 38160, "loss": 0.4034, "lr": 4.856038295142179e-05, "epoch": 3.9544025157232703, "percentage": 19.77, "elapsed_time": "0:28:27", "remaining_time": "1:55:29", "throughput": 2885.17, "total_tokens": 4927512} {"current_steps": 7550, "total_steps": 38160, "loss": 0.396, "lr": 4.855655634938337e-05, "epoch": 3.9570230607966455, "percentage": 19.79, "elapsed_time": "0:28:28", "remaining_time": "1:55:28", "throughput": 2885.07, "total_tokens": 4930360} {"current_steps": 7555, "total_steps": 38160, "loss": 0.3059, "lr": 4.8552724819582106e-05, "epoch": 3.959643605870021, "percentage": 19.8, "elapsed_time": "0:28:29", "remaining_time": "1:55:26", "throughput": 2885.17, "total_tokens": 4933496} {"current_steps": 7560, "total_steps": 38160, "loss": 0.332, "lr": 4.8548888362819515e-05, "epoch": 3.9622641509433962, "percentage": 19.81, "elapsed_time": "0:28:31", "remaining_time": "1:55:25", "throughput": 2884.94, "total_tokens": 4936152} {"current_steps": 7565, "total_steps": 38160, "loss": 0.591, "lr": 4.854504697989814e-05, "epoch": 3.9648846960167714, "percentage": 19.82, "elapsed_time": "0:28:32", "remaining_time": "1:55:23", "throughput": 2885.34, "total_tokens": 4939832} {"current_steps": 7570, "total_steps": 38160, "loss": 0.4302, "lr": 4.8541200671621554e-05, "epoch": 3.967505241090147, "percentage": 19.84, "elapsed_time": "0:28:33", "remaining_time": "1:55:22", "throughput": 2885.56, "total_tokens": 4943192} {"current_steps": 7575, "total_steps": 38160, "loss": 0.3902, "lr": 4.8537349438794354e-05, "epoch": 3.970125786163522, "percentage": 19.85, "elapsed_time": "0:28:34", "remaining_time": "1:55:20", "throughput": 2885.68, "total_tokens": 4946392} {"current_steps": 7580, "total_steps": 38160, "loss": 0.3188, "lr": 4.853349328222219e-05, "epoch": 3.9727463312368974, "percentage": 19.86, "elapsed_time": "0:28:35", "remaining_time": "1:55:19", "throughput": 2885.68, "total_tokens": 4949464} {"current_steps": 7585, "total_steps": 38160, "loss": 0.3333, "lr": 4.8529632202711706e-05, "epoch": 3.9753668763102725, "percentage": 19.88, "elapsed_time": "0:28:36", "remaining_time": "1:55:20", "throughput": 2886.39, "total_tokens": 4955288} {"current_steps": 7590, "total_steps": 38160, "loss": 0.3249, "lr": 4.852576620107061e-05, "epoch": 3.9779874213836477, "percentage": 19.89, "elapsed_time": "0:28:37", "remaining_time": "1:55:18", "throughput": 2886.26, "total_tokens": 4958008} {"current_steps": 7595, "total_steps": 38160, "loss": 0.3146, "lr": 4.8521895278107615e-05, "epoch": 3.980607966457023, "percentage": 19.9, "elapsed_time": "0:28:38", "remaining_time": "1:55:17", "throughput": 2886.46, "total_tokens": 4961400} {"current_steps": 7600, "total_steps": 38160, "loss": 0.4976, "lr": 4.8518019434632484e-05, "epoch": 3.9832285115303985, "percentage": 19.92, "elapsed_time": "0:28:39", "remaining_time": "1:55:15", "throughput": 2886.45, "total_tokens": 4964536} {"current_steps": 7605, "total_steps": 38160, "loss": 0.4981, "lr": 4.8514138671455995e-05, "epoch": 3.9858490566037736, "percentage": 19.93, "elapsed_time": "0:28:41", "remaining_time": "1:55:14", "throughput": 2886.67, "total_tokens": 4968280} {"current_steps": 7610, "total_steps": 38160, "loss": 0.4843, "lr": 4.851025298938996e-05, "epoch": 3.988469601677149, "percentage": 19.94, "elapsed_time": "0:28:42", "remaining_time": "1:55:13", "throughput": 2886.82, "total_tokens": 4971640} {"current_steps": 7615, "total_steps": 38160, "loss": 0.4221, "lr": 4.850636238924722e-05, "epoch": 3.991090146750524, "percentage": 19.96, "elapsed_time": "0:28:43", "remaining_time": "1:55:12", "throughput": 2887.29, "total_tokens": 4975512} {"current_steps": 7620, "total_steps": 38160, "loss": 0.4703, "lr": 4.850246687184163e-05, "epoch": 3.9937106918238996, "percentage": 19.97, "elapsed_time": "0:28:44", "remaining_time": "1:55:10", "throughput": 2887.28, "total_tokens": 4978520} {"current_steps": 7625, "total_steps": 38160, "loss": 0.3305, "lr": 4.849856643798812e-05, "epoch": 3.9963312368972748, "percentage": 19.98, "elapsed_time": "0:28:45", "remaining_time": "1:55:09", "throughput": 2887.46, "total_tokens": 4981944} {"current_steps": 7630, "total_steps": 38160, "loss": 0.3453, "lr": 4.849466108850259e-05, "epoch": 3.99895178197065, "percentage": 19.99, "elapsed_time": "0:28:46", "remaining_time": "1:55:08", "throughput": 2887.24, "total_tokens": 4984632} {"current_steps": 7632, "total_steps": 38160, "eval_loss": 0.47423693537712097, "epoch": 4.0, "percentage": 20.0, "elapsed_time": "0:28:58", "remaining_time": "1:55:55", "throughput": 2866.85, "total_tokens": 4985200} {"current_steps": 7635, "total_steps": 38160, "loss": 0.3711, "lr": 4.8490750824202e-05, "epoch": 4.001572327044025, "percentage": 20.01, "elapsed_time": "0:29:02", "remaining_time": "1:56:07", "throughput": 2861.68, "total_tokens": 4987024} {"current_steps": 7640, "total_steps": 38160, "loss": 0.3108, "lr": 4.8486835645904324e-05, "epoch": 4.0041928721174, "percentage": 20.02, "elapsed_time": "0:29:03", "remaining_time": "1:56:06", "throughput": 2861.26, "total_tokens": 4989552} {"current_steps": 7645, "total_steps": 38160, "loss": 0.5508, "lr": 4.84829155544286e-05, "epoch": 4.006813417190775, "percentage": 20.03, "elapsed_time": "0:29:04", "remaining_time": "1:56:04", "throughput": 2860.94, "total_tokens": 4992080} {"current_steps": 7650, "total_steps": 38160, "loss": 0.512, "lr": 4.847899055059484e-05, "epoch": 4.009433962264151, "percentage": 20.05, "elapsed_time": "0:29:06", "remaining_time": "1:56:03", "throughput": 2860.54, "total_tokens": 4994512} {"current_steps": 7655, "total_steps": 38160, "loss": 0.2413, "lr": 4.847506063522412e-05, "epoch": 4.012054507337526, "percentage": 20.06, "elapsed_time": "0:29:07", "remaining_time": "1:56:02", "throughput": 2860.69, "total_tokens": 4998000} {"current_steps": 7660, "total_steps": 38160, "loss": 0.3379, "lr": 4.847112580913854e-05, "epoch": 4.014675052410902, "percentage": 20.07, "elapsed_time": "0:29:08", "remaining_time": "1:56:00", "throughput": 2861.18, "total_tokens": 5002000} {"current_steps": 7665, "total_steps": 38160, "loss": 0.3241, "lr": 4.846718607316121e-05, "epoch": 4.017295597484277, "percentage": 20.09, "elapsed_time": "0:29:09", "remaining_time": "1:55:59", "throughput": 2861.39, "total_tokens": 5005648} {"current_steps": 7670, "total_steps": 38160, "loss": 0.4635, "lr": 4.846324142811628e-05, "epoch": 4.019916142557652, "percentage": 20.1, "elapsed_time": "0:29:10", "remaining_time": "1:55:58", "throughput": 2861.6, "total_tokens": 5009104} {"current_steps": 7675, "total_steps": 38160, "loss": 0.2832, "lr": 4.8459291874828924e-05, "epoch": 4.022536687631027, "percentage": 20.11, "elapsed_time": "0:29:11", "remaining_time": "1:55:56", "throughput": 2861.72, "total_tokens": 5012304} {"current_steps": 7680, "total_steps": 38160, "loss": 0.4143, "lr": 4.845533741412534e-05, "epoch": 4.0251572327044025, "percentage": 20.13, "elapsed_time": "0:29:12", "remaining_time": "1:55:55", "throughput": 2861.35, "total_tokens": 5014608} {"current_steps": 7685, "total_steps": 38160, "loss": 0.3892, "lr": 4.845137804683277e-05, "epoch": 4.027777777777778, "percentage": 20.14, "elapsed_time": "0:29:13", "remaining_time": "1:55:54", "throughput": 2861.36, "total_tokens": 5017776} {"current_steps": 7690, "total_steps": 38160, "loss": 0.4519, "lr": 4.844741377377946e-05, "epoch": 4.030398322851153, "percentage": 20.15, "elapsed_time": "0:29:14", "remaining_time": "1:55:52", "throughput": 2861.19, "total_tokens": 5020432} {"current_steps": 7695, "total_steps": 38160, "loss": 0.242, "lr": 4.844344459579469e-05, "epoch": 4.033018867924528, "percentage": 20.17, "elapsed_time": "0:29:15", "remaining_time": "1:55:51", "throughput": 2861.28, "total_tokens": 5023824} {"current_steps": 7700, "total_steps": 38160, "loss": 0.3673, "lr": 4.8439470513708766e-05, "epoch": 4.035639412997903, "percentage": 20.18, "elapsed_time": "0:29:16", "remaining_time": "1:55:50", "throughput": 2861.46, "total_tokens": 5027344} {"current_steps": 7705, "total_steps": 38160, "loss": 0.3733, "lr": 4.8435491528353026e-05, "epoch": 4.038259958071279, "percentage": 20.19, "elapsed_time": "0:29:17", "remaining_time": "1:55:48", "throughput": 2861.77, "total_tokens": 5030928} {"current_steps": 7710, "total_steps": 38160, "loss": 0.3052, "lr": 4.843150764055982e-05, "epoch": 4.040880503144654, "percentage": 20.2, "elapsed_time": "0:29:19", "remaining_time": "1:55:47", "throughput": 2861.97, "total_tokens": 5034320} {"current_steps": 7715, "total_steps": 38160, "loss": 0.3427, "lr": 4.842751885116254e-05, "epoch": 4.04350104821803, "percentage": 20.22, "elapsed_time": "0:29:20", "remaining_time": "1:55:45", "throughput": 2862.04, "total_tokens": 5037456} {"current_steps": 7720, "total_steps": 38160, "loss": 0.269, "lr": 4.842352516099559e-05, "epoch": 4.046121593291405, "percentage": 20.23, "elapsed_time": "0:29:21", "remaining_time": "1:55:44", "throughput": 2862.23, "total_tokens": 5040784} {"current_steps": 7725, "total_steps": 38160, "loss": 0.4806, "lr": 4.84195265708944e-05, "epoch": 4.04874213836478, "percentage": 20.24, "elapsed_time": "0:29:22", "remaining_time": "1:55:42", "throughput": 2862.42, "total_tokens": 5044176} {"current_steps": 7730, "total_steps": 38160, "loss": 0.4261, "lr": 4.841552308169545e-05, "epoch": 4.051362683438155, "percentage": 20.26, "elapsed_time": "0:29:23", "remaining_time": "1:55:41", "throughput": 2862.52, "total_tokens": 5047376} {"current_steps": 7735, "total_steps": 38160, "loss": 0.3596, "lr": 4.841151469423619e-05, "epoch": 4.05398322851153, "percentage": 20.27, "elapsed_time": "0:29:24", "remaining_time": "1:55:42", "throughput": 2863.33, "total_tokens": 5053712} {"current_steps": 7740, "total_steps": 38160, "loss": 0.3722, "lr": 4.840750140935516e-05, "epoch": 4.056603773584905, "percentage": 20.28, "elapsed_time": "0:29:26", "remaining_time": "1:55:41", "throughput": 2863.75, "total_tokens": 5057968} {"current_steps": 7745, "total_steps": 38160, "loss": 0.4813, "lr": 4.840348322789189e-05, "epoch": 4.059224318658281, "percentage": 20.3, "elapsed_time": "0:29:27", "remaining_time": "1:55:40", "throughput": 2863.86, "total_tokens": 5061328} {"current_steps": 7750, "total_steps": 38160, "loss": 0.4019, "lr": 4.839946015068692e-05, "epoch": 4.061844863731656, "percentage": 20.31, "elapsed_time": "0:29:28", "remaining_time": "1:55:38", "throughput": 2863.87, "total_tokens": 5064464} {"current_steps": 7755, "total_steps": 38160, "loss": 0.2879, "lr": 4.839543217858184e-05, "epoch": 4.064465408805032, "percentage": 20.32, "elapsed_time": "0:29:29", "remaining_time": "1:55:37", "throughput": 2863.75, "total_tokens": 5067344} {"current_steps": 7760, "total_steps": 38160, "loss": 0.2937, "lr": 4.839139931241926e-05, "epoch": 4.067085953878407, "percentage": 20.34, "elapsed_time": "0:29:30", "remaining_time": "1:55:36", "throughput": 2863.8, "total_tokens": 5070512} {"current_steps": 7765, "total_steps": 38160, "loss": 0.2993, "lr": 4.838736155304281e-05, "epoch": 4.069706498951782, "percentage": 20.35, "elapsed_time": "0:29:31", "remaining_time": "1:55:34", "throughput": 2863.81, "total_tokens": 5073488} {"current_steps": 7770, "total_steps": 38160, "loss": 0.3447, "lr": 4.8383318901297135e-05, "epoch": 4.072327044025157, "percentage": 20.36, "elapsed_time": "0:29:33", "remaining_time": "1:55:35", "throughput": 2864.83, "total_tokens": 5079984} {"current_steps": 7775, "total_steps": 38160, "loss": 0.37, "lr": 4.837927135802792e-05, "epoch": 4.0749475890985325, "percentage": 20.37, "elapsed_time": "0:29:34", "remaining_time": "1:55:34", "throughput": 2864.76, "total_tokens": 5083056} {"current_steps": 7780, "total_steps": 38160, "loss": 0.3693, "lr": 4.8375218924081856e-05, "epoch": 4.077568134171908, "percentage": 20.39, "elapsed_time": "0:29:35", "remaining_time": "1:55:32", "throughput": 2864.62, "total_tokens": 5085904} {"current_steps": 7785, "total_steps": 38160, "loss": 0.3297, "lr": 4.837116160030668e-05, "epoch": 4.080188679245283, "percentage": 20.4, "elapsed_time": "0:29:36", "remaining_time": "1:55:31", "throughput": 2864.27, "total_tokens": 5088368} {"current_steps": 7790, "total_steps": 38160, "loss": 0.3393, "lr": 4.8367099387551126e-05, "epoch": 4.082809224318658, "percentage": 20.41, "elapsed_time": "0:29:37", "remaining_time": "1:55:30", "throughput": 2864.0, "total_tokens": 5091088} {"current_steps": 7795, "total_steps": 38160, "loss": 0.366, "lr": 4.8363032286664964e-05, "epoch": 4.085429769392033, "percentage": 20.43, "elapsed_time": "0:29:38", "remaining_time": "1:55:29", "throughput": 2864.33, "total_tokens": 5094960} {"current_steps": 7800, "total_steps": 38160, "loss": 0.3557, "lr": 4.835896029849899e-05, "epoch": 4.088050314465409, "percentage": 20.44, "elapsed_time": "0:29:39", "remaining_time": "1:55:27", "throughput": 2864.58, "total_tokens": 5098352} {"current_steps": 7805, "total_steps": 38160, "loss": 0.362, "lr": 4.835488342390502e-05, "epoch": 4.090670859538784, "percentage": 20.45, "elapsed_time": "0:29:41", "remaining_time": "1:55:26", "throughput": 2864.91, "total_tokens": 5102416} {"current_steps": 7810, "total_steps": 38160, "loss": 0.4739, "lr": 4.835080166373587e-05, "epoch": 4.09329140461216, "percentage": 20.47, "elapsed_time": "0:29:42", "remaining_time": "1:55:25", "throughput": 2864.66, "total_tokens": 5105072} {"current_steps": 7815, "total_steps": 38160, "loss": 0.3565, "lr": 4.834671501884542e-05, "epoch": 4.095911949685535, "percentage": 20.48, "elapsed_time": "0:29:43", "remaining_time": "1:55:23", "throughput": 2864.86, "total_tokens": 5108528} {"current_steps": 7820, "total_steps": 38160, "loss": 0.4564, "lr": 4.8342623490088543e-05, "epoch": 4.09853249475891, "percentage": 20.49, "elapsed_time": "0:29:44", "remaining_time": "1:55:22", "throughput": 2865.18, "total_tokens": 5112176} {"current_steps": 7825, "total_steps": 38160, "loss": 0.3747, "lr": 4.833852707832114e-05, "epoch": 4.101153039832285, "percentage": 20.51, "elapsed_time": "0:29:45", "remaining_time": "1:55:21", "throughput": 2865.73, "total_tokens": 5116848} {"current_steps": 7830, "total_steps": 38160, "loss": 0.3673, "lr": 4.833442578440013e-05, "epoch": 4.10377358490566, "percentage": 20.52, "elapsed_time": "0:29:46", "remaining_time": "1:55:20", "throughput": 2866.1, "total_tokens": 5120464} {"current_steps": 7835, "total_steps": 38160, "loss": 0.312, "lr": 4.833031960918346e-05, "epoch": 4.106394129979035, "percentage": 20.53, "elapsed_time": "0:29:47", "remaining_time": "1:55:18", "throughput": 2866.08, "total_tokens": 5123312} {"current_steps": 7840, "total_steps": 38160, "loss": 0.3564, "lr": 4.8326208553530095e-05, "epoch": 4.109014675052411, "percentage": 20.55, "elapsed_time": "0:29:48", "remaining_time": "1:55:17", "throughput": 2866.41, "total_tokens": 5127088} {"current_steps": 7845, "total_steps": 38160, "loss": 0.3596, "lr": 4.832209261830002e-05, "epoch": 4.111635220125786, "percentage": 20.56, "elapsed_time": "0:29:49", "remaining_time": "1:55:16", "throughput": 2866.5, "total_tokens": 5130384} {"current_steps": 7850, "total_steps": 38160, "loss": 0.3184, "lr": 4.831797180435423e-05, "epoch": 4.114255765199162, "percentage": 20.57, "elapsed_time": "0:29:50", "remaining_time": "1:55:14", "throughput": 2866.88, "total_tokens": 5134288} {"current_steps": 7855, "total_steps": 38160, "loss": 0.4354, "lr": 4.831384611255478e-05, "epoch": 4.116876310272537, "percentage": 20.58, "elapsed_time": "0:29:51", "remaining_time": "1:55:13", "throughput": 2866.96, "total_tokens": 5137392} {"current_steps": 7860, "total_steps": 38160, "loss": 0.3599, "lr": 4.8309715543764697e-05, "epoch": 4.119496855345912, "percentage": 20.6, "elapsed_time": "0:29:52", "remaining_time": "1:55:11", "throughput": 2866.69, "total_tokens": 5139824} {"current_steps": 7865, "total_steps": 38160, "loss": 0.4276, "lr": 4.8305580098848046e-05, "epoch": 4.122117400419287, "percentage": 20.61, "elapsed_time": "0:29:53", "remaining_time": "1:55:10", "throughput": 2866.95, "total_tokens": 5143280} {"current_steps": 7870, "total_steps": 38160, "loss": 0.4308, "lr": 4.830143977866993e-05, "epoch": 4.1247379454926625, "percentage": 20.62, "elapsed_time": "0:29:55", "remaining_time": "1:55:08", "throughput": 2866.56, "total_tokens": 5145584} {"current_steps": 7875, "total_steps": 38160, "loss": 0.3316, "lr": 4.829729458409645e-05, "epoch": 4.127358490566038, "percentage": 20.64, "elapsed_time": "0:29:56", "remaining_time": "1:55:07", "throughput": 2866.42, "total_tokens": 5148240} {"current_steps": 7880, "total_steps": 38160, "loss": 0.4417, "lr": 4.8293144515994725e-05, "epoch": 4.129979035639413, "percentage": 20.65, "elapsed_time": "0:29:57", "remaining_time": "1:55:05", "throughput": 2866.66, "total_tokens": 5151632} {"current_steps": 7885, "total_steps": 38160, "loss": 0.3808, "lr": 4.828898957523292e-05, "epoch": 4.132599580712788, "percentage": 20.66, "elapsed_time": "0:29:58", "remaining_time": "1:55:03", "throughput": 2866.66, "total_tokens": 5154576} {"current_steps": 7890, "total_steps": 38160, "loss": 0.3412, "lr": 4.8284829762680183e-05, "epoch": 4.135220125786163, "percentage": 20.68, "elapsed_time": "0:29:59", "remaining_time": "1:55:02", "throughput": 2867.01, "total_tokens": 5158224} {"current_steps": 7895, "total_steps": 38160, "loss": 0.3147, "lr": 4.828066507920671e-05, "epoch": 4.137840670859539, "percentage": 20.69, "elapsed_time": "0:30:00", "remaining_time": "1:55:01", "throughput": 2867.02, "total_tokens": 5161360} {"current_steps": 7900, "total_steps": 38160, "loss": 0.2949, "lr": 4.82764955256837e-05, "epoch": 4.140461215932914, "percentage": 20.7, "elapsed_time": "0:30:01", "remaining_time": "1:54:59", "throughput": 2867.18, "total_tokens": 5164656} {"current_steps": 7905, "total_steps": 38160, "loss": 0.3647, "lr": 4.827232110298338e-05, "epoch": 4.1430817610062896, "percentage": 20.72, "elapsed_time": "0:30:02", "remaining_time": "1:54:58", "throughput": 2867.55, "total_tokens": 5168336} {"current_steps": 7910, "total_steps": 38160, "loss": 0.3497, "lr": 4.8268141811978995e-05, "epoch": 4.145702306079665, "percentage": 20.73, "elapsed_time": "0:30:03", "remaining_time": "1:54:56", "throughput": 2867.26, "total_tokens": 5170736} {"current_steps": 7915, "total_steps": 38160, "loss": 0.2175, "lr": 4.826395765354479e-05, "epoch": 4.14832285115304, "percentage": 20.74, "elapsed_time": "0:30:04", "remaining_time": "1:54:55", "throughput": 2867.11, "total_tokens": 5173424} {"current_steps": 7920, "total_steps": 38160, "loss": 0.3003, "lr": 4.825976862855606e-05, "epoch": 4.150943396226415, "percentage": 20.75, "elapsed_time": "0:30:05", "remaining_time": "1:54:53", "throughput": 2866.85, "total_tokens": 5175856} {"current_steps": 7925, "total_steps": 38160, "loss": 0.3216, "lr": 4.8255574737889094e-05, "epoch": 4.15356394129979, "percentage": 20.77, "elapsed_time": "0:30:06", "remaining_time": "1:54:51", "throughput": 2866.8, "total_tokens": 5178672} {"current_steps": 7930, "total_steps": 38160, "loss": 0.3153, "lr": 4.82513759824212e-05, "epoch": 4.156184486373165, "percentage": 20.78, "elapsed_time": "0:30:07", "remaining_time": "1:54:51", "throughput": 2867.71, "total_tokens": 5184496} {"current_steps": 7935, "total_steps": 38160, "loss": 0.4007, "lr": 4.824717236303072e-05, "epoch": 4.158805031446541, "percentage": 20.79, "elapsed_time": "0:30:09", "remaining_time": "1:54:50", "throughput": 2867.91, "total_tokens": 5188144} {"current_steps": 7940, "total_steps": 38160, "loss": 0.3471, "lr": 4.8242963880597005e-05, "epoch": 4.161425576519916, "percentage": 20.81, "elapsed_time": "0:30:10", "remaining_time": "1:54:49", "throughput": 2868.27, "total_tokens": 5192112} {"current_steps": 7945, "total_steps": 38160, "loss": 0.3807, "lr": 4.823875053600041e-05, "epoch": 4.164046121593292, "percentage": 20.82, "elapsed_time": "0:30:11", "remaining_time": "1:54:48", "throughput": 2867.82, "total_tokens": 5194320} {"current_steps": 7950, "total_steps": 38160, "loss": 0.3488, "lr": 4.823453233012233e-05, "epoch": 4.166666666666667, "percentage": 20.83, "elapsed_time": "0:30:12", "remaining_time": "1:54:46", "throughput": 2867.87, "total_tokens": 5197456} {"current_steps": 7955, "total_steps": 38160, "loss": 0.3813, "lr": 4.8230309263845155e-05, "epoch": 4.169287211740042, "percentage": 20.85, "elapsed_time": "0:30:13", "remaining_time": "1:54:45", "throughput": 2867.42, "total_tokens": 5199792} {"current_steps": 7960, "total_steps": 38160, "loss": 0.4268, "lr": 4.822608133805231e-05, "epoch": 4.171907756813417, "percentage": 20.86, "elapsed_time": "0:30:14", "remaining_time": "1:54:43", "throughput": 2867.37, "total_tokens": 5202672} {"current_steps": 7965, "total_steps": 38160, "loss": 0.4139, "lr": 4.8221848553628226e-05, "epoch": 4.1745283018867925, "percentage": 20.87, "elapsed_time": "0:30:15", "remaining_time": "1:54:42", "throughput": 2867.44, "total_tokens": 5205808} {"current_steps": 7970, "total_steps": 38160, "loss": 0.2531, "lr": 4.8217610911458346e-05, "epoch": 4.177148846960168, "percentage": 20.89, "elapsed_time": "0:30:16", "remaining_time": "1:54:41", "throughput": 2867.06, "total_tokens": 5208176} {"current_steps": 7975, "total_steps": 38160, "loss": 0.3658, "lr": 4.821336841242915e-05, "epoch": 4.179769392033543, "percentage": 20.9, "elapsed_time": "0:30:18", "remaining_time": "1:54:43", "throughput": 2867.9, "total_tokens": 5215376} {"current_steps": 7980, "total_steps": 38160, "loss": 0.3933, "lr": 4.820912105742811e-05, "epoch": 4.182389937106918, "percentage": 20.91, "elapsed_time": "0:30:19", "remaining_time": "1:54:41", "throughput": 2867.68, "total_tokens": 5218064} {"current_steps": 7985, "total_steps": 38160, "loss": 0.3415, "lr": 4.8204868847343736e-05, "epoch": 4.185010482180293, "percentage": 20.93, "elapsed_time": "0:30:20", "remaining_time": "1:54:40", "throughput": 2867.78, "total_tokens": 5221328} {"current_steps": 7990, "total_steps": 38160, "loss": 0.3734, "lr": 4.820061178306553e-05, "epoch": 4.187631027253669, "percentage": 20.94, "elapsed_time": "0:30:21", "remaining_time": "1:54:39", "throughput": 2867.73, "total_tokens": 5224432} {"current_steps": 7995, "total_steps": 38160, "loss": 0.3728, "lr": 4.819634986548403e-05, "epoch": 4.190251572327044, "percentage": 20.95, "elapsed_time": "0:30:22", "remaining_time": "1:54:37", "throughput": 2867.44, "total_tokens": 5226896} {"current_steps": 8000, "total_steps": 38160, "loss": 0.3081, "lr": 4.819208309549077e-05, "epoch": 4.1928721174004195, "percentage": 20.96, "elapsed_time": "0:30:24", "remaining_time": "1:54:37", "throughput": 2867.67, "total_tokens": 5231056} {"current_steps": 8005, "total_steps": 38160, "loss": 0.2997, "lr": 4.8187811473978316e-05, "epoch": 4.195492662473795, "percentage": 20.98, "elapsed_time": "0:30:25", "remaining_time": "1:54:35", "throughput": 2867.94, "total_tokens": 5234480} {"current_steps": 8010, "total_steps": 38160, "loss": 0.4981, "lr": 4.818353500184025e-05, "epoch": 4.19811320754717, "percentage": 20.99, "elapsed_time": "0:30:26", "remaining_time": "1:54:33", "throughput": 2867.6, "total_tokens": 5236816} {"current_steps": 8015, "total_steps": 38160, "loss": 0.3766, "lr": 4.817925367997115e-05, "epoch": 4.200733752620545, "percentage": 21.0, "elapsed_time": "0:30:27", "remaining_time": "1:54:32", "throughput": 2867.48, "total_tokens": 5239600} {"current_steps": 8020, "total_steps": 38160, "loss": 0.4151, "lr": 4.8174967509266615e-05, "epoch": 4.20335429769392, "percentage": 21.02, "elapsed_time": "0:30:28", "remaining_time": "1:54:31", "throughput": 2867.57, "total_tokens": 5242896} {"current_steps": 8025, "total_steps": 38160, "loss": 0.4425, "lr": 4.817067649062328e-05, "epoch": 4.205974842767295, "percentage": 21.03, "elapsed_time": "0:30:29", "remaining_time": "1:54:29", "throughput": 2867.62, "total_tokens": 5245904} {"current_steps": 8030, "total_steps": 38160, "loss": 0.4357, "lr": 4.816638062493876e-05, "epoch": 4.2085953878406706, "percentage": 21.04, "elapsed_time": "0:30:30", "remaining_time": "1:54:28", "throughput": 2867.97, "total_tokens": 5249968} {"current_steps": 8035, "total_steps": 38160, "loss": 0.3264, "lr": 4.8162079913111716e-05, "epoch": 4.211215932914046, "percentage": 21.06, "elapsed_time": "0:30:31", "remaining_time": "1:54:27", "throughput": 2868.1, "total_tokens": 5253680} {"current_steps": 8040, "total_steps": 38160, "loss": 0.5064, "lr": 4.81577743560418e-05, "epoch": 4.213836477987422, "percentage": 21.07, "elapsed_time": "0:30:32", "remaining_time": "1:54:26", "throughput": 2867.86, "total_tokens": 5256144} {"current_steps": 8045, "total_steps": 38160, "loss": 0.2762, "lr": 4.8153463954629684e-05, "epoch": 4.216457023060797, "percentage": 21.08, "elapsed_time": "0:30:34", "remaining_time": "1:54:25", "throughput": 2868.6, "total_tokens": 5261456} {"current_steps": 8050, "total_steps": 38160, "loss": 0.4007, "lr": 4.814914870977706e-05, "epoch": 4.219077568134172, "percentage": 21.1, "elapsed_time": "0:30:35", "remaining_time": "1:54:24", "throughput": 2868.73, "total_tokens": 5264688} {"current_steps": 8055, "total_steps": 38160, "loss": 0.4569, "lr": 4.8144828622386627e-05, "epoch": 4.221698113207547, "percentage": 21.11, "elapsed_time": "0:30:36", "remaining_time": "1:54:22", "throughput": 2868.45, "total_tokens": 5267184} {"current_steps": 8060, "total_steps": 38160, "loss": 0.3461, "lr": 4.8140503693362095e-05, "epoch": 4.2243186582809225, "percentage": 21.12, "elapsed_time": "0:30:37", "remaining_time": "1:54:21", "throughput": 2868.2, "total_tokens": 5269776} {"current_steps": 8065, "total_steps": 38160, "loss": 0.3675, "lr": 4.813617392360818e-05, "epoch": 4.226939203354298, "percentage": 21.13, "elapsed_time": "0:30:38", "remaining_time": "1:54:19", "throughput": 2868.47, "total_tokens": 5273296} {"current_steps": 8070, "total_steps": 38160, "loss": 0.3563, "lr": 4.813183931403065e-05, "epoch": 4.229559748427673, "percentage": 21.15, "elapsed_time": "0:30:39", "remaining_time": "1:54:18", "throughput": 2868.56, "total_tokens": 5276432} {"current_steps": 8075, "total_steps": 38160, "loss": 0.3082, "lr": 4.8127499865536226e-05, "epoch": 4.232180293501048, "percentage": 21.16, "elapsed_time": "0:30:40", "remaining_time": "1:54:17", "throughput": 2868.66, "total_tokens": 5279696} {"current_steps": 8080, "total_steps": 38160, "loss": 0.3465, "lr": 4.812315557903269e-05, "epoch": 4.234800838574423, "percentage": 21.17, "elapsed_time": "0:30:41", "remaining_time": "1:54:15", "throughput": 2868.9, "total_tokens": 5283312} {"current_steps": 8085, "total_steps": 38160, "loss": 0.273, "lr": 4.8118806455428806e-05, "epoch": 4.237421383647799, "percentage": 21.19, "elapsed_time": "0:30:42", "remaining_time": "1:54:14", "throughput": 2868.56, "total_tokens": 5285712} {"current_steps": 8090, "total_steps": 38160, "loss": 0.4171, "lr": 4.811445249563437e-05, "epoch": 4.240041928721174, "percentage": 21.2, "elapsed_time": "0:30:43", "remaining_time": "1:54:12", "throughput": 2868.77, "total_tokens": 5289136} {"current_steps": 8095, "total_steps": 38160, "loss": 0.2031, "lr": 4.811009370056017e-05, "epoch": 4.2426624737945495, "percentage": 21.21, "elapsed_time": "0:30:44", "remaining_time": "1:54:11", "throughput": 2868.9, "total_tokens": 5292528} {"current_steps": 8100, "total_steps": 38160, "loss": 0.4117, "lr": 4.8105730071118016e-05, "epoch": 4.245283018867925, "percentage": 21.23, "elapsed_time": "0:30:45", "remaining_time": "1:54:10", "throughput": 2869.13, "total_tokens": 5295984} {"current_steps": 8105, "total_steps": 38160, "loss": 0.3496, "lr": 4.810136160822074e-05, "epoch": 4.2479035639413, "percentage": 21.24, "elapsed_time": "0:30:46", "remaining_time": "1:54:08", "throughput": 2869.21, "total_tokens": 5299120} {"current_steps": 8110, "total_steps": 38160, "loss": 0.3187, "lr": 4.8096988312782174e-05, "epoch": 4.250524109014675, "percentage": 21.25, "elapsed_time": "0:30:47", "remaining_time": "1:54:07", "throughput": 2869.17, "total_tokens": 5302192} {"current_steps": 8115, "total_steps": 38160, "loss": 0.6206, "lr": 4.809261018571715e-05, "epoch": 4.25314465408805, "percentage": 21.27, "elapsed_time": "0:30:49", "remaining_time": "1:54:05", "throughput": 2868.98, "total_tokens": 5304880} {"current_steps": 8120, "total_steps": 38160, "loss": 0.4106, "lr": 4.808822722794153e-05, "epoch": 4.255765199161425, "percentage": 21.28, "elapsed_time": "0:30:50", "remaining_time": "1:54:04", "throughput": 2869.08, "total_tokens": 5308304} {"current_steps": 8125, "total_steps": 38160, "loss": 0.4103, "lr": 4.8083839440372194e-05, "epoch": 4.2583857442348005, "percentage": 21.29, "elapsed_time": "0:30:51", "remaining_time": "1:54:03", "throughput": 2868.93, "total_tokens": 5310960} {"current_steps": 8130, "total_steps": 38160, "loss": 0.3483, "lr": 4.8079446823926984e-05, "epoch": 4.261006289308176, "percentage": 21.31, "elapsed_time": "0:30:52", "remaining_time": "1:54:01", "throughput": 2868.57, "total_tokens": 5313264} {"current_steps": 8135, "total_steps": 38160, "loss": 0.3897, "lr": 4.8075049379524805e-05, "epoch": 4.263626834381552, "percentage": 21.32, "elapsed_time": "0:30:53", "remaining_time": "1:54:00", "throughput": 2868.23, "total_tokens": 5315600} {"current_steps": 8140, "total_steps": 38160, "loss": 0.2927, "lr": 4.807064710808555e-05, "epoch": 4.266247379454927, "percentage": 21.33, "elapsed_time": "0:30:54", "remaining_time": "1:53:59", "throughput": 2868.3, "total_tokens": 5319024} {"current_steps": 8145, "total_steps": 38160, "loss": 0.3802, "lr": 4.806624001053013e-05, "epoch": 4.268867924528302, "percentage": 21.34, "elapsed_time": "0:30:55", "remaining_time": "1:53:57", "throughput": 2868.3, "total_tokens": 5322160} {"current_steps": 8150, "total_steps": 38160, "loss": 0.3201, "lr": 4.8061828087780455e-05, "epoch": 4.271488469601677, "percentage": 21.36, "elapsed_time": "0:30:56", "remaining_time": "1:53:57", "throughput": 2868.99, "total_tokens": 5327152} {"current_steps": 8155, "total_steps": 38160, "loss": 0.3016, "lr": 4.805741134075944e-05, "epoch": 4.274109014675052, "percentage": 21.37, "elapsed_time": "0:30:57", "remaining_time": "1:53:55", "throughput": 2869.06, "total_tokens": 5330256} {"current_steps": 8160, "total_steps": 38160, "loss": 0.3903, "lr": 4.8052989770391026e-05, "epoch": 4.276729559748428, "percentage": 21.38, "elapsed_time": "0:30:58", "remaining_time": "1:53:54", "throughput": 2869.03, "total_tokens": 5333392} {"current_steps": 8165, "total_steps": 38160, "loss": 0.3434, "lr": 4.804856337760016e-05, "epoch": 4.279350104821803, "percentage": 21.4, "elapsed_time": "0:30:59", "remaining_time": "1:53:52", "throughput": 2869.21, "total_tokens": 5336720} {"current_steps": 8170, "total_steps": 38160, "loss": 0.2722, "lr": 4.804413216331278e-05, "epoch": 4.281970649895178, "percentage": 21.41, "elapsed_time": "0:31:01", "remaining_time": "1:53:51", "throughput": 2869.2, "total_tokens": 5339696} {"current_steps": 8175, "total_steps": 38160, "loss": 0.4589, "lr": 4.8039696128455856e-05, "epoch": 4.284591194968553, "percentage": 21.42, "elapsed_time": "0:31:02", "remaining_time": "1:53:49", "throughput": 2869.31, "total_tokens": 5342896} {"current_steps": 8180, "total_steps": 38160, "loss": 0.3507, "lr": 4.803525527395736e-05, "epoch": 4.287211740041929, "percentage": 21.44, "elapsed_time": "0:31:03", "remaining_time": "1:53:48", "throughput": 2869.07, "total_tokens": 5345392} {"current_steps": 8185, "total_steps": 38160, "loss": 0.3204, "lr": 4.803080960074625e-05, "epoch": 4.289832285115304, "percentage": 21.45, "elapsed_time": "0:31:04", "remaining_time": "1:53:47", "throughput": 2869.47, "total_tokens": 5349392} {"current_steps": 8190, "total_steps": 38160, "loss": 0.3742, "lr": 4.8026359109752525e-05, "epoch": 4.2924528301886795, "percentage": 21.46, "elapsed_time": "0:31:05", "remaining_time": "1:53:46", "throughput": 2869.64, "total_tokens": 5353008} {"current_steps": 8195, "total_steps": 38160, "loss": 0.5795, "lr": 4.8021903801907175e-05, "epoch": 4.295073375262055, "percentage": 21.48, "elapsed_time": "0:31:06", "remaining_time": "1:53:44", "throughput": 2869.79, "total_tokens": 5356464} {"current_steps": 8200, "total_steps": 38160, "loss": 0.3045, "lr": 4.801744367814219e-05, "epoch": 4.29769392033543, "percentage": 21.49, "elapsed_time": "0:31:07", "remaining_time": "1:53:43", "throughput": 2869.72, "total_tokens": 5359440} {"current_steps": 8205, "total_steps": 38160, "loss": 0.4801, "lr": 4.801297873939059e-05, "epoch": 4.300314465408805, "percentage": 21.5, "elapsed_time": "0:31:08", "remaining_time": "1:53:42", "throughput": 2869.47, "total_tokens": 5361968} {"current_steps": 8210, "total_steps": 38160, "loss": 0.5104, "lr": 4.8008508986586384e-05, "epoch": 4.30293501048218, "percentage": 21.51, "elapsed_time": "0:31:09", "remaining_time": "1:53:40", "throughput": 2869.7, "total_tokens": 5365744} {"current_steps": 8215, "total_steps": 38160, "loss": 0.2969, "lr": 4.800403442066459e-05, "epoch": 4.305555555555555, "percentage": 21.53, "elapsed_time": "0:31:10", "remaining_time": "1:53:39", "throughput": 2869.61, "total_tokens": 5368720} {"current_steps": 8220, "total_steps": 38160, "loss": 0.336, "lr": 4.799955504256125e-05, "epoch": 4.3081761006289305, "percentage": 21.54, "elapsed_time": "0:31:12", "remaining_time": "1:53:38", "throughput": 2869.31, "total_tokens": 5371408} {"current_steps": 8225, "total_steps": 38160, "loss": 0.411, "lr": 4.7995070853213376e-05, "epoch": 4.310796645702306, "percentage": 21.55, "elapsed_time": "0:31:13", "remaining_time": "1:53:37", "throughput": 2869.17, "total_tokens": 5374256} {"current_steps": 8230, "total_steps": 38160, "loss": 0.4132, "lr": 4.799058185355903e-05, "epoch": 4.313417190775682, "percentage": 21.57, "elapsed_time": "0:31:14", "remaining_time": "1:53:35", "throughput": 2868.77, "total_tokens": 5376624} {"current_steps": 8235, "total_steps": 38160, "loss": 0.3729, "lr": 4.7986088044537235e-05, "epoch": 4.316037735849057, "percentage": 21.58, "elapsed_time": "0:31:15", "remaining_time": "1:53:34", "throughput": 2868.91, "total_tokens": 5380048} {"current_steps": 8240, "total_steps": 38160, "loss": 0.2837, "lr": 4.798158942708807e-05, "epoch": 4.318658280922432, "percentage": 21.59, "elapsed_time": "0:31:16", "remaining_time": "1:53:33", "throughput": 2868.58, "total_tokens": 5382416} {"current_steps": 8245, "total_steps": 38160, "loss": 0.4746, "lr": 4.797708600215258e-05, "epoch": 4.321278825995807, "percentage": 21.61, "elapsed_time": "0:31:17", "remaining_time": "1:53:31", "throughput": 2868.61, "total_tokens": 5385520} {"current_steps": 8250, "total_steps": 38160, "loss": 0.5343, "lr": 4.7972577770672845e-05, "epoch": 4.323899371069182, "percentage": 21.62, "elapsed_time": "0:31:18", "remaining_time": "1:53:30", "throughput": 2868.43, "total_tokens": 5388368} {"current_steps": 8255, "total_steps": 38160, "loss": 0.3241, "lr": 4.796806473359192e-05, "epoch": 4.326519916142558, "percentage": 21.63, "elapsed_time": "0:31:19", "remaining_time": "1:53:28", "throughput": 2868.74, "total_tokens": 5391920} {"current_steps": 8260, "total_steps": 38160, "loss": 0.2613, "lr": 4.796354689185389e-05, "epoch": 4.329140461215933, "percentage": 21.65, "elapsed_time": "0:31:20", "remaining_time": "1:53:27", "throughput": 2868.7, "total_tokens": 5394864} {"current_steps": 8265, "total_steps": 38160, "loss": 0.3523, "lr": 4.795902424640383e-05, "epoch": 4.331761006289308, "percentage": 21.66, "elapsed_time": "0:31:21", "remaining_time": "1:53:26", "throughput": 2868.89, "total_tokens": 5398448} {"current_steps": 8270, "total_steps": 38160, "loss": 0.3222, "lr": 4.795449679818782e-05, "epoch": 4.334381551362683, "percentage": 21.67, "elapsed_time": "0:31:22", "remaining_time": "1:53:24", "throughput": 2869.14, "total_tokens": 5401904} {"current_steps": 8275, "total_steps": 38160, "loss": 0.3074, "lr": 4.794996454815297e-05, "epoch": 4.337002096436059, "percentage": 21.69, "elapsed_time": "0:31:23", "remaining_time": "1:53:23", "throughput": 2868.91, "total_tokens": 5404432} {"current_steps": 8280, "total_steps": 38160, "loss": 0.3808, "lr": 4.7945427497247355e-05, "epoch": 4.339622641509434, "percentage": 21.7, "elapsed_time": "0:31:24", "remaining_time": "1:53:21", "throughput": 2868.82, "total_tokens": 5407376} {"current_steps": 8285, "total_steps": 38160, "loss": 0.3589, "lr": 4.7940885646420084e-05, "epoch": 4.3422431865828095, "percentage": 21.71, "elapsed_time": "0:31:25", "remaining_time": "1:53:20", "throughput": 2869.0, "total_tokens": 5410768} {"current_steps": 8290, "total_steps": 38160, "loss": 0.3953, "lr": 4.7936338996621264e-05, "epoch": 4.344863731656185, "percentage": 21.72, "elapsed_time": "0:31:27", "remaining_time": "1:53:19", "throughput": 2869.1, "total_tokens": 5414256} {"current_steps": 8295, "total_steps": 38160, "loss": 0.3168, "lr": 4.7931787548801996e-05, "epoch": 4.34748427672956, "percentage": 21.74, "elapsed_time": "0:31:28", "remaining_time": "1:53:18", "throughput": 2869.09, "total_tokens": 5417296} {"current_steps": 8300, "total_steps": 38160, "loss": 0.3634, "lr": 4.7927231303914394e-05, "epoch": 4.350104821802935, "percentage": 21.75, "elapsed_time": "0:31:29", "remaining_time": "1:53:16", "throughput": 2869.1, "total_tokens": 5420560} {"current_steps": 8305, "total_steps": 38160, "loss": 0.3383, "lr": 4.7922670262911565e-05, "epoch": 4.35272536687631, "percentage": 21.76, "elapsed_time": "0:31:30", "remaining_time": "1:53:16", "throughput": 2869.27, "total_tokens": 5424496} {"current_steps": 8310, "total_steps": 38160, "loss": 0.3609, "lr": 4.791810442674764e-05, "epoch": 4.355345911949685, "percentage": 21.78, "elapsed_time": "0:31:31", "remaining_time": "1:53:15", "throughput": 2869.63, "total_tokens": 5428944} {"current_steps": 8315, "total_steps": 38160, "loss": 0.4191, "lr": 4.791353379637773e-05, "epoch": 4.3579664570230605, "percentage": 21.79, "elapsed_time": "0:31:32", "remaining_time": "1:53:14", "throughput": 2869.86, "total_tokens": 5432624} {"current_steps": 8320, "total_steps": 38160, "loss": 0.3895, "lr": 4.790895837275796e-05, "epoch": 4.360587002096436, "percentage": 21.8, "elapsed_time": "0:31:34", "remaining_time": "1:53:13", "throughput": 2869.58, "total_tokens": 5435152} {"current_steps": 8325, "total_steps": 38160, "loss": 0.3536, "lr": 4.790437815684545e-05, "epoch": 4.363207547169811, "percentage": 21.82, "elapsed_time": "0:31:35", "remaining_time": "1:53:11", "throughput": 2869.71, "total_tokens": 5438640} {"current_steps": 8330, "total_steps": 38160, "loss": 0.3408, "lr": 4.789979314959835e-05, "epoch": 4.365828092243187, "percentage": 21.83, "elapsed_time": "0:31:36", "remaining_time": "1:53:10", "throughput": 2869.47, "total_tokens": 5441264} {"current_steps": 8335, "total_steps": 38160, "loss": 0.3412, "lr": 4.789520335197577e-05, "epoch": 4.368448637316562, "percentage": 21.84, "elapsed_time": "0:31:37", "remaining_time": "1:53:09", "throughput": 2869.58, "total_tokens": 5444752} {"current_steps": 8340, "total_steps": 38160, "loss": 0.3532, "lr": 4.789060876493785e-05, "epoch": 4.371069182389937, "percentage": 21.86, "elapsed_time": "0:31:38", "remaining_time": "1:53:08", "throughput": 2869.51, "total_tokens": 5447632} {"current_steps": 8345, "total_steps": 38160, "loss": 0.4608, "lr": 4.788600938944573e-05, "epoch": 4.373689727463312, "percentage": 21.87, "elapsed_time": "0:31:39", "remaining_time": "1:53:06", "throughput": 2869.69, "total_tokens": 5451344} {"current_steps": 8350, "total_steps": 38160, "loss": 0.4283, "lr": 4.788140522646155e-05, "epoch": 4.376310272536688, "percentage": 21.88, "elapsed_time": "0:31:40", "remaining_time": "1:53:05", "throughput": 2869.85, "total_tokens": 5454736} {"current_steps": 8355, "total_steps": 38160, "loss": 0.392, "lr": 4.787679627694843e-05, "epoch": 4.378930817610063, "percentage": 21.89, "elapsed_time": "0:31:41", "remaining_time": "1:53:04", "throughput": 2869.87, "total_tokens": 5458096} {"current_steps": 8360, "total_steps": 38160, "loss": 0.3785, "lr": 4.787218254187053e-05, "epoch": 4.381551362683438, "percentage": 21.91, "elapsed_time": "0:31:42", "remaining_time": "1:53:03", "throughput": 2869.49, "total_tokens": 5460560} {"current_steps": 8365, "total_steps": 38160, "loss": 0.3366, "lr": 4.7867564022192965e-05, "epoch": 4.384171907756813, "percentage": 21.92, "elapsed_time": "0:31:44", "remaining_time": "1:53:01", "throughput": 2869.61, "total_tokens": 5463792} {"current_steps": 8370, "total_steps": 38160, "loss": 0.3248, "lr": 4.786294071888191e-05, "epoch": 4.386792452830189, "percentage": 21.93, "elapsed_time": "0:31:45", "remaining_time": "1:53:00", "throughput": 2869.77, "total_tokens": 5467216} {"current_steps": 8375, "total_steps": 38160, "loss": 0.341, "lr": 4.785831263290449e-05, "epoch": 4.389412997903564, "percentage": 21.95, "elapsed_time": "0:31:46", "remaining_time": "1:52:59", "throughput": 2869.78, "total_tokens": 5470320} {"current_steps": 8380, "total_steps": 38160, "loss": 0.3379, "lr": 4.7853679765228845e-05, "epoch": 4.3920335429769395, "percentage": 21.96, "elapsed_time": "0:31:47", "remaining_time": "1:52:57", "throughput": 2869.73, "total_tokens": 5473232} {"current_steps": 8385, "total_steps": 38160, "loss": 0.4758, "lr": 4.7849042116824116e-05, "epoch": 4.394654088050315, "percentage": 21.97, "elapsed_time": "0:31:48", "remaining_time": "1:52:56", "throughput": 2869.78, "total_tokens": 5476432} {"current_steps": 8390, "total_steps": 38160, "loss": 0.4278, "lr": 4.7844399688660456e-05, "epoch": 4.39727463312369, "percentage": 21.99, "elapsed_time": "0:31:49", "remaining_time": "1:52:54", "throughput": 2869.48, "total_tokens": 5478928} {"current_steps": 8395, "total_steps": 38160, "loss": 0.2741, "lr": 4.783975248170901e-05, "epoch": 4.399895178197065, "percentage": 22.0, "elapsed_time": "0:31:50", "remaining_time": "1:52:53", "throughput": 2869.37, "total_tokens": 5481776} {"current_steps": 8400, "total_steps": 38160, "loss": 0.3825, "lr": 4.783510049694191e-05, "epoch": 4.40251572327044, "percentage": 22.01, "elapsed_time": "0:31:51", "remaining_time": "1:52:52", "throughput": 2869.47, "total_tokens": 5485008} {"current_steps": 8405, "total_steps": 38160, "loss": 0.374, "lr": 4.78304437353323e-05, "epoch": 4.405136268343815, "percentage": 22.03, "elapsed_time": "0:31:53", "remaining_time": "1:52:54", "throughput": 2870.34, "total_tokens": 5492496} {"current_steps": 8410, "total_steps": 38160, "loss": 0.3602, "lr": 4.782578219785433e-05, "epoch": 4.4077568134171905, "percentage": 22.04, "elapsed_time": "0:31:54", "remaining_time": "1:52:52", "throughput": 2870.35, "total_tokens": 5495664} {"current_steps": 8415, "total_steps": 38160, "loss": 0.3456, "lr": 4.782111588548312e-05, "epoch": 4.410377358490566, "percentage": 22.05, "elapsed_time": "0:31:55", "remaining_time": "1:52:52", "throughput": 2870.68, "total_tokens": 5499792} {"current_steps": 8420, "total_steps": 38160, "loss": 0.3161, "lr": 4.781644479919484e-05, "epoch": 4.412997903563941, "percentage": 22.06, "elapsed_time": "0:31:56", "remaining_time": "1:52:50", "throughput": 2870.62, "total_tokens": 5502736} {"current_steps": 8425, "total_steps": 38160, "loss": 0.3342, "lr": 4.7811768939966605e-05, "epoch": 4.415618448637317, "percentage": 22.08, "elapsed_time": "0:31:58", "remaining_time": "1:52:49", "throughput": 2870.32, "total_tokens": 5505328} {"current_steps": 8430, "total_steps": 38160, "loss": 0.3836, "lr": 4.780708830877656e-05, "epoch": 4.418238993710692, "percentage": 22.09, "elapsed_time": "0:31:59", "remaining_time": "1:52:47", "throughput": 2870.15, "total_tokens": 5507952} {"current_steps": 8435, "total_steps": 38160, "loss": 0.3056, "lr": 4.780240290660384e-05, "epoch": 4.420859538784067, "percentage": 22.1, "elapsed_time": "0:32:00", "remaining_time": "1:52:46", "throughput": 2869.86, "total_tokens": 5510544} {"current_steps": 8440, "total_steps": 38160, "loss": 0.4228, "lr": 4.7797712734428575e-05, "epoch": 4.423480083857442, "percentage": 22.12, "elapsed_time": "0:32:01", "remaining_time": "1:52:45", "throughput": 2869.57, "total_tokens": 5512976} {"current_steps": 8445, "total_steps": 38160, "loss": 0.4265, "lr": 4.779301779323189e-05, "epoch": 4.426100628930818, "percentage": 22.13, "elapsed_time": "0:32:02", "remaining_time": "1:52:43", "throughput": 2869.77, "total_tokens": 5516496} {"current_steps": 8450, "total_steps": 38160, "loss": 0.2724, "lr": 4.778831808399593e-05, "epoch": 4.428721174004193, "percentage": 22.14, "elapsed_time": "0:32:03", "remaining_time": "1:52:42", "throughput": 2870.25, "total_tokens": 5520720} {"current_steps": 8455, "total_steps": 38160, "loss": 0.3771, "lr": 4.77836136077038e-05, "epoch": 4.431341719077568, "percentage": 22.16, "elapsed_time": "0:32:04", "remaining_time": "1:52:41", "throughput": 2870.51, "total_tokens": 5524336} {"current_steps": 8460, "total_steps": 38160, "loss": 0.3322, "lr": 4.777890436533963e-05, "epoch": 4.433962264150943, "percentage": 22.17, "elapsed_time": "0:32:05", "remaining_time": "1:52:40", "throughput": 2870.81, "total_tokens": 5528112} {"current_steps": 8465, "total_steps": 38160, "loss": 0.3922, "lr": 4.777419035788855e-05, "epoch": 4.436582809224318, "percentage": 22.18, "elapsed_time": "0:32:06", "remaining_time": "1:52:38", "throughput": 2871.03, "total_tokens": 5531664} {"current_steps": 8470, "total_steps": 38160, "loss": 0.3035, "lr": 4.776947158633667e-05, "epoch": 4.439203354297694, "percentage": 22.2, "elapsed_time": "0:32:08", "remaining_time": "1:52:38", "throughput": 2871.49, "total_tokens": 5536368} {"current_steps": 8475, "total_steps": 38160, "loss": 0.3371, "lr": 4.7764748051671095e-05, "epoch": 4.4418238993710695, "percentage": 22.21, "elapsed_time": "0:32:09", "remaining_time": "1:52:37", "throughput": 2871.58, "total_tokens": 5539600} {"current_steps": 8480, "total_steps": 38160, "loss": 0.2937, "lr": 4.7760019754879946e-05, "epoch": 4.444444444444445, "percentage": 22.22, "elapsed_time": "0:32:10", "remaining_time": "1:52:35", "throughput": 2871.53, "total_tokens": 5542544} {"current_steps": 8485, "total_steps": 38160, "loss": 0.3326, "lr": 4.7755286696952324e-05, "epoch": 4.44706498951782, "percentage": 22.24, "elapsed_time": "0:32:11", "remaining_time": "1:52:34", "throughput": 2871.81, "total_tokens": 5546704} {"current_steps": 8490, "total_steps": 38160, "loss": 0.2956, "lr": 4.775054887887833e-05, "epoch": 4.449685534591195, "percentage": 22.25, "elapsed_time": "0:32:12", "remaining_time": "1:52:33", "throughput": 2871.67, "total_tokens": 5549520} {"current_steps": 8495, "total_steps": 38160, "loss": 0.3676, "lr": 4.774580630164906e-05, "epoch": 4.45230607966457, "percentage": 22.26, "elapsed_time": "0:32:13", "remaining_time": "1:52:32", "throughput": 2871.88, "total_tokens": 5553040} {"current_steps": 8500, "total_steps": 38160, "loss": 0.3963, "lr": 4.774105896625661e-05, "epoch": 4.454926624737945, "percentage": 22.27, "elapsed_time": "0:32:14", "remaining_time": "1:52:31", "throughput": 2872.14, "total_tokens": 5556880} {"current_steps": 8505, "total_steps": 38160, "loss": 0.3225, "lr": 4.773630687369407e-05, "epoch": 4.4575471698113205, "percentage": 22.29, "elapsed_time": "0:32:15", "remaining_time": "1:52:29", "throughput": 2872.06, "total_tokens": 5559760} {"current_steps": 8510, "total_steps": 38160, "loss": 0.3468, "lr": 4.773155002495552e-05, "epoch": 4.460167714884696, "percentage": 22.3, "elapsed_time": "0:32:17", "remaining_time": "1:52:29", "throughput": 2872.68, "total_tokens": 5564688} {"current_steps": 8515, "total_steps": 38160, "loss": 0.4322, "lr": 4.772678842103605e-05, "epoch": 4.462788259958071, "percentage": 22.31, "elapsed_time": "0:32:18", "remaining_time": "1:52:28", "throughput": 2872.74, "total_tokens": 5568112} {"current_steps": 8520, "total_steps": 38160, "loss": 0.4696, "lr": 4.772202206293172e-05, "epoch": 4.465408805031447, "percentage": 22.33, "elapsed_time": "0:32:19", "remaining_time": "1:52:26", "throughput": 2872.67, "total_tokens": 5570928} {"current_steps": 8525, "total_steps": 38160, "loss": 0.3574, "lr": 4.7717250951639586e-05, "epoch": 4.468029350104822, "percentage": 22.34, "elapsed_time": "0:32:20", "remaining_time": "1:52:25", "throughput": 2872.82, "total_tokens": 5574480} {"current_steps": 8530, "total_steps": 38160, "loss": 0.3725, "lr": 4.771247508815774e-05, "epoch": 4.470649895178197, "percentage": 22.35, "elapsed_time": "0:32:21", "remaining_time": "1:52:23", "throughput": 2872.71, "total_tokens": 5577296} {"current_steps": 8535, "total_steps": 38160, "loss": 0.2617, "lr": 4.770769447348522e-05, "epoch": 4.473270440251572, "percentage": 22.37, "elapsed_time": "0:32:22", "remaining_time": "1:52:22", "throughput": 2872.85, "total_tokens": 5580784} {"current_steps": 8540, "total_steps": 38160, "loss": 0.3372, "lr": 4.7702909108622074e-05, "epoch": 4.475890985324948, "percentage": 22.38, "elapsed_time": "0:32:23", "remaining_time": "1:52:21", "throughput": 2872.91, "total_tokens": 5583856} {"current_steps": 8545, "total_steps": 38160, "loss": 0.3364, "lr": 4.7698118994569355e-05, "epoch": 4.478511530398323, "percentage": 22.39, "elapsed_time": "0:32:24", "remaining_time": "1:52:19", "throughput": 2872.59, "total_tokens": 5586256} {"current_steps": 8550, "total_steps": 38160, "loss": 0.3479, "lr": 4.769332413232909e-05, "epoch": 4.481132075471698, "percentage": 22.41, "elapsed_time": "0:32:25", "remaining_time": "1:52:18", "throughput": 2872.57, "total_tokens": 5589200} {"current_steps": 8555, "total_steps": 38160, "loss": 0.4229, "lr": 4.768852452290432e-05, "epoch": 4.483752620545073, "percentage": 22.42, "elapsed_time": "0:32:26", "remaining_time": "1:52:17", "throughput": 2872.82, "total_tokens": 5592976} {"current_steps": 8560, "total_steps": 38160, "loss": 0.3812, "lr": 4.768372016729907e-05, "epoch": 4.486373165618448, "percentage": 22.43, "elapsed_time": "0:32:27", "remaining_time": "1:52:15", "throughput": 2872.62, "total_tokens": 5595696} {"current_steps": 8565, "total_steps": 38160, "loss": 0.4033, "lr": 4.767891106651834e-05, "epoch": 4.488993710691824, "percentage": 22.44, "elapsed_time": "0:32:29", "remaining_time": "1:52:14", "throughput": 2872.39, "total_tokens": 5598288} {"current_steps": 8570, "total_steps": 38160, "loss": 0.4444, "lr": 4.767409722156816e-05, "epoch": 4.4916142557651995, "percentage": 22.46, "elapsed_time": "0:32:30", "remaining_time": "1:52:13", "throughput": 2872.28, "total_tokens": 5601296} {"current_steps": 8575, "total_steps": 38160, "loss": 0.3087, "lr": 4.7669278633455515e-05, "epoch": 4.494234800838575, "percentage": 22.47, "elapsed_time": "0:32:31", "remaining_time": "1:52:11", "throughput": 2872.45, "total_tokens": 5604752} {"current_steps": 8580, "total_steps": 38160, "loss": 0.4445, "lr": 4.7664455303188404e-05, "epoch": 4.49685534591195, "percentage": 22.48, "elapsed_time": "0:32:32", "remaining_time": "1:52:11", "throughput": 2871.98, "total_tokens": 5607824} {"current_steps": 8585, "total_steps": 38160, "loss": 0.4076, "lr": 4.7659627231775815e-05, "epoch": 4.499475890985325, "percentage": 22.5, "elapsed_time": "0:32:33", "remaining_time": "1:52:10", "throughput": 2872.13, "total_tokens": 5611248} {"current_steps": 8590, "total_steps": 38160, "loss": 0.3121, "lr": 4.765479442022773e-05, "epoch": 4.5020964360587, "percentage": 22.51, "elapsed_time": "0:32:34", "remaining_time": "1:52:08", "throughput": 2872.13, "total_tokens": 5614192} {"current_steps": 8595, "total_steps": 38160, "loss": 0.3894, "lr": 4.76499568695551e-05, "epoch": 4.504716981132075, "percentage": 22.52, "elapsed_time": "0:32:35", "remaining_time": "1:52:07", "throughput": 2872.03, "total_tokens": 5616944} {"current_steps": 8600, "total_steps": 38160, "loss": 0.3693, "lr": 4.764511458076991e-05, "epoch": 4.5073375262054505, "percentage": 22.54, "elapsed_time": "0:32:36", "remaining_time": "1:52:05", "throughput": 2871.69, "total_tokens": 5619344} {"current_steps": 8605, "total_steps": 38160, "loss": 0.2901, "lr": 4.7640267554885085e-05, "epoch": 4.509958071278826, "percentage": 22.55, "elapsed_time": "0:32:37", "remaining_time": "1:52:04", "throughput": 2871.79, "total_tokens": 5622608} {"current_steps": 8610, "total_steps": 38160, "loss": 0.3918, "lr": 4.763541579291459e-05, "epoch": 4.512578616352201, "percentage": 22.56, "elapsed_time": "0:32:38", "remaining_time": "1:52:03", "throughput": 2871.61, "total_tokens": 5625296} {"current_steps": 8615, "total_steps": 38160, "loss": 0.2757, "lr": 4.763055929587336e-05, "epoch": 4.515199161425577, "percentage": 22.58, "elapsed_time": "0:32:40", "remaining_time": "1:52:01", "throughput": 2871.54, "total_tokens": 5628272} {"current_steps": 8620, "total_steps": 38160, "loss": 0.3261, "lr": 4.7625698064777294e-05, "epoch": 4.517819706498952, "percentage": 22.59, "elapsed_time": "0:32:41", "remaining_time": "1:52:01", "throughput": 2872.01, "total_tokens": 5632944} {"current_steps": 8625, "total_steps": 38160, "loss": 0.333, "lr": 4.762083210064332e-05, "epoch": 4.520440251572327, "percentage": 22.6, "elapsed_time": "0:32:42", "remaining_time": "1:51:59", "throughput": 2872.03, "total_tokens": 5636016} {"current_steps": 8630, "total_steps": 38160, "loss": 0.2938, "lr": 4.761596140448934e-05, "epoch": 4.523060796645702, "percentage": 22.62, "elapsed_time": "0:32:44", "remaining_time": "1:52:00", "throughput": 2872.57, "total_tokens": 5642064} {"current_steps": 8635, "total_steps": 38160, "loss": 0.4475, "lr": 4.7611085977334256e-05, "epoch": 4.5256813417190775, "percentage": 22.63, "elapsed_time": "0:32:45", "remaining_time": "1:51:59", "throughput": 2872.52, "total_tokens": 5645072} {"current_steps": 8640, "total_steps": 38160, "loss": 0.4248, "lr": 4.7606205820197946e-05, "epoch": 4.528301886792453, "percentage": 22.64, "elapsed_time": "0:32:46", "remaining_time": "1:51:58", "throughput": 2872.59, "total_tokens": 5648304} {"current_steps": 8645, "total_steps": 38160, "loss": 0.4417, "lr": 4.760132093410129e-05, "epoch": 4.530922431865828, "percentage": 22.65, "elapsed_time": "0:32:47", "remaining_time": "1:51:56", "throughput": 2872.45, "total_tokens": 5651120} {"current_steps": 8650, "total_steps": 38160, "loss": 0.2774, "lr": 4.759643132006614e-05, "epoch": 4.533542976939203, "percentage": 22.67, "elapsed_time": "0:32:48", "remaining_time": "1:51:55", "throughput": 2872.18, "total_tokens": 5653712} {"current_steps": 8655, "total_steps": 38160, "loss": 0.3248, "lr": 4.759153697911535e-05, "epoch": 4.536163522012579, "percentage": 22.68, "elapsed_time": "0:32:49", "remaining_time": "1:51:53", "throughput": 2872.14, "total_tokens": 5656624} {"current_steps": 8660, "total_steps": 38160, "loss": 0.3754, "lr": 4.758663791227276e-05, "epoch": 4.538784067085954, "percentage": 22.69, "elapsed_time": "0:32:50", "remaining_time": "1:51:52", "throughput": 2871.7, "total_tokens": 5658960} {"current_steps": 8665, "total_steps": 38160, "loss": 0.3703, "lr": 4.7581734120563206e-05, "epoch": 4.5414046121593294, "percentage": 22.71, "elapsed_time": "0:32:51", "remaining_time": "1:51:51", "throughput": 2871.67, "total_tokens": 5661872} {"current_steps": 8670, "total_steps": 38160, "loss": 0.4336, "lr": 4.757682560501249e-05, "epoch": 4.544025157232705, "percentage": 22.72, "elapsed_time": "0:32:52", "remaining_time": "1:51:49", "throughput": 2871.53, "total_tokens": 5664560} {"current_steps": 8675, "total_steps": 38160, "loss": 0.3309, "lr": 4.757191236664744e-05, "epoch": 4.54664570230608, "percentage": 22.73, "elapsed_time": "0:32:53", "remaining_time": "1:51:48", "throughput": 2871.5, "total_tokens": 5667664} {"current_steps": 8680, "total_steps": 38160, "loss": 0.3434, "lr": 4.7566994406495825e-05, "epoch": 4.549266247379455, "percentage": 22.75, "elapsed_time": "0:32:54", "remaining_time": "1:51:47", "throughput": 2871.2, "total_tokens": 5670128} {"current_steps": 8685, "total_steps": 38160, "loss": 0.4222, "lr": 4.756207172558645e-05, "epoch": 4.55188679245283, "percentage": 22.76, "elapsed_time": "0:32:55", "remaining_time": "1:51:45", "throughput": 2871.28, "total_tokens": 5673296} {"current_steps": 8690, "total_steps": 38160, "loss": 0.4472, "lr": 4.7557144324949065e-05, "epoch": 4.554507337526205, "percentage": 22.77, "elapsed_time": "0:32:56", "remaining_time": "1:51:44", "throughput": 2871.05, "total_tokens": 5675920} {"current_steps": 8695, "total_steps": 38160, "loss": 0.3139, "lr": 4.755221220561443e-05, "epoch": 4.5571278825995805, "percentage": 22.79, "elapsed_time": "0:32:57", "remaining_time": "1:51:42", "throughput": 2871.03, "total_tokens": 5678896} {"current_steps": 8700, "total_steps": 38160, "loss": 0.3659, "lr": 4.7547275368614295e-05, "epoch": 4.559748427672956, "percentage": 22.8, "elapsed_time": "0:32:59", "remaining_time": "1:51:41", "throughput": 2870.74, "total_tokens": 5681488} {"current_steps": 8705, "total_steps": 38160, "loss": 0.3839, "lr": 4.754233381498139e-05, "epoch": 4.562368972746331, "percentage": 22.81, "elapsed_time": "0:33:00", "remaining_time": "1:51:40", "throughput": 2870.67, "total_tokens": 5684432} {"current_steps": 8710, "total_steps": 38160, "loss": 0.3558, "lr": 4.753738754574942e-05, "epoch": 4.564989517819707, "percentage": 22.82, "elapsed_time": "0:33:01", "remaining_time": "1:51:39", "throughput": 2870.88, "total_tokens": 5688112} {"current_steps": 8715, "total_steps": 38160, "loss": 0.4023, "lr": 4.75324365619531e-05, "epoch": 4.567610062893082, "percentage": 22.84, "elapsed_time": "0:33:02", "remaining_time": "1:51:37", "throughput": 2870.48, "total_tokens": 5690416} {"current_steps": 8720, "total_steps": 38160, "loss": 0.4179, "lr": 4.752748086462811e-05, "epoch": 4.570230607966457, "percentage": 22.85, "elapsed_time": "0:33:03", "remaining_time": "1:51:36", "throughput": 2870.57, "total_tokens": 5693744} {"current_steps": 8725, "total_steps": 38160, "loss": 0.3855, "lr": 4.752252045481113e-05, "epoch": 4.572851153039832, "percentage": 22.86, "elapsed_time": "0:33:04", "remaining_time": "1:51:35", "throughput": 2870.96, "total_tokens": 5697776} {"current_steps": 8730, "total_steps": 38160, "loss": 0.5682, "lr": 4.7517555333539834e-05, "epoch": 4.5754716981132075, "percentage": 22.88, "elapsed_time": "0:33:05", "remaining_time": "1:51:34", "throughput": 2870.63, "total_tokens": 5700240} {"current_steps": 8735, "total_steps": 38160, "loss": 0.3339, "lr": 4.751258550185284e-05, "epoch": 4.578092243186583, "percentage": 22.89, "elapsed_time": "0:33:06", "remaining_time": "1:51:32", "throughput": 2870.47, "total_tokens": 5702992} {"current_steps": 8740, "total_steps": 38160, "loss": 0.3337, "lr": 4.7507610960789804e-05, "epoch": 4.580712788259958, "percentage": 22.9, "elapsed_time": "0:33:07", "remaining_time": "1:51:31", "throughput": 2870.69, "total_tokens": 5706544} {"current_steps": 8745, "total_steps": 38160, "loss": 0.3701, "lr": 4.7502631711391334e-05, "epoch": 4.583333333333333, "percentage": 22.92, "elapsed_time": "0:33:08", "remaining_time": "1:51:30", "throughput": 2870.56, "total_tokens": 5709328} {"current_steps": 8750, "total_steps": 38160, "loss": 0.3228, "lr": 4.749764775469904e-05, "epoch": 4.585953878406709, "percentage": 22.93, "elapsed_time": "0:33:10", "remaining_time": "1:51:28", "throughput": 2870.62, "total_tokens": 5712720} {"current_steps": 8755, "total_steps": 38160, "loss": 0.4431, "lr": 4.749265909175549e-05, "epoch": 4.588574423480084, "percentage": 22.94, "elapsed_time": "0:33:11", "remaining_time": "1:51:27", "throughput": 2870.4, "total_tokens": 5715536} {"current_steps": 8760, "total_steps": 38160, "loss": 0.3967, "lr": 4.7487665723604275e-05, "epoch": 4.591194968553459, "percentage": 22.96, "elapsed_time": "0:33:12", "remaining_time": "1:51:26", "throughput": 2870.26, "total_tokens": 5718352} {"current_steps": 8765, "total_steps": 38160, "loss": 0.3594, "lr": 4.7482667651289944e-05, "epoch": 4.593815513626835, "percentage": 22.97, "elapsed_time": "0:33:13", "remaining_time": "1:51:25", "throughput": 2870.52, "total_tokens": 5722096} {"current_steps": 8770, "total_steps": 38160, "loss": 0.3448, "lr": 4.747766487585803e-05, "epoch": 4.59643605870021, "percentage": 22.98, "elapsed_time": "0:33:14", "remaining_time": "1:51:23", "throughput": 2870.37, "total_tokens": 5724816} {"current_steps": 8775, "total_steps": 38160, "loss": 0.3598, "lr": 4.747265739835507e-05, "epoch": 4.599056603773585, "percentage": 23.0, "elapsed_time": "0:33:15", "remaining_time": "1:51:22", "throughput": 2870.76, "total_tokens": 5729040} {"current_steps": 8780, "total_steps": 38160, "loss": 0.3614, "lr": 4.746764521982856e-05, "epoch": 4.60167714884696, "percentage": 23.01, "elapsed_time": "0:33:16", "remaining_time": "1:51:21", "throughput": 2870.91, "total_tokens": 5732464} {"current_steps": 8785, "total_steps": 38160, "loss": 0.2482, "lr": 4.7462628341326995e-05, "epoch": 4.604297693920335, "percentage": 23.02, "elapsed_time": "0:33:17", "remaining_time": "1:51:20", "throughput": 2870.85, "total_tokens": 5735472} {"current_steps": 8790, "total_steps": 38160, "loss": 0.3582, "lr": 4.7457606763899856e-05, "epoch": 4.6069182389937104, "percentage": 23.03, "elapsed_time": "0:33:18", "remaining_time": "1:51:19", "throughput": 2870.95, "total_tokens": 5738896} {"current_steps": 8795, "total_steps": 38160, "loss": 0.2598, "lr": 4.745258048859758e-05, "epoch": 4.609538784067086, "percentage": 23.05, "elapsed_time": "0:33:20", "remaining_time": "1:51:17", "throughput": 2870.89, "total_tokens": 5742032} {"current_steps": 8800, "total_steps": 38160, "loss": 0.3728, "lr": 4.744754951647162e-05, "epoch": 4.612159329140461, "percentage": 23.06, "elapsed_time": "0:33:21", "remaining_time": "1:51:16", "throughput": 2870.84, "total_tokens": 5745168} {"current_steps": 8805, "total_steps": 38160, "loss": 0.446, "lr": 4.74425138485744e-05, "epoch": 4.614779874213837, "percentage": 23.07, "elapsed_time": "0:33:22", "remaining_time": "1:51:15", "throughput": 2870.67, "total_tokens": 5747920} {"current_steps": 8810, "total_steps": 38160, "loss": 0.367, "lr": 4.743747348595932e-05, "epoch": 4.617400419287212, "percentage": 23.09, "elapsed_time": "0:33:23", "remaining_time": "1:51:14", "throughput": 2870.68, "total_tokens": 5751120} {"current_steps": 8815, "total_steps": 38160, "loss": 0.3672, "lr": 4.743242842968077e-05, "epoch": 4.620020964360587, "percentage": 23.1, "elapsed_time": "0:33:24", "remaining_time": "1:51:12", "throughput": 2870.75, "total_tokens": 5754352} {"current_steps": 8820, "total_steps": 38160, "loss": 0.3404, "lr": 4.742737868079411e-05, "epoch": 4.622641509433962, "percentage": 23.11, "elapsed_time": "0:33:25", "remaining_time": "1:51:11", "throughput": 2870.59, "total_tokens": 5757200} {"current_steps": 8825, "total_steps": 38160, "loss": 0.2625, "lr": 4.7422324240355696e-05, "epoch": 4.6252620545073375, "percentage": 23.13, "elapsed_time": "0:33:26", "remaining_time": "1:51:10", "throughput": 2870.65, "total_tokens": 5760944} {"current_steps": 8830, "total_steps": 38160, "loss": 0.404, "lr": 4.741726510942286e-05, "epoch": 4.627882599580713, "percentage": 23.14, "elapsed_time": "0:33:27", "remaining_time": "1:51:09", "throughput": 2870.95, "total_tokens": 5764848} {"current_steps": 8835, "total_steps": 38160, "loss": 0.3113, "lr": 4.741220128905391e-05, "epoch": 4.630503144654088, "percentage": 23.15, "elapsed_time": "0:33:29", "remaining_time": "1:51:08", "throughput": 2871.03, "total_tokens": 5767984} {"current_steps": 8840, "total_steps": 38160, "loss": 0.3048, "lr": 4.740713278030815e-05, "epoch": 4.633123689727463, "percentage": 23.17, "elapsed_time": "0:33:30", "remaining_time": "1:51:07", "throughput": 2871.19, "total_tokens": 5771472} {"current_steps": 8845, "total_steps": 38160, "loss": 0.3674, "lr": 4.740205958424584e-05, "epoch": 4.635744234800838, "percentage": 23.18, "elapsed_time": "0:33:31", "remaining_time": "1:51:06", "throughput": 2871.43, "total_tokens": 5775536} {"current_steps": 8850, "total_steps": 38160, "loss": 0.3667, "lr": 4.739698170192824e-05, "epoch": 4.638364779874214, "percentage": 23.19, "elapsed_time": "0:33:32", "remaining_time": "1:51:04", "throughput": 2871.48, "total_tokens": 5778704} {"current_steps": 8855, "total_steps": 38160, "loss": 0.3682, "lr": 4.7391899134417596e-05, "epoch": 4.640985324947589, "percentage": 23.2, "elapsed_time": "0:33:33", "remaining_time": "1:51:03", "throughput": 2871.2, "total_tokens": 5781104} {"current_steps": 8860, "total_steps": 38160, "loss": 0.4055, "lr": 4.73868118827771e-05, "epoch": 4.643605870020965, "percentage": 23.22, "elapsed_time": "0:33:34", "remaining_time": "1:51:02", "throughput": 2871.3, "total_tokens": 5784528} {"current_steps": 8865, "total_steps": 38160, "loss": 0.5805, "lr": 4.738171994807097e-05, "epoch": 4.64622641509434, "percentage": 23.23, "elapsed_time": "0:33:35", "remaining_time": "1:51:00", "throughput": 2871.09, "total_tokens": 5787184} {"current_steps": 8870, "total_steps": 38160, "loss": 0.3793, "lr": 4.7376623331364364e-05, "epoch": 4.648846960167715, "percentage": 23.24, "elapsed_time": "0:33:36", "remaining_time": "1:50:59", "throughput": 2870.96, "total_tokens": 5790032} {"current_steps": 8875, "total_steps": 38160, "loss": 0.3737, "lr": 4.737152203372345e-05, "epoch": 4.65146750524109, "percentage": 23.26, "elapsed_time": "0:33:37", "remaining_time": "1:50:58", "throughput": 2870.93, "total_tokens": 5793104} {"current_steps": 8880, "total_steps": 38160, "loss": 0.4095, "lr": 4.7366416056215345e-05, "epoch": 4.654088050314465, "percentage": 23.27, "elapsed_time": "0:33:38", "remaining_time": "1:50:56", "throughput": 2871.03, "total_tokens": 5796368} {"current_steps": 8885, "total_steps": 38160, "loss": 0.4749, "lr": 4.7361305399908185e-05, "epoch": 4.65670859538784, "percentage": 23.28, "elapsed_time": "0:33:39", "remaining_time": "1:50:55", "throughput": 2870.94, "total_tokens": 5799248} {"current_steps": 8890, "total_steps": 38160, "loss": 0.421, "lr": 4.735619006587103e-05, "epoch": 4.659329140461216, "percentage": 23.3, "elapsed_time": "0:33:41", "remaining_time": "1:50:54", "throughput": 2871.0, "total_tokens": 5802448} {"current_steps": 8895, "total_steps": 38160, "loss": 0.4161, "lr": 4.735107005517398e-05, "epoch": 4.661949685534591, "percentage": 23.31, "elapsed_time": "0:33:42", "remaining_time": "1:50:53", "throughput": 2871.13, "total_tokens": 5805936} {"current_steps": 8900, "total_steps": 38160, "loss": 0.3092, "lr": 4.734594536888806e-05, "epoch": 4.664570230607967, "percentage": 23.32, "elapsed_time": "0:33:43", "remaining_time": "1:50:52", "throughput": 2871.23, "total_tokens": 5809744} {"current_steps": 8905, "total_steps": 38160, "loss": 0.4483, "lr": 4.734081600808531e-05, "epoch": 4.667190775681342, "percentage": 23.34, "elapsed_time": "0:33:44", "remaining_time": "1:50:51", "throughput": 2871.12, "total_tokens": 5812656} {"current_steps": 8910, "total_steps": 38160, "loss": 0.4856, "lr": 4.733568197383872e-05, "epoch": 4.669811320754717, "percentage": 23.35, "elapsed_time": "0:33:45", "remaining_time": "1:50:49", "throughput": 2871.2, "total_tokens": 5816048} {"current_steps": 8915, "total_steps": 38160, "loss": 0.4796, "lr": 4.7330543267222294e-05, "epoch": 4.672431865828092, "percentage": 23.36, "elapsed_time": "0:33:46", "remaining_time": "1:50:48", "throughput": 2871.63, "total_tokens": 5820080} {"current_steps": 8920, "total_steps": 38160, "loss": 0.4074, "lr": 4.732539988931097e-05, "epoch": 4.6750524109014675, "percentage": 23.38, "elapsed_time": "0:33:47", "remaining_time": "1:50:47", "throughput": 2871.73, "total_tokens": 5823344} {"current_steps": 8925, "total_steps": 38160, "loss": 0.3591, "lr": 4.732025184118068e-05, "epoch": 4.677672955974843, "percentage": 23.39, "elapsed_time": "0:33:48", "remaining_time": "1:50:46", "throughput": 2871.66, "total_tokens": 5826448} {"current_steps": 8930, "total_steps": 38160, "loss": 0.3282, "lr": 4.731509912390837e-05, "epoch": 4.680293501048218, "percentage": 23.4, "elapsed_time": "0:33:50", "remaining_time": "1:50:45", "throughput": 2871.78, "total_tokens": 5830000} {"current_steps": 8935, "total_steps": 38160, "loss": 0.2842, "lr": 4.730994173857189e-05, "epoch": 4.682914046121593, "percentage": 23.41, "elapsed_time": "0:33:51", "remaining_time": "1:50:43", "throughput": 2871.42, "total_tokens": 5832464} {"current_steps": 8940, "total_steps": 38160, "loss": 0.3502, "lr": 4.7304779686250126e-05, "epoch": 4.685534591194968, "percentage": 23.43, "elapsed_time": "0:33:52", "remaining_time": "1:50:42", "throughput": 2871.46, "total_tokens": 5835568} {"current_steps": 8945, "total_steps": 38160, "loss": 0.35, "lr": 4.729961296802292e-05, "epoch": 4.688155136268344, "percentage": 23.44, "elapsed_time": "0:33:53", "remaining_time": "1:50:42", "throughput": 2872.33, "total_tokens": 5841360} {"current_steps": 8950, "total_steps": 38160, "loss": 0.2893, "lr": 4.7294441584971095e-05, "epoch": 4.690775681341719, "percentage": 23.45, "elapsed_time": "0:33:54", "remaining_time": "1:50:40", "throughput": 2872.24, "total_tokens": 5844240} {"current_steps": 8955, "total_steps": 38160, "loss": 0.2843, "lr": 4.728926553817643e-05, "epoch": 4.693396226415095, "percentage": 23.47, "elapsed_time": "0:33:55", "remaining_time": "1:50:39", "throughput": 2872.5, "total_tokens": 5848144} {"current_steps": 8960, "total_steps": 38160, "loss": 0.433, "lr": 4.728408482872171e-05, "epoch": 4.69601677148847, "percentage": 23.48, "elapsed_time": "0:33:57", "remaining_time": "1:50:38", "throughput": 2872.26, "total_tokens": 5850800} {"current_steps": 8965, "total_steps": 38160, "loss": 0.3634, "lr": 4.727889945769067e-05, "epoch": 4.698637316561845, "percentage": 23.49, "elapsed_time": "0:33:58", "remaining_time": "1:50:37", "throughput": 2872.16, "total_tokens": 5853712} {"current_steps": 8970, "total_steps": 38160, "loss": 0.3336, "lr": 4.727370942616803e-05, "epoch": 4.70125786163522, "percentage": 23.51, "elapsed_time": "0:33:59", "remaining_time": "1:50:35", "throughput": 2871.97, "total_tokens": 5856400} {"current_steps": 8975, "total_steps": 38160, "loss": 0.4018, "lr": 4.72685147352395e-05, "epoch": 4.703878406708595, "percentage": 23.52, "elapsed_time": "0:34:00", "remaining_time": "1:50:34", "throughput": 2872.08, "total_tokens": 5859760} {"current_steps": 8980, "total_steps": 38160, "loss": 0.2979, "lr": 4.7263315385991735e-05, "epoch": 4.70649895178197, "percentage": 23.53, "elapsed_time": "0:34:01", "remaining_time": "1:50:33", "throughput": 2872.04, "total_tokens": 5862672} {"current_steps": 8985, "total_steps": 38160, "loss": 0.3644, "lr": 4.7258111379512384e-05, "epoch": 4.709119496855346, "percentage": 23.55, "elapsed_time": "0:34:02", "remaining_time": "1:50:31", "throughput": 2872.24, "total_tokens": 5866288} {"current_steps": 8990, "total_steps": 38160, "loss": 0.4432, "lr": 4.725290271689007e-05, "epoch": 4.711740041928721, "percentage": 23.56, "elapsed_time": "0:34:03", "remaining_time": "1:50:30", "throughput": 2872.28, "total_tokens": 5869424} {"current_steps": 8995, "total_steps": 38160, "loss": 0.2653, "lr": 4.724768939921438e-05, "epoch": 4.714360587002097, "percentage": 23.57, "elapsed_time": "0:34:04", "remaining_time": "1:50:29", "throughput": 2872.14, "total_tokens": 5872240} {"current_steps": 9000, "total_steps": 38160, "loss": 0.2932, "lr": 4.7242471427575884e-05, "epoch": 4.716981132075472, "percentage": 23.58, "elapsed_time": "0:34:05", "remaining_time": "1:50:27", "throughput": 2871.88, "total_tokens": 5874672} {"current_steps": 9005, "total_steps": 38160, "loss": 0.3062, "lr": 4.723724880306612e-05, "epoch": 4.719601677148847, "percentage": 23.6, "elapsed_time": "0:34:06", "remaining_time": "1:50:26", "throughput": 2872.19, "total_tokens": 5878544} {"current_steps": 9010, "total_steps": 38160, "loss": 0.421, "lr": 4.72320215267776e-05, "epoch": 4.722222222222222, "percentage": 23.61, "elapsed_time": "0:34:07", "remaining_time": "1:50:25", "throughput": 2872.39, "total_tokens": 5882096} {"current_steps": 9015, "total_steps": 38160, "loss": 0.3799, "lr": 4.722678959980381e-05, "epoch": 4.7248427672955975, "percentage": 23.62, "elapsed_time": "0:34:09", "remaining_time": "1:50:24", "throughput": 2872.79, "total_tokens": 5886512} {"current_steps": 9020, "total_steps": 38160, "loss": 0.2996, "lr": 4.7221553023239216e-05, "epoch": 4.727463312368973, "percentage": 23.64, "elapsed_time": "0:34:10", "remaining_time": "1:50:23", "throughput": 2872.75, "total_tokens": 5889648} {"current_steps": 9025, "total_steps": 38160, "loss": 0.3455, "lr": 4.721631179817925e-05, "epoch": 4.730083857442348, "percentage": 23.65, "elapsed_time": "0:34:11", "remaining_time": "1:50:22", "throughput": 2872.66, "total_tokens": 5892752} {"current_steps": 9030, "total_steps": 38160, "loss": 0.4538, "lr": 4.721106592572031e-05, "epoch": 4.732704402515723, "percentage": 23.66, "elapsed_time": "0:34:12", "remaining_time": "1:50:20", "throughput": 2872.84, "total_tokens": 5896112} {"current_steps": 9035, "total_steps": 38160, "loss": 0.3456, "lr": 4.7205815406959774e-05, "epoch": 4.735324947589098, "percentage": 23.68, "elapsed_time": "0:34:13", "remaining_time": "1:50:19", "throughput": 2872.98, "total_tokens": 5899440} {"current_steps": 9040, "total_steps": 38160, "loss": 0.4645, "lr": 4.7200560242996e-05, "epoch": 4.737945492662474, "percentage": 23.69, "elapsed_time": "0:34:14", "remaining_time": "1:50:17", "throughput": 2872.85, "total_tokens": 5902096} {"current_steps": 9045, "total_steps": 38160, "loss": 0.3478, "lr": 4.719530043492829e-05, "epoch": 4.740566037735849, "percentage": 23.7, "elapsed_time": "0:34:15", "remaining_time": "1:50:16", "throughput": 2872.77, "total_tokens": 5904880} {"current_steps": 9050, "total_steps": 38160, "loss": 0.4116, "lr": 4.7190035983856954e-05, "epoch": 4.743186582809225, "percentage": 23.72, "elapsed_time": "0:34:16", "remaining_time": "1:50:14", "throughput": 2872.7, "total_tokens": 5907632} {"current_steps": 9055, "total_steps": 38160, "loss": 0.3145, "lr": 4.718476689088325e-05, "epoch": 4.7458071278826, "percentage": 23.73, "elapsed_time": "0:34:17", "remaining_time": "1:50:13", "throughput": 2872.9, "total_tokens": 5911120} {"current_steps": 9060, "total_steps": 38160, "loss": 0.3193, "lr": 4.71794931571094e-05, "epoch": 4.748427672955975, "percentage": 23.74, "elapsed_time": "0:34:18", "remaining_time": "1:50:12", "throughput": 2873.26, "total_tokens": 5914928} {"current_steps": 9065, "total_steps": 38160, "loss": 0.3295, "lr": 4.717421478363862e-05, "epoch": 4.75104821802935, "percentage": 23.76, "elapsed_time": "0:34:19", "remaining_time": "1:50:10", "throughput": 2873.36, "total_tokens": 5918192} {"current_steps": 9070, "total_steps": 38160, "loss": 0.2664, "lr": 4.7168931771575085e-05, "epoch": 4.753668763102725, "percentage": 23.77, "elapsed_time": "0:34:20", "remaining_time": "1:50:09", "throughput": 2873.26, "total_tokens": 5921232} {"current_steps": 9075, "total_steps": 38160, "loss": 0.3054, "lr": 4.716364412202394e-05, "epoch": 4.7562893081761, "percentage": 23.78, "elapsed_time": "0:34:21", "remaining_time": "1:50:08", "throughput": 2873.55, "total_tokens": 5925040} {"current_steps": 9080, "total_steps": 38160, "loss": 0.4065, "lr": 4.7158351836091306e-05, "epoch": 4.758909853249476, "percentage": 23.79, "elapsed_time": "0:34:22", "remaining_time": "1:50:06", "throughput": 2873.26, "total_tokens": 5927376} {"current_steps": 9085, "total_steps": 38160, "loss": 0.3451, "lr": 4.7153054914884266e-05, "epoch": 4.761530398322851, "percentage": 23.81, "elapsed_time": "0:34:23", "remaining_time": "1:50:05", "throughput": 2873.35, "total_tokens": 5930576} {"current_steps": 9090, "total_steps": 38160, "loss": 0.3036, "lr": 4.714775335951086e-05, "epoch": 4.764150943396227, "percentage": 23.82, "elapsed_time": "0:34:25", "remaining_time": "1:50:03", "throughput": 2873.26, "total_tokens": 5933328} {"current_steps": 9095, "total_steps": 38160, "loss": 0.3708, "lr": 4.7142447171080137e-05, "epoch": 4.766771488469602, "percentage": 23.83, "elapsed_time": "0:34:26", "remaining_time": "1:50:02", "throughput": 2873.22, "total_tokens": 5936208} {"current_steps": 9100, "total_steps": 38160, "loss": 0.4631, "lr": 4.713713635070208e-05, "epoch": 4.769392033542977, "percentage": 23.85, "elapsed_time": "0:34:27", "remaining_time": "1:50:01", "throughput": 2873.03, "total_tokens": 5938832} {"current_steps": 9105, "total_steps": 38160, "loss": 0.2813, "lr": 4.713182089948765e-05, "epoch": 4.772012578616352, "percentage": 23.86, "elapsed_time": "0:34:28", "remaining_time": "1:49:59", "throughput": 2873.19, "total_tokens": 5942128} {"current_steps": 9110, "total_steps": 38160, "loss": 0.2277, "lr": 4.712650081854878e-05, "epoch": 4.7746331236897275, "percentage": 23.87, "elapsed_time": "0:34:29", "remaining_time": "1:49:58", "throughput": 2873.41, "total_tokens": 5945648} {"current_steps": 9115, "total_steps": 38160, "loss": 0.305, "lr": 4.712117610899837e-05, "epoch": 4.777253668763103, "percentage": 23.89, "elapsed_time": "0:34:30", "remaining_time": "1:49:57", "throughput": 2873.93, "total_tokens": 5950352} {"current_steps": 9120, "total_steps": 38160, "loss": 0.4747, "lr": 4.7115846771950286e-05, "epoch": 4.779874213836478, "percentage": 23.9, "elapsed_time": "0:34:31", "remaining_time": "1:49:56", "throughput": 2874.02, "total_tokens": 5953488} {"current_steps": 9125, "total_steps": 38160, "loss": 0.3468, "lr": 4.711051280851938e-05, "epoch": 4.782494758909853, "percentage": 23.91, "elapsed_time": "0:34:32", "remaining_time": "1:49:54", "throughput": 2874.14, "total_tokens": 5956784} {"current_steps": 9130, "total_steps": 38160, "loss": 0.3956, "lr": 4.7105174219821435e-05, "epoch": 4.785115303983228, "percentage": 23.93, "elapsed_time": "0:34:33", "remaining_time": "1:49:53", "throughput": 2874.26, "total_tokens": 5960080} {"current_steps": 9135, "total_steps": 38160, "loss": 0.2839, "lr": 4.709983100697323e-05, "epoch": 4.787735849056604, "percentage": 23.94, "elapsed_time": "0:34:34", "remaining_time": "1:49:51", "throughput": 2874.14, "total_tokens": 5962864} {"current_steps": 9140, "total_steps": 38160, "loss": 0.3351, "lr": 4.709448317109252e-05, "epoch": 4.790356394129979, "percentage": 23.95, "elapsed_time": "0:34:35", "remaining_time": "1:49:50", "throughput": 2874.19, "total_tokens": 5966000} {"current_steps": 9145, "total_steps": 38160, "loss": 0.3849, "lr": 4.708913071329798e-05, "epoch": 4.7929769392033545, "percentage": 23.96, "elapsed_time": "0:34:36", "remaining_time": "1:49:49", "throughput": 2874.24, "total_tokens": 5969168} {"current_steps": 9150, "total_steps": 38160, "loss": 0.4098, "lr": 4.708377363470932e-05, "epoch": 4.79559748427673, "percentage": 23.98, "elapsed_time": "0:34:37", "remaining_time": "1:49:47", "throughput": 2874.4, "total_tokens": 5972720} {"current_steps": 9155, "total_steps": 38160, "loss": 0.253, "lr": 4.7078411936447144e-05, "epoch": 4.798218029350105, "percentage": 23.99, "elapsed_time": "0:34:38", "remaining_time": "1:49:46", "throughput": 2874.42, "total_tokens": 5975760} {"current_steps": 9160, "total_steps": 38160, "loss": 0.2767, "lr": 4.707304561963308e-05, "epoch": 4.80083857442348, "percentage": 24.0, "elapsed_time": "0:34:39", "remaining_time": "1:49:45", "throughput": 2874.6, "total_tokens": 5979120} {"current_steps": 9165, "total_steps": 38160, "loss": 0.4002, "lr": 4.70676746853897e-05, "epoch": 4.803459119496855, "percentage": 24.02, "elapsed_time": "0:34:41", "remaining_time": "1:49:44", "throughput": 2875.02, "total_tokens": 5983376} {"current_steps": 9170, "total_steps": 38160, "loss": 0.4218, "lr": 4.706229913484054e-05, "epoch": 4.80607966457023, "percentage": 24.03, "elapsed_time": "0:34:42", "remaining_time": "1:49:42", "throughput": 2875.09, "total_tokens": 5986416} {"current_steps": 9175, "total_steps": 38160, "loss": 0.2802, "lr": 4.705691896911009e-05, "epoch": 4.808700209643606, "percentage": 24.04, "elapsed_time": "0:34:43", "remaining_time": "1:49:41", "throughput": 2874.97, "total_tokens": 5989136} {"current_steps": 9180, "total_steps": 38160, "loss": 0.4968, "lr": 4.705153418932383e-05, "epoch": 4.811320754716981, "percentage": 24.06, "elapsed_time": "0:34:44", "remaining_time": "1:49:39", "throughput": 2874.96, "total_tokens": 5992112} {"current_steps": 9185, "total_steps": 38160, "loss": 0.2862, "lr": 4.7046144796608206e-05, "epoch": 4.813941299790356, "percentage": 24.07, "elapsed_time": "0:34:45", "remaining_time": "1:49:38", "throughput": 2875.12, "total_tokens": 5995472} {"current_steps": 9190, "total_steps": 38160, "loss": 0.3115, "lr": 4.70407507920906e-05, "epoch": 4.816561844863732, "percentage": 24.08, "elapsed_time": "0:34:46", "remaining_time": "1:49:36", "throughput": 2875.2, "total_tokens": 5998736} {"current_steps": 9195, "total_steps": 38160, "loss": 0.4981, "lr": 4.7035352176899384e-05, "epoch": 4.819182389937107, "percentage": 24.1, "elapsed_time": "0:34:47", "remaining_time": "1:49:35", "throughput": 2875.15, "total_tokens": 6001552} {"current_steps": 9200, "total_steps": 38160, "loss": 0.3869, "lr": 4.7029948952163885e-05, "epoch": 4.821802935010482, "percentage": 24.11, "elapsed_time": "0:34:48", "remaining_time": "1:49:34", "throughput": 2875.5, "total_tokens": 6005520} {"current_steps": 9205, "total_steps": 38160, "loss": 0.3469, "lr": 4.7024541119014386e-05, "epoch": 4.8244234800838575, "percentage": 24.12, "elapsed_time": "0:34:49", "remaining_time": "1:49:32", "throughput": 2875.77, "total_tokens": 6009200} {"current_steps": 9210, "total_steps": 38160, "loss": 0.3385, "lr": 4.701912867858217e-05, "epoch": 4.827044025157233, "percentage": 24.14, "elapsed_time": "0:34:50", "remaining_time": "1:49:31", "throughput": 2876.01, "total_tokens": 6012912} {"current_steps": 9215, "total_steps": 38160, "loss": 0.4373, "lr": 4.7013711631999434e-05, "epoch": 4.829664570230608, "percentage": 24.15, "elapsed_time": "0:34:51", "remaining_time": "1:49:30", "throughput": 2876.64, "total_tokens": 6017744} {"current_steps": 9220, "total_steps": 38160, "loss": 0.345, "lr": 4.700828998039937e-05, "epoch": 4.832285115303983, "percentage": 24.16, "elapsed_time": "0:34:52", "remaining_time": "1:49:29", "throughput": 2876.59, "total_tokens": 6020624} {"current_steps": 9225, "total_steps": 38160, "loss": 0.3595, "lr": 4.700286372491612e-05, "epoch": 4.834905660377358, "percentage": 24.17, "elapsed_time": "0:34:54", "remaining_time": "1:49:28", "throughput": 2876.41, "total_tokens": 6023312} {"current_steps": 9230, "total_steps": 38160, "loss": 0.3568, "lr": 4.6997432866684816e-05, "epoch": 4.837526205450734, "percentage": 24.19, "elapsed_time": "0:34:55", "remaining_time": "1:49:26", "throughput": 2876.31, "total_tokens": 6026032} {"current_steps": 9235, "total_steps": 38160, "loss": 0.3219, "lr": 4.6991997406841504e-05, "epoch": 4.840146750524109, "percentage": 24.2, "elapsed_time": "0:34:56", "remaining_time": "1:49:25", "throughput": 2876.62, "total_tokens": 6029872} {"current_steps": 9240, "total_steps": 38160, "loss": 0.3666, "lr": 4.698655734652324e-05, "epoch": 4.8427672955974845, "percentage": 24.21, "elapsed_time": "0:34:57", "remaining_time": "1:49:24", "throughput": 2876.78, "total_tokens": 6033232} {"current_steps": 9245, "total_steps": 38160, "loss": 0.5103, "lr": 4.698111268686801e-05, "epoch": 4.84538784067086, "percentage": 24.23, "elapsed_time": "0:34:58", "remaining_time": "1:49:22", "throughput": 2876.66, "total_tokens": 6035888} {"current_steps": 9250, "total_steps": 38160, "loss": 0.3631, "lr": 4.6975663429014785e-05, "epoch": 4.848008385744235, "percentage": 24.24, "elapsed_time": "0:34:59", "remaining_time": "1:49:21", "throughput": 2876.9, "total_tokens": 6039408} {"current_steps": 9255, "total_steps": 38160, "loss": 0.4463, "lr": 4.697020957410347e-05, "epoch": 4.85062893081761, "percentage": 24.25, "elapsed_time": "0:35:00", "remaining_time": "1:49:19", "throughput": 2877.07, "total_tokens": 6042736} {"current_steps": 9260, "total_steps": 38160, "loss": 0.3639, "lr": 4.6964751123274974e-05, "epoch": 4.853249475890985, "percentage": 24.27, "elapsed_time": "0:35:01", "remaining_time": "1:49:18", "throughput": 2876.86, "total_tokens": 6045296} {"current_steps": 9265, "total_steps": 38160, "loss": 0.357, "lr": 4.695928807767113e-05, "epoch": 4.85587002096436, "percentage": 24.28, "elapsed_time": "0:35:02", "remaining_time": "1:49:16", "throughput": 2876.69, "total_tokens": 6047920} {"current_steps": 9270, "total_steps": 38160, "loss": 0.2745, "lr": 4.695382043843474e-05, "epoch": 4.8584905660377355, "percentage": 24.29, "elapsed_time": "0:35:03", "remaining_time": "1:49:15", "throughput": 2877.28, "total_tokens": 6052432} {"current_steps": 9275, "total_steps": 38160, "loss": 0.3252, "lr": 4.694834820670958e-05, "epoch": 4.861111111111111, "percentage": 24.31, "elapsed_time": "0:35:04", "remaining_time": "1:49:14", "throughput": 2877.24, "total_tokens": 6055472} {"current_steps": 9280, "total_steps": 38160, "loss": 0.4631, "lr": 4.694287138364037e-05, "epoch": 4.863731656184486, "percentage": 24.32, "elapsed_time": "0:35:05", "remaining_time": "1:49:13", "throughput": 2877.47, "total_tokens": 6059184} {"current_steps": 9285, "total_steps": 38160, "loss": 0.4664, "lr": 4.6937389970372815e-05, "epoch": 4.866352201257862, "percentage": 24.33, "elapsed_time": "0:35:06", "remaining_time": "1:49:11", "throughput": 2877.45, "total_tokens": 6062192} {"current_steps": 9290, "total_steps": 38160, "loss": 0.3279, "lr": 4.693190396805354e-05, "epoch": 4.868972746331237, "percentage": 24.34, "elapsed_time": "0:35:07", "remaining_time": "1:49:10", "throughput": 2877.49, "total_tokens": 6065264} {"current_steps": 9295, "total_steps": 38160, "loss": 0.4494, "lr": 4.692641337783017e-05, "epoch": 4.871593291404612, "percentage": 24.36, "elapsed_time": "0:35:08", "remaining_time": "1:49:09", "throughput": 2877.73, "total_tokens": 6069008} {"current_steps": 9300, "total_steps": 38160, "loss": 0.3033, "lr": 4.6920918200851274e-05, "epoch": 4.8742138364779874, "percentage": 24.37, "elapsed_time": "0:35:10", "remaining_time": "1:49:07", "throughput": 2877.95, "total_tokens": 6072624} {"current_steps": 9305, "total_steps": 38160, "loss": 0.4537, "lr": 4.691541843826638e-05, "epoch": 4.876834381551363, "percentage": 24.38, "elapsed_time": "0:35:11", "remaining_time": "1:49:06", "throughput": 2877.8, "total_tokens": 6075280} {"current_steps": 9310, "total_steps": 38160, "loss": 0.3965, "lr": 4.690991409122597e-05, "epoch": 4.879454926624738, "percentage": 24.4, "elapsed_time": "0:35:12", "remaining_time": "1:49:05", "throughput": 2877.83, "total_tokens": 6078448} {"current_steps": 9315, "total_steps": 38160, "loss": 0.2018, "lr": 4.690440516088149e-05, "epoch": 4.882075471698113, "percentage": 24.41, "elapsed_time": "0:35:13", "remaining_time": "1:49:03", "throughput": 2877.58, "total_tokens": 6081008} {"current_steps": 9320, "total_steps": 38160, "loss": 0.3887, "lr": 4.689889164838536e-05, "epoch": 4.884696016771488, "percentage": 24.42, "elapsed_time": "0:35:14", "remaining_time": "1:49:02", "throughput": 2878.02, "total_tokens": 6085296} {"current_steps": 9325, "total_steps": 38160, "loss": 0.403, "lr": 4.6893373554890925e-05, "epoch": 4.887316561844864, "percentage": 24.44, "elapsed_time": "0:35:15", "remaining_time": "1:49:01", "throughput": 2877.7, "total_tokens": 6087664} {"current_steps": 9330, "total_steps": 38160, "loss": 0.3801, "lr": 4.688785088155251e-05, "epoch": 4.889937106918239, "percentage": 24.45, "elapsed_time": "0:35:16", "remaining_time": "1:49:00", "throughput": 2877.74, "total_tokens": 6090832} {"current_steps": 9335, "total_steps": 38160, "loss": 0.4131, "lr": 4.688232362952541e-05, "epoch": 4.8925576519916145, "percentage": 24.46, "elapsed_time": "0:35:17", "remaining_time": "1:48:58", "throughput": 2877.66, "total_tokens": 6093616} {"current_steps": 9340, "total_steps": 38160, "loss": 0.2815, "lr": 4.687679179996585e-05, "epoch": 4.89517819706499, "percentage": 24.48, "elapsed_time": "0:35:18", "remaining_time": "1:48:57", "throughput": 2877.66, "total_tokens": 6096592} {"current_steps": 9345, "total_steps": 38160, "loss": 0.2589, "lr": 4.687125539403103e-05, "epoch": 4.897798742138365, "percentage": 24.49, "elapsed_time": "0:35:19", "remaining_time": "1:48:55", "throughput": 2877.93, "total_tokens": 6100144} {"current_steps": 9350, "total_steps": 38160, "loss": 0.4031, "lr": 4.68657144128791e-05, "epoch": 4.90041928721174, "percentage": 24.5, "elapsed_time": "0:35:20", "remaining_time": "1:48:54", "throughput": 2878.08, "total_tokens": 6103536} {"current_steps": 9355, "total_steps": 38160, "loss": 0.3618, "lr": 4.6860168857669175e-05, "epoch": 4.903039832285115, "percentage": 24.52, "elapsed_time": "0:35:21", "remaining_time": "1:48:53", "throughput": 2878.37, "total_tokens": 6107408} {"current_steps": 9360, "total_steps": 38160, "loss": 0.3789, "lr": 4.6854618729561315e-05, "epoch": 4.90566037735849, "percentage": 24.53, "elapsed_time": "0:35:22", "remaining_time": "1:48:51", "throughput": 2878.4, "total_tokens": 6110480} {"current_steps": 9365, "total_steps": 38160, "loss": 0.2984, "lr": 4.684906402971655e-05, "epoch": 4.9082809224318655, "percentage": 24.54, "elapsed_time": "0:35:23", "remaining_time": "1:48:50", "throughput": 2878.36, "total_tokens": 6113488} {"current_steps": 9370, "total_steps": 38160, "loss": 0.3795, "lr": 4.684350475929685e-05, "epoch": 4.910901467505241, "percentage": 24.55, "elapsed_time": "0:35:25", "remaining_time": "1:48:49", "throughput": 2878.7, "total_tokens": 6117648} {"current_steps": 9375, "total_steps": 38160, "loss": 0.372, "lr": 4.683794091946517e-05, "epoch": 4.913522012578616, "percentage": 24.57, "elapsed_time": "0:35:26", "remaining_time": "1:48:48", "throughput": 2878.62, "total_tokens": 6120592} {"current_steps": 9380, "total_steps": 38160, "loss": 0.4053, "lr": 4.683237251138538e-05, "epoch": 4.916142557651992, "percentage": 24.58, "elapsed_time": "0:35:27", "remaining_time": "1:48:47", "throughput": 2878.83, "total_tokens": 6124400} {"current_steps": 9385, "total_steps": 38160, "loss": 0.3844, "lr": 4.6826799536222346e-05, "epoch": 4.918763102725367, "percentage": 24.59, "elapsed_time": "0:35:28", "remaining_time": "1:48:46", "throughput": 2879.06, "total_tokens": 6128400} {"current_steps": 9390, "total_steps": 38160, "loss": 0.3179, "lr": 4.6821221995141865e-05, "epoch": 4.921383647798742, "percentage": 24.61, "elapsed_time": "0:35:29", "remaining_time": "1:48:45", "throughput": 2879.05, "total_tokens": 6131536} {"current_steps": 9395, "total_steps": 38160, "loss": 0.2556, "lr": 4.681563988931068e-05, "epoch": 4.924004192872117, "percentage": 24.62, "elapsed_time": "0:35:30", "remaining_time": "1:48:43", "throughput": 2879.35, "total_tokens": 6135280} {"current_steps": 9400, "total_steps": 38160, "loss": 0.3626, "lr": 4.681005321989652e-05, "epoch": 4.926624737945493, "percentage": 24.63, "elapsed_time": "0:35:31", "remaining_time": "1:48:42", "throughput": 2878.93, "total_tokens": 6137680} {"current_steps": 9405, "total_steps": 38160, "loss": 0.5751, "lr": 4.6804461988068055e-05, "epoch": 4.929245283018868, "percentage": 24.65, "elapsed_time": "0:35:33", "remaining_time": "1:48:41", "throughput": 2879.08, "total_tokens": 6141264} {"current_steps": 9410, "total_steps": 38160, "loss": 0.323, "lr": 4.6798866194994896e-05, "epoch": 4.931865828092243, "percentage": 24.66, "elapsed_time": "0:35:34", "remaining_time": "1:48:40", "throughput": 2879.38, "total_tokens": 6145104} {"current_steps": 9415, "total_steps": 38160, "loss": 0.3408, "lr": 4.6793265841847624e-05, "epoch": 4.934486373165618, "percentage": 24.67, "elapsed_time": "0:35:35", "remaining_time": "1:48:39", "throughput": 2879.71, "total_tokens": 6148976} {"current_steps": 9420, "total_steps": 38160, "loss": 0.4685, "lr": 4.6787660929797766e-05, "epoch": 4.937106918238994, "percentage": 24.69, "elapsed_time": "0:35:36", "remaining_time": "1:48:37", "throughput": 2879.96, "total_tokens": 6152560} {"current_steps": 9425, "total_steps": 38160, "loss": 0.3893, "lr": 4.678205146001781e-05, "epoch": 4.939727463312369, "percentage": 24.7, "elapsed_time": "0:35:37", "remaining_time": "1:48:36", "throughput": 2879.65, "total_tokens": 6155024} {"current_steps": 9430, "total_steps": 38160, "loss": 0.3421, "lr": 4.67764374336812e-05, "epoch": 4.9423480083857445, "percentage": 24.71, "elapsed_time": "0:35:38", "remaining_time": "1:48:35", "throughput": 2879.42, "total_tokens": 6157584} {"current_steps": 9435, "total_steps": 38160, "loss": 0.387, "lr": 4.6770818851962305e-05, "epoch": 4.94496855345912, "percentage": 24.72, "elapsed_time": "0:35:39", "remaining_time": "1:48:33", "throughput": 2879.18, "total_tokens": 6160240} {"current_steps": 9440, "total_steps": 38160, "loss": 0.4112, "lr": 4.676519571603648e-05, "epoch": 4.947589098532495, "percentage": 24.74, "elapsed_time": "0:35:40", "remaining_time": "1:48:32", "throughput": 2879.39, "total_tokens": 6163696} {"current_steps": 9445, "total_steps": 38160, "loss": 0.2873, "lr": 4.6759568027080034e-05, "epoch": 4.95020964360587, "percentage": 24.75, "elapsed_time": "0:35:42", "remaining_time": "1:48:32", "throughput": 2879.83, "total_tokens": 6168880} {"current_steps": 9450, "total_steps": 38160, "loss": 0.3763, "lr": 4.67539357862702e-05, "epoch": 4.952830188679245, "percentage": 24.76, "elapsed_time": "0:35:43", "remaining_time": "1:48:31", "throughput": 2879.92, "total_tokens": 6172208} {"current_steps": 9455, "total_steps": 38160, "loss": 0.2955, "lr": 4.6748298994785175e-05, "epoch": 4.95545073375262, "percentage": 24.78, "elapsed_time": "0:35:44", "remaining_time": "1:48:29", "throughput": 2879.79, "total_tokens": 6174928} {"current_steps": 9460, "total_steps": 38160, "loss": 0.388, "lr": 4.6742657653804116e-05, "epoch": 4.9580712788259955, "percentage": 24.79, "elapsed_time": "0:35:45", "remaining_time": "1:48:28", "throughput": 2880.11, "total_tokens": 6178992} {"current_steps": 9465, "total_steps": 38160, "loss": 0.3534, "lr": 4.673701176450713e-05, "epoch": 4.960691823899371, "percentage": 24.8, "elapsed_time": "0:35:46", "remaining_time": "1:48:27", "throughput": 2880.06, "total_tokens": 6182128} {"current_steps": 9470, "total_steps": 38160, "loss": 0.3122, "lr": 4.6731361328075286e-05, "epoch": 4.963312368972746, "percentage": 24.82, "elapsed_time": "0:35:47", "remaining_time": "1:48:26", "throughput": 2880.07, "total_tokens": 6185328} {"current_steps": 9475, "total_steps": 38160, "loss": 0.3856, "lr": 4.672570634569056e-05, "epoch": 4.965932914046122, "percentage": 24.83, "elapsed_time": "0:35:48", "remaining_time": "1:48:25", "throughput": 2880.16, "total_tokens": 6188560} {"current_steps": 9480, "total_steps": 38160, "loss": 0.4483, "lr": 4.672004681853593e-05, "epoch": 4.968553459119497, "percentage": 24.84, "elapsed_time": "0:35:49", "remaining_time": "1:48:24", "throughput": 2880.53, "total_tokens": 6193136} {"current_steps": 9485, "total_steps": 38160, "loss": 0.5353, "lr": 4.6714382747795304e-05, "epoch": 4.971174004192872, "percentage": 24.86, "elapsed_time": "0:35:51", "remaining_time": "1:48:23", "throughput": 2880.71, "total_tokens": 6196816} {"current_steps": 9490, "total_steps": 38160, "loss": 0.3617, "lr": 4.670871413465354e-05, "epoch": 4.973794549266247, "percentage": 24.87, "elapsed_time": "0:35:52", "remaining_time": "1:48:22", "throughput": 2880.75, "total_tokens": 6200272} {"current_steps": 9495, "total_steps": 38160, "loss": 0.2916, "lr": 4.670304098029645e-05, "epoch": 4.976415094339623, "percentage": 24.88, "elapsed_time": "0:35:53", "remaining_time": "1:48:21", "throughput": 2880.67, "total_tokens": 6203216} {"current_steps": 9500, "total_steps": 38160, "loss": 0.2961, "lr": 4.669736328591078e-05, "epoch": 4.979035639412998, "percentage": 24.9, "elapsed_time": "0:35:54", "remaining_time": "1:48:19", "throughput": 2880.85, "total_tokens": 6206736} {"current_steps": 9505, "total_steps": 38160, "loss": 0.3203, "lr": 4.669168105268424e-05, "epoch": 4.981656184486373, "percentage": 24.91, "elapsed_time": "0:35:55", "remaining_time": "1:48:18", "throughput": 2880.95, "total_tokens": 6209936} {"current_steps": 9510, "total_steps": 38160, "loss": 0.3416, "lr": 4.6685994281805514e-05, "epoch": 4.984276729559748, "percentage": 24.92, "elapsed_time": "0:35:56", "remaining_time": "1:48:17", "throughput": 2881.01, "total_tokens": 6213424} {"current_steps": 9515, "total_steps": 38160, "loss": 0.3071, "lr": 4.6680302974464175e-05, "epoch": 4.986897274633124, "percentage": 24.93, "elapsed_time": "0:35:57", "remaining_time": "1:48:16", "throughput": 2881.34, "total_tokens": 6217360} {"current_steps": 9520, "total_steps": 38160, "loss": 0.4092, "lr": 4.66746071318508e-05, "epoch": 4.989517819706499, "percentage": 24.95, "elapsed_time": "0:35:58", "remaining_time": "1:48:14", "throughput": 2881.17, "total_tokens": 6219984} {"current_steps": 9525, "total_steps": 38160, "loss": 0.2863, "lr": 4.6668906755156896e-05, "epoch": 4.9921383647798745, "percentage": 24.96, "elapsed_time": "0:35:59", "remaining_time": "1:48:13", "throughput": 2881.38, "total_tokens": 6223664} {"current_steps": 9530, "total_steps": 38160, "loss": 0.3646, "lr": 4.6663201845574906e-05, "epoch": 4.99475890985325, "percentage": 24.97, "elapsed_time": "0:36:01", "remaining_time": "1:48:12", "throughput": 2881.63, "total_tokens": 6227440} {"current_steps": 9535, "total_steps": 38160, "loss": 0.2882, "lr": 4.6657492404298234e-05, "epoch": 4.997379454926625, "percentage": 24.99, "elapsed_time": "0:36:02", "remaining_time": "1:48:10", "throughput": 2881.67, "total_tokens": 6230608} {"current_steps": 9540, "total_steps": 38160, "loss": 0.406, "lr": 4.665177843252124e-05, "epoch": 5.0, "percentage": 25.0, "elapsed_time": "0:36:03", "remaining_time": "1:48:10", "throughput": 2881.55, "total_tokens": 6233920} {"current_steps": 9540, "total_steps": 38160, "eval_loss": 0.4919157326221466, "epoch": 5.0, "percentage": 25.0, "elapsed_time": "0:36:15", "remaining_time": "1:48:45", "throughput": 2866.04, "total_tokens": 6233920} {"current_steps": 9545, "total_steps": 38160, "loss": 0.27, "lr": 4.664605993143921e-05, "epoch": 5.002620545073375, "percentage": 25.01, "elapsed_time": "0:36:19", "remaining_time": "1:48:53", "throughput": 2861.89, "total_tokens": 6237312} {"current_steps": 9550, "total_steps": 38160, "loss": 0.2943, "lr": 4.6640336902248396e-05, "epoch": 5.00524109014675, "percentage": 25.03, "elapsed_time": "0:36:20", "remaining_time": "1:48:52", "throughput": 2862.22, "total_tokens": 6241344} {"current_steps": 9555, "total_steps": 38160, "loss": 0.372, "lr": 4.6634609346145984e-05, "epoch": 5.0078616352201255, "percentage": 25.04, "elapsed_time": "0:36:21", "remaining_time": "1:48:51", "throughput": 2861.98, "total_tokens": 6244064} {"current_steps": 9560, "total_steps": 38160, "loss": 0.4397, "lr": 4.6628877264330116e-05, "epoch": 5.010482180293501, "percentage": 25.05, "elapsed_time": "0:36:22", "remaining_time": "1:48:50", "throughput": 2861.89, "total_tokens": 6247008} {"current_steps": 9565, "total_steps": 38160, "loss": 0.3941, "lr": 4.6623140657999886e-05, "epoch": 5.013102725366877, "percentage": 25.07, "elapsed_time": "0:36:23", "remaining_time": "1:48:49", "throughput": 2861.8, "total_tokens": 6250016} {"current_steps": 9570, "total_steps": 38160, "loss": 0.4142, "lr": 4.661739952835532e-05, "epoch": 5.015723270440252, "percentage": 25.08, "elapsed_time": "0:36:25", "remaining_time": "1:48:47", "throughput": 2861.88, "total_tokens": 6253504} {"current_steps": 9575, "total_steps": 38160, "loss": 0.3131, "lr": 4.66116538765974e-05, "epoch": 5.018343815513627, "percentage": 25.09, "elapsed_time": "0:36:26", "remaining_time": "1:48:46", "throughput": 2861.68, "total_tokens": 6256256} {"current_steps": 9580, "total_steps": 38160, "loss": 0.4556, "lr": 4.6605903703928034e-05, "epoch": 5.020964360587002, "percentage": 25.1, "elapsed_time": "0:36:27", "remaining_time": "1:48:45", "throughput": 2861.94, "total_tokens": 6260160} {"current_steps": 9585, "total_steps": 38160, "loss": 0.324, "lr": 4.6600149011550116e-05, "epoch": 5.023584905660377, "percentage": 25.12, "elapsed_time": "0:36:28", "remaining_time": "1:48:44", "throughput": 2862.08, "total_tokens": 6264032} {"current_steps": 9590, "total_steps": 38160, "loss": 0.3344, "lr": 4.659438980066745e-05, "epoch": 5.026205450733753, "percentage": 25.13, "elapsed_time": "0:36:29", "remaining_time": "1:48:43", "throughput": 2862.28, "total_tokens": 6267552} {"current_steps": 9595, "total_steps": 38160, "loss": 0.3248, "lr": 4.65886260724848e-05, "epoch": 5.028825995807128, "percentage": 25.14, "elapsed_time": "0:36:30", "remaining_time": "1:48:42", "throughput": 2862.11, "total_tokens": 6270272} {"current_steps": 9600, "total_steps": 38160, "loss": 0.164, "lr": 4.658285782820787e-05, "epoch": 5.031446540880503, "percentage": 25.16, "elapsed_time": "0:36:31", "remaining_time": "1:48:41", "throughput": 2862.54, "total_tokens": 6274624} {"current_steps": 9605, "total_steps": 38160, "loss": 0.3192, "lr": 4.657708506904331e-05, "epoch": 5.034067085953878, "percentage": 25.17, "elapsed_time": "0:36:33", "remaining_time": "1:48:39", "throughput": 2862.6, "total_tokens": 6277728} {"current_steps": 9610, "total_steps": 38160, "loss": 0.2789, "lr": 4.6571307796198724e-05, "epoch": 5.036687631027253, "percentage": 25.18, "elapsed_time": "0:36:34", "remaining_time": "1:48:38", "throughput": 2862.55, "total_tokens": 6281024} {"current_steps": 9615, "total_steps": 38160, "loss": 0.3877, "lr": 4.656552601088265e-05, "epoch": 5.039308176100629, "percentage": 25.2, "elapsed_time": "0:36:35", "remaining_time": "1:48:37", "throughput": 2862.76, "total_tokens": 6284576} {"current_steps": 9620, "total_steps": 38160, "loss": 0.3723, "lr": 4.655973971430456e-05, "epoch": 5.0419287211740045, "percentage": 25.21, "elapsed_time": "0:36:36", "remaining_time": "1:48:36", "throughput": 2862.94, "total_tokens": 6288096} {"current_steps": 9625, "total_steps": 38160, "loss": 0.3451, "lr": 4.6553948907674895e-05, "epoch": 5.04454926624738, "percentage": 25.22, "elapsed_time": "0:36:37", "remaining_time": "1:48:34", "throughput": 2863.31, "total_tokens": 6292128} {"current_steps": 9630, "total_steps": 38160, "loss": 0.307, "lr": 4.654815359220501e-05, "epoch": 5.047169811320755, "percentage": 25.24, "elapsed_time": "0:36:39", "remaining_time": "1:48:36", "throughput": 2863.9, "total_tokens": 6298912} {"current_steps": 9635, "total_steps": 38160, "loss": 0.3188, "lr": 4.6542353769107226e-05, "epoch": 5.04979035639413, "percentage": 25.25, "elapsed_time": "0:36:40", "remaining_time": "1:48:34", "throughput": 2863.74, "total_tokens": 6301536} {"current_steps": 9640, "total_steps": 38160, "loss": 0.2761, "lr": 4.653654943959481e-05, "epoch": 5.052410901467505, "percentage": 25.26, "elapsed_time": "0:36:41", "remaining_time": "1:48:33", "throughput": 2863.48, "total_tokens": 6303936} {"current_steps": 9645, "total_steps": 38160, "loss": 0.2972, "lr": 4.653074060488195e-05, "epoch": 5.05503144654088, "percentage": 25.28, "elapsed_time": "0:36:42", "remaining_time": "1:48:31", "throughput": 2863.38, "total_tokens": 6306880} {"current_steps": 9650, "total_steps": 38160, "loss": 0.3, "lr": 4.6524927266183796e-05, "epoch": 5.0576519916142555, "percentage": 25.29, "elapsed_time": "0:36:43", "remaining_time": "1:48:30", "throughput": 2863.38, "total_tokens": 6309920} {"current_steps": 9655, "total_steps": 38160, "loss": 0.2766, "lr": 4.6519109424716426e-05, "epoch": 5.060272536687631, "percentage": 25.3, "elapsed_time": "0:36:44", "remaining_time": "1:48:29", "throughput": 2863.2, "total_tokens": 6312480} {"current_steps": 9660, "total_steps": 38160, "loss": 0.2831, "lr": 4.6513287081696855e-05, "epoch": 5.062893081761007, "percentage": 25.31, "elapsed_time": "0:36:45", "remaining_time": "1:48:27", "throughput": 2863.43, "total_tokens": 6316256} {"current_steps": 9665, "total_steps": 38160, "loss": 0.3217, "lr": 4.6507460238343076e-05, "epoch": 5.065513626834382, "percentage": 25.33, "elapsed_time": "0:36:46", "remaining_time": "1:48:26", "throughput": 2863.59, "total_tokens": 6319520} {"current_steps": 9670, "total_steps": 38160, "loss": 0.3764, "lr": 4.6501628895873984e-05, "epoch": 5.068134171907757, "percentage": 25.34, "elapsed_time": "0:36:47", "remaining_time": "1:48:25", "throughput": 2863.9, "total_tokens": 6323328} {"current_steps": 9675, "total_steps": 38160, "loss": 0.2134, "lr": 4.649579305550942e-05, "epoch": 5.070754716981132, "percentage": 25.35, "elapsed_time": "0:36:49", "remaining_time": "1:48:23", "throughput": 2864.06, "total_tokens": 6326720} {"current_steps": 9680, "total_steps": 38160, "loss": 0.334, "lr": 4.64899527184702e-05, "epoch": 5.073375262054507, "percentage": 25.37, "elapsed_time": "0:36:50", "remaining_time": "1:48:22", "throughput": 2863.91, "total_tokens": 6329280} {"current_steps": 9685, "total_steps": 38160, "loss": 0.283, "lr": 4.6484107885978035e-05, "epoch": 5.075995807127883, "percentage": 25.38, "elapsed_time": "0:36:51", "remaining_time": "1:48:20", "throughput": 2863.87, "total_tokens": 6332384} {"current_steps": 9690, "total_steps": 38160, "loss": 0.2464, "lr": 4.64782585592556e-05, "epoch": 5.078616352201258, "percentage": 25.39, "elapsed_time": "0:36:52", "remaining_time": "1:48:19", "throughput": 2864.1, "total_tokens": 6336096} {"current_steps": 9695, "total_steps": 38160, "loss": 0.3347, "lr": 4.647240473952652e-05, "epoch": 5.081236897274633, "percentage": 25.41, "elapsed_time": "0:36:53", "remaining_time": "1:48:18", "throughput": 2863.74, "total_tokens": 6338432} {"current_steps": 9700, "total_steps": 38160, "loss": 0.2565, "lr": 4.6466546428015336e-05, "epoch": 5.083857442348008, "percentage": 25.42, "elapsed_time": "0:36:54", "remaining_time": "1:48:17", "throughput": 2863.85, "total_tokens": 6342016} {"current_steps": 9705, "total_steps": 38160, "loss": 0.3348, "lr": 4.646068362594753e-05, "epoch": 5.086477987421383, "percentage": 25.43, "elapsed_time": "0:36:55", "remaining_time": "1:48:16", "throughput": 2863.76, "total_tokens": 6344896} {"current_steps": 9710, "total_steps": 38160, "loss": 0.3056, "lr": 4.645481633454956e-05, "epoch": 5.089098532494759, "percentage": 25.45, "elapsed_time": "0:36:56", "remaining_time": "1:48:14", "throughput": 2863.75, "total_tokens": 6348096} {"current_steps": 9715, "total_steps": 38160, "loss": 0.3949, "lr": 4.644894455504878e-05, "epoch": 5.0917190775681345, "percentage": 25.46, "elapsed_time": "0:36:57", "remaining_time": "1:48:13", "throughput": 2863.84, "total_tokens": 6351488} {"current_steps": 9720, "total_steps": 38160, "loss": 0.3559, "lr": 4.64430682886735e-05, "epoch": 5.09433962264151, "percentage": 25.47, "elapsed_time": "0:36:58", "remaining_time": "1:48:12", "throughput": 2863.8, "total_tokens": 6354464} {"current_steps": 9725, "total_steps": 38160, "loss": 0.3004, "lr": 4.643718753665297e-05, "epoch": 5.096960167714885, "percentage": 25.48, "elapsed_time": "0:37:00", "remaining_time": "1:48:11", "throughput": 2864.2, "total_tokens": 6358912} {"current_steps": 9730, "total_steps": 38160, "loss": 0.2573, "lr": 4.643130230021737e-05, "epoch": 5.09958071278826, "percentage": 25.5, "elapsed_time": "0:37:01", "remaining_time": "1:48:10", "throughput": 2864.24, "total_tokens": 6362112} {"current_steps": 9735, "total_steps": 38160, "loss": 0.3051, "lr": 4.6425412580597836e-05, "epoch": 5.102201257861635, "percentage": 25.51, "elapsed_time": "0:37:02", "remaining_time": "1:48:08", "throughput": 2864.15, "total_tokens": 6364896} {"current_steps": 9740, "total_steps": 38160, "loss": 0.4556, "lr": 4.641951837902643e-05, "epoch": 5.10482180293501, "percentage": 25.52, "elapsed_time": "0:37:03", "remaining_time": "1:48:07", "throughput": 2864.22, "total_tokens": 6368160} {"current_steps": 9745, "total_steps": 38160, "loss": 0.2429, "lr": 4.641361969673614e-05, "epoch": 5.1074423480083855, "percentage": 25.54, "elapsed_time": "0:37:04", "remaining_time": "1:48:06", "throughput": 2864.17, "total_tokens": 6371264} {"current_steps": 9750, "total_steps": 38160, "loss": 0.3834, "lr": 4.640771653496091e-05, "epoch": 5.110062893081761, "percentage": 25.55, "elapsed_time": "0:37:05", "remaining_time": "1:48:04", "throughput": 2864.09, "total_tokens": 6374144} {"current_steps": 9755, "total_steps": 38160, "loss": 0.322, "lr": 4.64018088949356e-05, "epoch": 5.112683438155136, "percentage": 25.56, "elapsed_time": "0:37:06", "remaining_time": "1:48:03", "throughput": 2864.31, "total_tokens": 6377600} {"current_steps": 9760, "total_steps": 38160, "loss": 0.2916, "lr": 4.6395896777896055e-05, "epoch": 5.115303983228512, "percentage": 25.58, "elapsed_time": "0:37:07", "remaining_time": "1:48:02", "throughput": 2864.29, "total_tokens": 6380608} {"current_steps": 9765, "total_steps": 38160, "loss": 0.4509, "lr": 4.638998018507899e-05, "epoch": 5.117924528301887, "percentage": 25.59, "elapsed_time": "0:37:08", "remaining_time": "1:48:01", "throughput": 2864.52, "total_tokens": 6384640} {"current_steps": 9770, "total_steps": 38160, "loss": 0.2593, "lr": 4.63840591177221e-05, "epoch": 5.120545073375262, "percentage": 25.6, "elapsed_time": "0:37:09", "remaining_time": "1:47:59", "throughput": 2864.4, "total_tokens": 6387456} {"current_steps": 9775, "total_steps": 38160, "loss": 0.2854, "lr": 4.637813357706401e-05, "epoch": 5.123165618448637, "percentage": 25.62, "elapsed_time": "0:37:11", "remaining_time": "1:47:58", "throughput": 2864.54, "total_tokens": 6390880} {"current_steps": 9780, "total_steps": 38160, "loss": 0.2481, "lr": 4.6372203564344264e-05, "epoch": 5.1257861635220126, "percentage": 25.63, "elapsed_time": "0:37:12", "remaining_time": "1:47:57", "throughput": 2864.46, "total_tokens": 6393696} {"current_steps": 9785, "total_steps": 38160, "loss": 0.3013, "lr": 4.6366269080803364e-05, "epoch": 5.128406708595388, "percentage": 25.64, "elapsed_time": "0:37:13", "remaining_time": "1:47:55", "throughput": 2864.76, "total_tokens": 6397472} {"current_steps": 9790, "total_steps": 38160, "loss": 0.3188, "lr": 4.636033012768273e-05, "epoch": 5.131027253668763, "percentage": 25.66, "elapsed_time": "0:37:14", "remaining_time": "1:47:54", "throughput": 2864.82, "total_tokens": 6400576} {"current_steps": 9795, "total_steps": 38160, "loss": 0.3943, "lr": 4.635438670622473e-05, "epoch": 5.133647798742138, "percentage": 25.67, "elapsed_time": "0:37:15", "remaining_time": "1:47:53", "throughput": 2864.61, "total_tokens": 6403168} {"current_steps": 9800, "total_steps": 38160, "loss": 0.3139, "lr": 4.6348438817672646e-05, "epoch": 5.136268343815513, "percentage": 25.68, "elapsed_time": "0:37:16", "remaining_time": "1:47:51", "throughput": 2864.54, "total_tokens": 6406144} {"current_steps": 9805, "total_steps": 38160, "loss": 0.327, "lr": 4.634248646327072e-05, "epoch": 5.138888888888889, "percentage": 25.69, "elapsed_time": "0:37:17", "remaining_time": "1:47:50", "throughput": 2864.54, "total_tokens": 6409344} {"current_steps": 9810, "total_steps": 38160, "loss": 0.3205, "lr": 4.6336529644264114e-05, "epoch": 5.1415094339622645, "percentage": 25.71, "elapsed_time": "0:37:18", "remaining_time": "1:47:49", "throughput": 2864.31, "total_tokens": 6411776} {"current_steps": 9815, "total_steps": 38160, "loss": 0.2738, "lr": 4.633056836189893e-05, "epoch": 5.14412997903564, "percentage": 25.72, "elapsed_time": "0:37:19", "remaining_time": "1:47:48", "throughput": 2864.1, "total_tokens": 6414784} {"current_steps": 9820, "total_steps": 38160, "loss": 0.2902, "lr": 4.632460261742219e-05, "epoch": 5.146750524109015, "percentage": 25.73, "elapsed_time": "0:37:20", "remaining_time": "1:47:46", "throughput": 2863.84, "total_tokens": 6417248} {"current_steps": 9825, "total_steps": 38160, "loss": 0.3909, "lr": 4.631863241208187e-05, "epoch": 5.14937106918239, "percentage": 25.75, "elapsed_time": "0:37:21", "remaining_time": "1:47:45", "throughput": 2863.81, "total_tokens": 6420416} {"current_steps": 9830, "total_steps": 38160, "loss": 0.2403, "lr": 4.6312657747126865e-05, "epoch": 5.151991614255765, "percentage": 25.76, "elapsed_time": "0:37:23", "remaining_time": "1:47:44", "throughput": 2864.13, "total_tokens": 6424288} {"current_steps": 9835, "total_steps": 38160, "loss": 0.3997, "lr": 4.630667862380701e-05, "epoch": 5.15461215932914, "percentage": 25.77, "elapsed_time": "0:37:24", "remaining_time": "1:47:43", "throughput": 2863.86, "total_tokens": 6426784} {"current_steps": 9840, "total_steps": 38160, "loss": 0.3193, "lr": 4.630069504337306e-05, "epoch": 5.1572327044025155, "percentage": 25.79, "elapsed_time": "0:37:25", "remaining_time": "1:47:42", "throughput": 2863.67, "total_tokens": 6429760} {"current_steps": 9845, "total_steps": 38160, "loss": 0.2744, "lr": 4.629470700707672e-05, "epoch": 5.159853249475891, "percentage": 25.8, "elapsed_time": "0:37:26", "remaining_time": "1:47:40", "throughput": 2863.53, "total_tokens": 6432480} {"current_steps": 9850, "total_steps": 38160, "loss": 0.3321, "lr": 4.628871451617062e-05, "epoch": 5.162473794549266, "percentage": 25.81, "elapsed_time": "0:37:27", "remaining_time": "1:47:40", "throughput": 2863.95, "total_tokens": 6437312} {"current_steps": 9855, "total_steps": 38160, "loss": 0.384, "lr": 4.628271757190832e-05, "epoch": 5.165094339622642, "percentage": 25.83, "elapsed_time": "0:37:28", "remaining_time": "1:47:39", "throughput": 2864.4, "total_tokens": 6441664} {"current_steps": 9860, "total_steps": 38160, "loss": 0.2653, "lr": 4.62767161755443e-05, "epoch": 5.167714884696017, "percentage": 25.84, "elapsed_time": "0:37:29", "remaining_time": "1:47:37", "throughput": 2864.57, "total_tokens": 6445120} {"current_steps": 9865, "total_steps": 38160, "loss": 0.3262, "lr": 4.6270710328334004e-05, "epoch": 5.170335429769392, "percentage": 25.85, "elapsed_time": "0:37:30", "remaining_time": "1:47:36", "throughput": 2864.54, "total_tokens": 6447968} {"current_steps": 9870, "total_steps": 38160, "loss": 0.2896, "lr": 4.626470003153377e-05, "epoch": 5.172955974842767, "percentage": 25.86, "elapsed_time": "0:37:32", "remaining_time": "1:47:34", "throughput": 2864.35, "total_tokens": 6450592} {"current_steps": 9875, "total_steps": 38160, "loss": 0.296, "lr": 4.625868528640089e-05, "epoch": 5.1755765199161425, "percentage": 25.88, "elapsed_time": "0:37:33", "remaining_time": "1:47:33", "throughput": 2864.71, "total_tokens": 6454496} {"current_steps": 9880, "total_steps": 38160, "loss": 0.2297, "lr": 4.6252666094193586e-05, "epoch": 5.178197064989518, "percentage": 25.89, "elapsed_time": "0:37:34", "remaining_time": "1:47:32", "throughput": 2864.56, "total_tokens": 6457088} {"current_steps": 9885, "total_steps": 38160, "loss": 0.3669, "lr": 4.6246642456171e-05, "epoch": 5.180817610062893, "percentage": 25.9, "elapsed_time": "0:37:35", "remaining_time": "1:47:30", "throughput": 2864.88, "total_tokens": 6461088} {"current_steps": 9890, "total_steps": 38160, "loss": 0.3565, "lr": 4.6240614373593196e-05, "epoch": 5.183438155136268, "percentage": 25.92, "elapsed_time": "0:37:36", "remaining_time": "1:47:29", "throughput": 2864.75, "total_tokens": 6463872} {"current_steps": 9895, "total_steps": 38160, "loss": 0.3355, "lr": 4.623458184772119e-05, "epoch": 5.186058700209643, "percentage": 25.93, "elapsed_time": "0:37:37", "remaining_time": "1:47:28", "throughput": 2864.9, "total_tokens": 6467424} {"current_steps": 9900, "total_steps": 38160, "loss": 0.2888, "lr": 4.622854487981693e-05, "epoch": 5.188679245283019, "percentage": 25.94, "elapsed_time": "0:37:38", "remaining_time": "1:47:27", "throughput": 2864.92, "total_tokens": 6470688} {"current_steps": 9905, "total_steps": 38160, "loss": 0.3018, "lr": 4.622250347114326e-05, "epoch": 5.191299790356394, "percentage": 25.96, "elapsed_time": "0:37:39", "remaining_time": "1:47:25", "throughput": 2864.85, "total_tokens": 6473440} {"current_steps": 9910, "total_steps": 38160, "loss": 0.3653, "lr": 4.621645762296399e-05, "epoch": 5.19392033542977, "percentage": 25.97, "elapsed_time": "0:37:40", "remaining_time": "1:47:24", "throughput": 2864.84, "total_tokens": 6476352} {"current_steps": 9915, "total_steps": 38160, "loss": 0.2625, "lr": 4.6210407336543835e-05, "epoch": 5.196540880503145, "percentage": 25.98, "elapsed_time": "0:37:41", "remaining_time": "1:47:23", "throughput": 2865.04, "total_tokens": 6480064} {"current_steps": 9920, "total_steps": 38160, "loss": 0.2812, "lr": 4.620435261314844e-05, "epoch": 5.19916142557652, "percentage": 26.0, "elapsed_time": "0:37:42", "remaining_time": "1:47:21", "throughput": 2865.3, "total_tokens": 6483840} {"current_steps": 9925, "total_steps": 38160, "loss": 0.5182, "lr": 4.61982934540444e-05, "epoch": 5.201781970649895, "percentage": 26.01, "elapsed_time": "0:37:43", "remaining_time": "1:47:20", "throughput": 2865.1, "total_tokens": 6486368} {"current_steps": 9930, "total_steps": 38160, "loss": 0.2906, "lr": 4.6192229860499206e-05, "epoch": 5.20440251572327, "percentage": 26.02, "elapsed_time": "0:37:45", "remaining_time": "1:47:19", "throughput": 2864.87, "total_tokens": 6489152} {"current_steps": 9935, "total_steps": 38160, "loss": 0.2863, "lr": 4.6186161833781295e-05, "epoch": 5.2070230607966455, "percentage": 26.04, "elapsed_time": "0:37:46", "remaining_time": "1:47:18", "throughput": 2865.05, "total_tokens": 6493088} {"current_steps": 9940, "total_steps": 38160, "loss": 0.3073, "lr": 4.618008937516003e-05, "epoch": 5.209643605870021, "percentage": 26.05, "elapsed_time": "0:37:47", "remaining_time": "1:47:17", "throughput": 2865.07, "total_tokens": 6496256} {"current_steps": 9945, "total_steps": 38160, "loss": 0.2673, "lr": 4.617401248590572e-05, "epoch": 5.212264150943396, "percentage": 26.06, "elapsed_time": "0:37:48", "remaining_time": "1:47:15", "throughput": 2865.05, "total_tokens": 6499296} {"current_steps": 9950, "total_steps": 38160, "loss": 0.2805, "lr": 4.616793116728955e-05, "epoch": 5.214884696016772, "percentage": 26.07, "elapsed_time": "0:37:49", "remaining_time": "1:47:14", "throughput": 2865.21, "total_tokens": 6502624} {"current_steps": 9955, "total_steps": 38160, "loss": 0.4704, "lr": 4.6161845420583685e-05, "epoch": 5.217505241090147, "percentage": 26.09, "elapsed_time": "0:37:50", "remaining_time": "1:47:13", "throughput": 2865.29, "total_tokens": 6506272} {"current_steps": 9960, "total_steps": 38160, "loss": 0.312, "lr": 4.6155755247061174e-05, "epoch": 5.220125786163522, "percentage": 26.1, "elapsed_time": "0:37:51", "remaining_time": "1:47:12", "throughput": 2865.28, "total_tokens": 6509504} {"current_steps": 9965, "total_steps": 38160, "loss": 0.3527, "lr": 4.614966064799603e-05, "epoch": 5.222746331236897, "percentage": 26.11, "elapsed_time": "0:37:52", "remaining_time": "1:47:11", "throughput": 2865.26, "total_tokens": 6512512} {"current_steps": 9970, "total_steps": 38160, "loss": 0.3546, "lr": 4.6143561624663166e-05, "epoch": 5.2253668763102725, "percentage": 26.13, "elapsed_time": "0:37:53", "remaining_time": "1:47:09", "throughput": 2865.25, "total_tokens": 6515456} {"current_steps": 9975, "total_steps": 38160, "loss": 0.2624, "lr": 4.6137458178338425e-05, "epoch": 5.227987421383648, "percentage": 26.14, "elapsed_time": "0:37:55", "remaining_time": "1:47:08", "throughput": 2865.4, "total_tokens": 6518880} {"current_steps": 9980, "total_steps": 38160, "loss": 0.2955, "lr": 4.613135031029859e-05, "epoch": 5.230607966457023, "percentage": 26.15, "elapsed_time": "0:37:56", "remaining_time": "1:47:07", "throughput": 2865.21, "total_tokens": 6521664} {"current_steps": 9985, "total_steps": 38160, "loss": 0.299, "lr": 4.612523802182134e-05, "epoch": 5.233228511530398, "percentage": 26.17, "elapsed_time": "0:37:57", "remaining_time": "1:47:05", "throughput": 2864.96, "total_tokens": 6524160} {"current_steps": 9990, "total_steps": 38160, "loss": 0.2255, "lr": 4.611912131418531e-05, "epoch": 5.235849056603773, "percentage": 26.18, "elapsed_time": "0:37:58", "remaining_time": "1:47:04", "throughput": 2865.3, "total_tokens": 6527904} {"current_steps": 9995, "total_steps": 38160, "loss": 0.4939, "lr": 4.611300018867004e-05, "epoch": 5.238469601677149, "percentage": 26.19, "elapsed_time": "0:37:59", "remaining_time": "1:47:02", "throughput": 2865.13, "total_tokens": 6530560} {"current_steps": 10000, "total_steps": 38160, "loss": 0.3324, "lr": 4.6106874646556e-05, "epoch": 5.241090146750524, "percentage": 26.21, "elapsed_time": "0:38:00", "remaining_time": "1:47:01", "throughput": 2865.31, "total_tokens": 6534048} {"current_steps": 10005, "total_steps": 38160, "loss": 0.286, "lr": 4.6100744689124584e-05, "epoch": 5.2437106918239, "percentage": 26.22, "elapsed_time": "0:38:01", "remaining_time": "1:47:00", "throughput": 2865.24, "total_tokens": 6536864} {"current_steps": 10010, "total_steps": 38160, "loss": 0.3708, "lr": 4.6094610317658116e-05, "epoch": 5.246331236897275, "percentage": 26.23, "elapsed_time": "0:38:02", "remaining_time": "1:46:59", "throughput": 2865.46, "total_tokens": 6540608} {"current_steps": 10015, "total_steps": 38160, "loss": 0.3579, "lr": 4.608847153343982e-05, "epoch": 5.24895178197065, "percentage": 26.24, "elapsed_time": "0:38:03", "remaining_time": "1:46:57", "throughput": 2865.48, "total_tokens": 6543744} {"current_steps": 10020, "total_steps": 38160, "loss": 0.2994, "lr": 4.6082328337753874e-05, "epoch": 5.251572327044025, "percentage": 26.26, "elapsed_time": "0:38:04", "remaining_time": "1:46:56", "throughput": 2865.4, "total_tokens": 6546656} {"current_steps": 10025, "total_steps": 38160, "loss": 0.3736, "lr": 4.6076180731885353e-05, "epoch": 5.2541928721174, "percentage": 26.27, "elapsed_time": "0:38:05", "remaining_time": "1:46:55", "throughput": 2865.15, "total_tokens": 6549152} {"current_steps": 10030, "total_steps": 38160, "loss": 0.328, "lr": 4.6070028717120286e-05, "epoch": 5.256813417190775, "percentage": 26.28, "elapsed_time": "0:38:06", "remaining_time": "1:46:53", "throughput": 2865.12, "total_tokens": 6552096} {"current_steps": 10035, "total_steps": 38160, "loss": 0.3604, "lr": 4.606387229474558e-05, "epoch": 5.259433962264151, "percentage": 26.3, "elapsed_time": "0:38:07", "remaining_time": "1:46:52", "throughput": 2865.09, "total_tokens": 6555232} {"current_steps": 10040, "total_steps": 38160, "loss": 0.2832, "lr": 4.60577114660491e-05, "epoch": 5.262054507337526, "percentage": 26.31, "elapsed_time": "0:38:09", "remaining_time": "1:46:51", "throughput": 2864.89, "total_tokens": 6557920} {"current_steps": 10045, "total_steps": 38160, "loss": 0.2785, "lr": 4.605154623231962e-05, "epoch": 5.264675052410902, "percentage": 26.32, "elapsed_time": "0:38:10", "remaining_time": "1:46:49", "throughput": 2864.89, "total_tokens": 6560928} {"current_steps": 10050, "total_steps": 38160, "loss": 0.2771, "lr": 4.604537659484684e-05, "epoch": 5.267295597484277, "percentage": 26.34, "elapsed_time": "0:38:11", "remaining_time": "1:46:48", "throughput": 2864.69, "total_tokens": 6563488} {"current_steps": 10055, "total_steps": 38160, "loss": 0.3064, "lr": 4.603920255492138e-05, "epoch": 5.269916142557652, "percentage": 26.35, "elapsed_time": "0:38:12", "remaining_time": "1:46:47", "throughput": 2864.99, "total_tokens": 6567520} {"current_steps": 10060, "total_steps": 38160, "loss": 0.3483, "lr": 4.603302411383477e-05, "epoch": 5.272536687631027, "percentage": 26.36, "elapsed_time": "0:38:13", "remaining_time": "1:46:45", "throughput": 2865.03, "total_tokens": 6570528} {"current_steps": 10065, "total_steps": 38160, "loss": 0.2611, "lr": 4.602684127287946e-05, "epoch": 5.2751572327044025, "percentage": 26.38, "elapsed_time": "0:38:14", "remaining_time": "1:46:44", "throughput": 2865.15, "total_tokens": 6573824} {"current_steps": 10070, "total_steps": 38160, "loss": 0.3496, "lr": 4.602065403334885e-05, "epoch": 5.277777777777778, "percentage": 26.39, "elapsed_time": "0:38:15", "remaining_time": "1:46:43", "throughput": 2865.2, "total_tokens": 6576896} {"current_steps": 10075, "total_steps": 38160, "loss": 0.3514, "lr": 4.601446239653724e-05, "epoch": 5.280398322851153, "percentage": 26.4, "elapsed_time": "0:38:16", "remaining_time": "1:46:41", "throughput": 2864.85, "total_tokens": 6579136} {"current_steps": 10080, "total_steps": 38160, "loss": 0.2666, "lr": 4.600826636373984e-05, "epoch": 5.283018867924528, "percentage": 26.42, "elapsed_time": "0:38:17", "remaining_time": "1:46:40", "throughput": 2864.79, "total_tokens": 6582080} {"current_steps": 10085, "total_steps": 38160, "loss": 0.2866, "lr": 4.600206593625279e-05, "epoch": 5.285639412997903, "percentage": 26.43, "elapsed_time": "0:38:18", "remaining_time": "1:46:39", "throughput": 2864.66, "total_tokens": 6584896} {"current_steps": 10090, "total_steps": 38160, "loss": 0.3253, "lr": 4.599586111537315e-05, "epoch": 5.288259958071279, "percentage": 26.44, "elapsed_time": "0:38:19", "remaining_time": "1:46:37", "throughput": 2864.82, "total_tokens": 6588448} {"current_steps": 10095, "total_steps": 38160, "loss": 0.2979, "lr": 4.59896519023989e-05, "epoch": 5.290880503144654, "percentage": 26.45, "elapsed_time": "0:38:20", "remaining_time": "1:46:36", "throughput": 2865.21, "total_tokens": 6592704} {"current_steps": 10100, "total_steps": 38160, "loss": 0.3082, "lr": 4.5983438298628935e-05, "epoch": 5.29350104821803, "percentage": 26.47, "elapsed_time": "0:38:22", "remaining_time": "1:46:35", "throughput": 2865.44, "total_tokens": 6596256} {"current_steps": 10105, "total_steps": 38160, "loss": 0.3502, "lr": 4.597722030536306e-05, "epoch": 5.296121593291405, "percentage": 26.48, "elapsed_time": "0:38:23", "remaining_time": "1:46:34", "throughput": 2865.19, "total_tokens": 6598656} {"current_steps": 10110, "total_steps": 38160, "loss": 0.3322, "lr": 4.597099792390202e-05, "epoch": 5.29874213836478, "percentage": 26.49, "elapsed_time": "0:38:24", "remaining_time": "1:46:32", "throughput": 2865.13, "total_tokens": 6601504} {"current_steps": 10115, "total_steps": 38160, "loss": 0.3126, "lr": 4.596477115554748e-05, "epoch": 5.301362683438155, "percentage": 26.51, "elapsed_time": "0:38:25", "remaining_time": "1:46:31", "throughput": 2865.19, "total_tokens": 6604640} {"current_steps": 10120, "total_steps": 38160, "loss": 0.3387, "lr": 4.5958540001601976e-05, "epoch": 5.30398322851153, "percentage": 26.52, "elapsed_time": "0:38:26", "remaining_time": "1:46:29", "throughput": 2865.13, "total_tokens": 6607520} {"current_steps": 10125, "total_steps": 38160, "loss": 0.2452, "lr": 4.595230446336902e-05, "epoch": 5.306603773584905, "percentage": 26.53, "elapsed_time": "0:38:27", "remaining_time": "1:46:28", "throughput": 2865.45, "total_tokens": 6611360} {"current_steps": 10130, "total_steps": 38160, "loss": 0.2351, "lr": 4.5946064542153005e-05, "epoch": 5.309224318658281, "percentage": 26.55, "elapsed_time": "0:38:28", "remaining_time": "1:46:28", "throughput": 2866.04, "total_tokens": 6616672} {"current_steps": 10135, "total_steps": 38160, "loss": 0.4065, "lr": 4.593982023925926e-05, "epoch": 5.311844863731656, "percentage": 26.56, "elapsed_time": "0:38:29", "remaining_time": "1:46:26", "throughput": 2865.93, "total_tokens": 6619424} {"current_steps": 10140, "total_steps": 38160, "loss": 0.2099, "lr": 4.5933571555994e-05, "epoch": 5.314465408805032, "percentage": 26.57, "elapsed_time": "0:38:30", "remaining_time": "1:46:25", "throughput": 2866.04, "total_tokens": 6622656} {"current_steps": 10145, "total_steps": 38160, "loss": 0.2537, "lr": 4.59273184936644e-05, "epoch": 5.317085953878407, "percentage": 26.59, "elapsed_time": "0:38:31", "remaining_time": "1:46:23", "throughput": 2866.0, "total_tokens": 6625568} {"current_steps": 10150, "total_steps": 38160, "loss": 0.4434, "lr": 4.5921061053578523e-05, "epoch": 5.319706498951782, "percentage": 26.6, "elapsed_time": "0:38:32", "remaining_time": "1:46:22", "throughput": 2866.1, "total_tokens": 6628896} {"current_steps": 10155, "total_steps": 38160, "loss": 0.2702, "lr": 4.5914799237045355e-05, "epoch": 5.322327044025157, "percentage": 26.61, "elapsed_time": "0:38:33", "remaining_time": "1:46:21", "throughput": 2866.42, "total_tokens": 6632672} {"current_steps": 10160, "total_steps": 38160, "loss": 0.2793, "lr": 4.5908533045374796e-05, "epoch": 5.3249475890985325, "percentage": 26.62, "elapsed_time": "0:38:35", "remaining_time": "1:46:20", "throughput": 2866.93, "total_tokens": 6637344} {"current_steps": 10165, "total_steps": 38160, "loss": 0.3946, "lr": 4.590226247987766e-05, "epoch": 5.327568134171908, "percentage": 26.64, "elapsed_time": "0:38:36", "remaining_time": "1:46:19", "throughput": 2866.84, "total_tokens": 6640416} {"current_steps": 10170, "total_steps": 38160, "loss": 0.2387, "lr": 4.589598754186568e-05, "epoch": 5.330188679245283, "percentage": 26.65, "elapsed_time": "0:38:37", "remaining_time": "1:46:17", "throughput": 2866.51, "total_tokens": 6642688} {"current_steps": 10175, "total_steps": 38160, "loss": 0.3072, "lr": 4.5889708232651494e-05, "epoch": 5.332809224318658, "percentage": 26.66, "elapsed_time": "0:38:38", "remaining_time": "1:46:16", "throughput": 2866.62, "total_tokens": 6645952} {"current_steps": 10180, "total_steps": 38160, "loss": 0.3412, "lr": 4.588342455354867e-05, "epoch": 5.335429769392033, "percentage": 26.68, "elapsed_time": "0:38:39", "remaining_time": "1:46:15", "throughput": 2866.43, "total_tokens": 6648576} {"current_steps": 10185, "total_steps": 38160, "loss": 0.3545, "lr": 4.5877136505871685e-05, "epoch": 5.338050314465409, "percentage": 26.69, "elapsed_time": "0:38:40", "remaining_time": "1:46:13", "throughput": 2866.49, "total_tokens": 6651840} {"current_steps": 10190, "total_steps": 38160, "loss": 0.4337, "lr": 4.5870844090935914e-05, "epoch": 5.340670859538784, "percentage": 26.7, "elapsed_time": "0:38:41", "remaining_time": "1:46:12", "throughput": 2866.28, "total_tokens": 6654336} {"current_steps": 10195, "total_steps": 38160, "loss": 0.3602, "lr": 4.586454731005768e-05, "epoch": 5.34329140461216, "percentage": 26.72, "elapsed_time": "0:38:42", "remaining_time": "1:46:11", "throughput": 2866.27, "total_tokens": 6657600} {"current_steps": 10200, "total_steps": 38160, "loss": 0.2688, "lr": 4.5858246164554175e-05, "epoch": 5.345911949685535, "percentage": 26.73, "elapsed_time": "0:38:43", "remaining_time": "1:46:09", "throughput": 2866.31, "total_tokens": 6660768} {"current_steps": 10205, "total_steps": 38160, "loss": 0.3306, "lr": 4.5851940655743536e-05, "epoch": 5.34853249475891, "percentage": 26.74, "elapsed_time": "0:38:44", "remaining_time": "1:46:08", "throughput": 2866.27, "total_tokens": 6663808} {"current_steps": 10210, "total_steps": 38160, "loss": 0.3507, "lr": 4.5845630784944804e-05, "epoch": 5.351153039832285, "percentage": 26.76, "elapsed_time": "0:38:46", "remaining_time": "1:46:07", "throughput": 2865.84, "total_tokens": 6666048} {"current_steps": 10215, "total_steps": 38160, "loss": 0.2777, "lr": 4.583931655347793e-05, "epoch": 5.35377358490566, "percentage": 26.77, "elapsed_time": "0:38:47", "remaining_time": "1:46:06", "throughput": 2865.61, "total_tokens": 6668672} {"current_steps": 10220, "total_steps": 38160, "loss": 0.4198, "lr": 4.5832997962663785e-05, "epoch": 5.356394129979035, "percentage": 26.78, "elapsed_time": "0:38:48", "remaining_time": "1:46:04", "throughput": 2865.6, "total_tokens": 6671680} {"current_steps": 10225, "total_steps": 38160, "loss": 0.2697, "lr": 4.582667501382414e-05, "epoch": 5.359014675052411, "percentage": 26.8, "elapsed_time": "0:38:49", "remaining_time": "1:46:03", "throughput": 2865.58, "total_tokens": 6674592} {"current_steps": 10230, "total_steps": 38160, "loss": 0.2574, "lr": 4.582034770828169e-05, "epoch": 5.361635220125786, "percentage": 26.81, "elapsed_time": "0:38:50", "remaining_time": "1:46:02", "throughput": 2865.53, "total_tokens": 6677632} {"current_steps": 10235, "total_steps": 38160, "loss": 0.2318, "lr": 4.581401604736002e-05, "epoch": 5.364255765199162, "percentage": 26.82, "elapsed_time": "0:38:51", "remaining_time": "1:46:00", "throughput": 2865.56, "total_tokens": 6680768} {"current_steps": 10240, "total_steps": 38160, "loss": 0.329, "lr": 4.580768003238365e-05, "epoch": 5.366876310272537, "percentage": 26.83, "elapsed_time": "0:38:52", "remaining_time": "1:45:59", "throughput": 2865.44, "total_tokens": 6683712} {"current_steps": 10245, "total_steps": 38160, "loss": 0.3536, "lr": 4.5801339664678014e-05, "epoch": 5.369496855345912, "percentage": 26.85, "elapsed_time": "0:38:53", "remaining_time": "1:45:59", "throughput": 2865.86, "total_tokens": 6688512} {"current_steps": 10250, "total_steps": 38160, "loss": 0.2744, "lr": 4.579499494556943e-05, "epoch": 5.372117400419287, "percentage": 26.86, "elapsed_time": "0:38:54", "remaining_time": "1:45:57", "throughput": 2865.86, "total_tokens": 6691520} {"current_steps": 10255, "total_steps": 38160, "loss": 0.3418, "lr": 4.5788645876385147e-05, "epoch": 5.3747379454926625, "percentage": 26.87, "elapsed_time": "0:38:56", "remaining_time": "1:45:56", "throughput": 2866.05, "total_tokens": 6695360} {"current_steps": 10260, "total_steps": 38160, "loss": 0.2932, "lr": 4.578229245845331e-05, "epoch": 5.377358490566038, "percentage": 26.89, "elapsed_time": "0:38:57", "remaining_time": "1:45:55", "throughput": 2866.13, "total_tokens": 6698688} {"current_steps": 10265, "total_steps": 38160, "loss": 0.328, "lr": 4.5775934693102994e-05, "epoch": 5.379979035639413, "percentage": 26.9, "elapsed_time": "0:38:58", "remaining_time": "1:45:54", "throughput": 2865.89, "total_tokens": 6701312} {"current_steps": 10270, "total_steps": 38160, "loss": 0.326, "lr": 4.5769572581664165e-05, "epoch": 5.382599580712788, "percentage": 26.91, "elapsed_time": "0:38:59", "remaining_time": "1:45:52", "throughput": 2865.69, "total_tokens": 6703840} {"current_steps": 10275, "total_steps": 38160, "loss": 0.2874, "lr": 4.57632061254677e-05, "epoch": 5.385220125786163, "percentage": 26.93, "elapsed_time": "0:39:00", "remaining_time": "1:45:51", "throughput": 2865.66, "total_tokens": 6706720} {"current_steps": 10280, "total_steps": 38160, "loss": 0.2894, "lr": 4.5756835325845394e-05, "epoch": 5.387840670859539, "percentage": 26.94, "elapsed_time": "0:39:01", "remaining_time": "1:45:50", "throughput": 2865.82, "total_tokens": 6710240} {"current_steps": 10285, "total_steps": 38160, "loss": 0.4559, "lr": 4.575046018412995e-05, "epoch": 5.390461215932914, "percentage": 26.95, "elapsed_time": "0:39:02", "remaining_time": "1:45:48", "throughput": 2865.97, "total_tokens": 6713632} {"current_steps": 10290, "total_steps": 38160, "loss": 0.2871, "lr": 4.5744080701654955e-05, "epoch": 5.3930817610062896, "percentage": 26.97, "elapsed_time": "0:39:03", "remaining_time": "1:45:47", "throughput": 2865.63, "total_tokens": 6716032} {"current_steps": 10295, "total_steps": 38160, "loss": 0.2989, "lr": 4.573769687975495e-05, "epoch": 5.395702306079665, "percentage": 26.98, "elapsed_time": "0:39:04", "remaining_time": "1:45:46", "throughput": 2865.6, "total_tokens": 6719136} {"current_steps": 10300, "total_steps": 38160, "loss": 0.3077, "lr": 4.573130871976534e-05, "epoch": 5.39832285115304, "percentage": 26.99, "elapsed_time": "0:39:05", "remaining_time": "1:45:45", "throughput": 2865.41, "total_tokens": 6721824} {"current_steps": 10305, "total_steps": 38160, "loss": 0.2882, "lr": 4.572491622302247e-05, "epoch": 5.400943396226415, "percentage": 27.0, "elapsed_time": "0:39:06", "remaining_time": "1:45:43", "throughput": 2865.38, "total_tokens": 6724864} {"current_steps": 10310, "total_steps": 38160, "loss": 0.237, "lr": 4.571851939086356e-05, "epoch": 5.40356394129979, "percentage": 27.02, "elapsed_time": "0:39:07", "remaining_time": "1:45:42", "throughput": 2865.47, "total_tokens": 6728064} {"current_steps": 10315, "total_steps": 38160, "loss": 0.4129, "lr": 4.571211822462676e-05, "epoch": 5.406184486373165, "percentage": 27.03, "elapsed_time": "0:39:09", "remaining_time": "1:45:41", "throughput": 2865.32, "total_tokens": 6730784} {"current_steps": 10320, "total_steps": 38160, "loss": 0.383, "lr": 4.570571272565114e-05, "epoch": 5.408805031446541, "percentage": 27.04, "elapsed_time": "0:39:10", "remaining_time": "1:45:39", "throughput": 2865.15, "total_tokens": 6733408} {"current_steps": 10325, "total_steps": 38160, "loss": 0.329, "lr": 4.569930289527663e-05, "epoch": 5.411425576519916, "percentage": 27.06, "elapsed_time": "0:39:11", "remaining_time": "1:45:40", "throughput": 2865.33, "total_tokens": 6738912} {"current_steps": 10330, "total_steps": 38160, "loss": 0.342, "lr": 4.56928887348441e-05, "epoch": 5.414046121593292, "percentage": 27.07, "elapsed_time": "0:39:13", "remaining_time": "1:45:39", "throughput": 2865.51, "total_tokens": 6742784} {"current_steps": 10335, "total_steps": 38160, "loss": 0.2658, "lr": 4.568647024569533e-05, "epoch": 5.416666666666667, "percentage": 27.08, "elapsed_time": "0:39:14", "remaining_time": "1:45:38", "throughput": 2865.6, "total_tokens": 6746080} {"current_steps": 10340, "total_steps": 38160, "loss": 0.3821, "lr": 4.568004742917299e-05, "epoch": 5.419287211740042, "percentage": 27.1, "elapsed_time": "0:39:15", "remaining_time": "1:45:37", "throughput": 2866.01, "total_tokens": 6750368} {"current_steps": 10345, "total_steps": 38160, "loss": 0.3279, "lr": 4.567362028662065e-05, "epoch": 5.421907756813417, "percentage": 27.11, "elapsed_time": "0:39:16", "remaining_time": "1:45:35", "throughput": 2866.17, "total_tokens": 6753984} {"current_steps": 10350, "total_steps": 38160, "loss": 0.3987, "lr": 4.566718881938281e-05, "epoch": 5.4245283018867925, "percentage": 27.12, "elapsed_time": "0:39:17", "remaining_time": "1:45:34", "throughput": 2865.99, "total_tokens": 6756576} {"current_steps": 10355, "total_steps": 38160, "loss": 0.2989, "lr": 4.5660753028804846e-05, "epoch": 5.427148846960168, "percentage": 27.14, "elapsed_time": "0:39:18", "remaining_time": "1:45:33", "throughput": 2866.03, "total_tokens": 6759904} {"current_steps": 10360, "total_steps": 38160, "loss": 0.2891, "lr": 4.5654312916233066e-05, "epoch": 5.429769392033543, "percentage": 27.15, "elapsed_time": "0:39:19", "remaining_time": "1:45:32", "throughput": 2865.89, "total_tokens": 6762880} {"current_steps": 10365, "total_steps": 38160, "loss": 0.511, "lr": 4.564786848301466e-05, "epoch": 5.432389937106918, "percentage": 27.16, "elapsed_time": "0:39:20", "remaining_time": "1:45:30", "throughput": 2865.79, "total_tokens": 6765728} {"current_steps": 10370, "total_steps": 38160, "loss": 0.2766, "lr": 4.564141973049773e-05, "epoch": 5.435010482180293, "percentage": 27.18, "elapsed_time": "0:39:22", "remaining_time": "1:45:29", "throughput": 2865.61, "total_tokens": 6768704} {"current_steps": 10375, "total_steps": 38160, "loss": 0.2345, "lr": 4.563496666003128e-05, "epoch": 5.437631027253669, "percentage": 27.19, "elapsed_time": "0:39:23", "remaining_time": "1:45:28", "throughput": 2865.74, "total_tokens": 6772256} {"current_steps": 10380, "total_steps": 38160, "loss": 0.3491, "lr": 4.562850927296523e-05, "epoch": 5.440251572327044, "percentage": 27.2, "elapsed_time": "0:39:24", "remaining_time": "1:45:27", "throughput": 2865.81, "total_tokens": 6775552} {"current_steps": 10385, "total_steps": 38160, "loss": 0.2695, "lr": 4.5622047570650365e-05, "epoch": 5.4428721174004195, "percentage": 27.21, "elapsed_time": "0:39:25", "remaining_time": "1:45:26", "throughput": 2865.63, "total_tokens": 6778176} {"current_steps": 10390, "total_steps": 38160, "loss": 0.3208, "lr": 4.561558155443843e-05, "epoch": 5.445492662473795, "percentage": 27.23, "elapsed_time": "0:39:26", "remaining_time": "1:45:25", "throughput": 2865.81, "total_tokens": 6781888} {"current_steps": 10395, "total_steps": 38160, "loss": 0.3267, "lr": 4.560911122568202e-05, "epoch": 5.44811320754717, "percentage": 27.24, "elapsed_time": "0:39:27", "remaining_time": "1:45:23", "throughput": 2865.79, "total_tokens": 6785056} {"current_steps": 10400, "total_steps": 38160, "loss": 0.2994, "lr": 4.560263658573467e-05, "epoch": 5.450733752620545, "percentage": 27.25, "elapsed_time": "0:39:28", "remaining_time": "1:45:22", "throughput": 2866.05, "total_tokens": 6788832} {"current_steps": 10405, "total_steps": 38160, "loss": 0.3306, "lr": 4.559615763595079e-05, "epoch": 5.45335429769392, "percentage": 27.27, "elapsed_time": "0:39:29", "remaining_time": "1:45:21", "throughput": 2866.23, "total_tokens": 6792320} {"current_steps": 10410, "total_steps": 38160, "loss": 0.3829, "lr": 4.558967437768571e-05, "epoch": 5.455974842767295, "percentage": 27.28, "elapsed_time": "0:39:30", "remaining_time": "1:45:20", "throughput": 2866.41, "total_tokens": 6796000} {"current_steps": 10415, "total_steps": 38160, "loss": 0.2899, "lr": 4.558318681229565e-05, "epoch": 5.4585953878406706, "percentage": 27.29, "elapsed_time": "0:39:31", "remaining_time": "1:45:18", "throughput": 2866.14, "total_tokens": 6798400} {"current_steps": 10420, "total_steps": 38160, "loss": 0.3531, "lr": 4.557669494113773e-05, "epoch": 5.461215932914046, "percentage": 27.31, "elapsed_time": "0:39:33", "remaining_time": "1:45:17", "throughput": 2866.1, "total_tokens": 6801440} {"current_steps": 10425, "total_steps": 38160, "loss": 0.2964, "lr": 4.557019876556998e-05, "epoch": 5.463836477987422, "percentage": 27.32, "elapsed_time": "0:39:34", "remaining_time": "1:45:17", "throughput": 2866.66, "total_tokens": 6807072} {"current_steps": 10430, "total_steps": 38160, "loss": 0.3032, "lr": 4.556369828695133e-05, "epoch": 5.466457023060797, "percentage": 27.33, "elapsed_time": "0:39:35", "remaining_time": "1:45:16", "throughput": 2866.68, "total_tokens": 6810272} {"current_steps": 10435, "total_steps": 38160, "loss": 0.2909, "lr": 4.5557193506641596e-05, "epoch": 5.469077568134172, "percentage": 27.35, "elapsed_time": "0:39:36", "remaining_time": "1:45:14", "throughput": 2866.55, "total_tokens": 6813184} {"current_steps": 10440, "total_steps": 38160, "loss": 0.3324, "lr": 4.555068442600151e-05, "epoch": 5.471698113207547, "percentage": 27.36, "elapsed_time": "0:39:38", "remaining_time": "1:45:14", "throughput": 2866.88, "total_tokens": 6817824} {"current_steps": 10445, "total_steps": 38160, "loss": 0.2839, "lr": 4.5544171046392703e-05, "epoch": 5.4743186582809225, "percentage": 27.37, "elapsed_time": "0:39:39", "remaining_time": "1:45:13", "throughput": 2866.7, "total_tokens": 6820480} {"current_steps": 10450, "total_steps": 38160, "loss": 0.3665, "lr": 4.5537653369177685e-05, "epoch": 5.476939203354298, "percentage": 27.38, "elapsed_time": "0:39:40", "remaining_time": "1:45:11", "throughput": 2866.59, "total_tokens": 6823360} {"current_steps": 10455, "total_steps": 38160, "loss": 0.3656, "lr": 4.5531131395719895e-05, "epoch": 5.479559748427673, "percentage": 27.4, "elapsed_time": "0:39:41", "remaining_time": "1:45:10", "throughput": 2866.34, "total_tokens": 6825856} {"current_steps": 10460, "total_steps": 38160, "loss": 0.3488, "lr": 4.552460512738364e-05, "epoch": 5.482180293501048, "percentage": 27.41, "elapsed_time": "0:39:42", "remaining_time": "1:45:09", "throughput": 2866.3, "total_tokens": 6828896} {"current_steps": 10465, "total_steps": 38160, "loss": 0.3415, "lr": 4.551807456553416e-05, "epoch": 5.484800838574423, "percentage": 27.42, "elapsed_time": "0:39:43", "remaining_time": "1:45:07", "throughput": 2866.36, "total_tokens": 6832032} {"current_steps": 10470, "total_steps": 38160, "loss": 0.3436, "lr": 4.551153971153755e-05, "epoch": 5.487421383647799, "percentage": 27.44, "elapsed_time": "0:39:44", "remaining_time": "1:45:06", "throughput": 2866.21, "total_tokens": 6834624} {"current_steps": 10475, "total_steps": 38160, "loss": 0.422, "lr": 4.550500056676085e-05, "epoch": 5.490041928721174, "percentage": 27.45, "elapsed_time": "0:39:45", "remaining_time": "1:45:05", "throughput": 2866.11, "total_tokens": 6837504} {"current_steps": 10480, "total_steps": 38160, "loss": 0.3191, "lr": 4.5498457132571966e-05, "epoch": 5.4926624737945495, "percentage": 27.46, "elapsed_time": "0:39:46", "remaining_time": "1:45:03", "throughput": 2866.0, "total_tokens": 6840224} {"current_steps": 10485, "total_steps": 38160, "loss": 0.2182, "lr": 4.5491909410339706e-05, "epoch": 5.495283018867925, "percentage": 27.48, "elapsed_time": "0:39:47", "remaining_time": "1:45:02", "throughput": 2866.07, "total_tokens": 6843520} {"current_steps": 10490, "total_steps": 38160, "loss": 0.3206, "lr": 4.548535740143378e-05, "epoch": 5.4979035639413, "percentage": 27.49, "elapsed_time": "0:39:48", "remaining_time": "1:45:01", "throughput": 2866.03, "total_tokens": 6846464} {"current_steps": 10495, "total_steps": 38160, "loss": 0.3657, "lr": 4.54788011072248e-05, "epoch": 5.500524109014675, "percentage": 27.5, "elapsed_time": "0:39:49", "remaining_time": "1:44:59", "throughput": 2866.12, "total_tokens": 6849696} {"current_steps": 10500, "total_steps": 38160, "loss": 0.4195, "lr": 4.5472240529084254e-05, "epoch": 5.50314465408805, "percentage": 27.52, "elapsed_time": "0:39:50", "remaining_time": "1:44:58", "throughput": 2866.27, "total_tokens": 6853216} {"current_steps": 10505, "total_steps": 38160, "loss": 0.3271, "lr": 4.5465675668384557e-05, "epoch": 5.505765199161425, "percentage": 27.53, "elapsed_time": "0:39:52", "remaining_time": "1:44:57", "throughput": 2866.13, "total_tokens": 6855872} {"current_steps": 10510, "total_steps": 38160, "loss": 0.2631, "lr": 4.545910652649899e-05, "epoch": 5.5083857442348005, "percentage": 27.54, "elapsed_time": "0:39:53", "remaining_time": "1:44:55", "throughput": 2866.01, "total_tokens": 6858688} {"current_steps": 10515, "total_steps": 38160, "loss": 0.2985, "lr": 4.5452533104801756e-05, "epoch": 5.511006289308176, "percentage": 27.56, "elapsed_time": "0:39:54", "remaining_time": "1:44:54", "throughput": 2865.96, "total_tokens": 6861632} {"current_steps": 10520, "total_steps": 38160, "loss": 0.453, "lr": 4.544595540466792e-05, "epoch": 5.513626834381551, "percentage": 27.57, "elapsed_time": "0:39:55", "remaining_time": "1:44:53", "throughput": 2866.17, "total_tokens": 6865696} {"current_steps": 10525, "total_steps": 38160, "loss": 0.3037, "lr": 4.5439373427473476e-05, "epoch": 5.516247379454927, "percentage": 27.58, "elapsed_time": "0:39:56", "remaining_time": "1:44:52", "throughput": 2866.31, "total_tokens": 6869056} {"current_steps": 10530, "total_steps": 38160, "loss": 0.3027, "lr": 4.54327871745953e-05, "epoch": 5.518867924528302, "percentage": 27.59, "elapsed_time": "0:39:57", "remaining_time": "1:44:51", "throughput": 2866.0, "total_tokens": 6871488} {"current_steps": 10535, "total_steps": 38160, "loss": 0.3541, "lr": 4.542619664741116e-05, "epoch": 5.521488469601677, "percentage": 27.61, "elapsed_time": "0:39:58", "remaining_time": "1:44:50", "throughput": 2866.07, "total_tokens": 6875008} {"current_steps": 10540, "total_steps": 38160, "loss": 0.4527, "lr": 4.5419601847299706e-05, "epoch": 5.524109014675052, "percentage": 27.62, "elapsed_time": "0:39:59", "remaining_time": "1:44:49", "throughput": 2866.04, "total_tokens": 6878336} {"current_steps": 10545, "total_steps": 38160, "loss": 0.306, "lr": 4.5413002775640503e-05, "epoch": 5.526729559748428, "percentage": 27.63, "elapsed_time": "0:40:01", "remaining_time": "1:44:47", "throughput": 2866.25, "total_tokens": 6882080} {"current_steps": 10550, "total_steps": 38160, "loss": 0.2589, "lr": 4.540639943381401e-05, "epoch": 5.529350104821803, "percentage": 27.65, "elapsed_time": "0:40:02", "remaining_time": "1:44:46", "throughput": 2866.42, "total_tokens": 6885504} {"current_steps": 10555, "total_steps": 38160, "loss": 0.3609, "lr": 4.539979182320157e-05, "epoch": 5.531970649895178, "percentage": 27.66, "elapsed_time": "0:40:03", "remaining_time": "1:44:45", "throughput": 2866.5, "total_tokens": 6888704} {"current_steps": 10560, "total_steps": 38160, "loss": 0.3703, "lr": 4.5393179945185404e-05, "epoch": 5.534591194968553, "percentage": 27.67, "elapsed_time": "0:40:04", "remaining_time": "1:44:43", "throughput": 2866.61, "total_tokens": 6891936} {"current_steps": 10565, "total_steps": 38160, "loss": 0.3742, "lr": 4.538656380114865e-05, "epoch": 5.537211740041929, "percentage": 27.69, "elapsed_time": "0:40:05", "remaining_time": "1:44:42", "throughput": 2866.58, "total_tokens": 6894848} {"current_steps": 10570, "total_steps": 38160, "loss": 0.3052, "lr": 4.537994339247533e-05, "epoch": 5.539832285115304, "percentage": 27.7, "elapsed_time": "0:40:06", "remaining_time": "1:44:41", "throughput": 2866.38, "total_tokens": 6897728} {"current_steps": 10575, "total_steps": 38160, "loss": 0.2512, "lr": 4.5373318720550366e-05, "epoch": 5.5424528301886795, "percentage": 27.71, "elapsed_time": "0:40:07", "remaining_time": "1:44:40", "throughput": 2866.31, "total_tokens": 6900672} {"current_steps": 10580, "total_steps": 38160, "loss": 0.2936, "lr": 4.536668978675956e-05, "epoch": 5.545073375262055, "percentage": 27.73, "elapsed_time": "0:40:08", "remaining_time": "1:44:39", "throughput": 2866.72, "total_tokens": 6905920} {"current_steps": 10585, "total_steps": 38160, "loss": 0.329, "lr": 4.53600565924896e-05, "epoch": 5.54769392033543, "percentage": 27.74, "elapsed_time": "0:40:10", "remaining_time": "1:44:38", "throughput": 2866.93, "total_tokens": 6909408} {"current_steps": 10590, "total_steps": 38160, "loss": 0.2839, "lr": 4.535341913912808e-05, "epoch": 5.550314465408805, "percentage": 27.75, "elapsed_time": "0:40:11", "remaining_time": "1:44:36", "throughput": 2866.83, "total_tokens": 6912128} {"current_steps": 10595, "total_steps": 38160, "loss": 0.3664, "lr": 4.534677742806348e-05, "epoch": 5.55293501048218, "percentage": 27.76, "elapsed_time": "0:40:12", "remaining_time": "1:44:35", "throughput": 2866.86, "total_tokens": 6915136} {"current_steps": 10600, "total_steps": 38160, "loss": 0.3314, "lr": 4.5340131460685175e-05, "epoch": 5.555555555555555, "percentage": 27.78, "elapsed_time": "0:40:13", "remaining_time": "1:44:34", "throughput": 2866.74, "total_tokens": 6917856} {"current_steps": 10605, "total_steps": 38160, "loss": 0.3054, "lr": 4.533348123838341e-05, "epoch": 5.5581761006289305, "percentage": 27.79, "elapsed_time": "0:40:14", "remaining_time": "1:44:32", "throughput": 2866.75, "total_tokens": 6920864} {"current_steps": 10610, "total_steps": 38160, "loss": 0.4662, "lr": 4.532682676254936e-05, "epoch": 5.560796645702306, "percentage": 27.8, "elapsed_time": "0:40:15", "remaining_time": "1:44:31", "throughput": 2866.91, "total_tokens": 6924384} {"current_steps": 10615, "total_steps": 38160, "loss": 0.3365, "lr": 4.5320168034575044e-05, "epoch": 5.563417190775681, "percentage": 27.82, "elapsed_time": "0:40:16", "remaining_time": "1:44:30", "throughput": 2866.66, "total_tokens": 6926848} {"current_steps": 10620, "total_steps": 38160, "loss": 0.2447, "lr": 4.53135050558534e-05, "epoch": 5.566037735849057, "percentage": 27.83, "elapsed_time": "0:40:17", "remaining_time": "1:44:28", "throughput": 2866.5, "total_tokens": 6929536} {"current_steps": 10625, "total_steps": 38160, "loss": 0.3797, "lr": 4.530683782777825e-05, "epoch": 5.568658280922432, "percentage": 27.84, "elapsed_time": "0:40:18", "remaining_time": "1:44:27", "throughput": 2866.24, "total_tokens": 6932064} {"current_steps": 10630, "total_steps": 38160, "loss": 0.3196, "lr": 4.53001663517443e-05, "epoch": 5.571278825995807, "percentage": 27.86, "elapsed_time": "0:40:19", "remaining_time": "1:44:26", "throughput": 2866.26, "total_tokens": 6935296} {"current_steps": 10635, "total_steps": 38160, "loss": 0.2733, "lr": 4.529349062914714e-05, "epoch": 5.573899371069182, "percentage": 27.87, "elapsed_time": "0:40:20", "remaining_time": "1:44:25", "throughput": 2866.09, "total_tokens": 6937824} {"current_steps": 10640, "total_steps": 38160, "loss": 0.3403, "lr": 4.528681066138326e-05, "epoch": 5.576519916142558, "percentage": 27.88, "elapsed_time": "0:40:21", "remaining_time": "1:44:23", "throughput": 2866.32, "total_tokens": 6941600} {"current_steps": 10645, "total_steps": 38160, "loss": 0.3273, "lr": 4.528012644985005e-05, "epoch": 5.579140461215933, "percentage": 27.9, "elapsed_time": "0:40:22", "remaining_time": "1:44:22", "throughput": 2866.31, "total_tokens": 6944608} {"current_steps": 10650, "total_steps": 38160, "loss": 0.3793, "lr": 4.527343799594574e-05, "epoch": 5.581761006289308, "percentage": 27.91, "elapsed_time": "0:40:23", "remaining_time": "1:44:21", "throughput": 2866.48, "total_tokens": 6948000} {"current_steps": 10655, "total_steps": 38160, "loss": 0.248, "lr": 4.5266745301069494e-05, "epoch": 5.584381551362683, "percentage": 27.92, "elapsed_time": "0:40:24", "remaining_time": "1:44:19", "throughput": 2866.65, "total_tokens": 6951424} {"current_steps": 10660, "total_steps": 38160, "loss": 0.2945, "lr": 4.526004836662135e-05, "epoch": 5.587002096436059, "percentage": 27.94, "elapsed_time": "0:40:26", "remaining_time": "1:44:18", "throughput": 2867.08, "total_tokens": 6956000} {"current_steps": 10665, "total_steps": 38160, "loss": 0.3296, "lr": 4.525334719400223e-05, "epoch": 5.589622641509434, "percentage": 27.95, "elapsed_time": "0:40:27", "remaining_time": "1:44:17", "throughput": 2867.08, "total_tokens": 6958944} {"current_steps": 10670, "total_steps": 38160, "loss": 0.2856, "lr": 4.524664178461393e-05, "epoch": 5.5922431865828095, "percentage": 27.96, "elapsed_time": "0:40:28", "remaining_time": "1:44:16", "throughput": 2867.18, "total_tokens": 6962304} {"current_steps": 10675, "total_steps": 38160, "loss": 0.3645, "lr": 4.5239932139859154e-05, "epoch": 5.594863731656185, "percentage": 27.97, "elapsed_time": "0:40:29", "remaining_time": "1:44:14", "throughput": 2867.31, "total_tokens": 6965632} {"current_steps": 10680, "total_steps": 38160, "loss": 0.3735, "lr": 4.523321826114149e-05, "epoch": 5.59748427672956, "percentage": 27.99, "elapsed_time": "0:40:30", "remaining_time": "1:44:13", "throughput": 2867.52, "total_tokens": 6969312} {"current_steps": 10685, "total_steps": 38160, "loss": 0.2484, "lr": 4.5226500149865395e-05, "epoch": 5.600104821802935, "percentage": 28.0, "elapsed_time": "0:40:31", "remaining_time": "1:44:12", "throughput": 2867.61, "total_tokens": 6972576} {"current_steps": 10690, "total_steps": 38160, "loss": 0.2227, "lr": 4.5219777807436224e-05, "epoch": 5.60272536687631, "percentage": 28.01, "elapsed_time": "0:40:32", "remaining_time": "1:44:10", "throughput": 2867.7, "total_tokens": 6975872} {"current_steps": 10695, "total_steps": 38160, "loss": 0.2777, "lr": 4.5213051235260225e-05, "epoch": 5.605345911949685, "percentage": 28.03, "elapsed_time": "0:40:33", "remaining_time": "1:44:09", "throughput": 2867.69, "total_tokens": 6978784} {"current_steps": 10700, "total_steps": 38160, "loss": 0.467, "lr": 4.52063204347445e-05, "epoch": 5.6079664570230605, "percentage": 28.04, "elapsed_time": "0:40:34", "remaining_time": "1:44:08", "throughput": 2867.52, "total_tokens": 6981408} {"current_steps": 10705, "total_steps": 38160, "loss": 0.3016, "lr": 4.519958540729707e-05, "epoch": 5.610587002096436, "percentage": 28.05, "elapsed_time": "0:40:35", "remaining_time": "1:44:06", "throughput": 2867.65, "total_tokens": 6984800} {"current_steps": 10710, "total_steps": 38160, "loss": 0.3303, "lr": 4.519284615432682e-05, "epoch": 5.613207547169811, "percentage": 28.07, "elapsed_time": "0:40:36", "remaining_time": "1:44:05", "throughput": 2867.77, "total_tokens": 6988192} {"current_steps": 10715, "total_steps": 38160, "loss": 0.246, "lr": 4.518610267724352e-05, "epoch": 5.615828092243187, "percentage": 28.08, "elapsed_time": "0:40:37", "remaining_time": "1:44:04", "throughput": 2868.11, "total_tokens": 6992416} {"current_steps": 10720, "total_steps": 38160, "loss": 0.2863, "lr": 4.517935497745786e-05, "epoch": 5.618448637316562, "percentage": 28.09, "elapsed_time": "0:40:39", "remaining_time": "1:44:03", "throughput": 2868.12, "total_tokens": 6995520} {"current_steps": 10725, "total_steps": 38160, "loss": 0.2472, "lr": 4.517260305638133e-05, "epoch": 5.621069182389937, "percentage": 28.11, "elapsed_time": "0:40:40", "remaining_time": "1:44:01", "throughput": 2868.05, "total_tokens": 6998464} {"current_steps": 10730, "total_steps": 38160, "loss": 0.3122, "lr": 4.516584691542639e-05, "epoch": 5.623689727463312, "percentage": 28.12, "elapsed_time": "0:40:41", "remaining_time": "1:44:00", "throughput": 2868.01, "total_tokens": 7001600} {"current_steps": 10735, "total_steps": 38160, "loss": 0.3108, "lr": 4.515908655600634e-05, "epoch": 5.626310272536688, "percentage": 28.13, "elapsed_time": "0:40:42", "remaining_time": "1:43:59", "throughput": 2867.98, "total_tokens": 7004704} {"current_steps": 10740, "total_steps": 38160, "loss": 0.4083, "lr": 4.515232197953537e-05, "epoch": 5.628930817610063, "percentage": 28.14, "elapsed_time": "0:40:43", "remaining_time": "1:43:58", "throughput": 2867.88, "total_tokens": 7007424} {"current_steps": 10745, "total_steps": 38160, "loss": 0.2514, "lr": 4.514555318742856e-05, "epoch": 5.631551362683438, "percentage": 28.16, "elapsed_time": "0:40:44", "remaining_time": "1:43:56", "throughput": 2868.01, "total_tokens": 7010688} {"current_steps": 10750, "total_steps": 38160, "loss": 0.229, "lr": 4.513878018110184e-05, "epoch": 5.634171907756813, "percentage": 28.17, "elapsed_time": "0:40:45", "remaining_time": "1:43:55", "throughput": 2868.11, "total_tokens": 7014048} {"current_steps": 10755, "total_steps": 38160, "loss": 0.2816, "lr": 4.513200296197207e-05, "epoch": 5.636792452830189, "percentage": 28.18, "elapsed_time": "0:40:46", "remaining_time": "1:43:54", "throughput": 2868.22, "total_tokens": 7017856} {"current_steps": 10760, "total_steps": 38160, "loss": 0.2412, "lr": 4.512522153145696e-05, "epoch": 5.639412997903564, "percentage": 28.2, "elapsed_time": "0:40:47", "remaining_time": "1:43:53", "throughput": 2868.21, "total_tokens": 7021248} {"current_steps": 10765, "total_steps": 38160, "loss": 0.3291, "lr": 4.5118435890975106e-05, "epoch": 5.6420335429769395, "percentage": 28.21, "elapsed_time": "0:40:49", "remaining_time": "1:43:52", "throughput": 2868.23, "total_tokens": 7024320} {"current_steps": 10770, "total_steps": 38160, "loss": 0.3411, "lr": 4.511164604194598e-05, "epoch": 5.644654088050315, "percentage": 28.22, "elapsed_time": "0:40:50", "remaining_time": "1:43:50", "throughput": 2868.23, "total_tokens": 7027296} {"current_steps": 10775, "total_steps": 38160, "loss": 0.3025, "lr": 4.5104851985789956e-05, "epoch": 5.64727463312369, "percentage": 28.24, "elapsed_time": "0:40:51", "remaining_time": "1:43:49", "throughput": 2868.43, "total_tokens": 7030784} {"current_steps": 10780, "total_steps": 38160, "loss": 0.5014, "lr": 4.5098053723928254e-05, "epoch": 5.649895178197065, "percentage": 28.25, "elapsed_time": "0:40:52", "remaining_time": "1:43:48", "throughput": 2868.54, "total_tokens": 7034112} {"current_steps": 10785, "total_steps": 38160, "loss": 0.2582, "lr": 4.509125125778302e-05, "epoch": 5.65251572327044, "percentage": 28.26, "elapsed_time": "0:40:53", "remaining_time": "1:43:47", "throughput": 2869.0, "total_tokens": 7039072} {"current_steps": 10790, "total_steps": 38160, "loss": 0.2979, "lr": 4.508444458877722e-05, "epoch": 5.655136268343815, "percentage": 28.28, "elapsed_time": "0:40:54", "remaining_time": "1:43:46", "throughput": 2869.09, "total_tokens": 7042304} {"current_steps": 10795, "total_steps": 38160, "loss": 0.3736, "lr": 4.5077633718334755e-05, "epoch": 5.6577568134171905, "percentage": 28.29, "elapsed_time": "0:40:55", "remaining_time": "1:43:45", "throughput": 2869.38, "total_tokens": 7046400} {"current_steps": 10800, "total_steps": 38160, "loss": 0.3113, "lr": 4.5070818647880375e-05, "epoch": 5.660377358490566, "percentage": 28.3, "elapsed_time": "0:40:56", "remaining_time": "1:43:44", "throughput": 2869.67, "total_tokens": 7050656} {"current_steps": 10805, "total_steps": 38160, "loss": 0.3019, "lr": 4.506399937883972e-05, "epoch": 5.662997903563941, "percentage": 28.31, "elapsed_time": "0:40:58", "remaining_time": "1:43:43", "throughput": 2869.69, "total_tokens": 7053824} {"current_steps": 10810, "total_steps": 38160, "loss": 0.3289, "lr": 4.5057175912639286e-05, "epoch": 5.665618448637317, "percentage": 28.33, "elapsed_time": "0:40:59", "remaining_time": "1:43:41", "throughput": 2870.01, "total_tokens": 7057760} {"current_steps": 10815, "total_steps": 38160, "loss": 0.2798, "lr": 4.5050348250706475e-05, "epoch": 5.668238993710692, "percentage": 28.34, "elapsed_time": "0:41:00", "remaining_time": "1:43:40", "throughput": 2870.36, "total_tokens": 7061888} {"current_steps": 10820, "total_steps": 38160, "loss": 0.2484, "lr": 4.5043516394469566e-05, "epoch": 5.670859538784067, "percentage": 28.35, "elapsed_time": "0:41:01", "remaining_time": "1:43:39", "throughput": 2870.33, "total_tokens": 7064960} {"current_steps": 10825, "total_steps": 38160, "loss": 0.2948, "lr": 4.503668034535768e-05, "epoch": 5.673480083857442, "percentage": 28.37, "elapsed_time": "0:41:02", "remaining_time": "1:43:38", "throughput": 2870.29, "total_tokens": 7067968} {"current_steps": 10830, "total_steps": 38160, "loss": 0.3577, "lr": 4.5029840104800876e-05, "epoch": 5.676100628930818, "percentage": 28.38, "elapsed_time": "0:41:03", "remaining_time": "1:43:36", "throughput": 2870.43, "total_tokens": 7071424} {"current_steps": 10835, "total_steps": 38160, "loss": 0.3678, "lr": 4.5022995674230025e-05, "epoch": 5.678721174004193, "percentage": 28.39, "elapsed_time": "0:41:04", "remaining_time": "1:43:35", "throughput": 2870.52, "total_tokens": 7074656} {"current_steps": 10840, "total_steps": 38160, "loss": 0.3533, "lr": 4.5016147055076914e-05, "epoch": 5.681341719077568, "percentage": 28.41, "elapsed_time": "0:41:05", "remaining_time": "1:43:34", "throughput": 2870.64, "total_tokens": 7077952} {"current_steps": 10845, "total_steps": 38160, "loss": 0.2403, "lr": 4.500929424877419e-05, "epoch": 5.683962264150943, "percentage": 28.42, "elapsed_time": "0:41:06", "remaining_time": "1:43:32", "throughput": 2870.38, "total_tokens": 7080512} {"current_steps": 10850, "total_steps": 38160, "loss": 0.309, "lr": 4.5002437256755394e-05, "epoch": 5.686582809224319, "percentage": 28.43, "elapsed_time": "0:41:07", "remaining_time": "1:43:31", "throughput": 2870.44, "total_tokens": 7083904} {"current_steps": 10855, "total_steps": 38160, "loss": 0.2994, "lr": 4.4995576080454924e-05, "epoch": 5.689203354297694, "percentage": 28.45, "elapsed_time": "0:41:09", "remaining_time": "1:43:30", "throughput": 2870.04, "total_tokens": 7086144} {"current_steps": 10860, "total_steps": 38160, "loss": 0.3283, "lr": 4.4988710721308056e-05, "epoch": 5.6918238993710695, "percentage": 28.46, "elapsed_time": "0:41:10", "remaining_time": "1:43:29", "throughput": 2869.72, "total_tokens": 7088608} {"current_steps": 10865, "total_steps": 38160, "loss": 0.2564, "lr": 4.498184118075095e-05, "epoch": 5.694444444444445, "percentage": 28.47, "elapsed_time": "0:41:11", "remaining_time": "1:43:28", "throughput": 2869.6, "total_tokens": 7091296} {"current_steps": 10870, "total_steps": 38160, "loss": 0.2748, "lr": 4.497496746022063e-05, "epoch": 5.69706498951782, "percentage": 28.49, "elapsed_time": "0:41:12", "remaining_time": "1:43:26", "throughput": 2869.81, "total_tokens": 7095008} {"current_steps": 10875, "total_steps": 38160, "loss": 0.3163, "lr": 4.4968089561155015e-05, "epoch": 5.699685534591195, "percentage": 28.5, "elapsed_time": "0:41:13", "remaining_time": "1:43:25", "throughput": 2869.74, "total_tokens": 7098016} {"current_steps": 10880, "total_steps": 38160, "loss": 0.2523, "lr": 4.496120748499286e-05, "epoch": 5.70230607966457, "percentage": 28.51, "elapsed_time": "0:41:14", "remaining_time": "1:43:24", "throughput": 2869.73, "total_tokens": 7101056} {"current_steps": 10885, "total_steps": 38160, "loss": 0.2434, "lr": 4.4954321233173833e-05, "epoch": 5.704926624737945, "percentage": 28.52, "elapsed_time": "0:41:15", "remaining_time": "1:43:23", "throughput": 2869.49, "total_tokens": 7103488} {"current_steps": 10890, "total_steps": 38160, "loss": 0.274, "lr": 4.494743080713846e-05, "epoch": 5.7075471698113205, "percentage": 28.54, "elapsed_time": "0:41:16", "remaining_time": "1:43:21", "throughput": 2869.62, "total_tokens": 7107072} {"current_steps": 10895, "total_steps": 38160, "loss": 0.3316, "lr": 4.494053620832812e-05, "epoch": 5.710167714884696, "percentage": 28.55, "elapsed_time": "0:41:17", "remaining_time": "1:43:20", "throughput": 2869.72, "total_tokens": 7110336} {"current_steps": 10900, "total_steps": 38160, "loss": 0.3698, "lr": 4.493363743818511e-05, "epoch": 5.712788259958071, "percentage": 28.56, "elapsed_time": "0:41:18", "remaining_time": "1:43:19", "throughput": 2869.98, "total_tokens": 7114240} {"current_steps": 10905, "total_steps": 38160, "loss": 0.3589, "lr": 4.492673449815257e-05, "epoch": 5.715408805031447, "percentage": 28.58, "elapsed_time": "0:41:20", "remaining_time": "1:43:20", "throughput": 2870.5, "total_tokens": 7121216} {"current_steps": 10910, "total_steps": 38160, "loss": 0.2935, "lr": 4.4919827389674496e-05, "epoch": 5.718029350104822, "percentage": 28.59, "elapsed_time": "0:41:21", "remaining_time": "1:43:19", "throughput": 2870.66, "total_tokens": 7124800} {"current_steps": 10915, "total_steps": 38160, "loss": 0.394, "lr": 4.491291611419579e-05, "epoch": 5.720649895178197, "percentage": 28.6, "elapsed_time": "0:41:23", "remaining_time": "1:43:18", "throughput": 2870.72, "total_tokens": 7128224} {"current_steps": 10920, "total_steps": 38160, "loss": 0.2532, "lr": 4.4906000673162216e-05, "epoch": 5.723270440251572, "percentage": 28.62, "elapsed_time": "0:41:24", "remaining_time": "1:43:16", "throughput": 2870.68, "total_tokens": 7131456} {"current_steps": 10925, "total_steps": 38160, "loss": 0.3263, "lr": 4.48990810680204e-05, "epoch": 5.725890985324948, "percentage": 28.63, "elapsed_time": "0:41:25", "remaining_time": "1:43:15", "throughput": 2870.88, "total_tokens": 7134944} {"current_steps": 10930, "total_steps": 38160, "loss": 0.4392, "lr": 4.4892157300217844e-05, "epoch": 5.728511530398323, "percentage": 28.64, "elapsed_time": "0:41:26", "remaining_time": "1:43:14", "throughput": 2871.19, "total_tokens": 7139200} {"current_steps": 10935, "total_steps": 38160, "loss": 0.2547, "lr": 4.488522937120293e-05, "epoch": 5.731132075471698, "percentage": 28.66, "elapsed_time": "0:41:27", "remaining_time": "1:43:13", "throughput": 2871.05, "total_tokens": 7141792} {"current_steps": 10940, "total_steps": 38160, "loss": 0.2893, "lr": 4.4878297282424886e-05, "epoch": 5.733752620545073, "percentage": 28.67, "elapsed_time": "0:41:28", "remaining_time": "1:43:11", "throughput": 2871.24, "total_tokens": 7145152} {"current_steps": 10945, "total_steps": 38160, "loss": 0.4461, "lr": 4.4871361035333836e-05, "epoch": 5.736373165618449, "percentage": 28.68, "elapsed_time": "0:41:29", "remaining_time": "1:43:10", "throughput": 2871.28, "total_tokens": 7148192} {"current_steps": 10950, "total_steps": 38160, "loss": 0.2745, "lr": 4.486442063138076e-05, "epoch": 5.738993710691824, "percentage": 28.69, "elapsed_time": "0:41:30", "remaining_time": "1:43:08", "throughput": 2871.39, "total_tokens": 7151520} {"current_steps": 10955, "total_steps": 38160, "loss": 0.2743, "lr": 4.4857476072017516e-05, "epoch": 5.7416142557651995, "percentage": 28.71, "elapsed_time": "0:41:31", "remaining_time": "1:43:07", "throughput": 2871.36, "total_tokens": 7154496} {"current_steps": 10960, "total_steps": 38160, "loss": 0.3487, "lr": 4.485052735869682e-05, "epoch": 5.744234800838575, "percentage": 28.72, "elapsed_time": "0:41:32", "remaining_time": "1:43:06", "throughput": 2871.44, "total_tokens": 7157600} {"current_steps": 10965, "total_steps": 38160, "loss": 0.3314, "lr": 4.484357449287228e-05, "epoch": 5.74685534591195, "percentage": 28.73, "elapsed_time": "0:41:33", "remaining_time": "1:43:04", "throughput": 2871.33, "total_tokens": 7160224} {"current_steps": 10970, "total_steps": 38160, "loss": 0.241, "lr": 4.483661747599833e-05, "epoch": 5.749475890985325, "percentage": 28.75, "elapsed_time": "0:41:34", "remaining_time": "1:43:03", "throughput": 2871.16, "total_tokens": 7162720} {"current_steps": 10975, "total_steps": 38160, "loss": 0.4171, "lr": 4.482965630953031e-05, "epoch": 5.7520964360587, "percentage": 28.76, "elapsed_time": "0:41:35", "remaining_time": "1:43:01", "throughput": 2871.38, "total_tokens": 7166240} {"current_steps": 10980, "total_steps": 38160, "loss": 0.3717, "lr": 4.4822690994924425e-05, "epoch": 5.754716981132075, "percentage": 28.77, "elapsed_time": "0:41:37", "remaining_time": "1:43:02", "throughput": 2871.91, "total_tokens": 7172480} {"current_steps": 10985, "total_steps": 38160, "loss": 0.3721, "lr": 4.481572153363773e-05, "epoch": 5.7573375262054505, "percentage": 28.79, "elapsed_time": "0:41:38", "remaining_time": "1:43:01", "throughput": 2872.19, "total_tokens": 7176416} {"current_steps": 10990, "total_steps": 38160, "loss": 0.4179, "lr": 4.480874792712817e-05, "epoch": 5.759958071278826, "percentage": 28.8, "elapsed_time": "0:41:39", "remaining_time": "1:42:59", "throughput": 2872.63, "total_tokens": 7180832} {"current_steps": 10995, "total_steps": 38160, "loss": 0.3294, "lr": 4.480177017685452e-05, "epoch": 5.762578616352201, "percentage": 28.81, "elapsed_time": "0:41:40", "remaining_time": "1:42:58", "throughput": 2872.79, "total_tokens": 7184416} {"current_steps": 11000, "total_steps": 38160, "loss": 0.2885, "lr": 4.479478828427647e-05, "epoch": 5.765199161425577, "percentage": 28.83, "elapsed_time": "0:41:41", "remaining_time": "1:42:57", "throughput": 2872.5, "total_tokens": 7186816} {"current_steps": 11005, "total_steps": 38160, "loss": 0.4037, "lr": 4.478780225085454e-05, "epoch": 5.767819706498952, "percentage": 28.84, "elapsed_time": "0:41:42", "remaining_time": "1:42:56", "throughput": 2872.51, "total_tokens": 7189824} {"current_steps": 11010, "total_steps": 38160, "loss": 0.3819, "lr": 4.4780812078050125e-05, "epoch": 5.770440251572327, "percentage": 28.85, "elapsed_time": "0:41:44", "remaining_time": "1:42:54", "throughput": 2872.37, "total_tokens": 7192640} {"current_steps": 11015, "total_steps": 38160, "loss": 0.3513, "lr": 4.47738177673255e-05, "epoch": 5.773060796645702, "percentage": 28.87, "elapsed_time": "0:41:45", "remaining_time": "1:42:53", "throughput": 2872.17, "total_tokens": 7195328} {"current_steps": 11020, "total_steps": 38160, "loss": 0.4853, "lr": 4.4766819320143785e-05, "epoch": 5.7756813417190775, "percentage": 28.88, "elapsed_time": "0:41:46", "remaining_time": "1:42:52", "throughput": 2872.22, "total_tokens": 7198464} {"current_steps": 11025, "total_steps": 38160, "loss": 0.286, "lr": 4.475981673796899e-05, "epoch": 5.778301886792453, "percentage": 28.89, "elapsed_time": "0:41:47", "remaining_time": "1:42:51", "throughput": 2872.36, "total_tokens": 7202080} {"current_steps": 11030, "total_steps": 38160, "loss": 0.321, "lr": 4.475281002226596e-05, "epoch": 5.780922431865828, "percentage": 28.9, "elapsed_time": "0:41:48", "remaining_time": "1:42:49", "throughput": 2872.3, "total_tokens": 7204832} {"current_steps": 11035, "total_steps": 38160, "loss": 0.2806, "lr": 4.4745799174500414e-05, "epoch": 5.783542976939203, "percentage": 28.92, "elapsed_time": "0:41:49", "remaining_time": "1:42:48", "throughput": 2872.45, "total_tokens": 7208128} {"current_steps": 11040, "total_steps": 38160, "loss": 0.2864, "lr": 4.473878419613896e-05, "epoch": 5.786163522012579, "percentage": 28.93, "elapsed_time": "0:41:50", "remaining_time": "1:42:46", "throughput": 2872.5, "total_tokens": 7211232} {"current_steps": 11045, "total_steps": 38160, "loss": 0.292, "lr": 4.473176508864905e-05, "epoch": 5.788784067085954, "percentage": 28.94, "elapsed_time": "0:41:51", "remaining_time": "1:42:45", "throughput": 2872.69, "total_tokens": 7214720} {"current_steps": 11050, "total_steps": 38160, "loss": 0.3966, "lr": 4.4724741853498995e-05, "epoch": 5.7914046121593294, "percentage": 28.96, "elapsed_time": "0:41:52", "remaining_time": "1:42:44", "throughput": 2873.06, "total_tokens": 7219200} {"current_steps": 11055, "total_steps": 38160, "loss": 0.318, "lr": 4.471771449215797e-05, "epoch": 5.794025157232705, "percentage": 28.97, "elapsed_time": "0:41:53", "remaining_time": "1:42:43", "throughput": 2873.47, "total_tokens": 7223808} {"current_steps": 11060, "total_steps": 38160, "loss": 0.3468, "lr": 4.471068300609603e-05, "epoch": 5.79664570230608, "percentage": 28.98, "elapsed_time": "0:41:55", "remaining_time": "1:42:42", "throughput": 2873.53, "total_tokens": 7227264} {"current_steps": 11065, "total_steps": 38160, "loss": 0.3682, "lr": 4.4703647396784065e-05, "epoch": 5.799266247379455, "percentage": 29.0, "elapsed_time": "0:41:56", "remaining_time": "1:42:42", "throughput": 2873.78, "total_tokens": 7232672} {"current_steps": 11070, "total_steps": 38160, "loss": 0.284, "lr": 4.469660766569387e-05, "epoch": 5.80188679245283, "percentage": 29.01, "elapsed_time": "0:41:57", "remaining_time": "1:42:41", "throughput": 2873.69, "total_tokens": 7235584} {"current_steps": 11075, "total_steps": 38160, "loss": 0.3608, "lr": 4.4689563814298057e-05, "epoch": 5.804507337526205, "percentage": 29.02, "elapsed_time": "0:41:58", "remaining_time": "1:42:40", "throughput": 2873.7, "total_tokens": 7238592} {"current_steps": 11080, "total_steps": 38160, "loss": 0.3333, "lr": 4.468251584407012e-05, "epoch": 5.8071278825995805, "percentage": 29.04, "elapsed_time": "0:41:59", "remaining_time": "1:42:38", "throughput": 2873.81, "total_tokens": 7241952} {"current_steps": 11085, "total_steps": 38160, "loss": 0.3138, "lr": 4.467546375648443e-05, "epoch": 5.809748427672956, "percentage": 29.05, "elapsed_time": "0:42:01", "remaining_time": "1:42:37", "throughput": 2873.77, "total_tokens": 7245056} {"current_steps": 11090, "total_steps": 38160, "loss": 0.3458, "lr": 4.4668407553016176e-05, "epoch": 5.812368972746331, "percentage": 29.06, "elapsed_time": "0:42:02", "remaining_time": "1:42:36", "throughput": 2873.97, "total_tokens": 7248896} {"current_steps": 11095, "total_steps": 38160, "loss": 0.4015, "lr": 4.466134723514146e-05, "epoch": 5.814989517819707, "percentage": 29.07, "elapsed_time": "0:42:03", "remaining_time": "1:42:35", "throughput": 2873.86, "total_tokens": 7251680} {"current_steps": 11100, "total_steps": 38160, "loss": 0.3965, "lr": 4.465428280433721e-05, "epoch": 5.817610062893082, "percentage": 29.09, "elapsed_time": "0:42:04", "remaining_time": "1:42:34", "throughput": 2873.74, "total_tokens": 7254432} {"current_steps": 11105, "total_steps": 38160, "loss": 0.3124, "lr": 4.464721426208123e-05, "epoch": 5.820230607966457, "percentage": 29.1, "elapsed_time": "0:42:05", "remaining_time": "1:42:32", "throughput": 2873.66, "total_tokens": 7257280} {"current_steps": 11110, "total_steps": 38160, "loss": 0.2752, "lr": 4.464014160985217e-05, "epoch": 5.822851153039832, "percentage": 29.11, "elapsed_time": "0:42:06", "remaining_time": "1:42:31", "throughput": 2873.46, "total_tokens": 7259840} {"current_steps": 11115, "total_steps": 38160, "loss": 0.3036, "lr": 4.463306484912955e-05, "epoch": 5.8254716981132075, "percentage": 29.13, "elapsed_time": "0:42:07", "remaining_time": "1:42:30", "throughput": 2873.36, "total_tokens": 7262624} {"current_steps": 11120, "total_steps": 38160, "loss": 0.3028, "lr": 4.462598398139375e-05, "epoch": 5.828092243186583, "percentage": 29.14, "elapsed_time": "0:42:08", "remaining_time": "1:42:28", "throughput": 2873.29, "total_tokens": 7265568} {"current_steps": 11125, "total_steps": 38160, "loss": 0.2722, "lr": 4.4618899008126005e-05, "epoch": 5.830712788259958, "percentage": 29.15, "elapsed_time": "0:42:09", "remaining_time": "1:42:27", "throughput": 2873.36, "total_tokens": 7268896} {"current_steps": 11130, "total_steps": 38160, "loss": 0.2738, "lr": 4.461180993080841e-05, "epoch": 5.833333333333333, "percentage": 29.17, "elapsed_time": "0:42:10", "remaining_time": "1:42:26", "throughput": 2873.06, "total_tokens": 7271328} {"current_steps": 11135, "total_steps": 38160, "loss": 0.378, "lr": 4.460471675092393e-05, "epoch": 5.835953878406709, "percentage": 29.18, "elapsed_time": "0:42:11", "remaining_time": "1:42:25", "throughput": 2873.13, "total_tokens": 7274752} {"current_steps": 11140, "total_steps": 38160, "loss": 0.429, "lr": 4.4597619469956356e-05, "epoch": 5.838574423480084, "percentage": 29.19, "elapsed_time": "0:42:13", "remaining_time": "1:42:24", "throughput": 2873.41, "total_tokens": 7279168} {"current_steps": 11145, "total_steps": 38160, "loss": 0.317, "lr": 4.459051808939038e-05, "epoch": 5.841194968553459, "percentage": 29.21, "elapsed_time": "0:42:14", "remaining_time": "1:42:23", "throughput": 2873.58, "total_tokens": 7282944} {"current_steps": 11150, "total_steps": 38160, "loss": 0.3901, "lr": 4.458341261071151e-05, "epoch": 5.843815513626835, "percentage": 29.22, "elapsed_time": "0:42:15", "remaining_time": "1:42:22", "throughput": 2873.52, "total_tokens": 7285824} {"current_steps": 11155, "total_steps": 38160, "loss": 0.3073, "lr": 4.457630303540615e-05, "epoch": 5.84643605870021, "percentage": 29.23, "elapsed_time": "0:42:16", "remaining_time": "1:42:20", "throughput": 2873.31, "total_tokens": 7288384} {"current_steps": 11160, "total_steps": 38160, "loss": 0.3647, "lr": 4.456918936496154e-05, "epoch": 5.849056603773585, "percentage": 29.25, "elapsed_time": "0:42:17", "remaining_time": "1:42:19", "throughput": 2873.34, "total_tokens": 7291840} {"current_steps": 11165, "total_steps": 38160, "loss": 0.3062, "lr": 4.456207160086575e-05, "epoch": 5.85167714884696, "percentage": 29.26, "elapsed_time": "0:42:19", "remaining_time": "1:42:19", "throughput": 2873.5, "total_tokens": 7296032} {"current_steps": 11170, "total_steps": 38160, "loss": 0.4536, "lr": 4.4554949744607775e-05, "epoch": 5.854297693920335, "percentage": 29.27, "elapsed_time": "0:42:20", "remaining_time": "1:42:18", "throughput": 2873.16, "total_tokens": 7298560} {"current_steps": 11175, "total_steps": 38160, "loss": 0.2893, "lr": 4.4547823797677405e-05, "epoch": 5.8569182389937104, "percentage": 29.28, "elapsed_time": "0:42:21", "remaining_time": "1:42:16", "throughput": 2873.04, "total_tokens": 7301376} {"current_steps": 11180, "total_steps": 38160, "loss": 0.3752, "lr": 4.45406937615653e-05, "epoch": 5.859538784067086, "percentage": 29.3, "elapsed_time": "0:42:22", "remaining_time": "1:42:15", "throughput": 2873.19, "total_tokens": 7304896} {"current_steps": 11185, "total_steps": 38160, "loss": 0.3333, "lr": 4.4533559637763006e-05, "epoch": 5.862159329140461, "percentage": 29.31, "elapsed_time": "0:42:23", "remaining_time": "1:42:14", "throughput": 2873.16, "total_tokens": 7307968} {"current_steps": 11190, "total_steps": 38160, "loss": 0.3422, "lr": 4.452642142776288e-05, "epoch": 5.864779874213837, "percentage": 29.32, "elapsed_time": "0:42:24", "remaining_time": "1:42:12", "throughput": 2873.15, "total_tokens": 7311040} {"current_steps": 11195, "total_steps": 38160, "loss": 0.2813, "lr": 4.451927913305816e-05, "epoch": 5.867400419287212, "percentage": 29.34, "elapsed_time": "0:42:25", "remaining_time": "1:42:11", "throughput": 2873.38, "total_tokens": 7314848} {"current_steps": 11200, "total_steps": 38160, "loss": 0.3422, "lr": 4.4512132755142935e-05, "epoch": 5.870020964360587, "percentage": 29.35, "elapsed_time": "0:42:26", "remaining_time": "1:42:10", "throughput": 2873.17, "total_tokens": 7317440} {"current_steps": 11205, "total_steps": 38160, "loss": 0.3481, "lr": 4.450498229551214e-05, "epoch": 5.872641509433962, "percentage": 29.36, "elapsed_time": "0:42:27", "remaining_time": "1:42:09", "throughput": 2873.09, "total_tokens": 7320288} {"current_steps": 11210, "total_steps": 38160, "loss": 0.3764, "lr": 4.449782775566158e-05, "epoch": 5.8752620545073375, "percentage": 29.38, "elapsed_time": "0:42:28", "remaining_time": "1:42:07", "throughput": 2872.99, "total_tokens": 7323168} {"current_steps": 11215, "total_steps": 38160, "loss": 0.291, "lr": 4.449066913708789e-05, "epoch": 5.877882599580713, "percentage": 29.39, "elapsed_time": "0:42:29", "remaining_time": "1:42:06", "throughput": 2872.98, "total_tokens": 7326048} {"current_steps": 11220, "total_steps": 38160, "loss": 0.3297, "lr": 4.448350644128858e-05, "epoch": 5.880503144654088, "percentage": 29.4, "elapsed_time": "0:42:31", "remaining_time": "1:42:05", "throughput": 2872.68, "total_tokens": 7328288} {"current_steps": 11225, "total_steps": 38160, "loss": 0.3533, "lr": 4.4476339669762e-05, "epoch": 5.883123689727463, "percentage": 29.42, "elapsed_time": "0:42:32", "remaining_time": "1:42:03", "throughput": 2872.62, "total_tokens": 7331328} {"current_steps": 11230, "total_steps": 38160, "loss": 0.2884, "lr": 4.446916882400737e-05, "epoch": 5.885744234800838, "percentage": 29.43, "elapsed_time": "0:42:33", "remaining_time": "1:42:02", "throughput": 2872.72, "total_tokens": 7334720} {"current_steps": 11235, "total_steps": 38160, "loss": 0.2676, "lr": 4.446199390552472e-05, "epoch": 5.888364779874214, "percentage": 29.44, "elapsed_time": "0:42:34", "remaining_time": "1:42:01", "throughput": 2872.52, "total_tokens": 7337312} {"current_steps": 11240, "total_steps": 38160, "loss": 0.3822, "lr": 4.445481491581499e-05, "epoch": 5.890985324947589, "percentage": 29.45, "elapsed_time": "0:42:35", "remaining_time": "1:42:00", "throughput": 2872.51, "total_tokens": 7340384} {"current_steps": 11245, "total_steps": 38160, "loss": 0.3615, "lr": 4.444763185637993e-05, "epoch": 5.893605870020965, "percentage": 29.47, "elapsed_time": "0:42:36", "remaining_time": "1:41:58", "throughput": 2872.7, "total_tokens": 7343936} {"current_steps": 11250, "total_steps": 38160, "loss": 0.3192, "lr": 4.4440444728722166e-05, "epoch": 5.89622641509434, "percentage": 29.48, "elapsed_time": "0:42:37", "remaining_time": "1:41:57", "throughput": 2872.57, "total_tokens": 7346848} {"current_steps": 11255, "total_steps": 38160, "loss": 0.3991, "lr": 4.4433253534345136e-05, "epoch": 5.898846960167715, "percentage": 29.49, "elapsed_time": "0:42:38", "remaining_time": "1:41:56", "throughput": 2872.61, "total_tokens": 7350112} {"current_steps": 11260, "total_steps": 38160, "loss": 0.2958, "lr": 4.442605827475318e-05, "epoch": 5.90146750524109, "percentage": 29.51, "elapsed_time": "0:42:39", "remaining_time": "1:41:55", "throughput": 2872.75, "total_tokens": 7353952} {"current_steps": 11265, "total_steps": 38160, "loss": 0.3979, "lr": 4.4418858951451457e-05, "epoch": 5.904088050314465, "percentage": 29.52, "elapsed_time": "0:42:41", "remaining_time": "1:41:54", "throughput": 2872.84, "total_tokens": 7357440} {"current_steps": 11270, "total_steps": 38160, "loss": 0.3836, "lr": 4.441165556594599e-05, "epoch": 5.90670859538784, "percentage": 29.53, "elapsed_time": "0:42:42", "remaining_time": "1:41:53", "throughput": 2872.94, "total_tokens": 7360800} {"current_steps": 11275, "total_steps": 38160, "loss": 0.3847, "lr": 4.440444811974363e-05, "epoch": 5.909329140461216, "percentage": 29.55, "elapsed_time": "0:42:43", "remaining_time": "1:41:51", "throughput": 2872.97, "total_tokens": 7364032} {"current_steps": 11280, "total_steps": 38160, "loss": 0.3654, "lr": 4.43972366143521e-05, "epoch": 5.911949685534591, "percentage": 29.56, "elapsed_time": "0:42:44", "remaining_time": "1:41:50", "throughput": 2872.81, "total_tokens": 7366880} {"current_steps": 11285, "total_steps": 38160, "loss": 0.2861, "lr": 4.4390021051279975e-05, "epoch": 5.914570230607967, "percentage": 29.57, "elapsed_time": "0:42:45", "remaining_time": "1:41:49", "throughput": 2872.67, "total_tokens": 7369664} {"current_steps": 11290, "total_steps": 38160, "loss": 0.4137, "lr": 4.438280143203665e-05, "epoch": 5.917190775681342, "percentage": 29.59, "elapsed_time": "0:42:46", "remaining_time": "1:41:48", "throughput": 2872.49, "total_tokens": 7372192} {"current_steps": 11295, "total_steps": 38160, "loss": 0.3048, "lr": 4.43755777581324e-05, "epoch": 5.919811320754717, "percentage": 29.6, "elapsed_time": "0:42:47", "remaining_time": "1:41:46", "throughput": 2872.3, "total_tokens": 7374720} {"current_steps": 11300, "total_steps": 38160, "loss": 0.302, "lr": 4.4368350031078334e-05, "epoch": 5.922431865828092, "percentage": 29.61, "elapsed_time": "0:42:48", "remaining_time": "1:41:45", "throughput": 2872.45, "total_tokens": 7378112} {"current_steps": 11305, "total_steps": 38160, "loss": 0.3517, "lr": 4.43611182523864e-05, "epoch": 5.9250524109014675, "percentage": 29.63, "elapsed_time": "0:42:49", "remaining_time": "1:41:44", "throughput": 2872.57, "total_tokens": 7381728} {"current_steps": 11310, "total_steps": 38160, "loss": 0.3529, "lr": 4.4353882423569416e-05, "epoch": 5.927672955974843, "percentage": 29.64, "elapsed_time": "0:42:50", "remaining_time": "1:41:43", "throughput": 2872.75, "total_tokens": 7385504} {"current_steps": 11315, "total_steps": 38160, "loss": 0.2765, "lr": 4.434664254614103e-05, "epoch": 5.930293501048218, "percentage": 29.65, "elapsed_time": "0:42:52", "remaining_time": "1:41:42", "throughput": 2873.03, "total_tokens": 7389600} {"current_steps": 11320, "total_steps": 38160, "loss": 0.3063, "lr": 4.4339398621615734e-05, "epoch": 5.932914046121593, "percentage": 29.66, "elapsed_time": "0:42:53", "remaining_time": "1:41:41", "throughput": 2873.51, "total_tokens": 7394240} {"current_steps": 11325, "total_steps": 38160, "loss": 0.3342, "lr": 4.433215065150889e-05, "epoch": 5.935534591194968, "percentage": 29.68, "elapsed_time": "0:42:54", "remaining_time": "1:41:39", "throughput": 2873.25, "total_tokens": 7396704} {"current_steps": 11330, "total_steps": 38160, "loss": 0.282, "lr": 4.4324898637336674e-05, "epoch": 5.938155136268344, "percentage": 29.69, "elapsed_time": "0:42:55", "remaining_time": "1:41:38", "throughput": 2873.45, "total_tokens": 7400352} {"current_steps": 11335, "total_steps": 38160, "loss": 0.2618, "lr": 4.431764258061615e-05, "epoch": 5.940775681341719, "percentage": 29.7, "elapsed_time": "0:42:56", "remaining_time": "1:41:37", "throughput": 2873.25, "total_tokens": 7402816} {"current_steps": 11340, "total_steps": 38160, "loss": 0.2878, "lr": 4.431038248286517e-05, "epoch": 5.943396226415095, "percentage": 29.72, "elapsed_time": "0:42:57", "remaining_time": "1:41:36", "throughput": 2873.14, "total_tokens": 7405568} {"current_steps": 11345, "total_steps": 38160, "loss": 0.3416, "lr": 4.430311834560248e-05, "epoch": 5.94601677148847, "percentage": 29.73, "elapsed_time": "0:42:58", "remaining_time": "1:41:34", "throughput": 2873.16, "total_tokens": 7408608} {"current_steps": 11350, "total_steps": 38160, "loss": 0.3531, "lr": 4.4295850170347664e-05, "epoch": 5.948637316561845, "percentage": 29.74, "elapsed_time": "0:42:59", "remaining_time": "1:41:33", "throughput": 2873.41, "total_tokens": 7412448} {"current_steps": 11355, "total_steps": 38160, "loss": 0.26, "lr": 4.428857795862113e-05, "epoch": 5.95125786163522, "percentage": 29.76, "elapsed_time": "0:43:00", "remaining_time": "1:41:32", "throughput": 2873.28, "total_tokens": 7415104} {"current_steps": 11360, "total_steps": 38160, "loss": 0.2973, "lr": 4.428130171194414e-05, "epoch": 5.953878406708595, "percentage": 29.77, "elapsed_time": "0:43:01", "remaining_time": "1:41:31", "throughput": 2873.4, "total_tokens": 7418944} {"current_steps": 11365, "total_steps": 38160, "loss": 0.2703, "lr": 4.427402143183879e-05, "epoch": 5.95649895178197, "percentage": 29.78, "elapsed_time": "0:43:03", "remaining_time": "1:41:30", "throughput": 2873.59, "total_tokens": 7422816} {"current_steps": 11370, "total_steps": 38160, "loss": 0.238, "lr": 4.426673711982806e-05, "epoch": 5.959119496855346, "percentage": 29.8, "elapsed_time": "0:43:04", "remaining_time": "1:41:28", "throughput": 2873.54, "total_tokens": 7425824} {"current_steps": 11375, "total_steps": 38160, "loss": 0.3839, "lr": 4.425944877743573e-05, "epoch": 5.961740041928721, "percentage": 29.81, "elapsed_time": "0:43:05", "remaining_time": "1:41:27", "throughput": 2873.58, "total_tokens": 7429088} {"current_steps": 11380, "total_steps": 38160, "loss": 0.3912, "lr": 4.425215640618644e-05, "epoch": 5.964360587002097, "percentage": 29.82, "elapsed_time": "0:43:06", "remaining_time": "1:41:26", "throughput": 2873.71, "total_tokens": 7432736} {"current_steps": 11385, "total_steps": 38160, "loss": 0.3752, "lr": 4.424486000760567e-05, "epoch": 5.966981132075472, "percentage": 29.83, "elapsed_time": "0:43:07", "remaining_time": "1:41:25", "throughput": 2873.77, "total_tokens": 7435840} {"current_steps": 11390, "total_steps": 38160, "loss": 0.276, "lr": 4.423755958321974e-05, "epoch": 5.969601677148847, "percentage": 29.85, "elapsed_time": "0:43:08", "remaining_time": "1:41:24", "throughput": 2874.2, "total_tokens": 7441056} {"current_steps": 11395, "total_steps": 38160, "loss": 0.3614, "lr": 4.423025513455582e-05, "epoch": 5.972222222222222, "percentage": 29.86, "elapsed_time": "0:43:10", "remaining_time": "1:41:23", "throughput": 2874.3, "total_tokens": 7444640} {"current_steps": 11400, "total_steps": 38160, "loss": 0.3314, "lr": 4.422294666314192e-05, "epoch": 5.9748427672955975, "percentage": 29.87, "elapsed_time": "0:43:11", "remaining_time": "1:41:22", "throughput": 2874.46, "total_tokens": 7448096} {"current_steps": 11405, "total_steps": 38160, "loss": 0.2885, "lr": 4.421563417050688e-05, "epoch": 5.977463312368973, "percentage": 29.89, "elapsed_time": "0:43:12", "remaining_time": "1:41:21", "throughput": 2874.58, "total_tokens": 7451520} {"current_steps": 11410, "total_steps": 38160, "loss": 0.2929, "lr": 4.42083176581804e-05, "epoch": 5.980083857442348, "percentage": 29.9, "elapsed_time": "0:43:13", "remaining_time": "1:41:19", "throughput": 2874.38, "total_tokens": 7454048} {"current_steps": 11415, "total_steps": 38160, "loss": 0.2551, "lr": 4.4200997127693e-05, "epoch": 5.982704402515723, "percentage": 29.91, "elapsed_time": "0:43:14", "remaining_time": "1:41:18", "throughput": 2874.32, "total_tokens": 7457216} {"current_steps": 11420, "total_steps": 38160, "loss": 0.3328, "lr": 4.419367258057606e-05, "epoch": 5.985324947589098, "percentage": 29.93, "elapsed_time": "0:43:15", "remaining_time": "1:41:17", "throughput": 2874.57, "total_tokens": 7460992} {"current_steps": 11425, "total_steps": 38160, "loss": 0.2707, "lr": 4.418634401836179e-05, "epoch": 5.987945492662474, "percentage": 29.94, "elapsed_time": "0:43:16", "remaining_time": "1:41:16", "throughput": 2874.3, "total_tokens": 7463488} {"current_steps": 11430, "total_steps": 38160, "loss": 0.338, "lr": 4.417901144258324e-05, "epoch": 5.990566037735849, "percentage": 29.95, "elapsed_time": "0:43:17", "remaining_time": "1:41:14", "throughput": 2874.25, "total_tokens": 7466304} {"current_steps": 11435, "total_steps": 38160, "loss": 0.3519, "lr": 4.4171674854774305e-05, "epoch": 5.993186582809225, "percentage": 29.97, "elapsed_time": "0:43:18", "remaining_time": "1:41:13", "throughput": 2874.44, "total_tokens": 7470176} {"current_steps": 11440, "total_steps": 38160, "loss": 0.2776, "lr": 4.416433425646971e-05, "epoch": 5.9958071278826, "percentage": 29.98, "elapsed_time": "0:43:19", "remaining_time": "1:41:12", "throughput": 2874.53, "total_tokens": 7473376} {"current_steps": 11445, "total_steps": 38160, "loss": 0.3266, "lr": 4.415698964920503e-05, "epoch": 5.998427672955975, "percentage": 29.99, "elapsed_time": "0:43:20", "remaining_time": "1:41:11", "throughput": 2874.67, "total_tokens": 7476864} {"current_steps": 11448, "total_steps": 38160, "eval_loss": 0.5208126306533813, "epoch": 6.0, "percentage": 30.0, "elapsed_time": "0:43:33", "remaining_time": "1:41:38", "throughput": 2861.39, "total_tokens": 7478504} {"current_steps": 11450, "total_steps": 38160, "loss": 0.2806, "lr": 4.414964103451667e-05, "epoch": 6.00104821802935, "percentage": 30.01, "elapsed_time": "0:43:37", "remaining_time": "1:41:45", "throughput": 2857.58, "total_tokens": 7479688} {"current_steps": 11455, "total_steps": 38160, "loss": 0.2332, "lr": 4.414228841394187e-05, "epoch": 6.003668763102725, "percentage": 30.02, "elapsed_time": "0:43:38", "remaining_time": "1:41:44", "throughput": 2857.67, "total_tokens": 7483176} {"current_steps": 11460, "total_steps": 38160, "loss": 0.2558, "lr": 4.413493178901872e-05, "epoch": 6.0062893081761, "percentage": 30.03, "elapsed_time": "0:43:39", "remaining_time": "1:41:43", "throughput": 2857.61, "total_tokens": 7486120} {"current_steps": 11465, "total_steps": 38160, "loss": 0.2623, "lr": 4.412757116128614e-05, "epoch": 6.008909853249476, "percentage": 30.04, "elapsed_time": "0:43:40", "remaining_time": "1:41:42", "throughput": 2857.45, "total_tokens": 7488872} {"current_steps": 11470, "total_steps": 38160, "loss": 0.2907, "lr": 4.41202065322839e-05, "epoch": 6.011530398322851, "percentage": 30.06, "elapsed_time": "0:43:41", "remaining_time": "1:41:41", "throughput": 2857.37, "total_tokens": 7491880} {"current_steps": 11475, "total_steps": 38160, "loss": 0.2313, "lr": 4.411283790355259e-05, "epoch": 6.014150943396227, "percentage": 30.07, "elapsed_time": "0:43:42", "remaining_time": "1:41:39", "throughput": 2857.4, "total_tokens": 7494952} {"current_steps": 11480, "total_steps": 38160, "loss": 0.2925, "lr": 4.410546527663364e-05, "epoch": 6.016771488469602, "percentage": 30.08, "elapsed_time": "0:43:44", "remaining_time": "1:41:38", "throughput": 2857.54, "total_tokens": 7498600} {"current_steps": 11485, "total_steps": 38160, "loss": 0.2857, "lr": 4.409808865306931e-05, "epoch": 6.019392033542977, "percentage": 30.1, "elapsed_time": "0:43:45", "remaining_time": "1:41:37", "throughput": 2857.86, "total_tokens": 7502696} {"current_steps": 11490, "total_steps": 38160, "loss": 0.2533, "lr": 4.409070803440273e-05, "epoch": 6.022012578616352, "percentage": 30.11, "elapsed_time": "0:43:46", "remaining_time": "1:41:36", "throughput": 2857.87, "total_tokens": 7505800} {"current_steps": 11495, "total_steps": 38160, "loss": 0.2735, "lr": 4.4083323422177824e-05, "epoch": 6.0246331236897275, "percentage": 30.12, "elapsed_time": "0:43:47", "remaining_time": "1:41:34", "throughput": 2857.84, "total_tokens": 7508712} {"current_steps": 11500, "total_steps": 38160, "loss": 0.2131, "lr": 4.407593481793937e-05, "epoch": 6.027253668763103, "percentage": 30.14, "elapsed_time": "0:43:48", "remaining_time": "1:41:33", "throughput": 2857.7, "total_tokens": 7511400} {"current_steps": 11505, "total_steps": 38160, "loss": 0.2816, "lr": 4.406854222323298e-05, "epoch": 6.029874213836478, "percentage": 30.15, "elapsed_time": "0:43:49", "remaining_time": "1:41:32", "throughput": 2857.88, "total_tokens": 7515208} {"current_steps": 11510, "total_steps": 38160, "loss": 0.1415, "lr": 4.406114563960511e-05, "epoch": 6.032494758909853, "percentage": 30.16, "elapsed_time": "0:43:51", "remaining_time": "1:41:32", "throughput": 2858.2, "total_tokens": 7520712} {"current_steps": 11515, "total_steps": 38160, "loss": 0.2202, "lr": 4.4053745068603026e-05, "epoch": 6.035115303983228, "percentage": 30.18, "elapsed_time": "0:43:52", "remaining_time": "1:41:31", "throughput": 2857.88, "total_tokens": 7522984} {"current_steps": 11520, "total_steps": 38160, "loss": 0.2744, "lr": 4.404634051177485e-05, "epoch": 6.037735849056604, "percentage": 30.19, "elapsed_time": "0:43:53", "remaining_time": "1:41:29", "throughput": 2857.85, "total_tokens": 7526024} {"current_steps": 11525, "total_steps": 38160, "loss": 0.2362, "lr": 4.403893197066953e-05, "epoch": 6.040356394129979, "percentage": 30.2, "elapsed_time": "0:43:54", "remaining_time": "1:41:28", "throughput": 2857.93, "total_tokens": 7529288} {"current_steps": 11530, "total_steps": 38160, "loss": 0.226, "lr": 4.4031519446836855e-05, "epoch": 6.0429769392033545, "percentage": 30.21, "elapsed_time": "0:43:55", "remaining_time": "1:41:27", "throughput": 2857.72, "total_tokens": 7531752} {"current_steps": 11535, "total_steps": 38160, "loss": 0.2787, "lr": 4.402410294182743e-05, "epoch": 6.04559748427673, "percentage": 30.23, "elapsed_time": "0:43:56", "remaining_time": "1:41:25", "throughput": 2857.8, "total_tokens": 7535112} {"current_steps": 11540, "total_steps": 38160, "loss": 0.226, "lr": 4.4016682457192714e-05, "epoch": 6.048218029350105, "percentage": 30.24, "elapsed_time": "0:43:57", "remaining_time": "1:41:24", "throughput": 2857.87, "total_tokens": 7538344} {"current_steps": 11545, "total_steps": 38160, "loss": 0.2433, "lr": 4.400925799448497e-05, "epoch": 6.05083857442348, "percentage": 30.25, "elapsed_time": "0:43:58", "remaining_time": "1:41:23", "throughput": 2857.76, "total_tokens": 7541064} {"current_steps": 11550, "total_steps": 38160, "loss": 0.1972, "lr": 4.400182955525733e-05, "epoch": 6.053459119496855, "percentage": 30.27, "elapsed_time": "0:44:00", "remaining_time": "1:41:22", "throughput": 2857.79, "total_tokens": 7544808} {"current_steps": 11555, "total_steps": 38160, "loss": 0.2052, "lr": 4.3994397141063734e-05, "epoch": 6.05607966457023, "percentage": 30.28, "elapsed_time": "0:44:01", "remaining_time": "1:41:21", "throughput": 2857.95, "total_tokens": 7548872} {"current_steps": 11560, "total_steps": 38160, "loss": 0.3188, "lr": 4.398696075345896e-05, "epoch": 6.058700209643606, "percentage": 30.29, "elapsed_time": "0:44:02", "remaining_time": "1:41:20", "throughput": 2857.98, "total_tokens": 7551912} {"current_steps": 11565, "total_steps": 38160, "loss": 0.207, "lr": 4.39795203939986e-05, "epoch": 6.061320754716981, "percentage": 30.31, "elapsed_time": "0:44:03", "remaining_time": "1:41:18", "throughput": 2857.94, "total_tokens": 7554856} {"current_steps": 11570, "total_steps": 38160, "loss": 0.3229, "lr": 4.397207606423911e-05, "epoch": 6.063941299790357, "percentage": 30.32, "elapsed_time": "0:44:04", "remaining_time": "1:41:17", "throughput": 2858.08, "total_tokens": 7558344} {"current_steps": 11575, "total_steps": 38160, "loss": 0.273, "lr": 4.396462776573775e-05, "epoch": 6.066561844863732, "percentage": 30.33, "elapsed_time": "0:44:05", "remaining_time": "1:41:16", "throughput": 2858.16, "total_tokens": 7561704} {"current_steps": 11580, "total_steps": 38160, "loss": 0.2957, "lr": 4.395717550005262e-05, "epoch": 6.069182389937107, "percentage": 30.35, "elapsed_time": "0:44:06", "remaining_time": "1:41:15", "throughput": 2857.85, "total_tokens": 7563816} {"current_steps": 11585, "total_steps": 38160, "loss": 0.2015, "lr": 4.394971926874265e-05, "epoch": 6.071802935010482, "percentage": 30.36, "elapsed_time": "0:44:07", "remaining_time": "1:41:13", "throughput": 2857.66, "total_tokens": 7566408} {"current_steps": 11590, "total_steps": 38160, "loss": 0.2287, "lr": 4.3942259073367604e-05, "epoch": 6.0744234800838575, "percentage": 30.37, "elapsed_time": "0:44:08", "remaining_time": "1:41:12", "throughput": 2857.79, "total_tokens": 7569960} {"current_steps": 11595, "total_steps": 38160, "loss": 0.2299, "lr": 4.3934794915488065e-05, "epoch": 6.077044025157233, "percentage": 30.39, "elapsed_time": "0:44:09", "remaining_time": "1:41:11", "throughput": 2857.75, "total_tokens": 7572872} {"current_steps": 11600, "total_steps": 38160, "loss": 0.3412, "lr": 4.392732679666544e-05, "epoch": 6.079664570230608, "percentage": 30.4, "elapsed_time": "0:44:10", "remaining_time": "1:41:09", "throughput": 2857.83, "total_tokens": 7576104} {"current_steps": 11605, "total_steps": 38160, "loss": 0.205, "lr": 4.3919854718461986e-05, "epoch": 6.082285115303983, "percentage": 30.41, "elapsed_time": "0:44:12", "remaining_time": "1:41:08", "throughput": 2857.75, "total_tokens": 7578856} {"current_steps": 11610, "total_steps": 38160, "loss": 0.2746, "lr": 4.391237868244078e-05, "epoch": 6.084905660377358, "percentage": 30.42, "elapsed_time": "0:44:13", "remaining_time": "1:41:07", "throughput": 2857.83, "total_tokens": 7582408} {"current_steps": 11615, "total_steps": 38160, "loss": 0.2477, "lr": 4.390489869016571e-05, "epoch": 6.087526205450734, "percentage": 30.44, "elapsed_time": "0:44:14", "remaining_time": "1:41:06", "throughput": 2857.73, "total_tokens": 7585224} {"current_steps": 11620, "total_steps": 38160, "loss": 0.2408, "lr": 4.389741474320152e-05, "epoch": 6.090146750524109, "percentage": 30.45, "elapsed_time": "0:44:15", "remaining_time": "1:41:04", "throughput": 2857.62, "total_tokens": 7587880} {"current_steps": 11625, "total_steps": 38160, "loss": 0.3273, "lr": 4.388992684311376e-05, "epoch": 6.0927672955974845, "percentage": 30.46, "elapsed_time": "0:44:16", "remaining_time": "1:41:03", "throughput": 2857.86, "total_tokens": 7591784} {"current_steps": 11630, "total_steps": 38160, "loss": 0.2613, "lr": 4.388243499146881e-05, "epoch": 6.09538784067086, "percentage": 30.48, "elapsed_time": "0:44:17", "remaining_time": "1:41:02", "throughput": 2857.89, "total_tokens": 7594920} {"current_steps": 11635, "total_steps": 38160, "loss": 0.3908, "lr": 4.3874939189833876e-05, "epoch": 6.098008385744235, "percentage": 30.49, "elapsed_time": "0:44:18", "remaining_time": "1:41:01", "throughput": 2857.97, "total_tokens": 7598504} {"current_steps": 11640, "total_steps": 38160, "loss": 0.325, "lr": 4.3867439439777005e-05, "epoch": 6.10062893081761, "percentage": 30.5, "elapsed_time": "0:44:19", "remaining_time": "1:40:59", "throughput": 2857.98, "total_tokens": 7601640} {"current_steps": 11645, "total_steps": 38160, "loss": 0.2826, "lr": 4.385993574286705e-05, "epoch": 6.103249475890985, "percentage": 30.52, "elapsed_time": "0:44:20", "remaining_time": "1:40:58", "throughput": 2857.93, "total_tokens": 7604520} {"current_steps": 11650, "total_steps": 38160, "loss": 0.1822, "lr": 4.3852428100673705e-05, "epoch": 6.10587002096436, "percentage": 30.53, "elapsed_time": "0:44:21", "remaining_time": "1:40:57", "throughput": 2858.15, "total_tokens": 7608136} {"current_steps": 11655, "total_steps": 38160, "loss": 0.3052, "lr": 4.3844916514767484e-05, "epoch": 6.1084905660377355, "percentage": 30.54, "elapsed_time": "0:44:23", "remaining_time": "1:40:56", "throughput": 2858.26, "total_tokens": 7611592} {"current_steps": 11660, "total_steps": 38160, "loss": 0.2676, "lr": 4.383740098671972e-05, "epoch": 6.111111111111111, "percentage": 30.56, "elapsed_time": "0:44:24", "remaining_time": "1:40:54", "throughput": 2858.12, "total_tokens": 7614184} {"current_steps": 11665, "total_steps": 38160, "loss": 0.1936, "lr": 4.3829881518102576e-05, "epoch": 6.113731656184487, "percentage": 30.57, "elapsed_time": "0:44:25", "remaining_time": "1:40:53", "throughput": 2858.0, "total_tokens": 7617064} {"current_steps": 11670, "total_steps": 38160, "loss": 0.2457, "lr": 4.3822358110489045e-05, "epoch": 6.116352201257862, "percentage": 30.58, "elapsed_time": "0:44:26", "remaining_time": "1:40:52", "throughput": 2858.19, "total_tokens": 7620680} {"current_steps": 11675, "total_steps": 38160, "loss": 0.1959, "lr": 4.381483076545294e-05, "epoch": 6.118972746331237, "percentage": 30.59, "elapsed_time": "0:44:27", "remaining_time": "1:40:50", "throughput": 2858.28, "total_tokens": 7623944} {"current_steps": 11680, "total_steps": 38160, "loss": 0.215, "lr": 4.380729948456888e-05, "epoch": 6.121593291404612, "percentage": 30.61, "elapsed_time": "0:44:28", "remaining_time": "1:40:49", "throughput": 2858.33, "total_tokens": 7627144} {"current_steps": 11685, "total_steps": 38160, "loss": 0.2836, "lr": 4.3799764269412336e-05, "epoch": 6.1242138364779874, "percentage": 30.62, "elapsed_time": "0:44:29", "remaining_time": "1:40:48", "throughput": 2858.32, "total_tokens": 7630216} {"current_steps": 11690, "total_steps": 38160, "loss": 0.2468, "lr": 4.379222512155958e-05, "epoch": 6.126834381551363, "percentage": 30.63, "elapsed_time": "0:44:30", "remaining_time": "1:40:46", "throughput": 2858.22, "total_tokens": 7633000} {"current_steps": 11695, "total_steps": 38160, "loss": 0.1946, "lr": 4.378468204258773e-05, "epoch": 6.129454926624738, "percentage": 30.65, "elapsed_time": "0:44:31", "remaining_time": "1:40:45", "throughput": 2858.23, "total_tokens": 7636104} {"current_steps": 11700, "total_steps": 38160, "loss": 0.3896, "lr": 4.37771350340747e-05, "epoch": 6.132075471698113, "percentage": 30.66, "elapsed_time": "0:44:32", "remaining_time": "1:40:44", "throughput": 2858.24, "total_tokens": 7639208} {"current_steps": 11705, "total_steps": 38160, "loss": 0.2606, "lr": 4.376958409759925e-05, "epoch": 6.134696016771488, "percentage": 30.67, "elapsed_time": "0:44:33", "remaining_time": "1:40:43", "throughput": 2858.21, "total_tokens": 7642184} {"current_steps": 11710, "total_steps": 38160, "loss": 0.3036, "lr": 4.376202923474093e-05, "epoch": 6.137316561844864, "percentage": 30.69, "elapsed_time": "0:44:34", "remaining_time": "1:40:41", "throughput": 2858.29, "total_tokens": 7645480} {"current_steps": 11715, "total_steps": 38160, "loss": 0.2537, "lr": 4.3754470447080145e-05, "epoch": 6.139937106918239, "percentage": 30.7, "elapsed_time": "0:44:35", "remaining_time": "1:40:40", "throughput": 2858.42, "total_tokens": 7648936} {"current_steps": 11720, "total_steps": 38160, "loss": 0.2423, "lr": 4.374690773619811e-05, "epoch": 6.1425576519916145, "percentage": 30.71, "elapsed_time": "0:44:37", "remaining_time": "1:40:39", "throughput": 2858.33, "total_tokens": 7651816} {"current_steps": 11725, "total_steps": 38160, "loss": 0.2944, "lr": 4.373934110367685e-05, "epoch": 6.14517819706499, "percentage": 30.73, "elapsed_time": "0:44:38", "remaining_time": "1:40:38", "throughput": 2858.17, "total_tokens": 7654568} {"current_steps": 11730, "total_steps": 38160, "loss": 0.1676, "lr": 4.373177055109922e-05, "epoch": 6.147798742138365, "percentage": 30.74, "elapsed_time": "0:44:39", "remaining_time": "1:40:36", "throughput": 2858.14, "total_tokens": 7657544} {"current_steps": 11735, "total_steps": 38160, "loss": 0.3453, "lr": 4.3724196080048896e-05, "epoch": 6.15041928721174, "percentage": 30.75, "elapsed_time": "0:44:40", "remaining_time": "1:40:35", "throughput": 2858.24, "total_tokens": 7660936} {"current_steps": 11740, "total_steps": 38160, "loss": 0.2836, "lr": 4.3716617692110364e-05, "epoch": 6.153039832285115, "percentage": 30.77, "elapsed_time": "0:44:41", "remaining_time": "1:40:34", "throughput": 2857.99, "total_tokens": 7663336} {"current_steps": 11745, "total_steps": 38160, "loss": 0.2569, "lr": 4.3709035388868943e-05, "epoch": 6.15566037735849, "percentage": 30.78, "elapsed_time": "0:44:42", "remaining_time": "1:40:32", "throughput": 2857.94, "total_tokens": 7666312} {"current_steps": 11750, "total_steps": 38160, "loss": 0.3123, "lr": 4.3701449171910767e-05, "epoch": 6.1582809224318655, "percentage": 30.79, "elapsed_time": "0:44:43", "remaining_time": "1:40:31", "throughput": 2857.82, "total_tokens": 7669224} {"current_steps": 11755, "total_steps": 38160, "loss": 0.2396, "lr": 4.3693859042822774e-05, "epoch": 6.160901467505241, "percentage": 30.8, "elapsed_time": "0:44:44", "remaining_time": "1:40:30", "throughput": 2857.76, "total_tokens": 7672264} {"current_steps": 11760, "total_steps": 38160, "loss": 0.3193, "lr": 4.368626500319275e-05, "epoch": 6.163522012578617, "percentage": 30.82, "elapsed_time": "0:44:45", "remaining_time": "1:40:29", "throughput": 2857.52, "total_tokens": 7674824} {"current_steps": 11765, "total_steps": 38160, "loss": 0.1965, "lr": 4.367866705460927e-05, "epoch": 6.166142557651992, "percentage": 30.83, "elapsed_time": "0:44:46", "remaining_time": "1:40:28", "throughput": 2857.42, "total_tokens": 7677608} {"current_steps": 11770, "total_steps": 38160, "loss": 0.2809, "lr": 4.367106519866173e-05, "epoch": 6.168763102725367, "percentage": 30.84, "elapsed_time": "0:44:47", "remaining_time": "1:40:26", "throughput": 2857.44, "total_tokens": 7680680} {"current_steps": 11775, "total_steps": 38160, "loss": 0.2947, "lr": 4.366345943694037e-05, "epoch": 6.171383647798742, "percentage": 30.86, "elapsed_time": "0:44:49", "remaining_time": "1:40:25", "throughput": 2857.55, "total_tokens": 7684072} {"current_steps": 11780, "total_steps": 38160, "loss": 0.2752, "lr": 4.365584977103622e-05, "epoch": 6.174004192872117, "percentage": 30.87, "elapsed_time": "0:44:50", "remaining_time": "1:40:24", "throughput": 2857.68, "total_tokens": 7687624} {"current_steps": 11785, "total_steps": 38160, "loss": 0.353, "lr": 4.364823620254113e-05, "epoch": 6.176624737945493, "percentage": 30.88, "elapsed_time": "0:44:51", "remaining_time": "1:40:23", "throughput": 2857.88, "total_tokens": 7691656} {"current_steps": 11790, "total_steps": 38160, "loss": 0.283, "lr": 4.364061873304778e-05, "epoch": 6.179245283018868, "percentage": 30.9, "elapsed_time": "0:44:52", "remaining_time": "1:40:22", "throughput": 2857.82, "total_tokens": 7694568} {"current_steps": 11795, "total_steps": 38160, "loss": 0.243, "lr": 4.363299736414965e-05, "epoch": 6.181865828092243, "percentage": 30.91, "elapsed_time": "0:44:53", "remaining_time": "1:40:20", "throughput": 2857.74, "total_tokens": 7697544} {"current_steps": 11800, "total_steps": 38160, "loss": 0.5004, "lr": 4.3625372097441045e-05, "epoch": 6.184486373165618, "percentage": 30.92, "elapsed_time": "0:44:54", "remaining_time": "1:40:19", "throughput": 2857.63, "total_tokens": 7700456} {"current_steps": 11805, "total_steps": 38160, "loss": 0.2499, "lr": 4.3617742934517094e-05, "epoch": 6.187106918238993, "percentage": 30.94, "elapsed_time": "0:44:55", "remaining_time": "1:40:18", "throughput": 2857.44, "total_tokens": 7703112} {"current_steps": 11810, "total_steps": 38160, "loss": 0.2328, "lr": 4.361010987697373e-05, "epoch": 6.189727463312369, "percentage": 30.95, "elapsed_time": "0:44:56", "remaining_time": "1:40:17", "throughput": 2857.37, "total_tokens": 7705992} {"current_steps": 11815, "total_steps": 38160, "loss": 0.2719, "lr": 4.360247292640768e-05, "epoch": 6.1923480083857445, "percentage": 30.96, "elapsed_time": "0:44:58", "remaining_time": "1:40:16", "throughput": 2857.42, "total_tokens": 7709576} {"current_steps": 11820, "total_steps": 38160, "loss": 0.2712, "lr": 4.359483208441653e-05, "epoch": 6.19496855345912, "percentage": 30.97, "elapsed_time": "0:44:59", "remaining_time": "1:40:14", "throughput": 2857.4, "total_tokens": 7712712} {"current_steps": 11825, "total_steps": 38160, "loss": 0.2514, "lr": 4.3587187352598646e-05, "epoch": 6.197589098532495, "percentage": 30.99, "elapsed_time": "0:45:00", "remaining_time": "1:40:13", "throughput": 2857.21, "total_tokens": 7715432} {"current_steps": 11830, "total_steps": 38160, "loss": 0.2199, "lr": 4.357953873255323e-05, "epoch": 6.20020964360587, "percentage": 31.0, "elapsed_time": "0:45:01", "remaining_time": "1:40:12", "throughput": 2857.01, "total_tokens": 7718216} {"current_steps": 11835, "total_steps": 38160, "loss": 0.2737, "lr": 4.357188622588027e-05, "epoch": 6.202830188679245, "percentage": 31.01, "elapsed_time": "0:45:02", "remaining_time": "1:40:11", "throughput": 2856.96, "total_tokens": 7721096} {"current_steps": 11840, "total_steps": 38160, "loss": 0.2722, "lr": 4.356422983418059e-05, "epoch": 6.20545073375262, "percentage": 31.03, "elapsed_time": "0:45:03", "remaining_time": "1:40:10", "throughput": 2856.99, "total_tokens": 7724264} {"current_steps": 11845, "total_steps": 38160, "loss": 0.2349, "lr": 4.3556569559055824e-05, "epoch": 6.2080712788259955, "percentage": 31.04, "elapsed_time": "0:45:04", "remaining_time": "1:40:08", "throughput": 2856.93, "total_tokens": 7727176} {"current_steps": 11850, "total_steps": 38160, "loss": 0.2818, "lr": 4.3548905402108406e-05, "epoch": 6.210691823899371, "percentage": 31.05, "elapsed_time": "0:45:05", "remaining_time": "1:40:07", "throughput": 2856.67, "total_tokens": 7729544} {"current_steps": 11855, "total_steps": 38160, "loss": 0.3428, "lr": 4.35412373649416e-05, "epoch": 6.213312368972747, "percentage": 31.07, "elapsed_time": "0:45:06", "remaining_time": "1:40:06", "throughput": 2856.84, "total_tokens": 7733288} {"current_steps": 11860, "total_steps": 38160, "loss": 0.2456, "lr": 4.353356544915947e-05, "epoch": 6.215932914046122, "percentage": 31.08, "elapsed_time": "0:45:08", "remaining_time": "1:40:05", "throughput": 2857.1, "total_tokens": 7737096} {"current_steps": 11865, "total_steps": 38160, "loss": 0.2659, "lr": 4.352588965636689e-05, "epoch": 6.218553459119497, "percentage": 31.09, "elapsed_time": "0:45:09", "remaining_time": "1:40:04", "throughput": 2857.52, "total_tokens": 7741512} {"current_steps": 11870, "total_steps": 38160, "loss": 0.251, "lr": 4.351820998816954e-05, "epoch": 6.221174004192872, "percentage": 31.11, "elapsed_time": "0:45:10", "remaining_time": "1:40:02", "throughput": 2857.51, "total_tokens": 7744648} {"current_steps": 11875, "total_steps": 38160, "loss": 0.2101, "lr": 4.3510526446173935e-05, "epoch": 6.223794549266247, "percentage": 31.12, "elapsed_time": "0:45:11", "remaining_time": "1:40:01", "throughput": 2857.64, "total_tokens": 7748392} {"current_steps": 11880, "total_steps": 38160, "loss": 0.2209, "lr": 4.350283903198737e-05, "epoch": 6.226415094339623, "percentage": 31.13, "elapsed_time": "0:45:12", "remaining_time": "1:40:00", "throughput": 2857.79, "total_tokens": 7752360} {"current_steps": 11885, "total_steps": 38160, "loss": 0.2113, "lr": 4.349514774721797e-05, "epoch": 6.229035639412998, "percentage": 31.15, "elapsed_time": "0:45:13", "remaining_time": "1:39:59", "throughput": 2857.6, "total_tokens": 7755016} {"current_steps": 11890, "total_steps": 38160, "loss": 0.31, "lr": 4.348745259347467e-05, "epoch": 6.231656184486373, "percentage": 31.16, "elapsed_time": "0:45:14", "remaining_time": "1:39:58", "throughput": 2857.63, "total_tokens": 7758120} {"current_steps": 11895, "total_steps": 38160, "loss": 0.3484, "lr": 4.347975357236721e-05, "epoch": 6.234276729559748, "percentage": 31.17, "elapsed_time": "0:45:15", "remaining_time": "1:39:56", "throughput": 2857.61, "total_tokens": 7761032} {"current_steps": 11900, "total_steps": 38160, "loss": 0.2303, "lr": 4.347205068550612e-05, "epoch": 6.236897274633123, "percentage": 31.18, "elapsed_time": "0:45:17", "remaining_time": "1:39:55", "throughput": 2857.26, "total_tokens": 7763240} {"current_steps": 11905, "total_steps": 38160, "loss": 0.2431, "lr": 4.3464343934502774e-05, "epoch": 6.239517819706499, "percentage": 31.2, "elapsed_time": "0:45:18", "remaining_time": "1:39:54", "throughput": 2857.44, "total_tokens": 7766664} {"current_steps": 11910, "total_steps": 38160, "loss": 0.3223, "lr": 4.345663332096932e-05, "epoch": 6.2421383647798745, "percentage": 31.21, "elapsed_time": "0:45:19", "remaining_time": "1:39:52", "throughput": 2857.36, "total_tokens": 7769448} {"current_steps": 11915, "total_steps": 38160, "loss": 0.339, "lr": 4.344891884651875e-05, "epoch": 6.24475890985325, "percentage": 31.22, "elapsed_time": "0:45:20", "remaining_time": "1:39:51", "throughput": 2857.31, "total_tokens": 7772296} {"current_steps": 11920, "total_steps": 38160, "loss": 0.1822, "lr": 4.344120051276483e-05, "epoch": 6.247379454926625, "percentage": 31.24, "elapsed_time": "0:45:21", "remaining_time": "1:39:50", "throughput": 2857.45, "total_tokens": 7775912} {"current_steps": 11925, "total_steps": 38160, "loss": 0.3132, "lr": 4.3433478321322155e-05, "epoch": 6.25, "percentage": 31.25, "elapsed_time": "0:45:22", "remaining_time": "1:39:49", "throughput": 2857.67, "total_tokens": 7779784} {"current_steps": 11930, "total_steps": 38160, "loss": 0.2136, "lr": 4.3425752273806106e-05, "epoch": 6.252620545073375, "percentage": 31.26, "elapsed_time": "0:45:23", "remaining_time": "1:39:47", "throughput": 2857.57, "total_tokens": 7782504} {"current_steps": 11935, "total_steps": 38160, "loss": 0.1841, "lr": 4.34180223718329e-05, "epoch": 6.25524109014675, "percentage": 31.28, "elapsed_time": "0:45:24", "remaining_time": "1:39:46", "throughput": 2857.62, "total_tokens": 7785864} {"current_steps": 11940, "total_steps": 38160, "loss": 0.2428, "lr": 4.341028861701953e-05, "epoch": 6.2578616352201255, "percentage": 31.29, "elapsed_time": "0:45:25", "remaining_time": "1:39:45", "throughput": 2857.6, "total_tokens": 7788808} {"current_steps": 11945, "total_steps": 38160, "loss": 0.2566, "lr": 4.3402551010983825e-05, "epoch": 6.260482180293501, "percentage": 31.3, "elapsed_time": "0:45:26", "remaining_time": "1:39:44", "throughput": 2857.63, "total_tokens": 7792232} {"current_steps": 11950, "total_steps": 38160, "loss": 0.2374, "lr": 4.33948095553444e-05, "epoch": 6.263102725366876, "percentage": 31.32, "elapsed_time": "0:45:27", "remaining_time": "1:39:43", "throughput": 2857.45, "total_tokens": 7794856} {"current_steps": 11955, "total_steps": 38160, "loss": 0.3608, "lr": 4.338706425172067e-05, "epoch": 6.265723270440252, "percentage": 31.33, "elapsed_time": "0:45:28", "remaining_time": "1:39:41", "throughput": 2857.43, "total_tokens": 7797800} {"current_steps": 11960, "total_steps": 38160, "loss": 0.2096, "lr": 4.3379315101732866e-05, "epoch": 6.268343815513627, "percentage": 31.34, "elapsed_time": "0:45:30", "remaining_time": "1:39:40", "throughput": 2857.49, "total_tokens": 7801256} {"current_steps": 11965, "total_steps": 38160, "loss": 0.2337, "lr": 4.3371562107002026e-05, "epoch": 6.270964360587002, "percentage": 31.35, "elapsed_time": "0:45:31", "remaining_time": "1:39:39", "throughput": 2857.48, "total_tokens": 7804296} {"current_steps": 11970, "total_steps": 38160, "loss": 0.2467, "lr": 4.3363805269149984e-05, "epoch": 6.273584905660377, "percentage": 31.37, "elapsed_time": "0:45:32", "remaining_time": "1:39:38", "throughput": 2857.55, "total_tokens": 7807464} {"current_steps": 11975, "total_steps": 38160, "loss": 0.2008, "lr": 4.335604458979939e-05, "epoch": 6.276205450733753, "percentage": 31.38, "elapsed_time": "0:45:33", "remaining_time": "1:39:37", "throughput": 2857.71, "total_tokens": 7812008} {"current_steps": 11980, "total_steps": 38160, "loss": 0.2339, "lr": 4.3348280070573686e-05, "epoch": 6.278825995807128, "percentage": 31.39, "elapsed_time": "0:45:34", "remaining_time": "1:39:36", "throughput": 2857.71, "total_tokens": 7815336} {"current_steps": 11985, "total_steps": 38160, "loss": 0.1897, "lr": 4.334051171309712e-05, "epoch": 6.281446540880503, "percentage": 31.41, "elapsed_time": "0:45:36", "remaining_time": "1:39:35", "throughput": 2857.65, "total_tokens": 7818856} {"current_steps": 11990, "total_steps": 38160, "loss": 0.328, "lr": 4.333273951899474e-05, "epoch": 6.284067085953878, "percentage": 31.42, "elapsed_time": "0:45:37", "remaining_time": "1:39:34", "throughput": 2857.64, "total_tokens": 7822024} {"current_steps": 11995, "total_steps": 38160, "loss": 0.3479, "lr": 4.33249634898924e-05, "epoch": 6.286687631027253, "percentage": 31.43, "elapsed_time": "0:45:38", "remaining_time": "1:39:33", "throughput": 2857.81, "total_tokens": 7825640} {"current_steps": 12000, "total_steps": 38160, "loss": 0.2322, "lr": 4.331718362741677e-05, "epoch": 6.289308176100629, "percentage": 31.45, "elapsed_time": "0:45:39", "remaining_time": "1:39:32", "throughput": 2857.49, "total_tokens": 7827944} {"current_steps": 12005, "total_steps": 38160, "loss": 0.2929, "lr": 4.330939993319529e-05, "epoch": 6.2919287211740045, "percentage": 31.46, "elapsed_time": "0:45:40", "remaining_time": "1:39:30", "throughput": 2857.28, "total_tokens": 7830600} {"current_steps": 12010, "total_steps": 38160, "loss": 0.2019, "lr": 4.330161240885623e-05, "epoch": 6.29454926624738, "percentage": 31.47, "elapsed_time": "0:45:41", "remaining_time": "1:39:29", "throughput": 2857.36, "total_tokens": 7834056} {"current_steps": 12015, "total_steps": 38160, "loss": 0.2764, "lr": 4.3293821056028654e-05, "epoch": 6.297169811320755, "percentage": 31.49, "elapsed_time": "0:45:42", "remaining_time": "1:39:28", "throughput": 2857.26, "total_tokens": 7836904} {"current_steps": 12020, "total_steps": 38160, "loss": 0.2747, "lr": 4.3286025876342415e-05, "epoch": 6.29979035639413, "percentage": 31.5, "elapsed_time": "0:45:43", "remaining_time": "1:39:27", "throughput": 2857.17, "total_tokens": 7839880} {"current_steps": 12025, "total_steps": 38160, "loss": 0.278, "lr": 4.327822687142819e-05, "epoch": 6.302410901467505, "percentage": 31.51, "elapsed_time": "0:45:45", "remaining_time": "1:39:26", "throughput": 2857.25, "total_tokens": 7843432} {"current_steps": 12030, "total_steps": 38160, "loss": 0.2388, "lr": 4.327042404291742e-05, "epoch": 6.30503144654088, "percentage": 31.53, "elapsed_time": "0:45:46", "remaining_time": "1:39:25", "throughput": 2857.06, "total_tokens": 7846216} {"current_steps": 12035, "total_steps": 38160, "loss": 0.2962, "lr": 4.326261739244239e-05, "epoch": 6.3076519916142555, "percentage": 31.54, "elapsed_time": "0:45:47", "remaining_time": "1:39:23", "throughput": 2857.08, "total_tokens": 7849544} {"current_steps": 12040, "total_steps": 38160, "loss": 0.2827, "lr": 4.325480692163615e-05, "epoch": 6.310272536687631, "percentage": 31.55, "elapsed_time": "0:45:48", "remaining_time": "1:39:22", "throughput": 2857.01, "total_tokens": 7852552} {"current_steps": 12045, "total_steps": 38160, "loss": 0.3058, "lr": 4.324699263213256e-05, "epoch": 6.312893081761006, "percentage": 31.56, "elapsed_time": "0:45:49", "remaining_time": "1:39:21", "throughput": 2856.92, "total_tokens": 7855336} {"current_steps": 12050, "total_steps": 38160, "loss": 0.2963, "lr": 4.3239174525566285e-05, "epoch": 6.315513626834382, "percentage": 31.58, "elapsed_time": "0:45:50", "remaining_time": "1:39:20", "throughput": 2856.83, "total_tokens": 7858184} {"current_steps": 12055, "total_steps": 38160, "loss": 0.247, "lr": 4.3231352603572784e-05, "epoch": 6.318134171907757, "percentage": 31.59, "elapsed_time": "0:45:51", "remaining_time": "1:39:18", "throughput": 2856.82, "total_tokens": 7861192} {"current_steps": 12060, "total_steps": 38160, "loss": 0.2907, "lr": 4.322352686778832e-05, "epoch": 6.320754716981132, "percentage": 31.6, "elapsed_time": "0:45:52", "remaining_time": "1:39:17", "throughput": 2856.85, "total_tokens": 7864520} {"current_steps": 12065, "total_steps": 38160, "loss": 0.3099, "lr": 4.3215697319849926e-05, "epoch": 6.323375262054507, "percentage": 31.62, "elapsed_time": "0:45:53", "remaining_time": "1:39:16", "throughput": 2856.71, "total_tokens": 7867240} {"current_steps": 12070, "total_steps": 38160, "loss": 0.2985, "lr": 4.3207863961395476e-05, "epoch": 6.325995807127883, "percentage": 31.63, "elapsed_time": "0:45:54", "remaining_time": "1:39:15", "throughput": 2856.67, "total_tokens": 7870120} {"current_steps": 12075, "total_steps": 38160, "loss": 0.2313, "lr": 4.320002679406361e-05, "epoch": 6.328616352201258, "percentage": 31.64, "elapsed_time": "0:45:56", "remaining_time": "1:39:14", "throughput": 2856.7, "total_tokens": 7873736} {"current_steps": 12080, "total_steps": 38160, "loss": 0.2941, "lr": 4.319218581949378e-05, "epoch": 6.331236897274633, "percentage": 31.66, "elapsed_time": "0:45:57", "remaining_time": "1:39:12", "throughput": 2856.76, "total_tokens": 7877000} {"current_steps": 12085, "total_steps": 38160, "loss": 0.179, "lr": 4.318434103932622e-05, "epoch": 6.333857442348008, "percentage": 31.67, "elapsed_time": "0:45:58", "remaining_time": "1:39:11", "throughput": 2856.66, "total_tokens": 7879784} {"current_steps": 12090, "total_steps": 38160, "loss": 0.2337, "lr": 4.317649245520197e-05, "epoch": 6.336477987421383, "percentage": 31.68, "elapsed_time": "0:45:59", "remaining_time": "1:39:10", "throughput": 2856.68, "total_tokens": 7882792} {"current_steps": 12095, "total_steps": 38160, "loss": 0.3081, "lr": 4.3168640068762875e-05, "epoch": 6.339098532494759, "percentage": 31.7, "elapsed_time": "0:46:00", "remaining_time": "1:39:08", "throughput": 2856.51, "total_tokens": 7885416} {"current_steps": 12100, "total_steps": 38160, "loss": 0.285, "lr": 4.316078388165155e-05, "epoch": 6.3417190775681345, "percentage": 31.71, "elapsed_time": "0:46:01", "remaining_time": "1:39:07", "throughput": 2856.65, "total_tokens": 7888936} {"current_steps": 12105, "total_steps": 38160, "loss": 0.3356, "lr": 4.315292389551143e-05, "epoch": 6.34433962264151, "percentage": 31.72, "elapsed_time": "0:46:02", "remaining_time": "1:39:06", "throughput": 2856.54, "total_tokens": 7891976} {"current_steps": 12110, "total_steps": 38160, "loss": 0.3222, "lr": 4.3145060111986726e-05, "epoch": 6.346960167714885, "percentage": 31.73, "elapsed_time": "0:46:03", "remaining_time": "1:39:05", "throughput": 2856.72, "total_tokens": 7895848} {"current_steps": 12115, "total_steps": 38160, "loss": 0.3689, "lr": 4.313719253272246e-05, "epoch": 6.34958071278826, "percentage": 31.75, "elapsed_time": "0:46:05", "remaining_time": "1:39:04", "throughput": 2856.69, "total_tokens": 7898760} {"current_steps": 12120, "total_steps": 38160, "loss": 0.2668, "lr": 4.3129321159364436e-05, "epoch": 6.352201257861635, "percentage": 31.76, "elapsed_time": "0:46:06", "remaining_time": "1:39:03", "throughput": 2856.73, "total_tokens": 7902120} {"current_steps": 12125, "total_steps": 38160, "loss": 0.4266, "lr": 4.312144599355925e-05, "epoch": 6.35482180293501, "percentage": 31.77, "elapsed_time": "0:46:07", "remaining_time": "1:39:01", "throughput": 2856.75, "total_tokens": 7905224} {"current_steps": 12130, "total_steps": 38160, "loss": 0.3278, "lr": 4.31135670369543e-05, "epoch": 6.3574423480083855, "percentage": 31.79, "elapsed_time": "0:46:08", "remaining_time": "1:39:00", "throughput": 2856.77, "total_tokens": 7908424} {"current_steps": 12135, "total_steps": 38160, "loss": 0.2627, "lr": 4.310568429119779e-05, "epoch": 6.360062893081761, "percentage": 31.8, "elapsed_time": "0:46:09", "remaining_time": "1:38:59", "throughput": 2856.72, "total_tokens": 7911336} {"current_steps": 12140, "total_steps": 38160, "loss": 0.1925, "lr": 4.309779775793868e-05, "epoch": 6.362683438155136, "percentage": 31.81, "elapsed_time": "0:46:10", "remaining_time": "1:38:57", "throughput": 2856.5, "total_tokens": 7913704} {"current_steps": 12145, "total_steps": 38160, "loss": 0.2886, "lr": 4.308990743882675e-05, "epoch": 6.365303983228512, "percentage": 31.83, "elapsed_time": "0:46:11", "remaining_time": "1:38:56", "throughput": 2856.44, "total_tokens": 7916584} {"current_steps": 12150, "total_steps": 38160, "loss": 0.2887, "lr": 4.308201333551256e-05, "epoch": 6.367924528301887, "percentage": 31.84, "elapsed_time": "0:46:12", "remaining_time": "1:38:55", "throughput": 2856.58, "total_tokens": 7919880} {"current_steps": 12155, "total_steps": 38160, "loss": 0.3066, "lr": 4.3074115449647476e-05, "epoch": 6.370545073375262, "percentage": 31.85, "elapsed_time": "0:46:13", "remaining_time": "1:38:54", "throughput": 2856.81, "total_tokens": 7923752} {"current_steps": 12160, "total_steps": 38160, "loss": 0.3448, "lr": 4.306621378288364e-05, "epoch": 6.373165618448637, "percentage": 31.87, "elapsed_time": "0:46:14", "remaining_time": "1:38:52", "throughput": 2857.08, "total_tokens": 7927464} {"current_steps": 12165, "total_steps": 38160, "loss": 0.1936, "lr": 4.305830833687399e-05, "epoch": 6.3757861635220126, "percentage": 31.88, "elapsed_time": "0:46:15", "remaining_time": "1:38:51", "throughput": 2857.13, "total_tokens": 7930792} {"current_steps": 12170, "total_steps": 38160, "loss": 0.3156, "lr": 4.305039911327225e-05, "epoch": 6.378406708595388, "percentage": 31.89, "elapsed_time": "0:46:17", "remaining_time": "1:38:50", "throughput": 2857.42, "total_tokens": 7935112} {"current_steps": 12175, "total_steps": 38160, "loss": 0.2676, "lr": 4.304248611373296e-05, "epoch": 6.381027253668763, "percentage": 31.91, "elapsed_time": "0:46:18", "remaining_time": "1:38:49", "throughput": 2857.47, "total_tokens": 7938152} {"current_steps": 12180, "total_steps": 38160, "loss": 0.2802, "lr": 4.30345693399114e-05, "epoch": 6.383647798742138, "percentage": 31.92, "elapsed_time": "0:46:19", "remaining_time": "1:38:48", "throughput": 2857.76, "total_tokens": 7942536} {"current_steps": 12185, "total_steps": 38160, "loss": 0.2054, "lr": 4.30266487934637e-05, "epoch": 6.386268343815513, "percentage": 31.93, "elapsed_time": "0:46:20", "remaining_time": "1:38:46", "throughput": 2857.68, "total_tokens": 7945224} {"current_steps": 12190, "total_steps": 38160, "loss": 0.238, "lr": 4.3018724476046714e-05, "epoch": 6.388888888888889, "percentage": 31.94, "elapsed_time": "0:46:21", "remaining_time": "1:38:45", "throughput": 2857.82, "total_tokens": 7948520} {"current_steps": 12195, "total_steps": 38160, "loss": 0.3246, "lr": 4.301079638931814e-05, "epoch": 6.3915094339622645, "percentage": 31.96, "elapsed_time": "0:46:22", "remaining_time": "1:38:44", "throughput": 2857.8, "total_tokens": 7951368} {"current_steps": 12200, "total_steps": 38160, "loss": 0.3638, "lr": 4.3002864534936444e-05, "epoch": 6.39412997903564, "percentage": 31.97, "elapsed_time": "0:46:23", "remaining_time": "1:38:42", "throughput": 2857.84, "total_tokens": 7954472} {"current_steps": 12205, "total_steps": 38160, "loss": 0.2468, "lr": 4.2994928914560874e-05, "epoch": 6.396750524109015, "percentage": 31.98, "elapsed_time": "0:46:24", "remaining_time": "1:38:41", "throughput": 2857.71, "total_tokens": 7957000} {"current_steps": 12210, "total_steps": 38160, "loss": 0.2237, "lr": 4.298698952985147e-05, "epoch": 6.39937106918239, "percentage": 32.0, "elapsed_time": "0:46:25", "remaining_time": "1:38:39", "throughput": 2857.49, "total_tokens": 7959400} {"current_steps": 12215, "total_steps": 38160, "loss": 0.3323, "lr": 4.297904638246906e-05, "epoch": 6.401991614255765, "percentage": 32.01, "elapsed_time": "0:46:26", "remaining_time": "1:38:38", "throughput": 2857.47, "total_tokens": 7962312} {"current_steps": 12220, "total_steps": 38160, "loss": 0.3312, "lr": 4.297109947407527e-05, "epoch": 6.40461215932914, "percentage": 32.02, "elapsed_time": "0:46:27", "remaining_time": "1:38:37", "throughput": 2857.65, "total_tokens": 7965768} {"current_steps": 12225, "total_steps": 38160, "loss": 0.2283, "lr": 4.2963148806332486e-05, "epoch": 6.4072327044025155, "percentage": 32.04, "elapsed_time": "0:46:29", "remaining_time": "1:38:37", "throughput": 2858.17, "total_tokens": 7972840} {"current_steps": 12230, "total_steps": 38160, "loss": 0.2949, "lr": 4.2955194380903915e-05, "epoch": 6.409853249475891, "percentage": 32.05, "elapsed_time": "0:46:30", "remaining_time": "1:38:36", "throughput": 2857.94, "total_tokens": 7975304} {"current_steps": 12235, "total_steps": 38160, "loss": 0.23, "lr": 4.2947236199453524e-05, "epoch": 6.412473794549266, "percentage": 32.06, "elapsed_time": "0:46:31", "remaining_time": "1:38:35", "throughput": 2857.85, "total_tokens": 7977928} {"current_steps": 12240, "total_steps": 38160, "loss": 0.2683, "lr": 4.2939274263646065e-05, "epoch": 6.415094339622642, "percentage": 32.08, "elapsed_time": "0:46:32", "remaining_time": "1:38:34", "throughput": 2858.11, "total_tokens": 7982120} {"current_steps": 12245, "total_steps": 38160, "loss": 0.2714, "lr": 4.29313085751471e-05, "epoch": 6.417714884696017, "percentage": 32.09, "elapsed_time": "0:46:33", "remaining_time": "1:38:32", "throughput": 2858.09, "total_tokens": 7985032} {"current_steps": 12250, "total_steps": 38160, "loss": 0.2457, "lr": 4.292333913562294e-05, "epoch": 6.420335429769392, "percentage": 32.1, "elapsed_time": "0:46:34", "remaining_time": "1:38:31", "throughput": 2857.8, "total_tokens": 7987272} {"current_steps": 12255, "total_steps": 38160, "loss": 0.3235, "lr": 4.291536594674073e-05, "epoch": 6.422955974842767, "percentage": 32.11, "elapsed_time": "0:46:35", "remaining_time": "1:38:30", "throughput": 2857.78, "total_tokens": 7990152} {"current_steps": 12260, "total_steps": 38160, "loss": 0.3062, "lr": 4.2907389010168344e-05, "epoch": 6.4255765199161425, "percentage": 32.13, "elapsed_time": "0:46:37", "remaining_time": "1:38:28", "throughput": 2857.57, "total_tokens": 7992648} {"current_steps": 12265, "total_steps": 38160, "loss": 0.2359, "lr": 4.2899408327574475e-05, "epoch": 6.428197064989518, "percentage": 32.14, "elapsed_time": "0:46:38", "remaining_time": "1:38:27", "throughput": 2857.59, "total_tokens": 7995880} {"current_steps": 12270, "total_steps": 38160, "loss": 0.2601, "lr": 4.289142390062859e-05, "epoch": 6.430817610062893, "percentage": 32.15, "elapsed_time": "0:46:39", "remaining_time": "1:38:26", "throughput": 2857.38, "total_tokens": 7998312} {"current_steps": 12275, "total_steps": 38160, "loss": 0.2834, "lr": 4.2883435731000946e-05, "epoch": 6.433438155136268, "percentage": 32.17, "elapsed_time": "0:46:40", "remaining_time": "1:38:25", "throughput": 2857.52, "total_tokens": 8001768} {"current_steps": 12280, "total_steps": 38160, "loss": 0.2373, "lr": 4.287544382036256e-05, "epoch": 6.436058700209643, "percentage": 32.18, "elapsed_time": "0:46:41", "remaining_time": "1:38:23", "throughput": 2857.39, "total_tokens": 8004392} {"current_steps": 12285, "total_steps": 38160, "loss": 0.2516, "lr": 4.286744817038527e-05, "epoch": 6.438679245283019, "percentage": 32.19, "elapsed_time": "0:46:42", "remaining_time": "1:38:22", "throughput": 2857.27, "total_tokens": 8006984} {"current_steps": 12290, "total_steps": 38160, "loss": 0.4069, "lr": 4.2859448782741666e-05, "epoch": 6.441299790356394, "percentage": 32.21, "elapsed_time": "0:46:43", "remaining_time": "1:38:21", "throughput": 2857.55, "total_tokens": 8010920} {"current_steps": 12295, "total_steps": 38160, "loss": 0.3448, "lr": 4.2851445659105126e-05, "epoch": 6.44392033542977, "percentage": 32.22, "elapsed_time": "0:46:44", "remaining_time": "1:38:19", "throughput": 2857.53, "total_tokens": 8013800} {"current_steps": 12300, "total_steps": 38160, "loss": 0.2193, "lr": 4.284343880114982e-05, "epoch": 6.446540880503145, "percentage": 32.23, "elapsed_time": "0:46:45", "remaining_time": "1:38:18", "throughput": 2857.5, "total_tokens": 8016616} {"current_steps": 12305, "total_steps": 38160, "loss": 0.2134, "lr": 4.2835428210550676e-05, "epoch": 6.44916142557652, "percentage": 32.25, "elapsed_time": "0:46:46", "remaining_time": "1:38:17", "throughput": 2857.64, "total_tokens": 8020040} {"current_steps": 12310, "total_steps": 38160, "loss": 0.2291, "lr": 4.282741388898344e-05, "epoch": 6.451781970649895, "percentage": 32.26, "elapsed_time": "0:46:47", "remaining_time": "1:38:15", "throughput": 2857.96, "total_tokens": 8024008} {"current_steps": 12315, "total_steps": 38160, "loss": 0.289, "lr": 4.281939583812459e-05, "epoch": 6.45440251572327, "percentage": 32.27, "elapsed_time": "0:46:48", "remaining_time": "1:38:14", "throughput": 2858.14, "total_tokens": 8027528} {"current_steps": 12320, "total_steps": 38160, "loss": 0.3064, "lr": 4.281137405965143e-05, "epoch": 6.4570230607966455, "percentage": 32.29, "elapsed_time": "0:46:49", "remaining_time": "1:38:13", "throughput": 2858.06, "total_tokens": 8030312} {"current_steps": 12325, "total_steps": 38160, "loss": 0.2288, "lr": 4.280334855524203e-05, "epoch": 6.459643605870021, "percentage": 32.3, "elapsed_time": "0:46:50", "remaining_time": "1:38:12", "throughput": 2858.19, "total_tokens": 8034280} {"current_steps": 12330, "total_steps": 38160, "loss": 0.2947, "lr": 4.279531932657521e-05, "epoch": 6.462264150943396, "percentage": 32.31, "elapsed_time": "0:46:52", "remaining_time": "1:38:11", "throughput": 2858.5, "total_tokens": 8038408} {"current_steps": 12335, "total_steps": 38160, "loss": 0.3053, "lr": 4.278728637533062e-05, "epoch": 6.464884696016772, "percentage": 32.32, "elapsed_time": "0:46:53", "remaining_time": "1:38:09", "throughput": 2858.57, "total_tokens": 8041544} {"current_steps": 12340, "total_steps": 38160, "loss": 0.1847, "lr": 4.2779249703188626e-05, "epoch": 6.467505241090147, "percentage": 32.34, "elapsed_time": "0:46:54", "remaining_time": "1:38:08", "throughput": 2858.54, "total_tokens": 8045096} {"current_steps": 12345, "total_steps": 38160, "loss": 0.2726, "lr": 4.277120931183045e-05, "epoch": 6.470125786163522, "percentage": 32.35, "elapsed_time": "0:46:55", "remaining_time": "1:38:07", "throughput": 2858.83, "total_tokens": 8049064} {"current_steps": 12350, "total_steps": 38160, "loss": 0.3007, "lr": 4.276316520293803e-05, "epoch": 6.472746331236897, "percentage": 32.36, "elapsed_time": "0:46:56", "remaining_time": "1:38:06", "throughput": 2858.76, "total_tokens": 8051816} {"current_steps": 12355, "total_steps": 38160, "loss": 0.2642, "lr": 4.27551173781941e-05, "epoch": 6.4753668763102725, "percentage": 32.38, "elapsed_time": "0:46:57", "remaining_time": "1:38:04", "throughput": 2859.01, "total_tokens": 8055528} {"current_steps": 12360, "total_steps": 38160, "loss": 0.2545, "lr": 4.274706583928216e-05, "epoch": 6.477987421383648, "percentage": 32.39, "elapsed_time": "0:46:58", "remaining_time": "1:38:03", "throughput": 2859.03, "total_tokens": 8058472} {"current_steps": 12365, "total_steps": 38160, "loss": 0.4326, "lr": 4.273901058788654e-05, "epoch": 6.480607966457023, "percentage": 32.4, "elapsed_time": "0:46:59", "remaining_time": "1:38:02", "throughput": 2859.1, "total_tokens": 8061608} {"current_steps": 12370, "total_steps": 38160, "loss": 0.303, "lr": 4.2730951625692275e-05, "epoch": 6.483228511530398, "percentage": 32.42, "elapsed_time": "0:47:00", "remaining_time": "1:38:00", "throughput": 2859.11, "total_tokens": 8064648} {"current_steps": 12375, "total_steps": 38160, "loss": 0.3746, "lr": 4.27228889543852e-05, "epoch": 6.485849056603773, "percentage": 32.43, "elapsed_time": "0:47:01", "remaining_time": "1:37:59", "throughput": 2859.0, "total_tokens": 8067496} {"current_steps": 12380, "total_steps": 38160, "loss": 0.24, "lr": 4.2714822575651966e-05, "epoch": 6.488469601677149, "percentage": 32.44, "elapsed_time": "0:47:02", "remaining_time": "1:37:58", "throughput": 2858.72, "total_tokens": 8069864} {"current_steps": 12385, "total_steps": 38160, "loss": 0.3244, "lr": 4.270675249117994e-05, "epoch": 6.491090146750524, "percentage": 32.46, "elapsed_time": "0:47:04", "remaining_time": "1:37:57", "throughput": 2858.68, "total_tokens": 8072936} {"current_steps": 12390, "total_steps": 38160, "loss": 0.3089, "lr": 4.269867870265731e-05, "epoch": 6.4937106918239, "percentage": 32.47, "elapsed_time": "0:47:05", "remaining_time": "1:37:55", "throughput": 2858.56, "total_tokens": 8075784} {"current_steps": 12395, "total_steps": 38160, "loss": 0.3411, "lr": 4.269060121177301e-05, "epoch": 6.496331236897275, "percentage": 32.48, "elapsed_time": "0:47:06", "remaining_time": "1:37:54", "throughput": 2858.38, "total_tokens": 8078280} {"current_steps": 12400, "total_steps": 38160, "loss": 0.2094, "lr": 4.2682520020216764e-05, "epoch": 6.49895178197065, "percentage": 32.49, "elapsed_time": "0:47:07", "remaining_time": "1:37:53", "throughput": 2858.57, "total_tokens": 8081992} {"current_steps": 12405, "total_steps": 38160, "loss": 0.2697, "lr": 4.267443512967906e-05, "epoch": 6.501572327044025, "percentage": 32.51, "elapsed_time": "0:47:08", "remaining_time": "1:37:52", "throughput": 2858.73, "total_tokens": 8085672} {"current_steps": 12410, "total_steps": 38160, "loss": 0.2394, "lr": 4.2666346541851165e-05, "epoch": 6.5041928721174, "percentage": 32.52, "elapsed_time": "0:47:09", "remaining_time": "1:37:50", "throughput": 2858.87, "total_tokens": 8089000} {"current_steps": 12415, "total_steps": 38160, "loss": 0.2355, "lr": 4.265825425842512e-05, "epoch": 6.506813417190775, "percentage": 32.53, "elapsed_time": "0:47:10", "remaining_time": "1:37:49", "throughput": 2858.95, "total_tokens": 8092168} {"current_steps": 12420, "total_steps": 38160, "loss": 0.3175, "lr": 4.265015828109375e-05, "epoch": 6.509433962264151, "percentage": 32.55, "elapsed_time": "0:47:11", "remaining_time": "1:37:48", "throughput": 2858.74, "total_tokens": 8094728} {"current_steps": 12425, "total_steps": 38160, "loss": 0.3051, "lr": 4.264205861155063e-05, "epoch": 6.512054507337526, "percentage": 32.56, "elapsed_time": "0:47:12", "remaining_time": "1:37:47", "throughput": 2858.85, "total_tokens": 8098088} {"current_steps": 12430, "total_steps": 38160, "loss": 0.3324, "lr": 4.263395525149011e-05, "epoch": 6.514675052410902, "percentage": 32.57, "elapsed_time": "0:47:13", "remaining_time": "1:37:45", "throughput": 2858.8, "total_tokens": 8100904} {"current_steps": 12435, "total_steps": 38160, "loss": 0.2336, "lr": 4.262584820260734e-05, "epoch": 6.517295597484277, "percentage": 32.59, "elapsed_time": "0:47:14", "remaining_time": "1:37:44", "throughput": 2858.95, "total_tokens": 8104264} {"current_steps": 12440, "total_steps": 38160, "loss": 0.2483, "lr": 4.261773746659821e-05, "epoch": 6.519916142557652, "percentage": 32.6, "elapsed_time": "0:47:15", "remaining_time": "1:37:42", "throughput": 2858.93, "total_tokens": 8107144} {"current_steps": 12445, "total_steps": 38160, "loss": 0.2234, "lr": 4.260962304515939e-05, "epoch": 6.522536687631027, "percentage": 32.61, "elapsed_time": "0:47:17", "remaining_time": "1:37:42", "throughput": 2859.09, "total_tokens": 8111304} {"current_steps": 12450, "total_steps": 38160, "loss": 0.3023, "lr": 4.2601504939988335e-05, "epoch": 6.5251572327044025, "percentage": 32.63, "elapsed_time": "0:47:18", "remaining_time": "1:37:40", "throughput": 2858.97, "total_tokens": 8114056} {"current_steps": 12455, "total_steps": 38160, "loss": 0.3511, "lr": 4.259338315278325e-05, "epoch": 6.527777777777778, "percentage": 32.64, "elapsed_time": "0:47:19", "remaining_time": "1:37:39", "throughput": 2858.91, "total_tokens": 8116808} {"current_steps": 12460, "total_steps": 38160, "loss": 0.2647, "lr": 4.258525768524313e-05, "epoch": 6.530398322851153, "percentage": 32.65, "elapsed_time": "0:47:20", "remaining_time": "1:37:38", "throughput": 2858.77, "total_tokens": 8119496} {"current_steps": 12465, "total_steps": 38160, "loss": 0.2927, "lr": 4.2577128539067725e-05, "epoch": 6.533018867924528, "percentage": 32.67, "elapsed_time": "0:47:21", "remaining_time": "1:37:36", "throughput": 2858.8, "total_tokens": 8122728} {"current_steps": 12470, "total_steps": 38160, "loss": 0.3815, "lr": 4.256899571595756e-05, "epoch": 6.535639412997903, "percentage": 32.68, "elapsed_time": "0:47:22", "remaining_time": "1:37:35", "throughput": 2859.05, "total_tokens": 8126504} {"current_steps": 12475, "total_steps": 38160, "loss": 0.352, "lr": 4.256085921761393e-05, "epoch": 6.538259958071279, "percentage": 32.69, "elapsed_time": "0:47:23", "remaining_time": "1:37:34", "throughput": 2858.83, "total_tokens": 8128776} {"current_steps": 12480, "total_steps": 38160, "loss": 0.3517, "lr": 4.25527190457389e-05, "epoch": 6.540880503144654, "percentage": 32.7, "elapsed_time": "0:47:24", "remaining_time": "1:37:32", "throughput": 2858.84, "total_tokens": 8131720} {"current_steps": 12485, "total_steps": 38160, "loss": 0.3279, "lr": 4.2544575202035285e-05, "epoch": 6.54350104821803, "percentage": 32.72, "elapsed_time": "0:47:25", "remaining_time": "1:37:31", "throughput": 2859.01, "total_tokens": 8135624} {"current_steps": 12490, "total_steps": 38160, "loss": 0.2536, "lr": 4.253642768820671e-05, "epoch": 6.546121593291405, "percentage": 32.73, "elapsed_time": "0:47:26", "remaining_time": "1:37:30", "throughput": 2859.03, "total_tokens": 8138632} {"current_steps": 12495, "total_steps": 38160, "loss": 0.2908, "lr": 4.252827650595752e-05, "epoch": 6.54874213836478, "percentage": 32.74, "elapsed_time": "0:47:27", "remaining_time": "1:37:29", "throughput": 2859.21, "total_tokens": 8142184} {"current_steps": 12500, "total_steps": 38160, "loss": 0.305, "lr": 4.252012165699286e-05, "epoch": 6.551362683438155, "percentage": 32.76, "elapsed_time": "0:47:28", "remaining_time": "1:37:28", "throughput": 2859.66, "total_tokens": 8146792} {"current_steps": 12505, "total_steps": 38160, "loss": 0.2019, "lr": 4.2511963143018634e-05, "epoch": 6.55398322851153, "percentage": 32.77, "elapsed_time": "0:47:29", "remaining_time": "1:37:26", "throughput": 2859.85, "total_tokens": 8150504} {"current_steps": 12510, "total_steps": 38160, "loss": 0.2865, "lr": 4.25038009657415e-05, "epoch": 6.556603773584905, "percentage": 32.78, "elapsed_time": "0:47:30", "remaining_time": "1:37:25", "throughput": 2859.7, "total_tokens": 8153000} {"current_steps": 12515, "total_steps": 38160, "loss": 0.1911, "lr": 4.24956351268689e-05, "epoch": 6.559224318658281, "percentage": 32.8, "elapsed_time": "0:47:32", "remaining_time": "1:37:24", "throughput": 2859.59, "total_tokens": 8155720} {"current_steps": 12520, "total_steps": 38160, "loss": 0.2103, "lr": 4.2487465628109036e-05, "epoch": 6.561844863731656, "percentage": 32.81, "elapsed_time": "0:47:33", "remaining_time": "1:37:22", "throughput": 2859.83, "total_tokens": 8159400} {"current_steps": 12525, "total_steps": 38160, "loss": 0.1856, "lr": 4.247929247117087e-05, "epoch": 6.564465408805032, "percentage": 32.82, "elapsed_time": "0:47:34", "remaining_time": "1:37:21", "throughput": 2859.99, "total_tokens": 8162952} {"current_steps": 12530, "total_steps": 38160, "loss": 0.2676, "lr": 4.247111565776413e-05, "epoch": 6.567085953878407, "percentage": 32.84, "elapsed_time": "0:47:35", "remaining_time": "1:37:20", "throughput": 2860.14, "total_tokens": 8166376} {"current_steps": 12535, "total_steps": 38160, "loss": 0.3302, "lr": 4.246293518959932e-05, "epoch": 6.569706498951782, "percentage": 32.85, "elapsed_time": "0:47:36", "remaining_time": "1:37:19", "throughput": 2860.03, "total_tokens": 8169064} {"current_steps": 12540, "total_steps": 38160, "loss": 0.3346, "lr": 4.245475106838769e-05, "epoch": 6.572327044025157, "percentage": 32.86, "elapsed_time": "0:47:37", "remaining_time": "1:37:17", "throughput": 2859.95, "total_tokens": 8171976} {"current_steps": 12545, "total_steps": 38160, "loss": 0.2664, "lr": 4.2446563295841266e-05, "epoch": 6.5749475890985325, "percentage": 32.87, "elapsed_time": "0:47:38", "remaining_time": "1:37:16", "throughput": 2860.17, "total_tokens": 8176200} {"current_steps": 12550, "total_steps": 38160, "loss": 0.291, "lr": 4.243837187367285e-05, "epoch": 6.577568134171908, "percentage": 32.89, "elapsed_time": "0:47:39", "remaining_time": "1:37:15", "throughput": 2860.16, "total_tokens": 8179368} {"current_steps": 12555, "total_steps": 38160, "loss": 0.2135, "lr": 4.2430176803595987e-05, "epoch": 6.580188679245283, "percentage": 32.9, "elapsed_time": "0:47:40", "remaining_time": "1:37:14", "throughput": 2860.08, "total_tokens": 8182248} {"current_steps": 12560, "total_steps": 38160, "loss": 0.3276, "lr": 4.2421978087324985e-05, "epoch": 6.582809224318658, "percentage": 32.91, "elapsed_time": "0:47:41", "remaining_time": "1:37:13", "throughput": 2859.91, "total_tokens": 8184776} {"current_steps": 12565, "total_steps": 38160, "loss": 0.2167, "lr": 4.241377572657493e-05, "epoch": 6.585429769392033, "percentage": 32.93, "elapsed_time": "0:47:42", "remaining_time": "1:37:11", "throughput": 2859.94, "total_tokens": 8187976} {"current_steps": 12570, "total_steps": 38160, "loss": 0.2628, "lr": 4.2405569723061654e-05, "epoch": 6.588050314465409, "percentage": 32.94, "elapsed_time": "0:47:44", "remaining_time": "1:37:10", "throughput": 2859.95, "total_tokens": 8190984} {"current_steps": 12575, "total_steps": 38160, "loss": 0.2283, "lr": 4.239736007850178e-05, "epoch": 6.590670859538784, "percentage": 32.95, "elapsed_time": "0:47:45", "remaining_time": "1:37:09", "throughput": 2860.17, "total_tokens": 8194568} {"current_steps": 12580, "total_steps": 38160, "loss": 0.3383, "lr": 4.238914679461264e-05, "epoch": 6.59329140461216, "percentage": 32.97, "elapsed_time": "0:47:46", "remaining_time": "1:37:07", "throughput": 2860.12, "total_tokens": 8197512} {"current_steps": 12585, "total_steps": 38160, "loss": 0.2475, "lr": 4.2380929873112386e-05, "epoch": 6.595911949685535, "percentage": 32.98, "elapsed_time": "0:47:47", "remaining_time": "1:37:06", "throughput": 2860.27, "total_tokens": 8201128} {"current_steps": 12590, "total_steps": 38160, "loss": 0.1674, "lr": 4.2372709315719896e-05, "epoch": 6.59853249475891, "percentage": 32.99, "elapsed_time": "0:47:48", "remaining_time": "1:37:05", "throughput": 2860.36, "total_tokens": 8204392} {"current_steps": 12595, "total_steps": 38160, "loss": 0.2608, "lr": 4.2364485124154806e-05, "epoch": 6.601153039832285, "percentage": 33.01, "elapsed_time": "0:47:49", "remaining_time": "1:37:04", "throughput": 2860.17, "total_tokens": 8206952} {"current_steps": 12600, "total_steps": 38160, "loss": 0.1977, "lr": 4.235625730013754e-05, "epoch": 6.60377358490566, "percentage": 33.02, "elapsed_time": "0:47:50", "remaining_time": "1:37:02", "throughput": 2860.1, "total_tokens": 8209768} {"current_steps": 12605, "total_steps": 38160, "loss": 0.2855, "lr": 4.234802584538926e-05, "epoch": 6.606394129979035, "percentage": 33.03, "elapsed_time": "0:47:52", "remaining_time": "1:37:03", "throughput": 2860.61, "total_tokens": 8216680} {"current_steps": 12610, "total_steps": 38160, "loss": 0.2606, "lr": 4.2339790761631884e-05, "epoch": 6.609014675052411, "percentage": 33.05, "elapsed_time": "0:47:53", "remaining_time": "1:37:02", "throughput": 2860.82, "total_tokens": 8220552} {"current_steps": 12615, "total_steps": 38160, "loss": 0.3028, "lr": 4.233155205058811e-05, "epoch": 6.611635220125786, "percentage": 33.06, "elapsed_time": "0:47:54", "remaining_time": "1:37:01", "throughput": 2861.24, "total_tokens": 8225064} {"current_steps": 12620, "total_steps": 38160, "loss": 0.3221, "lr": 4.232330971398137e-05, "epoch": 6.614255765199162, "percentage": 33.07, "elapsed_time": "0:47:55", "remaining_time": "1:36:59", "throughput": 2861.28, "total_tokens": 8228168} {"current_steps": 12625, "total_steps": 38160, "loss": 0.2227, "lr": 4.2315063753535875e-05, "epoch": 6.616876310272537, "percentage": 33.08, "elapsed_time": "0:47:56", "remaining_time": "1:36:58", "throughput": 2861.48, "total_tokens": 8231944} {"current_steps": 12630, "total_steps": 38160, "loss": 0.2899, "lr": 4.230681417097658e-05, "epoch": 6.619496855345912, "percentage": 33.1, "elapsed_time": "0:47:57", "remaining_time": "1:36:57", "throughput": 2861.67, "total_tokens": 8235848} {"current_steps": 12635, "total_steps": 38160, "loss": 0.3829, "lr": 4.229856096802921e-05, "epoch": 6.622117400419287, "percentage": 33.11, "elapsed_time": "0:47:59", "remaining_time": "1:36:56", "throughput": 2861.66, "total_tokens": 8238792} {"current_steps": 12640, "total_steps": 38160, "loss": 0.2778, "lr": 4.229030414642024e-05, "epoch": 6.6247379454926625, "percentage": 33.12, "elapsed_time": "0:48:00", "remaining_time": "1:36:54", "throughput": 2861.76, "total_tokens": 8242088} {"current_steps": 12645, "total_steps": 38160, "loss": 0.3159, "lr": 4.2282043707876896e-05, "epoch": 6.627358490566038, "percentage": 33.14, "elapsed_time": "0:48:01", "remaining_time": "1:36:53", "throughput": 2861.57, "total_tokens": 8244616} {"current_steps": 12650, "total_steps": 38160, "loss": 0.2363, "lr": 4.2273779654127175e-05, "epoch": 6.629979035639413, "percentage": 33.15, "elapsed_time": "0:48:02", "remaining_time": "1:36:52", "throughput": 2861.67, "total_tokens": 8247912} {"current_steps": 12655, "total_steps": 38160, "loss": 0.3073, "lr": 4.226551198689982e-05, "epoch": 6.632599580712788, "percentage": 33.16, "elapsed_time": "0:48:03", "remaining_time": "1:36:51", "throughput": 2861.87, "total_tokens": 8251816} {"current_steps": 12660, "total_steps": 38160, "loss": 0.3228, "lr": 4.225724070792434e-05, "epoch": 6.635220125786163, "percentage": 33.18, "elapsed_time": "0:48:04", "remaining_time": "1:36:49", "throughput": 2862.03, "total_tokens": 8255432} {"current_steps": 12665, "total_steps": 38160, "loss": 0.205, "lr": 4.2248965818930975e-05, "epoch": 6.637840670859539, "percentage": 33.19, "elapsed_time": "0:48:05", "remaining_time": "1:36:48", "throughput": 2862.02, "total_tokens": 8258824} {"current_steps": 12670, "total_steps": 38160, "loss": 0.3028, "lr": 4.224068732165075e-05, "epoch": 6.640461215932914, "percentage": 33.2, "elapsed_time": "0:48:06", "remaining_time": "1:36:47", "throughput": 2862.34, "total_tokens": 8262888} {"current_steps": 12675, "total_steps": 38160, "loss": 0.2064, "lr": 4.223240521781543e-05, "epoch": 6.6430817610062896, "percentage": 33.22, "elapsed_time": "0:48:07", "remaining_time": "1:36:46", "throughput": 2862.56, "total_tokens": 8266568} {"current_steps": 12680, "total_steps": 38160, "loss": 0.3412, "lr": 4.2224119509157535e-05, "epoch": 6.645702306079665, "percentage": 33.23, "elapsed_time": "0:48:08", "remaining_time": "1:36:45", "throughput": 2862.6, "total_tokens": 8269800} {"current_steps": 12685, "total_steps": 38160, "loss": 0.2452, "lr": 4.221583019741033e-05, "epoch": 6.64832285115304, "percentage": 33.24, "elapsed_time": "0:48:09", "remaining_time": "1:36:43", "throughput": 2862.64, "total_tokens": 8272936} {"current_steps": 12690, "total_steps": 38160, "loss": 0.2739, "lr": 4.2207537284307876e-05, "epoch": 6.650943396226415, "percentage": 33.25, "elapsed_time": "0:48:11", "remaining_time": "1:36:42", "throughput": 2862.68, "total_tokens": 8276104} {"current_steps": 12695, "total_steps": 38160, "loss": 0.2265, "lr": 4.219924077158493e-05, "epoch": 6.65356394129979, "percentage": 33.27, "elapsed_time": "0:48:12", "remaining_time": "1:36:41", "throughput": 2862.54, "total_tokens": 8278728} {"current_steps": 12700, "total_steps": 38160, "loss": 0.253, "lr": 4.219094066097703e-05, "epoch": 6.656184486373165, "percentage": 33.28, "elapsed_time": "0:48:13", "remaining_time": "1:36:40", "throughput": 2862.7, "total_tokens": 8282312} {"current_steps": 12705, "total_steps": 38160, "loss": 0.3002, "lr": 4.218263695422047e-05, "epoch": 6.658805031446541, "percentage": 33.29, "elapsed_time": "0:48:14", "remaining_time": "1:36:38", "throughput": 2862.87, "total_tokens": 8285800} {"current_steps": 12710, "total_steps": 38160, "loss": 0.3345, "lr": 4.217432965305229e-05, "epoch": 6.661425576519916, "percentage": 33.31, "elapsed_time": "0:48:15", "remaining_time": "1:36:37", "throughput": 2862.84, "total_tokens": 8288648} {"current_steps": 12715, "total_steps": 38160, "loss": 0.2286, "lr": 4.2166018759210286e-05, "epoch": 6.664046121593291, "percentage": 33.32, "elapsed_time": "0:48:16", "remaining_time": "1:36:35", "throughput": 2862.87, "total_tokens": 8291688} {"current_steps": 12720, "total_steps": 38160, "loss": 0.301, "lr": 4.215770427443299e-05, "epoch": 6.666666666666667, "percentage": 33.33, "elapsed_time": "0:48:17", "remaining_time": "1:36:34", "throughput": 2863.1, "total_tokens": 8295400} {"current_steps": 12725, "total_steps": 38160, "loss": 0.2812, "lr": 4.214938620045971e-05, "epoch": 6.669287211740042, "percentage": 33.35, "elapsed_time": "0:48:18", "remaining_time": "1:36:33", "throughput": 2862.86, "total_tokens": 8297704} {"current_steps": 12730, "total_steps": 38160, "loss": 0.3792, "lr": 4.214106453903048e-05, "epoch": 6.671907756813417, "percentage": 33.36, "elapsed_time": "0:48:19", "remaining_time": "1:36:32", "throughput": 2862.9, "total_tokens": 8300808} {"current_steps": 12735, "total_steps": 38160, "loss": 0.3534, "lr": 4.2132739291886114e-05, "epoch": 6.6745283018867925, "percentage": 33.37, "elapsed_time": "0:48:20", "remaining_time": "1:36:30", "throughput": 2862.89, "total_tokens": 8304104} {"current_steps": 12740, "total_steps": 38160, "loss": 0.3173, "lr": 4.212441046076814e-05, "epoch": 6.677148846960168, "percentage": 33.39, "elapsed_time": "0:48:21", "remaining_time": "1:36:29", "throughput": 2863.08, "total_tokens": 8307784} {"current_steps": 12745, "total_steps": 38160, "loss": 0.2519, "lr": 4.211607804741887e-05, "epoch": 6.679769392033543, "percentage": 33.4, "elapsed_time": "0:48:22", "remaining_time": "1:36:28", "throughput": 2863.34, "total_tokens": 8311848} {"current_steps": 12750, "total_steps": 38160, "loss": 0.255, "lr": 4.2107742053581344e-05, "epoch": 6.682389937106918, "percentage": 33.41, "elapsed_time": "0:48:23", "remaining_time": "1:36:27", "throughput": 2863.52, "total_tokens": 8315272} {"current_steps": 12755, "total_steps": 38160, "loss": 0.2916, "lr": 4.209940248099935e-05, "epoch": 6.685010482180293, "percentage": 33.43, "elapsed_time": "0:48:24", "remaining_time": "1:36:25", "throughput": 2863.57, "total_tokens": 8318376} {"current_steps": 12760, "total_steps": 38160, "loss": 0.2365, "lr": 4.2091059331417445e-05, "epoch": 6.687631027253669, "percentage": 33.44, "elapsed_time": "0:48:26", "remaining_time": "1:36:24", "throughput": 2863.81, "total_tokens": 8322248} {"current_steps": 12765, "total_steps": 38160, "loss": 0.1782, "lr": 4.208271260658091e-05, "epoch": 6.690251572327044, "percentage": 33.45, "elapsed_time": "0:48:27", "remaining_time": "1:36:23", "throughput": 2864.03, "total_tokens": 8326056} {"current_steps": 12770, "total_steps": 38160, "loss": 0.3362, "lr": 4.2074362308235785e-05, "epoch": 6.6928721174004195, "percentage": 33.46, "elapsed_time": "0:48:28", "remaining_time": "1:36:22", "throughput": 2864.17, "total_tokens": 8329608} {"current_steps": 12775, "total_steps": 38160, "loss": 0.2389, "lr": 4.206600843812886e-05, "epoch": 6.695492662473795, "percentage": 33.48, "elapsed_time": "0:48:29", "remaining_time": "1:36:20", "throughput": 2864.01, "total_tokens": 8332072} {"current_steps": 12780, "total_steps": 38160, "loss": 0.2847, "lr": 4.205765099800767e-05, "epoch": 6.69811320754717, "percentage": 33.49, "elapsed_time": "0:48:30", "remaining_time": "1:36:19", "throughput": 2863.91, "total_tokens": 8334760} {"current_steps": 12785, "total_steps": 38160, "loss": 0.2125, "lr": 4.204928998962049e-05, "epoch": 6.700733752620545, "percentage": 33.5, "elapsed_time": "0:48:31", "remaining_time": "1:36:18", "throughput": 2863.88, "total_tokens": 8337736} {"current_steps": 12790, "total_steps": 38160, "loss": 0.2106, "lr": 4.204092541471636e-05, "epoch": 6.70335429769392, "percentage": 33.52, "elapsed_time": "0:48:32", "remaining_time": "1:36:16", "throughput": 2863.82, "total_tokens": 8340488} {"current_steps": 12795, "total_steps": 38160, "loss": 0.2982, "lr": 4.203255727504504e-05, "epoch": 6.705974842767295, "percentage": 33.53, "elapsed_time": "0:48:33", "remaining_time": "1:36:15", "throughput": 2863.72, "total_tokens": 8343176} {"current_steps": 12800, "total_steps": 38160, "loss": 0.3286, "lr": 4.202418557235706e-05, "epoch": 6.7085953878406706, "percentage": 33.54, "elapsed_time": "0:48:34", "remaining_time": "1:36:14", "throughput": 2863.79, "total_tokens": 8346376} {"current_steps": 12805, "total_steps": 38160, "loss": 0.2493, "lr": 4.201581030840368e-05, "epoch": 6.711215932914046, "percentage": 33.56, "elapsed_time": "0:48:35", "remaining_time": "1:36:13", "throughput": 2863.83, "total_tokens": 8349672} {"current_steps": 12810, "total_steps": 38160, "loss": 0.2627, "lr": 4.200743148493691e-05, "epoch": 6.713836477987421, "percentage": 33.57, "elapsed_time": "0:48:36", "remaining_time": "1:36:11", "throughput": 2863.66, "total_tokens": 8352232} {"current_steps": 12815, "total_steps": 38160, "loss": 0.2176, "lr": 4.199904910370951e-05, "epoch": 6.716457023060797, "percentage": 33.58, "elapsed_time": "0:48:37", "remaining_time": "1:36:10", "throughput": 2863.71, "total_tokens": 8355592} {"current_steps": 12820, "total_steps": 38160, "loss": 0.1844, "lr": 4.1990663166474964e-05, "epoch": 6.719077568134172, "percentage": 33.6, "elapsed_time": "0:48:38", "remaining_time": "1:36:09", "throughput": 2863.4, "total_tokens": 8357736} {"current_steps": 12825, "total_steps": 38160, "loss": 0.2092, "lr": 4.1982273674987524e-05, "epoch": 6.721698113207547, "percentage": 33.61, "elapsed_time": "0:48:40", "remaining_time": "1:36:08", "throughput": 2863.57, "total_tokens": 8362568} {"current_steps": 12830, "total_steps": 38160, "loss": 0.3137, "lr": 4.197388063100218e-05, "epoch": 6.7243186582809225, "percentage": 33.62, "elapsed_time": "0:48:41", "remaining_time": "1:36:07", "throughput": 2863.72, "total_tokens": 8366152} {"current_steps": 12835, "total_steps": 38160, "loss": 0.248, "lr": 4.196548403627465e-05, "epoch": 6.726939203354298, "percentage": 33.63, "elapsed_time": "0:48:42", "remaining_time": "1:36:06", "throughput": 2863.5, "total_tokens": 8368456} {"current_steps": 12840, "total_steps": 38160, "loss": 0.2949, "lr": 4.195708389256142e-05, "epoch": 6.729559748427673, "percentage": 33.65, "elapsed_time": "0:48:43", "remaining_time": "1:36:05", "throughput": 2863.49, "total_tokens": 8371560} {"current_steps": 12845, "total_steps": 38160, "loss": 0.2416, "lr": 4.194868020161969e-05, "epoch": 6.732180293501048, "percentage": 33.66, "elapsed_time": "0:48:44", "remaining_time": "1:36:03", "throughput": 2863.56, "total_tokens": 8374792} {"current_steps": 12850, "total_steps": 38160, "loss": 0.2761, "lr": 4.1940272965207425e-05, "epoch": 6.734800838574423, "percentage": 33.67, "elapsed_time": "0:48:45", "remaining_time": "1:36:02", "throughput": 2863.58, "total_tokens": 8377832} {"current_steps": 12855, "total_steps": 38160, "loss": 0.3178, "lr": 4.1931862185083326e-05, "epoch": 6.737421383647799, "percentage": 33.69, "elapsed_time": "0:48:46", "remaining_time": "1:36:01", "throughput": 2863.58, "total_tokens": 8380872} {"current_steps": 12860, "total_steps": 38160, "loss": 0.3055, "lr": 4.192344786300682e-05, "epoch": 6.740041928721174, "percentage": 33.7, "elapsed_time": "0:48:47", "remaining_time": "1:36:00", "throughput": 2863.65, "total_tokens": 8384264} {"current_steps": 12865, "total_steps": 38160, "loss": 0.3096, "lr": 4.19150300007381e-05, "epoch": 6.7426624737945495, "percentage": 33.71, "elapsed_time": "0:48:49", "remaining_time": "1:35:59", "throughput": 2864.08, "total_tokens": 8389064} {"current_steps": 12870, "total_steps": 38160, "loss": 0.3341, "lr": 4.190660860003806e-05, "epoch": 6.745283018867925, "percentage": 33.73, "elapsed_time": "0:48:50", "remaining_time": "1:35:57", "throughput": 2864.03, "total_tokens": 8391976} {"current_steps": 12875, "total_steps": 38160, "loss": 0.1935, "lr": 4.189818366266841e-05, "epoch": 6.7479035639413, "percentage": 33.74, "elapsed_time": "0:48:51", "remaining_time": "1:35:56", "throughput": 2864.09, "total_tokens": 8395176} {"current_steps": 12880, "total_steps": 38160, "loss": 0.3019, "lr": 4.188975519039151e-05, "epoch": 6.750524109014675, "percentage": 33.75, "elapsed_time": "0:48:52", "remaining_time": "1:35:55", "throughput": 2864.11, "total_tokens": 8398216} {"current_steps": 12885, "total_steps": 38160, "loss": 0.3194, "lr": 4.188132318497051e-05, "epoch": 6.75314465408805, "percentage": 33.77, "elapsed_time": "0:48:53", "remaining_time": "1:35:54", "throughput": 2864.22, "total_tokens": 8402120} {"current_steps": 12890, "total_steps": 38160, "loss": 0.3275, "lr": 4.1872887648169304e-05, "epoch": 6.755765199161425, "percentage": 33.78, "elapsed_time": "0:48:54", "remaining_time": "1:35:53", "throughput": 2864.36, "total_tokens": 8405736} {"current_steps": 12895, "total_steps": 38160, "loss": 0.2645, "lr": 4.186444858175248e-05, "epoch": 6.7583857442348005, "percentage": 33.79, "elapsed_time": "0:48:55", "remaining_time": "1:35:51", "throughput": 2864.38, "total_tokens": 8408808} {"current_steps": 12900, "total_steps": 38160, "loss": 0.2001, "lr": 4.1856005987485424e-05, "epoch": 6.761006289308176, "percentage": 33.81, "elapsed_time": "0:48:56", "remaining_time": "1:35:50", "throughput": 2864.24, "total_tokens": 8411400} {"current_steps": 12905, "total_steps": 38160, "loss": 0.2015, "lr": 4.1847559867134215e-05, "epoch": 6.763626834381551, "percentage": 33.82, "elapsed_time": "0:48:57", "remaining_time": "1:35:49", "throughput": 2864.27, "total_tokens": 8414632} {"current_steps": 12910, "total_steps": 38160, "loss": 0.2764, "lr": 4.1839110222465693e-05, "epoch": 6.766247379454927, "percentage": 33.83, "elapsed_time": "0:48:58", "remaining_time": "1:35:47", "throughput": 2864.12, "total_tokens": 8417256} {"current_steps": 12915, "total_steps": 38160, "loss": 0.2552, "lr": 4.183065705524742e-05, "epoch": 6.768867924528302, "percentage": 33.84, "elapsed_time": "0:48:59", "remaining_time": "1:35:46", "throughput": 2864.2, "total_tokens": 8420584} {"current_steps": 12920, "total_steps": 38160, "loss": 0.3421, "lr": 4.1822200367247696e-05, "epoch": 6.771488469601677, "percentage": 33.86, "elapsed_time": "0:49:00", "remaining_time": "1:35:45", "throughput": 2864.31, "total_tokens": 8423912} {"current_steps": 12925, "total_steps": 38160, "loss": 0.2434, "lr": 4.181374016023559e-05, "epoch": 6.774109014675052, "percentage": 33.87, "elapsed_time": "0:49:02", "remaining_time": "1:35:44", "throughput": 2864.45, "total_tokens": 8427368} {"current_steps": 12930, "total_steps": 38160, "loss": 0.2819, "lr": 4.1805276435980854e-05, "epoch": 6.776729559748428, "percentage": 33.88, "elapsed_time": "0:49:03", "remaining_time": "1:35:42", "throughput": 2864.73, "total_tokens": 8431176} {"current_steps": 12935, "total_steps": 38160, "loss": 0.2668, "lr": 4.1796809196254014e-05, "epoch": 6.779350104821803, "percentage": 33.9, "elapsed_time": "0:49:04", "remaining_time": "1:35:41", "throughput": 2864.55, "total_tokens": 8433768} {"current_steps": 12940, "total_steps": 38160, "loss": 0.2404, "lr": 4.178833844282632e-05, "epoch": 6.781970649895178, "percentage": 33.91, "elapsed_time": "0:49:05", "remaining_time": "1:35:40", "throughput": 2864.73, "total_tokens": 8437384} {"current_steps": 12945, "total_steps": 38160, "loss": 0.2496, "lr": 4.177986417746976e-05, "epoch": 6.784591194968553, "percentage": 33.92, "elapsed_time": "0:49:06", "remaining_time": "1:35:39", "throughput": 2865.0, "total_tokens": 8441192} {"current_steps": 12950, "total_steps": 38160, "loss": 0.4044, "lr": 4.177138640195704e-05, "epoch": 6.787211740041929, "percentage": 33.94, "elapsed_time": "0:49:07", "remaining_time": "1:35:38", "throughput": 2865.51, "total_tokens": 8446504} {"current_steps": 12955, "total_steps": 38160, "loss": 0.1973, "lr": 4.176290511806162e-05, "epoch": 6.789832285115304, "percentage": 33.95, "elapsed_time": "0:49:08", "remaining_time": "1:35:37", "throughput": 2865.41, "total_tokens": 8449384} {"current_steps": 12960, "total_steps": 38160, "loss": 0.2604, "lr": 4.1754420327557706e-05, "epoch": 6.7924528301886795, "percentage": 33.96, "elapsed_time": "0:49:09", "remaining_time": "1:35:35", "throughput": 2865.35, "total_tokens": 8452456} {"current_steps": 12965, "total_steps": 38160, "loss": 0.3319, "lr": 4.1745932032220195e-05, "epoch": 6.795073375262055, "percentage": 33.98, "elapsed_time": "0:49:11", "remaining_time": "1:35:34", "throughput": 2865.68, "total_tokens": 8457000} {"current_steps": 12970, "total_steps": 38160, "loss": 0.2601, "lr": 4.173744023382474e-05, "epoch": 6.79769392033543, "percentage": 33.99, "elapsed_time": "0:49:12", "remaining_time": "1:35:34", "throughput": 2865.83, "total_tokens": 8461576} {"current_steps": 12975, "total_steps": 38160, "loss": 0.2767, "lr": 4.172894493414776e-05, "epoch": 6.800314465408805, "percentage": 34.0, "elapsed_time": "0:49:13", "remaining_time": "1:35:33", "throughput": 2865.79, "total_tokens": 8464712} {"current_steps": 12980, "total_steps": 38160, "loss": 0.209, "lr": 4.172044613496634e-05, "epoch": 6.80293501048218, "percentage": 34.01, "elapsed_time": "0:49:14", "remaining_time": "1:35:31", "throughput": 2865.85, "total_tokens": 8467880} {"current_steps": 12985, "total_steps": 38160, "loss": 0.2087, "lr": 4.171194383805835e-05, "epoch": 6.805555555555555, "percentage": 34.03, "elapsed_time": "0:49:15", "remaining_time": "1:35:30", "throughput": 2865.91, "total_tokens": 8471208} {"current_steps": 12990, "total_steps": 38160, "loss": 0.2497, "lr": 4.170343804520237e-05, "epoch": 6.8081761006289305, "percentage": 34.04, "elapsed_time": "0:49:16", "remaining_time": "1:35:29", "throughput": 2865.89, "total_tokens": 8474248} {"current_steps": 12995, "total_steps": 38160, "loss": 0.2552, "lr": 4.169492875817771e-05, "epoch": 6.810796645702306, "percentage": 34.05, "elapsed_time": "0:49:18", "remaining_time": "1:35:28", "throughput": 2865.8, "total_tokens": 8477064} {"current_steps": 13000, "total_steps": 38160, "loss": 0.2268, "lr": 4.1686415978764415e-05, "epoch": 6.813417190775681, "percentage": 34.07, "elapsed_time": "0:49:19", "remaining_time": "1:35:26", "throughput": 2865.62, "total_tokens": 8479528} {"current_steps": 13005, "total_steps": 38160, "loss": 0.1833, "lr": 4.167789970874327e-05, "epoch": 6.816037735849057, "percentage": 34.08, "elapsed_time": "0:49:20", "remaining_time": "1:35:25", "throughput": 2865.61, "total_tokens": 8482856} {"current_steps": 13010, "total_steps": 38160, "loss": 0.3118, "lr": 4.166937994989578e-05, "epoch": 6.818658280922432, "percentage": 34.09, "elapsed_time": "0:49:21", "remaining_time": "1:35:24", "throughput": 2865.64, "total_tokens": 8486312} {"current_steps": 13015, "total_steps": 38160, "loss": 0.2886, "lr": 4.166085670400418e-05, "epoch": 6.821278825995807, "percentage": 34.11, "elapsed_time": "0:49:22", "remaining_time": "1:35:23", "throughput": 2865.55, "total_tokens": 8489096} {"current_steps": 13020, "total_steps": 38160, "loss": 0.3123, "lr": 4.165232997285143e-05, "epoch": 6.823899371069182, "percentage": 34.12, "elapsed_time": "0:49:23", "remaining_time": "1:35:22", "throughput": 2865.8, "total_tokens": 8493448} {"current_steps": 13025, "total_steps": 38160, "loss": 0.1927, "lr": 4.164379975822124e-05, "epoch": 6.826519916142558, "percentage": 34.13, "elapsed_time": "0:49:24", "remaining_time": "1:35:21", "throughput": 2865.96, "total_tokens": 8496968} {"current_steps": 13030, "total_steps": 38160, "loss": 0.2071, "lr": 4.1635266061898015e-05, "epoch": 6.829140461215933, "percentage": 34.15, "elapsed_time": "0:49:25", "remaining_time": "1:35:20", "throughput": 2866.15, "total_tokens": 8500616} {"current_steps": 13035, "total_steps": 38160, "loss": 0.2963, "lr": 4.162672888566691e-05, "epoch": 6.831761006289308, "percentage": 34.16, "elapsed_time": "0:49:26", "remaining_time": "1:35:18", "throughput": 2866.3, "total_tokens": 8504136} {"current_steps": 13040, "total_steps": 38160, "loss": 0.2989, "lr": 4.1618188231313816e-05, "epoch": 6.834381551362683, "percentage": 34.17, "elapsed_time": "0:49:27", "remaining_time": "1:35:17", "throughput": 2866.41, "total_tokens": 8507464} {"current_steps": 13045, "total_steps": 38160, "loss": 0.3301, "lr": 4.1609644100625335e-05, "epoch": 6.837002096436059, "percentage": 34.19, "elapsed_time": "0:49:29", "remaining_time": "1:35:16", "throughput": 2866.33, "total_tokens": 8510216} {"current_steps": 13050, "total_steps": 38160, "loss": 0.3098, "lr": 4.16010964953888e-05, "epoch": 6.839622641509434, "percentage": 34.2, "elapsed_time": "0:49:30", "remaining_time": "1:35:14", "throughput": 2866.52, "total_tokens": 8513960} {"current_steps": 13055, "total_steps": 38160, "loss": 0.2897, "lr": 4.159254541739227e-05, "epoch": 6.8422431865828095, "percentage": 34.21, "elapsed_time": "0:49:31", "remaining_time": "1:35:13", "throughput": 2866.73, "total_tokens": 8517768} {"current_steps": 13060, "total_steps": 38160, "loss": 0.3569, "lr": 4.158399086842454e-05, "epoch": 6.844863731656185, "percentage": 34.22, "elapsed_time": "0:49:32", "remaining_time": "1:35:12", "throughput": 2866.79, "total_tokens": 8521640} {"current_steps": 13065, "total_steps": 38160, "loss": 0.2488, "lr": 4.157543285027512e-05, "epoch": 6.84748427672956, "percentage": 34.24, "elapsed_time": "0:49:33", "remaining_time": "1:35:11", "throughput": 2866.91, "total_tokens": 8524968} {"current_steps": 13070, "total_steps": 38160, "loss": 0.4216, "lr": 4.156687136473425e-05, "epoch": 6.850104821802935, "percentage": 34.25, "elapsed_time": "0:49:34", "remaining_time": "1:35:10", "throughput": 2866.96, "total_tokens": 8528200} {"current_steps": 13075, "total_steps": 38160, "loss": 0.2652, "lr": 4.1558306413592894e-05, "epoch": 6.85272536687631, "percentage": 34.26, "elapsed_time": "0:49:35", "remaining_time": "1:35:09", "throughput": 2866.95, "total_tokens": 8531144} {"current_steps": 13080, "total_steps": 38160, "loss": 0.2826, "lr": 4.1549737998642745e-05, "epoch": 6.855345911949685, "percentage": 34.28, "elapsed_time": "0:49:36", "remaining_time": "1:35:07", "throughput": 2867.3, "total_tokens": 8535240} {"current_steps": 13085, "total_steps": 38160, "loss": 0.2771, "lr": 4.154116612167622e-05, "epoch": 6.8579664570230605, "percentage": 34.29, "elapsed_time": "0:49:37", "remaining_time": "1:35:06", "throughput": 2867.02, "total_tokens": 8537352} {"current_steps": 13090, "total_steps": 38160, "loss": 0.2748, "lr": 4.1532590784486444e-05, "epoch": 6.860587002096436, "percentage": 34.3, "elapsed_time": "0:49:38", "remaining_time": "1:35:05", "throughput": 2867.11, "total_tokens": 8540776} {"current_steps": 13095, "total_steps": 38160, "loss": 0.2985, "lr": 4.1524011988867294e-05, "epoch": 6.863207547169811, "percentage": 34.32, "elapsed_time": "0:49:39", "remaining_time": "1:35:03", "throughput": 2867.12, "total_tokens": 8543944} {"current_steps": 13100, "total_steps": 38160, "loss": 0.2931, "lr": 4.151542973661336e-05, "epoch": 6.865828092243187, "percentage": 34.33, "elapsed_time": "0:49:41", "remaining_time": "1:35:02", "throughput": 2867.07, "total_tokens": 8546984} {"current_steps": 13105, "total_steps": 38160, "loss": 0.6053, "lr": 4.150684402951994e-05, "epoch": 6.868448637316562, "percentage": 34.34, "elapsed_time": "0:49:42", "remaining_time": "1:35:01", "throughput": 2867.15, "total_tokens": 8550376} {"current_steps": 13110, "total_steps": 38160, "loss": 0.2825, "lr": 4.149825486938306e-05, "epoch": 6.871069182389937, "percentage": 34.36, "elapsed_time": "0:49:43", "remaining_time": "1:35:00", "throughput": 2867.08, "total_tokens": 8553512} {"current_steps": 13115, "total_steps": 38160, "loss": 0.2693, "lr": 4.148966225799949e-05, "epoch": 6.873689727463312, "percentage": 34.37, "elapsed_time": "0:49:44", "remaining_time": "1:34:59", "throughput": 2867.3, "total_tokens": 8557320} {"current_steps": 13120, "total_steps": 38160, "loss": 0.2305, "lr": 4.14810661971667e-05, "epoch": 6.876310272536688, "percentage": 34.38, "elapsed_time": "0:49:45", "remaining_time": "1:34:57", "throughput": 2867.17, "total_tokens": 8559848} {"current_steps": 13125, "total_steps": 38160, "loss": 0.1855, "lr": 4.147246668868289e-05, "epoch": 6.878930817610063, "percentage": 34.39, "elapsed_time": "0:49:46", "remaining_time": "1:34:56", "throughput": 2867.27, "total_tokens": 8563400} {"current_steps": 13130, "total_steps": 38160, "loss": 0.2809, "lr": 4.1463863734346964e-05, "epoch": 6.881551362683438, "percentage": 34.41, "elapsed_time": "0:49:47", "remaining_time": "1:34:55", "throughput": 2867.41, "total_tokens": 8566728} {"current_steps": 13135, "total_steps": 38160, "loss": 0.2826, "lr": 4.145525733595859e-05, "epoch": 6.884171907756813, "percentage": 34.42, "elapsed_time": "0:49:48", "remaining_time": "1:34:54", "throughput": 2867.4, "total_tokens": 8570056} {"current_steps": 13140, "total_steps": 38160, "loss": 0.2468, "lr": 4.14466474953181e-05, "epoch": 6.886792452830189, "percentage": 34.43, "elapsed_time": "0:49:49", "remaining_time": "1:34:53", "throughput": 2867.33, "total_tokens": 8573064} {"current_steps": 13145, "total_steps": 38160, "loss": 0.3488, "lr": 4.14380342142266e-05, "epoch": 6.889412997903564, "percentage": 34.45, "elapsed_time": "0:49:51", "remaining_time": "1:34:52", "throughput": 2867.76, "total_tokens": 8577640} {"current_steps": 13150, "total_steps": 38160, "loss": 0.3434, "lr": 4.142941749448587e-05, "epoch": 6.8920335429769395, "percentage": 34.46, "elapsed_time": "0:49:52", "remaining_time": "1:34:50", "throughput": 2867.92, "total_tokens": 8581256} {"current_steps": 13155, "total_steps": 38160, "loss": 0.224, "lr": 4.142079733789843e-05, "epoch": 6.894654088050315, "percentage": 34.47, "elapsed_time": "0:49:53", "remaining_time": "1:34:49", "throughput": 2867.87, "total_tokens": 8584168} {"current_steps": 13160, "total_steps": 38160, "loss": 0.3297, "lr": 4.141217374626753e-05, "epoch": 6.89727463312369, "percentage": 34.49, "elapsed_time": "0:49:54", "remaining_time": "1:34:48", "throughput": 2867.93, "total_tokens": 8587432} {"current_steps": 13165, "total_steps": 38160, "loss": 0.2819, "lr": 4.140354672139713e-05, "epoch": 6.899895178197065, "percentage": 34.5, "elapsed_time": "0:49:55", "remaining_time": "1:34:46", "throughput": 2868.02, "total_tokens": 8590728} {"current_steps": 13170, "total_steps": 38160, "loss": 0.2185, "lr": 4.1394916265091886e-05, "epoch": 6.90251572327044, "percentage": 34.51, "elapsed_time": "0:49:56", "remaining_time": "1:34:45", "throughput": 2868.08, "total_tokens": 8594120} {"current_steps": 13175, "total_steps": 38160, "loss": 0.3097, "lr": 4.1386282379157214e-05, "epoch": 6.905136268343815, "percentage": 34.53, "elapsed_time": "0:49:57", "remaining_time": "1:34:44", "throughput": 2868.01, "total_tokens": 8596904} {"current_steps": 13180, "total_steps": 38160, "loss": 0.2598, "lr": 4.137764506539921e-05, "epoch": 6.9077568134171905, "percentage": 34.54, "elapsed_time": "0:49:58", "remaining_time": "1:34:43", "throughput": 2868.0, "total_tokens": 8599848} {"current_steps": 13185, "total_steps": 38160, "loss": 0.2741, "lr": 4.136900432562471e-05, "epoch": 6.910377358490566, "percentage": 34.55, "elapsed_time": "0:49:59", "remaining_time": "1:34:41", "throughput": 2868.11, "total_tokens": 8603272} {"current_steps": 13190, "total_steps": 38160, "loss": 0.2881, "lr": 4.136036016164123e-05, "epoch": 6.912997903563941, "percentage": 34.56, "elapsed_time": "0:50:00", "remaining_time": "1:34:40", "throughput": 2868.3, "total_tokens": 8607240} {"current_steps": 13195, "total_steps": 38160, "loss": 0.3748, "lr": 4.135171257525707e-05, "epoch": 6.915618448637317, "percentage": 34.58, "elapsed_time": "0:50:02", "remaining_time": "1:34:40", "throughput": 2868.62, "total_tokens": 8613160} {"current_steps": 13200, "total_steps": 38160, "loss": 0.2958, "lr": 4.1343061568281195e-05, "epoch": 6.918238993710692, "percentage": 34.59, "elapsed_time": "0:50:03", "remaining_time": "1:34:39", "throughput": 2868.9, "total_tokens": 8617480} {"current_steps": 13205, "total_steps": 38160, "loss": 0.2165, "lr": 4.133440714252328e-05, "epoch": 6.920859538784067, "percentage": 34.6, "elapsed_time": "0:50:04", "remaining_time": "1:34:38", "throughput": 2868.91, "total_tokens": 8620520} {"current_steps": 13210, "total_steps": 38160, "loss": 0.1776, "lr": 4.132574929979375e-05, "epoch": 6.923480083857442, "percentage": 34.62, "elapsed_time": "0:50:06", "remaining_time": "1:34:38", "throughput": 2869.24, "total_tokens": 8626568} {"current_steps": 13215, "total_steps": 38160, "loss": 0.2801, "lr": 4.1317088041903714e-05, "epoch": 6.926100628930818, "percentage": 34.63, "elapsed_time": "0:50:07", "remaining_time": "1:34:37", "throughput": 2869.42, "total_tokens": 8630184} {"current_steps": 13220, "total_steps": 38160, "loss": 0.2462, "lr": 4.1308423370665015e-05, "epoch": 6.928721174004193, "percentage": 34.64, "elapsed_time": "0:50:08", "remaining_time": "1:34:36", "throughput": 2869.52, "total_tokens": 8633576} {"current_steps": 13225, "total_steps": 38160, "loss": 0.2808, "lr": 4.1299755287890206e-05, "epoch": 6.931341719077568, "percentage": 34.66, "elapsed_time": "0:50:09", "remaining_time": "1:34:34", "throughput": 2869.49, "total_tokens": 8636520} {"current_steps": 13230, "total_steps": 38160, "loss": 0.2172, "lr": 4.129108379539255e-05, "epoch": 6.933962264150943, "percentage": 34.67, "elapsed_time": "0:50:10", "remaining_time": "1:34:33", "throughput": 2869.59, "total_tokens": 8639816} {"current_steps": 13235, "total_steps": 38160, "loss": 0.3058, "lr": 4.128240889498602e-05, "epoch": 6.936582809224319, "percentage": 34.68, "elapsed_time": "0:50:11", "remaining_time": "1:34:32", "throughput": 2869.59, "total_tokens": 8642888} {"current_steps": 13240, "total_steps": 38160, "loss": 0.3106, "lr": 4.127373058848531e-05, "epoch": 6.939203354297694, "percentage": 34.7, "elapsed_time": "0:50:13", "remaining_time": "1:34:31", "throughput": 2869.46, "total_tokens": 8645704} {"current_steps": 13245, "total_steps": 38160, "loss": 0.2359, "lr": 4.126504887770582e-05, "epoch": 6.9418238993710695, "percentage": 34.71, "elapsed_time": "0:50:14", "remaining_time": "1:34:29", "throughput": 2869.44, "total_tokens": 8648648} {"current_steps": 13250, "total_steps": 38160, "loss": 0.236, "lr": 4.1256363764463666e-05, "epoch": 6.944444444444445, "percentage": 34.72, "elapsed_time": "0:50:15", "remaining_time": "1:34:28", "throughput": 2869.37, "total_tokens": 8651560} {"current_steps": 13255, "total_steps": 38160, "loss": 0.3272, "lr": 4.1247675250575676e-05, "epoch": 6.94706498951782, "percentage": 34.74, "elapsed_time": "0:50:16", "remaining_time": "1:34:27", "throughput": 2869.56, "total_tokens": 8655208} {"current_steps": 13260, "total_steps": 38160, "loss": 0.1996, "lr": 4.1238983337859396e-05, "epoch": 6.949685534591195, "percentage": 34.75, "elapsed_time": "0:50:17", "remaining_time": "1:34:25", "throughput": 2869.35, "total_tokens": 8657576} {"current_steps": 13265, "total_steps": 38160, "loss": 0.4335, "lr": 4.123028802813305e-05, "epoch": 6.95230607966457, "percentage": 34.76, "elapsed_time": "0:50:18", "remaining_time": "1:34:24", "throughput": 2869.42, "total_tokens": 8660872} {"current_steps": 13270, "total_steps": 38160, "loss": 0.2687, "lr": 4.1221589323215625e-05, "epoch": 6.954926624737945, "percentage": 34.77, "elapsed_time": "0:50:19", "remaining_time": "1:34:23", "throughput": 2869.73, "total_tokens": 8665192} {"current_steps": 13275, "total_steps": 38160, "loss": 0.2466, "lr": 4.121288722492678e-05, "epoch": 6.9575471698113205, "percentage": 34.79, "elapsed_time": "0:50:20", "remaining_time": "1:34:22", "throughput": 2870.09, "total_tokens": 8670088} {"current_steps": 13280, "total_steps": 38160, "loss": 0.2684, "lr": 4.120418173508688e-05, "epoch": 6.960167714884696, "percentage": 34.8, "elapsed_time": "0:50:21", "remaining_time": "1:34:21", "throughput": 2870.25, "total_tokens": 8673576} {"current_steps": 13285, "total_steps": 38160, "loss": 0.4037, "lr": 4.1195472855517045e-05, "epoch": 6.962788259958071, "percentage": 34.81, "elapsed_time": "0:50:22", "remaining_time": "1:34:20", "throughput": 2870.16, "total_tokens": 8676424} {"current_steps": 13290, "total_steps": 38160, "loss": 0.2674, "lr": 4.1186760588039045e-05, "epoch": 6.965408805031447, "percentage": 34.83, "elapsed_time": "0:50:24", "remaining_time": "1:34:19", "throughput": 2870.28, "total_tokens": 8679912} {"current_steps": 13295, "total_steps": 38160, "loss": 0.4953, "lr": 4.11780449344754e-05, "epoch": 6.968029350104822, "percentage": 34.84, "elapsed_time": "0:50:25", "remaining_time": "1:34:18", "throughput": 2870.42, "total_tokens": 8683880} {"current_steps": 13300, "total_steps": 38160, "loss": 0.3659, "lr": 4.1169325896649326e-05, "epoch": 6.970649895178197, "percentage": 34.85, "elapsed_time": "0:50:26", "remaining_time": "1:34:17", "throughput": 2870.52, "total_tokens": 8687784} {"current_steps": 13305, "total_steps": 38160, "loss": 0.271, "lr": 4.116060347638474e-05, "epoch": 6.973270440251572, "percentage": 34.87, "elapsed_time": "0:50:27", "remaining_time": "1:34:15", "throughput": 2870.56, "total_tokens": 8690920} {"current_steps": 13310, "total_steps": 38160, "loss": 0.2252, "lr": 4.115187767550628e-05, "epoch": 6.975890985324948, "percentage": 34.88, "elapsed_time": "0:50:28", "remaining_time": "1:34:14", "throughput": 2870.54, "total_tokens": 8693960} {"current_steps": 13315, "total_steps": 38160, "loss": 0.2686, "lr": 4.114314849583928e-05, "epoch": 6.978511530398323, "percentage": 34.89, "elapsed_time": "0:50:29", "remaining_time": "1:34:13", "throughput": 2870.68, "total_tokens": 8697640} {"current_steps": 13320, "total_steps": 38160, "loss": 0.4185, "lr": 4.113441593920979e-05, "epoch": 6.981132075471698, "percentage": 34.91, "elapsed_time": "0:50:30", "remaining_time": "1:34:12", "throughput": 2870.42, "total_tokens": 8699912} {"current_steps": 13325, "total_steps": 38160, "loss": 0.3583, "lr": 4.112568000744454e-05, "epoch": 6.983752620545073, "percentage": 34.92, "elapsed_time": "0:50:31", "remaining_time": "1:34:10", "throughput": 2870.52, "total_tokens": 8703240} {"current_steps": 13330, "total_steps": 38160, "loss": 0.2146, "lr": 4.1116940702371025e-05, "epoch": 6.986373165618449, "percentage": 34.93, "elapsed_time": "0:50:33", "remaining_time": "1:34:09", "throughput": 2870.52, "total_tokens": 8706376} {"current_steps": 13335, "total_steps": 38160, "loss": 0.3494, "lr": 4.1108198025817376e-05, "epoch": 6.988993710691824, "percentage": 34.94, "elapsed_time": "0:50:34", "remaining_time": "1:34:08", "throughput": 2870.48, "total_tokens": 8709224} {"current_steps": 13340, "total_steps": 38160, "loss": 0.3415, "lr": 4.1099451979612476e-05, "epoch": 6.9916142557651995, "percentage": 34.96, "elapsed_time": "0:50:35", "remaining_time": "1:34:07", "throughput": 2870.32, "total_tokens": 8711816} {"current_steps": 13345, "total_steps": 38160, "loss": 0.2762, "lr": 4.109070256558589e-05, "epoch": 6.994234800838575, "percentage": 34.97, "elapsed_time": "0:50:36", "remaining_time": "1:34:06", "throughput": 2870.41, "total_tokens": 8715496} {"current_steps": 13350, "total_steps": 38160, "loss": 0.2766, "lr": 4.108194978556791e-05, "epoch": 6.99685534591195, "percentage": 34.98, "elapsed_time": "0:50:37", "remaining_time": "1:34:04", "throughput": 2870.32, "total_tokens": 8718312} {"current_steps": 13355, "total_steps": 38160, "loss": 0.2651, "lr": 4.1073193641389495e-05, "epoch": 6.999475890985325, "percentage": 35.0, "elapsed_time": "0:50:38", "remaining_time": "1:34:03", "throughput": 2870.58, "total_tokens": 8722632} {"current_steps": 13356, "total_steps": 38160, "eval_loss": 0.5636921525001526, "epoch": 7.0, "percentage": 35.0, "elapsed_time": "0:50:50", "remaining_time": "1:34:25", "throughput": 2859.33, "total_tokens": 8722744} {"current_steps": 13360, "total_steps": 38160, "loss": 0.1985, "lr": 4.1064434134882345e-05, "epoch": 7.0020964360587, "percentage": 35.01, "elapsed_time": "0:50:54", "remaining_time": "1:34:30", "throughput": 2856.51, "total_tokens": 8725944} {"current_steps": 13365, "total_steps": 38160, "loss": 0.2322, "lr": 4.1055671267878847e-05, "epoch": 7.004716981132075, "percentage": 35.02, "elapsed_time": "0:50:55", "remaining_time": "1:34:29", "throughput": 2856.65, "total_tokens": 8729592} {"current_steps": 13370, "total_steps": 38160, "loss": 0.203, "lr": 4.1046905042212106e-05, "epoch": 7.0073375262054505, "percentage": 35.04, "elapsed_time": "0:50:57", "remaining_time": "1:34:28", "throughput": 2856.95, "total_tokens": 8734264} {"current_steps": 13375, "total_steps": 38160, "loss": 0.1807, "lr": 4.103813545971589e-05, "epoch": 7.009958071278826, "percentage": 35.05, "elapsed_time": "0:50:58", "remaining_time": "1:34:27", "throughput": 2857.22, "total_tokens": 8738744} {"current_steps": 13380, "total_steps": 38160, "loss": 0.2002, "lr": 4.10293625222247e-05, "epoch": 7.012578616352202, "percentage": 35.06, "elapsed_time": "0:50:59", "remaining_time": "1:34:26", "throughput": 2857.09, "total_tokens": 8741720} {"current_steps": 13385, "total_steps": 38160, "loss": 0.1993, "lr": 4.102058623157376e-05, "epoch": 7.015199161425577, "percentage": 35.08, "elapsed_time": "0:51:00", "remaining_time": "1:34:25", "throughput": 2857.18, "total_tokens": 8745112} {"current_steps": 13390, "total_steps": 38160, "loss": 0.1775, "lr": 4.101180658959894e-05, "epoch": 7.017819706498952, "percentage": 35.09, "elapsed_time": "0:51:01", "remaining_time": "1:34:24", "throughput": 2857.01, "total_tokens": 8747960} {"current_steps": 13395, "total_steps": 38160, "loss": 0.2448, "lr": 4.1003023598136866e-05, "epoch": 7.020440251572327, "percentage": 35.1, "elapsed_time": "0:51:02", "remaining_time": "1:34:22", "throughput": 2856.95, "total_tokens": 8750808} {"current_steps": 13400, "total_steps": 38160, "loss": 0.2215, "lr": 4.099423725902482e-05, "epoch": 7.023060796645702, "percentage": 35.12, "elapsed_time": "0:51:04", "remaining_time": "1:34:21", "throughput": 2856.74, "total_tokens": 8753368} {"current_steps": 13405, "total_steps": 38160, "loss": 0.2081, "lr": 4.098544757410081e-05, "epoch": 7.0256813417190775, "percentage": 35.13, "elapsed_time": "0:51:05", "remaining_time": "1:34:20", "throughput": 2856.55, "total_tokens": 8756056} {"current_steps": 13410, "total_steps": 38160, "loss": 0.2249, "lr": 4.097665454520354e-05, "epoch": 7.028301886792453, "percentage": 35.14, "elapsed_time": "0:51:06", "remaining_time": "1:34:19", "throughput": 2856.56, "total_tokens": 8759256} {"current_steps": 13415, "total_steps": 38160, "loss": 0.1641, "lr": 4.096785817417241e-05, "epoch": 7.030922431865828, "percentage": 35.15, "elapsed_time": "0:51:07", "remaining_time": "1:34:18", "throughput": 2856.78, "total_tokens": 8763032} {"current_steps": 13420, "total_steps": 38160, "loss": 0.1342, "lr": 4.0959058462847524e-05, "epoch": 7.033542976939203, "percentage": 35.17, "elapsed_time": "0:51:08", "remaining_time": "1:34:16", "throughput": 2856.77, "total_tokens": 8766072} {"current_steps": 13425, "total_steps": 38160, "loss": 0.2057, "lr": 4.095025541306968e-05, "epoch": 7.036163522012578, "percentage": 35.18, "elapsed_time": "0:51:09", "remaining_time": "1:34:15", "throughput": 2856.99, "total_tokens": 8769976} {"current_steps": 13430, "total_steps": 38160, "loss": 0.2502, "lr": 4.0941449026680374e-05, "epoch": 7.038784067085954, "percentage": 35.19, "elapsed_time": "0:51:10", "remaining_time": "1:34:14", "throughput": 2857.21, "total_tokens": 8773528} {"current_steps": 13435, "total_steps": 38160, "loss": 0.217, "lr": 4.09326393055218e-05, "epoch": 7.0414046121593294, "percentage": 35.21, "elapsed_time": "0:51:11", "remaining_time": "1:34:12", "throughput": 2857.22, "total_tokens": 8776440} {"current_steps": 13440, "total_steps": 38160, "loss": 0.18, "lr": 4.0923826251436845e-05, "epoch": 7.044025157232705, "percentage": 35.22, "elapsed_time": "0:51:12", "remaining_time": "1:34:11", "throughput": 2857.49, "total_tokens": 8780408} {"current_steps": 13445, "total_steps": 38160, "loss": 0.2224, "lr": 4.0915009866269115e-05, "epoch": 7.04664570230608, "percentage": 35.23, "elapsed_time": "0:51:13", "remaining_time": "1:34:10", "throughput": 2857.32, "total_tokens": 8782872} {"current_steps": 13450, "total_steps": 38160, "loss": 0.2269, "lr": 4.090619015186288e-05, "epoch": 7.049266247379455, "percentage": 35.25, "elapsed_time": "0:51:14", "remaining_time": "1:34:09", "throughput": 2857.5, "total_tokens": 8786776} {"current_steps": 13455, "total_steps": 38160, "loss": 0.208, "lr": 4.0897367110063145e-05, "epoch": 7.05188679245283, "percentage": 35.26, "elapsed_time": "0:51:16", "remaining_time": "1:34:08", "throughput": 2857.75, "total_tokens": 8791576} {"current_steps": 13460, "total_steps": 38160, "loss": 0.159, "lr": 4.088854074271557e-05, "epoch": 7.054507337526205, "percentage": 35.27, "elapsed_time": "0:51:17", "remaining_time": "1:34:07", "throughput": 2857.59, "total_tokens": 8794072} {"current_steps": 13465, "total_steps": 38160, "loss": 0.2387, "lr": 4.0879711051666534e-05, "epoch": 7.0571278825995805, "percentage": 35.29, "elapsed_time": "0:51:18", "remaining_time": "1:34:06", "throughput": 2857.88, "total_tokens": 8798424} {"current_steps": 13470, "total_steps": 38160, "loss": 0.183, "lr": 4.087087803876313e-05, "epoch": 7.059748427672956, "percentage": 35.3, "elapsed_time": "0:51:19", "remaining_time": "1:34:05", "throughput": 2857.77, "total_tokens": 8801208} {"current_steps": 13475, "total_steps": 38160, "loss": 0.2291, "lr": 4.086204170585308e-05, "epoch": 7.062368972746331, "percentage": 35.31, "elapsed_time": "0:51:20", "remaining_time": "1:34:03", "throughput": 2857.8, "total_tokens": 8804472} {"current_steps": 13480, "total_steps": 38160, "loss": 0.2636, "lr": 4.085320205478488e-05, "epoch": 7.064989517819707, "percentage": 35.32, "elapsed_time": "0:51:21", "remaining_time": "1:34:02", "throughput": 2857.99, "total_tokens": 8808152} {"current_steps": 13485, "total_steps": 38160, "loss": 0.1885, "lr": 4.084435908740768e-05, "epoch": 7.067610062893082, "percentage": 35.34, "elapsed_time": "0:51:22", "remaining_time": "1:34:01", "throughput": 2858.08, "total_tokens": 8811352} {"current_steps": 13490, "total_steps": 38160, "loss": 0.1779, "lr": 4.0835512805571306e-05, "epoch": 7.070230607966457, "percentage": 35.35, "elapsed_time": "0:51:24", "remaining_time": "1:33:59", "throughput": 2858.05, "total_tokens": 8814328} {"current_steps": 13495, "total_steps": 38160, "loss": 0.253, "lr": 4.082666321112633e-05, "epoch": 7.072851153039832, "percentage": 35.36, "elapsed_time": "0:51:25", "remaining_time": "1:33:58", "throughput": 2858.24, "total_tokens": 8817976} {"current_steps": 13500, "total_steps": 38160, "loss": 0.1567, "lr": 4.081781030592396e-05, "epoch": 7.0754716981132075, "percentage": 35.38, "elapsed_time": "0:51:26", "remaining_time": "1:33:57", "throughput": 2858.22, "total_tokens": 8820856} {"current_steps": 13505, "total_steps": 38160, "loss": 0.3171, "lr": 4.080895409181613e-05, "epoch": 7.078092243186583, "percentage": 35.39, "elapsed_time": "0:51:27", "remaining_time": "1:33:56", "throughput": 2858.3, "total_tokens": 8824120} {"current_steps": 13510, "total_steps": 38160, "loss": 0.1943, "lr": 4.080009457065547e-05, "epoch": 7.080712788259958, "percentage": 35.4, "elapsed_time": "0:51:28", "remaining_time": "1:33:54", "throughput": 2858.31, "total_tokens": 8827192} {"current_steps": 13515, "total_steps": 38160, "loss": 0.174, "lr": 4.0791231744295286e-05, "epoch": 7.083333333333333, "percentage": 35.42, "elapsed_time": "0:51:29", "remaining_time": "1:33:53", "throughput": 2858.57, "total_tokens": 8831064} {"current_steps": 13520, "total_steps": 38160, "loss": 0.2832, "lr": 4.078236561458957e-05, "epoch": 7.085953878406708, "percentage": 35.43, "elapsed_time": "0:51:30", "remaining_time": "1:33:52", "throughput": 2858.56, "total_tokens": 8834200} {"current_steps": 13525, "total_steps": 38160, "loss": 0.1506, "lr": 4.077349618339302e-05, "epoch": 7.088574423480084, "percentage": 35.44, "elapsed_time": "0:51:31", "remaining_time": "1:33:51", "throughput": 2858.5, "total_tokens": 8837240} {"current_steps": 13530, "total_steps": 38160, "loss": 0.3065, "lr": 4.076462345256103e-05, "epoch": 7.091194968553459, "percentage": 35.46, "elapsed_time": "0:51:32", "remaining_time": "1:33:50", "throughput": 2858.79, "total_tokens": 8841976} {"current_steps": 13535, "total_steps": 38160, "loss": 0.1592, "lr": 4.0755747423949655e-05, "epoch": 7.093815513626835, "percentage": 35.47, "elapsed_time": "0:51:33", "remaining_time": "1:33:49", "throughput": 2858.88, "total_tokens": 8845336} {"current_steps": 13540, "total_steps": 38160, "loss": 0.2317, "lr": 4.074686809941568e-05, "epoch": 7.09643605870021, "percentage": 35.48, "elapsed_time": "0:51:35", "remaining_time": "1:33:47", "throughput": 2858.85, "total_tokens": 8848184} {"current_steps": 13545, "total_steps": 38160, "loss": 0.2047, "lr": 4.0737985480816546e-05, "epoch": 7.099056603773585, "percentage": 35.5, "elapsed_time": "0:51:36", "remaining_time": "1:33:46", "throughput": 2858.72, "total_tokens": 8850840} {"current_steps": 13550, "total_steps": 38160, "loss": 0.3042, "lr": 4.0729099570010395e-05, "epoch": 7.10167714884696, "percentage": 35.51, "elapsed_time": "0:51:37", "remaining_time": "1:33:45", "throughput": 2858.74, "total_tokens": 8854296} {"current_steps": 13555, "total_steps": 38160, "loss": 0.1617, "lr": 4.072021036885607e-05, "epoch": 7.104297693920335, "percentage": 35.52, "elapsed_time": "0:51:38", "remaining_time": "1:33:44", "throughput": 2858.76, "total_tokens": 8857560} {"current_steps": 13560, "total_steps": 38160, "loss": 0.1995, "lr": 4.0711317879213075e-05, "epoch": 7.1069182389937104, "percentage": 35.53, "elapsed_time": "0:51:39", "remaining_time": "1:33:43", "throughput": 2859.0, "total_tokens": 8861496} {"current_steps": 13565, "total_steps": 38160, "loss": 0.2068, "lr": 4.070242210294162e-05, "epoch": 7.109538784067086, "percentage": 35.55, "elapsed_time": "0:51:40", "remaining_time": "1:33:41", "throughput": 2858.97, "total_tokens": 8864344} {"current_steps": 13570, "total_steps": 38160, "loss": 0.2895, "lr": 4.069352304190261e-05, "epoch": 7.112159329140461, "percentage": 35.56, "elapsed_time": "0:51:41", "remaining_time": "1:33:40", "throughput": 2859.06, "total_tokens": 8868152} {"current_steps": 13575, "total_steps": 38160, "loss": 0.1695, "lr": 4.068462069795761e-05, "epoch": 7.114779874213837, "percentage": 35.57, "elapsed_time": "0:51:42", "remaining_time": "1:33:39", "throughput": 2858.95, "total_tokens": 8870776} {"current_steps": 13580, "total_steps": 38160, "loss": 0.2387, "lr": 4.067571507296891e-05, "epoch": 7.117400419287212, "percentage": 35.59, "elapsed_time": "0:51:43", "remaining_time": "1:33:38", "throughput": 2858.97, "total_tokens": 8873944} {"current_steps": 13585, "total_steps": 38160, "loss": 0.208, "lr": 4.0666806168799455e-05, "epoch": 7.120020964360587, "percentage": 35.6, "elapsed_time": "0:51:44", "remaining_time": "1:33:36", "throughput": 2858.91, "total_tokens": 8876792} {"current_steps": 13590, "total_steps": 38160, "loss": 0.2355, "lr": 4.0657893987312876e-05, "epoch": 7.122641509433962, "percentage": 35.61, "elapsed_time": "0:51:46", "remaining_time": "1:33:35", "throughput": 2858.87, "total_tokens": 8879672} {"current_steps": 13595, "total_steps": 38160, "loss": 0.1697, "lr": 4.064897853037352e-05, "epoch": 7.1252620545073375, "percentage": 35.63, "elapsed_time": "0:51:47", "remaining_time": "1:33:34", "throughput": 2858.94, "total_tokens": 8882904} {"current_steps": 13600, "total_steps": 38160, "loss": 0.1742, "lr": 4.064005979984639e-05, "epoch": 7.127882599580713, "percentage": 35.64, "elapsed_time": "0:51:48", "remaining_time": "1:33:32", "throughput": 2859.06, "total_tokens": 8886328} {"current_steps": 13605, "total_steps": 38160, "loss": 0.1858, "lr": 4.0631137797597176e-05, "epoch": 7.130503144654088, "percentage": 35.65, "elapsed_time": "0:51:49", "remaining_time": "1:33:31", "throughput": 2858.95, "total_tokens": 8888888} {"current_steps": 13610, "total_steps": 38160, "loss": 0.1891, "lr": 4.0622212525492266e-05, "epoch": 7.133123689727463, "percentage": 35.67, "elapsed_time": "0:51:50", "remaining_time": "1:33:30", "throughput": 2859.17, "total_tokens": 8892536} {"current_steps": 13615, "total_steps": 38160, "loss": 0.1992, "lr": 4.061328398539872e-05, "epoch": 7.135744234800838, "percentage": 35.68, "elapsed_time": "0:51:51", "remaining_time": "1:33:28", "throughput": 2859.23, "total_tokens": 8895768} {"current_steps": 13620, "total_steps": 38160, "loss": 0.2043, "lr": 4.060435217918429e-05, "epoch": 7.138364779874214, "percentage": 35.69, "elapsed_time": "0:51:52", "remaining_time": "1:33:27", "throughput": 2859.39, "total_tokens": 8899320} {"current_steps": 13625, "total_steps": 38160, "loss": 0.233, "lr": 4.0595417108717405e-05, "epoch": 7.140985324947589, "percentage": 35.7, "elapsed_time": "0:51:53", "remaining_time": "1:33:26", "throughput": 2859.23, "total_tokens": 8901816} {"current_steps": 13630, "total_steps": 38160, "loss": 0.1684, "lr": 4.0586478775867185e-05, "epoch": 7.143605870020965, "percentage": 35.72, "elapsed_time": "0:51:54", "remaining_time": "1:33:25", "throughput": 2859.28, "total_tokens": 8904984} {"current_steps": 13635, "total_steps": 38160, "loss": 0.2459, "lr": 4.057753718250343e-05, "epoch": 7.14622641509434, "percentage": 35.73, "elapsed_time": "0:51:55", "remaining_time": "1:33:23", "throughput": 2859.56, "total_tokens": 8909272} {"current_steps": 13640, "total_steps": 38160, "loss": 0.2116, "lr": 4.056859233049661e-05, "epoch": 7.148846960167715, "percentage": 35.74, "elapsed_time": "0:51:56", "remaining_time": "1:33:22", "throughput": 2859.47, "total_tokens": 8912088} {"current_steps": 13645, "total_steps": 38160, "loss": 0.2539, "lr": 4.05596442217179e-05, "epoch": 7.15146750524109, "percentage": 35.76, "elapsed_time": "0:51:57", "remaining_time": "1:33:21", "throughput": 2859.46, "total_tokens": 8915160} {"current_steps": 13650, "total_steps": 38160, "loss": 0.1883, "lr": 4.055069285803912e-05, "epoch": 7.154088050314465, "percentage": 35.77, "elapsed_time": "0:51:58", "remaining_time": "1:33:20", "throughput": 2859.47, "total_tokens": 8918200} {"current_steps": 13655, "total_steps": 38160, "loss": 0.1455, "lr": 4.0541738241332815e-05, "epoch": 7.15670859538784, "percentage": 35.78, "elapsed_time": "0:51:59", "remaining_time": "1:33:18", "throughput": 2859.58, "total_tokens": 8921464} {"current_steps": 13660, "total_steps": 38160, "loss": 0.2018, "lr": 4.053278037347217e-05, "epoch": 7.159329140461216, "percentage": 35.8, "elapsed_time": "0:52:00", "remaining_time": "1:33:17", "throughput": 2859.54, "total_tokens": 8924344} {"current_steps": 13665, "total_steps": 38160, "loss": 0.157, "lr": 4.052381925633109e-05, "epoch": 7.161949685534591, "percentage": 35.81, "elapsed_time": "0:52:01", "remaining_time": "1:33:16", "throughput": 2859.52, "total_tokens": 8927352} {"current_steps": 13670, "total_steps": 38160, "loss": 0.2235, "lr": 4.051485489178412e-05, "epoch": 7.164570230607967, "percentage": 35.82, "elapsed_time": "0:52:03", "remaining_time": "1:33:15", "throughput": 2859.64, "total_tokens": 8930936} {"current_steps": 13675, "total_steps": 38160, "loss": 0.2837, "lr": 4.05058872817065e-05, "epoch": 7.167190775681342, "percentage": 35.84, "elapsed_time": "0:52:04", "remaining_time": "1:33:13", "throughput": 2859.7, "total_tokens": 8934296} {"current_steps": 13680, "total_steps": 38160, "loss": 0.1459, "lr": 4.0496916427974177e-05, "epoch": 7.169811320754717, "percentage": 35.85, "elapsed_time": "0:52:05", "remaining_time": "1:33:12", "throughput": 2859.57, "total_tokens": 8937016} {"current_steps": 13685, "total_steps": 38160, "loss": 0.1488, "lr": 4.048794233246373e-05, "epoch": 7.172431865828092, "percentage": 35.86, "elapsed_time": "0:52:06", "remaining_time": "1:33:11", "throughput": 2859.78, "total_tokens": 8940792} {"current_steps": 13690, "total_steps": 38160, "loss": 0.2723, "lr": 4.0478964997052435e-05, "epoch": 7.1750524109014675, "percentage": 35.88, "elapsed_time": "0:52:07", "remaining_time": "1:33:10", "throughput": 2859.77, "total_tokens": 8944024} {"current_steps": 13695, "total_steps": 38160, "loss": 0.2152, "lr": 4.046998442361827e-05, "epoch": 7.177672955974843, "percentage": 35.89, "elapsed_time": "0:52:08", "remaining_time": "1:33:08", "throughput": 2859.74, "total_tokens": 8946872} {"current_steps": 13700, "total_steps": 38160, "loss": 0.1939, "lr": 4.046100061403984e-05, "epoch": 7.180293501048218, "percentage": 35.9, "elapsed_time": "0:52:09", "remaining_time": "1:33:07", "throughput": 2859.84, "total_tokens": 8950168} {"current_steps": 13705, "total_steps": 38160, "loss": 0.2274, "lr": 4.045201357019648e-05, "epoch": 7.182914046121593, "percentage": 35.91, "elapsed_time": "0:52:10", "remaining_time": "1:33:06", "throughput": 2859.85, "total_tokens": 8953112} {"current_steps": 13710, "total_steps": 38160, "loss": 0.1843, "lr": 4.044302329396816e-05, "epoch": 7.185534591194968, "percentage": 35.93, "elapsed_time": "0:52:11", "remaining_time": "1:33:04", "throughput": 2859.91, "total_tokens": 8956312} {"current_steps": 13715, "total_steps": 38160, "loss": 0.1987, "lr": 4.0434029787235564e-05, "epoch": 7.188155136268344, "percentage": 35.94, "elapsed_time": "0:52:12", "remaining_time": "1:33:03", "throughput": 2859.83, "total_tokens": 8959032} {"current_steps": 13720, "total_steps": 38160, "loss": 0.2824, "lr": 4.042503305188e-05, "epoch": 7.190775681341719, "percentage": 35.95, "elapsed_time": "0:52:13", "remaining_time": "1:33:02", "throughput": 2859.96, "total_tokens": 8962744} {"current_steps": 13725, "total_steps": 38160, "loss": 0.2527, "lr": 4.041603308978351e-05, "epoch": 7.193396226415095, "percentage": 35.97, "elapsed_time": "0:52:14", "remaining_time": "1:33:01", "throughput": 2860.16, "total_tokens": 8966520} {"current_steps": 13730, "total_steps": 38160, "loss": 0.2008, "lr": 4.040702990282878e-05, "epoch": 7.19601677148847, "percentage": 35.98, "elapsed_time": "0:52:16", "remaining_time": "1:32:59", "throughput": 2860.1, "total_tokens": 8969304} {"current_steps": 13735, "total_steps": 38160, "loss": 0.3044, "lr": 4.039802349289914e-05, "epoch": 7.198637316561845, "percentage": 35.99, "elapsed_time": "0:52:17", "remaining_time": "1:32:58", "throughput": 2860.47, "total_tokens": 8973432} {"current_steps": 13740, "total_steps": 38160, "loss": 0.2141, "lr": 4.038901386187868e-05, "epoch": 7.20125786163522, "percentage": 36.01, "elapsed_time": "0:52:18", "remaining_time": "1:32:57", "throughput": 2860.35, "total_tokens": 8976248} {"current_steps": 13745, "total_steps": 38160, "loss": 0.2232, "lr": 4.038000101165208e-05, "epoch": 7.203878406708595, "percentage": 36.02, "elapsed_time": "0:52:19", "remaining_time": "1:32:56", "throughput": 2860.64, "total_tokens": 8980792} {"current_steps": 13750, "total_steps": 38160, "loss": 0.2477, "lr": 4.0370984944104725e-05, "epoch": 7.20649895178197, "percentage": 36.03, "elapsed_time": "0:52:20", "remaining_time": "1:32:55", "throughput": 2860.53, "total_tokens": 8983480} {"current_steps": 13755, "total_steps": 38160, "loss": 0.199, "lr": 4.0361965661122695e-05, "epoch": 7.209119496855346, "percentage": 36.05, "elapsed_time": "0:52:21", "remaining_time": "1:32:54", "throughput": 2860.4, "total_tokens": 8986200} {"current_steps": 13760, "total_steps": 38160, "loss": 0.2065, "lr": 4.035294316459271e-05, "epoch": 7.211740041928721, "percentage": 36.06, "elapsed_time": "0:52:22", "remaining_time": "1:32:52", "throughput": 2860.5, "total_tokens": 8989816} {"current_steps": 13765, "total_steps": 38160, "loss": 0.1309, "lr": 4.034391745640215e-05, "epoch": 7.214360587002097, "percentage": 36.07, "elapsed_time": "0:52:23", "remaining_time": "1:32:51", "throughput": 2860.4, "total_tokens": 8992600} {"current_steps": 13770, "total_steps": 38160, "loss": 0.2191, "lr": 4.033488853843913e-05, "epoch": 7.216981132075472, "percentage": 36.08, "elapsed_time": "0:52:25", "remaining_time": "1:32:50", "throughput": 2860.79, "total_tokens": 8997432} {"current_steps": 13775, "total_steps": 38160, "loss": 0.1945, "lr": 4.0325856412592363e-05, "epoch": 7.219601677148847, "percentage": 36.1, "elapsed_time": "0:52:26", "remaining_time": "1:32:49", "throughput": 2860.55, "total_tokens": 8999864} {"current_steps": 13780, "total_steps": 38160, "loss": 0.1872, "lr": 4.031682108075129e-05, "epoch": 7.222222222222222, "percentage": 36.11, "elapsed_time": "0:52:27", "remaining_time": "1:32:48", "throughput": 2860.55, "total_tokens": 9003160} {"current_steps": 13785, "total_steps": 38160, "loss": 0.1854, "lr": 4.030778254480599e-05, "epoch": 7.2248427672955975, "percentage": 36.12, "elapsed_time": "0:52:28", "remaining_time": "1:32:47", "throughput": 2860.51, "total_tokens": 9006040} {"current_steps": 13790, "total_steps": 38160, "loss": 0.2179, "lr": 4.029874080664722e-05, "epoch": 7.227463312368973, "percentage": 36.14, "elapsed_time": "0:52:29", "remaining_time": "1:32:45", "throughput": 2860.6, "total_tokens": 9009624} {"current_steps": 13795, "total_steps": 38160, "loss": 0.191, "lr": 4.0289695868166414e-05, "epoch": 7.230083857442348, "percentage": 36.15, "elapsed_time": "0:52:30", "remaining_time": "1:32:44", "throughput": 2860.9, "total_tokens": 9013912} {"current_steps": 13800, "total_steps": 38160, "loss": 0.2221, "lr": 4.028064773125566e-05, "epoch": 7.232704402515723, "percentage": 36.16, "elapsed_time": "0:52:31", "remaining_time": "1:32:43", "throughput": 2860.94, "total_tokens": 9017016} {"current_steps": 13805, "total_steps": 38160, "loss": 0.2134, "lr": 4.0271596397807734e-05, "epoch": 7.235324947589098, "percentage": 36.18, "elapsed_time": "0:52:32", "remaining_time": "1:32:42", "throughput": 2860.55, "total_tokens": 9019000} {"current_steps": 13810, "total_steps": 38160, "loss": 0.3029, "lr": 4.026254186971607e-05, "epoch": 7.237945492662474, "percentage": 36.19, "elapsed_time": "0:52:34", "remaining_time": "1:32:41", "throughput": 2860.64, "total_tokens": 9022520} {"current_steps": 13815, "total_steps": 38160, "loss": 0.2148, "lr": 4.025348414887477e-05, "epoch": 7.240566037735849, "percentage": 36.2, "elapsed_time": "0:52:35", "remaining_time": "1:32:39", "throughput": 2860.64, "total_tokens": 9025496} {"current_steps": 13820, "total_steps": 38160, "loss": 0.205, "lr": 4.024442323717861e-05, "epoch": 7.243186582809225, "percentage": 36.22, "elapsed_time": "0:52:36", "remaining_time": "1:32:38", "throughput": 2860.85, "total_tokens": 9029464} {"current_steps": 13825, "total_steps": 38160, "loss": 0.2654, "lr": 4.023535913652302e-05, "epoch": 7.2458071278826, "percentage": 36.23, "elapsed_time": "0:52:37", "remaining_time": "1:32:37", "throughput": 2860.76, "total_tokens": 9032088} {"current_steps": 13830, "total_steps": 38160, "loss": 0.2091, "lr": 4.022629184880412e-05, "epoch": 7.248427672955975, "percentage": 36.24, "elapsed_time": "0:52:38", "remaining_time": "1:32:36", "throughput": 2860.91, "total_tokens": 9035768} {"current_steps": 13835, "total_steps": 38160, "loss": 0.2115, "lr": 4.021722137591867e-05, "epoch": 7.25104821802935, "percentage": 36.26, "elapsed_time": "0:52:39", "remaining_time": "1:32:35", "throughput": 2860.86, "total_tokens": 9038840} {"current_steps": 13840, "total_steps": 38160, "loss": 0.1666, "lr": 4.020814771976412e-05, "epoch": 7.253668763102725, "percentage": 36.27, "elapsed_time": "0:52:40", "remaining_time": "1:32:33", "throughput": 2861.0, "total_tokens": 9042328} {"current_steps": 13845, "total_steps": 38160, "loss": 0.1717, "lr": 4.019907088223857e-05, "epoch": 7.2562893081761, "percentage": 36.28, "elapsed_time": "0:52:41", "remaining_time": "1:32:32", "throughput": 2861.0, "total_tokens": 9045336} {"current_steps": 13850, "total_steps": 38160, "loss": 0.2455, "lr": 4.018999086524079e-05, "epoch": 7.258909853249476, "percentage": 36.29, "elapsed_time": "0:52:42", "remaining_time": "1:32:31", "throughput": 2860.98, "total_tokens": 9048312} {"current_steps": 13855, "total_steps": 38160, "loss": 0.2806, "lr": 4.018090767067022e-05, "epoch": 7.261530398322851, "percentage": 36.31, "elapsed_time": "0:52:43", "remaining_time": "1:32:30", "throughput": 2861.24, "total_tokens": 9052760} {"current_steps": 13860, "total_steps": 38160, "loss": 0.3982, "lr": 4.017182130042696e-05, "epoch": 7.264150943396227, "percentage": 36.32, "elapsed_time": "0:52:44", "remaining_time": "1:32:29", "throughput": 2861.26, "total_tokens": 9055864} {"current_steps": 13865, "total_steps": 38160, "loss": 0.1759, "lr": 4.0162731756411764e-05, "epoch": 7.266771488469602, "percentage": 36.33, "elapsed_time": "0:52:46", "remaining_time": "1:32:27", "throughput": 2861.14, "total_tokens": 9058776} {"current_steps": 13870, "total_steps": 38160, "loss": 0.2724, "lr": 4.015363904052608e-05, "epoch": 7.269392033542977, "percentage": 36.35, "elapsed_time": "0:52:47", "remaining_time": "1:32:26", "throughput": 2861.27, "total_tokens": 9062360} {"current_steps": 13875, "total_steps": 38160, "loss": 0.2892, "lr": 4.014454315467199e-05, "epoch": 7.272012578616352, "percentage": 36.36, "elapsed_time": "0:52:48", "remaining_time": "1:32:25", "throughput": 2861.15, "total_tokens": 9065016} {"current_steps": 13880, "total_steps": 38160, "loss": 0.2203, "lr": 4.013544410075224e-05, "epoch": 7.2746331236897275, "percentage": 36.37, "elapsed_time": "0:52:50", "remaining_time": "1:32:25", "throughput": 2861.77, "total_tokens": 9071992} {"current_steps": 13885, "total_steps": 38160, "loss": 0.2451, "lr": 4.0126341880670273e-05, "epoch": 7.277253668763103, "percentage": 36.39, "elapsed_time": "0:52:51", "remaining_time": "1:32:24", "throughput": 2861.94, "total_tokens": 9075672} {"current_steps": 13890, "total_steps": 38160, "loss": 0.2222, "lr": 4.011723649633014e-05, "epoch": 7.279874213836478, "percentage": 36.4, "elapsed_time": "0:52:52", "remaining_time": "1:32:22", "throughput": 2862.01, "total_tokens": 9078936} {"current_steps": 13895, "total_steps": 38160, "loss": 0.3074, "lr": 4.0108127949636606e-05, "epoch": 7.282494758909853, "percentage": 36.41, "elapsed_time": "0:52:53", "remaining_time": "1:32:21", "throughput": 2862.04, "total_tokens": 9082168} {"current_steps": 13900, "total_steps": 38160, "loss": 0.2937, "lr": 4.009901624249507e-05, "epoch": 7.285115303983228, "percentage": 36.43, "elapsed_time": "0:52:54", "remaining_time": "1:32:20", "throughput": 2861.88, "total_tokens": 9084664} {"current_steps": 13905, "total_steps": 38160, "loss": 0.2188, "lr": 4.008990137681159e-05, "epoch": 7.287735849056604, "percentage": 36.44, "elapsed_time": "0:52:55", "remaining_time": "1:32:19", "throughput": 2861.89, "total_tokens": 9087864} {"current_steps": 13910, "total_steps": 38160, "loss": 0.2532, "lr": 4.00807833544929e-05, "epoch": 7.290356394129979, "percentage": 36.45, "elapsed_time": "0:52:56", "remaining_time": "1:32:17", "throughput": 2862.05, "total_tokens": 9091416} {"current_steps": 13915, "total_steps": 38160, "loss": 0.2495, "lr": 4.0071662177446376e-05, "epoch": 7.2929769392033545, "percentage": 36.46, "elapsed_time": "0:52:57", "remaining_time": "1:32:16", "throughput": 2861.95, "total_tokens": 9094296} {"current_steps": 13920, "total_steps": 38160, "loss": 0.2434, "lr": 4.006253784758008e-05, "epoch": 7.29559748427673, "percentage": 36.48, "elapsed_time": "0:52:58", "remaining_time": "1:32:15", "throughput": 2861.89, "total_tokens": 9097112} {"current_steps": 13925, "total_steps": 38160, "loss": 0.1989, "lr": 4.0053410366802704e-05, "epoch": 7.298218029350105, "percentage": 36.49, "elapsed_time": "0:52:59", "remaining_time": "1:32:14", "throughput": 2861.99, "total_tokens": 9100632} {"current_steps": 13930, "total_steps": 38160, "loss": 0.2127, "lr": 4.004427973702362e-05, "epoch": 7.30083857442348, "percentage": 36.5, "elapsed_time": "0:53:00", "remaining_time": "1:32:12", "throughput": 2862.0, "total_tokens": 9103864} {"current_steps": 13935, "total_steps": 38160, "loss": 0.2145, "lr": 4.003514596015285e-05, "epoch": 7.303459119496855, "percentage": 36.52, "elapsed_time": "0:53:02", "remaining_time": "1:32:11", "throughput": 2862.26, "total_tokens": 9107928} {"current_steps": 13940, "total_steps": 38160, "loss": 0.162, "lr": 4.002600903810108e-05, "epoch": 7.30607966457023, "percentage": 36.53, "elapsed_time": "0:53:03", "remaining_time": "1:32:10", "throughput": 2862.4, "total_tokens": 9111384} {"current_steps": 13945, "total_steps": 38160, "loss": 0.2424, "lr": 4.001686897277963e-05, "epoch": 7.308700209643606, "percentage": 36.54, "elapsed_time": "0:53:04", "remaining_time": "1:32:09", "throughput": 2862.41, "total_tokens": 9114488} {"current_steps": 13950, "total_steps": 38160, "loss": 0.2033, "lr": 4.000772576610052e-05, "epoch": 7.311320754716981, "percentage": 36.56, "elapsed_time": "0:53:05", "remaining_time": "1:32:07", "throughput": 2862.34, "total_tokens": 9117208} {"current_steps": 13955, "total_steps": 38160, "loss": 0.2149, "lr": 3.99985794199764e-05, "epoch": 7.313941299790357, "percentage": 36.57, "elapsed_time": "0:53:06", "remaining_time": "1:32:06", "throughput": 2862.53, "total_tokens": 9121176} {"current_steps": 13960, "total_steps": 38160, "loss": 0.2813, "lr": 3.998942993632058e-05, "epoch": 7.316561844863732, "percentage": 36.58, "elapsed_time": "0:53:07", "remaining_time": "1:32:05", "throughput": 2862.54, "total_tokens": 9124216} {"current_steps": 13965, "total_steps": 38160, "loss": 0.2322, "lr": 3.998027731704702e-05, "epoch": 7.319182389937107, "percentage": 36.6, "elapsed_time": "0:53:08", "remaining_time": "1:32:04", "throughput": 2862.45, "total_tokens": 9126936} {"current_steps": 13970, "total_steps": 38160, "loss": 0.2645, "lr": 3.9971121564070354e-05, "epoch": 7.321802935010482, "percentage": 36.61, "elapsed_time": "0:53:09", "remaining_time": "1:32:03", "throughput": 2862.3, "total_tokens": 9129688} {"current_steps": 13975, "total_steps": 38160, "loss": 0.1584, "lr": 3.996196267930585e-05, "epoch": 7.3244234800838575, "percentage": 36.62, "elapsed_time": "0:53:10", "remaining_time": "1:32:01", "throughput": 2862.07, "total_tokens": 9132152} {"current_steps": 13980, "total_steps": 38160, "loss": 0.2905, "lr": 3.995280066466945e-05, "epoch": 7.327044025157233, "percentage": 36.64, "elapsed_time": "0:53:11", "remaining_time": "1:32:00", "throughput": 2862.06, "total_tokens": 9135352} {"current_steps": 13985, "total_steps": 38160, "loss": 0.2998, "lr": 3.9943635522077746e-05, "epoch": 7.329664570230608, "percentage": 36.65, "elapsed_time": "0:53:12", "remaining_time": "1:31:59", "throughput": 2862.22, "total_tokens": 9139064} {"current_steps": 13990, "total_steps": 38160, "loss": 0.196, "lr": 3.993446725344797e-05, "epoch": 7.332285115303983, "percentage": 36.66, "elapsed_time": "0:53:14", "remaining_time": "1:31:58", "throughput": 2862.08, "total_tokens": 9141624} {"current_steps": 13995, "total_steps": 38160, "loss": 0.1546, "lr": 3.992529586069803e-05, "epoch": 7.334905660377358, "percentage": 36.67, "elapsed_time": "0:53:15", "remaining_time": "1:31:56", "throughput": 2861.93, "total_tokens": 9144120} {"current_steps": 14000, "total_steps": 38160, "loss": 0.1938, "lr": 3.991612134574648e-05, "epoch": 7.337526205450734, "percentage": 36.69, "elapsed_time": "0:53:16", "remaining_time": "1:31:55", "throughput": 2862.01, "total_tokens": 9147384} {"current_steps": 14005, "total_steps": 38160, "loss": 0.24, "lr": 3.99069437105125e-05, "epoch": 7.340146750524109, "percentage": 36.7, "elapsed_time": "0:53:17", "remaining_time": "1:31:54", "throughput": 2862.05, "total_tokens": 9150744} {"current_steps": 14010, "total_steps": 38160, "loss": 0.2109, "lr": 3.9897762956915976e-05, "epoch": 7.3427672955974845, "percentage": 36.71, "elapsed_time": "0:53:18", "remaining_time": "1:31:53", "throughput": 2862.01, "total_tokens": 9153560} {"current_steps": 14015, "total_steps": 38160, "loss": 0.1496, "lr": 3.9888579086877403e-05, "epoch": 7.34538784067086, "percentage": 36.73, "elapsed_time": "0:53:19", "remaining_time": "1:31:51", "throughput": 2862.02, "total_tokens": 9156696} {"current_steps": 14020, "total_steps": 38160, "loss": 0.1731, "lr": 3.987939210231794e-05, "epoch": 7.348008385744235, "percentage": 36.74, "elapsed_time": "0:53:20", "remaining_time": "1:31:50", "throughput": 2861.94, "total_tokens": 9159416} {"current_steps": 14025, "total_steps": 38160, "loss": 0.2119, "lr": 3.987020200515941e-05, "epoch": 7.35062893081761, "percentage": 36.75, "elapsed_time": "0:53:21", "remaining_time": "1:31:49", "throughput": 2861.99, "total_tokens": 9162584} {"current_steps": 14030, "total_steps": 38160, "loss": 0.1983, "lr": 3.9861008797324255e-05, "epoch": 7.353249475890985, "percentage": 36.77, "elapsed_time": "0:53:22", "remaining_time": "1:31:48", "throughput": 2862.04, "total_tokens": 9165848} {"current_steps": 14035, "total_steps": 38160, "loss": 0.2542, "lr": 3.9851812480735605e-05, "epoch": 7.35587002096436, "percentage": 36.78, "elapsed_time": "0:53:23", "remaining_time": "1:31:46", "throughput": 2861.93, "total_tokens": 9168600} {"current_steps": 14040, "total_steps": 38160, "loss": 0.1926, "lr": 3.9842613057317235e-05, "epoch": 7.3584905660377355, "percentage": 36.79, "elapsed_time": "0:53:24", "remaining_time": "1:31:45", "throughput": 2862.39, "total_tokens": 9173336} {"current_steps": 14045, "total_steps": 38160, "loss": 0.2004, "lr": 3.9833410528993534e-05, "epoch": 7.361111111111111, "percentage": 36.81, "elapsed_time": "0:53:25", "remaining_time": "1:31:44", "throughput": 2862.41, "total_tokens": 9176376} {"current_steps": 14050, "total_steps": 38160, "loss": 0.1938, "lr": 3.9824204897689585e-05, "epoch": 7.363731656184487, "percentage": 36.82, "elapsed_time": "0:53:26", "remaining_time": "1:31:43", "throughput": 2862.6, "total_tokens": 9180088} {"current_steps": 14055, "total_steps": 38160, "loss": 0.1737, "lr": 3.98149961653311e-05, "epoch": 7.366352201257862, "percentage": 36.83, "elapsed_time": "0:53:28", "remaining_time": "1:31:41", "throughput": 2862.49, "total_tokens": 9183064} {"current_steps": 14060, "total_steps": 38160, "loss": 0.2294, "lr": 3.980578433384442e-05, "epoch": 7.368972746331237, "percentage": 36.84, "elapsed_time": "0:53:29", "remaining_time": "1:31:40", "throughput": 2862.42, "total_tokens": 9186040} {"current_steps": 14065, "total_steps": 38160, "loss": 0.2566, "lr": 3.979656940515659e-05, "epoch": 7.371593291404612, "percentage": 36.86, "elapsed_time": "0:53:30", "remaining_time": "1:31:39", "throughput": 2862.4, "total_tokens": 9189080} {"current_steps": 14070, "total_steps": 38160, "loss": 0.3479, "lr": 3.9787351381195235e-05, "epoch": 7.3742138364779874, "percentage": 36.87, "elapsed_time": "0:53:31", "remaining_time": "1:31:38", "throughput": 2862.32, "total_tokens": 9191992} {"current_steps": 14075, "total_steps": 38160, "loss": 0.2032, "lr": 3.977813026388868e-05, "epoch": 7.376834381551363, "percentage": 36.88, "elapsed_time": "0:53:32", "remaining_time": "1:31:37", "throughput": 2862.1, "total_tokens": 9194520} {"current_steps": 14080, "total_steps": 38160, "loss": 0.2495, "lr": 3.976890605516587e-05, "epoch": 7.379454926624738, "percentage": 36.9, "elapsed_time": "0:53:33", "remaining_time": "1:31:36", "throughput": 2861.76, "total_tokens": 9196632} {"current_steps": 14085, "total_steps": 38160, "loss": 0.2401, "lr": 3.97596787569564e-05, "epoch": 7.382075471698113, "percentage": 36.91, "elapsed_time": "0:53:34", "remaining_time": "1:31:34", "throughput": 2861.8, "total_tokens": 9199832} {"current_steps": 14090, "total_steps": 38160, "loss": 0.2396, "lr": 3.975044837119053e-05, "epoch": 7.384696016771488, "percentage": 36.92, "elapsed_time": "0:53:35", "remaining_time": "1:31:33", "throughput": 2861.95, "total_tokens": 9203384} {"current_steps": 14095, "total_steps": 38160, "loss": 0.191, "lr": 3.974121489979914e-05, "epoch": 7.387316561844864, "percentage": 36.94, "elapsed_time": "0:53:36", "remaining_time": "1:31:32", "throughput": 2861.99, "total_tokens": 9206840} {"current_steps": 14100, "total_steps": 38160, "loss": 0.2783, "lr": 3.973197834471377e-05, "epoch": 7.389937106918239, "percentage": 36.95, "elapsed_time": "0:53:38", "remaining_time": "1:31:31", "throughput": 2861.84, "total_tokens": 9209432} {"current_steps": 14105, "total_steps": 38160, "loss": 0.2213, "lr": 3.9722738707866595e-05, "epoch": 7.3925576519916145, "percentage": 36.96, "elapsed_time": "0:53:39", "remaining_time": "1:31:29", "throughput": 2861.65, "total_tokens": 9212056} {"current_steps": 14110, "total_steps": 38160, "loss": 0.1573, "lr": 3.971349599119046e-05, "epoch": 7.39517819706499, "percentage": 36.98, "elapsed_time": "0:53:40", "remaining_time": "1:31:28", "throughput": 2861.62, "total_tokens": 9215224} {"current_steps": 14115, "total_steps": 38160, "loss": 0.1975, "lr": 3.970425019661881e-05, "epoch": 7.397798742138365, "percentage": 36.99, "elapsed_time": "0:53:41", "remaining_time": "1:31:27", "throughput": 2861.9, "total_tokens": 9219672} {"current_steps": 14120, "total_steps": 38160, "loss": 0.2033, "lr": 3.9695001326085785e-05, "epoch": 7.40041928721174, "percentage": 37.0, "elapsed_time": "0:53:42", "remaining_time": "1:31:26", "throughput": 2861.84, "total_tokens": 9222616} {"current_steps": 14125, "total_steps": 38160, "loss": 0.3727, "lr": 3.968574938152613e-05, "epoch": 7.403039832285115, "percentage": 37.02, "elapsed_time": "0:53:43", "remaining_time": "1:31:25", "throughput": 2862.11, "total_tokens": 9227032} {"current_steps": 14130, "total_steps": 38160, "loss": 0.251, "lr": 3.9676494364875247e-05, "epoch": 7.40566037735849, "percentage": 37.03, "elapsed_time": "0:53:44", "remaining_time": "1:31:24", "throughput": 2861.99, "total_tokens": 9229688} {"current_steps": 14135, "total_steps": 38160, "loss": 0.2661, "lr": 3.966723627806918e-05, "epoch": 7.4082809224318655, "percentage": 37.04, "elapsed_time": "0:53:45", "remaining_time": "1:31:23", "throughput": 2862.07, "total_tokens": 9233016} {"current_steps": 14140, "total_steps": 38160, "loss": 0.2138, "lr": 3.9657975123044624e-05, "epoch": 7.410901467505241, "percentage": 37.05, "elapsed_time": "0:53:47", "remaining_time": "1:31:21", "throughput": 2862.2, "total_tokens": 9236504} {"current_steps": 14145, "total_steps": 38160, "loss": 0.2309, "lr": 3.964871090173888e-05, "epoch": 7.413522012578617, "percentage": 37.07, "elapsed_time": "0:53:48", "remaining_time": "1:31:20", "throughput": 2862.42, "total_tokens": 9240344} {"current_steps": 14150, "total_steps": 38160, "loss": 0.185, "lr": 3.963944361608995e-05, "epoch": 7.416142557651992, "percentage": 37.08, "elapsed_time": "0:53:49", "remaining_time": "1:31:19", "throughput": 2862.29, "total_tokens": 9242904} {"current_steps": 14155, "total_steps": 38160, "loss": 0.2878, "lr": 3.963017326803644e-05, "epoch": 7.418763102725367, "percentage": 37.09, "elapsed_time": "0:53:50", "remaining_time": "1:31:18", "throughput": 2862.3, "total_tokens": 9246072} {"current_steps": 14160, "total_steps": 38160, "loss": 0.2064, "lr": 3.962089985951758e-05, "epoch": 7.421383647798742, "percentage": 37.11, "elapsed_time": "0:53:51", "remaining_time": "1:31:16", "throughput": 2862.18, "total_tokens": 9248696} {"current_steps": 14165, "total_steps": 38160, "loss": 0.3795, "lr": 3.961162339247327e-05, "epoch": 7.424004192872117, "percentage": 37.12, "elapsed_time": "0:53:52", "remaining_time": "1:31:15", "throughput": 2862.0, "total_tokens": 9251160} {"current_steps": 14170, "total_steps": 38160, "loss": 0.2428, "lr": 3.9602343868844055e-05, "epoch": 7.426624737945493, "percentage": 37.13, "elapsed_time": "0:53:53", "remaining_time": "1:31:14", "throughput": 2861.93, "total_tokens": 9254040} {"current_steps": 14175, "total_steps": 38160, "loss": 0.2239, "lr": 3.959306129057109e-05, "epoch": 7.429245283018868, "percentage": 37.15, "elapsed_time": "0:53:54", "remaining_time": "1:31:13", "throughput": 2862.09, "total_tokens": 9257816} {"current_steps": 14180, "total_steps": 38160, "loss": 0.2119, "lr": 3.958377565959619e-05, "epoch": 7.431865828092243, "percentage": 37.16, "elapsed_time": "0:53:55", "remaining_time": "1:31:11", "throughput": 2861.89, "total_tokens": 9260184} {"current_steps": 14185, "total_steps": 38160, "loss": 0.3073, "lr": 3.95744869778618e-05, "epoch": 7.434486373165618, "percentage": 37.17, "elapsed_time": "0:53:56", "remaining_time": "1:31:10", "throughput": 2861.85, "total_tokens": 9263032} {"current_steps": 14190, "total_steps": 38160, "loss": 0.2918, "lr": 3.956519524731101e-05, "epoch": 7.437106918238994, "percentage": 37.19, "elapsed_time": "0:53:57", "remaining_time": "1:31:09", "throughput": 2862.1, "total_tokens": 9267448} {"current_steps": 14195, "total_steps": 38160, "loss": 0.1936, "lr": 3.9555900469887555e-05, "epoch": 7.439727463312369, "percentage": 37.2, "elapsed_time": "0:53:59", "remaining_time": "1:31:08", "throughput": 2862.0, "total_tokens": 9270200} {"current_steps": 14200, "total_steps": 38160, "loss": 0.2248, "lr": 3.954660264753577e-05, "epoch": 7.4423480083857445, "percentage": 37.21, "elapsed_time": "0:54:00", "remaining_time": "1:31:07", "throughput": 2861.9, "total_tokens": 9272856} {"current_steps": 14205, "total_steps": 38160, "loss": 0.2069, "lr": 3.953730178220067e-05, "epoch": 7.44496855345912, "percentage": 37.22, "elapsed_time": "0:54:01", "remaining_time": "1:31:05", "throughput": 2862.05, "total_tokens": 9276504} {"current_steps": 14210, "total_steps": 38160, "loss": 0.28, "lr": 3.952799787582789e-05, "epoch": 7.447589098532495, "percentage": 37.24, "elapsed_time": "0:54:02", "remaining_time": "1:31:04", "throughput": 2862.09, "total_tokens": 9279736} {"current_steps": 14215, "total_steps": 38160, "loss": 0.2268, "lr": 3.9518690930363694e-05, "epoch": 7.45020964360587, "percentage": 37.25, "elapsed_time": "0:54:03", "remaining_time": "1:31:03", "throughput": 2862.08, "total_tokens": 9282680} {"current_steps": 14220, "total_steps": 38160, "loss": 0.1736, "lr": 3.9509380947754994e-05, "epoch": 7.452830188679245, "percentage": 37.26, "elapsed_time": "0:54:04", "remaining_time": "1:31:02", "throughput": 2862.15, "total_tokens": 9285912} {"current_steps": 14225, "total_steps": 38160, "loss": 0.1549, "lr": 3.9500067929949336e-05, "epoch": 7.45545073375262, "percentage": 37.28, "elapsed_time": "0:54:05", "remaining_time": "1:31:00", "throughput": 2862.18, "total_tokens": 9289176} {"current_steps": 14230, "total_steps": 38160, "loss": 0.2157, "lr": 3.9490751878894895e-05, "epoch": 7.4580712788259955, "percentage": 37.29, "elapsed_time": "0:54:06", "remaining_time": "1:30:59", "throughput": 2862.03, "total_tokens": 9291736} {"current_steps": 14235, "total_steps": 38160, "loss": 0.2035, "lr": 3.948143279654047e-05, "epoch": 7.460691823899371, "percentage": 37.3, "elapsed_time": "0:54:07", "remaining_time": "1:30:58", "throughput": 2862.4, "total_tokens": 9296312} {"current_steps": 14240, "total_steps": 38160, "loss": 0.2267, "lr": 3.947211068483553e-05, "epoch": 7.463312368972747, "percentage": 37.32, "elapsed_time": "0:54:08", "remaining_time": "1:30:57", "throughput": 2862.24, "total_tokens": 9298904} {"current_steps": 14245, "total_steps": 38160, "loss": 0.2182, "lr": 3.946278554573013e-05, "epoch": 7.465932914046122, "percentage": 37.33, "elapsed_time": "0:54:09", "remaining_time": "1:30:55", "throughput": 2862.09, "total_tokens": 9301432} {"current_steps": 14250, "total_steps": 38160, "loss": 0.2447, "lr": 3.9453457381175e-05, "epoch": 7.468553459119497, "percentage": 37.34, "elapsed_time": "0:54:10", "remaining_time": "1:30:54", "throughput": 2862.03, "total_tokens": 9304376} {"current_steps": 14255, "total_steps": 38160, "loss": 0.2469, "lr": 3.9444126193121474e-05, "epoch": 7.471174004192872, "percentage": 37.36, "elapsed_time": "0:54:12", "remaining_time": "1:30:53", "throughput": 2862.15, "total_tokens": 9307864} {"current_steps": 14260, "total_steps": 38160, "loss": 0.2619, "lr": 3.943479198352153e-05, "epoch": 7.473794549266247, "percentage": 37.37, "elapsed_time": "0:54:13", "remaining_time": "1:30:52", "throughput": 2862.2, "total_tokens": 9311032} {"current_steps": 14265, "total_steps": 38160, "loss": 0.1928, "lr": 3.94254547543278e-05, "epoch": 7.476415094339623, "percentage": 37.38, "elapsed_time": "0:54:14", "remaining_time": "1:30:51", "throughput": 2862.24, "total_tokens": 9314264} {"current_steps": 14270, "total_steps": 38160, "loss": 0.2089, "lr": 3.9416114507493504e-05, "epoch": 7.479035639412998, "percentage": 37.4, "elapsed_time": "0:54:15", "remaining_time": "1:30:49", "throughput": 2862.24, "total_tokens": 9317272} {"current_steps": 14275, "total_steps": 38160, "loss": 0.2167, "lr": 3.940677124497252e-05, "epoch": 7.481656184486373, "percentage": 37.41, "elapsed_time": "0:54:16", "remaining_time": "1:30:48", "throughput": 2862.24, "total_tokens": 9320504} {"current_steps": 14280, "total_steps": 38160, "loss": 0.199, "lr": 3.939742496871935e-05, "epoch": 7.484276729559748, "percentage": 37.42, "elapsed_time": "0:54:17", "remaining_time": "1:30:47", "throughput": 2862.5, "total_tokens": 9324792} {"current_steps": 14285, "total_steps": 38160, "loss": 0.1447, "lr": 3.9388075680689136e-05, "epoch": 7.486897274633124, "percentage": 37.43, "elapsed_time": "0:54:18", "remaining_time": "1:30:46", "throughput": 2862.37, "total_tokens": 9327544} {"current_steps": 14290, "total_steps": 38160, "loss": 0.2448, "lr": 3.9378723382837634e-05, "epoch": 7.489517819706499, "percentage": 37.45, "elapsed_time": "0:54:19", "remaining_time": "1:30:45", "throughput": 2862.27, "total_tokens": 9330488} {"current_steps": 14295, "total_steps": 38160, "loss": 0.2944, "lr": 3.936936807712124e-05, "epoch": 7.4921383647798745, "percentage": 37.46, "elapsed_time": "0:54:21", "remaining_time": "1:30:44", "throughput": 2862.7, "total_tokens": 9335288} {"current_steps": 14300, "total_steps": 38160, "loss": 0.1887, "lr": 3.936000976549698e-05, "epoch": 7.49475890985325, "percentage": 37.47, "elapsed_time": "0:54:22", "remaining_time": "1:30:43", "throughput": 2862.82, "total_tokens": 9339384} {"current_steps": 14305, "total_steps": 38160, "loss": 0.2639, "lr": 3.935064844992251e-05, "epoch": 7.497379454926625, "percentage": 37.49, "elapsed_time": "0:54:23", "remaining_time": "1:30:41", "throughput": 2862.97, "total_tokens": 9342872} {"current_steps": 14310, "total_steps": 38160, "loss": 0.1836, "lr": 3.93412841323561e-05, "epoch": 7.5, "percentage": 37.5, "elapsed_time": "0:54:24", "remaining_time": "1:30:40", "throughput": 2862.96, "total_tokens": 9345976} {"current_steps": 14315, "total_steps": 38160, "loss": 0.2078, "lr": 3.933191681475666e-05, "epoch": 7.502620545073375, "percentage": 37.51, "elapsed_time": "0:54:25", "remaining_time": "1:30:40", "throughput": 2862.73, "total_tokens": 9349208} {"current_steps": 14320, "total_steps": 38160, "loss": 0.1914, "lr": 3.932254649908373e-05, "epoch": 7.50524109014675, "percentage": 37.53, "elapsed_time": "0:54:26", "remaining_time": "1:30:38", "throughput": 2862.71, "total_tokens": 9352184} {"current_steps": 14325, "total_steps": 38160, "loss": 0.2304, "lr": 3.931317318729748e-05, "epoch": 7.5078616352201255, "percentage": 37.54, "elapsed_time": "0:54:28", "remaining_time": "1:30:37", "throughput": 2862.96, "total_tokens": 9356216} {"current_steps": 14330, "total_steps": 38160, "loss": 0.2148, "lr": 3.930379688135869e-05, "epoch": 7.510482180293501, "percentage": 37.55, "elapsed_time": "0:54:29", "remaining_time": "1:30:36", "throughput": 2863.08, "total_tokens": 9359544} {"current_steps": 14335, "total_steps": 38160, "loss": 0.2071, "lr": 3.929441758322878e-05, "epoch": 7.513102725366876, "percentage": 37.57, "elapsed_time": "0:54:30", "remaining_time": "1:30:34", "throughput": 2862.97, "total_tokens": 9362200} {"current_steps": 14340, "total_steps": 38160, "loss": 0.1827, "lr": 3.928503529486979e-05, "epoch": 7.515723270440252, "percentage": 37.58, "elapsed_time": "0:54:31", "remaining_time": "1:30:33", "throughput": 2863.37, "total_tokens": 9366520} {"current_steps": 14345, "total_steps": 38160, "loss": 0.2321, "lr": 3.927565001824438e-05, "epoch": 7.518343815513627, "percentage": 37.59, "elapsed_time": "0:54:32", "remaining_time": "1:30:33", "throughput": 2863.86, "total_tokens": 9372440} {"current_steps": 14350, "total_steps": 38160, "loss": 0.1588, "lr": 3.926626175531586e-05, "epoch": 7.520964360587002, "percentage": 37.6, "elapsed_time": "0:54:33", "remaining_time": "1:30:31", "throughput": 2863.77, "total_tokens": 9375064} {"current_steps": 14355, "total_steps": 38160, "loss": 0.201, "lr": 3.925687050804814e-05, "epoch": 7.523584905660377, "percentage": 37.62, "elapsed_time": "0:54:34", "remaining_time": "1:30:30", "throughput": 2863.66, "total_tokens": 9377720} {"current_steps": 14360, "total_steps": 38160, "loss": 0.218, "lr": 3.924747627840575e-05, "epoch": 7.526205450733753, "percentage": 37.63, "elapsed_time": "0:54:35", "remaining_time": "1:30:29", "throughput": 2863.75, "total_tokens": 9380984} {"current_steps": 14365, "total_steps": 38160, "loss": 0.1989, "lr": 3.923807906835388e-05, "epoch": 7.528825995807128, "percentage": 37.64, "elapsed_time": "0:54:36", "remaining_time": "1:30:27", "throughput": 2863.74, "total_tokens": 9383992} {"current_steps": 14370, "total_steps": 38160, "loss": 0.192, "lr": 3.92286788798583e-05, "epoch": 7.531446540880503, "percentage": 37.66, "elapsed_time": "0:54:37", "remaining_time": "1:30:26", "throughput": 2863.52, "total_tokens": 9386360} {"current_steps": 14375, "total_steps": 38160, "loss": 0.2935, "lr": 3.921927571488543e-05, "epoch": 7.534067085953878, "percentage": 37.67, "elapsed_time": "0:54:38", "remaining_time": "1:30:25", "throughput": 2863.47, "total_tokens": 9389144} {"current_steps": 14380, "total_steps": 38160, "loss": 0.1628, "lr": 3.9209869575402296e-05, "epoch": 7.536687631027254, "percentage": 37.68, "elapsed_time": "0:54:40", "remaining_time": "1:30:24", "throughput": 2863.37, "total_tokens": 9392024} {"current_steps": 14385, "total_steps": 38160, "loss": 0.2589, "lr": 3.9200460463376566e-05, "epoch": 7.539308176100629, "percentage": 37.7, "elapsed_time": "0:54:41", "remaining_time": "1:30:22", "throughput": 2863.32, "total_tokens": 9394872} {"current_steps": 14390, "total_steps": 38160, "loss": 0.2685, "lr": 3.9191048380776515e-05, "epoch": 7.5419287211740045, "percentage": 37.71, "elapsed_time": "0:54:42", "remaining_time": "1:30:21", "throughput": 2863.15, "total_tokens": 9397304} {"current_steps": 14395, "total_steps": 38160, "loss": 0.2395, "lr": 3.918163332957104e-05, "epoch": 7.54454926624738, "percentage": 37.72, "elapsed_time": "0:54:43", "remaining_time": "1:30:20", "throughput": 2863.25, "total_tokens": 9400664} {"current_steps": 14400, "total_steps": 38160, "loss": 0.2783, "lr": 3.9172215311729665e-05, "epoch": 7.547169811320755, "percentage": 37.74, "elapsed_time": "0:54:44", "remaining_time": "1:30:19", "throughput": 2863.3, "total_tokens": 9403864} {"current_steps": 14405, "total_steps": 38160, "loss": 0.2084, "lr": 3.916279432922254e-05, "epoch": 7.54979035639413, "percentage": 37.75, "elapsed_time": "0:54:45", "remaining_time": "1:30:18", "throughput": 2863.35, "total_tokens": 9407544} {"current_steps": 14410, "total_steps": 38160, "loss": 0.1904, "lr": 3.915337038402041e-05, "epoch": 7.552410901467505, "percentage": 37.76, "elapsed_time": "0:54:46", "remaining_time": "1:30:16", "throughput": 2863.48, "total_tokens": 9410968} {"current_steps": 14415, "total_steps": 38160, "loss": 0.2571, "lr": 3.914394347809467e-05, "epoch": 7.55503144654088, "percentage": 37.78, "elapsed_time": "0:54:47", "remaining_time": "1:30:15", "throughput": 2863.35, "total_tokens": 9413400} {"current_steps": 14420, "total_steps": 38160, "loss": 0.1999, "lr": 3.9134513613417315e-05, "epoch": 7.5576519916142555, "percentage": 37.79, "elapsed_time": "0:54:48", "remaining_time": "1:30:14", "throughput": 2863.21, "total_tokens": 9415832} {"current_steps": 14425, "total_steps": 38160, "loss": 0.3008, "lr": 3.912508079196097e-05, "epoch": 7.560272536687631, "percentage": 37.8, "elapsed_time": "0:54:49", "remaining_time": "1:30:12", "throughput": 2863.29, "total_tokens": 9419064} {"current_steps": 14430, "total_steps": 38160, "loss": 0.2622, "lr": 3.9115645015698866e-05, "epoch": 7.562893081761006, "percentage": 37.81, "elapsed_time": "0:54:50", "remaining_time": "1:30:11", "throughput": 2863.22, "total_tokens": 9421752} {"current_steps": 14435, "total_steps": 38160, "loss": 0.2301, "lr": 3.9106206286604865e-05, "epoch": 7.565513626834382, "percentage": 37.83, "elapsed_time": "0:54:51", "remaining_time": "1:30:10", "throughput": 2863.29, "total_tokens": 9424984} {"current_steps": 14440, "total_steps": 38160, "loss": 0.1832, "lr": 3.909676460665345e-05, "epoch": 7.568134171907757, "percentage": 37.84, "elapsed_time": "0:54:52", "remaining_time": "1:30:08", "throughput": 2863.38, "total_tokens": 9428216} {"current_steps": 14445, "total_steps": 38160, "loss": 0.2063, "lr": 3.908731997781969e-05, "epoch": 7.570754716981132, "percentage": 37.85, "elapsed_time": "0:54:53", "remaining_time": "1:30:07", "throughput": 2863.43, "total_tokens": 9431576} {"current_steps": 14450, "total_steps": 38160, "loss": 0.2581, "lr": 3.907787240207932e-05, "epoch": 7.573375262054507, "percentage": 37.87, "elapsed_time": "0:54:54", "remaining_time": "1:30:06", "throughput": 2863.45, "total_tokens": 9434680} {"current_steps": 14455, "total_steps": 38160, "loss": 0.1367, "lr": 3.9068421881408645e-05, "epoch": 7.575995807127883, "percentage": 37.88, "elapsed_time": "0:54:55", "remaining_time": "1:30:05", "throughput": 2863.34, "total_tokens": 9437432} {"current_steps": 14460, "total_steps": 38160, "loss": 0.1854, "lr": 3.9058968417784614e-05, "epoch": 7.578616352201258, "percentage": 37.89, "elapsed_time": "0:54:57", "remaining_time": "1:30:03", "throughput": 2863.55, "total_tokens": 9441208} {"current_steps": 14465, "total_steps": 38160, "loss": 0.2162, "lr": 3.9049512013184785e-05, "epoch": 7.581236897274633, "percentage": 37.91, "elapsed_time": "0:54:58", "remaining_time": "1:30:02", "throughput": 2863.51, "total_tokens": 9444056} {"current_steps": 14470, "total_steps": 38160, "loss": 0.2689, "lr": 3.9040052669587325e-05, "epoch": 7.583857442348008, "percentage": 37.92, "elapsed_time": "0:54:59", "remaining_time": "1:30:01", "throughput": 2863.42, "total_tokens": 9446968} {"current_steps": 14475, "total_steps": 38160, "loss": 0.1945, "lr": 3.9030590388971026e-05, "epoch": 7.586477987421384, "percentage": 37.93, "elapsed_time": "0:55:00", "remaining_time": "1:30:00", "throughput": 2863.62, "total_tokens": 9450712} {"current_steps": 14480, "total_steps": 38160, "loss": 0.1757, "lr": 3.902112517331529e-05, "epoch": 7.589098532494759, "percentage": 37.95, "elapsed_time": "0:55:01", "remaining_time": "1:29:58", "throughput": 2863.44, "total_tokens": 9453240} {"current_steps": 14485, "total_steps": 38160, "loss": 0.1728, "lr": 3.901165702460012e-05, "epoch": 7.5917190775681345, "percentage": 37.96, "elapsed_time": "0:55:02", "remaining_time": "1:29:57", "throughput": 2863.59, "total_tokens": 9456728} {"current_steps": 14490, "total_steps": 38160, "loss": 0.2544, "lr": 3.900218594480616e-05, "epoch": 7.59433962264151, "percentage": 37.97, "elapsed_time": "0:55:03", "remaining_time": "1:29:56", "throughput": 2863.55, "total_tokens": 9459800} {"current_steps": 14495, "total_steps": 38160, "loss": 0.1962, "lr": 3.899271193591465e-05, "epoch": 7.596960167714885, "percentage": 37.98, "elapsed_time": "0:55:04", "remaining_time": "1:29:55", "throughput": 2863.69, "total_tokens": 9463384} {"current_steps": 14500, "total_steps": 38160, "loss": 0.1869, "lr": 3.8983234999907435e-05, "epoch": 7.59958071278826, "percentage": 38.0, "elapsed_time": "0:55:05", "remaining_time": "1:29:53", "throughput": 2863.72, "total_tokens": 9466520} {"current_steps": 14505, "total_steps": 38160, "loss": 0.1649, "lr": 3.897375513876699e-05, "epoch": 7.602201257861635, "percentage": 38.01, "elapsed_time": "0:55:06", "remaining_time": "1:29:52", "throughput": 2863.78, "total_tokens": 9469944} {"current_steps": 14510, "total_steps": 38160, "loss": 0.1724, "lr": 3.8964272354476396e-05, "epoch": 7.60482180293501, "percentage": 38.02, "elapsed_time": "0:55:07", "remaining_time": "1:29:51", "throughput": 2863.55, "total_tokens": 9472280} {"current_steps": 14515, "total_steps": 38160, "loss": 0.2288, "lr": 3.895478664901933e-05, "epoch": 7.6074423480083855, "percentage": 38.04, "elapsed_time": "0:55:08", "remaining_time": "1:29:50", "throughput": 2863.36, "total_tokens": 9474808} {"current_steps": 14520, "total_steps": 38160, "loss": 0.2516, "lr": 3.89452980243801e-05, "epoch": 7.610062893081761, "percentage": 38.05, "elapsed_time": "0:55:10", "remaining_time": "1:29:49", "throughput": 2863.58, "total_tokens": 9479064} {"current_steps": 14525, "total_steps": 38160, "loss": 0.2682, "lr": 3.893580648254362e-05, "epoch": 7.612683438155136, "percentage": 38.06, "elapsed_time": "0:55:11", "remaining_time": "1:29:48", "throughput": 2863.82, "total_tokens": 9483128} {"current_steps": 14530, "total_steps": 38160, "loss": 0.1934, "lr": 3.8926312025495414e-05, "epoch": 7.615303983228512, "percentage": 38.08, "elapsed_time": "0:55:12", "remaining_time": "1:29:46", "throughput": 2863.8, "total_tokens": 9486136} {"current_steps": 14535, "total_steps": 38160, "loss": 0.4412, "lr": 3.891681465522161e-05, "epoch": 7.617924528301887, "percentage": 38.09, "elapsed_time": "0:55:13", "remaining_time": "1:29:45", "throughput": 2863.61, "total_tokens": 9488568} {"current_steps": 14540, "total_steps": 38160, "loss": 0.2152, "lr": 3.890731437370896e-05, "epoch": 7.620545073375262, "percentage": 38.1, "elapsed_time": "0:55:14", "remaining_time": "1:29:44", "throughput": 2863.83, "total_tokens": 9492440} {"current_steps": 14545, "total_steps": 38160, "loss": 0.1767, "lr": 3.88978111829448e-05, "epoch": 7.623165618448637, "percentage": 38.12, "elapsed_time": "0:55:15", "remaining_time": "1:29:43", "throughput": 2863.74, "total_tokens": 9495192} {"current_steps": 14550, "total_steps": 38160, "loss": 0.2581, "lr": 3.88883050849171e-05, "epoch": 7.6257861635220126, "percentage": 38.13, "elapsed_time": "0:55:16", "remaining_time": "1:29:42", "throughput": 2863.56, "total_tokens": 9497688} {"current_steps": 14555, "total_steps": 38160, "loss": 0.213, "lr": 3.8878796081614417e-05, "epoch": 7.628406708595388, "percentage": 38.14, "elapsed_time": "0:55:17", "remaining_time": "1:29:40", "throughput": 2863.59, "total_tokens": 9500984} {"current_steps": 14560, "total_steps": 38160, "loss": 0.2235, "lr": 3.8869284175025935e-05, "epoch": 7.631027253668763, "percentage": 38.16, "elapsed_time": "0:55:18", "remaining_time": "1:29:39", "throughput": 2863.63, "total_tokens": 9504152} {"current_steps": 14565, "total_steps": 38160, "loss": 0.2381, "lr": 3.885976936714143e-05, "epoch": 7.633647798742138, "percentage": 38.17, "elapsed_time": "0:55:19", "remaining_time": "1:29:38", "throughput": 2863.53, "total_tokens": 9506840} {"current_steps": 14570, "total_steps": 38160, "loss": 0.2581, "lr": 3.885025165995129e-05, "epoch": 7.636268343815514, "percentage": 38.18, "elapsed_time": "0:55:21", "remaining_time": "1:29:36", "throughput": 2863.54, "total_tokens": 9509880} {"current_steps": 14575, "total_steps": 38160, "loss": 0.1914, "lr": 3.884073105544652e-05, "epoch": 7.638888888888889, "percentage": 38.19, "elapsed_time": "0:55:22", "remaining_time": "1:29:35", "throughput": 2863.64, "total_tokens": 9513464} {"current_steps": 14580, "total_steps": 38160, "loss": 0.2247, "lr": 3.8831207555618723e-05, "epoch": 7.6415094339622645, "percentage": 38.21, "elapsed_time": "0:55:23", "remaining_time": "1:29:34", "throughput": 2863.57, "total_tokens": 9516216} {"current_steps": 14585, "total_steps": 38160, "loss": 0.2028, "lr": 3.882168116246009e-05, "epoch": 7.64412997903564, "percentage": 38.22, "elapsed_time": "0:55:24", "remaining_time": "1:29:33", "throughput": 2863.51, "total_tokens": 9519032} {"current_steps": 14590, "total_steps": 38160, "loss": 0.1937, "lr": 3.881215187796344e-05, "epoch": 7.646750524109015, "percentage": 38.23, "elapsed_time": "0:55:25", "remaining_time": "1:29:32", "throughput": 2863.9, "total_tokens": 9523640} {"current_steps": 14595, "total_steps": 38160, "loss": 0.2318, "lr": 3.8802619704122204e-05, "epoch": 7.64937106918239, "percentage": 38.25, "elapsed_time": "0:55:26", "remaining_time": "1:29:30", "throughput": 2863.91, "total_tokens": 9526616} {"current_steps": 14600, "total_steps": 38160, "loss": 0.2351, "lr": 3.8793084642930387e-05, "epoch": 7.651991614255765, "percentage": 38.26, "elapsed_time": "0:55:27", "remaining_time": "1:29:29", "throughput": 2863.94, "total_tokens": 9529656} {"current_steps": 14605, "total_steps": 38160, "loss": 0.2069, "lr": 3.878354669638263e-05, "epoch": 7.65461215932914, "percentage": 38.27, "elapsed_time": "0:55:28", "remaining_time": "1:29:28", "throughput": 2864.02, "total_tokens": 9532984} {"current_steps": 14610, "total_steps": 38160, "loss": 0.2005, "lr": 3.8774005866474155e-05, "epoch": 7.6572327044025155, "percentage": 38.29, "elapsed_time": "0:55:29", "remaining_time": "1:29:27", "throughput": 2863.98, "total_tokens": 9535928} {"current_steps": 14615, "total_steps": 38160, "loss": 0.2455, "lr": 3.876446215520079e-05, "epoch": 7.659853249475891, "percentage": 38.3, "elapsed_time": "0:55:30", "remaining_time": "1:29:25", "throughput": 2864.07, "total_tokens": 9539256} {"current_steps": 14620, "total_steps": 38160, "loss": 0.2562, "lr": 3.875491556455898e-05, "epoch": 7.662473794549266, "percentage": 38.31, "elapsed_time": "0:55:31", "remaining_time": "1:29:24", "throughput": 2864.09, "total_tokens": 9542296} {"current_steps": 14625, "total_steps": 38160, "loss": 0.1802, "lr": 3.8745366096545754e-05, "epoch": 7.665094339622642, "percentage": 38.33, "elapsed_time": "0:55:32", "remaining_time": "1:29:23", "throughput": 2864.13, "total_tokens": 9545368} {"current_steps": 14630, "total_steps": 38160, "loss": 0.2037, "lr": 3.873581375315876e-05, "epoch": 7.667714884696017, "percentage": 38.34, "elapsed_time": "0:55:33", "remaining_time": "1:29:21", "throughput": 2864.19, "total_tokens": 9548472} {"current_steps": 14635, "total_steps": 38160, "loss": 0.1978, "lr": 3.872625853639623e-05, "epoch": 7.670335429769392, "percentage": 38.35, "elapsed_time": "0:55:34", "remaining_time": "1:29:20", "throughput": 2864.36, "total_tokens": 9552248} {"current_steps": 14640, "total_steps": 38160, "loss": 0.409, "lr": 3.871670044825701e-05, "epoch": 7.672955974842767, "percentage": 38.36, "elapsed_time": "0:55:35", "remaining_time": "1:29:19", "throughput": 2864.35, "total_tokens": 9555320} {"current_steps": 14645, "total_steps": 38160, "loss": 0.2233, "lr": 3.870713949074056e-05, "epoch": 7.6755765199161425, "percentage": 38.38, "elapsed_time": "0:55:37", "remaining_time": "1:29:18", "throughput": 2864.5, "total_tokens": 9558904} {"current_steps": 14650, "total_steps": 38160, "loss": 0.2154, "lr": 3.86975756658469e-05, "epoch": 7.678197064989518, "percentage": 38.39, "elapsed_time": "0:55:38", "remaining_time": "1:29:16", "throughput": 2864.43, "total_tokens": 9561624} {"current_steps": 14655, "total_steps": 38160, "loss": 0.3135, "lr": 3.868800897557667e-05, "epoch": 7.680817610062893, "percentage": 38.4, "elapsed_time": "0:55:39", "remaining_time": "1:29:15", "throughput": 2864.42, "total_tokens": 9564568} {"current_steps": 14660, "total_steps": 38160, "loss": 0.2303, "lr": 3.867843942193113e-05, "epoch": 7.683438155136268, "percentage": 38.42, "elapsed_time": "0:55:40", "remaining_time": "1:29:14", "throughput": 2864.47, "total_tokens": 9567704} {"current_steps": 14665, "total_steps": 38160, "loss": 0.1966, "lr": 3.866886700691212e-05, "epoch": 7.686058700209644, "percentage": 38.43, "elapsed_time": "0:55:41", "remaining_time": "1:29:12", "throughput": 2864.68, "total_tokens": 9571512} {"current_steps": 14670, "total_steps": 38160, "loss": 0.3102, "lr": 3.8659291732522075e-05, "epoch": 7.688679245283019, "percentage": 38.44, "elapsed_time": "0:55:42", "remaining_time": "1:29:11", "throughput": 2864.98, "total_tokens": 9575448} {"current_steps": 14675, "total_steps": 38160, "loss": 0.1396, "lr": 3.8649713600764026e-05, "epoch": 7.691299790356394, "percentage": 38.46, "elapsed_time": "0:55:44", "remaining_time": "1:29:11", "throughput": 2865.74, "total_tokens": 9583704} {"current_steps": 14680, "total_steps": 38160, "loss": 0.2005, "lr": 3.864013261364162e-05, "epoch": 7.69392033542977, "percentage": 38.47, "elapsed_time": "0:55:45", "remaining_time": "1:29:10", "throughput": 2865.66, "total_tokens": 9586392} {"current_steps": 14685, "total_steps": 38160, "loss": 0.3194, "lr": 3.8630548773159084e-05, "epoch": 7.696540880503145, "percentage": 38.48, "elapsed_time": "0:55:46", "remaining_time": "1:29:09", "throughput": 2865.64, "total_tokens": 9589336} {"current_steps": 14690, "total_steps": 38160, "loss": 0.2318, "lr": 3.862096208132125e-05, "epoch": 7.69916142557652, "percentage": 38.5, "elapsed_time": "0:55:47", "remaining_time": "1:29:08", "throughput": 2865.81, "total_tokens": 9593016} {"current_steps": 14695, "total_steps": 38160, "loss": 0.2324, "lr": 3.861137254013355e-05, "epoch": 7.701781970649895, "percentage": 38.51, "elapsed_time": "0:55:48", "remaining_time": "1:29:06", "throughput": 2865.62, "total_tokens": 9595512} {"current_steps": 14700, "total_steps": 38160, "loss": 0.2238, "lr": 3.8601780151601996e-05, "epoch": 7.70440251572327, "percentage": 38.52, "elapsed_time": "0:55:49", "remaining_time": "1:29:05", "throughput": 2865.7, "total_tokens": 9598904} {"current_steps": 14705, "total_steps": 38160, "loss": 0.1359, "lr": 3.859218491773321e-05, "epoch": 7.7070230607966455, "percentage": 38.54, "elapsed_time": "0:55:50", "remaining_time": "1:29:04", "throughput": 2865.95, "total_tokens": 9602712} {"current_steps": 14710, "total_steps": 38160, "loss": 0.1837, "lr": 3.858258684053441e-05, "epoch": 7.709643605870021, "percentage": 38.55, "elapsed_time": "0:55:51", "remaining_time": "1:29:03", "throughput": 2865.94, "total_tokens": 9605560} {"current_steps": 14715, "total_steps": 38160, "loss": 0.3292, "lr": 3.8572985922013405e-05, "epoch": 7.712264150943396, "percentage": 38.56, "elapsed_time": "0:55:52", "remaining_time": "1:29:01", "throughput": 2866.04, "total_tokens": 9609048} {"current_steps": 14720, "total_steps": 38160, "loss": 0.222, "lr": 3.856338216417859e-05, "epoch": 7.714884696016772, "percentage": 38.57, "elapsed_time": "0:55:53", "remaining_time": "1:29:00", "throughput": 2866.15, "total_tokens": 9612824} {"current_steps": 14725, "total_steps": 38160, "loss": 0.2, "lr": 3.855377556903897e-05, "epoch": 7.717505241090147, "percentage": 38.59, "elapsed_time": "0:55:54", "remaining_time": "1:28:59", "throughput": 2866.09, "total_tokens": 9615704} {"current_steps": 14730, "total_steps": 38160, "loss": 0.2452, "lr": 3.8544166138604124e-05, "epoch": 7.720125786163522, "percentage": 38.6, "elapsed_time": "0:55:56", "remaining_time": "1:28:58", "throughput": 2866.08, "total_tokens": 9618840} {"current_steps": 14735, "total_steps": 38160, "loss": 0.152, "lr": 3.8534553874884244e-05, "epoch": 7.722746331236897, "percentage": 38.61, "elapsed_time": "0:55:57", "remaining_time": "1:28:57", "throughput": 2866.21, "total_tokens": 9622552} {"current_steps": 14740, "total_steps": 38160, "loss": 0.2868, "lr": 3.852493877989011e-05, "epoch": 7.7253668763102725, "percentage": 38.63, "elapsed_time": "0:55:58", "remaining_time": "1:28:55", "throughput": 2866.27, "total_tokens": 9625720} {"current_steps": 14745, "total_steps": 38160, "loss": 0.2154, "lr": 3.851532085563308e-05, "epoch": 7.727987421383648, "percentage": 38.64, "elapsed_time": "0:55:59", "remaining_time": "1:28:54", "throughput": 2866.2, "total_tokens": 9628664} {"current_steps": 14750, "total_steps": 38160, "loss": 0.2223, "lr": 3.850570010412511e-05, "epoch": 7.730607966457023, "percentage": 38.65, "elapsed_time": "0:56:00", "remaining_time": "1:28:53", "throughput": 2866.24, "total_tokens": 9632088} {"current_steps": 14755, "total_steps": 38160, "loss": 0.2216, "lr": 3.8496076527378766e-05, "epoch": 7.733228511530398, "percentage": 38.67, "elapsed_time": "0:56:01", "remaining_time": "1:28:52", "throughput": 2866.27, "total_tokens": 9635160} {"current_steps": 14760, "total_steps": 38160, "loss": 0.2439, "lr": 3.848645012740718e-05, "epoch": 7.735849056603773, "percentage": 38.68, "elapsed_time": "0:56:02", "remaining_time": "1:28:51", "throughput": 2866.35, "total_tokens": 9638776} {"current_steps": 14765, "total_steps": 38160, "loss": 0.2275, "lr": 3.8476820906224096e-05, "epoch": 7.738469601677149, "percentage": 38.69, "elapsed_time": "0:56:03", "remaining_time": "1:28:49", "throughput": 2866.31, "total_tokens": 9641624} {"current_steps": 14770, "total_steps": 38160, "loss": 0.2785, "lr": 3.846718886584382e-05, "epoch": 7.741090146750524, "percentage": 38.71, "elapsed_time": "0:56:05", "remaining_time": "1:28:50", "throughput": 2866.89, "total_tokens": 9649176} {"current_steps": 14775, "total_steps": 38160, "loss": 0.3375, "lr": 3.845755400828128e-05, "epoch": 7.7437106918239, "percentage": 38.72, "elapsed_time": "0:56:06", "remaining_time": "1:28:48", "throughput": 2866.76, "total_tokens": 9651768} {"current_steps": 14780, "total_steps": 38160, "loss": 0.1532, "lr": 3.844791633555198e-05, "epoch": 7.746331236897275, "percentage": 38.73, "elapsed_time": "0:56:07", "remaining_time": "1:28:47", "throughput": 2866.7, "total_tokens": 9654552} {"current_steps": 14785, "total_steps": 38160, "loss": 0.1955, "lr": 3.8438275849671996e-05, "epoch": 7.74895178197065, "percentage": 38.74, "elapsed_time": "0:56:08", "remaining_time": "1:28:46", "throughput": 2866.58, "total_tokens": 9657112} {"current_steps": 14790, "total_steps": 38160, "loss": 0.2152, "lr": 3.842863255265802e-05, "epoch": 7.751572327044025, "percentage": 38.76, "elapsed_time": "0:56:10", "remaining_time": "1:28:45", "throughput": 2866.75, "total_tokens": 9661176} {"current_steps": 14795, "total_steps": 38160, "loss": 0.2239, "lr": 3.841898644652732e-05, "epoch": 7.7541928721174, "percentage": 38.77, "elapsed_time": "0:56:11", "remaining_time": "1:28:43", "throughput": 2866.53, "total_tokens": 9663480} {"current_steps": 14800, "total_steps": 38160, "loss": 0.2273, "lr": 3.840933753329774e-05, "epoch": 7.756813417190775, "percentage": 38.78, "elapsed_time": "0:56:12", "remaining_time": "1:28:42", "throughput": 2866.58, "total_tokens": 9666808} {"current_steps": 14805, "total_steps": 38160, "loss": 0.2955, "lr": 3.839968581498773e-05, "epoch": 7.759433962264151, "percentage": 38.8, "elapsed_time": "0:56:13", "remaining_time": "1:28:41", "throughput": 2866.42, "total_tokens": 9669336} {"current_steps": 14810, "total_steps": 38160, "loss": 0.2195, "lr": 3.839003129361632e-05, "epoch": 7.762054507337526, "percentage": 38.81, "elapsed_time": "0:56:14", "remaining_time": "1:28:40", "throughput": 2866.32, "total_tokens": 9671928} {"current_steps": 14815, "total_steps": 38160, "loss": 0.3004, "lr": 3.8380373971203134e-05, "epoch": 7.764675052410902, "percentage": 38.82, "elapsed_time": "0:56:15", "remaining_time": "1:28:38", "throughput": 2866.59, "total_tokens": 9676120} {"current_steps": 14820, "total_steps": 38160, "loss": 0.2057, "lr": 3.8370713849768346e-05, "epoch": 7.767295597484277, "percentage": 38.84, "elapsed_time": "0:56:16", "remaining_time": "1:28:37", "throughput": 2866.58, "total_tokens": 9679032} {"current_steps": 14825, "total_steps": 38160, "loss": 0.1933, "lr": 3.8361050931332774e-05, "epoch": 7.769916142557652, "percentage": 38.85, "elapsed_time": "0:56:17", "remaining_time": "1:28:36", "throughput": 2866.73, "total_tokens": 9682744} {"current_steps": 14830, "total_steps": 38160, "loss": 0.3217, "lr": 3.835138521791778e-05, "epoch": 7.772536687631027, "percentage": 38.86, "elapsed_time": "0:56:18", "remaining_time": "1:28:35", "throughput": 2866.7, "total_tokens": 9686040} {"current_steps": 14835, "total_steps": 38160, "loss": 0.2262, "lr": 3.8341716711545314e-05, "epoch": 7.7751572327044025, "percentage": 38.88, "elapsed_time": "0:56:19", "remaining_time": "1:28:34", "throughput": 2866.95, "total_tokens": 9690168} {"current_steps": 14840, "total_steps": 38160, "loss": 0.2229, "lr": 3.833204541423793e-05, "epoch": 7.777777777777778, "percentage": 38.89, "elapsed_time": "0:56:20", "remaining_time": "1:28:32", "throughput": 2867.06, "total_tokens": 9693496} {"current_steps": 14845, "total_steps": 38160, "loss": 0.2331, "lr": 3.832237132801874e-05, "epoch": 7.780398322851153, "percentage": 38.9, "elapsed_time": "0:56:22", "remaining_time": "1:28:31", "throughput": 2867.14, "total_tokens": 9696760} {"current_steps": 14850, "total_steps": 38160, "loss": 0.2907, "lr": 3.831269445491146e-05, "epoch": 7.783018867924528, "percentage": 38.92, "elapsed_time": "0:56:23", "remaining_time": "1:28:30", "throughput": 2867.11, "total_tokens": 9699672} {"current_steps": 14855, "total_steps": 38160, "loss": 0.1893, "lr": 3.8303014796940375e-05, "epoch": 7.785639412997903, "percentage": 38.93, "elapsed_time": "0:56:24", "remaining_time": "1:28:29", "throughput": 2867.26, "total_tokens": 9703384} {"current_steps": 14860, "total_steps": 38160, "loss": 0.2846, "lr": 3.829333235613036e-05, "epoch": 7.788259958071279, "percentage": 38.94, "elapsed_time": "0:56:25", "remaining_time": "1:28:28", "throughput": 2867.22, "total_tokens": 9706328} {"current_steps": 14865, "total_steps": 38160, "loss": 0.2489, "lr": 3.828364713450688e-05, "epoch": 7.790880503144654, "percentage": 38.95, "elapsed_time": "0:56:26", "remaining_time": "1:28:26", "throughput": 2867.16, "total_tokens": 9709432} {"current_steps": 14870, "total_steps": 38160, "loss": 0.3318, "lr": 3.827395913409597e-05, "epoch": 7.79350104821803, "percentage": 38.97, "elapsed_time": "0:56:27", "remaining_time": "1:28:25", "throughput": 2867.18, "total_tokens": 9712696} {"current_steps": 14875, "total_steps": 38160, "loss": 0.2325, "lr": 3.826426835692424e-05, "epoch": 7.796121593291405, "percentage": 38.98, "elapsed_time": "0:56:28", "remaining_time": "1:28:24", "throughput": 2867.19, "total_tokens": 9715704} {"current_steps": 14880, "total_steps": 38160, "loss": 0.4263, "lr": 3.825457480501891e-05, "epoch": 7.79874213836478, "percentage": 38.99, "elapsed_time": "0:56:29", "remaining_time": "1:28:23", "throughput": 2867.53, "total_tokens": 9720344} {"current_steps": 14885, "total_steps": 38160, "loss": 0.2347, "lr": 3.824487848040773e-05, "epoch": 7.801362683438155, "percentage": 39.01, "elapsed_time": "0:56:30", "remaining_time": "1:28:22", "throughput": 2867.59, "total_tokens": 9723544} {"current_steps": 14890, "total_steps": 38160, "loss": 0.3844, "lr": 3.823517938511908e-05, "epoch": 7.80398322851153, "percentage": 39.02, "elapsed_time": "0:56:31", "remaining_time": "1:28:20", "throughput": 2867.54, "total_tokens": 9726424} {"current_steps": 14895, "total_steps": 38160, "loss": 0.1825, "lr": 3.8225477521181906e-05, "epoch": 7.806603773584905, "percentage": 39.03, "elapsed_time": "0:56:32", "remaining_time": "1:28:19", "throughput": 2867.43, "total_tokens": 9729144} {"current_steps": 14900, "total_steps": 38160, "loss": 0.1993, "lr": 3.821577289062571e-05, "epoch": 7.809224318658281, "percentage": 39.05, "elapsed_time": "0:56:34", "remaining_time": "1:28:18", "throughput": 2867.52, "total_tokens": 9732504} {"current_steps": 14905, "total_steps": 38160, "loss": 0.2215, "lr": 3.82060654954806e-05, "epoch": 7.811844863731656, "percentage": 39.06, "elapsed_time": "0:56:35", "remaining_time": "1:28:17", "throughput": 2867.93, "total_tokens": 9737048} {"current_steps": 14910, "total_steps": 38160, "loss": 0.3008, "lr": 3.819635533777726e-05, "epoch": 7.814465408805032, "percentage": 39.07, "elapsed_time": "0:56:36", "remaining_time": "1:28:16", "throughput": 2867.83, "total_tokens": 9739960} {"current_steps": 14915, "total_steps": 38160, "loss": 0.1599, "lr": 3.8186642419546924e-05, "epoch": 7.817085953878407, "percentage": 39.09, "elapsed_time": "0:56:37", "remaining_time": "1:28:14", "throughput": 2867.91, "total_tokens": 9743288} {"current_steps": 14920, "total_steps": 38160, "loss": 0.3448, "lr": 3.817692674282145e-05, "epoch": 7.819706498951782, "percentage": 39.1, "elapsed_time": "0:56:38", "remaining_time": "1:28:13", "throughput": 2867.85, "total_tokens": 9746072} {"current_steps": 14925, "total_steps": 38160, "loss": 0.2869, "lr": 3.816720830963322e-05, "epoch": 7.822327044025157, "percentage": 39.11, "elapsed_time": "0:56:39", "remaining_time": "1:28:12", "throughput": 2867.81, "total_tokens": 9748920} {"current_steps": 14930, "total_steps": 38160, "loss": 0.1803, "lr": 3.815748712201523e-05, "epoch": 7.8249475890985325, "percentage": 39.12, "elapsed_time": "0:56:40", "remaining_time": "1:28:10", "throughput": 2867.81, "total_tokens": 9751864} {"current_steps": 14935, "total_steps": 38160, "loss": 0.2632, "lr": 3.814776318200105e-05, "epoch": 7.827568134171908, "percentage": 39.14, "elapsed_time": "0:56:41", "remaining_time": "1:28:09", "throughput": 2867.85, "total_tokens": 9755128} {"current_steps": 14940, "total_steps": 38160, "loss": 0.1619, "lr": 3.8138036491624805e-05, "epoch": 7.830188679245283, "percentage": 39.15, "elapsed_time": "0:56:42", "remaining_time": "1:28:08", "throughput": 2867.77, "total_tokens": 9757976} {"current_steps": 14945, "total_steps": 38160, "loss": 0.192, "lr": 3.812830705292122e-05, "epoch": 7.832809224318658, "percentage": 39.16, "elapsed_time": "0:56:43", "remaining_time": "1:28:07", "throughput": 2867.87, "total_tokens": 9761464} {"current_steps": 14950, "total_steps": 38160, "loss": 0.2424, "lr": 3.8118574867925564e-05, "epoch": 7.835429769392033, "percentage": 39.18, "elapsed_time": "0:56:45", "remaining_time": "1:28:07", "throughput": 2868.23, "total_tokens": 9768408} {"current_steps": 14955, "total_steps": 38160, "loss": 0.2422, "lr": 3.810883993867371e-05, "epoch": 7.838050314465409, "percentage": 39.19, "elapsed_time": "0:56:46", "remaining_time": "1:28:06", "throughput": 2868.32, "total_tokens": 9771832} {"current_steps": 14960, "total_steps": 38160, "loss": 0.2802, "lr": 3.80991022672021e-05, "epoch": 7.840670859538784, "percentage": 39.2, "elapsed_time": "0:56:47", "remaining_time": "1:28:04", "throughput": 2868.54, "total_tokens": 9775736} {"current_steps": 14965, "total_steps": 38160, "loss": 0.2636, "lr": 3.8089361855547744e-05, "epoch": 7.84329140461216, "percentage": 39.22, "elapsed_time": "0:56:48", "remaining_time": "1:28:03", "throughput": 2868.62, "total_tokens": 9779096} {"current_steps": 14970, "total_steps": 38160, "loss": 0.3663, "lr": 3.8079618705748214e-05, "epoch": 7.845911949685535, "percentage": 39.23, "elapsed_time": "0:56:50", "remaining_time": "1:28:02", "throughput": 2868.61, "total_tokens": 9782264} {"current_steps": 14975, "total_steps": 38160, "loss": 0.197, "lr": 3.806987281984167e-05, "epoch": 7.84853249475891, "percentage": 39.24, "elapsed_time": "0:56:51", "remaining_time": "1:28:01", "throughput": 2868.64, "total_tokens": 9785368} {"current_steps": 14980, "total_steps": 38160, "loss": 0.1859, "lr": 3.806012419986684e-05, "epoch": 7.851153039832285, "percentage": 39.26, "elapsed_time": "0:56:52", "remaining_time": "1:28:00", "throughput": 2868.89, "total_tokens": 9789304} {"current_steps": 14985, "total_steps": 38160, "loss": 0.3164, "lr": 3.805037284786303e-05, "epoch": 7.85377358490566, "percentage": 39.27, "elapsed_time": "0:56:53", "remaining_time": "1:27:58", "throughput": 2868.81, "total_tokens": 9792184} {"current_steps": 14990, "total_steps": 38160, "loss": 0.305, "lr": 3.804061876587009e-05, "epoch": 7.856394129979035, "percentage": 39.28, "elapsed_time": "0:56:54", "remaining_time": "1:27:57", "throughput": 2868.98, "total_tokens": 9795928} {"current_steps": 14995, "total_steps": 38160, "loss": 0.2122, "lr": 3.80308619559285e-05, "epoch": 7.859014675052411, "percentage": 39.3, "elapsed_time": "0:56:55", "remaining_time": "1:27:56", "throughput": 2868.94, "total_tokens": 9798776} {"current_steps": 15000, "total_steps": 38160, "loss": 0.1938, "lr": 3.802110242007925e-05, "epoch": 7.861635220125786, "percentage": 39.31, "elapsed_time": "0:56:56", "remaining_time": "1:27:55", "throughput": 2869.03, "total_tokens": 9802008} {"current_steps": 15005, "total_steps": 38160, "loss": 0.3106, "lr": 3.801134016036392e-05, "epoch": 7.864255765199162, "percentage": 39.32, "elapsed_time": "0:56:57", "remaining_time": "1:27:53", "throughput": 2869.22, "total_tokens": 9805912} {"current_steps": 15010, "total_steps": 38160, "loss": 0.2187, "lr": 3.8001575178824665e-05, "epoch": 7.866876310272537, "percentage": 39.33, "elapsed_time": "0:56:58", "remaining_time": "1:27:52", "throughput": 2869.15, "total_tokens": 9808664} {"current_steps": 15015, "total_steps": 38160, "loss": 0.1975, "lr": 3.799180747750422e-05, "epoch": 7.869496855345912, "percentage": 39.35, "elapsed_time": "0:56:59", "remaining_time": "1:27:51", "throughput": 2869.05, "total_tokens": 9811256} {"current_steps": 15020, "total_steps": 38160, "loss": 0.2564, "lr": 3.798203705844586e-05, "epoch": 7.872117400419287, "percentage": 39.36, "elapsed_time": "0:57:01", "remaining_time": "1:27:50", "throughput": 2869.45, "total_tokens": 9816440} {"current_steps": 15025, "total_steps": 38160, "loss": 0.2182, "lr": 3.7972263923693476e-05, "epoch": 7.8747379454926625, "percentage": 39.37, "elapsed_time": "0:57:02", "remaining_time": "1:27:49", "throughput": 2869.23, "total_tokens": 9818776} {"current_steps": 15030, "total_steps": 38160, "loss": 0.238, "lr": 3.796248807529145e-05, "epoch": 7.877358490566038, "percentage": 39.39, "elapsed_time": "0:57:03", "remaining_time": "1:27:47", "throughput": 2869.44, "total_tokens": 9822520} {"current_steps": 15035, "total_steps": 38160, "loss": 0.1493, "lr": 3.795270951528482e-05, "epoch": 7.879979035639413, "percentage": 39.4, "elapsed_time": "0:57:04", "remaining_time": "1:27:46", "throughput": 2869.44, "total_tokens": 9825496} {"current_steps": 15040, "total_steps": 38160, "loss": 0.3192, "lr": 3.7942928245719124e-05, "epoch": 7.882599580712788, "percentage": 39.41, "elapsed_time": "0:57:05", "remaining_time": "1:27:45", "throughput": 2869.51, "total_tokens": 9829080} {"current_steps": 15045, "total_steps": 38160, "loss": 0.2299, "lr": 3.7933144268640495e-05, "epoch": 7.885220125786163, "percentage": 39.43, "elapsed_time": "0:57:06", "remaining_time": "1:27:44", "throughput": 2869.53, "total_tokens": 9832056} {"current_steps": 15050, "total_steps": 38160, "loss": 0.209, "lr": 3.7923357586095645e-05, "epoch": 7.887840670859539, "percentage": 39.44, "elapsed_time": "0:57:07", "remaining_time": "1:27:42", "throughput": 2869.42, "total_tokens": 9834680} {"current_steps": 15055, "total_steps": 38160, "loss": 0.2884, "lr": 3.7913568200131823e-05, "epoch": 7.890461215932914, "percentage": 39.45, "elapsed_time": "0:57:08", "remaining_time": "1:27:41", "throughput": 2869.54, "total_tokens": 9838008} {"current_steps": 15060, "total_steps": 38160, "loss": 0.2781, "lr": 3.790377611279685e-05, "epoch": 7.8930817610062896, "percentage": 39.47, "elapsed_time": "0:57:09", "remaining_time": "1:27:40", "throughput": 2869.71, "total_tokens": 9841528} {"current_steps": 15065, "total_steps": 38160, "loss": 0.3515, "lr": 3.789398132613914e-05, "epoch": 7.895702306079665, "percentage": 39.48, "elapsed_time": "0:57:10", "remaining_time": "1:27:39", "throughput": 2869.76, "total_tokens": 9844984} {"current_steps": 15070, "total_steps": 38160, "loss": 0.201, "lr": 3.788418384220763e-05, "epoch": 7.89832285115304, "percentage": 39.49, "elapsed_time": "0:57:11", "remaining_time": "1:27:38", "throughput": 2869.77, "total_tokens": 9848568} {"current_steps": 15075, "total_steps": 38160, "loss": 0.1495, "lr": 3.7874383663051846e-05, "epoch": 7.900943396226415, "percentage": 39.5, "elapsed_time": "0:57:12", "remaining_time": "1:27:36", "throughput": 2869.81, "total_tokens": 9851640} {"current_steps": 15080, "total_steps": 38160, "loss": 0.1837, "lr": 3.7864580790721894e-05, "epoch": 7.90356394129979, "percentage": 39.52, "elapsed_time": "0:57:13", "remaining_time": "1:27:35", "throughput": 2869.96, "total_tokens": 9855192} {"current_steps": 15085, "total_steps": 38160, "loss": 0.2397, "lr": 3.785477522726839e-05, "epoch": 7.906184486373165, "percentage": 39.53, "elapsed_time": "0:57:14", "remaining_time": "1:27:34", "throughput": 2869.93, "total_tokens": 9858072} {"current_steps": 15090, "total_steps": 38160, "loss": 0.2038, "lr": 3.784496697474258e-05, "epoch": 7.908805031446541, "percentage": 39.54, "elapsed_time": "0:57:16", "remaining_time": "1:27:33", "throughput": 2870.06, "total_tokens": 9861784} {"current_steps": 15095, "total_steps": 38160, "loss": 0.2947, "lr": 3.783515603519622e-05, "epoch": 7.911425576519916, "percentage": 39.56, "elapsed_time": "0:57:17", "remaining_time": "1:27:32", "throughput": 2870.28, "total_tokens": 9866104} {"current_steps": 15100, "total_steps": 38160, "loss": 0.2928, "lr": 3.782534241068164e-05, "epoch": 7.914046121593291, "percentage": 39.57, "elapsed_time": "0:57:18", "remaining_time": "1:27:31", "throughput": 2870.41, "total_tokens": 9869816} {"current_steps": 15105, "total_steps": 38160, "loss": 0.1655, "lr": 3.781552610325175e-05, "epoch": 7.916666666666667, "percentage": 39.58, "elapsed_time": "0:57:19", "remaining_time": "1:27:29", "throughput": 2870.32, "total_tokens": 9872504} {"current_steps": 15110, "total_steps": 38160, "loss": 0.2319, "lr": 3.780570711496001e-05, "epoch": 7.919287211740042, "percentage": 39.6, "elapsed_time": "0:57:20", "remaining_time": "1:27:28", "throughput": 2870.29, "total_tokens": 9875320} {"current_steps": 15115, "total_steps": 38160, "loss": 0.206, "lr": 3.779588544786044e-05, "epoch": 7.921907756813417, "percentage": 39.61, "elapsed_time": "0:57:21", "remaining_time": "1:27:27", "throughput": 2870.26, "total_tokens": 9878136} {"current_steps": 15120, "total_steps": 38160, "loss": 0.1995, "lr": 3.778606110400761e-05, "epoch": 7.9245283018867925, "percentage": 39.62, "elapsed_time": "0:57:22", "remaining_time": "1:27:25", "throughput": 2870.09, "total_tokens": 9880792} {"current_steps": 15125, "total_steps": 38160, "loss": 0.2247, "lr": 3.7776234085456665e-05, "epoch": 7.927148846960168, "percentage": 39.64, "elapsed_time": "0:57:23", "remaining_time": "1:27:24", "throughput": 2870.21, "total_tokens": 9884312} {"current_steps": 15130, "total_steps": 38160, "loss": 0.2319, "lr": 3.776640439426332e-05, "epoch": 7.929769392033543, "percentage": 39.65, "elapsed_time": "0:57:24", "remaining_time": "1:27:23", "throughput": 2870.15, "total_tokens": 9887416} {"current_steps": 15135, "total_steps": 38160, "loss": 0.1504, "lr": 3.775657203248381e-05, "epoch": 7.932389937106918, "percentage": 39.66, "elapsed_time": "0:57:25", "remaining_time": "1:27:22", "throughput": 2870.06, "total_tokens": 9890200} {"current_steps": 15140, "total_steps": 38160, "loss": 0.22, "lr": 3.774673700217497e-05, "epoch": 7.935010482180293, "percentage": 39.68, "elapsed_time": "0:57:27", "remaining_time": "1:27:21", "throughput": 2870.12, "total_tokens": 9893368} {"current_steps": 15145, "total_steps": 38160, "loss": 0.2732, "lr": 3.773689930539418e-05, "epoch": 7.937631027253669, "percentage": 39.69, "elapsed_time": "0:57:28", "remaining_time": "1:27:20", "throughput": 2870.38, "total_tokens": 9899224} {"current_steps": 15150, "total_steps": 38160, "loss": 0.2631, "lr": 3.7727058944199354e-05, "epoch": 7.940251572327044, "percentage": 39.7, "elapsed_time": "0:57:29", "remaining_time": "1:27:19", "throughput": 2870.29, "total_tokens": 9901944} {"current_steps": 15155, "total_steps": 38160, "loss": 0.3045, "lr": 3.7717215920648994e-05, "epoch": 7.9428721174004195, "percentage": 39.71, "elapsed_time": "0:57:30", "remaining_time": "1:27:18", "throughput": 2870.43, "total_tokens": 9905720} {"current_steps": 15160, "total_steps": 38160, "loss": 0.3141, "lr": 3.770737023680215e-05, "epoch": 7.945492662473795, "percentage": 39.73, "elapsed_time": "0:57:32", "remaining_time": "1:27:17", "throughput": 2870.3, "total_tokens": 9908440} {"current_steps": 15165, "total_steps": 38160, "loss": 0.258, "lr": 3.7697521894718436e-05, "epoch": 7.94811320754717, "percentage": 39.74, "elapsed_time": "0:57:33", "remaining_time": "1:27:16", "throughput": 2870.24, "total_tokens": 9911256} {"current_steps": 15170, "total_steps": 38160, "loss": 0.2465, "lr": 3.7687670896458e-05, "epoch": 7.950733752620545, "percentage": 39.75, "elapsed_time": "0:57:34", "remaining_time": "1:27:14", "throughput": 2869.94, "total_tokens": 9913336} {"current_steps": 15175, "total_steps": 38160, "loss": 0.1849, "lr": 3.7677817244081556e-05, "epoch": 7.95335429769392, "percentage": 39.77, "elapsed_time": "0:57:35", "remaining_time": "1:27:13", "throughput": 2870.1, "total_tokens": 9917048} {"current_steps": 15180, "total_steps": 38160, "loss": 0.1895, "lr": 3.766796093965038e-05, "epoch": 7.955974842767295, "percentage": 39.78, "elapsed_time": "0:57:36", "remaining_time": "1:27:12", "throughput": 2870.27, "total_tokens": 9920952} {"current_steps": 15185, "total_steps": 38160, "loss": 0.1694, "lr": 3.76581019852263e-05, "epoch": 7.9585953878406706, "percentage": 39.79, "elapsed_time": "0:57:37", "remaining_time": "1:27:11", "throughput": 2870.27, "total_tokens": 9924376} {"current_steps": 15190, "total_steps": 38160, "loss": 0.2556, "lr": 3.7648240382871705e-05, "epoch": 7.961215932914046, "percentage": 39.81, "elapsed_time": "0:57:38", "remaining_time": "1:27:10", "throughput": 2870.16, "total_tokens": 9927160} {"current_steps": 15195, "total_steps": 38160, "loss": 0.2523, "lr": 3.763837613464951e-05, "epoch": 7.963836477987421, "percentage": 39.82, "elapsed_time": "0:57:39", "remaining_time": "1:27:08", "throughput": 2870.34, "total_tokens": 9930840} {"current_steps": 15200, "total_steps": 38160, "loss": 0.3002, "lr": 3.7628509242623215e-05, "epoch": 7.966457023060797, "percentage": 39.83, "elapsed_time": "0:57:40", "remaining_time": "1:27:07", "throughput": 2870.43, "total_tokens": 9934104} {"current_steps": 15205, "total_steps": 38160, "loss": 0.2085, "lr": 3.761863970885686e-05, "epoch": 7.969077568134172, "percentage": 39.85, "elapsed_time": "0:57:41", "remaining_time": "1:27:06", "throughput": 2870.4, "total_tokens": 9937016} {"current_steps": 15210, "total_steps": 38160, "loss": 0.2692, "lr": 3.760876753541504e-05, "epoch": 7.971698113207547, "percentage": 39.86, "elapsed_time": "0:57:42", "remaining_time": "1:27:05", "throughput": 2870.31, "total_tokens": 9939736} {"current_steps": 15215, "total_steps": 38160, "loss": 0.2496, "lr": 3.7598892724362907e-05, "epoch": 7.9743186582809225, "percentage": 39.87, "elapsed_time": "0:57:43", "remaining_time": "1:27:03", "throughput": 2870.31, "total_tokens": 9942744} {"current_steps": 15220, "total_steps": 38160, "loss": 0.2761, "lr": 3.758901527776615e-05, "epoch": 7.976939203354298, "percentage": 39.88, "elapsed_time": "0:57:45", "remaining_time": "1:27:02", "throughput": 2870.44, "total_tokens": 9946776} {"current_steps": 15225, "total_steps": 38160, "loss": 0.2133, "lr": 3.7579135197691015e-05, "epoch": 7.979559748427673, "percentage": 39.9, "elapsed_time": "0:57:46", "remaining_time": "1:27:01", "throughput": 2870.27, "total_tokens": 9949304} {"current_steps": 15230, "total_steps": 38160, "loss": 0.2267, "lr": 3.7569252486204306e-05, "epoch": 7.982180293501048, "percentage": 39.91, "elapsed_time": "0:57:47", "remaining_time": "1:27:00", "throughput": 2870.4, "total_tokens": 9953112} {"current_steps": 15235, "total_steps": 38160, "loss": 0.2656, "lr": 3.755936714537338e-05, "epoch": 7.984800838574423, "percentage": 39.92, "elapsed_time": "0:57:48", "remaining_time": "1:26:59", "throughput": 2870.38, "total_tokens": 9956056} {"current_steps": 15240, "total_steps": 38160, "loss": 0.2382, "lr": 3.754947917726612e-05, "epoch": 7.987421383647799, "percentage": 39.94, "elapsed_time": "0:57:49", "remaining_time": "1:26:58", "throughput": 2870.48, "total_tokens": 9959416} {"current_steps": 15245, "total_steps": 38160, "loss": 0.1839, "lr": 3.7539588583951e-05, "epoch": 7.990041928721174, "percentage": 39.95, "elapsed_time": "0:57:50", "remaining_time": "1:26:56", "throughput": 2870.55, "total_tokens": 9962680} {"current_steps": 15250, "total_steps": 38160, "loss": 0.3443, "lr": 3.752969536749701e-05, "epoch": 7.9926624737945495, "percentage": 39.96, "elapsed_time": "0:57:51", "remaining_time": "1:26:55", "throughput": 2870.79, "total_tokens": 9966616} {"current_steps": 15255, "total_steps": 38160, "loss": 0.2542, "lr": 3.7519799529973685e-05, "epoch": 7.995283018867925, "percentage": 39.98, "elapsed_time": "0:57:53", "remaining_time": "1:26:54", "throughput": 2871.08, "total_tokens": 9971864} {"current_steps": 15260, "total_steps": 38160, "loss": 0.4997, "lr": 3.7509901073451134e-05, "epoch": 7.9979035639413, "percentage": 39.99, "elapsed_time": "0:57:54", "remaining_time": "1:26:53", "throughput": 2871.19, "total_tokens": 9975864} {"current_steps": 15264, "total_steps": 38160, "eval_loss": 0.6323651075363159, "epoch": 8.0, "percentage": 40.0, "elapsed_time": "0:58:07", "remaining_time": "1:27:10", "throughput": 2861.14, "total_tokens": 9977520} {"current_steps": 15265, "total_steps": 38160, "loss": 0.2409, "lr": 3.7500000000000003e-05, "epoch": 8.000524109014675, "percentage": 40.0, "elapsed_time": "0:58:10", "remaining_time": "1:27:15", "throughput": 2858.46, "total_tokens": 9978032} {"current_steps": 15270, "total_steps": 38160, "loss": 0.2744, "lr": 3.749009631169147e-05, "epoch": 8.00314465408805, "percentage": 40.02, "elapsed_time": "0:58:11", "remaining_time": "1:27:14", "throughput": 2858.57, "total_tokens": 9981616} {"current_steps": 15275, "total_steps": 38160, "loss": 0.1285, "lr": 3.74801900105973e-05, "epoch": 8.005765199161425, "percentage": 40.03, "elapsed_time": "0:58:12", "remaining_time": "1:27:13", "throughput": 2858.52, "total_tokens": 9984624} {"current_steps": 15280, "total_steps": 38160, "loss": 0.1645, "lr": 3.747028109878975e-05, "epoch": 8.0083857442348, "percentage": 40.04, "elapsed_time": "0:58:14", "remaining_time": "1:27:11", "throughput": 2858.49, "total_tokens": 9987568} {"current_steps": 15285, "total_steps": 38160, "loss": 0.1591, "lr": 3.746036957834167e-05, "epoch": 8.011006289308176, "percentage": 40.06, "elapsed_time": "0:58:15", "remaining_time": "1:27:10", "throughput": 2858.65, "total_tokens": 9991280} {"current_steps": 15290, "total_steps": 38160, "loss": 0.1619, "lr": 3.7450455451326415e-05, "epoch": 8.01362683438155, "percentage": 40.07, "elapsed_time": "0:58:16", "remaining_time": "1:27:09", "throughput": 2858.6, "total_tokens": 9994288} {"current_steps": 15295, "total_steps": 38160, "loss": 0.1383, "lr": 3.7440538719817935e-05, "epoch": 8.016247379454926, "percentage": 40.08, "elapsed_time": "0:58:17", "remaining_time": "1:27:08", "throughput": 2858.53, "total_tokens": 9997200} {"current_steps": 15300, "total_steps": 38160, "loss": 0.2369, "lr": 3.743061938589068e-05, "epoch": 8.018867924528301, "percentage": 40.09, "elapsed_time": "0:58:18", "remaining_time": "1:27:06", "throughput": 2858.52, "total_tokens": 10000176} {"current_steps": 15305, "total_steps": 38160, "loss": 0.171, "lr": 3.742069745161966e-05, "epoch": 8.021488469601676, "percentage": 40.11, "elapsed_time": "0:58:19", "remaining_time": "1:27:05", "throughput": 2858.58, "total_tokens": 10003504} {"current_steps": 15310, "total_steps": 38160, "loss": 0.1829, "lr": 3.741077291908045e-05, "epoch": 8.024109014675052, "percentage": 40.12, "elapsed_time": "0:58:21", "remaining_time": "1:27:05", "throughput": 2858.72, "total_tokens": 10008688} {"current_steps": 15315, "total_steps": 38160, "loss": 0.2083, "lr": 3.740084579034913e-05, "epoch": 8.026729559748428, "percentage": 40.13, "elapsed_time": "0:58:22", "remaining_time": "1:27:04", "throughput": 2858.69, "total_tokens": 10011536} {"current_steps": 15320, "total_steps": 38160, "loss": 0.1664, "lr": 3.739091606750234e-05, "epoch": 8.029350104821804, "percentage": 40.15, "elapsed_time": "0:58:23", "remaining_time": "1:27:02", "throughput": 2858.54, "total_tokens": 10014096} {"current_steps": 15325, "total_steps": 38160, "loss": 0.2121, "lr": 3.7380983752617275e-05, "epoch": 8.031970649895179, "percentage": 40.16, "elapsed_time": "0:58:24", "remaining_time": "1:27:01", "throughput": 2858.59, "total_tokens": 10017360} {"current_steps": 15330, "total_steps": 38160, "loss": 0.2177, "lr": 3.737104884777166e-05, "epoch": 8.034591194968554, "percentage": 40.17, "elapsed_time": "0:58:25", "remaining_time": "1:27:00", "throughput": 2858.64, "total_tokens": 10020560} {"current_steps": 15335, "total_steps": 38160, "loss": 0.1856, "lr": 3.736111135504376e-05, "epoch": 8.03721174004193, "percentage": 40.19, "elapsed_time": "0:58:26", "remaining_time": "1:26:59", "throughput": 2858.78, "total_tokens": 10024176} {"current_steps": 15340, "total_steps": 38160, "loss": 0.0812, "lr": 3.735117127651239e-05, "epoch": 8.039832285115304, "percentage": 40.2, "elapsed_time": "0:58:27", "remaining_time": "1:26:58", "throughput": 2858.98, "total_tokens": 10028336} {"current_steps": 15345, "total_steps": 38160, "loss": 0.1838, "lr": 3.734122861425689e-05, "epoch": 8.04245283018868, "percentage": 40.21, "elapsed_time": "0:58:28", "remaining_time": "1:26:56", "throughput": 2858.98, "total_tokens": 10031376} {"current_steps": 15350, "total_steps": 38160, "loss": 0.1413, "lr": 3.7331283370357173e-05, "epoch": 8.045073375262055, "percentage": 40.23, "elapsed_time": "0:58:29", "remaining_time": "1:26:55", "throughput": 2858.81, "total_tokens": 10033904} {"current_steps": 15355, "total_steps": 38160, "loss": 0.1538, "lr": 3.732133554689365e-05, "epoch": 8.04769392033543, "percentage": 40.24, "elapsed_time": "0:58:30", "remaining_time": "1:26:54", "throughput": 2858.75, "total_tokens": 10036720} {"current_steps": 15360, "total_steps": 38160, "loss": 0.1542, "lr": 3.73113851459473e-05, "epoch": 8.050314465408805, "percentage": 40.25, "elapsed_time": "0:58:32", "remaining_time": "1:26:53", "throughput": 2858.76, "total_tokens": 10040016} {"current_steps": 15365, "total_steps": 38160, "loss": 0.2229, "lr": 3.730143216959964e-05, "epoch": 8.05293501048218, "percentage": 40.26, "elapsed_time": "0:58:33", "remaining_time": "1:26:51", "throughput": 2858.77, "total_tokens": 10043088} {"current_steps": 15370, "total_steps": 38160, "loss": 0.2234, "lr": 3.729147661993271e-05, "epoch": 8.055555555555555, "percentage": 40.28, "elapsed_time": "0:58:34", "remaining_time": "1:26:50", "throughput": 2858.78, "total_tokens": 10046160} {"current_steps": 15375, "total_steps": 38160, "loss": 0.1459, "lr": 3.728151849902909e-05, "epoch": 8.05817610062893, "percentage": 40.29, "elapsed_time": "0:58:35", "remaining_time": "1:26:49", "throughput": 2858.61, "total_tokens": 10048592} {"current_steps": 15380, "total_steps": 38160, "loss": 0.1666, "lr": 3.727155780897193e-05, "epoch": 8.060796645702306, "percentage": 40.3, "elapsed_time": "0:58:36", "remaining_time": "1:26:48", "throughput": 2858.54, "total_tokens": 10051536} {"current_steps": 15385, "total_steps": 38160, "loss": 0.2317, "lr": 3.7261594551844865e-05, "epoch": 8.06341719077568, "percentage": 40.32, "elapsed_time": "0:58:37", "remaining_time": "1:26:47", "throughput": 2858.71, "total_tokens": 10055632} {"current_steps": 15390, "total_steps": 38160, "loss": 0.1901, "lr": 3.7251628729732116e-05, "epoch": 8.066037735849056, "percentage": 40.33, "elapsed_time": "0:58:38", "remaining_time": "1:26:46", "throughput": 2859.13, "total_tokens": 10060528} {"current_steps": 15395, "total_steps": 38160, "loss": 0.1001, "lr": 3.724166034471841e-05, "epoch": 8.068658280922431, "percentage": 40.34, "elapsed_time": "0:58:39", "remaining_time": "1:26:44", "throughput": 2859.12, "total_tokens": 10063664} {"current_steps": 15400, "total_steps": 38160, "loss": 0.177, "lr": 3.723168939888901e-05, "epoch": 8.071278825995806, "percentage": 40.36, "elapsed_time": "0:58:41", "remaining_time": "1:26:43", "throughput": 2858.92, "total_tokens": 10066288} {"current_steps": 15405, "total_steps": 38160, "loss": 0.169, "lr": 3.7221715894329747e-05, "epoch": 8.073899371069182, "percentage": 40.37, "elapsed_time": "0:58:42", "remaining_time": "1:26:42", "throughput": 2859.06, "total_tokens": 10070064} {"current_steps": 15410, "total_steps": 38160, "loss": 0.1381, "lr": 3.7211739833126945e-05, "epoch": 8.076519916142558, "percentage": 40.38, "elapsed_time": "0:58:43", "remaining_time": "1:26:41", "throughput": 2859.19, "total_tokens": 10074128} {"current_steps": 15415, "total_steps": 38160, "loss": 0.1308, "lr": 3.720176121736748e-05, "epoch": 8.079140461215934, "percentage": 40.4, "elapsed_time": "0:58:44", "remaining_time": "1:26:40", "throughput": 2859.3, "total_tokens": 10077936} {"current_steps": 15420, "total_steps": 38160, "loss": 0.136, "lr": 3.719178004913879e-05, "epoch": 8.081761006289309, "percentage": 40.41, "elapsed_time": "0:58:45", "remaining_time": "1:26:39", "throughput": 2859.3, "total_tokens": 10080976} {"current_steps": 15425, "total_steps": 38160, "loss": 0.1808, "lr": 3.7181796330528796e-05, "epoch": 8.084381551362684, "percentage": 40.42, "elapsed_time": "0:58:46", "remaining_time": "1:26:38", "throughput": 2859.26, "total_tokens": 10083984} {"current_steps": 15430, "total_steps": 38160, "loss": 0.1991, "lr": 3.717181006362599e-05, "epoch": 8.08700209643606, "percentage": 40.44, "elapsed_time": "0:58:47", "remaining_time": "1:26:36", "throughput": 2859.21, "total_tokens": 10086800} {"current_steps": 15435, "total_steps": 38160, "loss": 0.1415, "lr": 3.7161821250519384e-05, "epoch": 8.089622641509434, "percentage": 40.45, "elapsed_time": "0:58:48", "remaining_time": "1:26:35", "throughput": 2859.36, "total_tokens": 10090544} {"current_steps": 15440, "total_steps": 38160, "loss": 0.1282, "lr": 3.7151829893298515e-05, "epoch": 8.09224318658281, "percentage": 40.46, "elapsed_time": "0:58:49", "remaining_time": "1:26:34", "throughput": 2859.32, "total_tokens": 10093360} {"current_steps": 15445, "total_steps": 38160, "loss": 0.2361, "lr": 3.714183599405347e-05, "epoch": 8.094863731656185, "percentage": 40.47, "elapsed_time": "0:58:51", "remaining_time": "1:26:33", "throughput": 2859.59, "total_tokens": 10097520} {"current_steps": 15450, "total_steps": 38160, "loss": 0.1246, "lr": 3.713183955487487e-05, "epoch": 8.09748427672956, "percentage": 40.49, "elapsed_time": "0:58:52", "remaining_time": "1:26:31", "throughput": 2859.49, "total_tokens": 10100240} {"current_steps": 15455, "total_steps": 38160, "loss": 0.1923, "lr": 3.7121840577853815e-05, "epoch": 8.100104821802935, "percentage": 40.5, "elapsed_time": "0:58:53", "remaining_time": "1:26:30", "throughput": 2859.48, "total_tokens": 10103280} {"current_steps": 15460, "total_steps": 38160, "loss": 0.136, "lr": 3.7111839065082027e-05, "epoch": 8.10272536687631, "percentage": 40.51, "elapsed_time": "0:58:54", "remaining_time": "1:26:29", "throughput": 2859.42, "total_tokens": 10106288} {"current_steps": 15465, "total_steps": 38160, "loss": 0.1462, "lr": 3.710183501865168e-05, "epoch": 8.105345911949685, "percentage": 40.53, "elapsed_time": "0:58:55", "remaining_time": "1:26:28", "throughput": 2859.54, "total_tokens": 10110064} {"current_steps": 15470, "total_steps": 38160, "loss": 0.1322, "lr": 3.7091828440655514e-05, "epoch": 8.10796645702306, "percentage": 40.54, "elapsed_time": "0:58:56", "remaining_time": "1:26:27", "throughput": 2859.6, "total_tokens": 10113360} {"current_steps": 15475, "total_steps": 38160, "loss": 0.1872, "lr": 3.708181933318678e-05, "epoch": 8.110587002096436, "percentage": 40.55, "elapsed_time": "0:58:58", "remaining_time": "1:26:27", "throughput": 2859.88, "total_tokens": 10119760} {"current_steps": 15480, "total_steps": 38160, "loss": 0.1077, "lr": 3.707180769833929e-05, "epoch": 8.11320754716981, "percentage": 40.57, "elapsed_time": "0:59:00", "remaining_time": "1:26:27", "throughput": 2860.24, "total_tokens": 10126864} {"current_steps": 15485, "total_steps": 38160, "loss": 0.1156, "lr": 3.706179353820734e-05, "epoch": 8.115828092243186, "percentage": 40.58, "elapsed_time": "0:59:01", "remaining_time": "1:26:26", "throughput": 2860.22, "total_tokens": 10129776} {"current_steps": 15490, "total_steps": 38160, "loss": 0.1479, "lr": 3.7051776854885794e-05, "epoch": 8.118448637316561, "percentage": 40.59, "elapsed_time": "0:59:02", "remaining_time": "1:26:24", "throughput": 2860.2, "total_tokens": 10132816} {"current_steps": 15495, "total_steps": 38160, "loss": 0.1184, "lr": 3.7041757650470025e-05, "epoch": 8.121069182389936, "percentage": 40.61, "elapsed_time": "0:59:03", "remaining_time": "1:26:23", "throughput": 2860.28, "total_tokens": 10136112} {"current_steps": 15500, "total_steps": 38160, "loss": 0.1756, "lr": 3.703173592705594e-05, "epoch": 8.123689727463312, "percentage": 40.62, "elapsed_time": "0:59:04", "remaining_time": "1:26:22", "throughput": 2860.2, "total_tokens": 10138896} {"current_steps": 15505, "total_steps": 38160, "loss": 0.2267, "lr": 3.702171168673996e-05, "epoch": 8.126310272536688, "percentage": 40.63, "elapsed_time": "0:59:05", "remaining_time": "1:26:21", "throughput": 2860.05, "total_tokens": 10141456} {"current_steps": 15510, "total_steps": 38160, "loss": 0.2103, "lr": 3.701168493161905e-05, "epoch": 8.128930817610064, "percentage": 40.64, "elapsed_time": "0:59:06", "remaining_time": "1:26:19", "throughput": 2860.19, "total_tokens": 10144944} {"current_steps": 15515, "total_steps": 38160, "loss": 0.1428, "lr": 3.7001655663790676e-05, "epoch": 8.131551362683439, "percentage": 40.66, "elapsed_time": "0:59:08", "remaining_time": "1:26:18", "throughput": 2860.19, "total_tokens": 10148016} {"current_steps": 15520, "total_steps": 38160, "loss": 0.1946, "lr": 3.699162388535288e-05, "epoch": 8.134171907756814, "percentage": 40.67, "elapsed_time": "0:59:09", "remaining_time": "1:26:17", "throughput": 2860.39, "total_tokens": 10152048} {"current_steps": 15525, "total_steps": 38160, "loss": 0.1642, "lr": 3.698158959840416e-05, "epoch": 8.13679245283019, "percentage": 40.68, "elapsed_time": "0:59:10", "remaining_time": "1:26:16", "throughput": 2860.51, "total_tokens": 10155600} {"current_steps": 15530, "total_steps": 38160, "loss": 0.1904, "lr": 3.6971552805043585e-05, "epoch": 8.139412997903564, "percentage": 40.7, "elapsed_time": "0:59:11", "remaining_time": "1:26:14", "throughput": 2860.39, "total_tokens": 10158160} {"current_steps": 15535, "total_steps": 38160, "loss": 0.2171, "lr": 3.6961513507370754e-05, "epoch": 8.14203354297694, "percentage": 40.71, "elapsed_time": "0:59:12", "remaining_time": "1:26:13", "throughput": 2860.38, "total_tokens": 10161296} {"current_steps": 15540, "total_steps": 38160, "loss": 0.1841, "lr": 3.695147170748576e-05, "epoch": 8.144654088050315, "percentage": 40.72, "elapsed_time": "0:59:13", "remaining_time": "1:26:12", "throughput": 2860.33, "total_tokens": 10164112} {"current_steps": 15545, "total_steps": 38160, "loss": 0.169, "lr": 3.694142740748923e-05, "epoch": 8.14727463312369, "percentage": 40.74, "elapsed_time": "0:59:14", "remaining_time": "1:26:11", "throughput": 2860.37, "total_tokens": 10167248} {"current_steps": 15550, "total_steps": 38160, "loss": 0.1696, "lr": 3.693138060948232e-05, "epoch": 8.149895178197065, "percentage": 40.75, "elapsed_time": "0:59:15", "remaining_time": "1:26:09", "throughput": 2860.54, "total_tokens": 10171088} {"current_steps": 15555, "total_steps": 38160, "loss": 0.159, "lr": 3.692133131556671e-05, "epoch": 8.15251572327044, "percentage": 40.76, "elapsed_time": "0:59:16", "remaining_time": "1:26:08", "throughput": 2860.55, "total_tokens": 10174192} {"current_steps": 15560, "total_steps": 38160, "loss": 0.18, "lr": 3.6911279527844596e-05, "epoch": 8.155136268343815, "percentage": 40.78, "elapsed_time": "0:59:17", "remaining_time": "1:26:07", "throughput": 2860.5, "total_tokens": 10177264} {"current_steps": 15565, "total_steps": 38160, "loss": 0.1533, "lr": 3.69012252484187e-05, "epoch": 8.15775681341719, "percentage": 40.79, "elapsed_time": "0:59:18", "remaining_time": "1:26:06", "throughput": 2860.36, "total_tokens": 10179824} {"current_steps": 15570, "total_steps": 38160, "loss": 0.1686, "lr": 3.6891168479392245e-05, "epoch": 8.160377358490566, "percentage": 40.8, "elapsed_time": "0:59:20", "remaining_time": "1:26:05", "throughput": 2860.38, "total_tokens": 10183024} {"current_steps": 15575, "total_steps": 38160, "loss": 0.1754, "lr": 3.688110922286901e-05, "epoch": 8.16299790356394, "percentage": 40.81, "elapsed_time": "0:59:21", "remaining_time": "1:26:03", "throughput": 2860.56, "total_tokens": 10186832} {"current_steps": 15580, "total_steps": 38160, "loss": 0.1977, "lr": 3.687104748095328e-05, "epoch": 8.165618448637316, "percentage": 40.83, "elapsed_time": "0:59:22", "remaining_time": "1:26:02", "throughput": 2860.42, "total_tokens": 10189360} {"current_steps": 15585, "total_steps": 38160, "loss": 0.1765, "lr": 3.686098325574984e-05, "epoch": 8.168238993710691, "percentage": 40.84, "elapsed_time": "0:59:23", "remaining_time": "1:26:01", "throughput": 2860.61, "total_tokens": 10193360} {"current_steps": 15590, "total_steps": 38160, "loss": 0.1945, "lr": 3.685091654936403e-05, "epoch": 8.170859538784066, "percentage": 40.85, "elapsed_time": "0:59:24", "remaining_time": "1:26:00", "throughput": 2860.71, "total_tokens": 10197136} {"current_steps": 15595, "total_steps": 38160, "loss": 0.179, "lr": 3.6840847363901675e-05, "epoch": 8.173480083857442, "percentage": 40.87, "elapsed_time": "0:59:25", "remaining_time": "1:25:59", "throughput": 2860.81, "total_tokens": 10200592} {"current_steps": 15600, "total_steps": 38160, "loss": 0.1563, "lr": 3.683077570146914e-05, "epoch": 8.176100628930818, "percentage": 40.88, "elapsed_time": "0:59:26", "remaining_time": "1:25:58", "throughput": 2860.63, "total_tokens": 10203088} {"current_steps": 15605, "total_steps": 38160, "loss": 0.2922, "lr": 3.68207015641733e-05, "epoch": 8.178721174004194, "percentage": 40.89, "elapsed_time": "0:59:27", "remaining_time": "1:25:56", "throughput": 2860.55, "total_tokens": 10205840} {"current_steps": 15610, "total_steps": 38160, "loss": 0.1685, "lr": 3.681062495412155e-05, "epoch": 8.181341719077569, "percentage": 40.91, "elapsed_time": "0:59:28", "remaining_time": "1:25:55", "throughput": 2860.58, "total_tokens": 10209040} {"current_steps": 15615, "total_steps": 38160, "loss": 0.1229, "lr": 3.68005458734218e-05, "epoch": 8.183962264150944, "percentage": 40.92, "elapsed_time": "0:59:29", "remaining_time": "1:25:54", "throughput": 2860.59, "total_tokens": 10212048} {"current_steps": 15620, "total_steps": 38160, "loss": 0.1705, "lr": 3.679046432418248e-05, "epoch": 8.18658280922432, "percentage": 40.93, "elapsed_time": "0:59:30", "remaining_time": "1:25:53", "throughput": 2860.52, "total_tokens": 10214896} {"current_steps": 15625, "total_steps": 38160, "loss": 0.2102, "lr": 3.6780380308512543e-05, "epoch": 8.189203354297694, "percentage": 40.95, "elapsed_time": "0:59:32", "remaining_time": "1:25:51", "throughput": 2860.48, "total_tokens": 10217872} {"current_steps": 15630, "total_steps": 38160, "loss": 0.1329, "lr": 3.677029382852144e-05, "epoch": 8.19182389937107, "percentage": 40.96, "elapsed_time": "0:59:33", "remaining_time": "1:25:50", "throughput": 2860.61, "total_tokens": 10221488} {"current_steps": 15635, "total_steps": 38160, "loss": 0.092, "lr": 3.676020488631915e-05, "epoch": 8.194444444444445, "percentage": 40.97, "elapsed_time": "0:59:34", "remaining_time": "1:25:49", "throughput": 2860.5, "total_tokens": 10224048} {"current_steps": 15640, "total_steps": 38160, "loss": 0.1042, "lr": 3.675011348401617e-05, "epoch": 8.19706498951782, "percentage": 40.99, "elapsed_time": "0:59:35", "remaining_time": "1:25:48", "throughput": 2860.77, "total_tokens": 10228368} {"current_steps": 15645, "total_steps": 38160, "loss": 0.1717, "lr": 3.6740019623723494e-05, "epoch": 8.199685534591195, "percentage": 41.0, "elapsed_time": "0:59:36", "remaining_time": "1:25:47", "throughput": 2860.81, "total_tokens": 10231728} {"current_steps": 15650, "total_steps": 38160, "loss": 0.2215, "lr": 3.672992330755265e-05, "epoch": 8.20230607966457, "percentage": 41.01, "elapsed_time": "0:59:37", "remaining_time": "1:25:45", "throughput": 2860.85, "total_tokens": 10234960} {"current_steps": 15655, "total_steps": 38160, "loss": 0.199, "lr": 3.671982453761568e-05, "epoch": 8.204926624737945, "percentage": 41.02, "elapsed_time": "0:59:38", "remaining_time": "1:25:44", "throughput": 2860.98, "total_tokens": 10238448} {"current_steps": 15660, "total_steps": 38160, "loss": 0.1028, "lr": 3.6709723316025114e-05, "epoch": 8.20754716981132, "percentage": 41.04, "elapsed_time": "0:59:39", "remaining_time": "1:25:43", "throughput": 2860.82, "total_tokens": 10240912} {"current_steps": 15665, "total_steps": 38160, "loss": 0.1964, "lr": 3.669961964489403e-05, "epoch": 8.210167714884696, "percentage": 41.05, "elapsed_time": "0:59:40", "remaining_time": "1:25:42", "throughput": 2861.0, "total_tokens": 10244816} {"current_steps": 15670, "total_steps": 38160, "loss": 0.1649, "lr": 3.668951352633599e-05, "epoch": 8.21278825995807, "percentage": 41.06, "elapsed_time": "0:59:41", "remaining_time": "1:25:40", "throughput": 2860.96, "total_tokens": 10247728} {"current_steps": 15675, "total_steps": 38160, "loss": 0.1508, "lr": 3.6679404962465084e-05, "epoch": 8.215408805031446, "percentage": 41.08, "elapsed_time": "0:59:43", "remaining_time": "1:25:39", "throughput": 2861.02, "total_tokens": 10251248} {"current_steps": 15680, "total_steps": 38160, "loss": 0.1905, "lr": 3.66692939553959e-05, "epoch": 8.218029350104821, "percentage": 41.09, "elapsed_time": "0:59:44", "remaining_time": "1:25:38", "throughput": 2860.96, "total_tokens": 10254160} {"current_steps": 15685, "total_steps": 38160, "loss": 0.1817, "lr": 3.6659180507243554e-05, "epoch": 8.220649895178196, "percentage": 41.1, "elapsed_time": "0:59:45", "remaining_time": "1:25:37", "throughput": 2860.89, "total_tokens": 10256944} {"current_steps": 15690, "total_steps": 38160, "loss": 0.2004, "lr": 3.664906462012366e-05, "epoch": 8.223270440251572, "percentage": 41.12, "elapsed_time": "0:59:46", "remaining_time": "1:25:36", "throughput": 2860.86, "total_tokens": 10259888} {"current_steps": 15695, "total_steps": 38160, "loss": 0.2123, "lr": 3.663894629615234e-05, "epoch": 8.225890985324948, "percentage": 41.13, "elapsed_time": "0:59:47", "remaining_time": "1:25:34", "throughput": 2860.8, "total_tokens": 10262640} {"current_steps": 15700, "total_steps": 38160, "loss": 0.1969, "lr": 3.6628825537446246e-05, "epoch": 8.228511530398324, "percentage": 41.14, "elapsed_time": "0:59:48", "remaining_time": "1:25:33", "throughput": 2860.7, "total_tokens": 10265424} {"current_steps": 15705, "total_steps": 38160, "loss": 0.1687, "lr": 3.6618702346122525e-05, "epoch": 8.231132075471699, "percentage": 41.16, "elapsed_time": "0:59:49", "remaining_time": "1:25:32", "throughput": 2860.53, "total_tokens": 10267888} {"current_steps": 15710, "total_steps": 38160, "loss": 0.1369, "lr": 3.6608576724298817e-05, "epoch": 8.233752620545074, "percentage": 41.17, "elapsed_time": "0:59:50", "remaining_time": "1:25:31", "throughput": 2860.48, "total_tokens": 10270992} {"current_steps": 15715, "total_steps": 38160, "loss": 0.2042, "lr": 3.65984486740933e-05, "epoch": 8.23637316561845, "percentage": 41.18, "elapsed_time": "0:59:51", "remaining_time": "1:25:29", "throughput": 2860.47, "total_tokens": 10274128} {"current_steps": 15720, "total_steps": 38160, "loss": 0.1531, "lr": 3.6588318197624644e-05, "epoch": 8.238993710691824, "percentage": 41.19, "elapsed_time": "0:59:52", "remaining_time": "1:25:28", "throughput": 2860.63, "total_tokens": 10278128} {"current_steps": 15725, "total_steps": 38160, "loss": 0.1158, "lr": 3.6578185297012015e-05, "epoch": 8.2416142557652, "percentage": 41.21, "elapsed_time": "0:59:53", "remaining_time": "1:25:27", "throughput": 2860.53, "total_tokens": 10280720} {"current_steps": 15730, "total_steps": 38160, "loss": 0.1752, "lr": 3.656804997437512e-05, "epoch": 8.244234800838575, "percentage": 41.22, "elapsed_time": "0:59:55", "remaining_time": "1:25:26", "throughput": 2860.4, "total_tokens": 10283280} {"current_steps": 15735, "total_steps": 38160, "loss": 0.1742, "lr": 3.6557912231834155e-05, "epoch": 8.24685534591195, "percentage": 41.23, "elapsed_time": "0:59:56", "remaining_time": "1:25:25", "throughput": 2860.6, "total_tokens": 10287600} {"current_steps": 15740, "total_steps": 38160, "loss": 0.1486, "lr": 3.65477720715098e-05, "epoch": 8.249475890985325, "percentage": 41.25, "elapsed_time": "0:59:57", "remaining_time": "1:25:24", "throughput": 2860.37, "total_tokens": 10289808} {"current_steps": 15745, "total_steps": 38160, "loss": 0.2438, "lr": 3.653762949552328e-05, "epoch": 8.2520964360587, "percentage": 41.26, "elapsed_time": "0:59:58", "remaining_time": "1:25:22", "throughput": 2860.32, "total_tokens": 10292656} {"current_steps": 15750, "total_steps": 38160, "loss": 0.1778, "lr": 3.6527484505996295e-05, "epoch": 8.254716981132075, "percentage": 41.27, "elapsed_time": "0:59:59", "remaining_time": "1:25:21", "throughput": 2860.29, "total_tokens": 10295664} {"current_steps": 15755, "total_steps": 38160, "loss": 0.1442, "lr": 3.651733710505106e-05, "epoch": 8.25733752620545, "percentage": 41.29, "elapsed_time": "1:00:00", "remaining_time": "1:25:20", "throughput": 2860.33, "total_tokens": 10299248} {"current_steps": 15760, "total_steps": 38160, "loss": 0.1402, "lr": 3.6507187294810305e-05, "epoch": 8.259958071278826, "percentage": 41.3, "elapsed_time": "1:00:01", "remaining_time": "1:25:19", "throughput": 2860.44, "total_tokens": 10302832} {"current_steps": 15765, "total_steps": 38160, "loss": 0.1887, "lr": 3.649703507739724e-05, "epoch": 8.2625786163522, "percentage": 41.31, "elapsed_time": "1:00:03", "remaining_time": "1:25:18", "throughput": 2860.79, "total_tokens": 10307888} {"current_steps": 15770, "total_steps": 38160, "loss": 0.1747, "lr": 3.6486880454935606e-05, "epoch": 8.265199161425576, "percentage": 41.33, "elapsed_time": "1:00:04", "remaining_time": "1:25:17", "throughput": 2860.87, "total_tokens": 10311248} {"current_steps": 15775, "total_steps": 38160, "loss": 0.1917, "lr": 3.647672342954963e-05, "epoch": 8.267819706498951, "percentage": 41.34, "elapsed_time": "1:00:05", "remaining_time": "1:25:15", "throughput": 2860.88, "total_tokens": 10314320} {"current_steps": 15780, "total_steps": 38160, "loss": 0.1646, "lr": 3.646656400336405e-05, "epoch": 8.270440251572326, "percentage": 41.35, "elapsed_time": "1:00:06", "remaining_time": "1:25:14", "throughput": 2860.99, "total_tokens": 10317936} {"current_steps": 15785, "total_steps": 38160, "loss": 0.2004, "lr": 3.6456402178504094e-05, "epoch": 8.273060796645701, "percentage": 41.37, "elapsed_time": "1:00:07", "remaining_time": "1:25:13", "throughput": 2861.04, "total_tokens": 10321136} {"current_steps": 15790, "total_steps": 38160, "loss": 0.26, "lr": 3.6446237957095505e-05, "epoch": 8.275681341719078, "percentage": 41.38, "elapsed_time": "1:00:08", "remaining_time": "1:25:12", "throughput": 2860.94, "total_tokens": 10323760} {"current_steps": 15795, "total_steps": 38160, "loss": 0.1906, "lr": 3.643607134126452e-05, "epoch": 8.278301886792454, "percentage": 41.39, "elapsed_time": "1:00:09", "remaining_time": "1:25:11", "throughput": 2860.99, "total_tokens": 10327088} {"current_steps": 15800, "total_steps": 38160, "loss": 0.2222, "lr": 3.642590233313789e-05, "epoch": 8.280922431865829, "percentage": 41.4, "elapsed_time": "1:00:10", "remaining_time": "1:25:09", "throughput": 2861.09, "total_tokens": 10330448} {"current_steps": 15805, "total_steps": 38160, "loss": 0.1539, "lr": 3.6415730934842827e-05, "epoch": 8.283542976939204, "percentage": 41.42, "elapsed_time": "1:00:11", "remaining_time": "1:25:08", "throughput": 2861.35, "total_tokens": 10334672} {"current_steps": 15810, "total_steps": 38160, "loss": 0.1654, "lr": 3.64055571485071e-05, "epoch": 8.286163522012579, "percentage": 41.43, "elapsed_time": "1:00:12", "remaining_time": "1:25:07", "throughput": 2861.38, "total_tokens": 10337904} {"current_steps": 15815, "total_steps": 38160, "loss": 0.1842, "lr": 3.639538097625894e-05, "epoch": 8.288784067085954, "percentage": 41.44, "elapsed_time": "1:00:14", "remaining_time": "1:25:06", "throughput": 2861.47, "total_tokens": 10341488} {"current_steps": 15820, "total_steps": 38160, "loss": 0.1596, "lr": 3.638520242022708e-05, "epoch": 8.29140461215933, "percentage": 41.46, "elapsed_time": "1:00:15", "remaining_time": "1:25:05", "throughput": 2861.57, "total_tokens": 10344944} {"current_steps": 15825, "total_steps": 38160, "loss": 0.2318, "lr": 3.637502148254077e-05, "epoch": 8.294025157232705, "percentage": 41.47, "elapsed_time": "1:00:16", "remaining_time": "1:25:03", "throughput": 2861.35, "total_tokens": 10347248} {"current_steps": 15830, "total_steps": 38160, "loss": 0.2193, "lr": 3.636483816532974e-05, "epoch": 8.29664570230608, "percentage": 41.48, "elapsed_time": "1:00:17", "remaining_time": "1:25:02", "throughput": 2861.16, "total_tokens": 10349712} {"current_steps": 15835, "total_steps": 38160, "loss": 0.1605, "lr": 3.6354652470724217e-05, "epoch": 8.299266247379455, "percentage": 41.5, "elapsed_time": "1:00:18", "remaining_time": "1:25:01", "throughput": 2861.39, "total_tokens": 10353936} {"current_steps": 15840, "total_steps": 38160, "loss": 0.1439, "lr": 3.634446440085494e-05, "epoch": 8.30188679245283, "percentage": 41.51, "elapsed_time": "1:00:19", "remaining_time": "1:25:00", "throughput": 2861.26, "total_tokens": 10356432} {"current_steps": 15845, "total_steps": 38160, "loss": 0.3262, "lr": 3.633427395785313e-05, "epoch": 8.304507337526205, "percentage": 41.52, "elapsed_time": "1:00:20", "remaining_time": "1:24:59", "throughput": 2861.46, "total_tokens": 10360624} {"current_steps": 15850, "total_steps": 38160, "loss": 0.1757, "lr": 3.6324081143850516e-05, "epoch": 8.30712788259958, "percentage": 41.54, "elapsed_time": "1:00:21", "remaining_time": "1:24:57", "throughput": 2861.65, "total_tokens": 10364432} {"current_steps": 15855, "total_steps": 38160, "loss": 0.1635, "lr": 3.6313885960979326e-05, "epoch": 8.309748427672956, "percentage": 41.55, "elapsed_time": "1:00:22", "remaining_time": "1:24:56", "throughput": 2861.55, "total_tokens": 10367184} {"current_steps": 15860, "total_steps": 38160, "loss": 0.1571, "lr": 3.630368841137226e-05, "epoch": 8.31236897274633, "percentage": 41.56, "elapsed_time": "1:00:24", "remaining_time": "1:24:55", "throughput": 2861.52, "total_tokens": 10370192} {"current_steps": 15865, "total_steps": 38160, "loss": 0.2809, "lr": 3.6293488497162554e-05, "epoch": 8.314989517819706, "percentage": 41.57, "elapsed_time": "1:00:25", "remaining_time": "1:24:54", "throughput": 2861.63, "total_tokens": 10373744} {"current_steps": 15870, "total_steps": 38160, "loss": 0.2017, "lr": 3.628328622048388e-05, "epoch": 8.317610062893081, "percentage": 41.59, "elapsed_time": "1:00:26", "remaining_time": "1:24:53", "throughput": 2861.51, "total_tokens": 10376400} {"current_steps": 15875, "total_steps": 38160, "loss": 0.1409, "lr": 3.627308158347046e-05, "epoch": 8.320230607966456, "percentage": 41.6, "elapsed_time": "1:00:27", "remaining_time": "1:24:51", "throughput": 2861.54, "total_tokens": 10379600} {"current_steps": 15880, "total_steps": 38160, "loss": 0.1935, "lr": 3.626287458825699e-05, "epoch": 8.322851153039831, "percentage": 41.61, "elapsed_time": "1:00:28", "remaining_time": "1:24:50", "throughput": 2861.65, "total_tokens": 10383088} {"current_steps": 15885, "total_steps": 38160, "loss": 0.2197, "lr": 3.625266523697864e-05, "epoch": 8.325471698113208, "percentage": 41.63, "elapsed_time": "1:00:29", "remaining_time": "1:24:49", "throughput": 2861.69, "total_tokens": 10386288} {"current_steps": 15890, "total_steps": 38160, "loss": 0.2709, "lr": 3.62424535317711e-05, "epoch": 8.328092243186584, "percentage": 41.64, "elapsed_time": "1:00:30", "remaining_time": "1:24:48", "throughput": 2861.81, "total_tokens": 10389744} {"current_steps": 15895, "total_steps": 38160, "loss": 0.1687, "lr": 3.623223947477055e-05, "epoch": 8.330712788259959, "percentage": 41.65, "elapsed_time": "1:00:31", "remaining_time": "1:24:46", "throughput": 2861.82, "total_tokens": 10392880} {"current_steps": 15900, "total_steps": 38160, "loss": 0.217, "lr": 3.6222023068113635e-05, "epoch": 8.333333333333334, "percentage": 41.67, "elapsed_time": "1:00:32", "remaining_time": "1:24:45", "throughput": 2862.07, "total_tokens": 10397168} {"current_steps": 15905, "total_steps": 38160, "loss": 0.1762, "lr": 3.621180431393754e-05, "epoch": 8.335953878406709, "percentage": 41.68, "elapsed_time": "1:00:33", "remaining_time": "1:24:44", "throughput": 2862.15, "total_tokens": 10400784} {"current_steps": 15910, "total_steps": 38160, "loss": 0.1019, "lr": 3.6201583214379874e-05, "epoch": 8.338574423480084, "percentage": 41.69, "elapsed_time": "1:00:34", "remaining_time": "1:24:43", "throughput": 2862.06, "total_tokens": 10403568} {"current_steps": 15915, "total_steps": 38160, "loss": 0.1452, "lr": 3.61913597715788e-05, "epoch": 8.34119496855346, "percentage": 41.71, "elapsed_time": "1:00:36", "remaining_time": "1:24:42", "throughput": 2862.08, "total_tokens": 10406800} {"current_steps": 15920, "total_steps": 38160, "loss": 0.1863, "lr": 3.6181133987672944e-05, "epoch": 8.343815513626835, "percentage": 41.72, "elapsed_time": "1:00:37", "remaining_time": "1:24:41", "throughput": 2862.07, "total_tokens": 10409744} {"current_steps": 15925, "total_steps": 38160, "loss": 0.143, "lr": 3.617090586480142e-05, "epoch": 8.34643605870021, "percentage": 41.73, "elapsed_time": "1:00:38", "remaining_time": "1:24:39", "throughput": 2862.09, "total_tokens": 10412880} {"current_steps": 15930, "total_steps": 38160, "loss": 0.2206, "lr": 3.6160675405103826e-05, "epoch": 8.349056603773585, "percentage": 41.75, "elapsed_time": "1:00:39", "remaining_time": "1:24:38", "throughput": 2862.21, "total_tokens": 10416432} {"current_steps": 15935, "total_steps": 38160, "loss": 0.1835, "lr": 3.615044261072027e-05, "epoch": 8.35167714884696, "percentage": 41.76, "elapsed_time": "1:00:40", "remaining_time": "1:24:37", "throughput": 2862.27, "total_tokens": 10419824} {"current_steps": 15940, "total_steps": 38160, "loss": 0.1766, "lr": 3.614020748379133e-05, "epoch": 8.354297693920335, "percentage": 41.77, "elapsed_time": "1:00:41", "remaining_time": "1:24:36", "throughput": 2862.2, "total_tokens": 10422800} {"current_steps": 15945, "total_steps": 38160, "loss": 0.1481, "lr": 3.6129970026458076e-05, "epoch": 8.35691823899371, "percentage": 41.78, "elapsed_time": "1:00:42", "remaining_time": "1:24:35", "throughput": 2862.14, "total_tokens": 10425808} {"current_steps": 15950, "total_steps": 38160, "loss": 0.1668, "lr": 3.611973024086207e-05, "epoch": 8.359538784067086, "percentage": 41.8, "elapsed_time": "1:00:43", "remaining_time": "1:24:33", "throughput": 2862.11, "total_tokens": 10428944} {"current_steps": 15955, "total_steps": 38160, "loss": 0.2238, "lr": 3.610948812914536e-05, "epoch": 8.36215932914046, "percentage": 41.81, "elapsed_time": "1:00:45", "remaining_time": "1:24:32", "throughput": 2862.4, "total_tokens": 10433648} {"current_steps": 15960, "total_steps": 38160, "loss": 0.2008, "lr": 3.609924369345048e-05, "epoch": 8.364779874213836, "percentage": 41.82, "elapsed_time": "1:00:46", "remaining_time": "1:24:31", "throughput": 2862.39, "total_tokens": 10436784} {"current_steps": 15965, "total_steps": 38160, "loss": 0.1557, "lr": 3.6088996935920444e-05, "epoch": 8.367400419287211, "percentage": 41.84, "elapsed_time": "1:00:47", "remaining_time": "1:24:30", "throughput": 2862.22, "total_tokens": 10439280} {"current_steps": 15970, "total_steps": 38160, "loss": 0.1544, "lr": 3.607874785869876e-05, "epoch": 8.370020964360586, "percentage": 41.85, "elapsed_time": "1:00:48", "remaining_time": "1:24:29", "throughput": 2862.03, "total_tokens": 10441744} {"current_steps": 15975, "total_steps": 38160, "loss": 0.1745, "lr": 3.6068496463929416e-05, "epoch": 8.372641509433961, "percentage": 41.86, "elapsed_time": "1:00:49", "remaining_time": "1:24:28", "throughput": 2862.18, "total_tokens": 10445424} {"current_steps": 15980, "total_steps": 38160, "loss": 0.2553, "lr": 3.605824275375689e-05, "epoch": 8.375262054507338, "percentage": 41.88, "elapsed_time": "1:00:50", "remaining_time": "1:24:26", "throughput": 2862.25, "total_tokens": 10448688} {"current_steps": 15985, "total_steps": 38160, "loss": 0.2068, "lr": 3.604798673032613e-05, "epoch": 8.377882599580714, "percentage": 41.89, "elapsed_time": "1:00:51", "remaining_time": "1:24:25", "throughput": 2862.41, "total_tokens": 10453040} {"current_steps": 15990, "total_steps": 38160, "loss": 0.2188, "lr": 3.60377283957826e-05, "epoch": 8.380503144654089, "percentage": 41.9, "elapsed_time": "1:00:52", "remaining_time": "1:24:24", "throughput": 2862.65, "total_tokens": 10457072} {"current_steps": 15995, "total_steps": 38160, "loss": 0.1498, "lr": 3.6027467752272203e-05, "epoch": 8.383123689727464, "percentage": 41.92, "elapsed_time": "1:00:53", "remaining_time": "1:24:23", "throughput": 2862.42, "total_tokens": 10459280} {"current_steps": 16000, "total_steps": 38160, "loss": 0.1611, "lr": 3.601720480194137e-05, "epoch": 8.385744234800839, "percentage": 41.93, "elapsed_time": "1:00:55", "remaining_time": "1:24:22", "throughput": 2862.33, "total_tokens": 10462192} {"current_steps": 16005, "total_steps": 38160, "loss": 0.2101, "lr": 3.600693954693698e-05, "epoch": 8.388364779874214, "percentage": 41.94, "elapsed_time": "1:00:56", "remaining_time": "1:24:21", "throughput": 2862.61, "total_tokens": 10466672} {"current_steps": 16010, "total_steps": 38160, "loss": 0.1549, "lr": 3.5996671989406414e-05, "epoch": 8.39098532494759, "percentage": 41.95, "elapsed_time": "1:00:57", "remaining_time": "1:24:20", "throughput": 2862.62, "total_tokens": 10469776} {"current_steps": 16015, "total_steps": 38160, "loss": 0.139, "lr": 3.598640213149752e-05, "epoch": 8.393605870020965, "percentage": 41.97, "elapsed_time": "1:00:58", "remaining_time": "1:24:18", "throughput": 2862.57, "total_tokens": 10472848} {"current_steps": 16020, "total_steps": 38160, "loss": 0.1795, "lr": 3.597612997535864e-05, "epoch": 8.39622641509434, "percentage": 41.98, "elapsed_time": "1:00:59", "remaining_time": "1:24:17", "throughput": 2862.62, "total_tokens": 10476368} {"current_steps": 16025, "total_steps": 38160, "loss": 0.1702, "lr": 3.596585552313859e-05, "epoch": 8.398846960167715, "percentage": 41.99, "elapsed_time": "1:01:00", "remaining_time": "1:24:16", "throughput": 2862.59, "total_tokens": 10479472} {"current_steps": 16030, "total_steps": 38160, "loss": 0.1973, "lr": 3.595557877698666e-05, "epoch": 8.40146750524109, "percentage": 42.01, "elapsed_time": "1:01:01", "remaining_time": "1:24:15", "throughput": 2862.43, "total_tokens": 10482000} {"current_steps": 16035, "total_steps": 38160, "loss": 0.2296, "lr": 3.594529973905266e-05, "epoch": 8.404088050314465, "percentage": 42.02, "elapsed_time": "1:01:03", "remaining_time": "1:24:14", "throughput": 2862.29, "total_tokens": 10484592} {"current_steps": 16040, "total_steps": 38160, "loss": 0.1559, "lr": 3.593501841148681e-05, "epoch": 8.40670859538784, "percentage": 42.03, "elapsed_time": "1:01:04", "remaining_time": "1:24:13", "throughput": 2862.14, "total_tokens": 10487216} {"current_steps": 16045, "total_steps": 38160, "loss": 0.2192, "lr": 3.5924734796439864e-05, "epoch": 8.409329140461216, "percentage": 42.05, "elapsed_time": "1:01:05", "remaining_time": "1:24:11", "throughput": 2862.19, "total_tokens": 10490512} {"current_steps": 16050, "total_steps": 38160, "loss": 0.142, "lr": 3.5914448896063044e-05, "epoch": 8.41194968553459, "percentage": 42.06, "elapsed_time": "1:01:06", "remaining_time": "1:24:10", "throughput": 2862.16, "total_tokens": 10493552} {"current_steps": 16055, "total_steps": 38160, "loss": 0.21, "lr": 3.590416071250802e-05, "epoch": 8.414570230607966, "percentage": 42.07, "elapsed_time": "1:01:07", "remaining_time": "1:24:09", "throughput": 2862.33, "total_tokens": 10497264} {"current_steps": 16060, "total_steps": 38160, "loss": 0.1321, "lr": 3.589387024792699e-05, "epoch": 8.417190775681341, "percentage": 42.09, "elapsed_time": "1:01:08", "remaining_time": "1:24:08", "throughput": 2862.23, "total_tokens": 10499984} {"current_steps": 16065, "total_steps": 38160, "loss": 0.1633, "lr": 3.5883577504472576e-05, "epoch": 8.419811320754716, "percentage": 42.1, "elapsed_time": "1:01:09", "remaining_time": "1:24:06", "throughput": 2862.27, "total_tokens": 10503248} {"current_steps": 16070, "total_steps": 38160, "loss": 0.1773, "lr": 3.587328248429792e-05, "epoch": 8.422431865828091, "percentage": 42.11, "elapsed_time": "1:01:10", "remaining_time": "1:24:05", "throughput": 2862.49, "total_tokens": 10507088} {"current_steps": 16075, "total_steps": 38160, "loss": 0.1679, "lr": 3.586298518955661e-05, "epoch": 8.425052410901468, "percentage": 42.13, "elapsed_time": "1:01:11", "remaining_time": "1:24:04", "throughput": 2862.55, "total_tokens": 10510416} {"current_steps": 16080, "total_steps": 38160, "loss": 0.248, "lr": 3.5852685622402746e-05, "epoch": 8.427672955974844, "percentage": 42.14, "elapsed_time": "1:01:12", "remaining_time": "1:24:03", "throughput": 2862.74, "total_tokens": 10514384} {"current_steps": 16085, "total_steps": 38160, "loss": 0.2242, "lr": 3.584238378499085e-05, "epoch": 8.430293501048219, "percentage": 42.15, "elapsed_time": "1:01:13", "remaining_time": "1:24:02", "throughput": 2862.88, "total_tokens": 10517872} {"current_steps": 16090, "total_steps": 38160, "loss": 0.1361, "lr": 3.5832079679475974e-05, "epoch": 8.432914046121594, "percentage": 42.16, "elapsed_time": "1:01:14", "remaining_time": "1:24:00", "throughput": 2862.96, "total_tokens": 10521200} {"current_steps": 16095, "total_steps": 38160, "loss": 0.1634, "lr": 3.582177330801359e-05, "epoch": 8.435534591194969, "percentage": 42.18, "elapsed_time": "1:01:15", "remaining_time": "1:23:59", "throughput": 2862.88, "total_tokens": 10523856} {"current_steps": 16100, "total_steps": 38160, "loss": 0.2558, "lr": 3.58114646727597e-05, "epoch": 8.438155136268344, "percentage": 42.19, "elapsed_time": "1:01:17", "remaining_time": "1:23:58", "throughput": 2863.05, "total_tokens": 10527728} {"current_steps": 16105, "total_steps": 38160, "loss": 0.1868, "lr": 3.580115377587075e-05, "epoch": 8.44077568134172, "percentage": 42.2, "elapsed_time": "1:01:18", "remaining_time": "1:23:57", "throughput": 2863.18, "total_tokens": 10531536} {"current_steps": 16110, "total_steps": 38160, "loss": 0.1792, "lr": 3.5790840619503654e-05, "epoch": 8.443396226415095, "percentage": 42.22, "elapsed_time": "1:01:19", "remaining_time": "1:23:55", "throughput": 2863.1, "total_tokens": 10534352} {"current_steps": 16115, "total_steps": 38160, "loss": 0.1976, "lr": 3.57805252058158e-05, "epoch": 8.44601677148847, "percentage": 42.23, "elapsed_time": "1:01:20", "remaining_time": "1:23:54", "throughput": 2863.17, "total_tokens": 10537552} {"current_steps": 16120, "total_steps": 38160, "loss": 0.1047, "lr": 3.577020753696507e-05, "epoch": 8.448637316561845, "percentage": 42.24, "elapsed_time": "1:01:21", "remaining_time": "1:23:53", "throughput": 2863.03, "total_tokens": 10539952} {"current_steps": 16125, "total_steps": 38160, "loss": 0.1771, "lr": 3.57598876151098e-05, "epoch": 8.45125786163522, "percentage": 42.26, "elapsed_time": "1:01:22", "remaining_time": "1:23:52", "throughput": 2863.16, "total_tokens": 10543408} {"current_steps": 16130, "total_steps": 38160, "loss": 0.088, "lr": 3.5749565442408796e-05, "epoch": 8.453878406708595, "percentage": 42.27, "elapsed_time": "1:01:23", "remaining_time": "1:23:50", "throughput": 2863.11, "total_tokens": 10546352} {"current_steps": 16135, "total_steps": 38160, "loss": 0.159, "lr": 3.573924102102133e-05, "epoch": 8.45649895178197, "percentage": 42.28, "elapsed_time": "1:01:24", "remaining_time": "1:23:49", "throughput": 2863.33, "total_tokens": 10550352} {"current_steps": 16140, "total_steps": 38160, "loss": 0.3028, "lr": 3.572891435310717e-05, "epoch": 8.459119496855346, "percentage": 42.3, "elapsed_time": "1:01:25", "remaining_time": "1:23:48", "throughput": 2863.58, "total_tokens": 10554864} {"current_steps": 16145, "total_steps": 38160, "loss": 0.1084, "lr": 3.5718585440826527e-05, "epoch": 8.46174004192872, "percentage": 42.31, "elapsed_time": "1:01:27", "remaining_time": "1:23:47", "throughput": 2863.68, "total_tokens": 10558960} {"current_steps": 16150, "total_steps": 38160, "loss": 0.1815, "lr": 3.570825428634009e-05, "epoch": 8.464360587002096, "percentage": 42.32, "elapsed_time": "1:01:28", "remaining_time": "1:23:46", "throughput": 2864.0, "total_tokens": 10563600} {"current_steps": 16155, "total_steps": 38160, "loss": 0.2009, "lr": 3.569792089180903e-05, "epoch": 8.466981132075471, "percentage": 42.33, "elapsed_time": "1:01:29", "remaining_time": "1:23:45", "throughput": 2863.96, "total_tokens": 10566480} {"current_steps": 16160, "total_steps": 38160, "loss": 0.1258, "lr": 3.568758525939497e-05, "epoch": 8.469601677148846, "percentage": 42.35, "elapsed_time": "1:01:30", "remaining_time": "1:23:44", "throughput": 2864.0, "total_tokens": 10569616} {"current_steps": 16165, "total_steps": 38160, "loss": 0.2192, "lr": 3.5677247391259995e-05, "epoch": 8.472222222222221, "percentage": 42.36, "elapsed_time": "1:01:31", "remaining_time": "1:23:42", "throughput": 2863.93, "total_tokens": 10572336} {"current_steps": 16170, "total_steps": 38160, "loss": 0.2217, "lr": 3.566690728956668e-05, "epoch": 8.474842767295598, "percentage": 42.37, "elapsed_time": "1:01:32", "remaining_time": "1:23:41", "throughput": 2863.73, "total_tokens": 10574576} {"current_steps": 16175, "total_steps": 38160, "loss": 0.1824, "lr": 3.5656564956478056e-05, "epoch": 8.477463312368974, "percentage": 42.39, "elapsed_time": "1:01:33", "remaining_time": "1:23:40", "throughput": 2863.96, "total_tokens": 10578640} {"current_steps": 16180, "total_steps": 38160, "loss": 0.1434, "lr": 3.5646220394157626e-05, "epoch": 8.480083857442349, "percentage": 42.4, "elapsed_time": "1:01:34", "remaining_time": "1:23:39", "throughput": 2863.9, "total_tokens": 10581392} {"current_steps": 16185, "total_steps": 38160, "loss": 0.2122, "lr": 3.563587360476933e-05, "epoch": 8.482704402515724, "percentage": 42.41, "elapsed_time": "1:01:35", "remaining_time": "1:23:37", "throughput": 2863.84, "total_tokens": 10584144} {"current_steps": 16190, "total_steps": 38160, "loss": 0.2139, "lr": 3.562552459047763e-05, "epoch": 8.485324947589099, "percentage": 42.43, "elapsed_time": "1:01:36", "remaining_time": "1:23:36", "throughput": 2863.9, "total_tokens": 10587600} {"current_steps": 16195, "total_steps": 38160, "loss": 0.203, "lr": 3.561517335344741e-05, "epoch": 8.487945492662474, "percentage": 42.44, "elapsed_time": "1:01:38", "remaining_time": "1:23:35", "throughput": 2863.91, "total_tokens": 10590832} {"current_steps": 16200, "total_steps": 38160, "loss": 0.1702, "lr": 3.560481989584402e-05, "epoch": 8.49056603773585, "percentage": 42.45, "elapsed_time": "1:01:39", "remaining_time": "1:23:34", "throughput": 2863.89, "total_tokens": 10593712} {"current_steps": 16205, "total_steps": 38160, "loss": 0.2081, "lr": 3.55944642198333e-05, "epoch": 8.493186582809225, "percentage": 42.47, "elapsed_time": "1:01:40", "remaining_time": "1:23:32", "throughput": 2863.8, "total_tokens": 10596336} {"current_steps": 16210, "total_steps": 38160, "loss": 0.2494, "lr": 3.5584106327581536e-05, "epoch": 8.4958071278826, "percentage": 42.48, "elapsed_time": "1:01:41", "remaining_time": "1:23:31", "throughput": 2863.77, "total_tokens": 10599536} {"current_steps": 16215, "total_steps": 38160, "loss": 0.099, "lr": 3.557374622125547e-05, "epoch": 8.498427672955975, "percentage": 42.49, "elapsed_time": "1:01:42", "remaining_time": "1:23:30", "throughput": 2863.78, "total_tokens": 10602576} {"current_steps": 16220, "total_steps": 38160, "loss": 0.1571, "lr": 3.556338390302234e-05, "epoch": 8.50104821802935, "percentage": 42.51, "elapsed_time": "1:01:43", "remaining_time": "1:23:29", "throughput": 2863.73, "total_tokens": 10605616} {"current_steps": 16225, "total_steps": 38160, "loss": 0.2927, "lr": 3.55530193750498e-05, "epoch": 8.503668763102725, "percentage": 42.52, "elapsed_time": "1:01:44", "remaining_time": "1:23:28", "throughput": 2863.78, "total_tokens": 10609040} {"current_steps": 16230, "total_steps": 38160, "loss": 0.2168, "lr": 3.5542652639505996e-05, "epoch": 8.5062893081761, "percentage": 42.53, "elapsed_time": "1:01:45", "remaining_time": "1:23:27", "throughput": 2863.86, "total_tokens": 10612304} {"current_steps": 16235, "total_steps": 38160, "loss": 0.1623, "lr": 3.5532283698559556e-05, "epoch": 8.508909853249476, "percentage": 42.54, "elapsed_time": "1:01:46", "remaining_time": "1:23:25", "throughput": 2863.74, "total_tokens": 10614928} {"current_steps": 16240, "total_steps": 38160, "loss": 0.2031, "lr": 3.55219125543795e-05, "epoch": 8.51153039832285, "percentage": 42.56, "elapsed_time": "1:01:47", "remaining_time": "1:23:24", "throughput": 2863.79, "total_tokens": 10618320} {"current_steps": 16245, "total_steps": 38160, "loss": 0.2168, "lr": 3.5511539209135396e-05, "epoch": 8.514150943396226, "percentage": 42.57, "elapsed_time": "1:01:48", "remaining_time": "1:23:23", "throughput": 2863.78, "total_tokens": 10621296} {"current_steps": 16250, "total_steps": 38160, "loss": 0.2212, "lr": 3.550116366499721e-05, "epoch": 8.516771488469601, "percentage": 42.58, "elapsed_time": "1:01:49", "remaining_time": "1:23:22", "throughput": 2863.64, "total_tokens": 10623984} {"current_steps": 16255, "total_steps": 38160, "loss": 0.1787, "lr": 3.549078592413538e-05, "epoch": 8.519392033542976, "percentage": 42.6, "elapsed_time": "1:01:51", "remaining_time": "1:23:21", "throughput": 2863.83, "total_tokens": 10628560} {"current_steps": 16260, "total_steps": 38160, "loss": 0.173, "lr": 3.548040598872083e-05, "epoch": 8.522012578616351, "percentage": 42.61, "elapsed_time": "1:01:52", "remaining_time": "1:23:20", "throughput": 2863.93, "total_tokens": 10631856} {"current_steps": 16265, "total_steps": 38160, "loss": 0.1647, "lr": 3.5470023860924905e-05, "epoch": 8.524633123689728, "percentage": 42.62, "elapsed_time": "1:01:53", "remaining_time": "1:23:18", "throughput": 2864.08, "total_tokens": 10635696} {"current_steps": 16270, "total_steps": 38160, "loss": 0.1819, "lr": 3.5459639542919444e-05, "epoch": 8.527253668763104, "percentage": 42.64, "elapsed_time": "1:01:54", "remaining_time": "1:23:17", "throughput": 2863.96, "total_tokens": 10638384} {"current_steps": 16275, "total_steps": 38160, "loss": 0.192, "lr": 3.5449253036876715e-05, "epoch": 8.529874213836479, "percentage": 42.65, "elapsed_time": "1:01:55", "remaining_time": "1:23:16", "throughput": 2863.98, "total_tokens": 10641456} {"current_steps": 16280, "total_steps": 38160, "loss": 0.158, "lr": 3.543886434496947e-05, "epoch": 8.532494758909854, "percentage": 42.66, "elapsed_time": "1:01:56", "remaining_time": "1:23:15", "throughput": 2863.95, "total_tokens": 10644336} {"current_steps": 16285, "total_steps": 38160, "loss": 0.1861, "lr": 3.542847346937089e-05, "epoch": 8.535115303983229, "percentage": 42.68, "elapsed_time": "1:01:57", "remaining_time": "1:23:13", "throughput": 2864.0, "total_tokens": 10647440} {"current_steps": 16290, "total_steps": 38160, "loss": 0.1671, "lr": 3.541808041225464e-05, "epoch": 8.537735849056604, "percentage": 42.69, "elapsed_time": "1:01:58", "remaining_time": "1:23:12", "throughput": 2863.81, "total_tokens": 10649872} {"current_steps": 16295, "total_steps": 38160, "loss": 0.1657, "lr": 3.540768517579481e-05, "epoch": 8.54035639412998, "percentage": 42.7, "elapsed_time": "1:01:59", "remaining_time": "1:23:11", "throughput": 2863.81, "total_tokens": 10652976} {"current_steps": 16300, "total_steps": 38160, "loss": 0.1113, "lr": 3.539728776216599e-05, "epoch": 8.542976939203355, "percentage": 42.71, "elapsed_time": "1:02:00", "remaining_time": "1:23:10", "throughput": 2863.8, "total_tokens": 10656016} {"current_steps": 16305, "total_steps": 38160, "loss": 0.2847, "lr": 3.5386888173543185e-05, "epoch": 8.54559748427673, "percentage": 42.73, "elapsed_time": "1:02:02", "remaining_time": "1:23:08", "throughput": 2863.88, "total_tokens": 10659536} {"current_steps": 16310, "total_steps": 38160, "loss": 0.1517, "lr": 3.5376486412101875e-05, "epoch": 8.548218029350105, "percentage": 42.74, "elapsed_time": "1:02:03", "remaining_time": "1:23:07", "throughput": 2863.84, "total_tokens": 10662416} {"current_steps": 16315, "total_steps": 38160, "loss": 0.1366, "lr": 3.5366082480017994e-05, "epoch": 8.55083857442348, "percentage": 42.75, "elapsed_time": "1:02:04", "remaining_time": "1:23:06", "throughput": 2864.03, "total_tokens": 10666320} {"current_steps": 16320, "total_steps": 38160, "loss": 0.2384, "lr": 3.535567637946792e-05, "epoch": 8.553459119496855, "percentage": 42.77, "elapsed_time": "1:02:05", "remaining_time": "1:23:05", "throughput": 2863.98, "total_tokens": 10669136} {"current_steps": 16325, "total_steps": 38160, "loss": 0.1695, "lr": 3.534526811262848e-05, "epoch": 8.55607966457023, "percentage": 42.78, "elapsed_time": "1:02:06", "remaining_time": "1:23:04", "throughput": 2864.01, "total_tokens": 10672240} {"current_steps": 16330, "total_steps": 38160, "loss": 0.2016, "lr": 3.533485768167698e-05, "epoch": 8.558700209643606, "percentage": 42.79, "elapsed_time": "1:02:07", "remaining_time": "1:23:02", "throughput": 2863.93, "total_tokens": 10674992} {"current_steps": 16335, "total_steps": 38160, "loss": 0.1856, "lr": 3.532444508879117e-05, "epoch": 8.56132075471698, "percentage": 42.81, "elapsed_time": "1:02:08", "remaining_time": "1:23:01", "throughput": 2863.82, "total_tokens": 10677616} {"current_steps": 16340, "total_steps": 38160, "loss": 0.1602, "lr": 3.531403033614922e-05, "epoch": 8.563941299790356, "percentage": 42.82, "elapsed_time": "1:02:09", "remaining_time": "1:23:00", "throughput": 2863.92, "total_tokens": 10681136} {"current_steps": 16345, "total_steps": 38160, "loss": 0.2619, "lr": 3.530361342592981e-05, "epoch": 8.566561844863731, "percentage": 42.83, "elapsed_time": "1:02:10", "remaining_time": "1:22:59", "throughput": 2863.95, "total_tokens": 10684368} {"current_steps": 16350, "total_steps": 38160, "loss": 0.2126, "lr": 3.5293194360312006e-05, "epoch": 8.569182389937106, "percentage": 42.85, "elapsed_time": "1:02:11", "remaining_time": "1:22:57", "throughput": 2863.97, "total_tokens": 10687632} {"current_steps": 16355, "total_steps": 38160, "loss": 0.1925, "lr": 3.528277314147538e-05, "epoch": 8.571802935010481, "percentage": 42.86, "elapsed_time": "1:02:13", "remaining_time": "1:22:57", "throughput": 2864.24, "total_tokens": 10692336} {"current_steps": 16360, "total_steps": 38160, "loss": 0.1899, "lr": 3.5272349771599925e-05, "epoch": 8.574423480083858, "percentage": 42.87, "elapsed_time": "1:02:14", "remaining_time": "1:22:55", "throughput": 2864.36, "total_tokens": 10696048} {"current_steps": 16365, "total_steps": 38160, "loss": 0.1334, "lr": 3.526192425286609e-05, "epoch": 8.577044025157234, "percentage": 42.89, "elapsed_time": "1:02:15", "remaining_time": "1:22:54", "throughput": 2864.53, "total_tokens": 10700304} {"current_steps": 16370, "total_steps": 38160, "loss": 0.1561, "lr": 3.525149658745476e-05, "epoch": 8.579664570230609, "percentage": 42.9, "elapsed_time": "1:02:16", "remaining_time": "1:22:53", "throughput": 2864.46, "total_tokens": 10703120} {"current_steps": 16375, "total_steps": 38160, "loss": 0.1839, "lr": 3.5241066777547315e-05, "epoch": 8.582285115303984, "percentage": 42.91, "elapsed_time": "1:02:17", "remaining_time": "1:22:52", "throughput": 2864.69, "total_tokens": 10707536} {"current_steps": 16380, "total_steps": 38160, "loss": 0.2248, "lr": 3.523063482532554e-05, "epoch": 8.584905660377359, "percentage": 42.92, "elapsed_time": "1:02:18", "remaining_time": "1:22:51", "throughput": 2864.61, "total_tokens": 10710384} {"current_steps": 16385, "total_steps": 38160, "loss": 0.1574, "lr": 3.5220200732971665e-05, "epoch": 8.587526205450734, "percentage": 42.94, "elapsed_time": "1:02:19", "remaining_time": "1:22:50", "throughput": 2864.68, "total_tokens": 10713840} {"current_steps": 16390, "total_steps": 38160, "loss": 0.1668, "lr": 3.52097645026684e-05, "epoch": 8.59014675052411, "percentage": 42.95, "elapsed_time": "1:02:21", "remaining_time": "1:22:49", "throughput": 2864.63, "total_tokens": 10716720} {"current_steps": 16395, "total_steps": 38160, "loss": 0.2087, "lr": 3.519932613659889e-05, "epoch": 8.592767295597485, "percentage": 42.96, "elapsed_time": "1:02:22", "remaining_time": "1:22:47", "throughput": 2864.78, "total_tokens": 10720720} {"current_steps": 16400, "total_steps": 38160, "loss": 0.1778, "lr": 3.5188885636946696e-05, "epoch": 8.59538784067086, "percentage": 42.98, "elapsed_time": "1:02:23", "remaining_time": "1:22:46", "throughput": 2864.82, "total_tokens": 10723952} {"current_steps": 16405, "total_steps": 38160, "loss": 0.2379, "lr": 3.5178443005895884e-05, "epoch": 8.598008385744235, "percentage": 42.99, "elapsed_time": "1:02:24", "remaining_time": "1:22:45", "throughput": 2864.55, "total_tokens": 10726096} {"current_steps": 16410, "total_steps": 38160, "loss": 0.1687, "lr": 3.51679982456309e-05, "epoch": 8.60062893081761, "percentage": 43.0, "elapsed_time": "1:02:25", "remaining_time": "1:22:44", "throughput": 2864.56, "total_tokens": 10729456} {"current_steps": 16415, "total_steps": 38160, "loss": 0.165, "lr": 3.51575513583367e-05, "epoch": 8.603249475890985, "percentage": 43.02, "elapsed_time": "1:02:26", "remaining_time": "1:22:43", "throughput": 2864.39, "total_tokens": 10731824} {"current_steps": 16420, "total_steps": 38160, "loss": 0.1628, "lr": 3.5147102346198635e-05, "epoch": 8.60587002096436, "percentage": 43.03, "elapsed_time": "1:02:27", "remaining_time": "1:22:41", "throughput": 2864.38, "total_tokens": 10734864} {"current_steps": 16425, "total_steps": 38160, "loss": 0.1585, "lr": 3.5136651211402515e-05, "epoch": 8.608490566037736, "percentage": 43.04, "elapsed_time": "1:02:28", "remaining_time": "1:22:40", "throughput": 2864.32, "total_tokens": 10737744} {"current_steps": 16430, "total_steps": 38160, "loss": 0.126, "lr": 3.5126197956134614e-05, "epoch": 8.61111111111111, "percentage": 43.06, "elapsed_time": "1:02:29", "remaining_time": "1:22:39", "throughput": 2864.27, "total_tokens": 10740656} {"current_steps": 16435, "total_steps": 38160, "loss": 0.3036, "lr": 3.5115742582581626e-05, "epoch": 8.613731656184486, "percentage": 43.07, "elapsed_time": "1:02:31", "remaining_time": "1:22:38", "throughput": 2864.38, "total_tokens": 10744688} {"current_steps": 16440, "total_steps": 38160, "loss": 0.2278, "lr": 3.51052850929307e-05, "epoch": 8.616352201257861, "percentage": 43.08, "elapsed_time": "1:02:32", "remaining_time": "1:22:37", "throughput": 2864.19, "total_tokens": 10747184} {"current_steps": 16445, "total_steps": 38160, "loss": 0.2015, "lr": 3.509482548936941e-05, "epoch": 8.618972746331236, "percentage": 43.09, "elapsed_time": "1:02:33", "remaining_time": "1:22:36", "throughput": 2864.21, "total_tokens": 10750320} {"current_steps": 16450, "total_steps": 38160, "loss": 0.1451, "lr": 3.5084363774085804e-05, "epoch": 8.621593291404611, "percentage": 43.11, "elapsed_time": "1:02:34", "remaining_time": "1:22:34", "throughput": 2864.23, "total_tokens": 10753328} {"current_steps": 16455, "total_steps": 38160, "loss": 0.1779, "lr": 3.507389994926834e-05, "epoch": 8.624213836477988, "percentage": 43.12, "elapsed_time": "1:02:35", "remaining_time": "1:22:33", "throughput": 2864.18, "total_tokens": 10756208} {"current_steps": 16460, "total_steps": 38160, "loss": 0.1685, "lr": 3.5063434017105946e-05, "epoch": 8.626834381551364, "percentage": 43.13, "elapsed_time": "1:02:36", "remaining_time": "1:22:32", "throughput": 2864.29, "total_tokens": 10759888} {"current_steps": 16465, "total_steps": 38160, "loss": 0.1364, "lr": 3.505296597978795e-05, "epoch": 8.629454926624739, "percentage": 43.15, "elapsed_time": "1:02:37", "remaining_time": "1:22:31", "throughput": 2864.32, "total_tokens": 10763152} {"current_steps": 16470, "total_steps": 38160, "loss": 0.1895, "lr": 3.504249583950417e-05, "epoch": 8.632075471698114, "percentage": 43.16, "elapsed_time": "1:02:38", "remaining_time": "1:22:30", "throughput": 2864.45, "total_tokens": 10767024} {"current_steps": 16475, "total_steps": 38160, "loss": 0.1488, "lr": 3.503202359844483e-05, "epoch": 8.634696016771489, "percentage": 43.17, "elapsed_time": "1:02:39", "remaining_time": "1:22:28", "throughput": 2864.46, "total_tokens": 10770096} {"current_steps": 16480, "total_steps": 38160, "loss": 0.1879, "lr": 3.50215492588006e-05, "epoch": 8.637316561844864, "percentage": 43.19, "elapsed_time": "1:02:41", "remaining_time": "1:22:28", "throughput": 2864.64, "total_tokens": 10774576} {"current_steps": 16485, "total_steps": 38160, "loss": 0.1754, "lr": 3.5011072822762605e-05, "epoch": 8.63993710691824, "percentage": 43.2, "elapsed_time": "1:02:42", "remaining_time": "1:22:26", "throughput": 2864.54, "total_tokens": 10777296} {"current_steps": 16490, "total_steps": 38160, "loss": 0.177, "lr": 3.500059429252238e-05, "epoch": 8.642557651991615, "percentage": 43.21, "elapsed_time": "1:02:43", "remaining_time": "1:22:25", "throughput": 2864.4, "total_tokens": 10779696} {"current_steps": 16495, "total_steps": 38160, "loss": 0.1877, "lr": 3.499011367027193e-05, "epoch": 8.64517819706499, "percentage": 43.23, "elapsed_time": "1:02:44", "remaining_time": "1:22:24", "throughput": 2864.47, "total_tokens": 10783184} {"current_steps": 16500, "total_steps": 38160, "loss": 0.3019, "lr": 3.4979630958203665e-05, "epoch": 8.647798742138365, "percentage": 43.24, "elapsed_time": "1:02:45", "remaining_time": "1:22:23", "throughput": 2864.43, "total_tokens": 10786512} {"current_steps": 16505, "total_steps": 38160, "loss": 0.16, "lr": 3.496914615851046e-05, "epoch": 8.65041928721174, "percentage": 43.25, "elapsed_time": "1:02:46", "remaining_time": "1:22:22", "throughput": 2864.51, "total_tokens": 10789872} {"current_steps": 16510, "total_steps": 38160, "loss": 0.1669, "lr": 3.495865927338562e-05, "epoch": 8.653039832285115, "percentage": 43.27, "elapsed_time": "1:02:47", "remaining_time": "1:22:20", "throughput": 2864.51, "total_tokens": 10792944} {"current_steps": 16515, "total_steps": 38160, "loss": 0.1747, "lr": 3.494817030502286e-05, "epoch": 8.65566037735849, "percentage": 43.28, "elapsed_time": "1:02:48", "remaining_time": "1:22:19", "throughput": 2864.64, "total_tokens": 10796624} {"current_steps": 16520, "total_steps": 38160, "loss": 0.1836, "lr": 3.493767925561638e-05, "epoch": 8.658280922431866, "percentage": 43.29, "elapsed_time": "1:02:50", "remaining_time": "1:22:18", "throughput": 2864.76, "total_tokens": 10800144} {"current_steps": 16525, "total_steps": 38160, "loss": 0.139, "lr": 3.492718612736077e-05, "epoch": 8.66090146750524, "percentage": 43.3, "elapsed_time": "1:02:51", "remaining_time": "1:22:17", "throughput": 2864.7, "total_tokens": 10803152} {"current_steps": 16530, "total_steps": 38160, "loss": 0.2643, "lr": 3.491669092245108e-05, "epoch": 8.663522012578616, "percentage": 43.32, "elapsed_time": "1:02:52", "remaining_time": "1:22:16", "throughput": 2864.52, "total_tokens": 10805552} {"current_steps": 16535, "total_steps": 38160, "loss": 0.1798, "lr": 3.4906193643082784e-05, "epoch": 8.666142557651991, "percentage": 43.33, "elapsed_time": "1:02:53", "remaining_time": "1:22:14", "throughput": 2864.56, "total_tokens": 10808880} {"current_steps": 16540, "total_steps": 38160, "loss": 0.1739, "lr": 3.4895694291451795e-05, "epoch": 8.668763102725366, "percentage": 43.34, "elapsed_time": "1:02:54", "remaining_time": "1:22:13", "throughput": 2864.56, "total_tokens": 10812240} {"current_steps": 16545, "total_steps": 38160, "loss": 0.1699, "lr": 3.4885192869754444e-05, "epoch": 8.671383647798741, "percentage": 43.36, "elapsed_time": "1:02:55", "remaining_time": "1:22:12", "throughput": 2864.57, "total_tokens": 10815600} {"current_steps": 16550, "total_steps": 38160, "loss": 0.159, "lr": 3.4874689380187537e-05, "epoch": 8.674004192872118, "percentage": 43.37, "elapsed_time": "1:02:56", "remaining_time": "1:22:11", "throughput": 2864.62, "total_tokens": 10819120} {"current_steps": 16555, "total_steps": 38160, "loss": 0.1504, "lr": 3.486418382494826e-05, "epoch": 8.676624737945493, "percentage": 43.38, "elapsed_time": "1:02:57", "remaining_time": "1:22:10", "throughput": 2864.48, "total_tokens": 10821744} {"current_steps": 16560, "total_steps": 38160, "loss": 0.1827, "lr": 3.485367620623426e-05, "epoch": 8.679245283018869, "percentage": 43.4, "elapsed_time": "1:02:58", "remaining_time": "1:22:09", "throughput": 2864.34, "total_tokens": 10824336} {"current_steps": 16565, "total_steps": 38160, "loss": 0.2374, "lr": 3.484316652624362e-05, "epoch": 8.681865828092244, "percentage": 43.41, "elapsed_time": "1:03:00", "remaining_time": "1:22:07", "throughput": 2864.15, "total_tokens": 10826672} {"current_steps": 16570, "total_steps": 38160, "loss": 0.149, "lr": 3.483265478717484e-05, "epoch": 8.684486373165619, "percentage": 43.42, "elapsed_time": "1:03:01", "remaining_time": "1:22:06", "throughput": 2864.22, "total_tokens": 10830192} {"current_steps": 16575, "total_steps": 38160, "loss": 0.2754, "lr": 3.482214099122686e-05, "epoch": 8.687106918238994, "percentage": 43.44, "elapsed_time": "1:03:02", "remaining_time": "1:22:05", "throughput": 2864.37, "total_tokens": 10834096} {"current_steps": 16580, "total_steps": 38160, "loss": 0.1959, "lr": 3.481162514059903e-05, "epoch": 8.68972746331237, "percentage": 43.45, "elapsed_time": "1:03:03", "remaining_time": "1:22:04", "throughput": 2864.4, "total_tokens": 10837360} {"current_steps": 16585, "total_steps": 38160, "loss": 0.2569, "lr": 3.480110723749116e-05, "epoch": 8.692348008385745, "percentage": 43.46, "elapsed_time": "1:03:04", "remaining_time": "1:22:03", "throughput": 2864.53, "total_tokens": 10841168} {"current_steps": 16590, "total_steps": 38160, "loss": 0.1395, "lr": 3.479058728410348e-05, "epoch": 8.69496855345912, "percentage": 43.47, "elapsed_time": "1:03:05", "remaining_time": "1:22:02", "throughput": 2864.62, "total_tokens": 10844784} {"current_steps": 16595, "total_steps": 38160, "loss": 0.1881, "lr": 3.478006528263663e-05, "epoch": 8.697589098532495, "percentage": 43.49, "elapsed_time": "1:03:06", "remaining_time": "1:22:00", "throughput": 2864.49, "total_tokens": 10847376} {"current_steps": 16600, "total_steps": 38160, "loss": 0.1493, "lr": 3.4769541235291704e-05, "epoch": 8.70020964360587, "percentage": 43.5, "elapsed_time": "1:03:07", "remaining_time": "1:21:59", "throughput": 2864.38, "total_tokens": 10850000} {"current_steps": 16605, "total_steps": 38160, "loss": 0.1242, "lr": 3.475901514427021e-05, "epoch": 8.702830188679245, "percentage": 43.51, "elapsed_time": "1:03:08", "remaining_time": "1:21:58", "throughput": 2864.24, "total_tokens": 10852528} {"current_steps": 16610, "total_steps": 38160, "loss": 0.1504, "lr": 3.4748487011774075e-05, "epoch": 8.70545073375262, "percentage": 43.53, "elapsed_time": "1:03:10", "remaining_time": "1:21:57", "throughput": 2864.14, "total_tokens": 10855312} {"current_steps": 16615, "total_steps": 38160, "loss": 0.3024, "lr": 3.473795684000569e-05, "epoch": 8.708071278825996, "percentage": 43.54, "elapsed_time": "1:03:11", "remaining_time": "1:21:56", "throughput": 2864.36, "total_tokens": 10859376} {"current_steps": 16620, "total_steps": 38160, "loss": 0.189, "lr": 3.4727424631167815e-05, "epoch": 8.71069182389937, "percentage": 43.55, "elapsed_time": "1:03:12", "remaining_time": "1:21:54", "throughput": 2864.27, "total_tokens": 10862224} {"current_steps": 16625, "total_steps": 38160, "loss": 0.1903, "lr": 3.471689038746369e-05, "epoch": 8.713312368972746, "percentage": 43.57, "elapsed_time": "1:03:13", "remaining_time": "1:21:53", "throughput": 2864.23, "total_tokens": 10865104} {"current_steps": 16630, "total_steps": 38160, "loss": 0.1487, "lr": 3.470635411109695e-05, "epoch": 8.715932914046121, "percentage": 43.58, "elapsed_time": "1:03:14", "remaining_time": "1:21:52", "throughput": 2864.13, "total_tokens": 10867792} {"current_steps": 16635, "total_steps": 38160, "loss": 0.1898, "lr": 3.469581580427167e-05, "epoch": 8.718553459119496, "percentage": 43.59, "elapsed_time": "1:03:15", "remaining_time": "1:21:51", "throughput": 2864.13, "total_tokens": 10870768} {"current_steps": 16640, "total_steps": 38160, "loss": 0.1372, "lr": 3.4685275469192335e-05, "epoch": 8.721174004192871, "percentage": 43.61, "elapsed_time": "1:03:16", "remaining_time": "1:21:50", "throughput": 2864.3, "total_tokens": 10875056} {"current_steps": 16645, "total_steps": 38160, "loss": 0.2025, "lr": 3.467473310806387e-05, "epoch": 8.723794549266248, "percentage": 43.62, "elapsed_time": "1:03:17", "remaining_time": "1:21:49", "throughput": 2864.28, "total_tokens": 10878288} {"current_steps": 16650, "total_steps": 38160, "loss": 0.2226, "lr": 3.466418872309161e-05, "epoch": 8.726415094339622, "percentage": 43.63, "elapsed_time": "1:03:19", "remaining_time": "1:21:47", "throughput": 2864.06, "total_tokens": 10880720} {"current_steps": 16655, "total_steps": 38160, "loss": 0.1162, "lr": 3.465364231648133e-05, "epoch": 8.729035639412999, "percentage": 43.65, "elapsed_time": "1:03:20", "remaining_time": "1:21:46", "throughput": 2864.17, "total_tokens": 10884528} {"current_steps": 16660, "total_steps": 38160, "loss": 0.23, "lr": 3.464309389043921e-05, "epoch": 8.731656184486374, "percentage": 43.66, "elapsed_time": "1:03:21", "remaining_time": "1:21:45", "throughput": 2863.98, "total_tokens": 10886960} {"current_steps": 16665, "total_steps": 38160, "loss": 0.1751, "lr": 3.4632543447171856e-05, "epoch": 8.734276729559749, "percentage": 43.67, "elapsed_time": "1:03:22", "remaining_time": "1:21:44", "throughput": 2863.94, "total_tokens": 10889904} {"current_steps": 16670, "total_steps": 38160, "loss": 0.2261, "lr": 3.4621990988886315e-05, "epoch": 8.736897274633124, "percentage": 43.68, "elapsed_time": "1:03:23", "remaining_time": "1:21:43", "throughput": 2863.96, "total_tokens": 10893072} {"current_steps": 16675, "total_steps": 38160, "loss": 0.2305, "lr": 3.461143651779003e-05, "epoch": 8.7395178197065, "percentage": 43.7, "elapsed_time": "1:03:24", "remaining_time": "1:21:42", "throughput": 2864.25, "total_tokens": 10897392} {"current_steps": 16680, "total_steps": 38160, "loss": 0.22, "lr": 3.4600880036090876e-05, "epoch": 8.742138364779874, "percentage": 43.71, "elapsed_time": "1:03:25", "remaining_time": "1:21:40", "throughput": 2864.32, "total_tokens": 10901008} {"current_steps": 16685, "total_steps": 38160, "loss": 0.2071, "lr": 3.459032154599715e-05, "epoch": 8.74475890985325, "percentage": 43.72, "elapsed_time": "1:03:26", "remaining_time": "1:21:39", "throughput": 2864.5, "total_tokens": 10904848} {"current_steps": 16690, "total_steps": 38160, "loss": 0.1792, "lr": 3.457976104971757e-05, "epoch": 8.747379454926625, "percentage": 43.74, "elapsed_time": "1:03:27", "remaining_time": "1:21:38", "throughput": 2864.67, "total_tokens": 10908528} {"current_steps": 16695, "total_steps": 38160, "loss": 0.2333, "lr": 3.4569198549461276e-05, "epoch": 8.75, "percentage": 43.75, "elapsed_time": "1:03:29", "remaining_time": "1:21:37", "throughput": 2864.8, "total_tokens": 10912080} {"current_steps": 16700, "total_steps": 38160, "loss": 0.2358, "lr": 3.455863404743781e-05, "epoch": 8.752620545073375, "percentage": 43.76, "elapsed_time": "1:03:30", "remaining_time": "1:21:36", "throughput": 2865.0, "total_tokens": 10916528} {"current_steps": 16705, "total_steps": 38160, "loss": 0.1483, "lr": 3.454806754585716e-05, "epoch": 8.75524109014675, "percentage": 43.78, "elapsed_time": "1:03:31", "remaining_time": "1:21:35", "throughput": 2865.17, "total_tokens": 10920688} {"current_steps": 16710, "total_steps": 38160, "loss": 0.1899, "lr": 3.453749904692971e-05, "epoch": 8.757861635220126, "percentage": 43.79, "elapsed_time": "1:03:32", "remaining_time": "1:21:34", "throughput": 2865.1, "total_tokens": 10923600} {"current_steps": 16715, "total_steps": 38160, "loss": 0.1594, "lr": 3.452692855286626e-05, "epoch": 8.7604821802935, "percentage": 43.8, "elapsed_time": "1:03:33", "remaining_time": "1:21:32", "throughput": 2865.04, "total_tokens": 10926544} {"current_steps": 16720, "total_steps": 38160, "loss": 0.1716, "lr": 3.4516356065878055e-05, "epoch": 8.763102725366876, "percentage": 43.82, "elapsed_time": "1:03:34", "remaining_time": "1:21:31", "throughput": 2864.98, "total_tokens": 10929392} {"current_steps": 16725, "total_steps": 38160, "loss": 0.1528, "lr": 3.450578158817671e-05, "epoch": 8.765723270440251, "percentage": 43.83, "elapsed_time": "1:03:36", "remaining_time": "1:21:30", "throughput": 2865.16, "total_tokens": 10933456} {"current_steps": 16730, "total_steps": 38160, "loss": 0.2361, "lr": 3.4495205121974325e-05, "epoch": 8.768343815513626, "percentage": 43.84, "elapsed_time": "1:03:37", "remaining_time": "1:21:29", "throughput": 2865.09, "total_tokens": 10936336} {"current_steps": 16735, "total_steps": 38160, "loss": 0.1979, "lr": 3.448462666948335e-05, "epoch": 8.770964360587001, "percentage": 43.85, "elapsed_time": "1:03:38", "remaining_time": "1:21:28", "throughput": 2865.15, "total_tokens": 10939696} {"current_steps": 16740, "total_steps": 38160, "loss": 0.1292, "lr": 3.4474046232916674e-05, "epoch": 8.773584905660378, "percentage": 43.87, "elapsed_time": "1:03:39", "remaining_time": "1:21:27", "throughput": 2865.0, "total_tokens": 10942192} {"current_steps": 16745, "total_steps": 38160, "loss": 0.1262, "lr": 3.4463463814487616e-05, "epoch": 8.776205450733752, "percentage": 43.88, "elapsed_time": "1:03:40", "remaining_time": "1:21:25", "throughput": 2864.86, "total_tokens": 10944624} {"current_steps": 16750, "total_steps": 38160, "loss": 0.1389, "lr": 3.44528794164099e-05, "epoch": 8.778825995807129, "percentage": 43.89, "elapsed_time": "1:03:41", "remaining_time": "1:21:24", "throughput": 2864.91, "total_tokens": 10947952} {"current_steps": 16755, "total_steps": 38160, "loss": 0.1568, "lr": 3.4442293040897646e-05, "epoch": 8.781446540880504, "percentage": 43.91, "elapsed_time": "1:03:42", "remaining_time": "1:21:23", "throughput": 2864.97, "total_tokens": 10951440} {"current_steps": 16760, "total_steps": 38160, "loss": 0.1191, "lr": 3.443170469016542e-05, "epoch": 8.784067085953879, "percentage": 43.92, "elapsed_time": "1:03:43", "remaining_time": "1:21:22", "throughput": 2864.85, "total_tokens": 10954224} {"current_steps": 16765, "total_steps": 38160, "loss": 0.1811, "lr": 3.442111436642817e-05, "epoch": 8.786687631027254, "percentage": 43.93, "elapsed_time": "1:03:44", "remaining_time": "1:21:21", "throughput": 2864.86, "total_tokens": 10957392} {"current_steps": 16770, "total_steps": 38160, "loss": 0.235, "lr": 3.441052207190127e-05, "epoch": 8.78930817610063, "percentage": 43.95, "elapsed_time": "1:03:45", "remaining_time": "1:21:19", "throughput": 2865.01, "total_tokens": 10961136} {"current_steps": 16775, "total_steps": 38160, "loss": 0.199, "lr": 3.4399927808800526e-05, "epoch": 8.791928721174004, "percentage": 43.96, "elapsed_time": "1:03:46", "remaining_time": "1:21:18", "throughput": 2865.01, "total_tokens": 10964272} {"current_steps": 16780, "total_steps": 38160, "loss": 0.1107, "lr": 3.438933157934211e-05, "epoch": 8.79454926624738, "percentage": 43.97, "elapsed_time": "1:03:48", "remaining_time": "1:21:17", "throughput": 2864.99, "total_tokens": 10967344} {"current_steps": 16785, "total_steps": 38160, "loss": 0.1867, "lr": 3.4378733385742653e-05, "epoch": 8.797169811320755, "percentage": 43.99, "elapsed_time": "1:03:49", "remaining_time": "1:21:16", "throughput": 2865.09, "total_tokens": 10970800} {"current_steps": 16790, "total_steps": 38160, "loss": 0.1527, "lr": 3.436813323021918e-05, "epoch": 8.79979035639413, "percentage": 44.0, "elapsed_time": "1:03:50", "remaining_time": "1:21:15", "throughput": 2865.18, "total_tokens": 10974544} {"current_steps": 16795, "total_steps": 38160, "loss": 0.202, "lr": 3.43575311149891e-05, "epoch": 8.802410901467505, "percentage": 44.01, "elapsed_time": "1:03:51", "remaining_time": "1:21:13", "throughput": 2864.94, "total_tokens": 10976784} {"current_steps": 16800, "total_steps": 38160, "loss": 0.2263, "lr": 3.434692704227028e-05, "epoch": 8.80503144654088, "percentage": 44.03, "elapsed_time": "1:03:52", "remaining_time": "1:21:12", "throughput": 2865.02, "total_tokens": 10980400} {"current_steps": 16805, "total_steps": 38160, "loss": 0.1349, "lr": 3.4336321014280944e-05, "epoch": 8.807651991614255, "percentage": 44.04, "elapsed_time": "1:03:54", "remaining_time": "1:21:12", "throughput": 2865.29, "total_tokens": 10986160} {"current_steps": 16810, "total_steps": 38160, "loss": 0.1785, "lr": 3.432571303323977e-05, "epoch": 8.81027253668763, "percentage": 44.05, "elapsed_time": "1:03:55", "remaining_time": "1:21:11", "throughput": 2865.3, "total_tokens": 10989584} {"current_steps": 16815, "total_steps": 38160, "loss": 0.2367, "lr": 3.431510310136583e-05, "epoch": 8.812893081761006, "percentage": 44.06, "elapsed_time": "1:03:56", "remaining_time": "1:21:10", "throughput": 2865.24, "total_tokens": 10992464} {"current_steps": 16820, "total_steps": 38160, "loss": 0.2234, "lr": 3.4304491220878585e-05, "epoch": 8.815513626834381, "percentage": 44.08, "elapsed_time": "1:03:57", "remaining_time": "1:21:08", "throughput": 2865.21, "total_tokens": 10995472} {"current_steps": 16825, "total_steps": 38160, "loss": 0.1646, "lr": 3.429387739399793e-05, "epoch": 8.818134171907756, "percentage": 44.09, "elapsed_time": "1:03:58", "remaining_time": "1:21:07", "throughput": 2865.24, "total_tokens": 10999088} {"current_steps": 16830, "total_steps": 38160, "loss": 0.1696, "lr": 3.428326162294416e-05, "epoch": 8.820754716981131, "percentage": 44.1, "elapsed_time": "1:03:59", "remaining_time": "1:21:06", "throughput": 2865.15, "total_tokens": 11002000} {"current_steps": 16835, "total_steps": 38160, "loss": 0.2176, "lr": 3.427264390993795e-05, "epoch": 8.823375262054507, "percentage": 44.12, "elapsed_time": "1:04:01", "remaining_time": "1:21:05", "throughput": 2865.2, "total_tokens": 11005360} {"current_steps": 16840, "total_steps": 38160, "loss": 0.1495, "lr": 3.426202425720044e-05, "epoch": 8.825995807127882, "percentage": 44.13, "elapsed_time": "1:04:02", "remaining_time": "1:21:04", "throughput": 2865.11, "total_tokens": 11008272} {"current_steps": 16845, "total_steps": 38160, "loss": 0.1844, "lr": 3.425140266695312e-05, "epoch": 8.828616352201259, "percentage": 44.14, "elapsed_time": "1:04:03", "remaining_time": "1:21:03", "throughput": 2865.16, "total_tokens": 11011760} {"current_steps": 16850, "total_steps": 38160, "loss": 0.1786, "lr": 3.4240779141417905e-05, "epoch": 8.831236897274634, "percentage": 44.16, "elapsed_time": "1:04:04", "remaining_time": "1:21:01", "throughput": 2865.12, "total_tokens": 11014736} {"current_steps": 16855, "total_steps": 38160, "loss": 0.1819, "lr": 3.423015368281711e-05, "epoch": 8.833857442348009, "percentage": 44.17, "elapsed_time": "1:04:05", "remaining_time": "1:21:00", "throughput": 2865.15, "total_tokens": 11018128} {"current_steps": 16860, "total_steps": 38160, "loss": 0.1328, "lr": 3.421952629337348e-05, "epoch": 8.836477987421384, "percentage": 44.18, "elapsed_time": "1:04:06", "remaining_time": "1:20:59", "throughput": 2865.28, "total_tokens": 11022032} {"current_steps": 16865, "total_steps": 38160, "loss": 0.152, "lr": 3.420889697531013e-05, "epoch": 8.83909853249476, "percentage": 44.2, "elapsed_time": "1:04:07", "remaining_time": "1:20:58", "throughput": 2865.25, "total_tokens": 11024944} {"current_steps": 16870, "total_steps": 38160, "loss": 0.1727, "lr": 3.419826573085058e-05, "epoch": 8.841719077568134, "percentage": 44.21, "elapsed_time": "1:04:08", "remaining_time": "1:20:57", "throughput": 2865.29, "total_tokens": 11028272} {"current_steps": 16875, "total_steps": 38160, "loss": 0.1695, "lr": 3.418763256221879e-05, "epoch": 8.84433962264151, "percentage": 44.22, "elapsed_time": "1:04:10", "remaining_time": "1:20:56", "throughput": 2865.22, "total_tokens": 11031088} {"current_steps": 16880, "total_steps": 38160, "loss": 0.2177, "lr": 3.4176997471639085e-05, "epoch": 8.846960167714885, "percentage": 44.23, "elapsed_time": "1:04:11", "remaining_time": "1:20:54", "throughput": 2865.05, "total_tokens": 11033456} {"current_steps": 16885, "total_steps": 38160, "loss": 0.2381, "lr": 3.4166360461336206e-05, "epoch": 8.84958071278826, "percentage": 44.25, "elapsed_time": "1:04:12", "remaining_time": "1:20:53", "throughput": 2865.11, "total_tokens": 11036976} {"current_steps": 16890, "total_steps": 38160, "loss": 0.1812, "lr": 3.41557215335353e-05, "epoch": 8.852201257861635, "percentage": 44.26, "elapsed_time": "1:04:13", "remaining_time": "1:20:52", "throughput": 2864.93, "total_tokens": 11039472} {"current_steps": 16895, "total_steps": 38160, "loss": 0.2005, "lr": 3.4145080690461887e-05, "epoch": 8.85482180293501, "percentage": 44.27, "elapsed_time": "1:04:14", "remaining_time": "1:20:51", "throughput": 2864.74, "total_tokens": 11042064} {"current_steps": 16900, "total_steps": 38160, "loss": 0.2113, "lr": 3.4134437934341936e-05, "epoch": 8.857442348008385, "percentage": 44.29, "elapsed_time": "1:04:15", "remaining_time": "1:20:50", "throughput": 2864.73, "total_tokens": 11045232} {"current_steps": 16905, "total_steps": 38160, "loss": 0.1847, "lr": 3.4123793267401784e-05, "epoch": 8.86006289308176, "percentage": 44.3, "elapsed_time": "1:04:16", "remaining_time": "1:20:49", "throughput": 2864.81, "total_tokens": 11048784} {"current_steps": 16910, "total_steps": 38160, "loss": 0.2113, "lr": 3.411314669186816e-05, "epoch": 8.862683438155136, "percentage": 44.31, "elapsed_time": "1:04:17", "remaining_time": "1:20:47", "throughput": 2864.97, "total_tokens": 11052528} {"current_steps": 16915, "total_steps": 38160, "loss": 0.227, "lr": 3.410249820996823e-05, "epoch": 8.865303983228511, "percentage": 44.33, "elapsed_time": "1:04:18", "remaining_time": "1:20:46", "throughput": 2864.99, "total_tokens": 11055824} {"current_steps": 16920, "total_steps": 38160, "loss": 0.1316, "lr": 3.4091847823929513e-05, "epoch": 8.867924528301886, "percentage": 44.34, "elapsed_time": "1:04:20", "remaining_time": "1:20:45", "throughput": 2865.09, "total_tokens": 11059504} {"current_steps": 16925, "total_steps": 38160, "loss": 0.142, "lr": 3.4081195535979946e-05, "epoch": 8.870545073375261, "percentage": 44.35, "elapsed_time": "1:04:21", "remaining_time": "1:20:44", "throughput": 2865.09, "total_tokens": 11062544} {"current_steps": 16930, "total_steps": 38160, "loss": 0.1961, "lr": 3.40705413483479e-05, "epoch": 8.873165618448636, "percentage": 44.37, "elapsed_time": "1:04:22", "remaining_time": "1:20:43", "throughput": 2865.09, "total_tokens": 11065584} {"current_steps": 16935, "total_steps": 38160, "loss": 0.1175, "lr": 3.405988526326207e-05, "epoch": 8.875786163522012, "percentage": 44.38, "elapsed_time": "1:04:23", "remaining_time": "1:20:41", "throughput": 2865.04, "total_tokens": 11068336} {"current_steps": 16940, "total_steps": 38160, "loss": 0.1554, "lr": 3.40492272829516e-05, "epoch": 8.878406708595389, "percentage": 44.39, "elapsed_time": "1:04:24", "remaining_time": "1:20:40", "throughput": 2864.94, "total_tokens": 11071184} {"current_steps": 16945, "total_steps": 38160, "loss": 0.0998, "lr": 3.403856740964604e-05, "epoch": 8.881027253668764, "percentage": 44.41, "elapsed_time": "1:04:25", "remaining_time": "1:20:39", "throughput": 2864.94, "total_tokens": 11074320} {"current_steps": 16950, "total_steps": 38160, "loss": 0.147, "lr": 3.4027905645575275e-05, "epoch": 8.883647798742139, "percentage": 44.42, "elapsed_time": "1:04:26", "remaining_time": "1:20:38", "throughput": 2864.86, "total_tokens": 11077168} {"current_steps": 16955, "total_steps": 38160, "loss": 0.1873, "lr": 3.401724199296966e-05, "epoch": 8.886268343815514, "percentage": 44.43, "elapsed_time": "1:04:27", "remaining_time": "1:20:37", "throughput": 2864.84, "total_tokens": 11080080} {"current_steps": 16960, "total_steps": 38160, "loss": 0.1541, "lr": 3.400657645405989e-05, "epoch": 8.88888888888889, "percentage": 44.44, "elapsed_time": "1:04:28", "remaining_time": "1:20:35", "throughput": 2864.94, "total_tokens": 11083408} {"current_steps": 16965, "total_steps": 38160, "loss": 0.2243, "lr": 3.3995909031077065e-05, "epoch": 8.891509433962264, "percentage": 44.46, "elapsed_time": "1:04:29", "remaining_time": "1:20:34", "throughput": 2865.09, "total_tokens": 11087184} {"current_steps": 16970, "total_steps": 38160, "loss": 0.0949, "lr": 3.398523972625272e-05, "epoch": 8.89412997903564, "percentage": 44.47, "elapsed_time": "1:04:30", "remaining_time": "1:20:33", "throughput": 2865.2, "total_tokens": 11090864} {"current_steps": 16975, "total_steps": 38160, "loss": 0.1172, "lr": 3.3974568541818723e-05, "epoch": 8.896750524109015, "percentage": 44.48, "elapsed_time": "1:04:31", "remaining_time": "1:20:32", "throughput": 2865.31, "total_tokens": 11094288} {"current_steps": 16980, "total_steps": 38160, "loss": 0.1166, "lr": 3.396389548000738e-05, "epoch": 8.89937106918239, "percentage": 44.5, "elapsed_time": "1:04:32", "remaining_time": "1:20:30", "throughput": 2865.15, "total_tokens": 11096656} {"current_steps": 16985, "total_steps": 38160, "loss": 0.1859, "lr": 3.395322054305137e-05, "epoch": 8.901991614255765, "percentage": 44.51, "elapsed_time": "1:04:34", "remaining_time": "1:20:29", "throughput": 2865.21, "total_tokens": 11100144} {"current_steps": 16990, "total_steps": 38160, "loss": 0.1686, "lr": 3.394254373318376e-05, "epoch": 8.90461215932914, "percentage": 44.52, "elapsed_time": "1:04:35", "remaining_time": "1:20:28", "throughput": 2865.29, "total_tokens": 11103440} {"current_steps": 16995, "total_steps": 38160, "loss": 0.148, "lr": 3.3931865052638026e-05, "epoch": 8.907232704402515, "percentage": 44.54, "elapsed_time": "1:04:36", "remaining_time": "1:20:27", "throughput": 2865.43, "total_tokens": 11107056} {"current_steps": 17000, "total_steps": 38160, "loss": 0.1567, "lr": 3.392118450364802e-05, "epoch": 8.90985324947589, "percentage": 44.55, "elapsed_time": "1:04:37", "remaining_time": "1:20:26", "throughput": 2865.53, "total_tokens": 11110640} {"current_steps": 17005, "total_steps": 38160, "loss": 0.124, "lr": 3.391050208844799e-05, "epoch": 8.912473794549266, "percentage": 44.56, "elapsed_time": "1:04:39", "remaining_time": "1:20:25", "throughput": 2865.84, "total_tokens": 11117008} {"current_steps": 17010, "total_steps": 38160, "loss": 0.1377, "lr": 3.389981780927259e-05, "epoch": 8.915094339622641, "percentage": 44.58, "elapsed_time": "1:04:40", "remaining_time": "1:20:24", "throughput": 2865.85, "total_tokens": 11120176} {"current_steps": 17015, "total_steps": 38160, "loss": 0.171, "lr": 3.3889131668356834e-05, "epoch": 8.917714884696016, "percentage": 44.59, "elapsed_time": "1:04:41", "remaining_time": "1:20:23", "throughput": 2865.9, "total_tokens": 11123504} {"current_steps": 17020, "total_steps": 38160, "loss": 0.2625, "lr": 3.387844366793614e-05, "epoch": 8.920335429769391, "percentage": 44.6, "elapsed_time": "1:04:42", "remaining_time": "1:20:22", "throughput": 2865.72, "total_tokens": 11126000} {"current_steps": 17025, "total_steps": 38160, "loss": 0.1594, "lr": 3.3867753810246326e-05, "epoch": 8.922955974842766, "percentage": 44.61, "elapsed_time": "1:04:43", "remaining_time": "1:20:21", "throughput": 2865.86, "total_tokens": 11129584} {"current_steps": 17030, "total_steps": 38160, "loss": 0.2012, "lr": 3.3857062097523586e-05, "epoch": 8.925576519916142, "percentage": 44.63, "elapsed_time": "1:04:44", "remaining_time": "1:20:19", "throughput": 2865.71, "total_tokens": 11132240} {"current_steps": 17035, "total_steps": 38160, "loss": 0.1822, "lr": 3.38463685320045e-05, "epoch": 8.928197064989519, "percentage": 44.64, "elapsed_time": "1:04:45", "remaining_time": "1:20:18", "throughput": 2865.63, "total_tokens": 11135120} {"current_steps": 17040, "total_steps": 38160, "loss": 0.0985, "lr": 3.3835673115926045e-05, "epoch": 8.930817610062894, "percentage": 44.65, "elapsed_time": "1:04:46", "remaining_time": "1:20:17", "throughput": 2865.55, "total_tokens": 11137968} {"current_steps": 17045, "total_steps": 38160, "loss": 0.1638, "lr": 3.382497585152557e-05, "epoch": 8.933438155136269, "percentage": 44.67, "elapsed_time": "1:04:47", "remaining_time": "1:20:16", "throughput": 2865.38, "total_tokens": 11140368} {"current_steps": 17050, "total_steps": 38160, "loss": 0.2064, "lr": 3.3814276741040835e-05, "epoch": 8.936058700209644, "percentage": 44.68, "elapsed_time": "1:04:49", "remaining_time": "1:20:15", "throughput": 2865.56, "total_tokens": 11145168} {"current_steps": 17055, "total_steps": 38160, "loss": 0.1919, "lr": 3.380357578670996e-05, "epoch": 8.93867924528302, "percentage": 44.69, "elapsed_time": "1:04:50", "remaining_time": "1:20:14", "throughput": 2865.67, "total_tokens": 11149008} {"current_steps": 17060, "total_steps": 38160, "loss": 0.1787, "lr": 3.379287299077146e-05, "epoch": 8.941299790356394, "percentage": 44.71, "elapsed_time": "1:04:52", "remaining_time": "1:20:14", "throughput": 2866.18, "total_tokens": 11156336} {"current_steps": 17065, "total_steps": 38160, "loss": 0.2454, "lr": 3.3782168355464263e-05, "epoch": 8.94392033542977, "percentage": 44.72, "elapsed_time": "1:04:53", "remaining_time": "1:20:12", "throughput": 2866.14, "total_tokens": 11159152} {"current_steps": 17070, "total_steps": 38160, "loss": 0.1854, "lr": 3.377146188302762e-05, "epoch": 8.946540880503145, "percentage": 44.73, "elapsed_time": "1:04:54", "remaining_time": "1:20:11", "throughput": 2866.09, "total_tokens": 11162096} {"current_steps": 17075, "total_steps": 38160, "loss": 0.1748, "lr": 3.376075357570124e-05, "epoch": 8.94916142557652, "percentage": 44.75, "elapsed_time": "1:04:55", "remaining_time": "1:20:10", "throughput": 2866.11, "total_tokens": 11165200} {"current_steps": 17080, "total_steps": 38160, "loss": 0.2237, "lr": 3.3750043435725144e-05, "epoch": 8.951781970649895, "percentage": 44.76, "elapsed_time": "1:04:56", "remaining_time": "1:20:09", "throughput": 2866.12, "total_tokens": 11168368} {"current_steps": 17085, "total_steps": 38160, "loss": 0.1986, "lr": 3.373933146533979e-05, "epoch": 8.95440251572327, "percentage": 44.77, "elapsed_time": "1:04:57", "remaining_time": "1:20:08", "throughput": 2866.2, "total_tokens": 11172048} {"current_steps": 17090, "total_steps": 38160, "loss": 0.1746, "lr": 3.3728617666786e-05, "epoch": 8.957023060796645, "percentage": 44.79, "elapsed_time": "1:04:59", "remaining_time": "1:20:07", "throughput": 2866.25, "total_tokens": 11175600} {"current_steps": 17095, "total_steps": 38160, "loss": 0.188, "lr": 3.371790204230497e-05, "epoch": 8.95964360587002, "percentage": 44.8, "elapsed_time": "1:05:00", "remaining_time": "1:20:05", "throughput": 2866.21, "total_tokens": 11178576} {"current_steps": 17100, "total_steps": 38160, "loss": 0.1999, "lr": 3.3707184594138295e-05, "epoch": 8.962264150943396, "percentage": 44.81, "elapsed_time": "1:05:01", "remaining_time": "1:20:04", "throughput": 2866.03, "total_tokens": 11181168} {"current_steps": 17105, "total_steps": 38160, "loss": 0.1465, "lr": 3.369646532452795e-05, "epoch": 8.964884696016771, "percentage": 44.82, "elapsed_time": "1:05:02", "remaining_time": "1:20:03", "throughput": 2866.03, "total_tokens": 11184400} {"current_steps": 17110, "total_steps": 38160, "loss": 0.2313, "lr": 3.3685744235716254e-05, "epoch": 8.967505241090146, "percentage": 44.84, "elapsed_time": "1:05:03", "remaining_time": "1:20:02", "throughput": 2866.0, "total_tokens": 11187536} {"current_steps": 17115, "total_steps": 38160, "loss": 0.1938, "lr": 3.367502132994598e-05, "epoch": 8.970125786163521, "percentage": 44.85, "elapsed_time": "1:05:04", "remaining_time": "1:20:01", "throughput": 2866.13, "total_tokens": 11191568} {"current_steps": 17120, "total_steps": 38160, "loss": 0.1439, "lr": 3.366429660946019e-05, "epoch": 8.972746331236896, "percentage": 44.86, "elapsed_time": "1:05:05", "remaining_time": "1:20:00", "throughput": 2866.15, "total_tokens": 11195024} {"current_steps": 17125, "total_steps": 38160, "loss": 0.2183, "lr": 3.365357007650241e-05, "epoch": 8.975366876310272, "percentage": 44.88, "elapsed_time": "1:05:07", "remaining_time": "1:19:59", "throughput": 2866.23, "total_tokens": 11198480} {"current_steps": 17130, "total_steps": 38160, "loss": 0.2013, "lr": 3.364284173331649e-05, "epoch": 8.977987421383649, "percentage": 44.89, "elapsed_time": "1:05:08", "remaining_time": "1:19:57", "throughput": 2866.26, "total_tokens": 11201712} {"current_steps": 17135, "total_steps": 38160, "loss": 0.138, "lr": 3.3632111582146686e-05, "epoch": 8.980607966457024, "percentage": 44.9, "elapsed_time": "1:05:09", "remaining_time": "1:19:56", "throughput": 2866.25, "total_tokens": 11204720} {"current_steps": 17140, "total_steps": 38160, "loss": 0.1985, "lr": 3.362137962523761e-05, "epoch": 8.983228511530399, "percentage": 44.92, "elapsed_time": "1:05:10", "remaining_time": "1:19:55", "throughput": 2866.17, "total_tokens": 11207440} {"current_steps": 17145, "total_steps": 38160, "loss": 0.1748, "lr": 3.361064586483429e-05, "epoch": 8.985849056603774, "percentage": 44.93, "elapsed_time": "1:05:11", "remaining_time": "1:19:54", "throughput": 2866.13, "total_tokens": 11210384} {"current_steps": 17150, "total_steps": 38160, "loss": 0.1865, "lr": 3.359991030318208e-05, "epoch": 8.98846960167715, "percentage": 44.94, "elapsed_time": "1:05:12", "remaining_time": "1:19:53", "throughput": 2866.08, "total_tokens": 11213392} {"current_steps": 17155, "total_steps": 38160, "loss": 0.225, "lr": 3.358917294252675e-05, "epoch": 8.991090146750524, "percentage": 44.96, "elapsed_time": "1:05:13", "remaining_time": "1:19:51", "throughput": 2865.98, "total_tokens": 11216016} {"current_steps": 17160, "total_steps": 38160, "loss": 0.1796, "lr": 3.357843378511443e-05, "epoch": 8.9937106918239, "percentage": 44.97, "elapsed_time": "1:05:14", "remaining_time": "1:19:50", "throughput": 2865.76, "total_tokens": 11218160} {"current_steps": 17165, "total_steps": 38160, "loss": 0.3303, "lr": 3.3567692833191635e-05, "epoch": 8.996331236897275, "percentage": 44.98, "elapsed_time": "1:05:15", "remaining_time": "1:19:49", "throughput": 2865.82, "total_tokens": 11222000} {"current_steps": 17170, "total_steps": 38160, "loss": 0.1853, "lr": 3.355695008900525e-05, "epoch": 8.99895178197065, "percentage": 44.99, "elapsed_time": "1:05:16", "remaining_time": "1:19:48", "throughput": 2865.78, "total_tokens": 11224816} {"current_steps": 17172, "total_steps": 38160, "eval_loss": 0.7038738131523132, "epoch": 9.0, "percentage": 45.0, "elapsed_time": "1:05:29", "remaining_time": "1:20:02", "throughput": 2857.05, "total_tokens": 11225416} {"current_steps": 17175, "total_steps": 38160, "loss": 0.189, "lr": 3.354620555480251e-05, "epoch": 9.001572327044025, "percentage": 45.01, "elapsed_time": "1:05:33", "remaining_time": "1:20:05", "throughput": 2854.35, "total_tokens": 11227112} {"current_steps": 17180, "total_steps": 38160, "loss": 0.1216, "lr": 3.353545923283108e-05, "epoch": 9.0041928721174, "percentage": 45.02, "elapsed_time": "1:05:34", "remaining_time": "1:20:04", "throughput": 2854.17, "total_tokens": 11229544} {"current_steps": 17185, "total_steps": 38160, "loss": 0.1724, "lr": 3.352471112533895e-05, "epoch": 9.006813417190775, "percentage": 45.03, "elapsed_time": "1:05:35", "remaining_time": "1:20:03", "throughput": 2854.37, "total_tokens": 11233640} {"current_steps": 17190, "total_steps": 38160, "loss": 0.0785, "lr": 3.351396123457451e-05, "epoch": 9.00943396226415, "percentage": 45.05, "elapsed_time": "1:05:36", "remaining_time": "1:20:02", "throughput": 2854.3, "total_tokens": 11236552} {"current_steps": 17195, "total_steps": 38160, "loss": 0.1698, "lr": 3.350320956278652e-05, "epoch": 9.012054507337526, "percentage": 45.06, "elapsed_time": "1:05:37", "remaining_time": "1:20:01", "throughput": 2854.39, "total_tokens": 11240008} {"current_steps": 17200, "total_steps": 38160, "loss": 0.1602, "lr": 3.349245611222409e-05, "epoch": 9.014675052410901, "percentage": 45.07, "elapsed_time": "1:05:38", "remaining_time": "1:19:59", "throughput": 2854.37, "total_tokens": 11243176} {"current_steps": 17205, "total_steps": 38160, "loss": 0.1206, "lr": 3.348170088513673e-05, "epoch": 9.017295597484276, "percentage": 45.09, "elapsed_time": "1:05:40", "remaining_time": "1:19:58", "throughput": 2854.42, "total_tokens": 11246568} {"current_steps": 17210, "total_steps": 38160, "loss": 0.1037, "lr": 3.347094388377431e-05, "epoch": 9.019916142557651, "percentage": 45.1, "elapsed_time": "1:05:41", "remaining_time": "1:19:57", "throughput": 2854.6, "total_tokens": 11251080} {"current_steps": 17215, "total_steps": 38160, "loss": 0.1647, "lr": 3.3460185110387076e-05, "epoch": 9.022536687631026, "percentage": 45.11, "elapsed_time": "1:05:42", "remaining_time": "1:19:56", "throughput": 2854.41, "total_tokens": 11253256} {"current_steps": 17220, "total_steps": 38160, "loss": 0.1309, "lr": 3.344942456722563e-05, "epoch": 9.025157232704403, "percentage": 45.13, "elapsed_time": "1:05:43", "remaining_time": "1:19:55", "throughput": 2854.53, "total_tokens": 11256936} {"current_steps": 17225, "total_steps": 38160, "loss": 0.106, "lr": 3.343866225654096e-05, "epoch": 9.027777777777779, "percentage": 45.14, "elapsed_time": "1:05:44", "remaining_time": "1:19:54", "throughput": 2854.48, "total_tokens": 11259784} {"current_steps": 17230, "total_steps": 38160, "loss": 0.1303, "lr": 3.342789818058443e-05, "epoch": 9.030398322851154, "percentage": 45.15, "elapsed_time": "1:05:45", "remaining_time": "1:19:52", "throughput": 2854.47, "total_tokens": 11262728} {"current_steps": 17235, "total_steps": 38160, "loss": 0.141, "lr": 3.341713234160774e-05, "epoch": 9.033018867924529, "percentage": 45.17, "elapsed_time": "1:05:46", "remaining_time": "1:19:51", "throughput": 2854.41, "total_tokens": 11265640} {"current_steps": 17240, "total_steps": 38160, "loss": 0.1256, "lr": 3.3406364741862986e-05, "epoch": 9.035639412997904, "percentage": 45.18, "elapsed_time": "1:05:48", "remaining_time": "1:19:50", "throughput": 2854.63, "total_tokens": 11270344} {"current_steps": 17245, "total_steps": 38160, "loss": 0.1388, "lr": 3.3395595383602644e-05, "epoch": 9.03825995807128, "percentage": 45.19, "elapsed_time": "1:05:49", "remaining_time": "1:19:49", "throughput": 2854.44, "total_tokens": 11272584} {"current_steps": 17250, "total_steps": 38160, "loss": 0.1144, "lr": 3.338482426907953e-05, "epoch": 9.040880503144654, "percentage": 45.2, "elapsed_time": "1:05:50", "remaining_time": "1:19:48", "throughput": 2854.65, "total_tokens": 11276872} {"current_steps": 17255, "total_steps": 38160, "loss": 0.138, "lr": 3.337405140054683e-05, "epoch": 9.04350104821803, "percentage": 45.22, "elapsed_time": "1:05:51", "remaining_time": "1:19:47", "throughput": 2854.62, "total_tokens": 11279688} {"current_steps": 17260, "total_steps": 38160, "loss": 0.1134, "lr": 3.336327678025813e-05, "epoch": 9.046121593291405, "percentage": 45.23, "elapsed_time": "1:05:52", "remaining_time": "1:19:45", "throughput": 2854.67, "total_tokens": 11282888} {"current_steps": 17265, "total_steps": 38160, "loss": 0.2121, "lr": 3.3352500410467324e-05, "epoch": 9.04874213836478, "percentage": 45.24, "elapsed_time": "1:05:53", "remaining_time": "1:19:44", "throughput": 2854.69, "total_tokens": 11285928} {"current_steps": 17270, "total_steps": 38160, "loss": 0.1313, "lr": 3.3341722293428726e-05, "epoch": 9.051362683438155, "percentage": 45.26, "elapsed_time": "1:05:54", "remaining_time": "1:19:43", "throughput": 2854.73, "total_tokens": 11289288} {"current_steps": 17275, "total_steps": 38160, "loss": 0.1305, "lr": 3.3330942431397e-05, "epoch": 9.05398322851153, "percentage": 45.27, "elapsed_time": "1:05:56", "remaining_time": "1:19:43", "throughput": 2855.09, "total_tokens": 11295976} {"current_steps": 17280, "total_steps": 38160, "loss": 0.134, "lr": 3.332016082662715e-05, "epoch": 9.056603773584905, "percentage": 45.28, "elapsed_time": "1:05:57", "remaining_time": "1:19:42", "throughput": 2855.23, "total_tokens": 11299816} {"current_steps": 17285, "total_steps": 38160, "loss": 0.1401, "lr": 3.3309377481374584e-05, "epoch": 9.05922431865828, "percentage": 45.3, "elapsed_time": "1:05:58", "remaining_time": "1:19:40", "throughput": 2855.32, "total_tokens": 11303176} {"current_steps": 17290, "total_steps": 38160, "loss": 0.0857, "lr": 3.3298592397895046e-05, "epoch": 9.061844863731656, "percentage": 45.31, "elapsed_time": "1:05:59", "remaining_time": "1:19:39", "throughput": 2855.35, "total_tokens": 11306376} {"current_steps": 17295, "total_steps": 38160, "loss": 0.1038, "lr": 3.3287805578444645e-05, "epoch": 9.064465408805031, "percentage": 45.32, "elapsed_time": "1:06:00", "remaining_time": "1:19:38", "throughput": 2855.6, "total_tokens": 11310696} {"current_steps": 17300, "total_steps": 38160, "loss": 0.1175, "lr": 3.327701702527989e-05, "epoch": 9.067085953878406, "percentage": 45.34, "elapsed_time": "1:06:02", "remaining_time": "1:19:37", "throughput": 2855.79, "total_tokens": 11314888} {"current_steps": 17305, "total_steps": 38160, "loss": 0.1268, "lr": 3.3266226740657584e-05, "epoch": 9.069706498951781, "percentage": 45.35, "elapsed_time": "1:06:03", "remaining_time": "1:19:36", "throughput": 2855.72, "total_tokens": 11317576} {"current_steps": 17310, "total_steps": 38160, "loss": 0.1574, "lr": 3.3255434726834954e-05, "epoch": 9.072327044025156, "percentage": 45.36, "elapsed_time": "1:06:04", "remaining_time": "1:19:34", "throughput": 2855.77, "total_tokens": 11320840} {"current_steps": 17315, "total_steps": 38160, "loss": 0.0791, "lr": 3.324464098606957e-05, "epoch": 9.074947589098532, "percentage": 45.37, "elapsed_time": "1:06:05", "remaining_time": "1:19:33", "throughput": 2855.78, "total_tokens": 11324040} {"current_steps": 17320, "total_steps": 38160, "loss": 0.1495, "lr": 3.323384552061934e-05, "epoch": 9.077568134171909, "percentage": 45.39, "elapsed_time": "1:06:06", "remaining_time": "1:19:32", "throughput": 2855.78, "total_tokens": 11327784} {"current_steps": 17325, "total_steps": 38160, "loss": 0.1123, "lr": 3.322304833274257e-05, "epoch": 9.080188679245284, "percentage": 45.4, "elapsed_time": "1:06:07", "remaining_time": "1:19:31", "throughput": 2855.83, "total_tokens": 11331304} {"current_steps": 17330, "total_steps": 38160, "loss": 0.1465, "lr": 3.32122494246979e-05, "epoch": 9.082809224318659, "percentage": 45.41, "elapsed_time": "1:06:08", "remaining_time": "1:19:30", "throughput": 2855.8, "total_tokens": 11334312} {"current_steps": 17335, "total_steps": 38160, "loss": 0.1615, "lr": 3.320144879874434e-05, "epoch": 9.085429769392034, "percentage": 45.43, "elapsed_time": "1:06:10", "remaining_time": "1:19:29", "throughput": 2856.12, "total_tokens": 11339144} {"current_steps": 17340, "total_steps": 38160, "loss": 0.1125, "lr": 3.319064645714126e-05, "epoch": 9.08805031446541, "percentage": 45.44, "elapsed_time": "1:06:11", "remaining_time": "1:19:28", "throughput": 2856.18, "total_tokens": 11342664} {"current_steps": 17345, "total_steps": 38160, "loss": 0.1315, "lr": 3.3179842402148386e-05, "epoch": 9.090670859538784, "percentage": 45.45, "elapsed_time": "1:06:12", "remaining_time": "1:19:27", "throughput": 2856.19, "total_tokens": 11345768} {"current_steps": 17350, "total_steps": 38160, "loss": 0.1887, "lr": 3.316903663602581e-05, "epoch": 9.09329140461216, "percentage": 45.47, "elapsed_time": "1:06:13", "remaining_time": "1:19:25", "throughput": 2856.27, "total_tokens": 11349448} {"current_steps": 17355, "total_steps": 38160, "loss": 0.1109, "lr": 3.315822916103395e-05, "epoch": 9.095911949685535, "percentage": 45.48, "elapsed_time": "1:06:14", "remaining_time": "1:19:24", "throughput": 2856.34, "total_tokens": 11352744} {"current_steps": 17360, "total_steps": 38160, "loss": 0.1153, "lr": 3.3147419979433635e-05, "epoch": 9.09853249475891, "percentage": 45.49, "elapsed_time": "1:06:15", "remaining_time": "1:19:23", "throughput": 2856.08, "total_tokens": 11354920} {"current_steps": 17365, "total_steps": 38160, "loss": 0.1151, "lr": 3.313660909348601e-05, "epoch": 9.101153039832285, "percentage": 45.51, "elapsed_time": "1:06:16", "remaining_time": "1:19:22", "throughput": 2856.25, "total_tokens": 11359240} {"current_steps": 17370, "total_steps": 38160, "loss": 0.1934, "lr": 3.312579650545259e-05, "epoch": 9.10377358490566, "percentage": 45.52, "elapsed_time": "1:06:18", "remaining_time": "1:19:21", "throughput": 2856.16, "total_tokens": 11362056} {"current_steps": 17375, "total_steps": 38160, "loss": 0.0781, "lr": 3.311498221759524e-05, "epoch": 9.106394129979035, "percentage": 45.53, "elapsed_time": "1:06:19", "remaining_time": "1:19:20", "throughput": 2856.03, "total_tokens": 11364648} {"current_steps": 17380, "total_steps": 38160, "loss": 0.091, "lr": 3.310416623217619e-05, "epoch": 9.10901467505241, "percentage": 45.55, "elapsed_time": "1:06:20", "remaining_time": "1:19:19", "throughput": 2856.08, "total_tokens": 11368168} {"current_steps": 17385, "total_steps": 38160, "loss": 0.1208, "lr": 3.309334855145803e-05, "epoch": 9.111635220125786, "percentage": 45.56, "elapsed_time": "1:06:21", "remaining_time": "1:19:17", "throughput": 2855.98, "total_tokens": 11370856} {"current_steps": 17390, "total_steps": 38160, "loss": 0.1291, "lr": 3.3082529177703684e-05, "epoch": 9.114255765199161, "percentage": 45.57, "elapsed_time": "1:06:22", "remaining_time": "1:19:16", "throughput": 2855.93, "total_tokens": 11373768} {"current_steps": 17395, "total_steps": 38160, "loss": 0.1439, "lr": 3.3071708113176435e-05, "epoch": 9.116876310272536, "percentage": 45.58, "elapsed_time": "1:06:23", "remaining_time": "1:19:15", "throughput": 2855.99, "total_tokens": 11377192} {"current_steps": 17400, "total_steps": 38160, "loss": 0.1216, "lr": 3.306088536013995e-05, "epoch": 9.119496855345911, "percentage": 45.6, "elapsed_time": "1:06:24", "remaining_time": "1:19:14", "throughput": 2855.87, "total_tokens": 11379912} {"current_steps": 17405, "total_steps": 38160, "loss": 0.1284, "lr": 3.3050060920858206e-05, "epoch": 9.122117400419286, "percentage": 45.61, "elapsed_time": "1:06:25", "remaining_time": "1:19:13", "throughput": 2855.95, "total_tokens": 11383496} {"current_steps": 17410, "total_steps": 38160, "loss": 0.1314, "lr": 3.3039234797595544e-05, "epoch": 9.124737945492662, "percentage": 45.62, "elapsed_time": "1:06:27", "remaining_time": "1:19:11", "throughput": 2855.9, "total_tokens": 11386504} {"current_steps": 17415, "total_steps": 38160, "loss": 0.0834, "lr": 3.3028406992616695e-05, "epoch": 9.127358490566039, "percentage": 45.64, "elapsed_time": "1:06:28", "remaining_time": "1:19:10", "throughput": 2855.65, "total_tokens": 11388776} {"current_steps": 17420, "total_steps": 38160, "loss": 0.1451, "lr": 3.301757750818669e-05, "epoch": 9.129979035639414, "percentage": 45.65, "elapsed_time": "1:06:29", "remaining_time": "1:19:09", "throughput": 2855.66, "total_tokens": 11391976} {"current_steps": 17425, "total_steps": 38160, "loss": 0.1286, "lr": 3.300674634657094e-05, "epoch": 9.132599580712789, "percentage": 45.66, "elapsed_time": "1:06:30", "remaining_time": "1:19:08", "throughput": 2855.6, "total_tokens": 11394856} {"current_steps": 17430, "total_steps": 38160, "loss": 0.1359, "lr": 3.2995913510035206e-05, "epoch": 9.135220125786164, "percentage": 45.68, "elapsed_time": "1:06:31", "remaining_time": "1:19:07", "throughput": 2855.59, "total_tokens": 11397896} {"current_steps": 17435, "total_steps": 38160, "loss": 0.1286, "lr": 3.298507900084558e-05, "epoch": 9.13784067085954, "percentage": 45.69, "elapsed_time": "1:06:32", "remaining_time": "1:19:05", "throughput": 2855.62, "total_tokens": 11401096} {"current_steps": 17440, "total_steps": 38160, "loss": 0.1333, "lr": 3.2974242821268524e-05, "epoch": 9.140461215932914, "percentage": 45.7, "elapsed_time": "1:06:33", "remaining_time": "1:19:04", "throughput": 2855.75, "total_tokens": 11404616} {"current_steps": 17445, "total_steps": 38160, "loss": 0.1155, "lr": 3.2963404973570855e-05, "epoch": 9.14308176100629, "percentage": 45.72, "elapsed_time": "1:06:34", "remaining_time": "1:19:03", "throughput": 2855.79, "total_tokens": 11407848} {"current_steps": 17450, "total_steps": 38160, "loss": 0.1184, "lr": 3.2952565460019715e-05, "epoch": 9.145702306079665, "percentage": 45.73, "elapsed_time": "1:06:35", "remaining_time": "1:19:02", "throughput": 2855.73, "total_tokens": 11410760} {"current_steps": 17455, "total_steps": 38160, "loss": 0.1498, "lr": 3.29417242828826e-05, "epoch": 9.14832285115304, "percentage": 45.74, "elapsed_time": "1:06:36", "remaining_time": "1:19:01", "throughput": 2855.7, "total_tokens": 11413864} {"current_steps": 17460, "total_steps": 38160, "loss": 0.1315, "lr": 3.2930881444427374e-05, "epoch": 9.150943396226415, "percentage": 45.75, "elapsed_time": "1:06:37", "remaining_time": "1:18:59", "throughput": 2855.65, "total_tokens": 11416808} {"current_steps": 17465, "total_steps": 38160, "loss": 0.215, "lr": 3.292003694692223e-05, "epoch": 9.15356394129979, "percentage": 45.77, "elapsed_time": "1:06:39", "remaining_time": "1:18:58", "throughput": 2855.63, "total_tokens": 11419944} {"current_steps": 17470, "total_steps": 38160, "loss": 0.1225, "lr": 3.290919079263572e-05, "epoch": 9.156184486373165, "percentage": 45.78, "elapsed_time": "1:06:40", "remaining_time": "1:18:57", "throughput": 2855.53, "total_tokens": 11422728} {"current_steps": 17475, "total_steps": 38160, "loss": 0.1688, "lr": 3.2898342983836715e-05, "epoch": 9.15880503144654, "percentage": 45.79, "elapsed_time": "1:06:42", "remaining_time": "1:18:57", "throughput": 2856.13, "total_tokens": 11430984} {"current_steps": 17480, "total_steps": 38160, "loss": 0.129, "lr": 3.288749352279447e-05, "epoch": 9.161425576519916, "percentage": 45.81, "elapsed_time": "1:06:43", "remaining_time": "1:18:56", "throughput": 2856.01, "total_tokens": 11433672} {"current_steps": 17485, "total_steps": 38160, "loss": 0.1494, "lr": 3.2876642411778573e-05, "epoch": 9.164046121593291, "percentage": 45.82, "elapsed_time": "1:06:44", "remaining_time": "1:18:55", "throughput": 2855.87, "total_tokens": 11436168} {"current_steps": 17490, "total_steps": 38160, "loss": 0.1051, "lr": 3.286578965305894e-05, "epoch": 9.166666666666666, "percentage": 45.83, "elapsed_time": "1:06:45", "remaining_time": "1:18:54", "throughput": 2855.81, "total_tokens": 11439528} {"current_steps": 17495, "total_steps": 38160, "loss": 0.1594, "lr": 3.285493524890585e-05, "epoch": 9.169287211740041, "percentage": 45.85, "elapsed_time": "1:06:46", "remaining_time": "1:18:52", "throughput": 2855.75, "total_tokens": 11442312} {"current_steps": 17500, "total_steps": 38160, "loss": 0.1126, "lr": 3.284407920158992e-05, "epoch": 9.171907756813416, "percentage": 45.86, "elapsed_time": "1:06:47", "remaining_time": "1:18:51", "throughput": 2855.73, "total_tokens": 11445416} {"current_steps": 17505, "total_steps": 38160, "loss": 0.1921, "lr": 3.283322151338211e-05, "epoch": 9.174528301886792, "percentage": 45.87, "elapsed_time": "1:06:49", "remaining_time": "1:18:50", "throughput": 2855.74, "total_tokens": 11448712} {"current_steps": 17510, "total_steps": 38160, "loss": 0.123, "lr": 3.282236218655373e-05, "epoch": 9.177148846960169, "percentage": 45.89, "elapsed_time": "1:06:50", "remaining_time": "1:18:49", "throughput": 2855.84, "total_tokens": 11452104} {"current_steps": 17515, "total_steps": 38160, "loss": 0.0902, "lr": 3.281150122337642e-05, "epoch": 9.179769392033544, "percentage": 45.9, "elapsed_time": "1:06:51", "remaining_time": "1:18:48", "throughput": 2856.01, "total_tokens": 11456136} {"current_steps": 17520, "total_steps": 38160, "loss": 0.1398, "lr": 3.280063862612216e-05, "epoch": 9.182389937106919, "percentage": 45.91, "elapsed_time": "1:06:52", "remaining_time": "1:18:46", "throughput": 2856.03, "total_tokens": 11459272} {"current_steps": 17525, "total_steps": 38160, "loss": 0.1297, "lr": 3.2789774397063314e-05, "epoch": 9.185010482180294, "percentage": 45.93, "elapsed_time": "1:06:53", "remaining_time": "1:18:45", "throughput": 2856.2, "total_tokens": 11463208} {"current_steps": 17530, "total_steps": 38160, "loss": 0.1438, "lr": 3.277890853847253e-05, "epoch": 9.18763102725367, "percentage": 45.94, "elapsed_time": "1:06:54", "remaining_time": "1:18:44", "throughput": 2856.26, "total_tokens": 11466472} {"current_steps": 17535, "total_steps": 38160, "loss": 0.1205, "lr": 3.2768041052622824e-05, "epoch": 9.190251572327044, "percentage": 45.95, "elapsed_time": "1:06:55", "remaining_time": "1:18:43", "throughput": 2856.19, "total_tokens": 11469192} {"current_steps": 17540, "total_steps": 38160, "loss": 0.1251, "lr": 3.275717194178755e-05, "epoch": 9.19287211740042, "percentage": 45.96, "elapsed_time": "1:06:56", "remaining_time": "1:18:41", "throughput": 2856.18, "total_tokens": 11472232} {"current_steps": 17545, "total_steps": 38160, "loss": 0.1529, "lr": 3.27463012082404e-05, "epoch": 9.195492662473795, "percentage": 45.98, "elapsed_time": "1:06:57", "remaining_time": "1:18:40", "throughput": 2856.27, "total_tokens": 11476040} {"current_steps": 17550, "total_steps": 38160, "loss": 0.133, "lr": 3.2735428854255416e-05, "epoch": 9.19811320754717, "percentage": 45.99, "elapsed_time": "1:06:58", "remaining_time": "1:18:39", "throughput": 2856.18, "total_tokens": 11478728} {"current_steps": 17555, "total_steps": 38160, "loss": 0.1426, "lr": 3.272455488210697e-05, "epoch": 9.200733752620545, "percentage": 46.0, "elapsed_time": "1:06:59", "remaining_time": "1:18:38", "throughput": 2856.11, "total_tokens": 11481448} {"current_steps": 17560, "total_steps": 38160, "loss": 0.1059, "lr": 3.271367929406977e-05, "epoch": 9.20335429769392, "percentage": 46.02, "elapsed_time": "1:07:01", "remaining_time": "1:18:37", "throughput": 2856.11, "total_tokens": 11484424} {"current_steps": 17565, "total_steps": 38160, "loss": 0.1277, "lr": 3.270280209241886e-05, "epoch": 9.205974842767295, "percentage": 46.03, "elapsed_time": "1:07:02", "remaining_time": "1:18:35", "throughput": 2856.12, "total_tokens": 11487560} {"current_steps": 17570, "total_steps": 38160, "loss": 0.1161, "lr": 3.2691923279429624e-05, "epoch": 9.20859538784067, "percentage": 46.04, "elapsed_time": "1:07:03", "remaining_time": "1:18:34", "throughput": 2856.13, "total_tokens": 11490632} {"current_steps": 17575, "total_steps": 38160, "loss": 0.144, "lr": 3.2681042857377804e-05, "epoch": 9.211215932914046, "percentage": 46.06, "elapsed_time": "1:07:04", "remaining_time": "1:18:33", "throughput": 2855.98, "total_tokens": 11493032} {"current_steps": 17580, "total_steps": 38160, "loss": 0.087, "lr": 3.2670160828539435e-05, "epoch": 9.213836477987421, "percentage": 46.07, "elapsed_time": "1:07:05", "remaining_time": "1:18:32", "throughput": 2856.0, "total_tokens": 11496200} {"current_steps": 17585, "total_steps": 38160, "loss": 0.1497, "lr": 3.2659277195190934e-05, "epoch": 9.216457023060796, "percentage": 46.08, "elapsed_time": "1:07:06", "remaining_time": "1:18:30", "throughput": 2855.87, "total_tokens": 11498696} {"current_steps": 17590, "total_steps": 38160, "loss": 0.0878, "lr": 3.2648391959609026e-05, "epoch": 9.219077568134171, "percentage": 46.1, "elapsed_time": "1:07:07", "remaining_time": "1:18:29", "throughput": 2856.0, "total_tokens": 11502312} {"current_steps": 17595, "total_steps": 38160, "loss": 0.1136, "lr": 3.263750512407078e-05, "epoch": 9.221698113207546, "percentage": 46.11, "elapsed_time": "1:07:08", "remaining_time": "1:18:28", "throughput": 2855.96, "total_tokens": 11505160} {"current_steps": 17600, "total_steps": 38160, "loss": 0.0879, "lr": 3.262661669085359e-05, "epoch": 9.224318658280922, "percentage": 46.12, "elapsed_time": "1:07:09", "remaining_time": "1:18:27", "throughput": 2856.03, "total_tokens": 11508456} {"current_steps": 17605, "total_steps": 38160, "loss": 0.1511, "lr": 3.2615726662235205e-05, "epoch": 9.226939203354299, "percentage": 46.13, "elapsed_time": "1:07:10", "remaining_time": "1:18:25", "throughput": 2856.1, "total_tokens": 11511816} {"current_steps": 17610, "total_steps": 38160, "loss": 0.1269, "lr": 3.2604835040493676e-05, "epoch": 9.229559748427674, "percentage": 46.15, "elapsed_time": "1:07:11", "remaining_time": "1:18:24", "throughput": 2855.93, "total_tokens": 11514088} {"current_steps": 17615, "total_steps": 38160, "loss": 0.1135, "lr": 3.259394182790742e-05, "epoch": 9.232180293501049, "percentage": 46.16, "elapsed_time": "1:07:12", "remaining_time": "1:18:23", "throughput": 2855.89, "total_tokens": 11517096} {"current_steps": 17620, "total_steps": 38160, "loss": 0.1156, "lr": 3.2583047026755174e-05, "epoch": 9.234800838574424, "percentage": 46.17, "elapsed_time": "1:07:13", "remaining_time": "1:18:22", "throughput": 2855.89, "total_tokens": 11520168} {"current_steps": 17625, "total_steps": 38160, "loss": 0.2102, "lr": 3.2572150639316e-05, "epoch": 9.2374213836478, "percentage": 46.19, "elapsed_time": "1:07:14", "remaining_time": "1:18:21", "throughput": 2856.01, "total_tokens": 11523944} {"current_steps": 17630, "total_steps": 38160, "loss": 0.1774, "lr": 3.256125266786931e-05, "epoch": 9.240041928721174, "percentage": 46.2, "elapsed_time": "1:07:16", "remaining_time": "1:18:20", "throughput": 2856.12, "total_tokens": 11527720} {"current_steps": 17635, "total_steps": 38160, "loss": 0.2222, "lr": 3.255035311469481e-05, "epoch": 9.24266247379455, "percentage": 46.21, "elapsed_time": "1:07:17", "remaining_time": "1:18:18", "throughput": 2856.27, "total_tokens": 11531304} {"current_steps": 17640, "total_steps": 38160, "loss": 0.131, "lr": 3.2539451982072586e-05, "epoch": 9.245283018867925, "percentage": 46.23, "elapsed_time": "1:07:18", "remaining_time": "1:18:17", "throughput": 2856.47, "total_tokens": 11535176} {"current_steps": 17645, "total_steps": 38160, "loss": 0.2077, "lr": 3.2528549272283016e-05, "epoch": 9.2479035639413, "percentage": 46.24, "elapsed_time": "1:07:19", "remaining_time": "1:18:16", "throughput": 2856.58, "total_tokens": 11539016} {"current_steps": 17650, "total_steps": 38160, "loss": 0.0902, "lr": 3.251764498760683e-05, "epoch": 9.250524109014675, "percentage": 46.25, "elapsed_time": "1:07:20", "remaining_time": "1:18:15", "throughput": 2856.82, "total_tokens": 11543752} {"current_steps": 17655, "total_steps": 38160, "loss": 0.1315, "lr": 3.2506739130325084e-05, "epoch": 9.25314465408805, "percentage": 46.27, "elapsed_time": "1:07:21", "remaining_time": "1:18:14", "throughput": 2856.75, "total_tokens": 11546664} {"current_steps": 17660, "total_steps": 38160, "loss": 0.1277, "lr": 3.2495831702719146e-05, "epoch": 9.255765199161425, "percentage": 46.28, "elapsed_time": "1:07:22", "remaining_time": "1:18:13", "throughput": 2856.58, "total_tokens": 11549032} {"current_steps": 17665, "total_steps": 38160, "loss": 0.1996, "lr": 3.248492270707074e-05, "epoch": 9.2583857442348, "percentage": 46.29, "elapsed_time": "1:07:24", "remaining_time": "1:18:11", "throughput": 2856.6, "total_tokens": 11552328} {"current_steps": 17670, "total_steps": 38160, "loss": 0.228, "lr": 3.247401214566189e-05, "epoch": 9.261006289308176, "percentage": 46.31, "elapsed_time": "1:07:25", "remaining_time": "1:18:10", "throughput": 2856.62, "total_tokens": 11555464} {"current_steps": 17675, "total_steps": 38160, "loss": 0.1407, "lr": 3.2463100020774965e-05, "epoch": 9.26362683438155, "percentage": 46.32, "elapsed_time": "1:07:26", "remaining_time": "1:18:09", "throughput": 2856.51, "total_tokens": 11558088} {"current_steps": 17680, "total_steps": 38160, "loss": 0.1612, "lr": 3.245218633469267e-05, "epoch": 9.266247379454926, "percentage": 46.33, "elapsed_time": "1:07:27", "remaining_time": "1:18:08", "throughput": 2856.42, "total_tokens": 11560872} {"current_steps": 17685, "total_steps": 38160, "loss": 0.1098, "lr": 3.244127108969801e-05, "epoch": 9.268867924528301, "percentage": 46.34, "elapsed_time": "1:07:28", "remaining_time": "1:18:07", "throughput": 2856.51, "total_tokens": 11564264} {"current_steps": 17690, "total_steps": 38160, "loss": 0.1224, "lr": 3.2430354288074314e-05, "epoch": 9.271488469601676, "percentage": 46.36, "elapsed_time": "1:07:29", "remaining_time": "1:18:05", "throughput": 2856.58, "total_tokens": 11567656} {"current_steps": 17695, "total_steps": 38160, "loss": 0.1228, "lr": 3.241943593210529e-05, "epoch": 9.274109014675052, "percentage": 46.37, "elapsed_time": "1:07:30", "remaining_time": "1:18:04", "throughput": 2856.68, "total_tokens": 11571176} {"current_steps": 17700, "total_steps": 38160, "loss": 0.1603, "lr": 3.2408516024074916e-05, "epoch": 9.276729559748428, "percentage": 46.38, "elapsed_time": "1:07:31", "remaining_time": "1:18:03", "throughput": 2856.63, "total_tokens": 11574216} {"current_steps": 17705, "total_steps": 38160, "loss": 0.1012, "lr": 3.2397594566267505e-05, "epoch": 9.279350104821804, "percentage": 46.4, "elapsed_time": "1:07:32", "remaining_time": "1:18:02", "throughput": 2856.71, "total_tokens": 11577608} {"current_steps": 17710, "total_steps": 38160, "loss": 0.1428, "lr": 3.23866715609677e-05, "epoch": 9.281970649895179, "percentage": 46.41, "elapsed_time": "1:07:33", "remaining_time": "1:18:01", "throughput": 2856.77, "total_tokens": 11581000} {"current_steps": 17715, "total_steps": 38160, "loss": 0.152, "lr": 3.237574701046049e-05, "epoch": 9.284591194968554, "percentage": 46.42, "elapsed_time": "1:07:35", "remaining_time": "1:18:00", "throughput": 2856.83, "total_tokens": 11584840} {"current_steps": 17720, "total_steps": 38160, "loss": 0.1597, "lr": 3.236482091703115e-05, "epoch": 9.28721174004193, "percentage": 46.44, "elapsed_time": "1:07:36", "remaining_time": "1:17:58", "throughput": 2856.8, "total_tokens": 11587912} {"current_steps": 17725, "total_steps": 38160, "loss": 0.1436, "lr": 3.235389328296528e-05, "epoch": 9.289832285115304, "percentage": 46.45, "elapsed_time": "1:07:37", "remaining_time": "1:17:57", "throughput": 2856.92, "total_tokens": 11591752} {"current_steps": 17730, "total_steps": 38160, "loss": 0.1821, "lr": 3.2342964110548845e-05, "epoch": 9.29245283018868, "percentage": 46.46, "elapsed_time": "1:07:38", "remaining_time": "1:17:56", "throughput": 2856.76, "total_tokens": 11594248} {"current_steps": 17735, "total_steps": 38160, "loss": 0.1308, "lr": 3.2332033402068093e-05, "epoch": 9.295073375262055, "percentage": 46.48, "elapsed_time": "1:07:39", "remaining_time": "1:17:55", "throughput": 2856.81, "total_tokens": 11597448} {"current_steps": 17740, "total_steps": 38160, "loss": 0.2033, "lr": 3.2321101159809605e-05, "epoch": 9.29769392033543, "percentage": 46.49, "elapsed_time": "1:07:40", "remaining_time": "1:17:54", "throughput": 2856.79, "total_tokens": 11600360} {"current_steps": 17745, "total_steps": 38160, "loss": 0.1808, "lr": 3.231016738606027e-05, "epoch": 9.300314465408805, "percentage": 46.5, "elapsed_time": "1:07:41", "remaining_time": "1:17:52", "throughput": 2856.82, "total_tokens": 11603528} {"current_steps": 17750, "total_steps": 38160, "loss": 0.1657, "lr": 3.2299232083107313e-05, "epoch": 9.30293501048218, "percentage": 46.51, "elapsed_time": "1:07:42", "remaining_time": "1:17:51", "throughput": 2856.78, "total_tokens": 11606600} {"current_steps": 17755, "total_steps": 38160, "loss": 0.1195, "lr": 3.228829525323829e-05, "epoch": 9.305555555555555, "percentage": 46.53, "elapsed_time": "1:07:43", "remaining_time": "1:17:50", "throughput": 2856.57, "total_tokens": 11609064} {"current_steps": 17760, "total_steps": 38160, "loss": 0.126, "lr": 3.227735689874104e-05, "epoch": 9.30817610062893, "percentage": 46.54, "elapsed_time": "1:07:45", "remaining_time": "1:17:49", "throughput": 2856.58, "total_tokens": 11612328} {"current_steps": 17765, "total_steps": 38160, "loss": 0.1857, "lr": 3.226641702190375e-05, "epoch": 9.310796645702306, "percentage": 46.55, "elapsed_time": "1:07:46", "remaining_time": "1:17:48", "throughput": 2856.67, "total_tokens": 11615912} {"current_steps": 17770, "total_steps": 38160, "loss": 0.1793, "lr": 3.225547562501493e-05, "epoch": 9.31341719077568, "percentage": 46.57, "elapsed_time": "1:07:47", "remaining_time": "1:17:47", "throughput": 2856.63, "total_tokens": 11618888} {"current_steps": 17775, "total_steps": 38160, "loss": 0.2876, "lr": 3.2244532710363375e-05, "epoch": 9.316037735849056, "percentage": 46.58, "elapsed_time": "1:07:48", "remaining_time": "1:17:45", "throughput": 2856.55, "total_tokens": 11621544} {"current_steps": 17780, "total_steps": 38160, "loss": 0.1222, "lr": 3.2233588280238224e-05, "epoch": 9.318658280922431, "percentage": 46.59, "elapsed_time": "1:07:49", "remaining_time": "1:17:44", "throughput": 2856.42, "total_tokens": 11624040} {"current_steps": 17785, "total_steps": 38160, "loss": 0.1346, "lr": 3.2222642336928944e-05, "epoch": 9.321278825995806, "percentage": 46.61, "elapsed_time": "1:07:50", "remaining_time": "1:17:43", "throughput": 2856.28, "total_tokens": 11626728} {"current_steps": 17790, "total_steps": 38160, "loss": 0.0682, "lr": 3.2211694882725275e-05, "epoch": 9.323899371069182, "percentage": 46.62, "elapsed_time": "1:07:51", "remaining_time": "1:17:42", "throughput": 2856.3, "total_tokens": 11629832} {"current_steps": 17795, "total_steps": 38160, "loss": 0.0953, "lr": 3.220074591991731e-05, "epoch": 9.326519916142558, "percentage": 46.63, "elapsed_time": "1:07:52", "remaining_time": "1:17:40", "throughput": 2856.37, "total_tokens": 11633320} {"current_steps": 17800, "total_steps": 38160, "loss": 0.1293, "lr": 3.218979545079546e-05, "epoch": 9.329140461215934, "percentage": 46.65, "elapsed_time": "1:07:53", "remaining_time": "1:17:39", "throughput": 2856.31, "total_tokens": 11636104} {"current_steps": 17805, "total_steps": 38160, "loss": 0.1713, "lr": 3.217884347765042e-05, "epoch": 9.331761006289309, "percentage": 46.66, "elapsed_time": "1:07:54", "remaining_time": "1:17:38", "throughput": 2856.43, "total_tokens": 11639752} {"current_steps": 17810, "total_steps": 38160, "loss": 0.1563, "lr": 3.216789000277323e-05, "epoch": 9.334381551362684, "percentage": 46.67, "elapsed_time": "1:07:56", "remaining_time": "1:17:37", "throughput": 2856.39, "total_tokens": 11642664} {"current_steps": 17815, "total_steps": 38160, "loss": 0.1475, "lr": 3.2156935028455224e-05, "epoch": 9.33700209643606, "percentage": 46.69, "elapsed_time": "1:07:57", "remaining_time": "1:17:36", "throughput": 2856.45, "total_tokens": 11646024} {"current_steps": 17820, "total_steps": 38160, "loss": 0.1262, "lr": 3.2145978556988056e-05, "epoch": 9.339622641509434, "percentage": 46.7, "elapsed_time": "1:07:58", "remaining_time": "1:17:34", "throughput": 2856.5, "total_tokens": 11649192} {"current_steps": 17825, "total_steps": 38160, "loss": 0.1875, "lr": 3.213502059066371e-05, "epoch": 9.34224318658281, "percentage": 46.71, "elapsed_time": "1:07:59", "remaining_time": "1:17:33", "throughput": 2856.68, "total_tokens": 11653192} {"current_steps": 17830, "total_steps": 38160, "loss": 0.1266, "lr": 3.212406113177445e-05, "epoch": 9.344863731656185, "percentage": 46.72, "elapsed_time": "1:08:00", "remaining_time": "1:17:32", "throughput": 2856.84, "total_tokens": 11657224} {"current_steps": 17835, "total_steps": 38160, "loss": 0.2119, "lr": 3.211310018261287e-05, "epoch": 9.34748427672956, "percentage": 46.74, "elapsed_time": "1:08:01", "remaining_time": "1:17:31", "throughput": 2856.87, "total_tokens": 11660328} {"current_steps": 17840, "total_steps": 38160, "loss": 0.1513, "lr": 3.21021377454719e-05, "epoch": 9.350104821802935, "percentage": 46.75, "elapsed_time": "1:08:02", "remaining_time": "1:17:30", "throughput": 2856.89, "total_tokens": 11663400} {"current_steps": 17845, "total_steps": 38160, "loss": 0.1675, "lr": 3.209117382264473e-05, "epoch": 9.35272536687631, "percentage": 46.76, "elapsed_time": "1:08:03", "remaining_time": "1:17:28", "throughput": 2856.79, "total_tokens": 11665992} {"current_steps": 17850, "total_steps": 38160, "loss": 0.114, "lr": 3.208020841642489e-05, "epoch": 9.355345911949685, "percentage": 46.78, "elapsed_time": "1:08:04", "remaining_time": "1:17:27", "throughput": 2856.72, "total_tokens": 11669000} {"current_steps": 17855, "total_steps": 38160, "loss": 0.1178, "lr": 3.206924152910623e-05, "epoch": 9.35796645702306, "percentage": 46.79, "elapsed_time": "1:08:05", "remaining_time": "1:17:26", "throughput": 2856.66, "total_tokens": 11671976} {"current_steps": 17860, "total_steps": 38160, "loss": 0.1357, "lr": 3.205827316298289e-05, "epoch": 9.360587002096436, "percentage": 46.8, "elapsed_time": "1:08:07", "remaining_time": "1:17:25", "throughput": 2856.6, "total_tokens": 11674984} {"current_steps": 17865, "total_steps": 38160, "loss": 0.1368, "lr": 3.204730332034934e-05, "epoch": 9.36320754716981, "percentage": 46.82, "elapsed_time": "1:08:08", "remaining_time": "1:17:24", "throughput": 2856.53, "total_tokens": 11677864} {"current_steps": 17870, "total_steps": 38160, "loss": 0.1423, "lr": 3.2036332003500324e-05, "epoch": 9.365828092243186, "percentage": 46.83, "elapsed_time": "1:08:09", "remaining_time": "1:17:23", "throughput": 2856.55, "total_tokens": 11681128} {"current_steps": 17875, "total_steps": 38160, "loss": 0.1164, "lr": 3.2025359214730924e-05, "epoch": 9.368448637316561, "percentage": 46.84, "elapsed_time": "1:08:10", "remaining_time": "1:17:21", "throughput": 2856.48, "total_tokens": 11683880} {"current_steps": 17880, "total_steps": 38160, "loss": 0.11, "lr": 3.201438495633654e-05, "epoch": 9.371069182389936, "percentage": 46.86, "elapsed_time": "1:08:11", "remaining_time": "1:17:20", "throughput": 2856.6, "total_tokens": 11687496} {"current_steps": 17885, "total_steps": 38160, "loss": 0.1738, "lr": 3.200340923061284e-05, "epoch": 9.373689727463312, "percentage": 46.87, "elapsed_time": "1:08:12", "remaining_time": "1:17:19", "throughput": 2856.62, "total_tokens": 11690696} {"current_steps": 17890, "total_steps": 38160, "loss": 0.1655, "lr": 3.199243203985583e-05, "epoch": 9.376310272536688, "percentage": 46.88, "elapsed_time": "1:08:13", "remaining_time": "1:17:18", "throughput": 2856.58, "total_tokens": 11693544} {"current_steps": 17895, "total_steps": 38160, "loss": 0.1536, "lr": 3.1981453386361804e-05, "epoch": 9.378930817610064, "percentage": 46.89, "elapsed_time": "1:08:14", "remaining_time": "1:17:16", "throughput": 2856.64, "total_tokens": 11696840} {"current_steps": 17900, "total_steps": 38160, "loss": 0.1535, "lr": 3.1970473272427386e-05, "epoch": 9.381551362683439, "percentage": 46.91, "elapsed_time": "1:08:15", "remaining_time": "1:17:15", "throughput": 2856.68, "total_tokens": 11700264} {"current_steps": 17905, "total_steps": 38160, "loss": 0.0862, "lr": 3.195949170034948e-05, "epoch": 9.384171907756814, "percentage": 46.92, "elapsed_time": "1:08:16", "remaining_time": "1:17:14", "throughput": 2856.73, "total_tokens": 11703496} {"current_steps": 17910, "total_steps": 38160, "loss": 0.1541, "lr": 3.19485086724253e-05, "epoch": 9.38679245283019, "percentage": 46.93, "elapsed_time": "1:08:17", "remaining_time": "1:17:13", "throughput": 2856.74, "total_tokens": 11706664} {"current_steps": 17915, "total_steps": 38160, "loss": 0.1396, "lr": 3.193752419095239e-05, "epoch": 9.389412997903564, "percentage": 46.95, "elapsed_time": "1:08:19", "remaining_time": "1:17:12", "throughput": 2856.63, "total_tokens": 11709480} {"current_steps": 17920, "total_steps": 38160, "loss": 0.1068, "lr": 3.192653825822857e-05, "epoch": 9.39203354297694, "percentage": 46.96, "elapsed_time": "1:08:20", "remaining_time": "1:17:10", "throughput": 2856.68, "total_tokens": 11712712} {"current_steps": 17925, "total_steps": 38160, "loss": 0.1417, "lr": 3.1915550876551964e-05, "epoch": 9.394654088050315, "percentage": 46.97, "elapsed_time": "1:08:21", "remaining_time": "1:17:09", "throughput": 2856.6, "total_tokens": 11715464} {"current_steps": 17930, "total_steps": 38160, "loss": 0.1186, "lr": 3.190456204822101e-05, "epoch": 9.39727463312369, "percentage": 46.99, "elapsed_time": "1:08:22", "remaining_time": "1:17:08", "throughput": 2856.49, "total_tokens": 11718120} {"current_steps": 17935, "total_steps": 38160, "loss": 0.1492, "lr": 3.1893571775534445e-05, "epoch": 9.399895178197065, "percentage": 47.0, "elapsed_time": "1:08:23", "remaining_time": "1:17:07", "throughput": 2856.54, "total_tokens": 11721512} {"current_steps": 17940, "total_steps": 38160, "loss": 0.0997, "lr": 3.1882580060791315e-05, "epoch": 9.40251572327044, "percentage": 47.01, "elapsed_time": "1:08:24", "remaining_time": "1:17:06", "throughput": 2856.42, "total_tokens": 11724008} {"current_steps": 17945, "total_steps": 38160, "loss": 0.1258, "lr": 3.187158690629095e-05, "epoch": 9.405136268343815, "percentage": 47.03, "elapsed_time": "1:08:25", "remaining_time": "1:17:04", "throughput": 2856.36, "total_tokens": 11726696} {"current_steps": 17950, "total_steps": 38160, "loss": 0.1119, "lr": 3.1860592314333e-05, "epoch": 9.40775681341719, "percentage": 47.04, "elapsed_time": "1:08:26", "remaining_time": "1:17:03", "throughput": 2856.49, "total_tokens": 11730408} {"current_steps": 17955, "total_steps": 38160, "loss": 0.1512, "lr": 3.184959628721742e-05, "epoch": 9.410377358490566, "percentage": 47.05, "elapsed_time": "1:08:27", "remaining_time": "1:17:02", "throughput": 2856.45, "total_tokens": 11733320} {"current_steps": 17960, "total_steps": 38160, "loss": 0.1583, "lr": 3.183859882724443e-05, "epoch": 9.41299790356394, "percentage": 47.06, "elapsed_time": "1:08:28", "remaining_time": "1:17:01", "throughput": 2856.8, "total_tokens": 11738472} {"current_steps": 17965, "total_steps": 38160, "loss": 0.1483, "lr": 3.1827599936714584e-05, "epoch": 9.415618448637316, "percentage": 47.08, "elapsed_time": "1:08:30", "remaining_time": "1:17:00", "throughput": 2856.68, "total_tokens": 11741032} {"current_steps": 17970, "total_steps": 38160, "loss": 0.1048, "lr": 3.1816599617928736e-05, "epoch": 9.418238993710691, "percentage": 47.09, "elapsed_time": "1:08:31", "remaining_time": "1:16:58", "throughput": 2856.73, "total_tokens": 11744328} {"current_steps": 17975, "total_steps": 38160, "loss": 0.0923, "lr": 3.1805597873188e-05, "epoch": 9.420859538784066, "percentage": 47.1, "elapsed_time": "1:08:32", "remaining_time": "1:16:57", "throughput": 2856.84, "total_tokens": 11747976} {"current_steps": 17980, "total_steps": 38160, "loss": 0.2139, "lr": 3.179459470479384e-05, "epoch": 9.423480083857442, "percentage": 47.12, "elapsed_time": "1:08:33", "remaining_time": "1:16:56", "throughput": 2856.82, "total_tokens": 11751144} {"current_steps": 17985, "total_steps": 38160, "loss": 0.1482, "lr": 3.1783590115047983e-05, "epoch": 9.426100628930818, "percentage": 47.13, "elapsed_time": "1:08:34", "remaining_time": "1:16:55", "throughput": 2856.85, "total_tokens": 11754312} {"current_steps": 17990, "total_steps": 38160, "loss": 0.1139, "lr": 3.177258410625246e-05, "epoch": 9.428721174004194, "percentage": 47.14, "elapsed_time": "1:08:35", "remaining_time": "1:16:54", "throughput": 2856.95, "total_tokens": 11757896} {"current_steps": 17995, "total_steps": 38160, "loss": 0.1067, "lr": 3.176157668070962e-05, "epoch": 9.431341719077569, "percentage": 47.16, "elapsed_time": "1:08:36", "remaining_time": "1:16:53", "throughput": 2856.89, "total_tokens": 11760840} {"current_steps": 18000, "total_steps": 38160, "loss": 0.0961, "lr": 3.175056784072207e-05, "epoch": 9.433962264150944, "percentage": 47.17, "elapsed_time": "1:08:37", "remaining_time": "1:16:51", "throughput": 2856.92, "total_tokens": 11764136} {"current_steps": 18005, "total_steps": 38160, "loss": 0.1614, "lr": 3.173955758859274e-05, "epoch": 9.43658280922432, "percentage": 47.18, "elapsed_time": "1:08:38", "remaining_time": "1:16:50", "throughput": 2856.8, "total_tokens": 11766696} {"current_steps": 18010, "total_steps": 38160, "loss": 0.1517, "lr": 3.172854592662486e-05, "epoch": 9.439203354297694, "percentage": 47.2, "elapsed_time": "1:08:39", "remaining_time": "1:16:49", "throughput": 2856.63, "total_tokens": 11769160} {"current_steps": 18015, "total_steps": 38160, "loss": 0.1614, "lr": 3.1717532857121926e-05, "epoch": 9.44182389937107, "percentage": 47.21, "elapsed_time": "1:08:41", "remaining_time": "1:16:48", "throughput": 2856.6, "total_tokens": 11772360} {"current_steps": 18020, "total_steps": 38160, "loss": 0.166, "lr": 3.170651838238776e-05, "epoch": 9.444444444444445, "percentage": 47.22, "elapsed_time": "1:08:42", "remaining_time": "1:16:47", "throughput": 2856.5, "total_tokens": 11774984} {"current_steps": 18025, "total_steps": 38160, "loss": 0.1204, "lr": 3.169550250472646e-05, "epoch": 9.44706498951782, "percentage": 47.24, "elapsed_time": "1:08:43", "remaining_time": "1:16:45", "throughput": 2856.43, "total_tokens": 11777928} {"current_steps": 18030, "total_steps": 38160, "loss": 0.1006, "lr": 3.168448522644243e-05, "epoch": 9.449685534591195, "percentage": 47.25, "elapsed_time": "1:08:44", "remaining_time": "1:16:44", "throughput": 2856.42, "total_tokens": 11781096} {"current_steps": 18035, "total_steps": 38160, "loss": 0.1166, "lr": 3.167346654984034e-05, "epoch": 9.45230607966457, "percentage": 47.26, "elapsed_time": "1:08:45", "remaining_time": "1:16:43", "throughput": 2856.34, "total_tokens": 11784104} {"current_steps": 18040, "total_steps": 38160, "loss": 0.1339, "lr": 3.166244647722519e-05, "epoch": 9.454926624737945, "percentage": 47.27, "elapsed_time": "1:08:46", "remaining_time": "1:16:42", "throughput": 2856.37, "total_tokens": 11787304} {"current_steps": 18045, "total_steps": 38160, "loss": 0.0923, "lr": 3.1651425010902244e-05, "epoch": 9.45754716981132, "percentage": 47.29, "elapsed_time": "1:08:47", "remaining_time": "1:16:41", "throughput": 2856.32, "total_tokens": 11790024} {"current_steps": 18050, "total_steps": 38160, "loss": 0.0963, "lr": 3.164040215317706e-05, "epoch": 9.460167714884696, "percentage": 47.3, "elapsed_time": "1:08:48", "remaining_time": "1:16:39", "throughput": 2856.26, "total_tokens": 11792840} {"current_steps": 18055, "total_steps": 38160, "loss": 0.0844, "lr": 3.162937790635552e-05, "epoch": 9.46278825995807, "percentage": 47.31, "elapsed_time": "1:08:49", "remaining_time": "1:16:38", "throughput": 2856.18, "total_tokens": 11795720} {"current_steps": 18060, "total_steps": 38160, "loss": 0.1026, "lr": 3.1618352272743746e-05, "epoch": 9.465408805031446, "percentage": 47.33, "elapsed_time": "1:08:50", "remaining_time": "1:16:37", "throughput": 2856.11, "total_tokens": 11798472} {"current_steps": 18065, "total_steps": 38160, "loss": 0.0876, "lr": 3.160732525464818e-05, "epoch": 9.468029350104821, "percentage": 47.34, "elapsed_time": "1:08:52", "remaining_time": "1:16:36", "throughput": 2856.15, "total_tokens": 11801800} {"current_steps": 18070, "total_steps": 38160, "loss": 0.1305, "lr": 3.1596296854375554e-05, "epoch": 9.470649895178196, "percentage": 47.35, "elapsed_time": "1:08:53", "remaining_time": "1:16:35", "throughput": 2856.21, "total_tokens": 11805160} {"current_steps": 18075, "total_steps": 38160, "loss": 0.157, "lr": 3.1585267074232884e-05, "epoch": 9.473270440251572, "percentage": 47.37, "elapsed_time": "1:08:55", "remaining_time": "1:16:35", "throughput": 2856.42, "total_tokens": 11811816} {"current_steps": 18080, "total_steps": 38160, "loss": 0.1828, "lr": 3.157423591652746e-05, "epoch": 9.475890985324948, "percentage": 47.38, "elapsed_time": "1:08:56", "remaining_time": "1:16:33", "throughput": 2856.59, "total_tokens": 11816040} {"current_steps": 18085, "total_steps": 38160, "loss": 0.1844, "lr": 3.1563203383566894e-05, "epoch": 9.478511530398324, "percentage": 47.39, "elapsed_time": "1:08:57", "remaining_time": "1:16:32", "throughput": 2856.54, "total_tokens": 11818920} {"current_steps": 18090, "total_steps": 38160, "loss": 0.1604, "lr": 3.155216947765906e-05, "epoch": 9.481132075471699, "percentage": 47.41, "elapsed_time": "1:08:58", "remaining_time": "1:16:31", "throughput": 2856.5, "total_tokens": 11821736} {"current_steps": 18095, "total_steps": 38160, "loss": 0.1485, "lr": 3.154113420111211e-05, "epoch": 9.483752620545074, "percentage": 47.42, "elapsed_time": "1:08:59", "remaining_time": "1:16:30", "throughput": 2856.57, "total_tokens": 11825256} {"current_steps": 18100, "total_steps": 38160, "loss": 0.1719, "lr": 3.1530097556234526e-05, "epoch": 9.48637316561845, "percentage": 47.43, "elapsed_time": "1:09:00", "remaining_time": "1:16:29", "throughput": 2856.76, "total_tokens": 11829416} {"current_steps": 18105, "total_steps": 38160, "loss": 0.2023, "lr": 3.151905954533502e-05, "epoch": 9.488993710691824, "percentage": 47.44, "elapsed_time": "1:09:01", "remaining_time": "1:16:28", "throughput": 2856.69, "total_tokens": 11832200} {"current_steps": 18110, "total_steps": 38160, "loss": 0.1455, "lr": 3.150802017072263e-05, "epoch": 9.4916142557652, "percentage": 47.46, "elapsed_time": "1:09:03", "remaining_time": "1:16:26", "throughput": 2856.71, "total_tokens": 11835592} {"current_steps": 18115, "total_steps": 38160, "loss": 0.1407, "lr": 3.149697943470668e-05, "epoch": 9.494234800838575, "percentage": 47.47, "elapsed_time": "1:09:04", "remaining_time": "1:16:25", "throughput": 2856.77, "total_tokens": 11839400} {"current_steps": 18120, "total_steps": 38160, "loss": 0.1714, "lr": 3.1485937339596736e-05, "epoch": 9.49685534591195, "percentage": 47.48, "elapsed_time": "1:09:05", "remaining_time": "1:16:24", "throughput": 2856.71, "total_tokens": 11842216} {"current_steps": 18125, "total_steps": 38160, "loss": 0.0891, "lr": 3.147489388770271e-05, "epoch": 9.499475890985325, "percentage": 47.5, "elapsed_time": "1:09:06", "remaining_time": "1:16:23", "throughput": 2856.61, "total_tokens": 11844936} {"current_steps": 18130, "total_steps": 38160, "loss": 0.1586, "lr": 3.146384908133475e-05, "epoch": 9.5020964360587, "percentage": 47.51, "elapsed_time": "1:09:07", "remaining_time": "1:16:22", "throughput": 2856.61, "total_tokens": 11847912} {"current_steps": 18135, "total_steps": 38160, "loss": 0.0933, "lr": 3.14528029228033e-05, "epoch": 9.504716981132075, "percentage": 47.52, "elapsed_time": "1:09:09", "remaining_time": "1:16:21", "throughput": 2856.84, "total_tokens": 11853192} {"current_steps": 18140, "total_steps": 38160, "loss": 0.1408, "lr": 3.144175541441911e-05, "epoch": 9.50733752620545, "percentage": 47.54, "elapsed_time": "1:09:10", "remaining_time": "1:16:20", "throughput": 2856.96, "total_tokens": 11856808} {"current_steps": 18145, "total_steps": 38160, "loss": 0.3099, "lr": 3.1430706558493166e-05, "epoch": 9.509958071278826, "percentage": 47.55, "elapsed_time": "1:09:11", "remaining_time": "1:16:19", "throughput": 2857.08, "total_tokens": 11860360} {"current_steps": 18150, "total_steps": 38160, "loss": 0.0871, "lr": 3.141965635733677e-05, "epoch": 9.5125786163522, "percentage": 47.56, "elapsed_time": "1:09:12", "remaining_time": "1:16:17", "throughput": 2857.0, "total_tokens": 11863048} {"current_steps": 18155, "total_steps": 38160, "loss": 0.1372, "lr": 3.140860481326152e-05, "epoch": 9.515199161425576, "percentage": 47.58, "elapsed_time": "1:09:13", "remaining_time": "1:16:16", "throughput": 2857.21, "total_tokens": 11867016} {"current_steps": 18160, "total_steps": 38160, "loss": 0.0898, "lr": 3.139755192857925e-05, "epoch": 9.517819706498951, "percentage": 47.59, "elapsed_time": "1:09:14", "remaining_time": "1:16:15", "throughput": 2857.35, "total_tokens": 11870728} {"current_steps": 18165, "total_steps": 38160, "loss": 0.1329, "lr": 3.1386497705602094e-05, "epoch": 9.520440251572326, "percentage": 47.6, "elapsed_time": "1:09:15", "remaining_time": "1:16:14", "throughput": 2857.39, "total_tokens": 11873928} {"current_steps": 18170, "total_steps": 38160, "loss": 0.1103, "lr": 3.137544214664249e-05, "epoch": 9.523060796645701, "percentage": 47.62, "elapsed_time": "1:09:16", "remaining_time": "1:16:12", "throughput": 2857.41, "total_tokens": 11876968} {"current_steps": 18175, "total_steps": 38160, "loss": 0.1264, "lr": 3.136438525401312e-05, "epoch": 9.525681341719078, "percentage": 47.63, "elapsed_time": "1:09:17", "remaining_time": "1:16:11", "throughput": 2857.57, "total_tokens": 11880648} {"current_steps": 18180, "total_steps": 38160, "loss": 0.1661, "lr": 3.135332703002696e-05, "epoch": 9.528301886792454, "percentage": 47.64, "elapsed_time": "1:09:18", "remaining_time": "1:16:10", "throughput": 2857.52, "total_tokens": 11883560} {"current_steps": 18185, "total_steps": 38160, "loss": 0.1218, "lr": 3.1342267476997276e-05, "epoch": 9.530922431865829, "percentage": 47.65, "elapsed_time": "1:09:19", "remaining_time": "1:16:09", "throughput": 2857.81, "total_tokens": 11888296} {"current_steps": 18190, "total_steps": 38160, "loss": 0.1548, "lr": 3.1331206597237584e-05, "epoch": 9.533542976939204, "percentage": 47.67, "elapsed_time": "1:09:21", "remaining_time": "1:16:08", "throughput": 2858.01, "total_tokens": 11892872} {"current_steps": 18195, "total_steps": 38160, "loss": 0.0968, "lr": 3.1320144393061715e-05, "epoch": 9.536163522012579, "percentage": 47.68, "elapsed_time": "1:09:22", "remaining_time": "1:16:07", "throughput": 2857.96, "total_tokens": 11895944} {"current_steps": 18200, "total_steps": 38160, "loss": 0.0899, "lr": 3.130908086678373e-05, "epoch": 9.538784067085954, "percentage": 47.69, "elapsed_time": "1:09:23", "remaining_time": "1:16:06", "throughput": 2857.89, "total_tokens": 11898696} {"current_steps": 18205, "total_steps": 38160, "loss": 0.1002, "lr": 3.1298016020718014e-05, "epoch": 9.54140461215933, "percentage": 47.71, "elapsed_time": "1:09:25", "remaining_time": "1:16:05", "throughput": 2858.22, "total_tokens": 11904744} {"current_steps": 18210, "total_steps": 38160, "loss": 0.1262, "lr": 3.128694985717919e-05, "epoch": 9.544025157232705, "percentage": 47.72, "elapsed_time": "1:09:26", "remaining_time": "1:16:04", "throughput": 2858.18, "total_tokens": 11907656} {"current_steps": 18215, "total_steps": 38160, "loss": 0.1901, "lr": 3.1275882378482185e-05, "epoch": 9.54664570230608, "percentage": 47.73, "elapsed_time": "1:09:27", "remaining_time": "1:16:03", "throughput": 2858.09, "total_tokens": 11910504} {"current_steps": 18220, "total_steps": 38160, "loss": 0.1127, "lr": 3.1264813586942185e-05, "epoch": 9.549266247379455, "percentage": 47.75, "elapsed_time": "1:09:28", "remaining_time": "1:16:01", "throughput": 2858.02, "total_tokens": 11913192} {"current_steps": 18225, "total_steps": 38160, "loss": 0.1874, "lr": 3.125374348487466e-05, "epoch": 9.55188679245283, "percentage": 47.76, "elapsed_time": "1:09:29", "remaining_time": "1:16:00", "throughput": 2858.11, "total_tokens": 11916680} {"current_steps": 18230, "total_steps": 38160, "loss": 0.1071, "lr": 3.1242672074595334e-05, "epoch": 9.554507337526205, "percentage": 47.77, "elapsed_time": "1:09:30", "remaining_time": "1:15:59", "throughput": 2858.11, "total_tokens": 11919656} {"current_steps": 18235, "total_steps": 38160, "loss": 0.1394, "lr": 3.123159935842024e-05, "epoch": 9.55712788259958, "percentage": 47.79, "elapsed_time": "1:09:31", "remaining_time": "1:15:58", "throughput": 2858.1, "total_tokens": 11922632} {"current_steps": 18240, "total_steps": 38160, "loss": 0.1373, "lr": 3.122052533866565e-05, "epoch": 9.559748427672956, "percentage": 47.8, "elapsed_time": "1:09:32", "remaining_time": "1:15:56", "throughput": 2858.24, "total_tokens": 11926280} {"current_steps": 18245, "total_steps": 38160, "loss": 0.082, "lr": 3.120945001764813e-05, "epoch": 9.56236897274633, "percentage": 47.81, "elapsed_time": "1:09:33", "remaining_time": "1:15:55", "throughput": 2858.33, "total_tokens": 11929768} {"current_steps": 18250, "total_steps": 38160, "loss": 0.1483, "lr": 3.11983733976845e-05, "epoch": 9.564989517819706, "percentage": 47.82, "elapsed_time": "1:09:34", "remaining_time": "1:15:54", "throughput": 2858.41, "total_tokens": 11933480} {"current_steps": 18255, "total_steps": 38160, "loss": 0.0922, "lr": 3.1187295481091876e-05, "epoch": 9.567610062893081, "percentage": 47.84, "elapsed_time": "1:09:35", "remaining_time": "1:15:53", "throughput": 2858.32, "total_tokens": 11936200} {"current_steps": 18260, "total_steps": 38160, "loss": 0.1652, "lr": 3.1176216270187625e-05, "epoch": 9.570230607966456, "percentage": 47.85, "elapsed_time": "1:09:37", "remaining_time": "1:15:52", "throughput": 2858.12, "total_tokens": 11938472} {"current_steps": 18265, "total_steps": 38160, "loss": 0.1748, "lr": 3.116513576728939e-05, "epoch": 9.572851153039831, "percentage": 47.86, "elapsed_time": "1:09:38", "remaining_time": "1:15:50", "throughput": 2858.32, "total_tokens": 11942280} {"current_steps": 18270, "total_steps": 38160, "loss": 0.1138, "lr": 3.1154053974715085e-05, "epoch": 9.575471698113208, "percentage": 47.88, "elapsed_time": "1:09:39", "remaining_time": "1:15:49", "throughput": 2858.42, "total_tokens": 11945800} {"current_steps": 18275, "total_steps": 38160, "loss": 0.1192, "lr": 3.1142970894782906e-05, "epoch": 9.578092243186584, "percentage": 47.89, "elapsed_time": "1:09:40", "remaining_time": "1:15:48", "throughput": 2858.24, "total_tokens": 11948200} {"current_steps": 18280, "total_steps": 38160, "loss": 0.1453, "lr": 3.1131886529811296e-05, "epoch": 9.580712788259959, "percentage": 47.9, "elapsed_time": "1:09:41", "remaining_time": "1:15:47", "throughput": 2858.32, "total_tokens": 11951656} {"current_steps": 18285, "total_steps": 38160, "loss": 0.1202, "lr": 3.1120800882118985e-05, "epoch": 9.583333333333334, "percentage": 47.92, "elapsed_time": "1:09:42", "remaining_time": "1:15:46", "throughput": 2858.34, "total_tokens": 11955208} {"current_steps": 18290, "total_steps": 38160, "loss": 0.085, "lr": 3.1109713954024945e-05, "epoch": 9.585953878406709, "percentage": 47.93, "elapsed_time": "1:09:43", "remaining_time": "1:15:45", "throughput": 2858.19, "total_tokens": 11957768} {"current_steps": 18295, "total_steps": 38160, "loss": 0.1312, "lr": 3.109862574784846e-05, "epoch": 9.588574423480084, "percentage": 47.94, "elapsed_time": "1:09:44", "remaining_time": "1:15:43", "throughput": 2858.12, "total_tokens": 11960552} {"current_steps": 18300, "total_steps": 38160, "loss": 0.1704, "lr": 3.108753626590905e-05, "epoch": 9.59119496855346, "percentage": 47.96, "elapsed_time": "1:09:45", "remaining_time": "1:15:42", "throughput": 2858.26, "total_tokens": 11964552} {"current_steps": 18305, "total_steps": 38160, "loss": 0.1087, "lr": 3.1076445510526486e-05, "epoch": 9.593815513626835, "percentage": 47.97, "elapsed_time": "1:09:47", "remaining_time": "1:15:41", "throughput": 2858.08, "total_tokens": 11966824} {"current_steps": 18310, "total_steps": 38160, "loss": 0.121, "lr": 3.106535348402086e-05, "epoch": 9.59643605870021, "percentage": 47.98, "elapsed_time": "1:09:48", "remaining_time": "1:15:40", "throughput": 2858.07, "total_tokens": 11969832} {"current_steps": 18315, "total_steps": 38160, "loss": 0.1043, "lr": 3.105426018871247e-05, "epoch": 9.599056603773585, "percentage": 48.0, "elapsed_time": "1:09:49", "remaining_time": "1:15:39", "throughput": 2857.99, "total_tokens": 11972424} {"current_steps": 18320, "total_steps": 38160, "loss": 0.1685, "lr": 3.104316562692193e-05, "epoch": 9.60167714884696, "percentage": 48.01, "elapsed_time": "1:09:50", "remaining_time": "1:15:38", "throughput": 2858.12, "total_tokens": 11976552} {"current_steps": 18325, "total_steps": 38160, "loss": 0.1383, "lr": 3.103206980097009e-05, "epoch": 9.604297693920335, "percentage": 48.02, "elapsed_time": "1:09:51", "remaining_time": "1:15:36", "throughput": 2858.16, "total_tokens": 11979720} {"current_steps": 18330, "total_steps": 38160, "loss": 0.1691, "lr": 3.102097271317805e-05, "epoch": 9.60691823899371, "percentage": 48.03, "elapsed_time": "1:09:52", "remaining_time": "1:15:35", "throughput": 2858.09, "total_tokens": 11982536} {"current_steps": 18335, "total_steps": 38160, "loss": 0.1006, "lr": 3.100987436586721e-05, "epoch": 9.609538784067086, "percentage": 48.05, "elapsed_time": "1:09:53", "remaining_time": "1:15:34", "throughput": 2858.04, "total_tokens": 11985384} {"current_steps": 18340, "total_steps": 38160, "loss": 0.1247, "lr": 3.099877476135923e-05, "epoch": 9.61215932914046, "percentage": 48.06, "elapsed_time": "1:09:54", "remaining_time": "1:15:33", "throughput": 2858.12, "total_tokens": 11988712} {"current_steps": 18345, "total_steps": 38160, "loss": 0.1384, "lr": 3.0987673901976e-05, "epoch": 9.614779874213836, "percentage": 48.07, "elapsed_time": "1:09:55", "remaining_time": "1:15:32", "throughput": 2858.3, "total_tokens": 11993352} {"current_steps": 18350, "total_steps": 38160, "loss": 0.1325, "lr": 3.0976571790039697e-05, "epoch": 9.617400419287211, "percentage": 48.09, "elapsed_time": "1:09:57", "remaining_time": "1:15:30", "throughput": 2858.17, "total_tokens": 11995848} {"current_steps": 18355, "total_steps": 38160, "loss": 0.1783, "lr": 3.096546842787277e-05, "epoch": 9.620020964360586, "percentage": 48.1, "elapsed_time": "1:09:58", "remaining_time": "1:15:29", "throughput": 2858.28, "total_tokens": 11999336} {"current_steps": 18360, "total_steps": 38160, "loss": 0.1427, "lr": 3.095436381779789e-05, "epoch": 9.622641509433961, "percentage": 48.11, "elapsed_time": "1:09:59", "remaining_time": "1:15:28", "throughput": 2858.38, "total_tokens": 12003080} {"current_steps": 18365, "total_steps": 38160, "loss": 0.0732, "lr": 3.0943257962138045e-05, "epoch": 9.625262054507338, "percentage": 48.13, "elapsed_time": "1:10:00", "remaining_time": "1:15:27", "throughput": 2858.57, "total_tokens": 12007240} {"current_steps": 18370, "total_steps": 38160, "loss": 0.148, "lr": 3.093215086321644e-05, "epoch": 9.627882599580714, "percentage": 48.14, "elapsed_time": "1:10:01", "remaining_time": "1:15:26", "throughput": 2858.5, "total_tokens": 12009928} {"current_steps": 18375, "total_steps": 38160, "loss": 0.1292, "lr": 3.092104252335654e-05, "epoch": 9.630503144654089, "percentage": 48.15, "elapsed_time": "1:10:02", "remaining_time": "1:15:25", "throughput": 2858.56, "total_tokens": 12013384} {"current_steps": 18380, "total_steps": 38160, "loss": 0.1106, "lr": 3.09099329448821e-05, "epoch": 9.633123689727464, "percentage": 48.17, "elapsed_time": "1:10:03", "remaining_time": "1:15:23", "throughput": 2858.56, "total_tokens": 12016520} {"current_steps": 18385, "total_steps": 38160, "loss": 0.1175, "lr": 3.089882213011711e-05, "epoch": 9.635744234800839, "percentage": 48.18, "elapsed_time": "1:10:04", "remaining_time": "1:15:22", "throughput": 2858.62, "total_tokens": 12020040} {"current_steps": 18390, "total_steps": 38160, "loss": 0.1309, "lr": 3.088771008138583e-05, "epoch": 9.638364779874214, "percentage": 48.19, "elapsed_time": "1:10:05", "remaining_time": "1:15:21", "throughput": 2858.68, "total_tokens": 12023464} {"current_steps": 18395, "total_steps": 38160, "loss": 0.085, "lr": 3.087659680101278e-05, "epoch": 9.64098532494759, "percentage": 48.2, "elapsed_time": "1:10:07", "remaining_time": "1:15:20", "throughput": 2858.69, "total_tokens": 12026664} {"current_steps": 18400, "total_steps": 38160, "loss": 0.1336, "lr": 3.086548229132271e-05, "epoch": 9.643605870020965, "percentage": 48.22, "elapsed_time": "1:10:08", "remaining_time": "1:15:19", "throughput": 2858.85, "total_tokens": 12030440} {"current_steps": 18405, "total_steps": 38160, "loss": 0.1376, "lr": 3.085436655464067e-05, "epoch": 9.64622641509434, "percentage": 48.23, "elapsed_time": "1:10:09", "remaining_time": "1:15:17", "throughput": 2858.7, "total_tokens": 12032872} {"current_steps": 18410, "total_steps": 38160, "loss": 0.1019, "lr": 3.084324959329193e-05, "epoch": 9.648846960167715, "percentage": 48.24, "elapsed_time": "1:10:10", "remaining_time": "1:15:16", "throughput": 2859.02, "total_tokens": 12037864} {"current_steps": 18415, "total_steps": 38160, "loss": 0.1017, "lr": 3.083213140960204e-05, "epoch": 9.65146750524109, "percentage": 48.26, "elapsed_time": "1:10:11", "remaining_time": "1:15:15", "throughput": 2859.03, "total_tokens": 12040904} {"current_steps": 18420, "total_steps": 38160, "loss": 0.1139, "lr": 3.08210120058968e-05, "epoch": 9.654088050314465, "percentage": 48.27, "elapsed_time": "1:10:12", "remaining_time": "1:15:14", "throughput": 2859.1, "total_tokens": 12044296} {"current_steps": 18425, "total_steps": 38160, "loss": 0.1073, "lr": 3.080989138450225e-05, "epoch": 9.65670859538784, "percentage": 48.28, "elapsed_time": "1:10:13", "remaining_time": "1:15:13", "throughput": 2859.06, "total_tokens": 12047208} {"current_steps": 18430, "total_steps": 38160, "loss": 0.1173, "lr": 3.0798769547744713e-05, "epoch": 9.659329140461216, "percentage": 48.3, "elapsed_time": "1:10:14", "remaining_time": "1:15:12", "throughput": 2859.11, "total_tokens": 12050696} {"current_steps": 18435, "total_steps": 38160, "loss": 0.1526, "lr": 3.0787646497950736e-05, "epoch": 9.66194968553459, "percentage": 48.31, "elapsed_time": "1:10:16", "remaining_time": "1:15:11", "throughput": 2859.23, "total_tokens": 12054536} {"current_steps": 18440, "total_steps": 38160, "loss": 0.141, "lr": 3.0776522237447146e-05, "epoch": 9.664570230607966, "percentage": 48.32, "elapsed_time": "1:10:17", "remaining_time": "1:15:09", "throughput": 2859.02, "total_tokens": 12056776} {"current_steps": 18445, "total_steps": 38160, "loss": 0.1248, "lr": 3.076539676856101e-05, "epoch": 9.667190775681341, "percentage": 48.34, "elapsed_time": "1:10:18", "remaining_time": "1:15:08", "throughput": 2858.96, "total_tokens": 12059720} {"current_steps": 18450, "total_steps": 38160, "loss": 0.1535, "lr": 3.0754270093619634e-05, "epoch": 9.669811320754716, "percentage": 48.35, "elapsed_time": "1:10:19", "remaining_time": "1:15:07", "throughput": 2859.04, "total_tokens": 12063304} {"current_steps": 18455, "total_steps": 38160, "loss": 0.146, "lr": 3.074314221495061e-05, "epoch": 9.672431865828091, "percentage": 48.36, "elapsed_time": "1:10:20", "remaining_time": "1:15:06", "throughput": 2859.27, "total_tokens": 12067592} {"current_steps": 18460, "total_steps": 38160, "loss": 0.1312, "lr": 3.0732013134881756e-05, "epoch": 9.675052410901468, "percentage": 48.38, "elapsed_time": "1:10:21", "remaining_time": "1:15:05", "throughput": 2859.31, "total_tokens": 12070856} {"current_steps": 18465, "total_steps": 38160, "loss": 0.1559, "lr": 3.072088285574114e-05, "epoch": 9.677672955974844, "percentage": 48.39, "elapsed_time": "1:10:22", "remaining_time": "1:15:03", "throughput": 2859.41, "total_tokens": 12074280} {"current_steps": 18470, "total_steps": 38160, "loss": 0.1173, "lr": 3.070975137985711e-05, "epoch": 9.680293501048219, "percentage": 48.4, "elapsed_time": "1:10:23", "remaining_time": "1:15:02", "throughput": 2859.41, "total_tokens": 12077288} {"current_steps": 18475, "total_steps": 38160, "loss": 0.11, "lr": 3.0698618709558226e-05, "epoch": 9.682914046121594, "percentage": 48.41, "elapsed_time": "1:10:25", "remaining_time": "1:15:01", "throughput": 2859.58, "total_tokens": 12082056} {"current_steps": 18480, "total_steps": 38160, "loss": 0.1602, "lr": 3.068748484717332e-05, "epoch": 9.685534591194969, "percentage": 48.43, "elapsed_time": "1:10:26", "remaining_time": "1:15:00", "throughput": 2859.59, "total_tokens": 12085128} {"current_steps": 18485, "total_steps": 38160, "loss": 0.1549, "lr": 3.067634979503147e-05, "epoch": 9.688155136268344, "percentage": 48.44, "elapsed_time": "1:10:27", "remaining_time": "1:14:59", "throughput": 2859.7, "total_tokens": 12089032} {"current_steps": 18490, "total_steps": 38160, "loss": 0.1253, "lr": 3.0665213555462e-05, "epoch": 9.69077568134172, "percentage": 48.45, "elapsed_time": "1:10:28", "remaining_time": "1:14:58", "throughput": 2859.58, "total_tokens": 12091496} {"current_steps": 18495, "total_steps": 38160, "loss": 0.1857, "lr": 3.0654076130794494e-05, "epoch": 9.693396226415095, "percentage": 48.47, "elapsed_time": "1:10:29", "remaining_time": "1:14:57", "throughput": 2859.74, "total_tokens": 12095208} {"current_steps": 18500, "total_steps": 38160, "loss": 0.1962, "lr": 3.064293752335876e-05, "epoch": 9.69601677148847, "percentage": 48.48, "elapsed_time": "1:10:30", "remaining_time": "1:14:55", "throughput": 2859.95, "total_tokens": 12099176} {"current_steps": 18505, "total_steps": 38160, "loss": 0.1453, "lr": 3.063179773548487e-05, "epoch": 9.698637316561845, "percentage": 48.49, "elapsed_time": "1:10:31", "remaining_time": "1:14:54", "throughput": 2859.98, "total_tokens": 12102408} {"current_steps": 18510, "total_steps": 38160, "loss": 0.1688, "lr": 3.0620656769503164e-05, "epoch": 9.70125786163522, "percentage": 48.51, "elapsed_time": "1:10:32", "remaining_time": "1:14:53", "throughput": 2860.02, "total_tokens": 12105704} {"current_steps": 18515, "total_steps": 38160, "loss": 0.2508, "lr": 3.060951462774417e-05, "epoch": 9.703878406708595, "percentage": 48.52, "elapsed_time": "1:10:33", "remaining_time": "1:14:52", "throughput": 2859.98, "total_tokens": 12108520} {"current_steps": 18520, "total_steps": 38160, "loss": 0.1423, "lr": 3.0598371312538714e-05, "epoch": 9.70649895178197, "percentage": 48.53, "elapsed_time": "1:10:34", "remaining_time": "1:14:50", "throughput": 2860.03, "total_tokens": 12111912} {"current_steps": 18525, "total_steps": 38160, "loss": 0.1377, "lr": 3.058722682621785e-05, "epoch": 9.709119496855346, "percentage": 48.55, "elapsed_time": "1:10:36", "remaining_time": "1:14:49", "throughput": 2860.14, "total_tokens": 12116040} {"current_steps": 18530, "total_steps": 38160, "loss": 0.0957, "lr": 3.0576081171112875e-05, "epoch": 9.71174004192872, "percentage": 48.56, "elapsed_time": "1:10:37", "remaining_time": "1:14:48", "throughput": 2860.06, "total_tokens": 12118632} {"current_steps": 18535, "total_steps": 38160, "loss": 0.0863, "lr": 3.056493434955534e-05, "epoch": 9.714360587002096, "percentage": 48.57, "elapsed_time": "1:10:38", "remaining_time": "1:14:47", "throughput": 2859.97, "total_tokens": 12121192} {"current_steps": 18540, "total_steps": 38160, "loss": 0.1092, "lr": 3.0553786363877027e-05, "epoch": 9.716981132075471, "percentage": 48.58, "elapsed_time": "1:10:39", "remaining_time": "1:14:46", "throughput": 2859.92, "total_tokens": 12123976} {"current_steps": 18545, "total_steps": 38160, "loss": 0.2022, "lr": 3.054263721640996e-05, "epoch": 9.719601677148846, "percentage": 48.6, "elapsed_time": "1:10:40", "remaining_time": "1:14:44", "throughput": 2860.12, "total_tokens": 12127816} {"current_steps": 18550, "total_steps": 38160, "loss": 0.1087, "lr": 3.053148690948642e-05, "epoch": 9.722222222222221, "percentage": 48.61, "elapsed_time": "1:10:41", "remaining_time": "1:14:43", "throughput": 2860.26, "total_tokens": 12131848} {"current_steps": 18555, "total_steps": 38160, "loss": 0.1839, "lr": 3.0520335445438935e-05, "epoch": 9.724842767295598, "percentage": 48.62, "elapsed_time": "1:10:42", "remaining_time": "1:14:42", "throughput": 2860.37, "total_tokens": 12135432} {"current_steps": 18560, "total_steps": 38160, "loss": 0.1794, "lr": 3.0509182826600246e-05, "epoch": 9.727463312368974, "percentage": 48.64, "elapsed_time": "1:10:43", "remaining_time": "1:14:41", "throughput": 2860.35, "total_tokens": 12138376} {"current_steps": 18565, "total_steps": 38160, "loss": 0.1606, "lr": 3.049802905530337e-05, "epoch": 9.730083857442349, "percentage": 48.65, "elapsed_time": "1:10:44", "remaining_time": "1:14:40", "throughput": 2860.34, "total_tokens": 12141480} {"current_steps": 18570, "total_steps": 38160, "loss": 0.1121, "lr": 3.0486874133881533e-05, "epoch": 9.732704402515724, "percentage": 48.66, "elapsed_time": "1:10:45", "remaining_time": "1:14:39", "throughput": 2860.26, "total_tokens": 12144168} {"current_steps": 18575, "total_steps": 38160, "loss": 0.1636, "lr": 3.047571806466823e-05, "epoch": 9.735324947589099, "percentage": 48.68, "elapsed_time": "1:10:46", "remaining_time": "1:14:37", "throughput": 2860.44, "total_tokens": 12148168} {"current_steps": 18580, "total_steps": 38160, "loss": 0.0958, "lr": 3.0464560849997177e-05, "epoch": 9.737945492662474, "percentage": 48.69, "elapsed_time": "1:10:48", "remaining_time": "1:14:36", "throughput": 2860.32, "total_tokens": 12150696} {"current_steps": 18585, "total_steps": 38160, "loss": 0.1142, "lr": 3.0453402492202325e-05, "epoch": 9.74056603773585, "percentage": 48.7, "elapsed_time": "1:10:49", "remaining_time": "1:14:35", "throughput": 2860.36, "total_tokens": 12153928} {"current_steps": 18590, "total_steps": 38160, "loss": 0.1409, "lr": 3.0442242993617904e-05, "epoch": 9.743186582809225, "percentage": 48.72, "elapsed_time": "1:10:50", "remaining_time": "1:14:34", "throughput": 2860.43, "total_tokens": 12157384} {"current_steps": 18595, "total_steps": 38160, "loss": 0.1372, "lr": 3.0431082356578334e-05, "epoch": 9.7458071278826, "percentage": 48.73, "elapsed_time": "1:10:51", "remaining_time": "1:14:33", "throughput": 2860.36, "total_tokens": 12160200} {"current_steps": 18600, "total_steps": 38160, "loss": 0.1755, "lr": 3.0419920583418294e-05, "epoch": 9.748427672955975, "percentage": 48.74, "elapsed_time": "1:10:52", "remaining_time": "1:14:31", "throughput": 2860.19, "total_tokens": 12162504} {"current_steps": 18605, "total_steps": 38160, "loss": 0.1454, "lr": 3.0408757676472694e-05, "epoch": 9.75104821802935, "percentage": 48.76, "elapsed_time": "1:10:53", "remaining_time": "1:14:30", "throughput": 2860.12, "total_tokens": 12165288} {"current_steps": 18610, "total_steps": 38160, "loss": 0.1148, "lr": 3.0397593638076705e-05, "epoch": 9.753668763102725, "percentage": 48.77, "elapsed_time": "1:10:54", "remaining_time": "1:14:29", "throughput": 2859.97, "total_tokens": 12167912} {"current_steps": 18615, "total_steps": 38160, "loss": 0.2116, "lr": 3.0386428470565702e-05, "epoch": 9.7562893081761, "percentage": 48.78, "elapsed_time": "1:10:55", "remaining_time": "1:14:28", "throughput": 2860.06, "total_tokens": 12171624} {"current_steps": 18620, "total_steps": 38160, "loss": 0.1276, "lr": 3.0375262176275308e-05, "epoch": 9.758909853249476, "percentage": 48.79, "elapsed_time": "1:10:56", "remaining_time": "1:14:27", "throughput": 2860.05, "total_tokens": 12174632} {"current_steps": 18625, "total_steps": 38160, "loss": 0.2024, "lr": 3.03640947575414e-05, "epoch": 9.76153039832285, "percentage": 48.81, "elapsed_time": "1:10:57", "remaining_time": "1:14:25", "throughput": 2860.09, "total_tokens": 12177896} {"current_steps": 18630, "total_steps": 38160, "loss": 0.1751, "lr": 3.0352926216700067e-05, "epoch": 9.764150943396226, "percentage": 48.82, "elapsed_time": "1:10:59", "remaining_time": "1:14:24", "throughput": 2860.12, "total_tokens": 12181256} {"current_steps": 18635, "total_steps": 38160, "loss": 0.1604, "lr": 3.034175655608763e-05, "epoch": 9.766771488469601, "percentage": 48.83, "elapsed_time": "1:11:00", "remaining_time": "1:14:23", "throughput": 2860.02, "total_tokens": 12183848} {"current_steps": 18640, "total_steps": 38160, "loss": 0.1314, "lr": 3.0330585778040677e-05, "epoch": 9.769392033542976, "percentage": 48.85, "elapsed_time": "1:11:01", "remaining_time": "1:14:22", "throughput": 2860.07, "total_tokens": 12187208} {"current_steps": 18645, "total_steps": 38160, "loss": 0.1375, "lr": 3.031941388489598e-05, "epoch": 9.772012578616351, "percentage": 48.86, "elapsed_time": "1:11:02", "remaining_time": "1:14:21", "throughput": 2860.1, "total_tokens": 12190568} {"current_steps": 18650, "total_steps": 38160, "loss": 0.1106, "lr": 3.0308240878990584e-05, "epoch": 9.774633123689728, "percentage": 48.87, "elapsed_time": "1:11:03", "remaining_time": "1:14:19", "throughput": 2860.01, "total_tokens": 12193224} {"current_steps": 18655, "total_steps": 38160, "loss": 0.1094, "lr": 3.0297066762661773e-05, "epoch": 9.777253668763104, "percentage": 48.89, "elapsed_time": "1:11:04", "remaining_time": "1:14:18", "throughput": 2859.91, "total_tokens": 12195816} {"current_steps": 18660, "total_steps": 38160, "loss": 0.154, "lr": 3.0285891538247015e-05, "epoch": 9.779874213836479, "percentage": 48.9, "elapsed_time": "1:11:05", "remaining_time": "1:14:17", "throughput": 2859.86, "total_tokens": 12198856} {"current_steps": 18665, "total_steps": 38160, "loss": 0.1417, "lr": 3.0274715208084053e-05, "epoch": 9.782494758909854, "percentage": 48.91, "elapsed_time": "1:11:06", "remaining_time": "1:14:16", "throughput": 2859.86, "total_tokens": 12201992} {"current_steps": 18670, "total_steps": 38160, "loss": 0.1176, "lr": 3.0263537774510847e-05, "epoch": 9.785115303983229, "percentage": 48.93, "elapsed_time": "1:11:07", "remaining_time": "1:14:15", "throughput": 2859.93, "total_tokens": 12205608} {"current_steps": 18675, "total_steps": 38160, "loss": 0.1824, "lr": 3.0252359239865585e-05, "epoch": 9.787735849056604, "percentage": 48.94, "elapsed_time": "1:11:08", "remaining_time": "1:14:14", "throughput": 2860.04, "total_tokens": 12209352} {"current_steps": 18680, "total_steps": 38160, "loss": 0.1228, "lr": 3.0241179606486704e-05, "epoch": 9.79035639412998, "percentage": 48.95, "elapsed_time": "1:11:10", "remaining_time": "1:14:13", "throughput": 2860.17, "total_tokens": 12213768} {"current_steps": 18685, "total_steps": 38160, "loss": 0.1102, "lr": 3.0229998876712827e-05, "epoch": 9.792976939203355, "percentage": 48.96, "elapsed_time": "1:11:11", "remaining_time": "1:14:11", "throughput": 2860.16, "total_tokens": 12216776} {"current_steps": 18690, "total_steps": 38160, "loss": 0.122, "lr": 3.0218817052882858e-05, "epoch": 9.79559748427673, "percentage": 48.98, "elapsed_time": "1:11:12", "remaining_time": "1:14:10", "throughput": 2860.38, "total_tokens": 12221000} {"current_steps": 18695, "total_steps": 38160, "loss": 0.1452, "lr": 3.020763413733591e-05, "epoch": 9.798218029350105, "percentage": 48.99, "elapsed_time": "1:11:13", "remaining_time": "1:14:09", "throughput": 2860.34, "total_tokens": 12224200} {"current_steps": 18700, "total_steps": 38160, "loss": 0.1132, "lr": 3.0196450132411302e-05, "epoch": 9.80083857442348, "percentage": 49.0, "elapsed_time": "1:11:14", "remaining_time": "1:14:08", "throughput": 2860.25, "total_tokens": 12226920} {"current_steps": 18705, "total_steps": 38160, "loss": 0.1723, "lr": 3.0185265040448616e-05, "epoch": 9.803459119496855, "percentage": 49.02, "elapsed_time": "1:11:15", "remaining_time": "1:14:07", "throughput": 2860.24, "total_tokens": 12229960} {"current_steps": 18710, "total_steps": 38160, "loss": 0.1361, "lr": 3.017407886378764e-05, "epoch": 9.80607966457023, "percentage": 49.03, "elapsed_time": "1:11:16", "remaining_time": "1:14:06", "throughput": 2860.0, "total_tokens": 12232040} {"current_steps": 18715, "total_steps": 38160, "loss": 0.0932, "lr": 3.016289160476839e-05, "epoch": 9.808700209643606, "percentage": 49.04, "elapsed_time": "1:11:17", "remaining_time": "1:14:04", "throughput": 2859.86, "total_tokens": 12234472} {"current_steps": 18720, "total_steps": 38160, "loss": 0.1126, "lr": 3.0151703265731125e-05, "epoch": 9.81132075471698, "percentage": 49.06, "elapsed_time": "1:11:19", "remaining_time": "1:14:03", "throughput": 2859.84, "total_tokens": 12237448} {"current_steps": 18725, "total_steps": 38160, "loss": 0.1779, "lr": 3.0140513849016305e-05, "epoch": 9.813941299790356, "percentage": 49.07, "elapsed_time": "1:11:20", "remaining_time": "1:14:02", "throughput": 2859.75, "total_tokens": 12240264} {"current_steps": 18730, "total_steps": 38160, "loss": 0.1277, "lr": 3.0129323356964627e-05, "epoch": 9.816561844863731, "percentage": 49.08, "elapsed_time": "1:11:21", "remaining_time": "1:14:01", "throughput": 2859.7, "total_tokens": 12243176} {"current_steps": 18735, "total_steps": 38160, "loss": 0.1089, "lr": 3.0118131791917032e-05, "epoch": 9.819182389937106, "percentage": 49.1, "elapsed_time": "1:11:22", "remaining_time": "1:14:00", "throughput": 2859.57, "total_tokens": 12245864} {"current_steps": 18740, "total_steps": 38160, "loss": 0.157, "lr": 3.010693915621466e-05, "epoch": 9.821802935010481, "percentage": 49.11, "elapsed_time": "1:11:23", "remaining_time": "1:13:58", "throughput": 2859.5, "total_tokens": 12248712} {"current_steps": 18745, "total_steps": 38160, "loss": 0.1592, "lr": 3.009574545219887e-05, "epoch": 9.824423480083858, "percentage": 49.12, "elapsed_time": "1:11:24", "remaining_time": "1:13:57", "throughput": 2859.34, "total_tokens": 12251144} {"current_steps": 18750, "total_steps": 38160, "loss": 0.136, "lr": 3.0084550682211272e-05, "epoch": 9.827044025157234, "percentage": 49.14, "elapsed_time": "1:11:25", "remaining_time": "1:13:56", "throughput": 2859.58, "total_tokens": 12255336} {"current_steps": 18755, "total_steps": 38160, "loss": 0.1122, "lr": 3.0073354848593677e-05, "epoch": 9.829664570230609, "percentage": 49.15, "elapsed_time": "1:11:26", "remaining_time": "1:13:55", "throughput": 2859.42, "total_tokens": 12257672} {"current_steps": 18760, "total_steps": 38160, "loss": 0.1414, "lr": 3.0062157953688125e-05, "epoch": 9.832285115303984, "percentage": 49.16, "elapsed_time": "1:11:27", "remaining_time": "1:13:54", "throughput": 2859.48, "total_tokens": 12261032} {"current_steps": 18765, "total_steps": 38160, "loss": 0.1444, "lr": 3.0050959999836887e-05, "epoch": 9.834905660377359, "percentage": 49.17, "elapsed_time": "1:11:29", "remaining_time": "1:13:53", "throughput": 2859.5, "total_tokens": 12264488} {"current_steps": 18770, "total_steps": 38160, "loss": 0.1401, "lr": 3.003976098938244e-05, "epoch": 9.837526205450734, "percentage": 49.19, "elapsed_time": "1:11:30", "remaining_time": "1:13:51", "throughput": 2859.48, "total_tokens": 12267432} {"current_steps": 18775, "total_steps": 38160, "loss": 0.0991, "lr": 3.0028560924667487e-05, "epoch": 9.84014675052411, "percentage": 49.2, "elapsed_time": "1:11:31", "remaining_time": "1:13:50", "throughput": 2859.51, "total_tokens": 12270888} {"current_steps": 18780, "total_steps": 38160, "loss": 0.125, "lr": 3.001735980803496e-05, "epoch": 9.842767295597485, "percentage": 49.21, "elapsed_time": "1:11:32", "remaining_time": "1:13:49", "throughput": 2859.5, "total_tokens": 12273896} {"current_steps": 18785, "total_steps": 38160, "loss": 0.148, "lr": 3.0006157641828004e-05, "epoch": 9.84538784067086, "percentage": 49.23, "elapsed_time": "1:11:33", "remaining_time": "1:13:48", "throughput": 2859.36, "total_tokens": 12276328} {"current_steps": 18790, "total_steps": 38160, "loss": 0.1103, "lr": 2.9994954428389977e-05, "epoch": 9.848008385744235, "percentage": 49.24, "elapsed_time": "1:11:34", "remaining_time": "1:13:47", "throughput": 2859.28, "total_tokens": 12279016} {"current_steps": 18795, "total_steps": 38160, "loss": 0.0894, "lr": 2.9983750170064472e-05, "epoch": 9.85062893081761, "percentage": 49.25, "elapsed_time": "1:11:35", "remaining_time": "1:13:45", "throughput": 2859.15, "total_tokens": 12281512} {"current_steps": 18800, "total_steps": 38160, "loss": 0.1848, "lr": 2.9972544869195292e-05, "epoch": 9.853249475890985, "percentage": 49.27, "elapsed_time": "1:11:36", "remaining_time": "1:13:44", "throughput": 2859.3, "total_tokens": 12285160} {"current_steps": 18805, "total_steps": 38160, "loss": 0.1892, "lr": 2.9961338528126447e-05, "epoch": 9.85587002096436, "percentage": 49.28, "elapsed_time": "1:11:37", "remaining_time": "1:13:43", "throughput": 2859.4, "total_tokens": 12288616} {"current_steps": 18810, "total_steps": 38160, "loss": 0.2446, "lr": 2.9950131149202192e-05, "epoch": 9.858490566037736, "percentage": 49.29, "elapsed_time": "1:11:38", "remaining_time": "1:13:42", "throughput": 2859.59, "total_tokens": 12292680} {"current_steps": 18815, "total_steps": 38160, "loss": 0.1552, "lr": 2.9938922734766973e-05, "epoch": 9.86111111111111, "percentage": 49.31, "elapsed_time": "1:11:39", "remaining_time": "1:13:41", "throughput": 2859.86, "total_tokens": 12297160} {"current_steps": 18820, "total_steps": 38160, "loss": 0.1787, "lr": 2.992771328716546e-05, "epoch": 9.863731656184486, "percentage": 49.32, "elapsed_time": "1:11:40", "remaining_time": "1:13:39", "throughput": 2859.95, "total_tokens": 12300520} {"current_steps": 18825, "total_steps": 38160, "loss": 0.1864, "lr": 2.991650280874255e-05, "epoch": 9.866352201257861, "percentage": 49.33, "elapsed_time": "1:11:42", "remaining_time": "1:13:38", "throughput": 2859.94, "total_tokens": 12303496} {"current_steps": 18830, "total_steps": 38160, "loss": 0.1502, "lr": 2.990529130184334e-05, "epoch": 9.868972746331236, "percentage": 49.34, "elapsed_time": "1:11:43", "remaining_time": "1:13:37", "throughput": 2859.95, "total_tokens": 12306568} {"current_steps": 18835, "total_steps": 38160, "loss": 0.172, "lr": 2.989407876881316e-05, "epoch": 9.871593291404611, "percentage": 49.36, "elapsed_time": "1:11:44", "remaining_time": "1:13:36", "throughput": 2859.86, "total_tokens": 12309160} {"current_steps": 18840, "total_steps": 38160, "loss": 0.1463, "lr": 2.988286521199753e-05, "epoch": 9.874213836477988, "percentage": 49.37, "elapsed_time": "1:11:45", "remaining_time": "1:13:34", "throughput": 2859.93, "total_tokens": 12312776} {"current_steps": 18845, "total_steps": 38160, "loss": 0.1144, "lr": 2.9871650633742198e-05, "epoch": 9.876834381551364, "percentage": 49.38, "elapsed_time": "1:11:46", "remaining_time": "1:13:33", "throughput": 2860.0, "total_tokens": 12316104} {"current_steps": 18850, "total_steps": 38160, "loss": 0.1678, "lr": 2.9860435036393142e-05, "epoch": 9.879454926624739, "percentage": 49.4, "elapsed_time": "1:11:47", "remaining_time": "1:13:32", "throughput": 2859.87, "total_tokens": 12318568} {"current_steps": 18855, "total_steps": 38160, "loss": 0.1334, "lr": 2.9849218422296527e-05, "epoch": 9.882075471698114, "percentage": 49.41, "elapsed_time": "1:11:48", "remaining_time": "1:13:31", "throughput": 2859.9, "total_tokens": 12321736} {"current_steps": 18860, "total_steps": 38160, "loss": 0.1778, "lr": 2.983800079379873e-05, "epoch": 9.884696016771489, "percentage": 49.42, "elapsed_time": "1:11:49", "remaining_time": "1:13:30", "throughput": 2859.95, "total_tokens": 12325032} {"current_steps": 18865, "total_steps": 38160, "loss": 0.2098, "lr": 2.982678215324638e-05, "epoch": 9.887316561844864, "percentage": 49.44, "elapsed_time": "1:11:50", "remaining_time": "1:13:28", "throughput": 2860.1, "total_tokens": 12329160} {"current_steps": 18870, "total_steps": 38160, "loss": 0.3122, "lr": 2.9815562502986256e-05, "epoch": 9.88993710691824, "percentage": 49.45, "elapsed_time": "1:11:51", "remaining_time": "1:13:27", "throughput": 2860.15, "total_tokens": 12332392} {"current_steps": 18875, "total_steps": 38160, "loss": 0.162, "lr": 2.9804341845365398e-05, "epoch": 9.892557651991615, "percentage": 49.46, "elapsed_time": "1:11:52", "remaining_time": "1:13:26", "throughput": 2860.31, "total_tokens": 12336456} {"current_steps": 18880, "total_steps": 38160, "loss": 0.1436, "lr": 2.9793120182731037e-05, "epoch": 9.89517819706499, "percentage": 49.48, "elapsed_time": "1:11:54", "remaining_time": "1:13:25", "throughput": 2860.16, "total_tokens": 12339080} {"current_steps": 18885, "total_steps": 38160, "loss": 0.1102, "lr": 2.9781897517430617e-05, "epoch": 9.897798742138365, "percentage": 49.49, "elapsed_time": "1:11:55", "remaining_time": "1:13:24", "throughput": 2860.08, "total_tokens": 12341768} {"current_steps": 18890, "total_steps": 38160, "loss": 0.1368, "lr": 2.977067385181179e-05, "epoch": 9.90041928721174, "percentage": 49.5, "elapsed_time": "1:11:56", "remaining_time": "1:13:23", "throughput": 2860.11, "total_tokens": 12344936} {"current_steps": 18895, "total_steps": 38160, "loss": 0.1194, "lr": 2.9759449188222426e-05, "epoch": 9.903039832285115, "percentage": 49.52, "elapsed_time": "1:11:57", "remaining_time": "1:13:21", "throughput": 2860.35, "total_tokens": 12349416} {"current_steps": 18900, "total_steps": 38160, "loss": 0.1248, "lr": 2.9748223529010582e-05, "epoch": 9.90566037735849, "percentage": 49.53, "elapsed_time": "1:11:58", "remaining_time": "1:13:20", "throughput": 2860.35, "total_tokens": 12352360} {"current_steps": 18905, "total_steps": 38160, "loss": 0.1852, "lr": 2.9736996876524546e-05, "epoch": 9.908280922431866, "percentage": 49.54, "elapsed_time": "1:11:59", "remaining_time": "1:13:19", "throughput": 2860.39, "total_tokens": 12355688} {"current_steps": 18910, "total_steps": 38160, "loss": 0.1561, "lr": 2.9725769233112816e-05, "epoch": 9.91090146750524, "percentage": 49.55, "elapsed_time": "1:12:00", "remaining_time": "1:13:18", "throughput": 2860.53, "total_tokens": 12359560} {"current_steps": 18915, "total_steps": 38160, "loss": 0.2172, "lr": 2.9714540601124074e-05, "epoch": 9.913522012578616, "percentage": 49.57, "elapsed_time": "1:12:01", "remaining_time": "1:13:17", "throughput": 2860.68, "total_tokens": 12363656} {"current_steps": 18920, "total_steps": 38160, "loss": 0.1262, "lr": 2.9703310982907218e-05, "epoch": 9.916142557651991, "percentage": 49.58, "elapsed_time": "1:12:03", "remaining_time": "1:13:16", "throughput": 2860.82, "total_tokens": 12367688} {"current_steps": 18925, "total_steps": 38160, "loss": 0.1381, "lr": 2.9692080380811365e-05, "epoch": 9.918763102725366, "percentage": 49.59, "elapsed_time": "1:12:04", "remaining_time": "1:13:15", "throughput": 2860.91, "total_tokens": 12371400} {"current_steps": 18930, "total_steps": 38160, "loss": 0.1267, "lr": 2.9680848797185828e-05, "epoch": 9.921383647798741, "percentage": 49.61, "elapsed_time": "1:12:05", "remaining_time": "1:13:13", "throughput": 2860.85, "total_tokens": 12374152} {"current_steps": 18935, "total_steps": 38160, "loss": 0.0924, "lr": 2.966961623438012e-05, "epoch": 9.924004192872118, "percentage": 49.62, "elapsed_time": "1:12:06", "remaining_time": "1:13:12", "throughput": 2861.02, "total_tokens": 12378472} {"current_steps": 18940, "total_steps": 38160, "loss": 0.1465, "lr": 2.9658382694743973e-05, "epoch": 9.926624737945493, "percentage": 49.63, "elapsed_time": "1:12:07", "remaining_time": "1:13:11", "throughput": 2860.99, "total_tokens": 12381480} {"current_steps": 18945, "total_steps": 38160, "loss": 0.164, "lr": 2.9647148180627317e-05, "epoch": 9.929245283018869, "percentage": 49.65, "elapsed_time": "1:12:08", "remaining_time": "1:13:10", "throughput": 2861.0, "total_tokens": 12384648} {"current_steps": 18950, "total_steps": 38160, "loss": 0.104, "lr": 2.9635912694380275e-05, "epoch": 9.931865828092244, "percentage": 49.66, "elapsed_time": "1:12:09", "remaining_time": "1:13:09", "throughput": 2860.96, "total_tokens": 12387432} {"current_steps": 18955, "total_steps": 38160, "loss": 0.142, "lr": 2.962467623835319e-05, "epoch": 9.934486373165619, "percentage": 49.67, "elapsed_time": "1:12:10", "remaining_time": "1:13:07", "throughput": 2861.08, "total_tokens": 12390984} {"current_steps": 18960, "total_steps": 38160, "loss": 0.1417, "lr": 2.961343881489659e-05, "epoch": 9.937106918238994, "percentage": 49.69, "elapsed_time": "1:12:11", "remaining_time": "1:13:06", "throughput": 2861.24, "total_tokens": 12394760} {"current_steps": 18965, "total_steps": 38160, "loss": 0.2078, "lr": 2.9602200426361226e-05, "epoch": 9.93972746331237, "percentage": 49.7, "elapsed_time": "1:12:12", "remaining_time": "1:13:05", "throughput": 2861.25, "total_tokens": 12397768} {"current_steps": 18970, "total_steps": 38160, "loss": 0.1301, "lr": 2.9590961075098038e-05, "epoch": 9.942348008385745, "percentage": 49.71, "elapsed_time": "1:12:14", "remaining_time": "1:13:04", "throughput": 2861.26, "total_tokens": 12400968} {"current_steps": 18975, "total_steps": 38160, "loss": 0.1607, "lr": 2.957972076345817e-05, "epoch": 9.94496855345912, "percentage": 49.72, "elapsed_time": "1:12:15", "remaining_time": "1:13:03", "throughput": 2861.4, "total_tokens": 12406664} {"current_steps": 18980, "total_steps": 38160, "loss": 0.1136, "lr": 2.9568479493792967e-05, "epoch": 9.947589098532495, "percentage": 49.74, "elapsed_time": "1:12:16", "remaining_time": "1:13:02", "throughput": 2861.35, "total_tokens": 12409448} {"current_steps": 18985, "total_steps": 38160, "loss": 0.0589, "lr": 2.955723726845397e-05, "epoch": 9.95020964360587, "percentage": 49.75, "elapsed_time": "1:12:17", "remaining_time": "1:13:01", "throughput": 2861.4, "total_tokens": 12412744} {"current_steps": 18990, "total_steps": 38160, "loss": 0.2658, "lr": 2.9545994089792928e-05, "epoch": 9.952830188679245, "percentage": 49.76, "elapsed_time": "1:12:19", "remaining_time": "1:13:00", "throughput": 2861.34, "total_tokens": 12415656} {"current_steps": 18995, "total_steps": 38160, "loss": 0.1745, "lr": 2.9534749960161795e-05, "epoch": 9.95545073375262, "percentage": 49.78, "elapsed_time": "1:12:20", "remaining_time": "1:12:58", "throughput": 2861.3, "total_tokens": 12418472} {"current_steps": 19000, "total_steps": 38160, "loss": 0.1179, "lr": 2.9523504881912694e-05, "epoch": 9.958071278825996, "percentage": 49.79, "elapsed_time": "1:12:21", "remaining_time": "1:12:57", "throughput": 2861.32, "total_tokens": 12421768} {"current_steps": 19005, "total_steps": 38160, "loss": 0.18, "lr": 2.9512258857397978e-05, "epoch": 9.96069182389937, "percentage": 49.8, "elapsed_time": "1:12:22", "remaining_time": "1:12:56", "throughput": 2861.52, "total_tokens": 12425800} {"current_steps": 19010, "total_steps": 38160, "loss": 0.1664, "lr": 2.9501011888970203e-05, "epoch": 9.963312368972746, "percentage": 49.82, "elapsed_time": "1:12:23", "remaining_time": "1:12:55", "throughput": 2861.57, "total_tokens": 12429288} {"current_steps": 19015, "total_steps": 38160, "loss": 0.0936, "lr": 2.9489763978982075e-05, "epoch": 9.965932914046121, "percentage": 49.83, "elapsed_time": "1:12:24", "remaining_time": "1:12:54", "throughput": 2861.69, "total_tokens": 12433160} {"current_steps": 19020, "total_steps": 38160, "loss": 0.1002, "lr": 2.9478515129786556e-05, "epoch": 9.968553459119496, "percentage": 49.84, "elapsed_time": "1:12:25", "remaining_time": "1:12:53", "throughput": 2861.63, "total_tokens": 12435944} {"current_steps": 19025, "total_steps": 38160, "loss": 0.1157, "lr": 2.946726534373676e-05, "epoch": 9.971174004192871, "percentage": 49.86, "elapsed_time": "1:12:26", "remaining_time": "1:12:51", "throughput": 2861.46, "total_tokens": 12438216} {"current_steps": 19030, "total_steps": 38160, "loss": 0.1129, "lr": 2.945601462318601e-05, "epoch": 9.973794549266248, "percentage": 49.87, "elapsed_time": "1:12:27", "remaining_time": "1:12:50", "throughput": 2861.4, "total_tokens": 12440904} {"current_steps": 19035, "total_steps": 38160, "loss": 0.1182, "lr": 2.944476297048786e-05, "epoch": 9.976415094339622, "percentage": 49.88, "elapsed_time": "1:12:28", "remaining_time": "1:12:49", "throughput": 2861.37, "total_tokens": 12443752} {"current_steps": 19040, "total_steps": 38160, "loss": 0.2191, "lr": 2.9433510387995987e-05, "epoch": 9.979035639412999, "percentage": 49.9, "elapsed_time": "1:12:29", "remaining_time": "1:12:48", "throughput": 2861.23, "total_tokens": 12446152} {"current_steps": 19045, "total_steps": 38160, "loss": 0.097, "lr": 2.9422256878064325e-05, "epoch": 9.981656184486374, "percentage": 49.91, "elapsed_time": "1:12:30", "remaining_time": "1:12:46", "throughput": 2861.22, "total_tokens": 12449160} {"current_steps": 19050, "total_steps": 38160, "loss": 0.1956, "lr": 2.9411002443046982e-05, "epoch": 9.984276729559749, "percentage": 49.92, "elapsed_time": "1:12:32", "remaining_time": "1:12:45", "throughput": 2861.38, "total_tokens": 12453064} {"current_steps": 19055, "total_steps": 38160, "loss": 0.1409, "lr": 2.9399747085298245e-05, "epoch": 9.986897274633124, "percentage": 49.93, "elapsed_time": "1:12:33", "remaining_time": "1:12:44", "throughput": 2861.36, "total_tokens": 12455944} {"current_steps": 19060, "total_steps": 38160, "loss": 0.1692, "lr": 2.9388490807172614e-05, "epoch": 9.9895178197065, "percentage": 49.95, "elapsed_time": "1:12:34", "remaining_time": "1:12:43", "throughput": 2861.46, "total_tokens": 12459528} {"current_steps": 19065, "total_steps": 38160, "loss": 0.1755, "lr": 2.9377233611024775e-05, "epoch": 9.992138364779874, "percentage": 49.96, "elapsed_time": "1:12:35", "remaining_time": "1:12:42", "throughput": 2861.52, "total_tokens": 12463048} {"current_steps": 19070, "total_steps": 38160, "loss": 0.1597, "lr": 2.9365975499209596e-05, "epoch": 9.99475890985325, "percentage": 49.97, "elapsed_time": "1:12:36", "remaining_time": "1:12:41", "throughput": 2861.72, "total_tokens": 12467240} {"current_steps": 19075, "total_steps": 38160, "loss": 0.286, "lr": 2.9354716474082154e-05, "epoch": 9.997379454926625, "percentage": 49.99, "elapsed_time": "1:12:37", "remaining_time": "1:12:39", "throughput": 2861.7, "total_tokens": 12470216} {"current_steps": 19080, "total_steps": 38160, "loss": 0.2099, "lr": 2.9343456537997714e-05, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "1:12:38", "remaining_time": "1:12:38", "throughput": 2861.55, "total_tokens": 12472912} {"current_steps": 19080, "total_steps": 38160, "eval_loss": 0.8089353442192078, "epoch": 10.0, "percentage": 50.0, "elapsed_time": "1:12:50", "remaining_time": "1:12:50", "throughput": 2853.93, "total_tokens": 12472912} {"current_steps": 19085, "total_steps": 38160, "loss": 0.0653, "lr": 2.9332195693311714e-05, "epoch": 10.002620545073375, "percentage": 50.01, "elapsed_time": "1:12:54", "remaining_time": "1:12:52", "throughput": 2851.68, "total_tokens": 12475568} {"current_steps": 19090, "total_steps": 38160, "loss": 0.0448, "lr": 2.9320933942379803e-05, "epoch": 10.00524109014675, "percentage": 50.03, "elapsed_time": "1:12:55", "remaining_time": "1:12:51", "throughput": 2851.55, "total_tokens": 12478128} {"current_steps": 19095, "total_steps": 38160, "loss": 0.0748, "lr": 2.9309671287557805e-05, "epoch": 10.007861635220126, "percentage": 50.04, "elapsed_time": "1:12:56", "remaining_time": "1:12:50", "throughput": 2851.64, "total_tokens": 12481520} {"current_steps": 19100, "total_steps": 38160, "loss": 0.1406, "lr": 2.9298407731201737e-05, "epoch": 10.0104821802935, "percentage": 50.05, "elapsed_time": "1:12:58", "remaining_time": "1:12:48", "throughput": 2851.75, "total_tokens": 12485264} {"current_steps": 19105, "total_steps": 38160, "loss": 0.0762, "lr": 2.928714327566781e-05, "epoch": 10.013102725366876, "percentage": 50.07, "elapsed_time": "1:12:59", "remaining_time": "1:12:47", "throughput": 2851.71, "total_tokens": 12488464} {"current_steps": 19110, "total_steps": 38160, "loss": 0.0922, "lr": 2.9275877923312427e-05, "epoch": 10.015723270440251, "percentage": 50.08, "elapsed_time": "1:13:00", "remaining_time": "1:12:46", "throughput": 2851.68, "total_tokens": 12491504} {"current_steps": 19115, "total_steps": 38160, "loss": 0.2096, "lr": 2.9264611676492165e-05, "epoch": 10.018343815513626, "percentage": 50.09, "elapsed_time": "1:13:01", "remaining_time": "1:12:45", "throughput": 2851.65, "total_tokens": 12494576} {"current_steps": 19120, "total_steps": 38160, "loss": 0.0881, "lr": 2.9253344537563782e-05, "epoch": 10.020964360587001, "percentage": 50.1, "elapsed_time": "1:13:02", "remaining_time": "1:12:44", "throughput": 2851.63, "total_tokens": 12497648} {"current_steps": 19125, "total_steps": 38160, "loss": 0.1158, "lr": 2.924207650888426e-05, "epoch": 10.023584905660377, "percentage": 50.12, "elapsed_time": "1:13:03", "remaining_time": "1:12:43", "throughput": 2851.5, "total_tokens": 12500208} {"current_steps": 19130, "total_steps": 38160, "loss": 0.1185, "lr": 2.9230807592810723e-05, "epoch": 10.026205450733753, "percentage": 50.13, "elapsed_time": "1:13:04", "remaining_time": "1:12:41", "throughput": 2851.48, "total_tokens": 12503248} {"current_steps": 19135, "total_steps": 38160, "loss": 0.0875, "lr": 2.92195377917005e-05, "epoch": 10.028825995807129, "percentage": 50.14, "elapsed_time": "1:13:06", "remaining_time": "1:12:40", "throughput": 2851.71, "total_tokens": 12508080} {"current_steps": 19140, "total_steps": 38160, "loss": 0.0728, "lr": 2.920826710791112e-05, "epoch": 10.031446540880504, "percentage": 50.16, "elapsed_time": "1:13:07", "remaining_time": "1:12:39", "throughput": 2851.83, "total_tokens": 12511856} {"current_steps": 19145, "total_steps": 38160, "loss": 0.1033, "lr": 2.919699554380026e-05, "epoch": 10.034067085953879, "percentage": 50.17, "elapsed_time": "1:13:08", "remaining_time": "1:12:38", "throughput": 2852.05, "total_tokens": 12515920} {"current_steps": 19150, "total_steps": 38160, "loss": 0.0997, "lr": 2.9185723101725825e-05, "epoch": 10.036687631027254, "percentage": 50.18, "elapsed_time": "1:13:09", "remaining_time": "1:12:37", "throughput": 2852.04, "total_tokens": 12519024} {"current_steps": 19155, "total_steps": 38160, "loss": 0.0816, "lr": 2.9174449784045867e-05, "epoch": 10.03930817610063, "percentage": 50.2, "elapsed_time": "1:13:10", "remaining_time": "1:12:36", "throughput": 2851.99, "total_tokens": 12521840} {"current_steps": 19160, "total_steps": 38160, "loss": 0.1147, "lr": 2.916317559311863e-05, "epoch": 10.041928721174004, "percentage": 50.21, "elapsed_time": "1:13:11", "remaining_time": "1:12:34", "throughput": 2852.0, "total_tokens": 12525008} {"current_steps": 19165, "total_steps": 38160, "loss": 0.0917, "lr": 2.9151900531302566e-05, "epoch": 10.04454926624738, "percentage": 50.22, "elapsed_time": "1:13:12", "remaining_time": "1:12:33", "throughput": 2852.0, "total_tokens": 12528048} {"current_steps": 19170, "total_steps": 38160, "loss": 0.0847, "lr": 2.9140624600956272e-05, "epoch": 10.047169811320755, "percentage": 50.24, "elapsed_time": "1:13:13", "remaining_time": "1:12:32", "throughput": 2852.05, "total_tokens": 12531536} {"current_steps": 19175, "total_steps": 38160, "loss": 0.1256, "lr": 2.912934780443855e-05, "epoch": 10.04979035639413, "percentage": 50.25, "elapsed_time": "1:13:15", "remaining_time": "1:12:31", "throughput": 2852.14, "total_tokens": 12535248} {"current_steps": 19180, "total_steps": 38160, "loss": 0.0731, "lr": 2.9118070144108388e-05, "epoch": 10.052410901467505, "percentage": 50.26, "elapsed_time": "1:13:16", "remaining_time": "1:12:30", "throughput": 2852.1, "total_tokens": 12538128} {"current_steps": 19185, "total_steps": 38160, "loss": 0.0928, "lr": 2.9106791622324924e-05, "epoch": 10.05503144654088, "percentage": 50.28, "elapsed_time": "1:13:17", "remaining_time": "1:12:29", "throughput": 2852.06, "total_tokens": 12541136} {"current_steps": 19190, "total_steps": 38160, "loss": 0.0985, "lr": 2.909551224144751e-05, "epoch": 10.057651991614255, "percentage": 50.29, "elapsed_time": "1:13:18", "remaining_time": "1:12:27", "throughput": 2852.08, "total_tokens": 12544272} {"current_steps": 19195, "total_steps": 38160, "loss": 0.1009, "lr": 2.9084232003835653e-05, "epoch": 10.06027253668763, "percentage": 50.3, "elapsed_time": "1:13:19", "remaining_time": "1:12:26", "throughput": 2852.02, "total_tokens": 12547184} {"current_steps": 19200, "total_steps": 38160, "loss": 0.0971, "lr": 2.9072950911849058e-05, "epoch": 10.062893081761006, "percentage": 50.31, "elapsed_time": "1:13:20", "remaining_time": "1:12:25", "throughput": 2852.03, "total_tokens": 12550416} {"current_steps": 19205, "total_steps": 38160, "loss": 0.0739, "lr": 2.90616689678476e-05, "epoch": 10.065513626834381, "percentage": 50.33, "elapsed_time": "1:13:21", "remaining_time": "1:12:24", "throughput": 2851.85, "total_tokens": 12552688} {"current_steps": 19210, "total_steps": 38160, "loss": 0.1141, "lr": 2.9050386174191337e-05, "epoch": 10.068134171907756, "percentage": 50.34, "elapsed_time": "1:13:22", "remaining_time": "1:12:23", "throughput": 2851.8, "total_tokens": 12555536} {"current_steps": 19215, "total_steps": 38160, "loss": 0.0707, "lr": 2.903910253324048e-05, "epoch": 10.070754716981131, "percentage": 50.35, "elapsed_time": "1:13:23", "remaining_time": "1:12:21", "throughput": 2851.77, "total_tokens": 12558672} {"current_steps": 19220, "total_steps": 38160, "loss": 0.0913, "lr": 2.9027818047355477e-05, "epoch": 10.073375262054507, "percentage": 50.37, "elapsed_time": "1:13:24", "remaining_time": "1:12:20", "throughput": 2851.81, "total_tokens": 12562192} {"current_steps": 19225, "total_steps": 38160, "loss": 0.0979, "lr": 2.9016532718896873e-05, "epoch": 10.075995807127883, "percentage": 50.38, "elapsed_time": "1:13:26", "remaining_time": "1:12:19", "throughput": 2851.84, "total_tokens": 12565584} {"current_steps": 19230, "total_steps": 38160, "loss": 0.1088, "lr": 2.900524655022545e-05, "epoch": 10.078616352201259, "percentage": 50.39, "elapsed_time": "1:13:27", "remaining_time": "1:12:18", "throughput": 2851.83, "total_tokens": 12568720} {"current_steps": 19235, "total_steps": 38160, "loss": 0.0879, "lr": 2.899395954370215e-05, "epoch": 10.081236897274634, "percentage": 50.41, "elapsed_time": "1:13:28", "remaining_time": "1:12:17", "throughput": 2851.95, "total_tokens": 12572432} {"current_steps": 19240, "total_steps": 38160, "loss": 0.1177, "lr": 2.898267170168807e-05, "epoch": 10.083857442348009, "percentage": 50.42, "elapsed_time": "1:13:29", "remaining_time": "1:12:16", "throughput": 2851.99, "total_tokens": 12575632} {"current_steps": 19245, "total_steps": 38160, "loss": 0.067, "lr": 2.8971383026544507e-05, "epoch": 10.086477987421384, "percentage": 50.43, "elapsed_time": "1:13:30", "remaining_time": "1:12:14", "throughput": 2852.18, "total_tokens": 12579888} {"current_steps": 19250, "total_steps": 38160, "loss": 0.0617, "lr": 2.896009352063293e-05, "epoch": 10.08909853249476, "percentage": 50.45, "elapsed_time": "1:13:31", "remaining_time": "1:12:13", "throughput": 2852.08, "total_tokens": 12582416} {"current_steps": 19255, "total_steps": 38160, "loss": 0.0663, "lr": 2.894880318631496e-05, "epoch": 10.091719077568134, "percentage": 50.46, "elapsed_time": "1:13:32", "remaining_time": "1:12:12", "throughput": 2852.04, "total_tokens": 12585360} {"current_steps": 19260, "total_steps": 38160, "loss": 0.0703, "lr": 2.8937512025952417e-05, "epoch": 10.09433962264151, "percentage": 50.47, "elapsed_time": "1:13:33", "remaining_time": "1:12:11", "throughput": 2852.19, "total_tokens": 12589456} {"current_steps": 19265, "total_steps": 38160, "loss": 0.0806, "lr": 2.8926220041907283e-05, "epoch": 10.096960167714885, "percentage": 50.48, "elapsed_time": "1:13:35", "remaining_time": "1:12:10", "throughput": 2852.24, "total_tokens": 12592752} {"current_steps": 19270, "total_steps": 38160, "loss": 0.1553, "lr": 2.8914927236541706e-05, "epoch": 10.09958071278826, "percentage": 50.5, "elapsed_time": "1:13:36", "remaining_time": "1:12:09", "throughput": 2852.27, "total_tokens": 12596304} {"current_steps": 19275, "total_steps": 38160, "loss": 0.151, "lr": 2.8903633612218012e-05, "epoch": 10.102201257861635, "percentage": 50.51, "elapsed_time": "1:13:37", "remaining_time": "1:12:08", "throughput": 2852.35, "total_tokens": 12600048} {"current_steps": 19280, "total_steps": 38160, "loss": 0.0855, "lr": 2.8892339171298703e-05, "epoch": 10.10482180293501, "percentage": 50.52, "elapsed_time": "1:13:38", "remaining_time": "1:12:06", "throughput": 2852.3, "total_tokens": 12602992} {"current_steps": 19285, "total_steps": 38160, "loss": 0.1083, "lr": 2.888104391614645e-05, "epoch": 10.107442348008385, "percentage": 50.54, "elapsed_time": "1:13:39", "remaining_time": "1:12:05", "throughput": 2852.42, "total_tokens": 12606960} {"current_steps": 19290, "total_steps": 38160, "loss": 0.0905, "lr": 2.886974784912408e-05, "epoch": 10.11006289308176, "percentage": 50.55, "elapsed_time": "1:13:40", "remaining_time": "1:12:04", "throughput": 2852.29, "total_tokens": 12609584} {"current_steps": 19295, "total_steps": 38160, "loss": 0.0784, "lr": 2.8858450972594612e-05, "epoch": 10.112683438155136, "percentage": 50.56, "elapsed_time": "1:13:41", "remaining_time": "1:12:03", "throughput": 2852.22, "total_tokens": 12612368} {"current_steps": 19300, "total_steps": 38160, "loss": 0.0949, "lr": 2.8847153288921226e-05, "epoch": 10.115303983228511, "percentage": 50.58, "elapsed_time": "1:13:43", "remaining_time": "1:12:02", "throughput": 2852.21, "total_tokens": 12615472} {"current_steps": 19305, "total_steps": 38160, "loss": 0.1524, "lr": 2.883585480046725e-05, "epoch": 10.117924528301886, "percentage": 50.59, "elapsed_time": "1:13:44", "remaining_time": "1:12:01", "throughput": 2852.43, "total_tokens": 12621456} {"current_steps": 19310, "total_steps": 38160, "loss": 0.0586, "lr": 2.8824555509596223e-05, "epoch": 10.120545073375261, "percentage": 50.6, "elapsed_time": "1:13:45", "remaining_time": "1:12:00", "throughput": 2852.43, "total_tokens": 12624624} {"current_steps": 19315, "total_steps": 38160, "loss": 0.1139, "lr": 2.8813255418671815e-05, "epoch": 10.123165618448636, "percentage": 50.62, "elapsed_time": "1:13:47", "remaining_time": "1:11:59", "throughput": 2852.48, "total_tokens": 12628112} {"current_steps": 19320, "total_steps": 38160, "loss": 0.0936, "lr": 2.8801954530057874e-05, "epoch": 10.125786163522013, "percentage": 50.63, "elapsed_time": "1:13:48", "remaining_time": "1:11:58", "throughput": 2852.51, "total_tokens": 12631536} {"current_steps": 19325, "total_steps": 38160, "loss": 0.0623, "lr": 2.879065284611842e-05, "epoch": 10.128406708595389, "percentage": 50.64, "elapsed_time": "1:13:49", "remaining_time": "1:11:56", "throughput": 2852.54, "total_tokens": 12634704} {"current_steps": 19330, "total_steps": 38160, "loss": 0.075, "lr": 2.8779350369217634e-05, "epoch": 10.131027253668764, "percentage": 50.66, "elapsed_time": "1:13:50", "remaining_time": "1:11:55", "throughput": 2852.65, "total_tokens": 12638640} {"current_steps": 19335, "total_steps": 38160, "loss": 0.0559, "lr": 2.876804710171987e-05, "epoch": 10.133647798742139, "percentage": 50.67, "elapsed_time": "1:13:51", "remaining_time": "1:11:54", "throughput": 2852.58, "total_tokens": 12641392} {"current_steps": 19340, "total_steps": 38160, "loss": 0.1218, "lr": 2.8756743045989643e-05, "epoch": 10.136268343815514, "percentage": 50.68, "elapsed_time": "1:13:53", "remaining_time": "1:11:54", "throughput": 2852.9, "total_tokens": 12648656} {"current_steps": 19345, "total_steps": 38160, "loss": 0.0836, "lr": 2.8745438204391623e-05, "epoch": 10.13888888888889, "percentage": 50.69, "elapsed_time": "1:13:54", "remaining_time": "1:11:53", "throughput": 2852.91, "total_tokens": 12651760} {"current_steps": 19350, "total_steps": 38160, "loss": 0.1116, "lr": 2.8734132579290675e-05, "epoch": 10.141509433962264, "percentage": 50.71, "elapsed_time": "1:13:55", "remaining_time": "1:11:51", "throughput": 2852.96, "total_tokens": 12655120} {"current_steps": 19355, "total_steps": 38160, "loss": 0.0492, "lr": 2.8722826173051782e-05, "epoch": 10.14412997903564, "percentage": 50.72, "elapsed_time": "1:13:56", "remaining_time": "1:11:50", "throughput": 2852.92, "total_tokens": 12657936} {"current_steps": 19360, "total_steps": 38160, "loss": 0.0634, "lr": 2.871151898804012e-05, "epoch": 10.146750524109015, "percentage": 50.73, "elapsed_time": "1:13:57", "remaining_time": "1:11:49", "throughput": 2853.06, "total_tokens": 12661648} {"current_steps": 19365, "total_steps": 38160, "loss": 0.1272, "lr": 2.8700211026621043e-05, "epoch": 10.14937106918239, "percentage": 50.75, "elapsed_time": "1:13:58", "remaining_time": "1:11:48", "throughput": 2853.21, "total_tokens": 12665328} {"current_steps": 19370, "total_steps": 38160, "loss": 0.1179, "lr": 2.8688902291160025e-05, "epoch": 10.151991614255765, "percentage": 50.76, "elapsed_time": "1:14:00", "remaining_time": "1:11:47", "throughput": 2853.23, "total_tokens": 12668464} {"current_steps": 19375, "total_steps": 38160, "loss": 0.0748, "lr": 2.867759278402273e-05, "epoch": 10.15461215932914, "percentage": 50.77, "elapsed_time": "1:14:01", "remaining_time": "1:11:45", "throughput": 2853.34, "total_tokens": 12672016} {"current_steps": 19380, "total_steps": 38160, "loss": 0.1064, "lr": 2.8666282507574994e-05, "epoch": 10.157232704402515, "percentage": 50.79, "elapsed_time": "1:14:02", "remaining_time": "1:11:44", "throughput": 2853.4, "total_tokens": 12675312} {"current_steps": 19385, "total_steps": 38160, "loss": 0.1502, "lr": 2.8654971464182773e-05, "epoch": 10.15985324947589, "percentage": 50.8, "elapsed_time": "1:14:03", "remaining_time": "1:11:43", "throughput": 2853.3, "total_tokens": 12677872} {"current_steps": 19390, "total_steps": 38160, "loss": 0.0876, "lr": 2.8643659656212222e-05, "epoch": 10.162473794549266, "percentage": 50.81, "elapsed_time": "1:14:04", "remaining_time": "1:11:42", "throughput": 2853.57, "total_tokens": 12684112} {"current_steps": 19395, "total_steps": 38160, "loss": 0.0614, "lr": 2.8632347086029642e-05, "epoch": 10.165094339622641, "percentage": 50.83, "elapsed_time": "1:14:06", "remaining_time": "1:11:41", "throughput": 2853.49, "total_tokens": 12686736} {"current_steps": 19400, "total_steps": 38160, "loss": 0.1702, "lr": 2.8621033756001486e-05, "epoch": 10.167714884696016, "percentage": 50.84, "elapsed_time": "1:14:07", "remaining_time": "1:11:40", "throughput": 2853.55, "total_tokens": 12690352} {"current_steps": 19405, "total_steps": 38160, "loss": 0.0702, "lr": 2.8609719668494394e-05, "epoch": 10.170335429769391, "percentage": 50.85, "elapsed_time": "1:14:08", "remaining_time": "1:11:39", "throughput": 2853.53, "total_tokens": 12693264} {"current_steps": 19410, "total_steps": 38160, "loss": 0.0718, "lr": 2.8598404825875113e-05, "epoch": 10.172955974842766, "percentage": 50.86, "elapsed_time": "1:14:09", "remaining_time": "1:11:38", "throughput": 2853.42, "total_tokens": 12695888} {"current_steps": 19415, "total_steps": 38160, "loss": 0.0692, "lr": 2.8587089230510604e-05, "epoch": 10.175576519916143, "percentage": 50.88, "elapsed_time": "1:14:10", "remaining_time": "1:11:36", "throughput": 2853.47, "total_tokens": 12699216} {"current_steps": 19420, "total_steps": 38160, "loss": 0.0819, "lr": 2.857577288476795e-05, "epoch": 10.178197064989519, "percentage": 50.89, "elapsed_time": "1:14:11", "remaining_time": "1:11:35", "throughput": 2853.68, "total_tokens": 12703344} {"current_steps": 19425, "total_steps": 38160, "loss": 0.0856, "lr": 2.85644557910144e-05, "epoch": 10.180817610062894, "percentage": 50.9, "elapsed_time": "1:14:12", "remaining_time": "1:11:34", "throughput": 2853.69, "total_tokens": 12706480} {"current_steps": 19430, "total_steps": 38160, "loss": 0.0844, "lr": 2.8553137951617366e-05, "epoch": 10.183438155136269, "percentage": 50.92, "elapsed_time": "1:14:13", "remaining_time": "1:11:33", "throughput": 2853.76, "total_tokens": 12709744} {"current_steps": 19435, "total_steps": 38160, "loss": 0.0999, "lr": 2.854181936894441e-05, "epoch": 10.186058700209644, "percentage": 50.93, "elapsed_time": "1:14:14", "remaining_time": "1:11:32", "throughput": 2853.77, "total_tokens": 12712816} {"current_steps": 19440, "total_steps": 38160, "loss": 0.0831, "lr": 2.8530500045363247e-05, "epoch": 10.18867924528302, "percentage": 50.94, "elapsed_time": "1:14:15", "remaining_time": "1:11:30", "throughput": 2853.84, "total_tokens": 12716304} {"current_steps": 19445, "total_steps": 38160, "loss": 0.0841, "lr": 2.851917998324175e-05, "epoch": 10.191299790356394, "percentage": 50.96, "elapsed_time": "1:14:16", "remaining_time": "1:11:29", "throughput": 2853.8, "total_tokens": 12719216} {"current_steps": 19450, "total_steps": 38160, "loss": 0.1252, "lr": 2.8507859184947957e-05, "epoch": 10.19392033542977, "percentage": 50.97, "elapsed_time": "1:14:18", "remaining_time": "1:11:28", "throughput": 2853.95, "total_tokens": 12723312} {"current_steps": 19455, "total_steps": 38160, "loss": 0.087, "lr": 2.8496537652850043e-05, "epoch": 10.196540880503145, "percentage": 50.98, "elapsed_time": "1:14:19", "remaining_time": "1:11:27", "throughput": 2853.94, "total_tokens": 12726320} {"current_steps": 19460, "total_steps": 38160, "loss": 0.1111, "lr": 2.8485215389316333e-05, "epoch": 10.19916142557652, "percentage": 51.0, "elapsed_time": "1:14:20", "remaining_time": "1:11:26", "throughput": 2854.1, "total_tokens": 12730128} {"current_steps": 19465, "total_steps": 38160, "loss": 0.192, "lr": 2.8473892396715328e-05, "epoch": 10.201781970649895, "percentage": 51.01, "elapsed_time": "1:14:21", "remaining_time": "1:11:25", "throughput": 2854.32, "total_tokens": 12735024} {"current_steps": 19470, "total_steps": 38160, "loss": 0.0561, "lr": 2.846256867741567e-05, "epoch": 10.20440251572327, "percentage": 51.02, "elapsed_time": "1:14:22", "remaining_time": "1:11:23", "throughput": 2854.28, "total_tokens": 12737872} {"current_steps": 19475, "total_steps": 38160, "loss": 0.1424, "lr": 2.845124423378614e-05, "epoch": 10.207023060796645, "percentage": 51.04, "elapsed_time": "1:14:23", "remaining_time": "1:11:22", "throughput": 2854.12, "total_tokens": 12740400} {"current_steps": 19480, "total_steps": 38160, "loss": 0.0608, "lr": 2.8439919068195697e-05, "epoch": 10.20964360587002, "percentage": 51.05, "elapsed_time": "1:14:24", "remaining_time": "1:11:21", "throughput": 2854.13, "total_tokens": 12743664} {"current_steps": 19485, "total_steps": 38160, "loss": 0.1525, "lr": 2.842859318301343e-05, "epoch": 10.212264150943396, "percentage": 51.06, "elapsed_time": "1:14:26", "remaining_time": "1:11:20", "throughput": 2854.09, "total_tokens": 12746512} {"current_steps": 19490, "total_steps": 38160, "loss": 0.0716, "lr": 2.841726658060858e-05, "epoch": 10.214884696016771, "percentage": 51.07, "elapsed_time": "1:14:27", "remaining_time": "1:11:19", "throughput": 2854.2, "total_tokens": 12750160} {"current_steps": 19495, "total_steps": 38160, "loss": 0.1011, "lr": 2.8405939263350555e-05, "epoch": 10.217505241090146, "percentage": 51.09, "elapsed_time": "1:14:28", "remaining_time": "1:11:18", "throughput": 2854.24, "total_tokens": 12753520} {"current_steps": 19500, "total_steps": 38160, "loss": 0.1172, "lr": 2.8394611233608886e-05, "epoch": 10.220125786163521, "percentage": 51.1, "elapsed_time": "1:14:29", "remaining_time": "1:11:16", "throughput": 2854.21, "total_tokens": 12756624} {"current_steps": 19505, "total_steps": 38160, "loss": 0.0897, "lr": 2.8383282493753283e-05, "epoch": 10.222746331236896, "percentage": 51.11, "elapsed_time": "1:14:30", "remaining_time": "1:11:15", "throughput": 2854.03, "total_tokens": 12759248} {"current_steps": 19510, "total_steps": 38160, "loss": 0.0915, "lr": 2.8371953046153575e-05, "epoch": 10.225366876310272, "percentage": 51.13, "elapsed_time": "1:14:31", "remaining_time": "1:11:14", "throughput": 2854.02, "total_tokens": 12762384} {"current_steps": 19515, "total_steps": 38160, "loss": 0.1301, "lr": 2.8360622893179757e-05, "epoch": 10.227987421383649, "percentage": 51.14, "elapsed_time": "1:14:33", "remaining_time": "1:11:13", "throughput": 2854.06, "total_tokens": 12766224} {"current_steps": 19520, "total_steps": 38160, "loss": 0.0785, "lr": 2.834929203720197e-05, "epoch": 10.230607966457024, "percentage": 51.15, "elapsed_time": "1:14:34", "remaining_time": "1:11:12", "throughput": 2853.97, "total_tokens": 12768912} {"current_steps": 19525, "total_steps": 38160, "loss": 0.0834, "lr": 2.83379604805905e-05, "epoch": 10.233228511530399, "percentage": 51.17, "elapsed_time": "1:14:35", "remaining_time": "1:11:11", "throughput": 2854.02, "total_tokens": 12772336} {"current_steps": 19530, "total_steps": 38160, "loss": 0.0729, "lr": 2.832662822571578e-05, "epoch": 10.235849056603774, "percentage": 51.18, "elapsed_time": "1:14:36", "remaining_time": "1:11:10", "throughput": 2853.89, "total_tokens": 12775216} {"current_steps": 19535, "total_steps": 38160, "loss": 0.0867, "lr": 2.8315295274948395e-05, "epoch": 10.23846960167715, "percentage": 51.19, "elapsed_time": "1:14:37", "remaining_time": "1:11:09", "throughput": 2853.86, "total_tokens": 12778512} {"current_steps": 19540, "total_steps": 38160, "loss": 0.0724, "lr": 2.8303961630659047e-05, "epoch": 10.241090146750524, "percentage": 51.21, "elapsed_time": "1:14:38", "remaining_time": "1:11:07", "throughput": 2854.02, "total_tokens": 12782576} {"current_steps": 19545, "total_steps": 38160, "loss": 0.0847, "lr": 2.8292627295218627e-05, "epoch": 10.2437106918239, "percentage": 51.22, "elapsed_time": "1:14:39", "remaining_time": "1:11:06", "throughput": 2854.01, "total_tokens": 12785584} {"current_steps": 19550, "total_steps": 38160, "loss": 0.0842, "lr": 2.828129227099815e-05, "epoch": 10.246331236897275, "percentage": 51.23, "elapsed_time": "1:14:40", "remaining_time": "1:11:05", "throughput": 2853.98, "total_tokens": 12788432} {"current_steps": 19555, "total_steps": 38160, "loss": 0.1756, "lr": 2.826995656036875e-05, "epoch": 10.24895178197065, "percentage": 51.24, "elapsed_time": "1:14:41", "remaining_time": "1:11:04", "throughput": 2853.93, "total_tokens": 12791312} {"current_steps": 19560, "total_steps": 38160, "loss": 0.0683, "lr": 2.8258620165701747e-05, "epoch": 10.251572327044025, "percentage": 51.26, "elapsed_time": "1:14:43", "remaining_time": "1:11:03", "throughput": 2854.01, "total_tokens": 12795120} {"current_steps": 19565, "total_steps": 38160, "loss": 0.0746, "lr": 2.8247283089368586e-05, "epoch": 10.2541928721174, "percentage": 51.27, "elapsed_time": "1:14:44", "remaining_time": "1:11:01", "throughput": 2853.98, "total_tokens": 12798032} {"current_steps": 19570, "total_steps": 38160, "loss": 0.0685, "lr": 2.8235945333740842e-05, "epoch": 10.256813417190775, "percentage": 51.28, "elapsed_time": "1:14:45", "remaining_time": "1:11:00", "throughput": 2853.84, "total_tokens": 12800688} {"current_steps": 19575, "total_steps": 38160, "loss": 0.12, "lr": 2.822460690119026e-05, "epoch": 10.25943396226415, "percentage": 51.3, "elapsed_time": "1:14:46", "remaining_time": "1:10:59", "throughput": 2853.91, "total_tokens": 12804240} {"current_steps": 19580, "total_steps": 38160, "loss": 0.171, "lr": 2.82132677940887e-05, "epoch": 10.262054507337526, "percentage": 51.31, "elapsed_time": "1:14:47", "remaining_time": "1:10:58", "throughput": 2853.89, "total_tokens": 12807216} {"current_steps": 19585, "total_steps": 38160, "loss": 0.0736, "lr": 2.820192801480817e-05, "epoch": 10.264675052410901, "percentage": 51.32, "elapsed_time": "1:14:48", "remaining_time": "1:10:57", "throughput": 2853.91, "total_tokens": 12810352} {"current_steps": 19590, "total_steps": 38160, "loss": 0.1012, "lr": 2.8190587565720842e-05, "epoch": 10.267295597484276, "percentage": 51.34, "elapsed_time": "1:14:49", "remaining_time": "1:10:56", "throughput": 2853.88, "total_tokens": 12813328} {"current_steps": 19595, "total_steps": 38160, "loss": 0.0934, "lr": 2.8179246449198986e-05, "epoch": 10.269916142557651, "percentage": 51.35, "elapsed_time": "1:14:50", "remaining_time": "1:10:54", "throughput": 2853.86, "total_tokens": 12816336} {"current_steps": 19600, "total_steps": 38160, "loss": 0.1229, "lr": 2.8167904667615048e-05, "epoch": 10.272536687631026, "percentage": 51.36, "elapsed_time": "1:14:52", "remaining_time": "1:10:53", "throughput": 2854.03, "total_tokens": 12820624} {"current_steps": 19605, "total_steps": 38160, "loss": 0.0892, "lr": 2.8156562223341592e-05, "epoch": 10.275157232704402, "percentage": 51.38, "elapsed_time": "1:14:53", "remaining_time": "1:10:52", "throughput": 2854.09, "total_tokens": 12824176} {"current_steps": 19610, "total_steps": 38160, "loss": 0.0811, "lr": 2.814521911875133e-05, "epoch": 10.277777777777779, "percentage": 51.39, "elapsed_time": "1:14:54", "remaining_time": "1:10:51", "throughput": 2854.11, "total_tokens": 12827376} {"current_steps": 19615, "total_steps": 38160, "loss": 0.0606, "lr": 2.8133875356217114e-05, "epoch": 10.280398322851154, "percentage": 51.4, "elapsed_time": "1:14:55", "remaining_time": "1:10:50", "throughput": 2854.18, "total_tokens": 12830704} {"current_steps": 19620, "total_steps": 38160, "loss": 0.1176, "lr": 2.8122530938111923e-05, "epoch": 10.283018867924529, "percentage": 51.42, "elapsed_time": "1:14:56", "remaining_time": "1:10:49", "throughput": 2854.11, "total_tokens": 12833616} {"current_steps": 19625, "total_steps": 38160, "loss": 0.1007, "lr": 2.8111185866808888e-05, "epoch": 10.285639412997904, "percentage": 51.43, "elapsed_time": "1:14:57", "remaining_time": "1:10:47", "throughput": 2854.11, "total_tokens": 12836688} {"current_steps": 19630, "total_steps": 38160, "loss": 0.0996, "lr": 2.809984014468126e-05, "epoch": 10.28825995807128, "percentage": 51.44, "elapsed_time": "1:14:58", "remaining_time": "1:10:46", "throughput": 2854.3, "total_tokens": 12840656} {"current_steps": 19635, "total_steps": 38160, "loss": 0.0956, "lr": 2.8088493774102443e-05, "epoch": 10.290880503144654, "percentage": 51.45, "elapsed_time": "1:14:59", "remaining_time": "1:10:45", "throughput": 2854.24, "total_tokens": 12843408} {"current_steps": 19640, "total_steps": 38160, "loss": 0.1239, "lr": 2.807714675744596e-05, "epoch": 10.29350104821803, "percentage": 51.47, "elapsed_time": "1:15:00", "remaining_time": "1:10:44", "throughput": 2854.18, "total_tokens": 12846224} {"current_steps": 19645, "total_steps": 38160, "loss": 0.109, "lr": 2.8065799097085475e-05, "epoch": 10.296121593291405, "percentage": 51.48, "elapsed_time": "1:15:02", "remaining_time": "1:10:43", "throughput": 2854.32, "total_tokens": 12850288} {"current_steps": 19650, "total_steps": 38160, "loss": 0.1149, "lr": 2.8054450795394804e-05, "epoch": 10.29874213836478, "percentage": 51.49, "elapsed_time": "1:15:03", "remaining_time": "1:10:41", "throughput": 2854.33, "total_tokens": 12853424} {"current_steps": 19655, "total_steps": 38160, "loss": 0.0935, "lr": 2.8043101854747878e-05, "epoch": 10.301362683438155, "percentage": 51.51, "elapsed_time": "1:15:04", "remaining_time": "1:10:40", "throughput": 2854.35, "total_tokens": 12856656} {"current_steps": 19660, "total_steps": 38160, "loss": 0.1111, "lr": 2.8031752277518748e-05, "epoch": 10.30398322851153, "percentage": 51.52, "elapsed_time": "1:15:05", "remaining_time": "1:10:39", "throughput": 2854.26, "total_tokens": 12859248} {"current_steps": 19665, "total_steps": 38160, "loss": 0.1158, "lr": 2.802040206608164e-05, "epoch": 10.306603773584905, "percentage": 51.53, "elapsed_time": "1:15:06", "remaining_time": "1:10:38", "throughput": 2854.23, "total_tokens": 12862160} {"current_steps": 19670, "total_steps": 38160, "loss": 0.0885, "lr": 2.8009051222810877e-05, "epoch": 10.30922431865828, "percentage": 51.55, "elapsed_time": "1:15:07", "remaining_time": "1:10:37", "throughput": 2854.01, "total_tokens": 12864304} {"current_steps": 19675, "total_steps": 38160, "loss": 0.114, "lr": 2.7997699750080918e-05, "epoch": 10.311844863731656, "percentage": 51.56, "elapsed_time": "1:15:08", "remaining_time": "1:10:35", "throughput": 2854.23, "total_tokens": 12868752} {"current_steps": 19680, "total_steps": 38160, "loss": 0.0578, "lr": 2.7986347650266386e-05, "epoch": 10.314465408805031, "percentage": 51.57, "elapsed_time": "1:15:09", "remaining_time": "1:10:34", "throughput": 2854.27, "total_tokens": 12872112} {"current_steps": 19685, "total_steps": 38160, "loss": 0.0848, "lr": 2.797499492574199e-05, "epoch": 10.317085953878406, "percentage": 51.59, "elapsed_time": "1:15:10", "remaining_time": "1:10:33", "throughput": 2854.16, "total_tokens": 12874576} {"current_steps": 19690, "total_steps": 38160, "loss": 0.0879, "lr": 2.7963641578882594e-05, "epoch": 10.319706498951781, "percentage": 51.6, "elapsed_time": "1:15:11", "remaining_time": "1:10:32", "throughput": 2854.09, "total_tokens": 12877232} {"current_steps": 19695, "total_steps": 38160, "loss": 0.1049, "lr": 2.7952287612063193e-05, "epoch": 10.322327044025156, "percentage": 51.61, "elapsed_time": "1:15:12", "remaining_time": "1:10:31", "throughput": 2854.17, "total_tokens": 12880656} {"current_steps": 19700, "total_steps": 38160, "loss": 0.0833, "lr": 2.79409330276589e-05, "epoch": 10.324947589098532, "percentage": 51.62, "elapsed_time": "1:15:13", "remaining_time": "1:10:29", "throughput": 2854.13, "total_tokens": 12883472} {"current_steps": 19705, "total_steps": 38160, "loss": 0.1178, "lr": 2.7929577828044974e-05, "epoch": 10.327568134171909, "percentage": 51.64, "elapsed_time": "1:15:15", "remaining_time": "1:10:28", "throughput": 2853.93, "total_tokens": 12885776} {"current_steps": 19710, "total_steps": 38160, "loss": 0.0884, "lr": 2.7918222015596784e-05, "epoch": 10.330188679245284, "percentage": 51.65, "elapsed_time": "1:15:16", "remaining_time": "1:10:27", "throughput": 2853.89, "total_tokens": 12888688} {"current_steps": 19715, "total_steps": 38160, "loss": 0.0942, "lr": 2.7906865592689847e-05, "epoch": 10.332809224318659, "percentage": 51.66, "elapsed_time": "1:15:17", "remaining_time": "1:10:26", "throughput": 2853.83, "total_tokens": 12891664} {"current_steps": 19720, "total_steps": 38160, "loss": 0.1011, "lr": 2.789550856169979e-05, "epoch": 10.335429769392034, "percentage": 51.68, "elapsed_time": "1:15:18", "remaining_time": "1:10:25", "throughput": 2853.84, "total_tokens": 12894832} {"current_steps": 19725, "total_steps": 38160, "loss": 0.0668, "lr": 2.7884150925002374e-05, "epoch": 10.33805031446541, "percentage": 51.69, "elapsed_time": "1:15:19", "remaining_time": "1:10:23", "throughput": 2853.82, "total_tokens": 12897744} {"current_steps": 19730, "total_steps": 38160, "loss": 0.1562, "lr": 2.787279268497349e-05, "epoch": 10.340670859538784, "percentage": 51.7, "elapsed_time": "1:15:20", "remaining_time": "1:10:22", "throughput": 2853.89, "total_tokens": 12901008} {"current_steps": 19735, "total_steps": 38160, "loss": 0.0792, "lr": 2.786143384398915e-05, "epoch": 10.34329140461216, "percentage": 51.72, "elapsed_time": "1:15:21", "remaining_time": "1:10:21", "throughput": 2853.8, "total_tokens": 12903792} {"current_steps": 19740, "total_steps": 38160, "loss": 0.0932, "lr": 2.785007440442549e-05, "epoch": 10.345911949685535, "percentage": 51.73, "elapsed_time": "1:15:22", "remaining_time": "1:10:20", "throughput": 2853.87, "total_tokens": 12907120} {"current_steps": 19745, "total_steps": 38160, "loss": 0.1459, "lr": 2.7838714368658785e-05, "epoch": 10.34853249475891, "percentage": 51.74, "elapsed_time": "1:15:23", "remaining_time": "1:10:19", "throughput": 2853.88, "total_tokens": 12910320} {"current_steps": 19750, "total_steps": 38160, "loss": 0.0668, "lr": 2.7827353739065427e-05, "epoch": 10.351153039832285, "percentage": 51.76, "elapsed_time": "1:15:24", "remaining_time": "1:10:17", "throughput": 2853.82, "total_tokens": 12913008} {"current_steps": 19755, "total_steps": 38160, "loss": 0.1214, "lr": 2.781599251802191e-05, "epoch": 10.35377358490566, "percentage": 51.77, "elapsed_time": "1:15:25", "remaining_time": "1:10:16", "throughput": 2853.92, "total_tokens": 12916432} {"current_steps": 19760, "total_steps": 38160, "loss": 0.1104, "lr": 2.780463070790489e-05, "epoch": 10.356394129979035, "percentage": 51.78, "elapsed_time": "1:15:26", "remaining_time": "1:10:15", "throughput": 2853.95, "total_tokens": 12919536} {"current_steps": 19765, "total_steps": 38160, "loss": 0.0879, "lr": 2.7793268311091125e-05, "epoch": 10.35901467505241, "percentage": 51.8, "elapsed_time": "1:15:28", "remaining_time": "1:10:14", "throughput": 2853.96, "total_tokens": 12922768} {"current_steps": 19770, "total_steps": 38160, "loss": 0.0758, "lr": 2.7781905329957496e-05, "epoch": 10.361635220125786, "percentage": 51.81, "elapsed_time": "1:15:29", "remaining_time": "1:10:13", "throughput": 2853.92, "total_tokens": 12925840} {"current_steps": 19775, "total_steps": 38160, "loss": 0.112, "lr": 2.7770541766881008e-05, "epoch": 10.364255765199161, "percentage": 51.82, "elapsed_time": "1:15:30", "remaining_time": "1:10:11", "throughput": 2853.87, "total_tokens": 12928656} {"current_steps": 19780, "total_steps": 38160, "loss": 0.0954, "lr": 2.7759177624238786e-05, "epoch": 10.366876310272536, "percentage": 51.83, "elapsed_time": "1:15:31", "remaining_time": "1:10:10", "throughput": 2853.85, "total_tokens": 12931504} {"current_steps": 19785, "total_steps": 38160, "loss": 0.0968, "lr": 2.7747812904408094e-05, "epoch": 10.369496855345911, "percentage": 51.85, "elapsed_time": "1:15:32", "remaining_time": "1:10:09", "throughput": 2853.91, "total_tokens": 12935056} {"current_steps": 19790, "total_steps": 38160, "loss": 0.1059, "lr": 2.7736447609766286e-05, "epoch": 10.372117400419286, "percentage": 51.86, "elapsed_time": "1:15:33", "remaining_time": "1:10:08", "throughput": 2853.9, "total_tokens": 12938064} {"current_steps": 19795, "total_steps": 38160, "loss": 0.1172, "lr": 2.772508174269085e-05, "epoch": 10.374737945492662, "percentage": 51.87, "elapsed_time": "1:15:34", "remaining_time": "1:10:06", "throughput": 2853.97, "total_tokens": 12941456} {"current_steps": 19800, "total_steps": 38160, "loss": 0.0988, "lr": 2.7713715305559414e-05, "epoch": 10.377358490566039, "percentage": 51.89, "elapsed_time": "1:15:35", "remaining_time": "1:10:05", "throughput": 2854.02, "total_tokens": 12945232} {"current_steps": 19805, "total_steps": 38160, "loss": 0.1028, "lr": 2.7702348300749692e-05, "epoch": 10.379979035639414, "percentage": 51.9, "elapsed_time": "1:15:36", "remaining_time": "1:10:04", "throughput": 2853.89, "total_tokens": 12947760} {"current_steps": 19810, "total_steps": 38160, "loss": 0.0822, "lr": 2.7690980730639533e-05, "epoch": 10.382599580712789, "percentage": 51.91, "elapsed_time": "1:15:37", "remaining_time": "1:10:03", "throughput": 2853.99, "total_tokens": 12951216} {"current_steps": 19815, "total_steps": 38160, "loss": 0.0893, "lr": 2.7679612597606902e-05, "epoch": 10.385220125786164, "percentage": 51.93, "elapsed_time": "1:15:38", "remaining_time": "1:10:02", "throughput": 2854.08, "total_tokens": 12954544} {"current_steps": 19820, "total_steps": 38160, "loss": 0.1712, "lr": 2.7668243904029894e-05, "epoch": 10.38784067085954, "percentage": 51.94, "elapsed_time": "1:15:40", "remaining_time": "1:10:01", "throughput": 2854.34, "total_tokens": 12959568} {"current_steps": 19825, "total_steps": 38160, "loss": 0.0924, "lr": 2.76568746522867e-05, "epoch": 10.390461215932914, "percentage": 51.95, "elapsed_time": "1:15:41", "remaining_time": "1:10:00", "throughput": 2854.41, "total_tokens": 12962992} {"current_steps": 19830, "total_steps": 38160, "loss": 0.1136, "lr": 2.7645504844755637e-05, "epoch": 10.39308176100629, "percentage": 51.97, "elapsed_time": "1:15:42", "remaining_time": "1:09:58", "throughput": 2854.52, "total_tokens": 12966608} {"current_steps": 19835, "total_steps": 38160, "loss": 0.1114, "lr": 2.7634134483815143e-05, "epoch": 10.395702306079665, "percentage": 51.98, "elapsed_time": "1:15:43", "remaining_time": "1:09:57", "throughput": 2854.53, "total_tokens": 12969744} {"current_steps": 19840, "total_steps": 38160, "loss": 0.1061, "lr": 2.762276357184377e-05, "epoch": 10.39832285115304, "percentage": 51.99, "elapsed_time": "1:15:44", "remaining_time": "1:09:56", "throughput": 2854.49, "total_tokens": 12972784} {"current_steps": 19845, "total_steps": 38160, "loss": 0.0878, "lr": 2.7611392111220176e-05, "epoch": 10.400943396226415, "percentage": 52.0, "elapsed_time": "1:15:45", "remaining_time": "1:09:55", "throughput": 2854.7, "total_tokens": 12976944} {"current_steps": 19850, "total_steps": 38160, "loss": 0.061, "lr": 2.7600020104323154e-05, "epoch": 10.40356394129979, "percentage": 52.02, "elapsed_time": "1:15:46", "remaining_time": "1:09:54", "throughput": 2854.72, "total_tokens": 12979984} {"current_steps": 19855, "total_steps": 38160, "loss": 0.098, "lr": 2.7588647553531576e-05, "epoch": 10.406184486373165, "percentage": 52.03, "elapsed_time": "1:15:47", "remaining_time": "1:09:52", "throughput": 2854.67, "total_tokens": 12982704} {"current_steps": 19860, "total_steps": 38160, "loss": 0.0843, "lr": 2.7577274461224463e-05, "epoch": 10.40880503144654, "percentage": 52.04, "elapsed_time": "1:15:48", "remaining_time": "1:09:51", "throughput": 2854.64, "total_tokens": 12985680} {"current_steps": 19865, "total_steps": 38160, "loss": 0.0883, "lr": 2.756590082978095e-05, "epoch": 10.411425576519916, "percentage": 52.06, "elapsed_time": "1:15:50", "remaining_time": "1:09:50", "throughput": 2854.7, "total_tokens": 12989200} {"current_steps": 19870, "total_steps": 38160, "loss": 0.1084, "lr": 2.7554526661580243e-05, "epoch": 10.414046121593291, "percentage": 52.07, "elapsed_time": "1:15:51", "remaining_time": "1:09:49", "throughput": 2854.79, "total_tokens": 12992560} {"current_steps": 19875, "total_steps": 38160, "loss": 0.0833, "lr": 2.7543151959001708e-05, "epoch": 10.416666666666666, "percentage": 52.08, "elapsed_time": "1:15:52", "remaining_time": "1:09:48", "throughput": 2854.76, "total_tokens": 12995472} {"current_steps": 19880, "total_steps": 38160, "loss": 0.1571, "lr": 2.7531776724424797e-05, "epoch": 10.419287211740041, "percentage": 52.1, "elapsed_time": "1:15:53", "remaining_time": "1:09:46", "throughput": 2854.82, "total_tokens": 12999024} {"current_steps": 19885, "total_steps": 38160, "loss": 0.119, "lr": 2.752040096022907e-05, "epoch": 10.421907756813416, "percentage": 52.11, "elapsed_time": "1:15:54", "remaining_time": "1:09:45", "throughput": 2854.76, "total_tokens": 13001744} {"current_steps": 19890, "total_steps": 38160, "loss": 0.0895, "lr": 2.750902466879423e-05, "epoch": 10.424528301886792, "percentage": 52.12, "elapsed_time": "1:15:55", "remaining_time": "1:09:44", "throughput": 2854.67, "total_tokens": 13004272} {"current_steps": 19895, "total_steps": 38160, "loss": 0.094, "lr": 2.7497647852500048e-05, "epoch": 10.427148846960169, "percentage": 52.14, "elapsed_time": "1:15:56", "remaining_time": "1:09:43", "throughput": 2854.66, "total_tokens": 13007472} {"current_steps": 19900, "total_steps": 38160, "loss": 0.1138, "lr": 2.7486270513726424e-05, "epoch": 10.429769392033544, "percentage": 52.15, "elapsed_time": "1:15:57", "remaining_time": "1:09:42", "throughput": 2854.81, "total_tokens": 13011120} {"current_steps": 19905, "total_steps": 38160, "loss": 0.0857, "lr": 2.7474892654853384e-05, "epoch": 10.432389937106919, "percentage": 52.16, "elapsed_time": "1:15:58", "remaining_time": "1:09:40", "throughput": 2854.74, "total_tokens": 13013872} {"current_steps": 19910, "total_steps": 38160, "loss": 0.0626, "lr": 2.7463514278261034e-05, "epoch": 10.435010482180294, "percentage": 52.18, "elapsed_time": "1:15:59", "remaining_time": "1:09:39", "throughput": 2854.69, "total_tokens": 13016592} {"current_steps": 19915, "total_steps": 38160, "loss": 0.0867, "lr": 2.7452135386329596e-05, "epoch": 10.43763102725367, "percentage": 52.19, "elapsed_time": "1:16:00", "remaining_time": "1:09:38", "throughput": 2854.72, "total_tokens": 13019888} {"current_steps": 19920, "total_steps": 38160, "loss": 0.1312, "lr": 2.7440755981439414e-05, "epoch": 10.440251572327044, "percentage": 52.2, "elapsed_time": "1:16:02", "remaining_time": "1:09:37", "throughput": 2854.81, "total_tokens": 13023664} {"current_steps": 19925, "total_steps": 38160, "loss": 0.1114, "lr": 2.7429376065970924e-05, "epoch": 10.44287211740042, "percentage": 52.21, "elapsed_time": "1:16:03", "remaining_time": "1:09:36", "throughput": 2854.85, "total_tokens": 13027152} {"current_steps": 19930, "total_steps": 38160, "loss": 0.0806, "lr": 2.7417995642304678e-05, "epoch": 10.445492662473795, "percentage": 52.23, "elapsed_time": "1:16:04", "remaining_time": "1:09:34", "throughput": 2854.85, "total_tokens": 13030160} {"current_steps": 19935, "total_steps": 38160, "loss": 0.0905, "lr": 2.7406614712821333e-05, "epoch": 10.44811320754717, "percentage": 52.24, "elapsed_time": "1:16:05", "remaining_time": "1:09:33", "throughput": 2854.91, "total_tokens": 13034000} {"current_steps": 19940, "total_steps": 38160, "loss": 0.0607, "lr": 2.739523327990164e-05, "epoch": 10.450733752620545, "percentage": 52.25, "elapsed_time": "1:16:06", "remaining_time": "1:09:32", "throughput": 2854.98, "total_tokens": 13037392} {"current_steps": 19945, "total_steps": 38160, "loss": 0.1144, "lr": 2.7383851345926477e-05, "epoch": 10.45335429769392, "percentage": 52.27, "elapsed_time": "1:16:07", "remaining_time": "1:09:31", "throughput": 2854.98, "total_tokens": 13040496} {"current_steps": 19950, "total_steps": 38160, "loss": 0.1435, "lr": 2.7372468913276804e-05, "epoch": 10.455974842767295, "percentage": 52.28, "elapsed_time": "1:16:08", "remaining_time": "1:09:30", "throughput": 2854.94, "total_tokens": 13043248} {"current_steps": 19955, "total_steps": 38160, "loss": 0.0662, "lr": 2.7361085984333705e-05, "epoch": 10.45859538784067, "percentage": 52.29, "elapsed_time": "1:16:09", "remaining_time": "1:09:28", "throughput": 2854.99, "total_tokens": 13046512} {"current_steps": 19960, "total_steps": 38160, "loss": 0.1128, "lr": 2.7349702561478356e-05, "epoch": 10.461215932914046, "percentage": 52.31, "elapsed_time": "1:16:10", "remaining_time": "1:09:27", "throughput": 2855.01, "total_tokens": 13049616} {"current_steps": 19965, "total_steps": 38160, "loss": 0.0671, "lr": 2.733831864709203e-05, "epoch": 10.463836477987421, "percentage": 52.32, "elapsed_time": "1:16:11", "remaining_time": "1:09:26", "throughput": 2854.9, "total_tokens": 13052048} {"current_steps": 19970, "total_steps": 38160, "loss": 0.0826, "lr": 2.732693424355613e-05, "epoch": 10.466457023060796, "percentage": 52.33, "elapsed_time": "1:16:12", "remaining_time": "1:09:25", "throughput": 2854.7, "total_tokens": 13054096} {"current_steps": 19975, "total_steps": 38160, "loss": 0.0671, "lr": 2.731554935325213e-05, "epoch": 10.469077568134171, "percentage": 52.35, "elapsed_time": "1:16:13", "remaining_time": "1:09:24", "throughput": 2854.75, "total_tokens": 13057488} {"current_steps": 19980, "total_steps": 38160, "loss": 0.0757, "lr": 2.7304163978561613e-05, "epoch": 10.471698113207546, "percentage": 52.36, "elapsed_time": "1:16:15", "remaining_time": "1:09:22", "throughput": 2854.71, "total_tokens": 13060336} {"current_steps": 19985, "total_steps": 38160, "loss": 0.1144, "lr": 2.729277812186629e-05, "epoch": 10.474318658280922, "percentage": 52.37, "elapsed_time": "1:16:16", "remaining_time": "1:09:21", "throughput": 2854.77, "total_tokens": 13063728} {"current_steps": 19990, "total_steps": 38160, "loss": 0.0924, "lr": 2.7281391785547945e-05, "epoch": 10.476939203354299, "percentage": 52.38, "elapsed_time": "1:16:17", "remaining_time": "1:09:20", "throughput": 2854.68, "total_tokens": 13066256} {"current_steps": 19995, "total_steps": 38160, "loss": 0.101, "lr": 2.7270004971988456e-05, "epoch": 10.479559748427674, "percentage": 52.4, "elapsed_time": "1:16:18", "remaining_time": "1:09:19", "throughput": 2854.72, "total_tokens": 13069424} {"current_steps": 20000, "total_steps": 38160, "loss": 0.0641, "lr": 2.7258617683569825e-05, "epoch": 10.482180293501049, "percentage": 52.41, "elapsed_time": "1:16:19", "remaining_time": "1:09:17", "throughput": 2854.76, "total_tokens": 13072560} {"current_steps": 20005, "total_steps": 38160, "loss": 0.1097, "lr": 2.7247229922674143e-05, "epoch": 10.484800838574424, "percentage": 52.42, "elapsed_time": "1:16:20", "remaining_time": "1:09:16", "throughput": 2854.9, "total_tokens": 13076176} {"current_steps": 20010, "total_steps": 38160, "loss": 0.0988, "lr": 2.7235841691683605e-05, "epoch": 10.4874213836478, "percentage": 52.44, "elapsed_time": "1:16:21", "remaining_time": "1:09:15", "throughput": 2855.06, "total_tokens": 13079984} {"current_steps": 20015, "total_steps": 38160, "loss": 0.0677, "lr": 2.7224452992980487e-05, "epoch": 10.490041928721174, "percentage": 52.45, "elapsed_time": "1:16:22", "remaining_time": "1:09:14", "throughput": 2855.04, "total_tokens": 13082928} {"current_steps": 20020, "total_steps": 38160, "loss": 0.1116, "lr": 2.7213063828947182e-05, "epoch": 10.49266247379455, "percentage": 52.46, "elapsed_time": "1:16:23", "remaining_time": "1:09:13", "throughput": 2855.02, "total_tokens": 13085776} {"current_steps": 20025, "total_steps": 38160, "loss": 0.1028, "lr": 2.7201674201966176e-05, "epoch": 10.495283018867925, "percentage": 52.48, "elapsed_time": "1:16:24", "remaining_time": "1:09:11", "throughput": 2854.98, "total_tokens": 13088656} {"current_steps": 20030, "total_steps": 38160, "loss": 0.119, "lr": 2.7190284114420035e-05, "epoch": 10.4979035639413, "percentage": 52.49, "elapsed_time": "1:16:25", "remaining_time": "1:09:10", "throughput": 2855.0, "total_tokens": 13091728} {"current_steps": 20035, "total_steps": 38160, "loss": 0.1402, "lr": 2.717889356869146e-05, "epoch": 10.500524109014675, "percentage": 52.5, "elapsed_time": "1:16:26", "remaining_time": "1:09:09", "throughput": 2855.23, "total_tokens": 13096048} {"current_steps": 20040, "total_steps": 38160, "loss": 0.1736, "lr": 2.7167502567163194e-05, "epoch": 10.50314465408805, "percentage": 52.52, "elapsed_time": "1:16:27", "remaining_time": "1:09:08", "throughput": 2855.14, "total_tokens": 13098608} {"current_steps": 20045, "total_steps": 38160, "loss": 0.0508, "lr": 2.715611111221813e-05, "epoch": 10.505765199161425, "percentage": 52.53, "elapsed_time": "1:16:28", "remaining_time": "1:09:06", "throughput": 2855.19, "total_tokens": 13101872} {"current_steps": 20050, "total_steps": 38160, "loss": 0.1253, "lr": 2.7144719206239217e-05, "epoch": 10.5083857442348, "percentage": 52.54, "elapsed_time": "1:16:30", "remaining_time": "1:09:06", "throughput": 2855.51, "total_tokens": 13109072} {"current_steps": 20055, "total_steps": 38160, "loss": 0.0776, "lr": 2.7133326851609508e-05, "epoch": 10.511006289308176, "percentage": 52.56, "elapsed_time": "1:16:31", "remaining_time": "1:09:05", "throughput": 2855.48, "total_tokens": 13112080} {"current_steps": 20060, "total_steps": 38160, "loss": 0.0748, "lr": 2.7121934050712166e-05, "epoch": 10.51362683438155, "percentage": 52.57, "elapsed_time": "1:16:33", "remaining_time": "1:09:04", "throughput": 2855.18, "total_tokens": 13114704} {"current_steps": 20065, "total_steps": 38160, "loss": 0.0894, "lr": 2.711054080593043e-05, "epoch": 10.516247379454926, "percentage": 52.58, "elapsed_time": "1:16:34", "remaining_time": "1:09:03", "throughput": 2855.06, "total_tokens": 13117360} {"current_steps": 20070, "total_steps": 38160, "loss": 0.0807, "lr": 2.7099147119647627e-05, "epoch": 10.518867924528301, "percentage": 52.59, "elapsed_time": "1:16:35", "remaining_time": "1:09:02", "throughput": 2855.13, "total_tokens": 13121104} {"current_steps": 20075, "total_steps": 38160, "loss": 0.1016, "lr": 2.7087752994247206e-05, "epoch": 10.521488469601676, "percentage": 52.61, "elapsed_time": "1:16:36", "remaining_time": "1:09:01", "throughput": 2855.2, "total_tokens": 13124464} {"current_steps": 20080, "total_steps": 38160, "loss": 0.0822, "lr": 2.707635843211267e-05, "epoch": 10.524109014675052, "percentage": 52.62, "elapsed_time": "1:16:37", "remaining_time": "1:08:59", "throughput": 2855.1, "total_tokens": 13127024} {"current_steps": 20085, "total_steps": 38160, "loss": 0.0973, "lr": 2.7064963435627637e-05, "epoch": 10.526729559748428, "percentage": 52.63, "elapsed_time": "1:16:38", "remaining_time": "1:08:58", "throughput": 2855.05, "total_tokens": 13129936} {"current_steps": 20090, "total_steps": 38160, "loss": 0.1331, "lr": 2.7053568007175823e-05, "epoch": 10.529350104821804, "percentage": 52.65, "elapsed_time": "1:16:39", "remaining_time": "1:08:57", "throughput": 2854.99, "total_tokens": 13132656} {"current_steps": 20095, "total_steps": 38160, "loss": 0.1417, "lr": 2.7042172149140994e-05, "epoch": 10.531970649895179, "percentage": 52.66, "elapsed_time": "1:16:40", "remaining_time": "1:08:56", "throughput": 2855.16, "total_tokens": 13136528} {"current_steps": 20100, "total_steps": 38160, "loss": 0.0678, "lr": 2.703077586390706e-05, "epoch": 10.534591194968554, "percentage": 52.67, "elapsed_time": "1:16:42", "remaining_time": "1:08:54", "throughput": 2855.15, "total_tokens": 13139568} {"current_steps": 20105, "total_steps": 38160, "loss": 0.0784, "lr": 2.7019379153857982e-05, "epoch": 10.53721174004193, "percentage": 52.69, "elapsed_time": "1:16:43", "remaining_time": "1:08:53", "throughput": 2855.14, "total_tokens": 13142704} {"current_steps": 20110, "total_steps": 38160, "loss": 0.095, "lr": 2.700798202137782e-05, "epoch": 10.539832285115304, "percentage": 52.7, "elapsed_time": "1:16:44", "remaining_time": "1:08:52", "throughput": 2855.15, "total_tokens": 13145936} {"current_steps": 20115, "total_steps": 38160, "loss": 0.1388, "lr": 2.6996584468850732e-05, "epoch": 10.54245283018868, "percentage": 52.71, "elapsed_time": "1:16:45", "remaining_time": "1:08:51", "throughput": 2855.23, "total_tokens": 13149360} {"current_steps": 20120, "total_steps": 38160, "loss": 0.1041, "lr": 2.6985186498660946e-05, "epoch": 10.545073375262055, "percentage": 52.73, "elapsed_time": "1:16:46", "remaining_time": "1:08:50", "throughput": 2855.13, "total_tokens": 13151920} {"current_steps": 20125, "total_steps": 38160, "loss": 0.1314, "lr": 2.69737881131928e-05, "epoch": 10.54769392033543, "percentage": 52.74, "elapsed_time": "1:16:47", "remaining_time": "1:08:48", "throughput": 2855.15, "total_tokens": 13155024} {"current_steps": 20130, "total_steps": 38160, "loss": 0.1333, "lr": 2.6962389314830692e-05, "epoch": 10.550314465408805, "percentage": 52.75, "elapsed_time": "1:16:48", "remaining_time": "1:08:47", "throughput": 2855.17, "total_tokens": 13158320} {"current_steps": 20135, "total_steps": 38160, "loss": 0.0676, "lr": 2.6950990105959135e-05, "epoch": 10.55293501048218, "percentage": 52.76, "elapsed_time": "1:16:49", "remaining_time": "1:08:46", "throughput": 2855.11, "total_tokens": 13161040} {"current_steps": 20140, "total_steps": 38160, "loss": 0.0904, "lr": 2.6939590488962703e-05, "epoch": 10.555555555555555, "percentage": 52.78, "elapsed_time": "1:16:50", "remaining_time": "1:08:45", "throughput": 2855.08, "total_tokens": 13163984} {"current_steps": 20145, "total_steps": 38160, "loss": 0.138, "lr": 2.6928190466226067e-05, "epoch": 10.55817610062893, "percentage": 52.79, "elapsed_time": "1:16:51", "remaining_time": "1:08:44", "throughput": 2855.2, "total_tokens": 13167888} {"current_steps": 20150, "total_steps": 38160, "loss": 0.0832, "lr": 2.691679004013398e-05, "epoch": 10.560796645702306, "percentage": 52.8, "elapsed_time": "1:16:53", "remaining_time": "1:08:43", "throughput": 2855.23, "total_tokens": 13171312} {"current_steps": 20155, "total_steps": 38160, "loss": 0.0897, "lr": 2.6905389213071285e-05, "epoch": 10.56341719077568, "percentage": 52.82, "elapsed_time": "1:16:54", "remaining_time": "1:08:41", "throughput": 2855.19, "total_tokens": 13174192} {"current_steps": 20160, "total_steps": 38160, "loss": 0.1445, "lr": 2.6893987987422907e-05, "epoch": 10.566037735849056, "percentage": 52.83, "elapsed_time": "1:16:55", "remaining_time": "1:08:40", "throughput": 2855.41, "total_tokens": 13178736} {"current_steps": 20165, "total_steps": 38160, "loss": 0.0879, "lr": 2.6882586365573854e-05, "epoch": 10.568658280922431, "percentage": 52.84, "elapsed_time": "1:16:56", "remaining_time": "1:08:39", "throughput": 2855.33, "total_tokens": 13181392} {"current_steps": 20170, "total_steps": 38160, "loss": 0.1193, "lr": 2.6871184349909206e-05, "epoch": 10.571278825995806, "percentage": 52.86, "elapsed_time": "1:16:57", "remaining_time": "1:08:38", "throughput": 2855.34, "total_tokens": 13184496} {"current_steps": 20175, "total_steps": 38160, "loss": 0.1665, "lr": 2.685978194281414e-05, "epoch": 10.573899371069182, "percentage": 52.87, "elapsed_time": "1:16:58", "remaining_time": "1:08:37", "throughput": 2855.38, "total_tokens": 13187760} {"current_steps": 20180, "total_steps": 38160, "loss": 0.0987, "lr": 2.6848379146673914e-05, "epoch": 10.576519916142558, "percentage": 52.88, "elapsed_time": "1:16:59", "remaining_time": "1:08:36", "throughput": 2855.35, "total_tokens": 13190640} {"current_steps": 20185, "total_steps": 38160, "loss": 0.1002, "lr": 2.6836975963873843e-05, "epoch": 10.579140461215934, "percentage": 52.9, "elapsed_time": "1:17:00", "remaining_time": "1:08:34", "throughput": 2855.37, "total_tokens": 13193840} {"current_steps": 20190, "total_steps": 38160, "loss": 0.1067, "lr": 2.6825572396799377e-05, "epoch": 10.581761006289309, "percentage": 52.91, "elapsed_time": "1:17:01", "remaining_time": "1:08:33", "throughput": 2855.44, "total_tokens": 13197648} {"current_steps": 20195, "total_steps": 38160, "loss": 0.0634, "lr": 2.6814168447835986e-05, "epoch": 10.584381551362684, "percentage": 52.92, "elapsed_time": "1:17:03", "remaining_time": "1:08:32", "throughput": 2855.63, "total_tokens": 13201808} {"current_steps": 20200, "total_steps": 38160, "loss": 0.1845, "lr": 2.6802764119369245e-05, "epoch": 10.58700209643606, "percentage": 52.94, "elapsed_time": "1:17:04", "remaining_time": "1:08:31", "throughput": 2855.66, "total_tokens": 13204976} {"current_steps": 20205, "total_steps": 38160, "loss": 0.1274, "lr": 2.6791359413784828e-05, "epoch": 10.589622641509434, "percentage": 52.95, "elapsed_time": "1:17:05", "remaining_time": "1:08:30", "throughput": 2855.59, "total_tokens": 13207856} {"current_steps": 20210, "total_steps": 38160, "loss": 0.0925, "lr": 2.677995433346845e-05, "epoch": 10.59224318658281, "percentage": 52.96, "elapsed_time": "1:17:06", "remaining_time": "1:08:29", "throughput": 2855.53, "total_tokens": 13210768} {"current_steps": 20215, "total_steps": 38160, "loss": 0.1334, "lr": 2.6768548880805934e-05, "epoch": 10.594863731656185, "percentage": 52.97, "elapsed_time": "1:17:07", "remaining_time": "1:08:27", "throughput": 2855.53, "total_tokens": 13213776} {"current_steps": 20220, "total_steps": 38160, "loss": 0.2043, "lr": 2.6757143058183177e-05, "epoch": 10.59748427672956, "percentage": 52.99, "elapsed_time": "1:17:08", "remaining_time": "1:08:26", "throughput": 2855.58, "total_tokens": 13217104} {"current_steps": 20225, "total_steps": 38160, "loss": 0.0985, "lr": 2.6745736867986132e-05, "epoch": 10.600104821802935, "percentage": 53.0, "elapsed_time": "1:17:09", "remaining_time": "1:08:25", "throughput": 2855.54, "total_tokens": 13220048} {"current_steps": 20230, "total_steps": 38160, "loss": 0.1218, "lr": 2.673433031260085e-05, "epoch": 10.60272536687631, "percentage": 53.01, "elapsed_time": "1:17:10", "remaining_time": "1:08:24", "throughput": 2855.6, "total_tokens": 13223376} {"current_steps": 20235, "total_steps": 38160, "loss": 0.157, "lr": 2.6722923394413456e-05, "epoch": 10.605345911949685, "percentage": 53.03, "elapsed_time": "1:17:11", "remaining_time": "1:08:22", "throughput": 2855.62, "total_tokens": 13226512} {"current_steps": 20240, "total_steps": 38160, "loss": 0.0905, "lr": 2.6711516115810136e-05, "epoch": 10.60796645702306, "percentage": 53.04, "elapsed_time": "1:17:12", "remaining_time": "1:08:21", "throughput": 2855.68, "total_tokens": 13229744} {"current_steps": 20245, "total_steps": 38160, "loss": 0.1286, "lr": 2.6700108479177188e-05, "epoch": 10.610587002096436, "percentage": 53.05, "elapsed_time": "1:17:13", "remaining_time": "1:08:20", "throughput": 2855.83, "total_tokens": 13233552} {"current_steps": 20250, "total_steps": 38160, "loss": 0.0606, "lr": 2.6688700486900926e-05, "epoch": 10.61320754716981, "percentage": 53.07, "elapsed_time": "1:17:14", "remaining_time": "1:08:19", "throughput": 2855.9, "total_tokens": 13237008} {"current_steps": 20255, "total_steps": 38160, "loss": 0.0862, "lr": 2.6677292141367787e-05, "epoch": 10.615828092243186, "percentage": 53.08, "elapsed_time": "1:17:16", "remaining_time": "1:08:18", "throughput": 2855.88, "total_tokens": 13240080} {"current_steps": 20260, "total_steps": 38160, "loss": 0.1087, "lr": 2.6665883444964278e-05, "epoch": 10.618448637316561, "percentage": 53.09, "elapsed_time": "1:17:17", "remaining_time": "1:08:17", "throughput": 2855.87, "total_tokens": 13243408} {"current_steps": 20265, "total_steps": 38160, "loss": 0.1128, "lr": 2.665447440007695e-05, "epoch": 10.621069182389936, "percentage": 53.11, "elapsed_time": "1:17:18", "remaining_time": "1:08:15", "throughput": 2855.95, "total_tokens": 13247152} {"current_steps": 20270, "total_steps": 38160, "loss": 0.0763, "lr": 2.664306500909246e-05, "epoch": 10.623689727463312, "percentage": 53.12, "elapsed_time": "1:17:19", "remaining_time": "1:08:14", "throughput": 2856.06, "total_tokens": 13251376} {"current_steps": 20275, "total_steps": 38160, "loss": 0.0866, "lr": 2.663165527439751e-05, "epoch": 10.626310272536688, "percentage": 53.13, "elapsed_time": "1:17:20", "remaining_time": "1:08:13", "throughput": 2856.08, "total_tokens": 13254992} {"current_steps": 20280, "total_steps": 38160, "loss": 0.0837, "lr": 2.662024519837889e-05, "epoch": 10.628930817610064, "percentage": 53.14, "elapsed_time": "1:17:22", "remaining_time": "1:08:12", "throughput": 2856.02, "total_tokens": 13257712} {"current_steps": 20285, "total_steps": 38160, "loss": 0.0761, "lr": 2.6608834783423465e-05, "epoch": 10.631551362683439, "percentage": 53.16, "elapsed_time": "1:17:23", "remaining_time": "1:08:11", "throughput": 2856.19, "total_tokens": 13262192} {"current_steps": 20290, "total_steps": 38160, "loss": 0.1174, "lr": 2.6597424031918156e-05, "epoch": 10.634171907756814, "percentage": 53.17, "elapsed_time": "1:17:24", "remaining_time": "1:08:10", "throughput": 2856.41, "total_tokens": 13266832} {"current_steps": 20295, "total_steps": 38160, "loss": 0.0786, "lr": 2.6586012946249954e-05, "epoch": 10.63679245283019, "percentage": 53.18, "elapsed_time": "1:17:25", "remaining_time": "1:08:09", "throughput": 2856.32, "total_tokens": 13269424} {"current_steps": 20300, "total_steps": 38160, "loss": 0.1151, "lr": 2.6574601528805953e-05, "epoch": 10.639412997903564, "percentage": 53.2, "elapsed_time": "1:17:26", "remaining_time": "1:08:08", "throughput": 2856.26, "total_tokens": 13272144} {"current_steps": 20305, "total_steps": 38160, "loss": 0.071, "lr": 2.6563189781973268e-05, "epoch": 10.64203354297694, "percentage": 53.21, "elapsed_time": "1:17:27", "remaining_time": "1:08:07", "throughput": 2856.27, "total_tokens": 13275376} {"current_steps": 20310, "total_steps": 38160, "loss": 0.1092, "lr": 2.655177770813912e-05, "epoch": 10.644654088050315, "percentage": 53.22, "elapsed_time": "1:17:28", "remaining_time": "1:08:05", "throughput": 2856.24, "total_tokens": 13278320} {"current_steps": 20315, "total_steps": 38160, "loss": 0.1191, "lr": 2.654036530969077e-05, "epoch": 10.64727463312369, "percentage": 53.24, "elapsed_time": "1:17:29", "remaining_time": "1:08:04", "throughput": 2856.14, "total_tokens": 13280816} {"current_steps": 20320, "total_steps": 38160, "loss": 0.2262, "lr": 2.6528952589015576e-05, "epoch": 10.649895178197065, "percentage": 53.25, "elapsed_time": "1:17:31", "remaining_time": "1:08:03", "throughput": 2856.24, "total_tokens": 13284784} {"current_steps": 20325, "total_steps": 38160, "loss": 0.1403, "lr": 2.6517539548500947e-05, "epoch": 10.65251572327044, "percentage": 53.26, "elapsed_time": "1:17:32", "remaining_time": "1:08:02", "throughput": 2856.15, "total_tokens": 13287376} {"current_steps": 20330, "total_steps": 38160, "loss": 0.0817, "lr": 2.6506126190534354e-05, "epoch": 10.655136268343815, "percentage": 53.28, "elapsed_time": "1:17:33", "remaining_time": "1:08:01", "throughput": 2856.24, "total_tokens": 13290928} {"current_steps": 20335, "total_steps": 38160, "loss": 0.1086, "lr": 2.649471251750334e-05, "epoch": 10.65775681341719, "percentage": 53.29, "elapsed_time": "1:17:34", "remaining_time": "1:07:59", "throughput": 2856.23, "total_tokens": 13294192} {"current_steps": 20340, "total_steps": 38160, "loss": 0.1344, "lr": 2.6483298531795527e-05, "epoch": 10.660377358490566, "percentage": 53.3, "elapsed_time": "1:17:35", "remaining_time": "1:07:58", "throughput": 2856.27, "total_tokens": 13297456} {"current_steps": 20345, "total_steps": 38160, "loss": 0.1439, "lr": 2.6471884235798583e-05, "epoch": 10.66299790356394, "percentage": 53.31, "elapsed_time": "1:17:36", "remaining_time": "1:07:57", "throughput": 2856.34, "total_tokens": 13301008} {"current_steps": 20350, "total_steps": 38160, "loss": 0.1099, "lr": 2.6460469631900247e-05, "epoch": 10.665618448637316, "percentage": 53.33, "elapsed_time": "1:17:37", "remaining_time": "1:07:56", "throughput": 2856.38, "total_tokens": 13304368} {"current_steps": 20355, "total_steps": 38160, "loss": 0.168, "lr": 2.644905472248832e-05, "epoch": 10.668238993710691, "percentage": 53.34, "elapsed_time": "1:17:38", "remaining_time": "1:07:55", "throughput": 2856.27, "total_tokens": 13306864} {"current_steps": 20360, "total_steps": 38160, "loss": 0.0811, "lr": 2.6437639509950686e-05, "epoch": 10.670859538784066, "percentage": 53.35, "elapsed_time": "1:17:39", "remaining_time": "1:07:54", "throughput": 2856.34, "total_tokens": 13310352} {"current_steps": 20365, "total_steps": 38160, "loss": 0.081, "lr": 2.6426223996675264e-05, "epoch": 10.673480083857442, "percentage": 53.37, "elapsed_time": "1:17:41", "remaining_time": "1:07:52", "throughput": 2856.33, "total_tokens": 13313488} {"current_steps": 20370, "total_steps": 38160, "loss": 0.1108, "lr": 2.641480818505005e-05, "epoch": 10.676100628930818, "percentage": 53.38, "elapsed_time": "1:17:42", "remaining_time": "1:07:51", "throughput": 2856.24, "total_tokens": 13316112} {"current_steps": 20375, "total_steps": 38160, "loss": 0.0866, "lr": 2.6403392077463108e-05, "epoch": 10.678721174004194, "percentage": 53.39, "elapsed_time": "1:17:43", "remaining_time": "1:07:50", "throughput": 2856.42, "total_tokens": 13320528} {"current_steps": 20380, "total_steps": 38160, "loss": 0.0716, "lr": 2.639197567630256e-05, "epoch": 10.681341719077569, "percentage": 53.41, "elapsed_time": "1:17:44", "remaining_time": "1:07:49", "throughput": 2856.49, "total_tokens": 13323888} {"current_steps": 20385, "total_steps": 38160, "loss": 0.1524, "lr": 2.638055898395657e-05, "epoch": 10.683962264150944, "percentage": 53.42, "elapsed_time": "1:17:45", "remaining_time": "1:07:48", "throughput": 2856.56, "total_tokens": 13327568} {"current_steps": 20390, "total_steps": 38160, "loss": 0.0921, "lr": 2.6369142002813403e-05, "epoch": 10.68658280922432, "percentage": 53.43, "elapsed_time": "1:17:46", "remaining_time": "1:07:47", "throughput": 2856.45, "total_tokens": 13330096} {"current_steps": 20395, "total_steps": 38160, "loss": 0.1042, "lr": 2.6357724735261335e-05, "epoch": 10.689203354297694, "percentage": 53.45, "elapsed_time": "1:17:47", "remaining_time": "1:07:45", "throughput": 2856.31, "total_tokens": 13332560} {"current_steps": 20400, "total_steps": 38160, "loss": 0.1593, "lr": 2.6346307183688752e-05, "epoch": 10.69182389937107, "percentage": 53.46, "elapsed_time": "1:17:48", "remaining_time": "1:07:44", "throughput": 2856.38, "total_tokens": 13336080} {"current_steps": 20405, "total_steps": 38160, "loss": 0.0826, "lr": 2.6334889350484064e-05, "epoch": 10.694444444444445, "percentage": 53.47, "elapsed_time": "1:17:50", "remaining_time": "1:07:43", "throughput": 2856.4, "total_tokens": 13339696} {"current_steps": 20410, "total_steps": 38160, "loss": 0.0877, "lr": 2.632347123803575e-05, "epoch": 10.69706498951782, "percentage": 53.49, "elapsed_time": "1:17:51", "remaining_time": "1:07:42", "throughput": 2856.55, "total_tokens": 13343760} {"current_steps": 20415, "total_steps": 38160, "loss": 0.1146, "lr": 2.6312052848732353e-05, "epoch": 10.699685534591195, "percentage": 53.5, "elapsed_time": "1:17:52", "remaining_time": "1:07:41", "throughput": 2856.55, "total_tokens": 13346928} {"current_steps": 20420, "total_steps": 38160, "loss": 0.1161, "lr": 2.6300634184962475e-05, "epoch": 10.70230607966457, "percentage": 53.51, "elapsed_time": "1:17:53", "remaining_time": "1:07:40", "throughput": 2856.54, "total_tokens": 13349968} {"current_steps": 20425, "total_steps": 38160, "loss": 0.0724, "lr": 2.628921524911475e-05, "epoch": 10.704926624737945, "percentage": 53.52, "elapsed_time": "1:17:54", "remaining_time": "1:07:38", "throughput": 2856.53, "total_tokens": 13353232} {"current_steps": 20430, "total_steps": 38160, "loss": 0.1353, "lr": 2.6277796043577924e-05, "epoch": 10.70754716981132, "percentage": 53.54, "elapsed_time": "1:17:55", "remaining_time": "1:07:37", "throughput": 2856.5, "total_tokens": 13356496} {"current_steps": 20435, "total_steps": 38160, "loss": 0.1073, "lr": 2.6266376570740725e-05, "epoch": 10.710167714884696, "percentage": 53.55, "elapsed_time": "1:17:56", "remaining_time": "1:07:36", "throughput": 2856.68, "total_tokens": 13360656} {"current_steps": 20440, "total_steps": 38160, "loss": 0.0887, "lr": 2.6254956832992005e-05, "epoch": 10.71278825995807, "percentage": 53.56, "elapsed_time": "1:17:58", "remaining_time": "1:07:35", "throughput": 2856.71, "total_tokens": 13363984} {"current_steps": 20445, "total_steps": 38160, "loss": 0.1227, "lr": 2.6243536832720627e-05, "epoch": 10.715408805031446, "percentage": 53.58, "elapsed_time": "1:17:59", "remaining_time": "1:07:34", "throughput": 2856.78, "total_tokens": 13367664} {"current_steps": 20450, "total_steps": 38160, "loss": 0.0608, "lr": 2.623211657231553e-05, "epoch": 10.718029350104821, "percentage": 53.59, "elapsed_time": "1:18:00", "remaining_time": "1:07:33", "throughput": 2856.59, "total_tokens": 13369744} {"current_steps": 20455, "total_steps": 38160, "loss": 0.1002, "lr": 2.6220696054165704e-05, "epoch": 10.720649895178196, "percentage": 53.6, "elapsed_time": "1:18:01", "remaining_time": "1:07:32", "throughput": 2856.7, "total_tokens": 13373584} {"current_steps": 20460, "total_steps": 38160, "loss": 0.1038, "lr": 2.6209275280660194e-05, "epoch": 10.723270440251572, "percentage": 53.62, "elapsed_time": "1:18:02", "remaining_time": "1:07:30", "throughput": 2856.76, "total_tokens": 13377232} {"current_steps": 20465, "total_steps": 38160, "loss": 0.1879, "lr": 2.6197854254188085e-05, "epoch": 10.725890985324948, "percentage": 53.63, "elapsed_time": "1:18:03", "remaining_time": "1:07:29", "throughput": 2856.84, "total_tokens": 13380944} {"current_steps": 20470, "total_steps": 38160, "loss": 0.1021, "lr": 2.618643297713854e-05, "epoch": 10.728511530398324, "percentage": 53.64, "elapsed_time": "1:18:05", "remaining_time": "1:07:28", "throughput": 2856.89, "total_tokens": 13385072} {"current_steps": 20475, "total_steps": 38160, "loss": 0.1162, "lr": 2.617501145190075e-05, "epoch": 10.731132075471699, "percentage": 53.66, "elapsed_time": "1:18:06", "remaining_time": "1:07:27", "throughput": 2856.85, "total_tokens": 13388016} {"current_steps": 20480, "total_steps": 38160, "loss": 0.128, "lr": 2.616358968086397e-05, "epoch": 10.733752620545074, "percentage": 53.67, "elapsed_time": "1:18:07", "remaining_time": "1:07:26", "throughput": 2856.98, "total_tokens": 13391760} {"current_steps": 20485, "total_steps": 38160, "loss": 0.1627, "lr": 2.6152167666417493e-05, "epoch": 10.73637316561845, "percentage": 53.68, "elapsed_time": "1:18:08", "remaining_time": "1:07:25", "throughput": 2857.21, "total_tokens": 13396144} {"current_steps": 20490, "total_steps": 38160, "loss": 0.0621, "lr": 2.6140745410950694e-05, "epoch": 10.738993710691824, "percentage": 53.69, "elapsed_time": "1:18:09", "remaining_time": "1:07:24", "throughput": 2857.29, "total_tokens": 13399824} {"current_steps": 20495, "total_steps": 38160, "loss": 0.0558, "lr": 2.6129322916852973e-05, "epoch": 10.7416142557652, "percentage": 53.71, "elapsed_time": "1:18:10", "remaining_time": "1:07:23", "throughput": 2857.37, "total_tokens": 13403248} {"current_steps": 20500, "total_steps": 38160, "loss": 0.0601, "lr": 2.611790018651377e-05, "epoch": 10.744234800838575, "percentage": 53.72, "elapsed_time": "1:18:11", "remaining_time": "1:07:21", "throughput": 2857.3, "total_tokens": 13405904} {"current_steps": 20505, "total_steps": 38160, "loss": 0.0743, "lr": 2.6106477222322613e-05, "epoch": 10.74685534591195, "percentage": 53.73, "elapsed_time": "1:18:12", "remaining_time": "1:07:20", "throughput": 2857.35, "total_tokens": 13409360} {"current_steps": 20510, "total_steps": 38160, "loss": 0.0936, "lr": 2.6095054026669037e-05, "epoch": 10.749475890985325, "percentage": 53.75, "elapsed_time": "1:18:13", "remaining_time": "1:07:19", "throughput": 2857.34, "total_tokens": 13412304} {"current_steps": 20515, "total_steps": 38160, "loss": 0.1181, "lr": 2.608363060194265e-05, "epoch": 10.7520964360587, "percentage": 53.76, "elapsed_time": "1:18:15", "remaining_time": "1:07:18", "throughput": 2857.39, "total_tokens": 13415568} {"current_steps": 20520, "total_steps": 38160, "loss": 0.1109, "lr": 2.6072206950533117e-05, "epoch": 10.754716981132075, "percentage": 53.77, "elapsed_time": "1:18:16", "remaining_time": "1:07:17", "throughput": 2857.28, "total_tokens": 13418160} {"current_steps": 20525, "total_steps": 38160, "loss": 0.0812, "lr": 2.606078307483011e-05, "epoch": 10.75733752620545, "percentage": 53.79, "elapsed_time": "1:18:17", "remaining_time": "1:07:15", "throughput": 2857.26, "total_tokens": 13421168} {"current_steps": 20530, "total_steps": 38160, "loss": 0.0989, "lr": 2.6049358977223392e-05, "epoch": 10.759958071278826, "percentage": 53.8, "elapsed_time": "1:18:18", "remaining_time": "1:07:14", "throughput": 2857.17, "total_tokens": 13423824} {"current_steps": 20535, "total_steps": 38160, "loss": 0.1052, "lr": 2.6037934660102747e-05, "epoch": 10.7625786163522, "percentage": 53.81, "elapsed_time": "1:18:19", "remaining_time": "1:07:13", "throughput": 2857.17, "total_tokens": 13426928} {"current_steps": 20540, "total_steps": 38160, "loss": 0.0858, "lr": 2.6026510125858006e-05, "epoch": 10.765199161425576, "percentage": 53.83, "elapsed_time": "1:18:20", "remaining_time": "1:07:12", "throughput": 2857.13, "total_tokens": 13429712} {"current_steps": 20545, "total_steps": 38160, "loss": 0.0766, "lr": 2.6015085376879063e-05, "epoch": 10.767819706498951, "percentage": 53.84, "elapsed_time": "1:18:21", "remaining_time": "1:07:11", "throughput": 2857.28, "total_tokens": 13433648} {"current_steps": 20550, "total_steps": 38160, "loss": 0.0595, "lr": 2.600366041555584e-05, "epoch": 10.770440251572326, "percentage": 53.85, "elapsed_time": "1:18:22", "remaining_time": "1:07:09", "throughput": 2857.15, "total_tokens": 13436048} {"current_steps": 20555, "total_steps": 38160, "loss": 0.1378, "lr": 2.5992235244278302e-05, "epoch": 10.773060796645701, "percentage": 53.87, "elapsed_time": "1:18:23", "remaining_time": "1:07:08", "throughput": 2857.07, "total_tokens": 13438672} {"current_steps": 20560, "total_steps": 38160, "loss": 0.0946, "lr": 2.5980809865436485e-05, "epoch": 10.775681341719078, "percentage": 53.88, "elapsed_time": "1:18:24", "remaining_time": "1:07:07", "throughput": 2856.9, "total_tokens": 13440976} {"current_steps": 20565, "total_steps": 38160, "loss": 0.0717, "lr": 2.5969384281420424e-05, "epoch": 10.778301886792454, "percentage": 53.89, "elapsed_time": "1:18:25", "remaining_time": "1:07:06", "throughput": 2857.0, "total_tokens": 13444528} {"current_steps": 20570, "total_steps": 38160, "loss": 0.1098, "lr": 2.5957958494620227e-05, "epoch": 10.780922431865829, "percentage": 53.9, "elapsed_time": "1:18:26", "remaining_time": "1:07:04", "throughput": 2857.02, "total_tokens": 13447664} {"current_steps": 20575, "total_steps": 38160, "loss": 0.1064, "lr": 2.594653250742605e-05, "epoch": 10.783542976939204, "percentage": 53.92, "elapsed_time": "1:18:28", "remaining_time": "1:07:03", "throughput": 2857.1, "total_tokens": 13451312} {"current_steps": 20580, "total_steps": 38160, "loss": 0.0717, "lr": 2.5935106322228065e-05, "epoch": 10.786163522012579, "percentage": 53.93, "elapsed_time": "1:18:29", "remaining_time": "1:07:02", "throughput": 2856.99, "total_tokens": 13453776} {"current_steps": 20585, "total_steps": 38160, "loss": 0.0896, "lr": 2.5923679941416514e-05, "epoch": 10.788784067085954, "percentage": 53.94, "elapsed_time": "1:18:30", "remaining_time": "1:07:01", "throughput": 2856.92, "total_tokens": 13456656} {"current_steps": 20590, "total_steps": 38160, "loss": 0.0671, "lr": 2.591225336738165e-05, "epoch": 10.79140461215933, "percentage": 53.96, "elapsed_time": "1:18:31", "remaining_time": "1:07:00", "throughput": 2856.87, "total_tokens": 13459440} {"current_steps": 20595, "total_steps": 38160, "loss": 0.1513, "lr": 2.5900826602513782e-05, "epoch": 10.794025157232705, "percentage": 53.97, "elapsed_time": "1:18:32", "remaining_time": "1:06:59", "throughput": 2856.89, "total_tokens": 13462608} {"current_steps": 20600, "total_steps": 38160, "loss": 0.0735, "lr": 2.5889399649203277e-05, "epoch": 10.79664570230608, "percentage": 53.98, "elapsed_time": "1:18:33", "remaining_time": "1:06:57", "throughput": 2856.83, "total_tokens": 13465424} {"current_steps": 20605, "total_steps": 38160, "loss": 0.0889, "lr": 2.5877972509840514e-05, "epoch": 10.799266247379455, "percentage": 54.0, "elapsed_time": "1:18:34", "remaining_time": "1:06:56", "throughput": 2856.85, "total_tokens": 13468688} {"current_steps": 20610, "total_steps": 38160, "loss": 0.0614, "lr": 2.5866545186815912e-05, "epoch": 10.80188679245283, "percentage": 54.01, "elapsed_time": "1:18:35", "remaining_time": "1:06:55", "throughput": 2856.77, "total_tokens": 13471312} {"current_steps": 20615, "total_steps": 38160, "loss": 0.0708, "lr": 2.5855117682519954e-05, "epoch": 10.804507337526205, "percentage": 54.02, "elapsed_time": "1:18:36", "remaining_time": "1:06:54", "throughput": 2856.67, "total_tokens": 13474352} {"current_steps": 20620, "total_steps": 38160, "loss": 0.1597, "lr": 2.584368999934312e-05, "epoch": 10.80712788259958, "percentage": 54.04, "elapsed_time": "1:18:38", "remaining_time": "1:06:53", "throughput": 2856.83, "total_tokens": 13478704} {"current_steps": 20625, "total_steps": 38160, "loss": 0.139, "lr": 2.5832262139675966e-05, "epoch": 10.809748427672956, "percentage": 54.05, "elapsed_time": "1:18:39", "remaining_time": "1:06:52", "throughput": 2856.85, "total_tokens": 13481904} {"current_steps": 20630, "total_steps": 38160, "loss": 0.2028, "lr": 2.582083410590907e-05, "epoch": 10.81236897274633, "percentage": 54.06, "elapsed_time": "1:18:40", "remaining_time": "1:06:50", "throughput": 2856.77, "total_tokens": 13484624} {"current_steps": 20635, "total_steps": 38160, "loss": 0.074, "lr": 2.5809405900433036e-05, "epoch": 10.814989517819706, "percentage": 54.07, "elapsed_time": "1:18:41", "remaining_time": "1:06:49", "throughput": 2856.87, "total_tokens": 13488368} {"current_steps": 20640, "total_steps": 38160, "loss": 0.0907, "lr": 2.579797752563853e-05, "epoch": 10.817610062893081, "percentage": 54.09, "elapsed_time": "1:18:42", "remaining_time": "1:06:48", "throughput": 2856.7, "total_tokens": 13490672} {"current_steps": 20645, "total_steps": 38160, "loss": 0.0955, "lr": 2.5786548983916232e-05, "epoch": 10.820230607966456, "percentage": 54.1, "elapsed_time": "1:18:44", "remaining_time": "1:06:47", "throughput": 2856.88, "total_tokens": 13495984} {"current_steps": 20650, "total_steps": 38160, "loss": 0.0691, "lr": 2.577512027765685e-05, "epoch": 10.822851153039831, "percentage": 54.11, "elapsed_time": "1:18:45", "remaining_time": "1:06:46", "throughput": 2856.77, "total_tokens": 13498416} {"current_steps": 20655, "total_steps": 38160, "loss": 0.1302, "lr": 2.5763691409251155e-05, "epoch": 10.825471698113208, "percentage": 54.13, "elapsed_time": "1:18:46", "remaining_time": "1:06:45", "throughput": 2856.94, "total_tokens": 13502512} {"current_steps": 20660, "total_steps": 38160, "loss": 0.1062, "lr": 2.5752262381089932e-05, "epoch": 10.828092243186584, "percentage": 54.14, "elapsed_time": "1:18:47", "remaining_time": "1:06:44", "throughput": 2857.02, "total_tokens": 13506416} {"current_steps": 20665, "total_steps": 38160, "loss": 0.1791, "lr": 2.5740833195563996e-05, "epoch": 10.830712788259959, "percentage": 54.15, "elapsed_time": "1:18:48", "remaining_time": "1:06:43", "throughput": 2857.0, "total_tokens": 13509392} {"current_steps": 20670, "total_steps": 38160, "loss": 0.122, "lr": 2.572940385506421e-05, "epoch": 10.833333333333334, "percentage": 54.17, "elapsed_time": "1:18:49", "remaining_time": "1:06:42", "throughput": 2857.17, "total_tokens": 13514032} {"current_steps": 20675, "total_steps": 38160, "loss": 0.1135, "lr": 2.5717974361981457e-05, "epoch": 10.835953878406709, "percentage": 54.18, "elapsed_time": "1:18:51", "remaining_time": "1:06:41", "throughput": 2857.29, "total_tokens": 13517968} {"current_steps": 20680, "total_steps": 38160, "loss": 0.1129, "lr": 2.5706544718706665e-05, "epoch": 10.838574423480084, "percentage": 54.19, "elapsed_time": "1:18:52", "remaining_time": "1:06:40", "throughput": 2857.31, "total_tokens": 13521616} {"current_steps": 20685, "total_steps": 38160, "loss": 0.0678, "lr": 2.569511492763077e-05, "epoch": 10.84119496855346, "percentage": 54.21, "elapsed_time": "1:18:53", "remaining_time": "1:06:38", "throughput": 2857.27, "total_tokens": 13524592} {"current_steps": 20690, "total_steps": 38160, "loss": 0.1215, "lr": 2.5683684991144764e-05, "epoch": 10.843815513626835, "percentage": 54.22, "elapsed_time": "1:18:54", "remaining_time": "1:06:37", "throughput": 2857.33, "total_tokens": 13528048} {"current_steps": 20695, "total_steps": 38160, "loss": 0.1032, "lr": 2.5672254911639666e-05, "epoch": 10.84643605870021, "percentage": 54.23, "elapsed_time": "1:18:55", "remaining_time": "1:06:36", "throughput": 2857.33, "total_tokens": 13531120} {"current_steps": 20700, "total_steps": 38160, "loss": 0.1202, "lr": 2.5660824691506496e-05, "epoch": 10.849056603773585, "percentage": 54.25, "elapsed_time": "1:18:56", "remaining_time": "1:06:35", "throughput": 2857.34, "total_tokens": 13534288} {"current_steps": 20705, "total_steps": 38160, "loss": 0.2127, "lr": 2.5649394333136356e-05, "epoch": 10.85167714884696, "percentage": 54.26, "elapsed_time": "1:18:57", "remaining_time": "1:06:34", "throughput": 2857.44, "total_tokens": 13538032} {"current_steps": 20710, "total_steps": 38160, "loss": 0.1226, "lr": 2.5637963838920316e-05, "epoch": 10.854297693920335, "percentage": 54.27, "elapsed_time": "1:18:58", "remaining_time": "1:06:32", "throughput": 2857.4, "total_tokens": 13541008} {"current_steps": 20715, "total_steps": 38160, "loss": 0.1395, "lr": 2.5626533211249525e-05, "epoch": 10.85691823899371, "percentage": 54.28, "elapsed_time": "1:19:00", "remaining_time": "1:06:31", "throughput": 2857.43, "total_tokens": 13544304} {"current_steps": 20720, "total_steps": 38160, "loss": 0.1685, "lr": 2.5615102452515138e-05, "epoch": 10.859538784067086, "percentage": 54.3, "elapsed_time": "1:19:01", "remaining_time": "1:06:30", "throughput": 2857.56, "total_tokens": 13548048} {"current_steps": 20725, "total_steps": 38160, "loss": 0.0778, "lr": 2.5603671565108328e-05, "epoch": 10.86215932914046, "percentage": 54.31, "elapsed_time": "1:19:02", "remaining_time": "1:06:29", "throughput": 2857.88, "total_tokens": 13554288} {"current_steps": 20730, "total_steps": 38160, "loss": 0.1198, "lr": 2.5592240551420317e-05, "epoch": 10.864779874213836, "percentage": 54.32, "elapsed_time": "1:19:03", "remaining_time": "1:06:28", "throughput": 2858.01, "total_tokens": 13558320} {"current_steps": 20735, "total_steps": 38160, "loss": 0.1227, "lr": 2.5580809413842343e-05, "epoch": 10.867400419287211, "percentage": 54.34, "elapsed_time": "1:19:05", "remaining_time": "1:06:27", "throughput": 2858.01, "total_tokens": 13561328} {"current_steps": 20740, "total_steps": 38160, "loss": 0.1538, "lr": 2.5569378154765655e-05, "epoch": 10.870020964360586, "percentage": 54.35, "elapsed_time": "1:19:06", "remaining_time": "1:06:26", "throughput": 2858.26, "total_tokens": 13566224} {"current_steps": 20745, "total_steps": 38160, "loss": 0.2048, "lr": 2.5557946776581572e-05, "epoch": 10.872641509433961, "percentage": 54.36, "elapsed_time": "1:19:07", "remaining_time": "1:06:25", "throughput": 2858.14, "total_tokens": 13568752} {"current_steps": 20750, "total_steps": 38160, "loss": 0.1031, "lr": 2.554651528168137e-05, "epoch": 10.875262054507338, "percentage": 54.38, "elapsed_time": "1:19:08", "remaining_time": "1:06:24", "throughput": 2858.09, "total_tokens": 13571664} {"current_steps": 20755, "total_steps": 38160, "loss": 0.1306, "lr": 2.5535083672456407e-05, "epoch": 10.877882599580714, "percentage": 54.39, "elapsed_time": "1:19:09", "remaining_time": "1:06:22", "throughput": 2858.09, "total_tokens": 13574704} {"current_steps": 20760, "total_steps": 38160, "loss": 0.1364, "lr": 2.5523651951298055e-05, "epoch": 10.880503144654089, "percentage": 54.4, "elapsed_time": "1:19:10", "remaining_time": "1:06:21", "throughput": 2858.0, "total_tokens": 13577264} {"current_steps": 20765, "total_steps": 38160, "loss": 0.0672, "lr": 2.5512220120597686e-05, "epoch": 10.883123689727464, "percentage": 54.42, "elapsed_time": "1:19:11", "remaining_time": "1:06:20", "throughput": 2857.99, "total_tokens": 13580240} {"current_steps": 20770, "total_steps": 38160, "loss": 0.1004, "lr": 2.550078818274671e-05, "epoch": 10.885744234800839, "percentage": 54.43, "elapsed_time": "1:19:12", "remaining_time": "1:06:19", "throughput": 2858.01, "total_tokens": 13583472} {"current_steps": 20775, "total_steps": 38160, "loss": 0.1087, "lr": 2.548935614013656e-05, "epoch": 10.888364779874214, "percentage": 54.44, "elapsed_time": "1:19:13", "remaining_time": "1:06:18", "throughput": 2858.01, "total_tokens": 13586640} {"current_steps": 20780, "total_steps": 38160, "loss": 0.07, "lr": 2.5477923995158683e-05, "epoch": 10.89098532494759, "percentage": 54.45, "elapsed_time": "1:19:14", "remaining_time": "1:06:16", "throughput": 2858.02, "total_tokens": 13589680} {"current_steps": 20785, "total_steps": 38160, "loss": 0.1453, "lr": 2.5466491750204562e-05, "epoch": 10.893605870020965, "percentage": 54.47, "elapsed_time": "1:19:16", "remaining_time": "1:06:15", "throughput": 2858.05, "total_tokens": 13593072} {"current_steps": 20790, "total_steps": 38160, "loss": 0.1138, "lr": 2.5455059407665693e-05, "epoch": 10.89622641509434, "percentage": 54.48, "elapsed_time": "1:19:17", "remaining_time": "1:06:14", "throughput": 2858.14, "total_tokens": 13596624} {"current_steps": 20795, "total_steps": 38160, "loss": 0.0807, "lr": 2.544362696993358e-05, "epoch": 10.898846960167715, "percentage": 54.49, "elapsed_time": "1:19:18", "remaining_time": "1:06:13", "throughput": 2858.0, "total_tokens": 13599088} {"current_steps": 20800, "total_steps": 38160, "loss": 0.0751, "lr": 2.5432194439399775e-05, "epoch": 10.90146750524109, "percentage": 54.51, "elapsed_time": "1:19:19", "remaining_time": "1:06:12", "throughput": 2857.89, "total_tokens": 13601552} {"current_steps": 20805, "total_steps": 38160, "loss": 0.0776, "lr": 2.542076181845582e-05, "epoch": 10.904088050314465, "percentage": 54.52, "elapsed_time": "1:19:20", "remaining_time": "1:06:10", "throughput": 2857.8, "total_tokens": 13604144} {"current_steps": 20810, "total_steps": 38160, "loss": 0.0849, "lr": 2.540932910949329e-05, "epoch": 10.90670859538784, "percentage": 54.53, "elapsed_time": "1:19:21", "remaining_time": "1:06:09", "throughput": 2857.73, "total_tokens": 13606928} {"current_steps": 20815, "total_steps": 38160, "loss": 0.0728, "lr": 2.5397896314903785e-05, "epoch": 10.909329140461216, "percentage": 54.55, "elapsed_time": "1:19:22", "remaining_time": "1:06:08", "throughput": 2857.78, "total_tokens": 13610320} {"current_steps": 20820, "total_steps": 38160, "loss": 0.2891, "lr": 2.5386463437078905e-05, "epoch": 10.91194968553459, "percentage": 54.56, "elapsed_time": "1:19:23", "remaining_time": "1:06:07", "throughput": 2857.79, "total_tokens": 13613680} {"current_steps": 20825, "total_steps": 38160, "loss": 0.0971, "lr": 2.5375030478410282e-05, "epoch": 10.914570230607966, "percentage": 54.57, "elapsed_time": "1:19:24", "remaining_time": "1:06:06", "throughput": 2857.85, "total_tokens": 13617264} {"current_steps": 20830, "total_steps": 38160, "loss": 0.1192, "lr": 2.536359744128957e-05, "epoch": 10.917190775681341, "percentage": 54.59, "elapsed_time": "1:19:25", "remaining_time": "1:06:05", "throughput": 2857.83, "total_tokens": 13620208} {"current_steps": 20835, "total_steps": 38160, "loss": 0.1268, "lr": 2.5352164328108413e-05, "epoch": 10.919811320754716, "percentage": 54.6, "elapsed_time": "1:19:27", "remaining_time": "1:06:03", "throughput": 2857.82, "total_tokens": 13623248} {"current_steps": 20840, "total_steps": 38160, "loss": 0.0769, "lr": 2.53407311412585e-05, "epoch": 10.922431865828091, "percentage": 54.61, "elapsed_time": "1:19:28", "remaining_time": "1:06:02", "throughput": 2857.86, "total_tokens": 13626672} {"current_steps": 20845, "total_steps": 38160, "loss": 0.1177, "lr": 2.5329297883131526e-05, "epoch": 10.925052410901468, "percentage": 54.63, "elapsed_time": "1:19:29", "remaining_time": "1:06:01", "throughput": 2857.84, "total_tokens": 13629776} {"current_steps": 20850, "total_steps": 38160, "loss": 0.154, "lr": 2.5317864556119182e-05, "epoch": 10.927672955974844, "percentage": 54.64, "elapsed_time": "1:19:30", "remaining_time": "1:06:00", "throughput": 2857.71, "total_tokens": 13632336} {"current_steps": 20855, "total_steps": 38160, "loss": 0.101, "lr": 2.53064311626132e-05, "epoch": 10.930293501048219, "percentage": 54.65, "elapsed_time": "1:19:31", "remaining_time": "1:05:59", "throughput": 2857.74, "total_tokens": 13635600} {"current_steps": 20860, "total_steps": 38160, "loss": 0.1066, "lr": 2.5294997705005318e-05, "epoch": 10.932914046121594, "percentage": 54.66, "elapsed_time": "1:19:32", "remaining_time": "1:05:58", "throughput": 2857.82, "total_tokens": 13639248} {"current_steps": 20865, "total_steps": 38160, "loss": 0.0962, "lr": 2.5283564185687282e-05, "epoch": 10.935534591194969, "percentage": 54.68, "elapsed_time": "1:19:33", "remaining_time": "1:05:56", "throughput": 2857.72, "total_tokens": 13641872} {"current_steps": 20870, "total_steps": 38160, "loss": 0.1056, "lr": 2.5272130607050848e-05, "epoch": 10.938155136268344, "percentage": 54.69, "elapsed_time": "1:19:34", "remaining_time": "1:05:55", "throughput": 2857.8, "total_tokens": 13645424} {"current_steps": 20875, "total_steps": 38160, "loss": 0.0833, "lr": 2.5260696971487802e-05, "epoch": 10.94077568134172, "percentage": 54.7, "elapsed_time": "1:19:35", "remaining_time": "1:05:54", "throughput": 2857.77, "total_tokens": 13648368} {"current_steps": 20880, "total_steps": 38160, "loss": 0.0972, "lr": 2.5249263281389923e-05, "epoch": 10.943396226415095, "percentage": 54.72, "elapsed_time": "1:19:36", "remaining_time": "1:05:53", "throughput": 2857.62, "total_tokens": 13650704} {"current_steps": 20885, "total_steps": 38160, "loss": 0.1106, "lr": 2.5237829539149004e-05, "epoch": 10.94601677148847, "percentage": 54.73, "elapsed_time": "1:19:38", "remaining_time": "1:05:52", "throughput": 2857.56, "total_tokens": 13653552} {"current_steps": 20890, "total_steps": 38160, "loss": 0.1464, "lr": 2.5226395747156866e-05, "epoch": 10.948637316561845, "percentage": 54.74, "elapsed_time": "1:19:39", "remaining_time": "1:05:51", "throughput": 2857.7, "total_tokens": 13657488} {"current_steps": 20895, "total_steps": 38160, "loss": 0.1177, "lr": 2.5214961907805317e-05, "epoch": 10.95125786163522, "percentage": 54.76, "elapsed_time": "1:19:40", "remaining_time": "1:05:49", "throughput": 2857.71, "total_tokens": 13660976} {"current_steps": 20900, "total_steps": 38160, "loss": 0.0864, "lr": 2.520352802348619e-05, "epoch": 10.953878406708595, "percentage": 54.77, "elapsed_time": "1:19:41", "remaining_time": "1:05:48", "throughput": 2857.71, "total_tokens": 13664080} {"current_steps": 20905, "total_steps": 38160, "loss": 0.1971, "lr": 2.5192094096591323e-05, "epoch": 10.95649895178197, "percentage": 54.78, "elapsed_time": "1:19:42", "remaining_time": "1:05:47", "throughput": 2857.69, "total_tokens": 13666960} {"current_steps": 20910, "total_steps": 38160, "loss": 0.088, "lr": 2.5180660129512556e-05, "epoch": 10.959119496855346, "percentage": 54.8, "elapsed_time": "1:19:43", "remaining_time": "1:05:46", "throughput": 2857.8, "total_tokens": 13670832} {"current_steps": 20915, "total_steps": 38160, "loss": 0.1299, "lr": 2.516922612464176e-05, "epoch": 10.96174004192872, "percentage": 54.81, "elapsed_time": "1:19:44", "remaining_time": "1:05:45", "throughput": 2857.7, "total_tokens": 13673456} {"current_steps": 20920, "total_steps": 38160, "loss": 0.0688, "lr": 2.5157792084370783e-05, "epoch": 10.964360587002096, "percentage": 54.82, "elapsed_time": "1:19:45", "remaining_time": "1:05:43", "throughput": 2857.66, "total_tokens": 13676208} {"current_steps": 20925, "total_steps": 38160, "loss": 0.1562, "lr": 2.5146358011091502e-05, "epoch": 10.966981132075471, "percentage": 54.83, "elapsed_time": "1:19:46", "remaining_time": "1:05:42", "throughput": 2857.66, "total_tokens": 13679184} {"current_steps": 20930, "total_steps": 38160, "loss": 0.1126, "lr": 2.5134923907195805e-05, "epoch": 10.969601677148846, "percentage": 54.85, "elapsed_time": "1:19:47", "remaining_time": "1:05:41", "throughput": 2857.76, "total_tokens": 13682896} {"current_steps": 20935, "total_steps": 38160, "loss": 0.1427, "lr": 2.5123489775075558e-05, "epoch": 10.972222222222221, "percentage": 54.86, "elapsed_time": "1:19:49", "remaining_time": "1:05:40", "throughput": 2857.81, "total_tokens": 13686064} {"current_steps": 20940, "total_steps": 38160, "loss": 0.1087, "lr": 2.511205561712266e-05, "epoch": 10.974842767295598, "percentage": 54.87, "elapsed_time": "1:19:50", "remaining_time": "1:05:39", "throughput": 2857.82, "total_tokens": 13689424} {"current_steps": 20945, "total_steps": 38160, "loss": 0.1597, "lr": 2.5100621435729004e-05, "epoch": 10.977463312368974, "percentage": 54.89, "elapsed_time": "1:19:51", "remaining_time": "1:05:37", "throughput": 2857.84, "total_tokens": 13692496} {"current_steps": 20950, "total_steps": 38160, "loss": 0.1121, "lr": 2.5089187233286492e-05, "epoch": 10.980083857442349, "percentage": 54.9, "elapsed_time": "1:19:52", "remaining_time": "1:05:36", "throughput": 2857.85, "total_tokens": 13695728} {"current_steps": 20955, "total_steps": 38160, "loss": 0.1125, "lr": 2.5077753012187026e-05, "epoch": 10.982704402515724, "percentage": 54.91, "elapsed_time": "1:19:53", "remaining_time": "1:05:35", "throughput": 2857.81, "total_tokens": 13698640} {"current_steps": 20960, "total_steps": 38160, "loss": 0.09, "lr": 2.506631877482252e-05, "epoch": 10.985324947589099, "percentage": 54.93, "elapsed_time": "1:19:54", "remaining_time": "1:05:34", "throughput": 2857.88, "total_tokens": 13702608} {"current_steps": 20965, "total_steps": 38160, "loss": 0.1617, "lr": 2.505488452358488e-05, "epoch": 10.987945492662474, "percentage": 54.94, "elapsed_time": "1:19:55", "remaining_time": "1:05:33", "throughput": 2857.97, "total_tokens": 13706352} {"current_steps": 20970, "total_steps": 38160, "loss": 0.1072, "lr": 2.504345026086603e-05, "epoch": 10.99056603773585, "percentage": 54.95, "elapsed_time": "1:19:57", "remaining_time": "1:05:32", "throughput": 2858.12, "total_tokens": 13711056} {"current_steps": 20975, "total_steps": 38160, "loss": 0.0739, "lr": 2.5032015989057877e-05, "epoch": 10.993186582809225, "percentage": 54.97, "elapsed_time": "1:19:58", "remaining_time": "1:05:31", "throughput": 2858.18, "total_tokens": 13714480} {"current_steps": 20980, "total_steps": 38160, "loss": 0.0808, "lr": 2.5020581710552348e-05, "epoch": 10.9958071278826, "percentage": 54.98, "elapsed_time": "1:19:59", "remaining_time": "1:05:30", "throughput": 2858.11, "total_tokens": 13717136} {"current_steps": 20985, "total_steps": 38160, "loss": 0.1702, "lr": 2.5009147427741358e-05, "epoch": 10.998427672955975, "percentage": 54.99, "elapsed_time": "1:20:00", "remaining_time": "1:05:28", "throughput": 2858.18, "total_tokens": 13720464} {"current_steps": 20988, "total_steps": 38160, "eval_loss": 0.891692042350769, "epoch": 11.0, "percentage": 55.0, "elapsed_time": "1:20:12", "remaining_time": "1:05:37", "throughput": 2851.1, "total_tokens": 13721824} {"current_steps": 20990, "total_steps": 38160, "loss": 0.0759, "lr": 2.4997713143016822e-05, "epoch": 11.00104821802935, "percentage": 55.01, "elapsed_time": "1:20:16", "remaining_time": "1:05:39", "throughput": 2849.4, "total_tokens": 13723072} {"current_steps": 20995, "total_steps": 38160, "loss": 0.0524, "lr": 2.498627885877068e-05, "epoch": 11.003668763102725, "percentage": 55.02, "elapsed_time": "1:20:17", "remaining_time": "1:05:38", "throughput": 2849.4, "total_tokens": 13726400} {"current_steps": 21000, "total_steps": 38160, "loss": 0.0493, "lr": 2.4974844577394846e-05, "epoch": 11.0062893081761, "percentage": 55.03, "elapsed_time": "1:20:18", "remaining_time": "1:05:37", "throughput": 2849.33, "total_tokens": 13729280} {"current_steps": 21005, "total_steps": 38160, "loss": 0.0653, "lr": 2.496341030128123e-05, "epoch": 11.008909853249476, "percentage": 55.04, "elapsed_time": "1:20:19", "remaining_time": "1:05:36", "throughput": 2849.32, "total_tokens": 13732416} {"current_steps": 21010, "total_steps": 38160, "loss": 0.1422, "lr": 2.495197603282177e-05, "epoch": 11.01153039832285, "percentage": 55.06, "elapsed_time": "1:20:20", "remaining_time": "1:05:35", "throughput": 2849.24, "total_tokens": 13735232} {"current_steps": 21015, "total_steps": 38160, "loss": 0.0938, "lr": 2.4940541774408368e-05, "epoch": 11.014150943396226, "percentage": 55.07, "elapsed_time": "1:20:21", "remaining_time": "1:05:33", "throughput": 2849.32, "total_tokens": 13738656} {"current_steps": 21020, "total_steps": 38160, "loss": 0.0828, "lr": 2.4929107528432953e-05, "epoch": 11.016771488469601, "percentage": 55.08, "elapsed_time": "1:20:22", "remaining_time": "1:05:32", "throughput": 2849.31, "total_tokens": 13741568} {"current_steps": 21025, "total_steps": 38160, "loss": 0.037, "lr": 2.4917673297287446e-05, "epoch": 11.019392033542976, "percentage": 55.1, "elapsed_time": "1:20:23", "remaining_time": "1:05:31", "throughput": 2849.19, "total_tokens": 13744192} {"current_steps": 21030, "total_steps": 38160, "loss": 0.0655, "lr": 2.4906239083363728e-05, "epoch": 11.022012578616351, "percentage": 55.11, "elapsed_time": "1:20:25", "remaining_time": "1:05:30", "throughput": 2849.02, "total_tokens": 13746656} {"current_steps": 21035, "total_steps": 38160, "loss": 0.0687, "lr": 2.4894804889053732e-05, "epoch": 11.024633123689727, "percentage": 55.12, "elapsed_time": "1:20:26", "remaining_time": "1:05:29", "throughput": 2849.02, "total_tokens": 13749920} {"current_steps": 21040, "total_steps": 38160, "loss": 0.0649, "lr": 2.4883370716749347e-05, "epoch": 11.027253668763104, "percentage": 55.14, "elapsed_time": "1:20:27", "remaining_time": "1:05:27", "throughput": 2848.99, "total_tokens": 13752864} {"current_steps": 21045, "total_steps": 38160, "loss": 0.0555, "lr": 2.4871936568842486e-05, "epoch": 11.029874213836479, "percentage": 55.15, "elapsed_time": "1:20:28", "remaining_time": "1:05:26", "throughput": 2849.04, "total_tokens": 13756192} {"current_steps": 21050, "total_steps": 38160, "loss": 0.0704, "lr": 2.4860502447725033e-05, "epoch": 11.032494758909854, "percentage": 55.16, "elapsed_time": "1:20:29", "remaining_time": "1:05:25", "throughput": 2849.13, "total_tokens": 13759968} {"current_steps": 21055, "total_steps": 38160, "loss": 0.0612, "lr": 2.4849068355788873e-05, "epoch": 11.035115303983229, "percentage": 55.18, "elapsed_time": "1:20:30", "remaining_time": "1:05:24", "throughput": 2849.14, "total_tokens": 13763072} {"current_steps": 21060, "total_steps": 38160, "loss": 0.044, "lr": 2.4837634295425892e-05, "epoch": 11.037735849056604, "percentage": 55.19, "elapsed_time": "1:20:31", "remaining_time": "1:05:23", "throughput": 2849.03, "total_tokens": 13765728} {"current_steps": 21065, "total_steps": 38160, "loss": 0.0608, "lr": 2.4826200269027957e-05, "epoch": 11.04035639412998, "percentage": 55.2, "elapsed_time": "1:20:32", "remaining_time": "1:05:22", "throughput": 2849.15, "total_tokens": 13769504} {"current_steps": 21070, "total_steps": 38160, "loss": 0.0785, "lr": 2.481476627898695e-05, "epoch": 11.042976939203355, "percentage": 55.21, "elapsed_time": "1:20:34", "remaining_time": "1:05:20", "throughput": 2849.27, "total_tokens": 13773760} {"current_steps": 21075, "total_steps": 38160, "loss": 0.0464, "lr": 2.4803332327694724e-05, "epoch": 11.04559748427673, "percentage": 55.23, "elapsed_time": "1:20:35", "remaining_time": "1:05:19", "throughput": 2849.27, "total_tokens": 13777088} {"current_steps": 21080, "total_steps": 38160, "loss": 0.05, "lr": 2.4791898417543136e-05, "epoch": 11.048218029350105, "percentage": 55.24, "elapsed_time": "1:20:36", "remaining_time": "1:05:18", "throughput": 2849.35, "total_tokens": 13781120} {"current_steps": 21085, "total_steps": 38160, "loss": 0.0582, "lr": 2.4780464550924014e-05, "epoch": 11.05083857442348, "percentage": 55.25, "elapsed_time": "1:20:37", "remaining_time": "1:05:17", "throughput": 2849.32, "total_tokens": 13784064} {"current_steps": 21090, "total_steps": 38160, "loss": 0.0726, "lr": 2.4769030730229213e-05, "epoch": 11.053459119496855, "percentage": 55.27, "elapsed_time": "1:20:38", "remaining_time": "1:05:16", "throughput": 2849.31, "total_tokens": 13787104} {"current_steps": 21095, "total_steps": 38160, "loss": 0.0693, "lr": 2.475759695785054e-05, "epoch": 11.05607966457023, "percentage": 55.28, "elapsed_time": "1:20:39", "remaining_time": "1:05:15", "throughput": 2849.21, "total_tokens": 13789824} {"current_steps": 21100, "total_steps": 38160, "loss": 0.1042, "lr": 2.4746163236179822e-05, "epoch": 11.058700209643606, "percentage": 55.29, "elapsed_time": "1:20:41", "remaining_time": "1:05:14", "throughput": 2849.23, "total_tokens": 13793152} {"current_steps": 21105, "total_steps": 38160, "loss": 0.1227, "lr": 2.4734729567608858e-05, "epoch": 11.06132075471698, "percentage": 55.31, "elapsed_time": "1:20:42", "remaining_time": "1:05:12", "throughput": 2849.2, "total_tokens": 13796288} {"current_steps": 21110, "total_steps": 38160, "loss": 0.0771, "lr": 2.472329595452945e-05, "epoch": 11.063941299790356, "percentage": 55.32, "elapsed_time": "1:20:43", "remaining_time": "1:05:11", "throughput": 2849.16, "total_tokens": 13799072} {"current_steps": 21115, "total_steps": 38160, "loss": 0.066, "lr": 2.4711862399333367e-05, "epoch": 11.066561844863731, "percentage": 55.33, "elapsed_time": "1:20:44", "remaining_time": "1:05:10", "throughput": 2849.21, "total_tokens": 13802560} {"current_steps": 21120, "total_steps": 38160, "loss": 0.0759, "lr": 2.4700428904412377e-05, "epoch": 11.069182389937106, "percentage": 55.35, "elapsed_time": "1:20:45", "remaining_time": "1:05:09", "throughput": 2849.4, "total_tokens": 13806592} {"current_steps": 21125, "total_steps": 38160, "loss": 0.0192, "lr": 2.4688995472158245e-05, "epoch": 11.071802935010481, "percentage": 55.36, "elapsed_time": "1:20:46", "remaining_time": "1:05:08", "throughput": 2849.38, "total_tokens": 13809568} {"current_steps": 21130, "total_steps": 38160, "loss": 0.038, "lr": 2.4677562104962712e-05, "epoch": 11.074423480083857, "percentage": 55.37, "elapsed_time": "1:20:47", "remaining_time": "1:05:07", "throughput": 2849.4, "total_tokens": 13812960} {"current_steps": 21135, "total_steps": 38160, "loss": 0.1754, "lr": 2.4666128805217513e-05, "epoch": 11.077044025157234, "percentage": 55.39, "elapsed_time": "1:20:48", "remaining_time": "1:05:05", "throughput": 2849.35, "total_tokens": 13815712} {"current_steps": 21140, "total_steps": 38160, "loss": 0.0711, "lr": 2.465469557531436e-05, "epoch": 11.079664570230609, "percentage": 55.4, "elapsed_time": "1:20:49", "remaining_time": "1:05:04", "throughput": 2849.33, "total_tokens": 13818560} {"current_steps": 21145, "total_steps": 38160, "loss": 0.0455, "lr": 2.4643262417644944e-05, "epoch": 11.082285115303984, "percentage": 55.41, "elapsed_time": "1:20:51", "remaining_time": "1:05:03", "throughput": 2849.51, "total_tokens": 13823264} {"current_steps": 21150, "total_steps": 38160, "loss": 0.043, "lr": 2.463182933460096e-05, "epoch": 11.084905660377359, "percentage": 55.42, "elapsed_time": "1:20:52", "remaining_time": "1:05:02", "throughput": 2849.53, "total_tokens": 13826464} {"current_steps": 21155, "total_steps": 38160, "loss": 0.0754, "lr": 2.4620396328574087e-05, "epoch": 11.087526205450734, "percentage": 55.44, "elapsed_time": "1:20:53", "remaining_time": "1:05:01", "throughput": 2849.5, "total_tokens": 13829280} {"current_steps": 21160, "total_steps": 38160, "loss": 0.0546, "lr": 2.4608963401955965e-05, "epoch": 11.09014675052411, "percentage": 55.45, "elapsed_time": "1:20:54", "remaining_time": "1:05:00", "throughput": 2849.65, "total_tokens": 13833344} {"current_steps": 21165, "total_steps": 38160, "loss": 0.1086, "lr": 2.4597530557138247e-05, "epoch": 11.092767295597485, "percentage": 55.46, "elapsed_time": "1:20:55", "remaining_time": "1:04:58", "throughput": 2849.76, "total_tokens": 13837088} {"current_steps": 21170, "total_steps": 38160, "loss": 0.0767, "lr": 2.4586097796512538e-05, "epoch": 11.09538784067086, "percentage": 55.48, "elapsed_time": "1:20:56", "remaining_time": "1:04:57", "throughput": 2849.6, "total_tokens": 13839488} {"current_steps": 21175, "total_steps": 38160, "loss": 0.0597, "lr": 2.457466512247045e-05, "epoch": 11.098008385744235, "percentage": 55.49, "elapsed_time": "1:20:57", "remaining_time": "1:04:56", "throughput": 2849.59, "total_tokens": 13842528} {"current_steps": 21180, "total_steps": 38160, "loss": 0.0392, "lr": 2.4563232537403563e-05, "epoch": 11.10062893081761, "percentage": 55.5, "elapsed_time": "1:20:58", "remaining_time": "1:04:55", "throughput": 2849.53, "total_tokens": 13845312} {"current_steps": 21185, "total_steps": 38160, "loss": 0.0566, "lr": 2.4551800043703442e-05, "epoch": 11.103249475890985, "percentage": 55.52, "elapsed_time": "1:20:59", "remaining_time": "1:04:54", "throughput": 2849.51, "total_tokens": 13848256} {"current_steps": 21190, "total_steps": 38160, "loss": 0.075, "lr": 2.454036764376165e-05, "epoch": 11.10587002096436, "percentage": 55.53, "elapsed_time": "1:21:01", "remaining_time": "1:04:52", "throughput": 2849.61, "total_tokens": 13852064} {"current_steps": 21195, "total_steps": 38160, "loss": 0.0792, "lr": 2.4528935339969705e-05, "epoch": 11.108490566037736, "percentage": 55.54, "elapsed_time": "1:21:02", "remaining_time": "1:04:51", "throughput": 2849.59, "total_tokens": 13855040} {"current_steps": 21200, "total_steps": 38160, "loss": 0.0658, "lr": 2.45175031347191e-05, "epoch": 11.11111111111111, "percentage": 55.56, "elapsed_time": "1:21:03", "remaining_time": "1:04:50", "throughput": 2849.59, "total_tokens": 13858528} {"current_steps": 21205, "total_steps": 38160, "loss": 0.1183, "lr": 2.4506071030401344e-05, "epoch": 11.113731656184486, "percentage": 55.57, "elapsed_time": "1:21:04", "remaining_time": "1:04:49", "throughput": 2849.65, "total_tokens": 13862048} {"current_steps": 21210, "total_steps": 38160, "loss": 0.0494, "lr": 2.4494639029407884e-05, "epoch": 11.116352201257861, "percentage": 55.58, "elapsed_time": "1:21:05", "remaining_time": "1:04:48", "throughput": 2849.6, "total_tokens": 13864864} {"current_steps": 21215, "total_steps": 38160, "loss": 0.0613, "lr": 2.448320713413018e-05, "epoch": 11.118972746331236, "percentage": 55.59, "elapsed_time": "1:21:06", "remaining_time": "1:04:47", "throughput": 2849.66, "total_tokens": 13868256} {"current_steps": 21220, "total_steps": 38160, "loss": 0.0407, "lr": 2.4471775346959654e-05, "epoch": 11.121593291404611, "percentage": 55.61, "elapsed_time": "1:21:07", "remaining_time": "1:04:45", "throughput": 2849.57, "total_tokens": 13870944} {"current_steps": 21225, "total_steps": 38160, "loss": 0.0968, "lr": 2.446034367028769e-05, "epoch": 11.124213836477987, "percentage": 55.62, "elapsed_time": "1:21:08", "remaining_time": "1:04:44", "throughput": 2849.56, "total_tokens": 13874016} {"current_steps": 21230, "total_steps": 38160, "loss": 0.1201, "lr": 2.444891210650567e-05, "epoch": 11.126834381551364, "percentage": 55.63, "elapsed_time": "1:21:10", "remaining_time": "1:04:44", "throughput": 2849.87, "total_tokens": 13881184} {"current_steps": 21235, "total_steps": 38160, "loss": 0.0726, "lr": 2.4437480658004958e-05, "epoch": 11.129454926624739, "percentage": 55.65, "elapsed_time": "1:21:11", "remaining_time": "1:04:43", "throughput": 2849.87, "total_tokens": 13884224} {"current_steps": 21240, "total_steps": 38160, "loss": 0.0459, "lr": 2.4426049327176868e-05, "epoch": 11.132075471698114, "percentage": 55.66, "elapsed_time": "1:21:13", "remaining_time": "1:04:41", "throughput": 2849.94, "total_tokens": 13888064} {"current_steps": 21245, "total_steps": 38160, "loss": 0.0522, "lr": 2.4414618116412716e-05, "epoch": 11.134696016771489, "percentage": 55.67, "elapsed_time": "1:21:14", "remaining_time": "1:04:40", "throughput": 2849.9, "total_tokens": 13890912} {"current_steps": 21250, "total_steps": 38160, "loss": 0.0787, "lr": 2.440318702810378e-05, "epoch": 11.137316561844864, "percentage": 55.69, "elapsed_time": "1:21:15", "remaining_time": "1:04:39", "throughput": 2850.0, "total_tokens": 13894432} {"current_steps": 21255, "total_steps": 38160, "loss": 0.0889, "lr": 2.43917560646413e-05, "epoch": 11.13993710691824, "percentage": 55.7, "elapsed_time": "1:21:16", "remaining_time": "1:04:38", "throughput": 2850.09, "total_tokens": 13898048} {"current_steps": 21260, "total_steps": 38160, "loss": 0.1799, "lr": 2.4380325228416518e-05, "epoch": 11.142557651991615, "percentage": 55.71, "elapsed_time": "1:21:17", "remaining_time": "1:04:37", "throughput": 2850.11, "total_tokens": 13901184} {"current_steps": 21265, "total_steps": 38160, "loss": 0.0488, "lr": 2.4368894521820624e-05, "epoch": 11.14517819706499, "percentage": 55.73, "elapsed_time": "1:21:18", "remaining_time": "1:04:36", "throughput": 2850.2, "total_tokens": 13904864} {"current_steps": 21270, "total_steps": 38160, "loss": 0.0506, "lr": 2.43574639472448e-05, "epoch": 11.147798742138365, "percentage": 55.74, "elapsed_time": "1:21:19", "remaining_time": "1:04:34", "throughput": 2850.22, "total_tokens": 13908096} {"current_steps": 21275, "total_steps": 38160, "loss": 0.0465, "lr": 2.4346033507080178e-05, "epoch": 11.15041928721174, "percentage": 55.75, "elapsed_time": "1:21:20", "remaining_time": "1:04:33", "throughput": 2850.28, "total_tokens": 13911392} {"current_steps": 21280, "total_steps": 38160, "loss": 0.1079, "lr": 2.4334603203717903e-05, "epoch": 11.153039832285115, "percentage": 55.77, "elapsed_time": "1:21:21", "remaining_time": "1:04:32", "throughput": 2850.4, "total_tokens": 13915104} {"current_steps": 21285, "total_steps": 38160, "loss": 0.0663, "lr": 2.432317303954904e-05, "epoch": 11.15566037735849, "percentage": 55.78, "elapsed_time": "1:21:22", "remaining_time": "1:04:31", "throughput": 2850.36, "total_tokens": 13918176} {"current_steps": 21290, "total_steps": 38160, "loss": 0.0482, "lr": 2.4311743016964648e-05, "epoch": 11.158280922431866, "percentage": 55.79, "elapsed_time": "1:21:24", "remaining_time": "1:04:30", "throughput": 2850.33, "total_tokens": 13921120} {"current_steps": 21295, "total_steps": 38160, "loss": 0.0695, "lr": 2.4300313138355772e-05, "epoch": 11.16090146750524, "percentage": 55.8, "elapsed_time": "1:21:25", "remaining_time": "1:04:28", "throughput": 2850.3, "total_tokens": 13924224} {"current_steps": 21300, "total_steps": 38160, "loss": 0.0438, "lr": 2.4288883406113396e-05, "epoch": 11.163522012578616, "percentage": 55.82, "elapsed_time": "1:21:26", "remaining_time": "1:04:27", "throughput": 2850.3, "total_tokens": 13927488} {"current_steps": 21305, "total_steps": 38160, "loss": 0.0517, "lr": 2.4277453822628512e-05, "epoch": 11.166142557651991, "percentage": 55.83, "elapsed_time": "1:21:27", "remaining_time": "1:04:26", "throughput": 2850.33, "total_tokens": 13930880} {"current_steps": 21310, "total_steps": 38160, "loss": 0.078, "lr": 2.4266024390292037e-05, "epoch": 11.168763102725366, "percentage": 55.84, "elapsed_time": "1:21:28", "remaining_time": "1:04:25", "throughput": 2850.29, "total_tokens": 13933728} {"current_steps": 21315, "total_steps": 38160, "loss": 0.0807, "lr": 2.425459511149489e-05, "epoch": 11.171383647798741, "percentage": 55.86, "elapsed_time": "1:21:29", "remaining_time": "1:04:24", "throughput": 2850.43, "total_tokens": 13937664} {"current_steps": 21320, "total_steps": 38160, "loss": 0.0546, "lr": 2.424316598862793e-05, "epoch": 11.174004192872117, "percentage": 55.87, "elapsed_time": "1:21:30", "remaining_time": "1:04:23", "throughput": 2850.38, "total_tokens": 13940544} {"current_steps": 21325, "total_steps": 38160, "loss": 0.0654, "lr": 2.4231737024082023e-05, "epoch": 11.176624737945493, "percentage": 55.88, "elapsed_time": "1:21:31", "remaining_time": "1:04:21", "throughput": 2850.42, "total_tokens": 13943712} {"current_steps": 21330, "total_steps": 38160, "loss": 0.0707, "lr": 2.4220308220247954e-05, "epoch": 11.179245283018869, "percentage": 55.9, "elapsed_time": "1:21:32", "remaining_time": "1:04:20", "throughput": 2850.45, "total_tokens": 13947200} {"current_steps": 21335, "total_steps": 38160, "loss": 0.339, "lr": 2.4208879579516528e-05, "epoch": 11.181865828092244, "percentage": 55.91, "elapsed_time": "1:21:34", "remaining_time": "1:04:19", "throughput": 2850.46, "total_tokens": 13950240} {"current_steps": 21340, "total_steps": 38160, "loss": 0.049, "lr": 2.419745110427846e-05, "epoch": 11.184486373165619, "percentage": 55.92, "elapsed_time": "1:21:35", "remaining_time": "1:04:18", "throughput": 2850.48, "total_tokens": 13953440} {"current_steps": 21345, "total_steps": 38160, "loss": 0.0551, "lr": 2.418602279692446e-05, "epoch": 11.187106918238994, "percentage": 55.94, "elapsed_time": "1:21:36", "remaining_time": "1:04:17", "throughput": 2850.44, "total_tokens": 13956416} {"current_steps": 21350, "total_steps": 38160, "loss": 0.0781, "lr": 2.417459465984521e-05, "epoch": 11.18972746331237, "percentage": 55.95, "elapsed_time": "1:21:37", "remaining_time": "1:04:16", "throughput": 2850.42, "total_tokens": 13959840} {"current_steps": 21355, "total_steps": 38160, "loss": 0.1223, "lr": 2.4163166695431336e-05, "epoch": 11.192348008385745, "percentage": 55.96, "elapsed_time": "1:21:38", "remaining_time": "1:04:14", "throughput": 2850.45, "total_tokens": 13963168} {"current_steps": 21360, "total_steps": 38160, "loss": 0.0735, "lr": 2.4151738906073446e-05, "epoch": 11.19496855345912, "percentage": 55.97, "elapsed_time": "1:21:39", "remaining_time": "1:04:13", "throughput": 2850.32, "total_tokens": 13965632} {"current_steps": 21365, "total_steps": 38160, "loss": 0.063, "lr": 2.4140311294162105e-05, "epoch": 11.197589098532495, "percentage": 55.99, "elapsed_time": "1:21:40", "remaining_time": "1:04:12", "throughput": 2850.36, "total_tokens": 13969184} {"current_steps": 21370, "total_steps": 38160, "loss": 0.0627, "lr": 2.412888386208782e-05, "epoch": 11.20020964360587, "percentage": 56.0, "elapsed_time": "1:21:41", "remaining_time": "1:04:11", "throughput": 2850.44, "total_tokens": 13972800} {"current_steps": 21375, "total_steps": 38160, "loss": 0.1053, "lr": 2.4117456612241103e-05, "epoch": 11.202830188679245, "percentage": 56.01, "elapsed_time": "1:21:43", "remaining_time": "1:04:10", "throughput": 2850.46, "total_tokens": 13976128} {"current_steps": 21380, "total_steps": 38160, "loss": 0.0746, "lr": 2.410602954701239e-05, "epoch": 11.20545073375262, "percentage": 56.03, "elapsed_time": "1:21:44", "remaining_time": "1:04:09", "throughput": 2850.51, "total_tokens": 13979424} {"current_steps": 21385, "total_steps": 38160, "loss": 0.0526, "lr": 2.409460266879209e-05, "epoch": 11.208071278825996, "percentage": 56.04, "elapsed_time": "1:21:45", "remaining_time": "1:04:07", "throughput": 2850.4, "total_tokens": 13981856} {"current_steps": 21390, "total_steps": 38160, "loss": 0.0402, "lr": 2.4083175979970592e-05, "epoch": 11.21069182389937, "percentage": 56.05, "elapsed_time": "1:21:46", "remaining_time": "1:04:06", "throughput": 2850.43, "total_tokens": 13985248} {"current_steps": 21395, "total_steps": 38160, "loss": 0.1368, "lr": 2.4071749482938226e-05, "epoch": 11.213312368972746, "percentage": 56.07, "elapsed_time": "1:21:47", "remaining_time": "1:04:05", "throughput": 2850.47, "total_tokens": 13988576} {"current_steps": 21400, "total_steps": 38160, "loss": 0.0676, "lr": 2.4060323180085266e-05, "epoch": 11.215932914046121, "percentage": 56.08, "elapsed_time": "1:21:48", "remaining_time": "1:04:04", "throughput": 2850.39, "total_tokens": 13991232} {"current_steps": 21405, "total_steps": 38160, "loss": 0.0546, "lr": 2.404889707380198e-05, "epoch": 11.218553459119496, "percentage": 56.09, "elapsed_time": "1:21:49", "remaining_time": "1:04:03", "throughput": 2850.43, "total_tokens": 13994592} {"current_steps": 21410, "total_steps": 38160, "loss": 0.0554, "lr": 2.403747116647857e-05, "epoch": 11.221174004192871, "percentage": 56.11, "elapsed_time": "1:21:50", "remaining_time": "1:04:01", "throughput": 2850.33, "total_tokens": 13997280} {"current_steps": 21415, "total_steps": 38160, "loss": 0.0717, "lr": 2.4026045460505216e-05, "epoch": 11.223794549266247, "percentage": 56.12, "elapsed_time": "1:21:51", "remaining_time": "1:04:00", "throughput": 2850.34, "total_tokens": 14000384} {"current_steps": 21420, "total_steps": 38160, "loss": 0.0413, "lr": 2.4014619958272047e-05, "epoch": 11.226415094339623, "percentage": 56.13, "elapsed_time": "1:21:52", "remaining_time": "1:03:59", "throughput": 2850.42, "total_tokens": 14003872} {"current_steps": 21425, "total_steps": 38160, "loss": 0.0503, "lr": 2.4003194662169132e-05, "epoch": 11.229035639412999, "percentage": 56.15, "elapsed_time": "1:21:54", "remaining_time": "1:03:58", "throughput": 2850.42, "total_tokens": 14006976} {"current_steps": 21430, "total_steps": 38160, "loss": 0.1709, "lr": 2.3991769574586522e-05, "epoch": 11.231656184486374, "percentage": 56.16, "elapsed_time": "1:21:55", "remaining_time": "1:03:57", "throughput": 2850.29, "total_tokens": 14009472} {"current_steps": 21435, "total_steps": 38160, "loss": 0.0816, "lr": 2.3980344697914215e-05, "epoch": 11.234276729559749, "percentage": 56.17, "elapsed_time": "1:21:56", "remaining_time": "1:03:55", "throughput": 2850.28, "total_tokens": 14012480} {"current_steps": 21440, "total_steps": 38160, "loss": 0.0594, "lr": 2.3968920034542168e-05, "epoch": 11.236897274633124, "percentage": 56.18, "elapsed_time": "1:21:57", "remaining_time": "1:03:54", "throughput": 2850.17, "total_tokens": 14015072} {"current_steps": 21445, "total_steps": 38160, "loss": 0.0551, "lr": 2.3957495586860278e-05, "epoch": 11.2395178197065, "percentage": 56.2, "elapsed_time": "1:21:58", "remaining_time": "1:03:53", "throughput": 2850.2, "total_tokens": 14018496} {"current_steps": 21450, "total_steps": 38160, "loss": 0.1548, "lr": 2.394607135725843e-05, "epoch": 11.242138364779874, "percentage": 56.21, "elapsed_time": "1:21:59", "remaining_time": "1:03:52", "throughput": 2850.17, "total_tokens": 14021600} {"current_steps": 21455, "total_steps": 38160, "loss": 0.0602, "lr": 2.3934647348126426e-05, "epoch": 11.24475890985325, "percentage": 56.22, "elapsed_time": "1:22:00", "remaining_time": "1:03:51", "throughput": 2850.15, "total_tokens": 14024544} {"current_steps": 21460, "total_steps": 38160, "loss": 0.0487, "lr": 2.3923223561854035e-05, "epoch": 11.247379454926625, "percentage": 56.24, "elapsed_time": "1:22:01", "remaining_time": "1:03:50", "throughput": 2850.24, "total_tokens": 14027968} {"current_steps": 21465, "total_steps": 38160, "loss": 0.0689, "lr": 2.391180000083099e-05, "epoch": 11.25, "percentage": 56.25, "elapsed_time": "1:22:02", "remaining_time": "1:03:48", "throughput": 2850.18, "total_tokens": 14030688} {"current_steps": 21470, "total_steps": 38160, "loss": 0.0581, "lr": 2.390037666744698e-05, "epoch": 11.252620545073375, "percentage": 56.26, "elapsed_time": "1:22:03", "remaining_time": "1:03:47", "throughput": 2850.1, "total_tokens": 14033408} {"current_steps": 21475, "total_steps": 38160, "loss": 0.0632, "lr": 2.388895356409162e-05, "epoch": 11.25524109014675, "percentage": 56.28, "elapsed_time": "1:22:04", "remaining_time": "1:03:46", "throughput": 2850.09, "total_tokens": 14036416} {"current_steps": 21480, "total_steps": 38160, "loss": 0.0833, "lr": 2.3877530693154506e-05, "epoch": 11.257861635220126, "percentage": 56.29, "elapsed_time": "1:22:05", "remaining_time": "1:03:45", "throughput": 2850.18, "total_tokens": 14039872} {"current_steps": 21485, "total_steps": 38160, "loss": 0.0497, "lr": 2.3866108057025162e-05, "epoch": 11.2604821802935, "percentage": 56.3, "elapsed_time": "1:22:07", "remaining_time": "1:03:43", "throughput": 2850.11, "total_tokens": 14042624} {"current_steps": 21490, "total_steps": 38160, "loss": 0.1123, "lr": 2.385468565809307e-05, "epoch": 11.263102725366876, "percentage": 56.32, "elapsed_time": "1:22:08", "remaining_time": "1:03:42", "throughput": 2850.17, "total_tokens": 14045984} {"current_steps": 21495, "total_steps": 38160, "loss": 0.1004, "lr": 2.3843263498747675e-05, "epoch": 11.265723270440251, "percentage": 56.33, "elapsed_time": "1:22:09", "remaining_time": "1:03:41", "throughput": 2850.17, "total_tokens": 14049152} {"current_steps": 21500, "total_steps": 38160, "loss": 0.0595, "lr": 2.383184158137836e-05, "epoch": 11.268343815513626, "percentage": 56.34, "elapsed_time": "1:22:10", "remaining_time": "1:03:40", "throughput": 2850.2, "total_tokens": 14052320} {"current_steps": 21505, "total_steps": 38160, "loss": 0.058, "lr": 2.3820419908374465e-05, "epoch": 11.270964360587001, "percentage": 56.35, "elapsed_time": "1:22:11", "remaining_time": "1:03:39", "throughput": 2850.22, "total_tokens": 14055584} {"current_steps": 21510, "total_steps": 38160, "loss": 0.066, "lr": 2.3808998482125265e-05, "epoch": 11.273584905660377, "percentage": 56.37, "elapsed_time": "1:22:12", "remaining_time": "1:03:38", "throughput": 2850.23, "total_tokens": 14058816} {"current_steps": 21515, "total_steps": 38160, "loss": 0.1572, "lr": 2.3797577305019987e-05, "epoch": 11.276205450733753, "percentage": 56.38, "elapsed_time": "1:22:13", "remaining_time": "1:03:36", "throughput": 2850.27, "total_tokens": 14062528} {"current_steps": 21520, "total_steps": 38160, "loss": 0.092, "lr": 2.378615637944783e-05, "epoch": 11.278825995807129, "percentage": 56.39, "elapsed_time": "1:22:14", "remaining_time": "1:03:35", "throughput": 2850.23, "total_tokens": 14065280} {"current_steps": 21525, "total_steps": 38160, "loss": 0.0705, "lr": 2.3774735707797895e-05, "epoch": 11.281446540880504, "percentage": 56.41, "elapsed_time": "1:22:15", "remaining_time": "1:03:34", "throughput": 2850.2, "total_tokens": 14068160} {"current_steps": 21530, "total_steps": 38160, "loss": 0.0585, "lr": 2.376331529245928e-05, "epoch": 11.284067085953879, "percentage": 56.42, "elapsed_time": "1:22:16", "remaining_time": "1:03:33", "throughput": 2850.3, "total_tokens": 14071712} {"current_steps": 21535, "total_steps": 38160, "loss": 0.0572, "lr": 2.3751895135821006e-05, "epoch": 11.286687631027254, "percentage": 56.43, "elapsed_time": "1:22:17", "remaining_time": "1:03:32", "throughput": 2850.33, "total_tokens": 14074912} {"current_steps": 21540, "total_steps": 38160, "loss": 0.0606, "lr": 2.374047524027202e-05, "epoch": 11.28930817610063, "percentage": 56.45, "elapsed_time": "1:22:19", "remaining_time": "1:03:30", "throughput": 2850.47, "total_tokens": 14078912} {"current_steps": 21545, "total_steps": 38160, "loss": 0.0634, "lr": 2.3729055608201243e-05, "epoch": 11.291928721174004, "percentage": 56.46, "elapsed_time": "1:22:20", "remaining_time": "1:03:29", "throughput": 2850.5, "total_tokens": 14082304} {"current_steps": 21550, "total_steps": 38160, "loss": 0.0665, "lr": 2.3717636241997537e-05, "epoch": 11.29454926624738, "percentage": 56.47, "elapsed_time": "1:22:21", "remaining_time": "1:03:28", "throughput": 2850.45, "total_tokens": 14085056} {"current_steps": 21555, "total_steps": 38160, "loss": 0.0715, "lr": 2.3706217144049696e-05, "epoch": 11.297169811320755, "percentage": 56.49, "elapsed_time": "1:22:22", "remaining_time": "1:03:27", "throughput": 2850.44, "total_tokens": 14088128} {"current_steps": 21560, "total_steps": 38160, "loss": 0.0637, "lr": 2.369479831674647e-05, "epoch": 11.29979035639413, "percentage": 56.5, "elapsed_time": "1:22:23", "remaining_time": "1:03:26", "throughput": 2850.39, "total_tokens": 14090912} {"current_steps": 21565, "total_steps": 38160, "loss": 0.1167, "lr": 2.3683379762476555e-05, "epoch": 11.302410901467505, "percentage": 56.51, "elapsed_time": "1:22:24", "remaining_time": "1:03:25", "throughput": 2850.46, "total_tokens": 14094464} {"current_steps": 21570, "total_steps": 38160, "loss": 0.093, "lr": 2.3671961483628562e-05, "epoch": 11.30503144654088, "percentage": 56.53, "elapsed_time": "1:22:25", "remaining_time": "1:03:23", "throughput": 2850.44, "total_tokens": 14097280} {"current_steps": 21575, "total_steps": 38160, "loss": 0.0773, "lr": 2.3660543482591078e-05, "epoch": 11.307651991614255, "percentage": 56.54, "elapsed_time": "1:22:26", "remaining_time": "1:03:22", "throughput": 2850.4, "total_tokens": 14100224} {"current_steps": 21580, "total_steps": 38160, "loss": 0.0712, "lr": 2.364912576175261e-05, "epoch": 11.31027253668763, "percentage": 56.55, "elapsed_time": "1:22:27", "remaining_time": "1:03:21", "throughput": 2850.49, "total_tokens": 14103744} {"current_steps": 21585, "total_steps": 38160, "loss": 0.0354, "lr": 2.363770832350163e-05, "epoch": 11.312893081761006, "percentage": 56.56, "elapsed_time": "1:22:29", "remaining_time": "1:03:20", "throughput": 2850.46, "total_tokens": 14107008} {"current_steps": 21590, "total_steps": 38160, "loss": 0.0418, "lr": 2.362629117022653e-05, "epoch": 11.315513626834381, "percentage": 56.58, "elapsed_time": "1:22:30", "remaining_time": "1:03:19", "throughput": 2850.46, "total_tokens": 14110176} {"current_steps": 21595, "total_steps": 38160, "loss": 0.1663, "lr": 2.3614874304315633e-05, "epoch": 11.318134171907756, "percentage": 56.59, "elapsed_time": "1:22:31", "remaining_time": "1:03:18", "throughput": 2850.62, "total_tokens": 14115968} {"current_steps": 21600, "total_steps": 38160, "loss": 0.0665, "lr": 2.3603457728157237e-05, "epoch": 11.320754716981131, "percentage": 56.6, "elapsed_time": "1:22:33", "remaining_time": "1:03:17", "throughput": 2850.87, "total_tokens": 14120864} {"current_steps": 21605, "total_steps": 38160, "loss": 0.0943, "lr": 2.3592041444139547e-05, "epoch": 11.323375262054507, "percentage": 56.62, "elapsed_time": "1:22:34", "remaining_time": "1:03:16", "throughput": 2850.94, "total_tokens": 14124576} {"current_steps": 21610, "total_steps": 38160, "loss": 0.1147, "lr": 2.358062545465073e-05, "epoch": 11.325995807127883, "percentage": 56.63, "elapsed_time": "1:22:35", "remaining_time": "1:03:15", "throughput": 2850.94, "total_tokens": 14127648} {"current_steps": 21615, "total_steps": 38160, "loss": 0.069, "lr": 2.3569209762078866e-05, "epoch": 11.328616352201259, "percentage": 56.64, "elapsed_time": "1:22:36", "remaining_time": "1:03:13", "throughput": 2850.86, "total_tokens": 14130400} {"current_steps": 21620, "total_steps": 38160, "loss": 0.0791, "lr": 2.355779436881201e-05, "epoch": 11.331236897274634, "percentage": 56.66, "elapsed_time": "1:22:37", "remaining_time": "1:03:12", "throughput": 2850.93, "total_tokens": 14134080} {"current_steps": 21625, "total_steps": 38160, "loss": 0.0835, "lr": 2.3546379277238107e-05, "epoch": 11.333857442348009, "percentage": 56.67, "elapsed_time": "1:22:39", "remaining_time": "1:03:11", "throughput": 2850.99, "total_tokens": 14138080} {"current_steps": 21630, "total_steps": 38160, "loss": 0.0681, "lr": 2.353496448974508e-05, "epoch": 11.336477987421384, "percentage": 56.68, "elapsed_time": "1:22:40", "remaining_time": "1:03:10", "throughput": 2851.16, "total_tokens": 14142432} {"current_steps": 21635, "total_steps": 38160, "loss": 0.089, "lr": 2.3523550008720763e-05, "epoch": 11.33909853249476, "percentage": 56.7, "elapsed_time": "1:22:41", "remaining_time": "1:03:09", "throughput": 2851.15, "total_tokens": 14145440} {"current_steps": 21640, "total_steps": 38160, "loss": 0.0682, "lr": 2.3512135836552945e-05, "epoch": 11.341719077568134, "percentage": 56.71, "elapsed_time": "1:22:42", "remaining_time": "1:03:08", "throughput": 2851.2, "total_tokens": 14148672} {"current_steps": 21645, "total_steps": 38160, "loss": 0.078, "lr": 2.350072197562933e-05, "epoch": 11.34433962264151, "percentage": 56.72, "elapsed_time": "1:22:43", "remaining_time": "1:03:07", "throughput": 2851.21, "total_tokens": 14152000} {"current_steps": 21650, "total_steps": 38160, "loss": 0.0616, "lr": 2.3489308428337586e-05, "epoch": 11.346960167714885, "percentage": 56.73, "elapsed_time": "1:22:44", "remaining_time": "1:03:05", "throughput": 2851.18, "total_tokens": 14154912} {"current_steps": 21655, "total_steps": 38160, "loss": 0.0637, "lr": 2.3477895197065275e-05, "epoch": 11.34958071278826, "percentage": 56.75, "elapsed_time": "1:22:45", "remaining_time": "1:03:04", "throughput": 2851.22, "total_tokens": 14158208} {"current_steps": 21660, "total_steps": 38160, "loss": 0.0641, "lr": 2.346648228419992e-05, "epoch": 11.352201257861635, "percentage": 56.76, "elapsed_time": "1:22:46", "remaining_time": "1:03:03", "throughput": 2851.35, "total_tokens": 14161920} {"current_steps": 21665, "total_steps": 38160, "loss": 0.0638, "lr": 2.3455069692128982e-05, "epoch": 11.35482180293501, "percentage": 56.77, "elapsed_time": "1:22:47", "remaining_time": "1:03:02", "throughput": 2851.39, "total_tokens": 14165120} {"current_steps": 21670, "total_steps": 38160, "loss": 0.0961, "lr": 2.3443657423239832e-05, "epoch": 11.357442348008385, "percentage": 56.79, "elapsed_time": "1:22:48", "remaining_time": "1:03:01", "throughput": 2851.36, "total_tokens": 14168000} {"current_steps": 21675, "total_steps": 38160, "loss": 0.0638, "lr": 2.34322454799198e-05, "epoch": 11.36006289308176, "percentage": 56.8, "elapsed_time": "1:22:49", "remaining_time": "1:02:59", "throughput": 2851.48, "total_tokens": 14171584} {"current_steps": 21680, "total_steps": 38160, "loss": 0.0685, "lr": 2.3420833864556133e-05, "epoch": 11.362683438155136, "percentage": 56.81, "elapsed_time": "1:22:50", "remaining_time": "1:02:58", "throughput": 2851.43, "total_tokens": 14174336} {"current_steps": 21685, "total_steps": 38160, "loss": 0.0771, "lr": 2.3409422579535995e-05, "epoch": 11.365303983228511, "percentage": 56.83, "elapsed_time": "1:22:52", "remaining_time": "1:02:57", "throughput": 2851.43, "total_tokens": 14177344} {"current_steps": 21690, "total_steps": 38160, "loss": 0.0672, "lr": 2.339801162724651e-05, "epoch": 11.367924528301886, "percentage": 56.84, "elapsed_time": "1:22:53", "remaining_time": "1:02:56", "throughput": 2851.48, "total_tokens": 14180608} {"current_steps": 21695, "total_steps": 38160, "loss": 0.1152, "lr": 2.338660101007471e-05, "epoch": 11.370545073375261, "percentage": 56.85, "elapsed_time": "1:22:54", "remaining_time": "1:02:55", "throughput": 2851.48, "total_tokens": 14183872} {"current_steps": 21700, "total_steps": 38160, "loss": 0.1258, "lr": 2.3375190730407578e-05, "epoch": 11.373165618448636, "percentage": 56.87, "elapsed_time": "1:22:55", "remaining_time": "1:02:53", "throughput": 2851.43, "total_tokens": 14186720} {"current_steps": 21705, "total_steps": 38160, "loss": 0.0979, "lr": 2.336378079063202e-05, "epoch": 11.375786163522013, "percentage": 56.88, "elapsed_time": "1:22:56", "remaining_time": "1:02:52", "throughput": 2851.52, "total_tokens": 14190336} {"current_steps": 21710, "total_steps": 38160, "loss": 0.095, "lr": 2.335237119313484e-05, "epoch": 11.378406708595389, "percentage": 56.89, "elapsed_time": "1:22:57", "remaining_time": "1:02:51", "throughput": 2851.51, "total_tokens": 14193760} {"current_steps": 21715, "total_steps": 38160, "loss": 0.0502, "lr": 2.3340961940302807e-05, "epoch": 11.381027253668764, "percentage": 56.91, "elapsed_time": "1:22:58", "remaining_time": "1:02:50", "throughput": 2851.35, "total_tokens": 14196096} {"current_steps": 21720, "total_steps": 38160, "loss": 0.0829, "lr": 2.3329553034522616e-05, "epoch": 11.383647798742139, "percentage": 56.92, "elapsed_time": "1:22:59", "remaining_time": "1:02:49", "throughput": 2851.37, "total_tokens": 14199296} {"current_steps": 21725, "total_steps": 38160, "loss": 0.0747, "lr": 2.3318144478180866e-05, "epoch": 11.386268343815514, "percentage": 56.93, "elapsed_time": "1:23:00", "remaining_time": "1:02:48", "throughput": 2851.38, "total_tokens": 14202528} {"current_steps": 21730, "total_steps": 38160, "loss": 0.075, "lr": 2.330673627366411e-05, "epoch": 11.38888888888889, "percentage": 56.94, "elapsed_time": "1:23:02", "remaining_time": "1:02:46", "throughput": 2851.34, "total_tokens": 14205568} {"current_steps": 21735, "total_steps": 38160, "loss": 0.0684, "lr": 2.329532842335881e-05, "epoch": 11.391509433962264, "percentage": 56.96, "elapsed_time": "1:23:03", "remaining_time": "1:02:45", "throughput": 2851.36, "total_tokens": 14209056} {"current_steps": 21740, "total_steps": 38160, "loss": 0.0227, "lr": 2.328392092965135e-05, "epoch": 11.39412997903564, "percentage": 56.97, "elapsed_time": "1:23:05", "remaining_time": "1:02:45", "throughput": 2851.48, "total_tokens": 14214720} {"current_steps": 21745, "total_steps": 38160, "loss": 0.0797, "lr": 2.3272513794928054e-05, "epoch": 11.396750524109015, "percentage": 56.98, "elapsed_time": "1:23:06", "remaining_time": "1:02:43", "throughput": 2851.45, "total_tokens": 14217664} {"current_steps": 21750, "total_steps": 38160, "loss": 0.0678, "lr": 2.326110702157516e-05, "epoch": 11.39937106918239, "percentage": 57.0, "elapsed_time": "1:23:07", "remaining_time": "1:02:42", "throughput": 2851.51, "total_tokens": 14221216} {"current_steps": 21755, "total_steps": 38160, "loss": 0.0784, "lr": 2.3249700611978847e-05, "epoch": 11.401991614255765, "percentage": 57.01, "elapsed_time": "1:23:08", "remaining_time": "1:02:41", "throughput": 2851.46, "total_tokens": 14224000} {"current_steps": 21760, "total_steps": 38160, "loss": 0.0789, "lr": 2.323829456852519e-05, "epoch": 11.40461215932914, "percentage": 57.02, "elapsed_time": "1:23:09", "remaining_time": "1:02:40", "throughput": 2851.55, "total_tokens": 14227872} {"current_steps": 21765, "total_steps": 38160, "loss": 0.0826, "lr": 2.3226888893600223e-05, "epoch": 11.407232704402515, "percentage": 57.04, "elapsed_time": "1:23:10", "remaining_time": "1:02:39", "throughput": 2851.72, "total_tokens": 14231936} {"current_steps": 21770, "total_steps": 38160, "loss": 0.0616, "lr": 2.3215483589589865e-05, "epoch": 11.40985324947589, "percentage": 57.05, "elapsed_time": "1:23:11", "remaining_time": "1:02:38", "throughput": 2851.77, "total_tokens": 14235328} {"current_steps": 21775, "total_steps": 38160, "loss": 0.0847, "lr": 2.3204078658879974e-05, "epoch": 11.412473794549266, "percentage": 57.06, "elapsed_time": "1:23:12", "remaining_time": "1:02:36", "throughput": 2851.83, "total_tokens": 14238848} {"current_steps": 21780, "total_steps": 38160, "loss": 0.0938, "lr": 2.3192674103856337e-05, "epoch": 11.415094339622641, "percentage": 57.08, "elapsed_time": "1:23:13", "remaining_time": "1:02:35", "throughput": 2851.91, "total_tokens": 14242336} {"current_steps": 21785, "total_steps": 38160, "loss": 0.0818, "lr": 2.318126992690467e-05, "epoch": 11.417714884696016, "percentage": 57.09, "elapsed_time": "1:23:15", "remaining_time": "1:02:34", "throughput": 2851.99, "total_tokens": 14245728} {"current_steps": 21790, "total_steps": 38160, "loss": 0.0431, "lr": 2.3169866130410585e-05, "epoch": 11.420335429769391, "percentage": 57.1, "elapsed_time": "1:23:16", "remaining_time": "1:02:33", "throughput": 2851.93, "total_tokens": 14248448} {"current_steps": 21795, "total_steps": 38160, "loss": 0.0412, "lr": 2.315846271675962e-05, "epoch": 11.422955974842766, "percentage": 57.11, "elapsed_time": "1:23:17", "remaining_time": "1:02:32", "throughput": 2851.97, "total_tokens": 14251648} {"current_steps": 21800, "total_steps": 38160, "loss": 0.0524, "lr": 2.3147059688337244e-05, "epoch": 11.425576519916142, "percentage": 57.13, "elapsed_time": "1:23:18", "remaining_time": "1:02:30", "throughput": 2851.96, "total_tokens": 14254624} {"current_steps": 21805, "total_steps": 38160, "loss": 0.0527, "lr": 2.313565704752884e-05, "epoch": 11.428197064989519, "percentage": 57.14, "elapsed_time": "1:23:19", "remaining_time": "1:02:29", "throughput": 2851.98, "total_tokens": 14257728} {"current_steps": 21810, "total_steps": 38160, "loss": 0.1395, "lr": 2.3124254796719718e-05, "epoch": 11.430817610062894, "percentage": 57.15, "elapsed_time": "1:23:20", "remaining_time": "1:02:28", "throughput": 2852.13, "total_tokens": 14262176} {"current_steps": 21815, "total_steps": 38160, "loss": 0.0778, "lr": 2.3112852938295088e-05, "epoch": 11.433438155136269, "percentage": 57.17, "elapsed_time": "1:23:21", "remaining_time": "1:02:27", "throughput": 2852.23, "total_tokens": 14265760} {"current_steps": 21820, "total_steps": 38160, "loss": 0.0772, "lr": 2.3101451474640104e-05, "epoch": 11.436058700209644, "percentage": 57.18, "elapsed_time": "1:23:22", "remaining_time": "1:02:26", "throughput": 2852.21, "total_tokens": 14268768} {"current_steps": 21825, "total_steps": 38160, "loss": 0.0898, "lr": 2.3090050408139808e-05, "epoch": 11.43867924528302, "percentage": 57.19, "elapsed_time": "1:23:23", "remaining_time": "1:02:25", "throughput": 2852.23, "total_tokens": 14272064} {"current_steps": 21830, "total_steps": 38160, "loss": 0.1113, "lr": 2.307864974117917e-05, "epoch": 11.441299790356394, "percentage": 57.21, "elapsed_time": "1:23:24", "remaining_time": "1:02:23", "throughput": 2852.24, "total_tokens": 14275456} {"current_steps": 21835, "total_steps": 38160, "loss": 0.0822, "lr": 2.3067249476143087e-05, "epoch": 11.44392033542977, "percentage": 57.22, "elapsed_time": "1:23:26", "remaining_time": "1:02:22", "throughput": 2852.42, "total_tokens": 14279712} {"current_steps": 21840, "total_steps": 38160, "loss": 0.0638, "lr": 2.3055849615416363e-05, "epoch": 11.446540880503145, "percentage": 57.23, "elapsed_time": "1:23:27", "remaining_time": "1:02:21", "throughput": 2852.59, "total_tokens": 14283616} {"current_steps": 21845, "total_steps": 38160, "loss": 0.0651, "lr": 2.304445016138372e-05, "epoch": 11.44916142557652, "percentage": 57.25, "elapsed_time": "1:23:28", "remaining_time": "1:02:20", "throughput": 2852.6, "total_tokens": 14286720} {"current_steps": 21850, "total_steps": 38160, "loss": 0.0703, "lr": 2.303305111642981e-05, "epoch": 11.451781970649895, "percentage": 57.26, "elapsed_time": "1:23:29", "remaining_time": "1:02:19", "throughput": 2852.76, "total_tokens": 14291232} {"current_steps": 21855, "total_steps": 38160, "loss": 0.0666, "lr": 2.3021652482939144e-05, "epoch": 11.45440251572327, "percentage": 57.27, "elapsed_time": "1:23:30", "remaining_time": "1:02:18", "throughput": 2852.76, "total_tokens": 14294496} {"current_steps": 21860, "total_steps": 38160, "loss": 0.0395, "lr": 2.3010254263296214e-05, "epoch": 11.457023060796645, "percentage": 57.29, "elapsed_time": "1:23:31", "remaining_time": "1:02:17", "throughput": 2852.64, "total_tokens": 14297088} {"current_steps": 21865, "total_steps": 38160, "loss": 0.0694, "lr": 2.2998856459885396e-05, "epoch": 11.45964360587002, "percentage": 57.3, "elapsed_time": "1:23:33", "remaining_time": "1:02:15", "throughput": 2852.77, "total_tokens": 14301056} {"current_steps": 21870, "total_steps": 38160, "loss": 0.059, "lr": 2.298745907509097e-05, "epoch": 11.462264150943396, "percentage": 57.31, "elapsed_time": "1:23:34", "remaining_time": "1:02:14", "throughput": 2852.73, "total_tokens": 14303968} {"current_steps": 21875, "total_steps": 38160, "loss": 0.0885, "lr": 2.2976062111297156e-05, "epoch": 11.464884696016771, "percentage": 57.32, "elapsed_time": "1:23:35", "remaining_time": "1:02:13", "throughput": 2852.93, "total_tokens": 14308256} {"current_steps": 21880, "total_steps": 38160, "loss": 0.1131, "lr": 2.296466557088805e-05, "epoch": 11.467505241090146, "percentage": 57.34, "elapsed_time": "1:23:36", "remaining_time": "1:02:12", "throughput": 2852.96, "total_tokens": 14311424} {"current_steps": 21885, "total_steps": 38160, "loss": 0.092, "lr": 2.2953269456247688e-05, "epoch": 11.470125786163521, "percentage": 57.35, "elapsed_time": "1:23:37", "remaining_time": "1:02:11", "throughput": 2852.97, "total_tokens": 14314752} {"current_steps": 21890, "total_steps": 38160, "loss": 0.0471, "lr": 2.2941873769760006e-05, "epoch": 11.472746331236896, "percentage": 57.36, "elapsed_time": "1:23:38", "remaining_time": "1:02:10", "throughput": 2852.97, "total_tokens": 14317760} {"current_steps": 21895, "total_steps": 38160, "loss": 0.099, "lr": 2.2930478513808844e-05, "epoch": 11.475366876310272, "percentage": 57.38, "elapsed_time": "1:23:39", "remaining_time": "1:02:08", "throughput": 2853.09, "total_tokens": 14321440} {"current_steps": 21900, "total_steps": 38160, "loss": 0.0748, "lr": 2.2919083690777976e-05, "epoch": 11.477987421383649, "percentage": 57.39, "elapsed_time": "1:23:40", "remaining_time": "1:02:07", "throughput": 2853.07, "total_tokens": 14324512} {"current_steps": 21905, "total_steps": 38160, "loss": 0.1023, "lr": 2.2907689303051062e-05, "epoch": 11.480607966457024, "percentage": 57.4, "elapsed_time": "1:23:41", "remaining_time": "1:02:06", "throughput": 2853.05, "total_tokens": 14327648} {"current_steps": 21910, "total_steps": 38160, "loss": 0.1158, "lr": 2.289629535301167e-05, "epoch": 11.483228511530399, "percentage": 57.42, "elapsed_time": "1:23:43", "remaining_time": "1:02:05", "throughput": 2853.07, "total_tokens": 14331040} {"current_steps": 21915, "total_steps": 38160, "loss": 0.0498, "lr": 2.288490184304329e-05, "epoch": 11.485849056603774, "percentage": 57.43, "elapsed_time": "1:23:44", "remaining_time": "1:02:04", "throughput": 2853.02, "total_tokens": 14333920} {"current_steps": 21920, "total_steps": 38160, "loss": 0.0611, "lr": 2.2873508775529308e-05, "epoch": 11.48846960167715, "percentage": 57.44, "elapsed_time": "1:23:45", "remaining_time": "1:02:03", "throughput": 2853.05, "total_tokens": 14337056} {"current_steps": 21925, "total_steps": 38160, "loss": 0.0558, "lr": 2.2862116152853034e-05, "epoch": 11.491090146750524, "percentage": 57.46, "elapsed_time": "1:23:46", "remaining_time": "1:02:01", "throughput": 2852.94, "total_tokens": 14339584} {"current_steps": 21930, "total_steps": 38160, "loss": 0.0487, "lr": 2.285072397739767e-05, "epoch": 11.4937106918239, "percentage": 57.47, "elapsed_time": "1:23:47", "remaining_time": "1:02:01", "throughput": 2853.07, "total_tokens": 14345024} {"current_steps": 21935, "total_steps": 38160, "loss": 0.0473, "lr": 2.283933225154634e-05, "epoch": 11.496331236897275, "percentage": 57.48, "elapsed_time": "1:23:48", "remaining_time": "1:01:59", "throughput": 2853.11, "total_tokens": 14348288} {"current_steps": 21940, "total_steps": 38160, "loss": 0.1087, "lr": 2.2827940977682045e-05, "epoch": 11.49895178197065, "percentage": 57.49, "elapsed_time": "1:23:50", "remaining_time": "1:01:58", "throughput": 2853.23, "total_tokens": 14352000} {"current_steps": 21945, "total_steps": 38160, "loss": 0.043, "lr": 2.2816550158187717e-05, "epoch": 11.501572327044025, "percentage": 57.51, "elapsed_time": "1:23:51", "remaining_time": "1:01:57", "throughput": 2853.07, "total_tokens": 14354336} {"current_steps": 21950, "total_steps": 38160, "loss": 0.1108, "lr": 2.2805159795446182e-05, "epoch": 11.5041928721174, "percentage": 57.52, "elapsed_time": "1:23:52", "remaining_time": "1:01:56", "throughput": 2853.13, "total_tokens": 14357728} {"current_steps": 21955, "total_steps": 38160, "loss": 0.097, "lr": 2.2793769891840184e-05, "epoch": 11.506813417190775, "percentage": 57.53, "elapsed_time": "1:23:53", "remaining_time": "1:01:55", "throughput": 2853.03, "total_tokens": 14360384} {"current_steps": 21960, "total_steps": 38160, "loss": 0.0951, "lr": 2.278238044975236e-05, "epoch": 11.50943396226415, "percentage": 57.55, "elapsed_time": "1:23:54", "remaining_time": "1:01:54", "throughput": 2853.19, "total_tokens": 14364800} {"current_steps": 21965, "total_steps": 38160, "loss": 0.0426, "lr": 2.2770991471565236e-05, "epoch": 11.512054507337526, "percentage": 57.56, "elapsed_time": "1:23:55", "remaining_time": "1:01:52", "throughput": 2853.17, "total_tokens": 14367872} {"current_steps": 21970, "total_steps": 38160, "loss": 0.0925, "lr": 2.2759602959661265e-05, "epoch": 11.514675052410901, "percentage": 57.57, "elapsed_time": "1:23:57", "remaining_time": "1:01:51", "throughput": 2853.26, "total_tokens": 14371872} {"current_steps": 21975, "total_steps": 38160, "loss": 0.0659, "lr": 2.2748214916422796e-05, "epoch": 11.517295597484276, "percentage": 57.59, "elapsed_time": "1:23:58", "remaining_time": "1:01:50", "throughput": 2853.22, "total_tokens": 14374752} {"current_steps": 21980, "total_steps": 38160, "loss": 0.0617, "lr": 2.2736827344232082e-05, "epoch": 11.519916142557651, "percentage": 57.6, "elapsed_time": "1:23:59", "remaining_time": "1:01:49", "throughput": 2853.21, "total_tokens": 14377792} {"current_steps": 21985, "total_steps": 38160, "loss": 0.0683, "lr": 2.272544024547126e-05, "epoch": 11.522536687631026, "percentage": 57.61, "elapsed_time": "1:24:00", "remaining_time": "1:01:48", "throughput": 2853.42, "total_tokens": 14382496} {"current_steps": 21990, "total_steps": 38160, "loss": 0.0765, "lr": 2.27140536225224e-05, "epoch": 11.525157232704402, "percentage": 57.63, "elapsed_time": "1:24:02", "remaining_time": "1:01:47", "throughput": 2853.65, "total_tokens": 14389184} {"current_steps": 21995, "total_steps": 38160, "loss": 0.0793, "lr": 2.270266747776744e-05, "epoch": 11.527777777777779, "percentage": 57.64, "elapsed_time": "1:24:03", "remaining_time": "1:01:46", "throughput": 2853.55, "total_tokens": 14391904} {"current_steps": 22000, "total_steps": 38160, "loss": 0.0669, "lr": 2.2691281813588226e-05, "epoch": 11.530398322851154, "percentage": 57.65, "elapsed_time": "1:24:04", "remaining_time": "1:01:45", "throughput": 2853.54, "total_tokens": 14394880} {"current_steps": 22005, "total_steps": 38160, "loss": 0.0875, "lr": 2.267989663236652e-05, "epoch": 11.533018867924529, "percentage": 57.67, "elapsed_time": "1:24:05", "remaining_time": "1:01:44", "throughput": 2853.66, "total_tokens": 14399168} {"current_steps": 22010, "total_steps": 38160, "loss": 0.0707, "lr": 2.2668511936483975e-05, "epoch": 11.535639412997904, "percentage": 57.68, "elapsed_time": "1:24:07", "remaining_time": "1:01:43", "throughput": 2853.72, "total_tokens": 14402848} {"current_steps": 22015, "total_steps": 38160, "loss": 0.0846, "lr": 2.2657127728322124e-05, "epoch": 11.53825995807128, "percentage": 57.69, "elapsed_time": "1:24:08", "remaining_time": "1:01:42", "throughput": 2853.77, "total_tokens": 14406272} {"current_steps": 22020, "total_steps": 38160, "loss": 0.0582, "lr": 2.264574401026244e-05, "epoch": 11.540880503144654, "percentage": 57.7, "elapsed_time": "1:24:09", "remaining_time": "1:01:40", "throughput": 2853.68, "total_tokens": 14409120} {"current_steps": 22025, "total_steps": 38160, "loss": 0.0813, "lr": 2.2634360784686242e-05, "epoch": 11.54350104821803, "percentage": 57.72, "elapsed_time": "1:24:10", "remaining_time": "1:01:39", "throughput": 2853.69, "total_tokens": 14412224} {"current_steps": 22030, "total_steps": 38160, "loss": 0.0593, "lr": 2.2622978053974776e-05, "epoch": 11.546121593291405, "percentage": 57.73, "elapsed_time": "1:24:11", "remaining_time": "1:01:38", "throughput": 2853.74, "total_tokens": 14415616} {"current_steps": 22035, "total_steps": 38160, "loss": 0.1536, "lr": 2.2611595820509186e-05, "epoch": 11.54874213836478, "percentage": 57.74, "elapsed_time": "1:24:12", "remaining_time": "1:01:37", "throughput": 2853.81, "total_tokens": 14419392} {"current_steps": 22040, "total_steps": 38160, "loss": 0.08, "lr": 2.2600214086670494e-05, "epoch": 11.551362683438155, "percentage": 57.76, "elapsed_time": "1:24:13", "remaining_time": "1:01:36", "throughput": 2853.91, "total_tokens": 14423040} {"current_steps": 22045, "total_steps": 38160, "loss": 0.1369, "lr": 2.2588832854839644e-05, "epoch": 11.55398322851153, "percentage": 57.77, "elapsed_time": "1:24:14", "remaining_time": "1:01:35", "throughput": 2853.96, "total_tokens": 14426656} {"current_steps": 22050, "total_steps": 38160, "loss": 0.059, "lr": 2.2577452127397463e-05, "epoch": 11.556603773584905, "percentage": 57.78, "elapsed_time": "1:24:16", "remaining_time": "1:01:34", "throughput": 2853.93, "total_tokens": 14429792} {"current_steps": 22055, "total_steps": 38160, "loss": 0.0524, "lr": 2.256607190672464e-05, "epoch": 11.55922431865828, "percentage": 57.8, "elapsed_time": "1:24:17", "remaining_time": "1:01:32", "throughput": 2853.9, "total_tokens": 14432992} {"current_steps": 22060, "total_steps": 38160, "loss": 0.0383, "lr": 2.2554692195201817e-05, "epoch": 11.561844863731656, "percentage": 57.81, "elapsed_time": "1:24:18", "remaining_time": "1:01:31", "throughput": 2853.92, "total_tokens": 14436448} {"current_steps": 22065, "total_steps": 38160, "loss": 0.0921, "lr": 2.254331299520948e-05, "epoch": 11.564465408805031, "percentage": 57.82, "elapsed_time": "1:24:19", "remaining_time": "1:01:30", "throughput": 2853.75, "total_tokens": 14438880} {"current_steps": 22070, "total_steps": 38160, "loss": 0.0685, "lr": 2.253193430912805e-05, "epoch": 11.567085953878406, "percentage": 57.84, "elapsed_time": "1:24:20", "remaining_time": "1:01:29", "throughput": 2853.54, "total_tokens": 14441248} {"current_steps": 22075, "total_steps": 38160, "loss": 0.0656, "lr": 2.2520556139337803e-05, "epoch": 11.569706498951781, "percentage": 57.85, "elapsed_time": "1:24:22", "remaining_time": "1:01:28", "throughput": 2853.53, "total_tokens": 14444576} {"current_steps": 22080, "total_steps": 38160, "loss": 0.0763, "lr": 2.250917848821892e-05, "epoch": 11.572327044025156, "percentage": 57.86, "elapsed_time": "1:24:23", "remaining_time": "1:01:27", "throughput": 2853.56, "total_tokens": 14447968} {"current_steps": 22085, "total_steps": 38160, "loss": 0.1052, "lr": 2.2497801358151472e-05, "epoch": 11.574947589098532, "percentage": 57.87, "elapsed_time": "1:24:24", "remaining_time": "1:01:26", "throughput": 2853.51, "total_tokens": 14450816} {"current_steps": 22090, "total_steps": 38160, "loss": 0.0567, "lr": 2.248642475151545e-05, "epoch": 11.577568134171909, "percentage": 57.89, "elapsed_time": "1:24:25", "remaining_time": "1:01:24", "throughput": 2853.49, "total_tokens": 14453728} {"current_steps": 22095, "total_steps": 38160, "loss": 0.1936, "lr": 2.2475048670690678e-05, "epoch": 11.580188679245284, "percentage": 57.9, "elapsed_time": "1:24:26", "remaining_time": "1:01:23", "throughput": 2853.44, "total_tokens": 14456512} {"current_steps": 22100, "total_steps": 38160, "loss": 0.0905, "lr": 2.2463673118056927e-05, "epoch": 11.582809224318659, "percentage": 57.91, "elapsed_time": "1:24:27", "remaining_time": "1:01:22", "throughput": 2853.5, "total_tokens": 14460160} {"current_steps": 22105, "total_steps": 38160, "loss": 0.0741, "lr": 2.245229809599383e-05, "epoch": 11.585429769392034, "percentage": 57.93, "elapsed_time": "1:24:28", "remaining_time": "1:01:21", "throughput": 2853.4, "total_tokens": 14462848} {"current_steps": 22110, "total_steps": 38160, "loss": 0.0655, "lr": 2.2440923606880896e-05, "epoch": 11.58805031446541, "percentage": 57.94, "elapsed_time": "1:24:29", "remaining_time": "1:01:20", "throughput": 2853.49, "total_tokens": 14466592} {"current_steps": 22115, "total_steps": 38160, "loss": 0.065, "lr": 2.242954965309755e-05, "epoch": 11.590670859538784, "percentage": 57.95, "elapsed_time": "1:24:30", "remaining_time": "1:01:19", "throughput": 2853.36, "total_tokens": 14468960} {"current_steps": 22120, "total_steps": 38160, "loss": 0.0754, "lr": 2.2418176237023088e-05, "epoch": 11.59329140461216, "percentage": 57.97, "elapsed_time": "1:24:31", "remaining_time": "1:01:17", "throughput": 2853.51, "total_tokens": 14472864} {"current_steps": 22125, "total_steps": 38160, "loss": 0.0793, "lr": 2.2406803361036706e-05, "epoch": 11.595911949685535, "percentage": 57.98, "elapsed_time": "1:24:33", "remaining_time": "1:01:16", "throughput": 2853.62, "total_tokens": 14476768} {"current_steps": 22130, "total_steps": 38160, "loss": 0.0735, "lr": 2.2395431027517475e-05, "epoch": 11.59853249475891, "percentage": 57.99, "elapsed_time": "1:24:34", "remaining_time": "1:01:15", "throughput": 2853.58, "total_tokens": 14479872} {"current_steps": 22135, "total_steps": 38160, "loss": 0.0872, "lr": 2.2384059238844364e-05, "epoch": 11.601153039832285, "percentage": 58.01, "elapsed_time": "1:24:35", "remaining_time": "1:01:14", "throughput": 2853.46, "total_tokens": 14482400} {"current_steps": 22140, "total_steps": 38160, "loss": 0.0758, "lr": 2.2372687997396215e-05, "epoch": 11.60377358490566, "percentage": 58.02, "elapsed_time": "1:24:36", "remaining_time": "1:01:13", "throughput": 2853.5, "total_tokens": 14485696} {"current_steps": 22145, "total_steps": 38160, "loss": 0.1186, "lr": 2.2361317305551756e-05, "epoch": 11.606394129979035, "percentage": 58.03, "elapsed_time": "1:24:37", "remaining_time": "1:01:12", "throughput": 2853.45, "total_tokens": 14488800} {"current_steps": 22150, "total_steps": 38160, "loss": 0.081, "lr": 2.2349947165689615e-05, "epoch": 11.60901467505241, "percentage": 58.05, "elapsed_time": "1:24:38", "remaining_time": "1:01:10", "throughput": 2853.38, "total_tokens": 14491520} {"current_steps": 22155, "total_steps": 38160, "loss": 0.0439, "lr": 2.2338577580188296e-05, "epoch": 11.611635220125786, "percentage": 58.06, "elapsed_time": "1:24:39", "remaining_time": "1:01:09", "throughput": 2853.28, "total_tokens": 14494176} {"current_steps": 22160, "total_steps": 38160, "loss": 0.0734, "lr": 2.2327208551426188e-05, "epoch": 11.614255765199161, "percentage": 58.07, "elapsed_time": "1:24:40", "remaining_time": "1:01:08", "throughput": 2853.15, "total_tokens": 14496640} {"current_steps": 22165, "total_steps": 38160, "loss": 0.0883, "lr": 2.2315840081781546e-05, "epoch": 11.616876310272536, "percentage": 58.08, "elapsed_time": "1:24:41", "remaining_time": "1:01:07", "throughput": 2853.06, "total_tokens": 14499232} {"current_steps": 22170, "total_steps": 38160, "loss": 0.0637, "lr": 2.230447217363255e-05, "epoch": 11.619496855345911, "percentage": 58.1, "elapsed_time": "1:24:43", "remaining_time": "1:01:06", "throughput": 2852.95, "total_tokens": 14501600} {"current_steps": 22175, "total_steps": 38160, "loss": 0.0603, "lr": 2.2293104829357212e-05, "epoch": 11.622117400419286, "percentage": 58.11, "elapsed_time": "1:24:44", "remaining_time": "1:01:04", "throughput": 2852.91, "total_tokens": 14504544} {"current_steps": 22180, "total_steps": 38160, "loss": 0.0487, "lr": 2.2281738051333467e-05, "epoch": 11.624737945492662, "percentage": 58.12, "elapsed_time": "1:24:45", "remaining_time": "1:01:03", "throughput": 2852.94, "total_tokens": 14507904} {"current_steps": 22185, "total_steps": 38160, "loss": 0.0528, "lr": 2.2270371841939105e-05, "epoch": 11.627358490566039, "percentage": 58.14, "elapsed_time": "1:24:46", "remaining_time": "1:01:02", "throughput": 2852.95, "total_tokens": 14511264} {"current_steps": 22190, "total_steps": 38160, "loss": 0.0665, "lr": 2.2259006203551824e-05, "epoch": 11.629979035639414, "percentage": 58.15, "elapsed_time": "1:24:47", "remaining_time": "1:01:01", "throughput": 2852.99, "total_tokens": 14514752} {"current_steps": 22195, "total_steps": 38160, "loss": 0.0552, "lr": 2.2247641138549168e-05, "epoch": 11.632599580712789, "percentage": 58.16, "elapsed_time": "1:24:48", "remaining_time": "1:01:00", "throughput": 2852.9, "total_tokens": 14517312} {"current_steps": 22200, "total_steps": 38160, "loss": 0.0804, "lr": 2.2236276649308583e-05, "epoch": 11.635220125786164, "percentage": 58.18, "elapsed_time": "1:24:49", "remaining_time": "1:00:59", "throughput": 2852.98, "total_tokens": 14520800} {"current_steps": 22205, "total_steps": 38160, "loss": 0.0515, "lr": 2.2224912738207395e-05, "epoch": 11.63784067085954, "percentage": 58.19, "elapsed_time": "1:24:50", "remaining_time": "1:00:57", "throughput": 2852.95, "total_tokens": 14524000} {"current_steps": 22210, "total_steps": 38160, "loss": 0.061, "lr": 2.2213549407622796e-05, "epoch": 11.640461215932914, "percentage": 58.2, "elapsed_time": "1:24:51", "remaining_time": "1:00:56", "throughput": 2852.91, "total_tokens": 14526944} {"current_steps": 22215, "total_steps": 38160, "loss": 0.0586, "lr": 2.220218665993188e-05, "epoch": 11.64308176100629, "percentage": 58.22, "elapsed_time": "1:24:53", "remaining_time": "1:00:55", "throughput": 2852.95, "total_tokens": 14530368} {"current_steps": 22220, "total_steps": 38160, "loss": 0.0476, "lr": 2.21908244975116e-05, "epoch": 11.645702306079665, "percentage": 58.23, "elapsed_time": "1:24:54", "remaining_time": "1:00:54", "throughput": 2853.0, "total_tokens": 14533824} {"current_steps": 22225, "total_steps": 38160, "loss": 0.0618, "lr": 2.2179462922738776e-05, "epoch": 11.64832285115304, "percentage": 58.24, "elapsed_time": "1:24:55", "remaining_time": "1:00:53", "throughput": 2853.22, "total_tokens": 14539232} {"current_steps": 22230, "total_steps": 38160, "loss": 0.0583, "lr": 2.2168101937990135e-05, "epoch": 11.650943396226415, "percentage": 58.25, "elapsed_time": "1:24:56", "remaining_time": "1:00:52", "throughput": 2853.3, "total_tokens": 14542784} {"current_steps": 22235, "total_steps": 38160, "loss": 0.0877, "lr": 2.2156741545642253e-05, "epoch": 11.65356394129979, "percentage": 58.27, "elapsed_time": "1:24:57", "remaining_time": "1:00:51", "throughput": 2853.23, "total_tokens": 14545696} {"current_steps": 22240, "total_steps": 38160, "loss": 0.0522, "lr": 2.2145381748071606e-05, "epoch": 11.656184486373165, "percentage": 58.28, "elapsed_time": "1:24:59", "remaining_time": "1:00:50", "throughput": 2853.3, "total_tokens": 14549344} {"current_steps": 22245, "total_steps": 38160, "loss": 0.056, "lr": 2.2134022547654538e-05, "epoch": 11.65880503144654, "percentage": 58.29, "elapsed_time": "1:25:00", "remaining_time": "1:00:48", "throughput": 2853.24, "total_tokens": 14552096} {"current_steps": 22250, "total_steps": 38160, "loss": 0.064, "lr": 2.212266394676725e-05, "epoch": 11.661425576519916, "percentage": 58.31, "elapsed_time": "1:25:01", "remaining_time": "1:00:47", "throughput": 2853.3, "total_tokens": 14556384} {"current_steps": 22255, "total_steps": 38160, "loss": 0.0525, "lr": 2.2111305947785836e-05, "epoch": 11.664046121593291, "percentage": 58.32, "elapsed_time": "1:25:02", "remaining_time": "1:00:46", "throughput": 2853.31, "total_tokens": 14559680} {"current_steps": 22260, "total_steps": 38160, "loss": 0.0641, "lr": 2.2099948553086263e-05, "epoch": 11.666666666666666, "percentage": 58.33, "elapsed_time": "1:25:03", "remaining_time": "1:00:45", "throughput": 2853.29, "total_tokens": 14562592} {"current_steps": 22265, "total_steps": 38160, "loss": 0.0722, "lr": 2.2088591765044365e-05, "epoch": 11.669287211740041, "percentage": 58.35, "elapsed_time": "1:25:04", "remaining_time": "1:00:44", "throughput": 2853.12, "total_tokens": 14564960} {"current_steps": 22270, "total_steps": 38160, "loss": 0.1105, "lr": 2.207723558603586e-05, "epoch": 11.671907756813416, "percentage": 58.36, "elapsed_time": "1:25:05", "remaining_time": "1:00:43", "throughput": 2853.19, "total_tokens": 14568384} {"current_steps": 22275, "total_steps": 38160, "loss": 0.0753, "lr": 2.206588001843633e-05, "epoch": 11.674528301886792, "percentage": 58.37, "elapsed_time": "1:25:07", "remaining_time": "1:00:42", "throughput": 2853.23, "total_tokens": 14571680} {"current_steps": 22280, "total_steps": 38160, "loss": 0.1019, "lr": 2.2054525064621216e-05, "epoch": 11.677148846960169, "percentage": 58.39, "elapsed_time": "1:25:08", "remaining_time": "1:00:40", "throughput": 2853.27, "total_tokens": 14575136} {"current_steps": 22285, "total_steps": 38160, "loss": 0.061, "lr": 2.2043170726965858e-05, "epoch": 11.679769392033544, "percentage": 58.4, "elapsed_time": "1:25:09", "remaining_time": "1:00:39", "throughput": 2853.21, "total_tokens": 14577888} {"current_steps": 22290, "total_steps": 38160, "loss": 0.0651, "lr": 2.2031817007845447e-05, "epoch": 11.682389937106919, "percentage": 58.41, "elapsed_time": "1:25:10", "remaining_time": "1:00:38", "throughput": 2853.23, "total_tokens": 14581248} {"current_steps": 22295, "total_steps": 38160, "loss": 0.0924, "lr": 2.202046390963506e-05, "epoch": 11.685010482180294, "percentage": 58.43, "elapsed_time": "1:25:11", "remaining_time": "1:00:37", "throughput": 2853.29, "total_tokens": 14584928} {"current_steps": 22300, "total_steps": 38160, "loss": 0.0928, "lr": 2.2009111434709627e-05, "epoch": 11.68763102725367, "percentage": 58.44, "elapsed_time": "1:25:12", "remaining_time": "1:00:36", "throughput": 2853.21, "total_tokens": 14587552} {"current_steps": 22305, "total_steps": 38160, "loss": 0.0513, "lr": 2.1997759585443968e-05, "epoch": 11.690251572327044, "percentage": 58.45, "elapsed_time": "1:25:13", "remaining_time": "1:00:35", "throughput": 2853.04, "total_tokens": 14589760} {"current_steps": 22310, "total_steps": 38160, "loss": 0.0318, "lr": 2.198640836421275e-05, "epoch": 11.69287211740042, "percentage": 58.46, "elapsed_time": "1:25:14", "remaining_time": "1:00:33", "throughput": 2852.97, "total_tokens": 14592448} {"current_steps": 22315, "total_steps": 38160, "loss": 0.0785, "lr": 2.1975057773390515e-05, "epoch": 11.695492662473795, "percentage": 58.48, "elapsed_time": "1:25:15", "remaining_time": "1:00:32", "throughput": 2852.99, "total_tokens": 14595808} {"current_steps": 22320, "total_steps": 38160, "loss": 0.0643, "lr": 2.1963707815351683e-05, "epoch": 11.69811320754717, "percentage": 58.49, "elapsed_time": "1:25:17", "remaining_time": "1:00:31", "throughput": 2852.96, "total_tokens": 14598624} {"current_steps": 22325, "total_steps": 38160, "loss": 0.0805, "lr": 2.1952358492470544e-05, "epoch": 11.700733752620545, "percentage": 58.5, "elapsed_time": "1:25:18", "remaining_time": "1:00:30", "throughput": 2852.92, "total_tokens": 14601536} {"current_steps": 22330, "total_steps": 38160, "loss": 0.0524, "lr": 2.194100980712124e-05, "epoch": 11.70335429769392, "percentage": 58.52, "elapsed_time": "1:25:19", "remaining_time": "1:00:29", "throughput": 2852.92, "total_tokens": 14604736} {"current_steps": 22335, "total_steps": 38160, "loss": 0.072, "lr": 2.1929661761677774e-05, "epoch": 11.705974842767295, "percentage": 58.53, "elapsed_time": "1:25:20", "remaining_time": "1:00:27", "throughput": 2852.92, "total_tokens": 14607840} {"current_steps": 22340, "total_steps": 38160, "loss": 0.0947, "lr": 2.191831435851405e-05, "epoch": 11.70859538784067, "percentage": 58.54, "elapsed_time": "1:25:21", "remaining_time": "1:00:26", "throughput": 2852.9, "total_tokens": 14610816} {"current_steps": 22345, "total_steps": 38160, "loss": 0.103, "lr": 2.1906967600003793e-05, "epoch": 11.711215932914046, "percentage": 58.56, "elapsed_time": "1:25:22", "remaining_time": "1:00:25", "throughput": 2853.01, "total_tokens": 14614464} {"current_steps": 22350, "total_steps": 38160, "loss": 0.0532, "lr": 2.1895621488520636e-05, "epoch": 11.713836477987421, "percentage": 58.57, "elapsed_time": "1:25:23", "remaining_time": "1:00:24", "throughput": 2852.83, "total_tokens": 14616704} {"current_steps": 22355, "total_steps": 38160, "loss": 0.0713, "lr": 2.1884276026438044e-05, "epoch": 11.716457023060796, "percentage": 58.58, "elapsed_time": "1:25:24", "remaining_time": "1:00:23", "throughput": 2852.92, "total_tokens": 14620832} {"current_steps": 22360, "total_steps": 38160, "loss": 0.0687, "lr": 2.187293121612937e-05, "epoch": 11.719077568134171, "percentage": 58.6, "elapsed_time": "1:25:25", "remaining_time": "1:00:22", "throughput": 2852.78, "total_tokens": 14623328} {"current_steps": 22365, "total_steps": 38160, "loss": 0.0986, "lr": 2.1861587059967804e-05, "epoch": 11.721698113207546, "percentage": 58.61, "elapsed_time": "1:25:27", "remaining_time": "1:00:21", "throughput": 2852.92, "total_tokens": 14627520} {"current_steps": 22370, "total_steps": 38160, "loss": 0.043, "lr": 2.1850243560326414e-05, "epoch": 11.724318658280922, "percentage": 58.62, "elapsed_time": "1:25:28", "remaining_time": "1:00:19", "throughput": 2853.05, "total_tokens": 14631712} {"current_steps": 22375, "total_steps": 38160, "loss": 0.0545, "lr": 2.1838900719578143e-05, "epoch": 11.726939203354299, "percentage": 58.63, "elapsed_time": "1:25:29", "remaining_time": "1:00:18", "throughput": 2853.07, "total_tokens": 14634912} {"current_steps": 22380, "total_steps": 38160, "loss": 0.0612, "lr": 2.1827558540095772e-05, "epoch": 11.729559748427674, "percentage": 58.65, "elapsed_time": "1:25:30", "remaining_time": "1:00:17", "throughput": 2852.97, "total_tokens": 14637440} {"current_steps": 22385, "total_steps": 38160, "loss": 0.0869, "lr": 2.1816217024251966e-05, "epoch": 11.732180293501049, "percentage": 58.66, "elapsed_time": "1:25:31", "remaining_time": "1:00:16", "throughput": 2853.21, "total_tokens": 14642336} {"current_steps": 22390, "total_steps": 38160, "loss": 0.1068, "lr": 2.1804876174419242e-05, "epoch": 11.734800838574424, "percentage": 58.67, "elapsed_time": "1:25:33", "remaining_time": "1:00:15", "throughput": 2853.3, "total_tokens": 14646016} {"current_steps": 22395, "total_steps": 38160, "loss": 0.0694, "lr": 2.179353599296996e-05, "epoch": 11.7374213836478, "percentage": 58.69, "elapsed_time": "1:25:34", "remaining_time": "1:00:14", "throughput": 2853.18, "total_tokens": 14648384} {"current_steps": 22400, "total_steps": 38160, "loss": 0.0742, "lr": 2.1782196482276368e-05, "epoch": 11.740041928721174, "percentage": 58.7, "elapsed_time": "1:25:35", "remaining_time": "1:00:12", "throughput": 2853.2, "total_tokens": 14651552} {"current_steps": 22405, "total_steps": 38160, "loss": 0.0512, "lr": 2.1770857644710567e-05, "epoch": 11.74266247379455, "percentage": 58.71, "elapsed_time": "1:25:36", "remaining_time": "1:00:11", "throughput": 2853.1, "total_tokens": 14654304} {"current_steps": 22410, "total_steps": 38160, "loss": 0.0661, "lr": 2.1759519482644495e-05, "epoch": 11.745283018867925, "percentage": 58.73, "elapsed_time": "1:25:37", "remaining_time": "1:00:10", "throughput": 2853.1, "total_tokens": 14657472} {"current_steps": 22415, "total_steps": 38160, "loss": 0.1707, "lr": 2.174818199844999e-05, "epoch": 11.7479035639413, "percentage": 58.74, "elapsed_time": "1:25:38", "remaining_time": "1:00:09", "throughput": 2853.14, "total_tokens": 14660992} {"current_steps": 22420, "total_steps": 38160, "loss": 0.0981, "lr": 2.173684519449872e-05, "epoch": 11.750524109014675, "percentage": 58.75, "elapsed_time": "1:25:39", "remaining_time": "1:00:08", "throughput": 2853.34, "total_tokens": 14665344} {"current_steps": 22425, "total_steps": 38160, "loss": 0.1037, "lr": 2.1725509073162188e-05, "epoch": 11.75314465408805, "percentage": 58.77, "elapsed_time": "1:25:40", "remaining_time": "1:00:07", "throughput": 2853.34, "total_tokens": 14668384} {"current_steps": 22430, "total_steps": 38160, "loss": 0.0615, "lr": 2.171417363681181e-05, "epoch": 11.755765199161425, "percentage": 58.78, "elapsed_time": "1:25:41", "remaining_time": "1:00:05", "throughput": 2853.32, "total_tokens": 14671488} {"current_steps": 22435, "total_steps": 38160, "loss": 0.0703, "lr": 2.1702838887818816e-05, "epoch": 11.7583857442348, "percentage": 58.79, "elapsed_time": "1:25:42", "remaining_time": "1:00:04", "throughput": 2853.33, "total_tokens": 14674592} {"current_steps": 22440, "total_steps": 38160, "loss": 0.1072, "lr": 2.1691504828554315e-05, "epoch": 11.761006289308176, "percentage": 58.81, "elapsed_time": "1:25:44", "remaining_time": "1:00:03", "throughput": 2853.42, "total_tokens": 14678176} {"current_steps": 22445, "total_steps": 38160, "loss": 0.0787, "lr": 2.1680171461389265e-05, "epoch": 11.76362683438155, "percentage": 58.82, "elapsed_time": "1:25:45", "remaining_time": "1:00:02", "throughput": 2853.38, "total_tokens": 14681184} {"current_steps": 22450, "total_steps": 38160, "loss": 0.0593, "lr": 2.166883878869446e-05, "epoch": 11.766247379454926, "percentage": 58.83, "elapsed_time": "1:25:46", "remaining_time": "1:00:01", "throughput": 2853.36, "total_tokens": 14684192} {"current_steps": 22455, "total_steps": 38160, "loss": 0.0647, "lr": 2.1657506812840582e-05, "epoch": 11.768867924528301, "percentage": 58.84, "elapsed_time": "1:25:47", "remaining_time": "1:00:00", "throughput": 2853.33, "total_tokens": 14687040} {"current_steps": 22460, "total_steps": 38160, "loss": 0.0634, "lr": 2.164617553619814e-05, "epoch": 11.771488469601676, "percentage": 58.86, "elapsed_time": "1:25:48", "remaining_time": "0:59:58", "throughput": 2853.36, "total_tokens": 14690592} {"current_steps": 22465, "total_steps": 38160, "loss": 0.0662, "lr": 2.1634844961137517e-05, "epoch": 11.774109014675052, "percentage": 58.87, "elapsed_time": "1:25:49", "remaining_time": "0:59:57", "throughput": 2853.35, "total_tokens": 14693792} {"current_steps": 22470, "total_steps": 38160, "loss": 0.0596, "lr": 2.162351509002893e-05, "epoch": 11.776729559748428, "percentage": 58.88, "elapsed_time": "1:25:50", "remaining_time": "0:59:56", "throughput": 2853.31, "total_tokens": 14696544} {"current_steps": 22475, "total_steps": 38160, "loss": 0.0503, "lr": 2.161218592524248e-05, "epoch": 11.779350104821804, "percentage": 58.9, "elapsed_time": "1:25:51", "remaining_time": "0:59:55", "throughput": 2853.47, "total_tokens": 14700416} {"current_steps": 22480, "total_steps": 38160, "loss": 0.129, "lr": 2.160085746914807e-05, "epoch": 11.781970649895179, "percentage": 58.91, "elapsed_time": "1:25:52", "remaining_time": "0:59:54", "throughput": 2853.49, "total_tokens": 14703648} {"current_steps": 22485, "total_steps": 38160, "loss": 0.0921, "lr": 2.1589529724115503e-05, "epoch": 11.784591194968554, "percentage": 58.92, "elapsed_time": "1:25:53", "remaining_time": "0:59:52", "throughput": 2853.42, "total_tokens": 14706304} {"current_steps": 22490, "total_steps": 38160, "loss": 0.0964, "lr": 2.1578202692514407e-05, "epoch": 11.78721174004193, "percentage": 58.94, "elapsed_time": "1:25:55", "remaining_time": "0:59:51", "throughput": 2853.28, "total_tokens": 14708672} {"current_steps": 22495, "total_steps": 38160, "loss": 0.0632, "lr": 2.1566876376714274e-05, "epoch": 11.789832285115304, "percentage": 58.95, "elapsed_time": "1:25:56", "remaining_time": "0:59:50", "throughput": 2853.33, "total_tokens": 14711904} {"current_steps": 22500, "total_steps": 38160, "loss": 0.0731, "lr": 2.155555077908443e-05, "epoch": 11.79245283018868, "percentage": 58.96, "elapsed_time": "1:25:57", "remaining_time": "0:59:49", "throughput": 2853.17, "total_tokens": 14714080} {"current_steps": 22505, "total_steps": 38160, "loss": 0.0433, "lr": 2.1544225901994077e-05, "epoch": 11.795073375262055, "percentage": 58.98, "elapsed_time": "1:25:58", "remaining_time": "0:59:48", "throughput": 2853.15, "total_tokens": 14717152} {"current_steps": 22510, "total_steps": 38160, "loss": 0.0554, "lr": 2.1532901747812234e-05, "epoch": 11.79769392033543, "percentage": 58.99, "elapsed_time": "1:25:59", "remaining_time": "0:59:46", "throughput": 2853.14, "total_tokens": 14720064} {"current_steps": 22515, "total_steps": 38160, "loss": 0.0806, "lr": 2.1521578318907787e-05, "epoch": 11.800314465408805, "percentage": 59.0, "elapsed_time": "1:26:00", "remaining_time": "0:59:45", "throughput": 2853.09, "total_tokens": 14722848} {"current_steps": 22520, "total_steps": 38160, "loss": 0.0759, "lr": 2.1510255617649476e-05, "epoch": 11.80293501048218, "percentage": 59.01, "elapsed_time": "1:26:01", "remaining_time": "0:59:44", "throughput": 2853.05, "total_tokens": 14725696} {"current_steps": 22525, "total_steps": 38160, "loss": 0.0792, "lr": 2.149893364640587e-05, "epoch": 11.805555555555555, "percentage": 59.03, "elapsed_time": "1:26:02", "remaining_time": "0:59:43", "throughput": 2853.05, "total_tokens": 14728800} {"current_steps": 22530, "total_steps": 38160, "loss": 0.0603, "lr": 2.1487612407545417e-05, "epoch": 11.80817610062893, "percentage": 59.04, "elapsed_time": "1:26:03", "remaining_time": "0:59:42", "throughput": 2853.15, "total_tokens": 14732608} {"current_steps": 22535, "total_steps": 38160, "loss": 0.0593, "lr": 2.147629190343637e-05, "epoch": 11.810796645702306, "percentage": 59.05, "elapsed_time": "1:26:04", "remaining_time": "0:59:41", "throughput": 2853.31, "total_tokens": 14736640} {"current_steps": 22540, "total_steps": 38160, "loss": 0.0391, "lr": 2.1464972136446852e-05, "epoch": 11.81341719077568, "percentage": 59.07, "elapsed_time": "1:26:05", "remaining_time": "0:59:39", "throughput": 2853.24, "total_tokens": 14739296} {"current_steps": 22545, "total_steps": 38160, "loss": 0.0552, "lr": 2.1453653108944838e-05, "epoch": 11.816037735849056, "percentage": 59.08, "elapsed_time": "1:26:06", "remaining_time": "0:59:38", "throughput": 2853.17, "total_tokens": 14742048} {"current_steps": 22550, "total_steps": 38160, "loss": 0.0405, "lr": 2.1442334823298128e-05, "epoch": 11.818658280922431, "percentage": 59.09, "elapsed_time": "1:26:08", "remaining_time": "0:59:37", "throughput": 2853.14, "total_tokens": 14745056} {"current_steps": 22555, "total_steps": 38160, "loss": 0.1927, "lr": 2.1431017281874386e-05, "epoch": 11.821278825995806, "percentage": 59.11, "elapsed_time": "1:26:09", "remaining_time": "0:59:36", "throughput": 2853.13, "total_tokens": 14748064} {"current_steps": 22560, "total_steps": 38160, "loss": 0.0778, "lr": 2.1419700487041123e-05, "epoch": 11.823899371069182, "percentage": 59.12, "elapsed_time": "1:26:10", "remaining_time": "0:59:35", "throughput": 2853.13, "total_tokens": 14751264} {"current_steps": 22565, "total_steps": 38160, "loss": 0.0941, "lr": 2.140838444116566e-05, "epoch": 11.826519916142558, "percentage": 59.13, "elapsed_time": "1:26:11", "remaining_time": "0:59:33", "throughput": 2853.27, "total_tokens": 14755168} {"current_steps": 22570, "total_steps": 38160, "loss": 0.0614, "lr": 2.13970691466152e-05, "epoch": 11.829140461215934, "percentage": 59.15, "elapsed_time": "1:26:12", "remaining_time": "0:59:32", "throughput": 2853.11, "total_tokens": 14757408} {"current_steps": 22575, "total_steps": 38160, "loss": 0.0736, "lr": 2.1385754605756773e-05, "epoch": 11.831761006289309, "percentage": 59.16, "elapsed_time": "1:26:13", "remaining_time": "0:59:31", "throughput": 2853.08, "total_tokens": 14760288} {"current_steps": 22580, "total_steps": 38160, "loss": 0.0874, "lr": 2.137444082095724e-05, "epoch": 11.834381551362684, "percentage": 59.17, "elapsed_time": "1:26:14", "remaining_time": "0:59:30", "throughput": 2853.11, "total_tokens": 14763616} {"current_steps": 22585, "total_steps": 38160, "loss": 0.0643, "lr": 2.1363127794583335e-05, "epoch": 11.83700209643606, "percentage": 59.19, "elapsed_time": "1:26:15", "remaining_time": "0:59:29", "throughput": 2853.3, "total_tokens": 14768544} {"current_steps": 22590, "total_steps": 38160, "loss": 0.0905, "lr": 2.1351815529001605e-05, "epoch": 11.839622641509434, "percentage": 59.2, "elapsed_time": "1:26:16", "remaining_time": "0:59:28", "throughput": 2853.29, "total_tokens": 14771456} {"current_steps": 22595, "total_steps": 38160, "loss": 0.153, "lr": 2.1340504026578438e-05, "epoch": 11.84224318658281, "percentage": 59.21, "elapsed_time": "1:26:18", "remaining_time": "0:59:27", "throughput": 2853.3, "total_tokens": 14774880} {"current_steps": 22600, "total_steps": 38160, "loss": 0.0729, "lr": 2.1329193289680084e-05, "epoch": 11.844863731656185, "percentage": 59.22, "elapsed_time": "1:26:19", "remaining_time": "0:59:25", "throughput": 2853.34, "total_tokens": 14778432} {"current_steps": 22605, "total_steps": 38160, "loss": 0.0612, "lr": 2.1317883320672608e-05, "epoch": 11.84748427672956, "percentage": 59.24, "elapsed_time": "1:26:20", "remaining_time": "0:59:24", "throughput": 2853.36, "total_tokens": 14781984} {"current_steps": 22610, "total_steps": 38160, "loss": 0.0845, "lr": 2.1306574121921942e-05, "epoch": 11.850104821802935, "percentage": 59.25, "elapsed_time": "1:26:21", "remaining_time": "0:59:23", "throughput": 2853.36, "total_tokens": 14785280} {"current_steps": 22615, "total_steps": 38160, "loss": 0.1686, "lr": 2.1295265695793836e-05, "epoch": 11.85272536687631, "percentage": 59.26, "elapsed_time": "1:26:22", "remaining_time": "0:59:22", "throughput": 2853.53, "total_tokens": 14789568} {"current_steps": 22620, "total_steps": 38160, "loss": 0.0533, "lr": 2.128395804465387e-05, "epoch": 11.855345911949685, "percentage": 59.28, "elapsed_time": "1:26:23", "remaining_time": "0:59:21", "throughput": 2853.52, "total_tokens": 14792608} {"current_steps": 22625, "total_steps": 38160, "loss": 0.0383, "lr": 2.1272651170867487e-05, "epoch": 11.85796645702306, "percentage": 59.29, "elapsed_time": "1:26:25", "remaining_time": "0:59:20", "throughput": 2853.69, "total_tokens": 14797760} {"current_steps": 22630, "total_steps": 38160, "loss": 0.0525, "lr": 2.1261345076799955e-05, "epoch": 11.860587002096436, "percentage": 59.3, "elapsed_time": "1:26:26", "remaining_time": "0:59:19", "throughput": 2853.7, "total_tokens": 14800768} {"current_steps": 22635, "total_steps": 38160, "loss": 0.0898, "lr": 2.125003976481638e-05, "epoch": 11.86320754716981, "percentage": 59.32, "elapsed_time": "1:26:27", "remaining_time": "0:59:18", "throughput": 2853.73, "total_tokens": 14804000} {"current_steps": 22640, "total_steps": 38160, "loss": 0.045, "lr": 2.123873523728171e-05, "epoch": 11.865828092243186, "percentage": 59.33, "elapsed_time": "1:26:28", "remaining_time": "0:59:16", "throughput": 2853.77, "total_tokens": 14807392} {"current_steps": 22645, "total_steps": 38160, "loss": 0.0603, "lr": 2.122743149656072e-05, "epoch": 11.868448637316561, "percentage": 59.34, "elapsed_time": "1:26:29", "remaining_time": "0:59:15", "throughput": 2853.8, "total_tokens": 14810816} {"current_steps": 22650, "total_steps": 38160, "loss": 0.0403, "lr": 2.1216128545018012e-05, "epoch": 11.871069182389936, "percentage": 59.36, "elapsed_time": "1:26:30", "remaining_time": "0:59:14", "throughput": 2853.63, "total_tokens": 14813056} {"current_steps": 22655, "total_steps": 38160, "loss": 0.0903, "lr": 2.1204826385018052e-05, "epoch": 11.873689727463312, "percentage": 59.37, "elapsed_time": "1:26:32", "remaining_time": "0:59:13", "throughput": 2853.72, "total_tokens": 14816736} {"current_steps": 22660, "total_steps": 38160, "loss": 0.1064, "lr": 2.1193525018925106e-05, "epoch": 11.876310272536688, "percentage": 59.38, "elapsed_time": "1:26:33", "remaining_time": "0:59:12", "throughput": 2853.78, "total_tokens": 14820160} {"current_steps": 22665, "total_steps": 38160, "loss": 0.0633, "lr": 2.1182224449103304e-05, "epoch": 11.878930817610064, "percentage": 59.39, "elapsed_time": "1:26:34", "remaining_time": "0:59:11", "throughput": 2853.72, "total_tokens": 14822944} {"current_steps": 22670, "total_steps": 38160, "loss": 0.0606, "lr": 2.117092467791659e-05, "epoch": 11.881551362683439, "percentage": 59.41, "elapsed_time": "1:26:35", "remaining_time": "0:59:09", "throughput": 2853.81, "total_tokens": 14826464} {"current_steps": 22675, "total_steps": 38160, "loss": 0.0724, "lr": 2.115962570772876e-05, "epoch": 11.884171907756814, "percentage": 59.42, "elapsed_time": "1:26:36", "remaining_time": "0:59:08", "throughput": 2853.84, "total_tokens": 14830080} {"current_steps": 22680, "total_steps": 38160, "loss": 0.067, "lr": 2.1148327540903408e-05, "epoch": 11.88679245283019, "percentage": 59.43, "elapsed_time": "1:26:37", "remaining_time": "0:59:07", "throughput": 2853.84, "total_tokens": 14833280} {"current_steps": 22685, "total_steps": 38160, "loss": 0.1277, "lr": 2.113703017980399e-05, "epoch": 11.889412997903564, "percentage": 59.45, "elapsed_time": "1:26:38", "remaining_time": "0:59:06", "throughput": 2853.91, "total_tokens": 14836768} {"current_steps": 22690, "total_steps": 38160, "loss": 0.0974, "lr": 2.1125733626793793e-05, "epoch": 11.89203354297694, "percentage": 59.46, "elapsed_time": "1:26:39", "remaining_time": "0:59:05", "throughput": 2853.82, "total_tokens": 14839456} {"current_steps": 22695, "total_steps": 38160, "loss": 0.0727, "lr": 2.1114437884235915e-05, "epoch": 11.894654088050315, "percentage": 59.47, "elapsed_time": "1:26:40", "remaining_time": "0:59:04", "throughput": 2853.78, "total_tokens": 14842272} {"current_steps": 22700, "total_steps": 38160, "loss": 0.1718, "lr": 2.1103142954493313e-05, "epoch": 11.89727463312369, "percentage": 59.49, "elapsed_time": "1:26:42", "remaining_time": "0:59:02", "throughput": 2853.94, "total_tokens": 14846304} {"current_steps": 22705, "total_steps": 38160, "loss": 0.0577, "lr": 2.1091848839928745e-05, "epoch": 11.899895178197065, "percentage": 59.5, "elapsed_time": "1:26:43", "remaining_time": "0:59:01", "throughput": 2853.9, "total_tokens": 14849184} {"current_steps": 22710, "total_steps": 38160, "loss": 0.088, "lr": 2.1080555542904805e-05, "epoch": 11.90251572327044, "percentage": 59.51, "elapsed_time": "1:26:44", "remaining_time": "0:59:00", "throughput": 2853.96, "total_tokens": 14852704} {"current_steps": 22715, "total_steps": 38160, "loss": 0.0514, "lr": 2.106926306578393e-05, "epoch": 11.905136268343815, "percentage": 59.53, "elapsed_time": "1:26:45", "remaining_time": "0:58:59", "throughput": 2854.04, "total_tokens": 14856288} {"current_steps": 22720, "total_steps": 38160, "loss": 0.0779, "lr": 2.1057971410928383e-05, "epoch": 11.90775681341719, "percentage": 59.54, "elapsed_time": "1:26:46", "remaining_time": "0:58:58", "throughput": 2853.99, "total_tokens": 14859232} {"current_steps": 22725, "total_steps": 38160, "loss": 0.0612, "lr": 2.104668058070024e-05, "epoch": 11.910377358490566, "percentage": 59.55, "elapsed_time": "1:26:47", "remaining_time": "0:58:57", "throughput": 2854.04, "total_tokens": 14862624} {"current_steps": 22730, "total_steps": 38160, "loss": 0.0827, "lr": 2.1035390577461427e-05, "epoch": 11.91299790356394, "percentage": 59.56, "elapsed_time": "1:26:48", "remaining_time": "0:58:55", "throughput": 2854.12, "total_tokens": 14866368} {"current_steps": 22735, "total_steps": 38160, "loss": 0.0474, "lr": 2.102410140357367e-05, "epoch": 11.915618448637316, "percentage": 59.58, "elapsed_time": "1:26:49", "remaining_time": "0:58:54", "throughput": 2854.05, "total_tokens": 14869024} {"current_steps": 22740, "total_steps": 38160, "loss": 0.0462, "lr": 2.1012813061398534e-05, "epoch": 11.918238993710691, "percentage": 59.59, "elapsed_time": "1:26:50", "remaining_time": "0:58:53", "throughput": 2854.03, "total_tokens": 14871936} {"current_steps": 22745, "total_steps": 38160, "loss": 0.1339, "lr": 2.1001525553297422e-05, "epoch": 11.920859538784066, "percentage": 59.6, "elapsed_time": "1:26:51", "remaining_time": "0:58:52", "throughput": 2853.9, "total_tokens": 14874400} {"current_steps": 22750, "total_steps": 38160, "loss": 0.0667, "lr": 2.099023888163154e-05, "epoch": 11.923480083857442, "percentage": 59.62, "elapsed_time": "1:26:53", "remaining_time": "0:58:51", "throughput": 2853.8, "total_tokens": 14876864} {"current_steps": 22755, "total_steps": 38160, "loss": 0.0722, "lr": 2.0978953048761947e-05, "epoch": 11.926100628930818, "percentage": 59.63, "elapsed_time": "1:26:54", "remaining_time": "0:58:49", "throughput": 2853.79, "total_tokens": 14879872} {"current_steps": 22760, "total_steps": 38160, "loss": 0.0703, "lr": 2.0967668057049507e-05, "epoch": 11.928721174004194, "percentage": 59.64, "elapsed_time": "1:26:55", "remaining_time": "0:58:48", "throughput": 2853.88, "total_tokens": 14883424} {"current_steps": 22765, "total_steps": 38160, "loss": 0.0661, "lr": 2.0956383908854895e-05, "epoch": 11.931341719077569, "percentage": 59.66, "elapsed_time": "1:26:56", "remaining_time": "0:58:47", "throughput": 2854.02, "total_tokens": 14887392} {"current_steps": 22770, "total_steps": 38160, "loss": 0.115, "lr": 2.0945100606538644e-05, "epoch": 11.933962264150944, "percentage": 59.67, "elapsed_time": "1:26:57", "remaining_time": "0:58:46", "throughput": 2854.02, "total_tokens": 14890688} {"current_steps": 22775, "total_steps": 38160, "loss": 0.0633, "lr": 2.0933818152461077e-05, "epoch": 11.93658280922432, "percentage": 59.68, "elapsed_time": "1:26:58", "remaining_time": "0:58:45", "throughput": 2854.14, "total_tokens": 14894464} {"current_steps": 22780, "total_steps": 38160, "loss": 0.0823, "lr": 2.092253654898237e-05, "epoch": 11.939203354297694, "percentage": 59.7, "elapsed_time": "1:26:59", "remaining_time": "0:58:44", "throughput": 2854.04, "total_tokens": 14897024} {"current_steps": 22785, "total_steps": 38160, "loss": 0.0756, "lr": 2.0911255798462494e-05, "epoch": 11.94182389937107, "percentage": 59.71, "elapsed_time": "1:27:00", "remaining_time": "0:58:42", "throughput": 2854.06, "total_tokens": 14900480} {"current_steps": 22790, "total_steps": 38160, "loss": 0.1178, "lr": 2.0899975903261266e-05, "epoch": 11.944444444444445, "percentage": 59.72, "elapsed_time": "1:27:01", "remaining_time": "0:58:41", "throughput": 2853.99, "total_tokens": 14903136} {"current_steps": 22795, "total_steps": 38160, "loss": 0.0662, "lr": 2.0888696865738295e-05, "epoch": 11.94706498951782, "percentage": 59.74, "elapsed_time": "1:27:03", "remaining_time": "0:58:40", "throughput": 2854.09, "total_tokens": 14907040} {"current_steps": 22800, "total_steps": 38160, "loss": 0.0881, "lr": 2.087741868825304e-05, "epoch": 11.949685534591195, "percentage": 59.75, "elapsed_time": "1:27:04", "remaining_time": "0:58:39", "throughput": 2854.07, "total_tokens": 14910304} {"current_steps": 22805, "total_steps": 38160, "loss": 0.0729, "lr": 2.0866141373164758e-05, "epoch": 11.95230607966457, "percentage": 59.76, "elapsed_time": "1:27:05", "remaining_time": "0:58:38", "throughput": 2854.05, "total_tokens": 14913312} {"current_steps": 22810, "total_steps": 38160, "loss": 0.0889, "lr": 2.0854864922832544e-05, "epoch": 11.954926624737945, "percentage": 59.77, "elapsed_time": "1:27:06", "remaining_time": "0:58:37", "throughput": 2854.0, "total_tokens": 14916512} {"current_steps": 22815, "total_steps": 38160, "loss": 0.0657, "lr": 2.0843589339615304e-05, "epoch": 11.95754716981132, "percentage": 59.79, "elapsed_time": "1:27:07", "remaining_time": "0:58:36", "throughput": 2854.06, "total_tokens": 14920416} {"current_steps": 22820, "total_steps": 38160, "loss": 0.0868, "lr": 2.0832314625871742e-05, "epoch": 11.960167714884696, "percentage": 59.8, "elapsed_time": "1:27:08", "remaining_time": "0:58:34", "throughput": 2854.08, "total_tokens": 14923840} {"current_steps": 22825, "total_steps": 38160, "loss": 0.1033, "lr": 2.0821040783960423e-05, "epoch": 11.96278825995807, "percentage": 59.81, "elapsed_time": "1:27:10", "remaining_time": "0:58:33", "throughput": 2854.15, "total_tokens": 14927520} {"current_steps": 22830, "total_steps": 38160, "loss": 0.0365, "lr": 2.0809767816239686e-05, "epoch": 11.965408805031446, "percentage": 59.83, "elapsed_time": "1:27:11", "remaining_time": "0:58:32", "throughput": 2854.09, "total_tokens": 14930240} {"current_steps": 22835, "total_steps": 38160, "loss": 0.0593, "lr": 2.0798495725067725e-05, "epoch": 11.968029350104821, "percentage": 59.84, "elapsed_time": "1:27:12", "remaining_time": "0:58:31", "throughput": 2854.02, "total_tokens": 14932928} {"current_steps": 22840, "total_steps": 38160, "loss": 0.0794, "lr": 2.078722451280252e-05, "epoch": 11.970649895178196, "percentage": 59.85, "elapsed_time": "1:27:13", "remaining_time": "0:58:30", "throughput": 2853.93, "total_tokens": 14935616} {"current_steps": 22845, "total_steps": 38160, "loss": 0.0876, "lr": 2.0775954181801893e-05, "epoch": 11.973270440251572, "percentage": 59.87, "elapsed_time": "1:27:14", "remaining_time": "0:58:29", "throughput": 2853.82, "total_tokens": 14938080} {"current_steps": 22850, "total_steps": 38160, "loss": 0.1284, "lr": 2.0764684734423455e-05, "epoch": 11.975890985324948, "percentage": 59.88, "elapsed_time": "1:27:15", "remaining_time": "0:58:27", "throughput": 2853.68, "total_tokens": 14940320} {"current_steps": 22855, "total_steps": 38160, "loss": 0.0812, "lr": 2.075341617302465e-05, "epoch": 11.978511530398324, "percentage": 59.89, "elapsed_time": "1:27:16", "remaining_time": "0:58:26", "throughput": 2853.8, "total_tokens": 14944000} {"current_steps": 22860, "total_steps": 38160, "loss": 0.0632, "lr": 2.074214849996274e-05, "epoch": 11.981132075471699, "percentage": 59.91, "elapsed_time": "1:27:17", "remaining_time": "0:58:25", "throughput": 2853.79, "total_tokens": 14947168} {"current_steps": 22865, "total_steps": 38160, "loss": 0.0878, "lr": 2.0730881717594776e-05, "epoch": 11.983752620545074, "percentage": 59.92, "elapsed_time": "1:27:18", "remaining_time": "0:58:24", "throughput": 2853.82, "total_tokens": 14950592} {"current_steps": 22870, "total_steps": 38160, "loss": 0.0996, "lr": 2.0719615828277657e-05, "epoch": 11.98637316561845, "percentage": 59.93, "elapsed_time": "1:27:19", "remaining_time": "0:58:23", "throughput": 2853.93, "total_tokens": 14954176} {"current_steps": 22875, "total_steps": 38160, "loss": 0.0954, "lr": 2.0708350834368083e-05, "epoch": 11.988993710691824, "percentage": 59.94, "elapsed_time": "1:27:20", "remaining_time": "0:58:22", "throughput": 2853.91, "total_tokens": 14957248} {"current_steps": 22880, "total_steps": 38160, "loss": 0.0689, "lr": 2.069708673822255e-05, "epoch": 11.9916142557652, "percentage": 59.96, "elapsed_time": "1:27:22", "remaining_time": "0:58:20", "throughput": 2853.98, "total_tokens": 14960640} {"current_steps": 22885, "total_steps": 38160, "loss": 0.0421, "lr": 2.068582354219737e-05, "epoch": 11.994234800838575, "percentage": 59.97, "elapsed_time": "1:27:23", "remaining_time": "0:58:19", "throughput": 2853.92, "total_tokens": 14963392} {"current_steps": 22890, "total_steps": 38160, "loss": 0.0511, "lr": 2.0674561248648697e-05, "epoch": 11.99685534591195, "percentage": 59.98, "elapsed_time": "1:27:24", "remaining_time": "0:58:18", "throughput": 2853.85, "total_tokens": 14966528} {"current_steps": 22895, "total_steps": 38160, "loss": 0.0829, "lr": 2.0663299859932456e-05, "epoch": 11.999475890985325, "percentage": 60.0, "elapsed_time": "1:27:25", "remaining_time": "0:58:17", "throughput": 2854.03, "total_tokens": 14970464} {"current_steps": 22896, "total_steps": 38160, "eval_loss": 1.0327281951904297, "epoch": 12.0, "percentage": 60.0, "elapsed_time": "1:27:37", "remaining_time": "0:58:24", "throughput": 2847.54, "total_tokens": 14970528} {"current_steps": 22900, "total_steps": 38160, "loss": 0.0299, "lr": 2.065203937840442e-05, "epoch": 12.0020964360587, "percentage": 60.01, "elapsed_time": "1:27:41", "remaining_time": "0:58:25", "throughput": 2846.06, "total_tokens": 14973600} {"current_steps": 22905, "total_steps": 38160, "loss": 0.0689, "lr": 2.0640779806420136e-05, "epoch": 12.004716981132075, "percentage": 60.02, "elapsed_time": "1:27:42", "remaining_time": "0:58:24", "throughput": 2846.16, "total_tokens": 14977536} {"current_steps": 22910, "total_steps": 38160, "loss": 0.037, "lr": 2.0629521146334978e-05, "epoch": 12.00733752620545, "percentage": 60.04, "elapsed_time": "1:27:43", "remaining_time": "0:58:23", "throughput": 2846.13, "total_tokens": 14980640} {"current_steps": 22915, "total_steps": 38160, "loss": 0.0363, "lr": 2.061826340050414e-05, "epoch": 12.009958071278826, "percentage": 60.05, "elapsed_time": "1:27:44", "remaining_time": "0:58:22", "throughput": 2846.06, "total_tokens": 14983456} {"current_steps": 22920, "total_steps": 38160, "loss": 0.0673, "lr": 2.0607006571282605e-05, "epoch": 12.0125786163522, "percentage": 60.06, "elapsed_time": "1:27:45", "remaining_time": "0:58:21", "throughput": 2846.14, "total_tokens": 14987328} {"current_steps": 22925, "total_steps": 38160, "loss": 0.05, "lr": 2.0595750661025183e-05, "epoch": 12.015199161425576, "percentage": 60.08, "elapsed_time": "1:27:46", "remaining_time": "0:58:20", "throughput": 2846.12, "total_tokens": 14990432} {"current_steps": 22930, "total_steps": 38160, "loss": 0.0408, "lr": 2.0584495672086483e-05, "epoch": 12.017819706498951, "percentage": 60.09, "elapsed_time": "1:27:48", "remaining_time": "0:58:19", "throughput": 2846.16, "total_tokens": 14993824} {"current_steps": 22935, "total_steps": 38160, "loss": 0.0328, "lr": 2.05732416068209e-05, "epoch": 12.020440251572326, "percentage": 60.1, "elapsed_time": "1:27:49", "remaining_time": "0:58:17", "throughput": 2846.11, "total_tokens": 14996608} {"current_steps": 22940, "total_steps": 38160, "loss": 0.0341, "lr": 2.0561988467582676e-05, "epoch": 12.023060796645701, "percentage": 60.12, "elapsed_time": "1:27:50", "remaining_time": "0:58:16", "throughput": 2846.16, "total_tokens": 15000128} {"current_steps": 22945, "total_steps": 38160, "loss": 0.0584, "lr": 2.0550736256725828e-05, "epoch": 12.025681341719078, "percentage": 60.13, "elapsed_time": "1:27:51", "remaining_time": "0:58:15", "throughput": 2846.14, "total_tokens": 15003104} {"current_steps": 22950, "total_steps": 38160, "loss": 0.0228, "lr": 2.0539484976604196e-05, "epoch": 12.028301886792454, "percentage": 60.14, "elapsed_time": "1:27:52", "remaining_time": "0:58:14", "throughput": 2846.07, "total_tokens": 15005632} {"current_steps": 22955, "total_steps": 38160, "loss": 0.0296, "lr": 2.052823462957142e-05, "epoch": 12.030922431865829, "percentage": 60.15, "elapsed_time": "1:27:53", "remaining_time": "0:58:13", "throughput": 2845.93, "total_tokens": 15009024} {"current_steps": 22960, "total_steps": 38160, "loss": 0.0461, "lr": 2.0516985217980953e-05, "epoch": 12.033542976939204, "percentage": 60.17, "elapsed_time": "1:27:54", "remaining_time": "0:58:12", "throughput": 2845.83, "total_tokens": 15011680} {"current_steps": 22965, "total_steps": 38160, "loss": 0.0659, "lr": 2.050573674418602e-05, "epoch": 12.036163522012579, "percentage": 60.18, "elapsed_time": "1:27:56", "remaining_time": "0:58:10", "throughput": 2845.77, "total_tokens": 15014656} {"current_steps": 22970, "total_steps": 38160, "loss": 0.0145, "lr": 2.0494489210539693e-05, "epoch": 12.038784067085954, "percentage": 60.19, "elapsed_time": "1:27:57", "remaining_time": "0:58:09", "throughput": 2845.8, "total_tokens": 15017952} {"current_steps": 22975, "total_steps": 38160, "loss": 0.0679, "lr": 2.0483242619394817e-05, "epoch": 12.04140461215933, "percentage": 60.21, "elapsed_time": "1:27:58", "remaining_time": "0:58:08", "throughput": 2845.75, "total_tokens": 15020736} {"current_steps": 22980, "total_steps": 38160, "loss": 0.1593, "lr": 2.0471996973104063e-05, "epoch": 12.044025157232705, "percentage": 60.22, "elapsed_time": "1:27:59", "remaining_time": "0:58:07", "throughput": 2845.82, "total_tokens": 15024544} {"current_steps": 22985, "total_steps": 38160, "loss": 0.0315, "lr": 2.0460752274019886e-05, "epoch": 12.04664570230608, "percentage": 60.23, "elapsed_time": "1:28:00", "remaining_time": "0:58:06", "throughput": 2845.79, "total_tokens": 15027424} {"current_steps": 22990, "total_steps": 38160, "loss": 0.0464, "lr": 2.0449508524494537e-05, "epoch": 12.049266247379455, "percentage": 60.25, "elapsed_time": "1:28:01", "remaining_time": "0:58:05", "throughput": 2845.85, "total_tokens": 15030976} {"current_steps": 22995, "total_steps": 38160, "loss": 0.0322, "lr": 2.0438265726880092e-05, "epoch": 12.05188679245283, "percentage": 60.26, "elapsed_time": "1:28:02", "remaining_time": "0:58:03", "throughput": 2845.89, "total_tokens": 15034464} {"current_steps": 23000, "total_steps": 38160, "loss": 0.0659, "lr": 2.042702388352841e-05, "epoch": 12.054507337526205, "percentage": 60.27, "elapsed_time": "1:28:04", "remaining_time": "0:58:02", "throughput": 2846.11, "total_tokens": 15039104} {"current_steps": 23005, "total_steps": 38160, "loss": 0.0479, "lr": 2.041578299679117e-05, "epoch": 12.05712788259958, "percentage": 60.29, "elapsed_time": "1:28:05", "remaining_time": "0:58:01", "throughput": 2846.04, "total_tokens": 15041920} {"current_steps": 23010, "total_steps": 38160, "loss": 0.08, "lr": 2.0404543069019818e-05, "epoch": 12.059748427672956, "percentage": 60.3, "elapsed_time": "1:28:06", "remaining_time": "0:58:00", "throughput": 2846.11, "total_tokens": 15045344} {"current_steps": 23015, "total_steps": 38160, "loss": 0.0631, "lr": 2.0393304102565642e-05, "epoch": 12.06236897274633, "percentage": 60.31, "elapsed_time": "1:28:07", "remaining_time": "0:57:59", "throughput": 2846.11, "total_tokens": 15048352} {"current_steps": 23020, "total_steps": 38160, "loss": 0.0283, "lr": 2.0382066099779685e-05, "epoch": 12.064989517819706, "percentage": 60.32, "elapsed_time": "1:28:08", "remaining_time": "0:57:58", "throughput": 2846.14, "total_tokens": 15051680} {"current_steps": 23025, "total_steps": 38160, "loss": 0.0701, "lr": 2.0370829063012808e-05, "epoch": 12.067610062893081, "percentage": 60.34, "elapsed_time": "1:28:09", "remaining_time": "0:57:56", "throughput": 2846.06, "total_tokens": 15054304} {"current_steps": 23030, "total_steps": 38160, "loss": 0.036, "lr": 2.035959299461568e-05, "epoch": 12.070230607966456, "percentage": 60.35, "elapsed_time": "1:28:10", "remaining_time": "0:57:55", "throughput": 2845.91, "total_tokens": 15056640} {"current_steps": 23035, "total_steps": 38160, "loss": 0.0519, "lr": 2.0348357896938762e-05, "epoch": 12.072851153039831, "percentage": 60.36, "elapsed_time": "1:28:11", "remaining_time": "0:57:54", "throughput": 2845.87, "total_tokens": 15059456} {"current_steps": 23040, "total_steps": 38160, "loss": 0.081, "lr": 2.03371237723323e-05, "epoch": 12.075471698113208, "percentage": 60.38, "elapsed_time": "1:28:12", "remaining_time": "0:57:53", "throughput": 2845.9, "total_tokens": 15062720} {"current_steps": 23045, "total_steps": 38160, "loss": 0.0272, "lr": 2.032589062314636e-05, "epoch": 12.078092243186584, "percentage": 60.39, "elapsed_time": "1:28:13", "remaining_time": "0:57:52", "throughput": 2845.86, "total_tokens": 15065568} {"current_steps": 23050, "total_steps": 38160, "loss": 0.039, "lr": 2.0314658451730767e-05, "epoch": 12.080712788259959, "percentage": 60.4, "elapsed_time": "1:28:14", "remaining_time": "0:57:50", "throughput": 2845.81, "total_tokens": 15068224} {"current_steps": 23055, "total_steps": 38160, "loss": 0.0732, "lr": 2.030342726043517e-05, "epoch": 12.083333333333334, "percentage": 60.42, "elapsed_time": "1:28:16", "remaining_time": "0:57:49", "throughput": 2845.91, "total_tokens": 15072032} {"current_steps": 23060, "total_steps": 38160, "loss": 0.0319, "lr": 2.0292197051609013e-05, "epoch": 12.085953878406709, "percentage": 60.43, "elapsed_time": "1:28:17", "remaining_time": "0:57:48", "throughput": 2845.91, "total_tokens": 15075104} {"current_steps": 23065, "total_steps": 38160, "loss": 0.0865, "lr": 2.0280967827601518e-05, "epoch": 12.088574423480084, "percentage": 60.44, "elapsed_time": "1:28:18", "remaining_time": "0:57:47", "throughput": 2845.96, "total_tokens": 15078336} {"current_steps": 23070, "total_steps": 38160, "loss": 0.0192, "lr": 2.0269739590761723e-05, "epoch": 12.09119496855346, "percentage": 60.46, "elapsed_time": "1:28:19", "remaining_time": "0:57:46", "throughput": 2845.84, "total_tokens": 15080736} {"current_steps": 23075, "total_steps": 38160, "loss": 0.0771, "lr": 2.0258512343438442e-05, "epoch": 12.093815513626835, "percentage": 60.47, "elapsed_time": "1:28:20", "remaining_time": "0:57:44", "throughput": 2845.79, "total_tokens": 15083392} {"current_steps": 23080, "total_steps": 38160, "loss": 0.0305, "lr": 2.0247286087980276e-05, "epoch": 12.09643605870021, "percentage": 60.48, "elapsed_time": "1:28:21", "remaining_time": "0:57:43", "throughput": 2845.84, "total_tokens": 15086784} {"current_steps": 23085, "total_steps": 38160, "loss": 0.0685, "lr": 2.0236060826735644e-05, "epoch": 12.099056603773585, "percentage": 60.5, "elapsed_time": "1:28:22", "remaining_time": "0:57:42", "throughput": 2845.79, "total_tokens": 15089504} {"current_steps": 23090, "total_steps": 38160, "loss": 0.061, "lr": 2.0224836562052732e-05, "epoch": 12.10167714884696, "percentage": 60.51, "elapsed_time": "1:28:23", "remaining_time": "0:57:41", "throughput": 2845.79, "total_tokens": 15092512} {"current_steps": 23095, "total_steps": 38160, "loss": 0.0531, "lr": 2.0213613296279533e-05, "epoch": 12.104297693920335, "percentage": 60.52, "elapsed_time": "1:28:24", "remaining_time": "0:57:40", "throughput": 2845.81, "total_tokens": 15095808} {"current_steps": 23100, "total_steps": 38160, "loss": 0.0989, "lr": 2.0202391031763844e-05, "epoch": 12.10691823899371, "percentage": 60.53, "elapsed_time": "1:28:25", "remaining_time": "0:57:38", "throughput": 2845.81, "total_tokens": 15098720} {"current_steps": 23105, "total_steps": 38160, "loss": 0.0642, "lr": 2.0191169770853195e-05, "epoch": 12.109538784067086, "percentage": 60.55, "elapsed_time": "1:28:26", "remaining_time": "0:57:37", "throughput": 2845.87, "total_tokens": 15102176} {"current_steps": 23110, "total_steps": 38160, "loss": 0.0246, "lr": 2.0179949515894975e-05, "epoch": 12.11215932914046, "percentage": 60.56, "elapsed_time": "1:28:27", "remaining_time": "0:57:36", "throughput": 2845.72, "total_tokens": 15104480} {"current_steps": 23115, "total_steps": 38160, "loss": 0.0669, "lr": 2.016873026923633e-05, "epoch": 12.114779874213836, "percentage": 60.57, "elapsed_time": "1:28:28", "remaining_time": "0:57:35", "throughput": 2845.68, "total_tokens": 15107264} {"current_steps": 23120, "total_steps": 38160, "loss": 0.0276, "lr": 2.0157512033224187e-05, "epoch": 12.117400419287211, "percentage": 60.59, "elapsed_time": "1:28:29", "remaining_time": "0:57:34", "throughput": 2845.81, "total_tokens": 15111104} {"current_steps": 23125, "total_steps": 38160, "loss": 0.0342, "lr": 2.0146294810205287e-05, "epoch": 12.120020964360586, "percentage": 60.6, "elapsed_time": "1:28:30", "remaining_time": "0:57:32", "throughput": 2845.85, "total_tokens": 15114240} {"current_steps": 23130, "total_steps": 38160, "loss": 0.0559, "lr": 2.0135078602526146e-05, "epoch": 12.122641509433961, "percentage": 60.61, "elapsed_time": "1:28:32", "remaining_time": "0:57:31", "throughput": 2845.9, "total_tokens": 15117600} {"current_steps": 23135, "total_steps": 38160, "loss": 0.026, "lr": 2.0123863412533046e-05, "epoch": 12.125262054507338, "percentage": 60.63, "elapsed_time": "1:28:33", "remaining_time": "0:57:30", "throughput": 2845.87, "total_tokens": 15120416} {"current_steps": 23140, "total_steps": 38160, "loss": 0.0475, "lr": 2.0112649242572095e-05, "epoch": 12.127882599580714, "percentage": 60.64, "elapsed_time": "1:28:34", "remaining_time": "0:57:29", "throughput": 2846.0, "total_tokens": 15124064} {"current_steps": 23145, "total_steps": 38160, "loss": 0.0384, "lr": 2.0101436094989164e-05, "epoch": 12.130503144654089, "percentage": 60.65, "elapsed_time": "1:28:35", "remaining_time": "0:57:28", "throughput": 2846.0, "total_tokens": 15127168} {"current_steps": 23150, "total_steps": 38160, "loss": 0.0375, "lr": 2.0090223972129918e-05, "epoch": 12.133123689727464, "percentage": 60.67, "elapsed_time": "1:28:36", "remaining_time": "0:57:26", "throughput": 2846.0, "total_tokens": 15130208} {"current_steps": 23155, "total_steps": 38160, "loss": 0.0992, "lr": 2.0079012876339797e-05, "epoch": 12.135744234800839, "percentage": 60.68, "elapsed_time": "1:28:37", "remaining_time": "0:57:25", "throughput": 2846.06, "total_tokens": 15133760} {"current_steps": 23160, "total_steps": 38160, "loss": 0.073, "lr": 2.0067802809964055e-05, "epoch": 12.138364779874214, "percentage": 60.69, "elapsed_time": "1:28:38", "remaining_time": "0:57:24", "throughput": 2846.11, "total_tokens": 15136992} {"current_steps": 23165, "total_steps": 38160, "loss": 0.0503, "lr": 2.0056593775347686e-05, "epoch": 12.14098532494759, "percentage": 60.7, "elapsed_time": "1:28:39", "remaining_time": "0:57:23", "throughput": 2845.97, "total_tokens": 15139296} {"current_steps": 23170, "total_steps": 38160, "loss": 0.0229, "lr": 2.00453857748355e-05, "epoch": 12.143605870020965, "percentage": 60.72, "elapsed_time": "1:28:40", "remaining_time": "0:57:22", "throughput": 2845.98, "total_tokens": 15142656} {"current_steps": 23175, "total_steps": 38160, "loss": 0.0794, "lr": 2.0034178810772082e-05, "epoch": 12.14622641509434, "percentage": 60.73, "elapsed_time": "1:28:41", "remaining_time": "0:57:21", "throughput": 2846.03, "total_tokens": 15145824} {"current_steps": 23180, "total_steps": 38160, "loss": 0.0491, "lr": 2.002297288550181e-05, "epoch": 12.148846960167715, "percentage": 60.74, "elapsed_time": "1:28:42", "remaining_time": "0:57:19", "throughput": 2845.96, "total_tokens": 15148608} {"current_steps": 23185, "total_steps": 38160, "loss": 0.0243, "lr": 2.0011768001368835e-05, "epoch": 12.15146750524109, "percentage": 60.76, "elapsed_time": "1:28:43", "remaining_time": "0:57:18", "throughput": 2845.85, "total_tokens": 15151200} {"current_steps": 23190, "total_steps": 38160, "loss": 0.0321, "lr": 2.0000564160717076e-05, "epoch": 12.154088050314465, "percentage": 60.77, "elapsed_time": "1:28:45", "remaining_time": "0:57:17", "throughput": 2845.87, "total_tokens": 15154464} {"current_steps": 23195, "total_steps": 38160, "loss": 0.1288, "lr": 1.9989361365890263e-05, "epoch": 12.15670859538784, "percentage": 60.78, "elapsed_time": "1:28:46", "remaining_time": "0:57:16", "throughput": 2845.96, "total_tokens": 15158272} {"current_steps": 23200, "total_steps": 38160, "loss": 0.0516, "lr": 1.997815961923188e-05, "epoch": 12.159329140461216, "percentage": 60.8, "elapsed_time": "1:28:47", "remaining_time": "0:57:15", "throughput": 2845.93, "total_tokens": 15161152} {"current_steps": 23205, "total_steps": 38160, "loss": 0.0283, "lr": 1.996695892308522e-05, "epoch": 12.16194968553459, "percentage": 60.81, "elapsed_time": "1:28:48", "remaining_time": "0:57:14", "throughput": 2845.82, "total_tokens": 15163616} {"current_steps": 23210, "total_steps": 38160, "loss": 0.0596, "lr": 1.9955759279793327e-05, "epoch": 12.164570230607966, "percentage": 60.82, "elapsed_time": "1:28:49", "remaining_time": "0:57:12", "throughput": 2845.95, "total_tokens": 15167264} {"current_steps": 23215, "total_steps": 38160, "loss": 0.0547, "lr": 1.9944560691699057e-05, "epoch": 12.167190775681341, "percentage": 60.84, "elapsed_time": "1:28:50", "remaining_time": "0:57:11", "throughput": 2846.0, "total_tokens": 15170816} {"current_steps": 23220, "total_steps": 38160, "loss": 0.0492, "lr": 1.9933363161145006e-05, "epoch": 12.169811320754716, "percentage": 60.85, "elapsed_time": "1:28:51", "remaining_time": "0:57:10", "throughput": 2845.9, "total_tokens": 15173280} {"current_steps": 23225, "total_steps": 38160, "loss": 0.0454, "lr": 1.9922166690473575e-05, "epoch": 12.172431865828091, "percentage": 60.86, "elapsed_time": "1:28:52", "remaining_time": "0:57:09", "throughput": 2845.95, "total_tokens": 15176544} {"current_steps": 23230, "total_steps": 38160, "loss": 0.0342, "lr": 1.991097128202695e-05, "epoch": 12.175052410901468, "percentage": 60.88, "elapsed_time": "1:28:53", "remaining_time": "0:57:08", "throughput": 2845.91, "total_tokens": 15179488} {"current_steps": 23235, "total_steps": 38160, "loss": 0.0269, "lr": 1.9899776938147065e-05, "epoch": 12.177672955974844, "percentage": 60.89, "elapsed_time": "1:28:54", "remaining_time": "0:57:06", "throughput": 2845.79, "total_tokens": 15182016} {"current_steps": 23240, "total_steps": 38160, "loss": 0.0554, "lr": 1.9888583661175665e-05, "epoch": 12.180293501048219, "percentage": 60.9, "elapsed_time": "1:28:55", "remaining_time": "0:57:05", "throughput": 2845.92, "total_tokens": 15185760} {"current_steps": 23245, "total_steps": 38160, "loss": 0.0462, "lr": 1.9877391453454253e-05, "epoch": 12.182914046121594, "percentage": 60.91, "elapsed_time": "1:28:57", "remaining_time": "0:57:04", "throughput": 2845.95, "total_tokens": 15188992} {"current_steps": 23250, "total_steps": 38160, "loss": 0.0511, "lr": 1.98662003173241e-05, "epoch": 12.185534591194969, "percentage": 60.93, "elapsed_time": "1:28:58", "remaining_time": "0:57:03", "throughput": 2846.05, "total_tokens": 15192768} {"current_steps": 23255, "total_steps": 38160, "loss": 0.0545, "lr": 1.9855010255126266e-05, "epoch": 12.188155136268344, "percentage": 60.94, "elapsed_time": "1:28:59", "remaining_time": "0:57:02", "throughput": 2846.09, "total_tokens": 15196256} {"current_steps": 23260, "total_steps": 38160, "loss": 0.0722, "lr": 1.9843821269201598e-05, "epoch": 12.19077568134172, "percentage": 60.95, "elapsed_time": "1:29:01", "remaining_time": "0:57:01", "throughput": 2846.38, "total_tokens": 15202848} {"current_steps": 23265, "total_steps": 38160, "loss": 0.0669, "lr": 1.983263336189069e-05, "epoch": 12.193396226415095, "percentage": 60.97, "elapsed_time": "1:29:02", "remaining_time": "0:57:00", "throughput": 2846.44, "total_tokens": 15206240} {"current_steps": 23270, "total_steps": 38160, "loss": 0.0397, "lr": 1.9821446535533937e-05, "epoch": 12.19601677148847, "percentage": 60.98, "elapsed_time": "1:29:03", "remaining_time": "0:56:59", "throughput": 2846.38, "total_tokens": 15208864} {"current_steps": 23275, "total_steps": 38160, "loss": 0.0487, "lr": 1.9810260792471492e-05, "epoch": 12.198637316561845, "percentage": 60.99, "elapsed_time": "1:29:04", "remaining_time": "0:56:57", "throughput": 2846.38, "total_tokens": 15211968} {"current_steps": 23280, "total_steps": 38160, "loss": 0.0428, "lr": 1.979907613504327e-05, "epoch": 12.20125786163522, "percentage": 61.01, "elapsed_time": "1:29:05", "remaining_time": "0:56:56", "throughput": 2846.31, "total_tokens": 15214656} {"current_steps": 23285, "total_steps": 38160, "loss": 0.0578, "lr": 1.978789256558899e-05, "epoch": 12.203878406708595, "percentage": 61.02, "elapsed_time": "1:29:06", "remaining_time": "0:56:55", "throughput": 2846.37, "total_tokens": 15218048} {"current_steps": 23290, "total_steps": 38160, "loss": 0.0939, "lr": 1.977671008644812e-05, "epoch": 12.20649895178197, "percentage": 61.03, "elapsed_time": "1:29:07", "remaining_time": "0:56:54", "throughput": 2846.45, "total_tokens": 15222112} {"current_steps": 23295, "total_steps": 38160, "loss": 0.0554, "lr": 1.9765528699959912e-05, "epoch": 12.209119496855346, "percentage": 61.05, "elapsed_time": "1:29:08", "remaining_time": "0:56:53", "throughput": 2846.44, "total_tokens": 15225312} {"current_steps": 23300, "total_steps": 38160, "loss": 0.1046, "lr": 1.975434840846339e-05, "epoch": 12.21174004192872, "percentage": 61.06, "elapsed_time": "1:29:10", "remaining_time": "0:56:52", "throughput": 2846.4, "total_tokens": 15228288} {"current_steps": 23305, "total_steps": 38160, "loss": 0.0352, "lr": 1.9743169214297326e-05, "epoch": 12.214360587002096, "percentage": 61.07, "elapsed_time": "1:29:11", "remaining_time": "0:56:50", "throughput": 2846.54, "total_tokens": 15232352} {"current_steps": 23310, "total_steps": 38160, "loss": 0.0593, "lr": 1.973199111980029e-05, "epoch": 12.216981132075471, "percentage": 61.08, "elapsed_time": "1:29:12", "remaining_time": "0:56:49", "throughput": 2846.85, "total_tokens": 15237984} {"current_steps": 23315, "total_steps": 38160, "loss": 0.0272, "lr": 1.9720814127310608e-05, "epoch": 12.219601677148846, "percentage": 61.1, "elapsed_time": "1:29:13", "remaining_time": "0:56:48", "throughput": 2846.88, "total_tokens": 15241184} {"current_steps": 23320, "total_steps": 38160, "loss": 0.0351, "lr": 1.9709638239166386e-05, "epoch": 12.222222222222221, "percentage": 61.11, "elapsed_time": "1:29:14", "remaining_time": "0:56:47", "throughput": 2846.77, "total_tokens": 15243744} {"current_steps": 23325, "total_steps": 38160, "loss": 0.1707, "lr": 1.9698463457705485e-05, "epoch": 12.224842767295598, "percentage": 61.12, "elapsed_time": "1:29:15", "remaining_time": "0:56:46", "throughput": 2846.68, "total_tokens": 15246432} {"current_steps": 23330, "total_steps": 38160, "loss": 0.0381, "lr": 1.968728978526556e-05, "epoch": 12.227463312368974, "percentage": 61.14, "elapsed_time": "1:29:16", "remaining_time": "0:56:45", "throughput": 2846.68, "total_tokens": 15249440} {"current_steps": 23335, "total_steps": 38160, "loss": 0.0552, "lr": 1.9676117224183986e-05, "epoch": 12.230083857442349, "percentage": 61.15, "elapsed_time": "1:29:18", "remaining_time": "0:56:44", "throughput": 2846.78, "total_tokens": 15253120} {"current_steps": 23340, "total_steps": 38160, "loss": 0.0583, "lr": 1.9664945776797956e-05, "epoch": 12.232704402515724, "percentage": 61.16, "elapsed_time": "1:29:19", "remaining_time": "0:56:42", "throughput": 2846.76, "total_tokens": 15256224} {"current_steps": 23345, "total_steps": 38160, "loss": 0.0385, "lr": 1.96537754454444e-05, "epoch": 12.235324947589099, "percentage": 61.18, "elapsed_time": "1:29:20", "remaining_time": "0:56:41", "throughput": 2846.62, "total_tokens": 15258720} {"current_steps": 23350, "total_steps": 38160, "loss": 0.0361, "lr": 1.964260623246003e-05, "epoch": 12.237945492662474, "percentage": 61.19, "elapsed_time": "1:29:21", "remaining_time": "0:56:40", "throughput": 2846.61, "total_tokens": 15261760} {"current_steps": 23355, "total_steps": 38160, "loss": 0.0507, "lr": 1.9631438140181324e-05, "epoch": 12.24056603773585, "percentage": 61.2, "elapsed_time": "1:29:22", "remaining_time": "0:56:39", "throughput": 2846.74, "total_tokens": 15265472} {"current_steps": 23360, "total_steps": 38160, "loss": 0.0347, "lr": 1.9620271170944503e-05, "epoch": 12.243186582809225, "percentage": 61.22, "elapsed_time": "1:29:23", "remaining_time": "0:56:38", "throughput": 2846.81, "total_tokens": 15268896} {"current_steps": 23365, "total_steps": 38160, "loss": 0.0167, "lr": 1.960910532708558e-05, "epoch": 12.2458071278826, "percentage": 61.23, "elapsed_time": "1:29:24", "remaining_time": "0:56:36", "throughput": 2846.84, "total_tokens": 15272320} {"current_steps": 23370, "total_steps": 38160, "loss": 0.0467, "lr": 1.9597940610940315e-05, "epoch": 12.248427672955975, "percentage": 61.24, "elapsed_time": "1:29:25", "remaining_time": "0:56:35", "throughput": 2846.88, "total_tokens": 15275776} {"current_steps": 23375, "total_steps": 38160, "loss": 0.0465, "lr": 1.958677702484425e-05, "epoch": 12.25104821802935, "percentage": 61.26, "elapsed_time": "1:29:26", "remaining_time": "0:56:34", "throughput": 2846.89, "total_tokens": 15278912} {"current_steps": 23380, "total_steps": 38160, "loss": 0.0419, "lr": 1.957561457113267e-05, "epoch": 12.253668763102725, "percentage": 61.27, "elapsed_time": "1:29:27", "remaining_time": "0:56:33", "throughput": 2846.81, "total_tokens": 15281536} {"current_steps": 23385, "total_steps": 38160, "loss": 0.0462, "lr": 1.9564453252140648e-05, "epoch": 12.2562893081761, "percentage": 61.28, "elapsed_time": "1:29:29", "remaining_time": "0:56:32", "throughput": 2846.8, "total_tokens": 15284544} {"current_steps": 23390, "total_steps": 38160, "loss": 0.0561, "lr": 1.9553293070202984e-05, "epoch": 12.258909853249476, "percentage": 61.29, "elapsed_time": "1:29:30", "remaining_time": "0:56:31", "throughput": 2846.86, "total_tokens": 15287968} {"current_steps": 23395, "total_steps": 38160, "loss": 0.0314, "lr": 1.9542134027654267e-05, "epoch": 12.26153039832285, "percentage": 61.31, "elapsed_time": "1:29:31", "remaining_time": "0:56:29", "throughput": 2846.88, "total_tokens": 15291136} {"current_steps": 23400, "total_steps": 38160, "loss": 0.0429, "lr": 1.953097612682885e-05, "epoch": 12.264150943396226, "percentage": 61.32, "elapsed_time": "1:29:32", "remaining_time": "0:56:28", "throughput": 2846.83, "total_tokens": 15293824} {"current_steps": 23405, "total_steps": 38160, "loss": 0.02, "lr": 1.9519819370060832e-05, "epoch": 12.266771488469601, "percentage": 61.33, "elapsed_time": "1:29:33", "remaining_time": "0:56:27", "throughput": 2846.85, "total_tokens": 15296928} {"current_steps": 23410, "total_steps": 38160, "loss": 0.0419, "lr": 1.9508663759684074e-05, "epoch": 12.269392033542976, "percentage": 61.35, "elapsed_time": "1:29:34", "remaining_time": "0:56:26", "throughput": 2846.85, "total_tokens": 15299904} {"current_steps": 23415, "total_steps": 38160, "loss": 0.0435, "lr": 1.9497509298032224e-05, "epoch": 12.272012578616351, "percentage": 61.36, "elapsed_time": "1:29:35", "remaining_time": "0:56:25", "throughput": 2846.77, "total_tokens": 15302624} {"current_steps": 23420, "total_steps": 38160, "loss": 0.0209, "lr": 1.9486355987438647e-05, "epoch": 12.274633123689728, "percentage": 61.37, "elapsed_time": "1:29:36", "remaining_time": "0:56:23", "throughput": 2846.73, "total_tokens": 15305408} {"current_steps": 23425, "total_steps": 38160, "loss": 0.0995, "lr": 1.947520383023649e-05, "epoch": 12.277253668763104, "percentage": 61.39, "elapsed_time": "1:29:37", "remaining_time": "0:56:22", "throughput": 2846.73, "total_tokens": 15308288} {"current_steps": 23430, "total_steps": 38160, "loss": 0.0306, "lr": 1.9464052828758666e-05, "epoch": 12.279874213836479, "percentage": 61.4, "elapsed_time": "1:29:38", "remaining_time": "0:56:21", "throughput": 2846.71, "total_tokens": 15311200} {"current_steps": 23435, "total_steps": 38160, "loss": 0.0694, "lr": 1.945290298533783e-05, "epoch": 12.282494758909854, "percentage": 61.41, "elapsed_time": "1:29:39", "remaining_time": "0:56:20", "throughput": 2846.81, "total_tokens": 15314688} {"current_steps": 23440, "total_steps": 38160, "loss": 0.0168, "lr": 1.9441754302306406e-05, "epoch": 12.285115303983229, "percentage": 61.43, "elapsed_time": "1:29:40", "remaining_time": "0:56:18", "throughput": 2846.79, "total_tokens": 15317632} {"current_steps": 23445, "total_steps": 38160, "loss": 0.0211, "lr": 1.9430606781996578e-05, "epoch": 12.287735849056604, "percentage": 61.44, "elapsed_time": "1:29:41", "remaining_time": "0:56:17", "throughput": 2846.73, "total_tokens": 15320288} {"current_steps": 23450, "total_steps": 38160, "loss": 0.0339, "lr": 1.941946042674026e-05, "epoch": 12.29035639412998, "percentage": 61.45, "elapsed_time": "1:29:42", "remaining_time": "0:56:16", "throughput": 2846.78, "total_tokens": 15323520} {"current_steps": 23455, "total_steps": 38160, "loss": 0.0686, "lr": 1.940831523886916e-05, "epoch": 12.292976939203355, "percentage": 61.46, "elapsed_time": "1:29:43", "remaining_time": "0:56:15", "throughput": 2846.84, "total_tokens": 15327008} {"current_steps": 23460, "total_steps": 38160, "loss": 0.0376, "lr": 1.9397171220714714e-05, "epoch": 12.29559748427673, "percentage": 61.48, "elapsed_time": "1:29:44", "remaining_time": "0:56:14", "throughput": 2846.82, "total_tokens": 15329952} {"current_steps": 23465, "total_steps": 38160, "loss": 0.0454, "lr": 1.9386028374608134e-05, "epoch": 12.298218029350105, "percentage": 61.49, "elapsed_time": "1:29:45", "remaining_time": "0:56:12", "throughput": 2846.85, "total_tokens": 15333056} {"current_steps": 23470, "total_steps": 38160, "loss": 0.0406, "lr": 1.9374886702880372e-05, "epoch": 12.30083857442348, "percentage": 61.5, "elapsed_time": "1:29:47", "remaining_time": "0:56:11", "throughput": 2846.96, "total_tokens": 15336736} {"current_steps": 23475, "total_steps": 38160, "loss": 0.0346, "lr": 1.936374620786213e-05, "epoch": 12.303459119496855, "percentage": 61.52, "elapsed_time": "1:29:48", "remaining_time": "0:56:10", "throughput": 2846.95, "total_tokens": 15339712} {"current_steps": 23480, "total_steps": 38160, "loss": 0.0655, "lr": 1.9352606891883885e-05, "epoch": 12.30607966457023, "percentage": 61.53, "elapsed_time": "1:29:49", "remaining_time": "0:56:09", "throughput": 2847.03, "total_tokens": 15343232} {"current_steps": 23485, "total_steps": 38160, "loss": 0.0451, "lr": 1.9341468757275844e-05, "epoch": 12.308700209643606, "percentage": 61.54, "elapsed_time": "1:29:50", "remaining_time": "0:56:08", "throughput": 2847.07, "total_tokens": 15346816} {"current_steps": 23490, "total_steps": 38160, "loss": 0.0486, "lr": 1.933033180636798e-05, "epoch": 12.31132075471698, "percentage": 61.56, "elapsed_time": "1:29:51", "remaining_time": "0:56:07", "throughput": 2847.03, "total_tokens": 15349760} {"current_steps": 23495, "total_steps": 38160, "loss": 0.0584, "lr": 1.9319196041490027e-05, "epoch": 12.313941299790356, "percentage": 61.57, "elapsed_time": "1:29:52", "remaining_time": "0:56:05", "throughput": 2847.08, "total_tokens": 15353184} {"current_steps": 23500, "total_steps": 38160, "loss": 0.053, "lr": 1.930806146497146e-05, "epoch": 12.316561844863731, "percentage": 61.58, "elapsed_time": "1:29:53", "remaining_time": "0:56:04", "throughput": 2847.12, "total_tokens": 15356512} {"current_steps": 23505, "total_steps": 38160, "loss": 0.0293, "lr": 1.9296928079141485e-05, "epoch": 12.319182389937106, "percentage": 61.6, "elapsed_time": "1:29:54", "remaining_time": "0:56:03", "throughput": 2847.02, "total_tokens": 15359104} {"current_steps": 23510, "total_steps": 38160, "loss": 0.0675, "lr": 1.9285795886329093e-05, "epoch": 12.321802935010481, "percentage": 61.61, "elapsed_time": "1:29:55", "remaining_time": "0:56:02", "throughput": 2847.07, "total_tokens": 15362528} {"current_steps": 23515, "total_steps": 38160, "loss": 0.0695, "lr": 1.927466488886301e-05, "epoch": 12.324423480083858, "percentage": 61.62, "elapsed_time": "1:29:57", "remaining_time": "0:56:01", "throughput": 2847.16, "total_tokens": 15366240} {"current_steps": 23520, "total_steps": 38160, "loss": 0.028, "lr": 1.926353508907172e-05, "epoch": 12.327044025157234, "percentage": 61.64, "elapsed_time": "1:29:58", "remaining_time": "0:56:00", "throughput": 2847.07, "total_tokens": 15368704} {"current_steps": 23525, "total_steps": 38160, "loss": 0.0574, "lr": 1.9252406489283437e-05, "epoch": 12.329664570230609, "percentage": 61.65, "elapsed_time": "1:29:59", "remaining_time": "0:55:58", "throughput": 2847.23, "total_tokens": 15373312} {"current_steps": 23530, "total_steps": 38160, "loss": 0.042, "lr": 1.9241279091826155e-05, "epoch": 12.332285115303984, "percentage": 61.66, "elapsed_time": "1:30:00", "remaining_time": "0:55:57", "throughput": 2847.42, "total_tokens": 15377632} {"current_steps": 23535, "total_steps": 38160, "loss": 0.0493, "lr": 1.923015289902758e-05, "epoch": 12.334905660377359, "percentage": 61.67, "elapsed_time": "1:30:01", "remaining_time": "0:55:56", "throughput": 2847.45, "total_tokens": 15380864} {"current_steps": 23540, "total_steps": 38160, "loss": 0.0314, "lr": 1.9219027913215193e-05, "epoch": 12.337526205450734, "percentage": 61.69, "elapsed_time": "1:30:02", "remaining_time": "0:55:55", "throughput": 2847.46, "total_tokens": 15384480} {"current_steps": 23545, "total_steps": 38160, "loss": 0.0511, "lr": 1.9207904136716214e-05, "epoch": 12.34014675052411, "percentage": 61.7, "elapsed_time": "1:30:04", "remaining_time": "0:55:54", "throughput": 2847.48, "total_tokens": 15387968} {"current_steps": 23550, "total_steps": 38160, "loss": 0.0494, "lr": 1.9196781571857608e-05, "epoch": 12.342767295597485, "percentage": 61.71, "elapsed_time": "1:30:05", "remaining_time": "0:55:53", "throughput": 2847.39, "total_tokens": 15390528} {"current_steps": 23555, "total_steps": 38160, "loss": 0.0406, "lr": 1.9185660220966097e-05, "epoch": 12.34538784067086, "percentage": 61.73, "elapsed_time": "1:30:06", "remaining_time": "0:55:52", "throughput": 2847.53, "total_tokens": 15394368} {"current_steps": 23560, "total_steps": 38160, "loss": 0.0562, "lr": 1.9174540086368135e-05, "epoch": 12.348008385744235, "percentage": 61.74, "elapsed_time": "1:30:07", "remaining_time": "0:55:50", "throughput": 2847.54, "total_tokens": 15397600} {"current_steps": 23565, "total_steps": 38160, "loss": 0.0352, "lr": 1.9163421170389918e-05, "epoch": 12.35062893081761, "percentage": 61.75, "elapsed_time": "1:30:08", "remaining_time": "0:55:49", "throughput": 2847.49, "total_tokens": 15400288} {"current_steps": 23570, "total_steps": 38160, "loss": 0.0749, "lr": 1.9152303475357402e-05, "epoch": 12.353249475890985, "percentage": 61.77, "elapsed_time": "1:30:09", "remaining_time": "0:55:48", "throughput": 2847.57, "total_tokens": 15404032} {"current_steps": 23575, "total_steps": 38160, "loss": 0.1301, "lr": 1.9141187003596295e-05, "epoch": 12.35587002096436, "percentage": 61.78, "elapsed_time": "1:30:10", "remaining_time": "0:55:47", "throughput": 2847.59, "total_tokens": 15407392} {"current_steps": 23580, "total_steps": 38160, "loss": 0.0246, "lr": 1.913007175743202e-05, "epoch": 12.358490566037736, "percentage": 61.79, "elapsed_time": "1:30:11", "remaining_time": "0:55:46", "throughput": 2847.55, "total_tokens": 15410208} {"current_steps": 23585, "total_steps": 38160, "loss": 0.0641, "lr": 1.9118957739189773e-05, "epoch": 12.36111111111111, "percentage": 61.81, "elapsed_time": "1:30:12", "remaining_time": "0:55:45", "throughput": 2847.49, "total_tokens": 15412992} {"current_steps": 23590, "total_steps": 38160, "loss": 0.0913, "lr": 1.910784495119447e-05, "epoch": 12.363731656184486, "percentage": 61.82, "elapsed_time": "1:30:14", "remaining_time": "0:55:43", "throughput": 2847.61, "total_tokens": 15417056} {"current_steps": 23595, "total_steps": 38160, "loss": 0.0685, "lr": 1.9096733395770778e-05, "epoch": 12.366352201257861, "percentage": 61.83, "elapsed_time": "1:30:15", "remaining_time": "0:55:42", "throughput": 2847.6, "total_tokens": 15420032} {"current_steps": 23600, "total_steps": 38160, "loss": 0.0567, "lr": 1.9085623075243114e-05, "epoch": 12.368972746331236, "percentage": 61.84, "elapsed_time": "1:30:16", "remaining_time": "0:55:41", "throughput": 2847.7, "total_tokens": 15423776} {"current_steps": 23605, "total_steps": 38160, "loss": 0.0773, "lr": 1.9074513991935623e-05, "epoch": 12.371593291404611, "percentage": 61.86, "elapsed_time": "1:30:17", "remaining_time": "0:55:40", "throughput": 2847.71, "total_tokens": 15426880} {"current_steps": 23610, "total_steps": 38160, "loss": 0.0821, "lr": 1.906340614817221e-05, "epoch": 12.374213836477987, "percentage": 61.87, "elapsed_time": "1:30:18", "remaining_time": "0:55:39", "throughput": 2847.83, "total_tokens": 15430688} {"current_steps": 23615, "total_steps": 38160, "loss": 0.0375, "lr": 1.9052299546276506e-05, "epoch": 12.376834381551364, "percentage": 61.88, "elapsed_time": "1:30:19", "remaining_time": "0:55:37", "throughput": 2847.82, "total_tokens": 15433728} {"current_steps": 23620, "total_steps": 38160, "loss": 0.0855, "lr": 1.904119418857187e-05, "epoch": 12.379454926624739, "percentage": 61.9, "elapsed_time": "1:30:20", "remaining_time": "0:55:36", "throughput": 2847.9, "total_tokens": 15437568} {"current_steps": 23625, "total_steps": 38160, "loss": 0.0679, "lr": 1.903009007738144e-05, "epoch": 12.382075471698114, "percentage": 61.91, "elapsed_time": "1:30:21", "remaining_time": "0:55:35", "throughput": 2847.85, "total_tokens": 15440384} {"current_steps": 23630, "total_steps": 38160, "loss": 0.0457, "lr": 1.9018987215028045e-05, "epoch": 12.384696016771489, "percentage": 61.92, "elapsed_time": "1:30:22", "remaining_time": "0:55:34", "throughput": 2847.96, "total_tokens": 15444032} {"current_steps": 23635, "total_steps": 38160, "loss": 0.0393, "lr": 1.9007885603834298e-05, "epoch": 12.387316561844864, "percentage": 61.94, "elapsed_time": "1:30:23", "remaining_time": "0:55:33", "throughput": 2847.83, "total_tokens": 15446400} {"current_steps": 23640, "total_steps": 38160, "loss": 0.0393, "lr": 1.8996785246122526e-05, "epoch": 12.38993710691824, "percentage": 61.95, "elapsed_time": "1:30:25", "remaining_time": "0:55:32", "throughput": 2847.98, "total_tokens": 15450880} {"current_steps": 23645, "total_steps": 38160, "loss": 0.0629, "lr": 1.898568614421478e-05, "epoch": 12.392557651991615, "percentage": 61.96, "elapsed_time": "1:30:26", "remaining_time": "0:55:31", "throughput": 2847.96, "total_tokens": 15453856} {"current_steps": 23650, "total_steps": 38160, "loss": 0.03, "lr": 1.897458830043288e-05, "epoch": 12.39517819706499, "percentage": 61.98, "elapsed_time": "1:30:27", "remaining_time": "0:55:29", "throughput": 2847.83, "total_tokens": 15456320} {"current_steps": 23655, "total_steps": 38160, "loss": 0.0745, "lr": 1.8963491717098372e-05, "epoch": 12.397798742138365, "percentage": 61.99, "elapsed_time": "1:30:28", "remaining_time": "0:55:28", "throughput": 2847.86, "total_tokens": 15459616} {"current_steps": 23660, "total_steps": 38160, "loss": 0.084, "lr": 1.8952396396532522e-05, "epoch": 12.40041928721174, "percentage": 62.0, "elapsed_time": "1:30:29", "remaining_time": "0:55:27", "throughput": 2848.0, "total_tokens": 15463520} {"current_steps": 23665, "total_steps": 38160, "loss": 0.0258, "lr": 1.8941302341056356e-05, "epoch": 12.403039832285115, "percentage": 62.02, "elapsed_time": "1:30:30", "remaining_time": "0:55:26", "throughput": 2848.07, "total_tokens": 15466976} {"current_steps": 23670, "total_steps": 38160, "loss": 0.0683, "lr": 1.8930209552990625e-05, "epoch": 12.40566037735849, "percentage": 62.03, "elapsed_time": "1:30:31", "remaining_time": "0:55:25", "throughput": 2848.14, "total_tokens": 15470784} {"current_steps": 23675, "total_steps": 38160, "loss": 0.0381, "lr": 1.8919118034655796e-05, "epoch": 12.408280922431866, "percentage": 62.04, "elapsed_time": "1:30:33", "remaining_time": "0:55:24", "throughput": 2848.21, "total_tokens": 15474816} {"current_steps": 23680, "total_steps": 38160, "loss": 0.0619, "lr": 1.8908027788372107e-05, "epoch": 12.41090146750524, "percentage": 62.05, "elapsed_time": "1:30:34", "remaining_time": "0:55:23", "throughput": 2848.2, "total_tokens": 15478016} {"current_steps": 23685, "total_steps": 38160, "loss": 0.0416, "lr": 1.88969388164595e-05, "epoch": 12.413522012578616, "percentage": 62.07, "elapsed_time": "1:30:35", "remaining_time": "0:55:21", "throughput": 2848.22, "total_tokens": 15481536} {"current_steps": 23690, "total_steps": 38160, "loss": 0.0348, "lr": 1.8885851121237666e-05, "epoch": 12.416142557651991, "percentage": 62.08, "elapsed_time": "1:30:36", "remaining_time": "0:55:20", "throughput": 2848.35, "total_tokens": 15485504} {"current_steps": 23695, "total_steps": 38160, "loss": 0.0976, "lr": 1.8874764705026023e-05, "epoch": 12.418763102725366, "percentage": 62.09, "elapsed_time": "1:30:37", "remaining_time": "0:55:19", "throughput": 2848.47, "total_tokens": 15489120} {"current_steps": 23700, "total_steps": 38160, "loss": 0.0729, "lr": 1.8863679570143728e-05, "epoch": 12.421383647798741, "percentage": 62.11, "elapsed_time": "1:30:38", "remaining_time": "0:55:18", "throughput": 2848.4, "total_tokens": 15491840} {"current_steps": 23705, "total_steps": 38160, "loss": 0.0235, "lr": 1.885259571890966e-05, "epoch": 12.424004192872117, "percentage": 62.12, "elapsed_time": "1:30:39", "remaining_time": "0:55:17", "throughput": 2848.37, "total_tokens": 15494880} {"current_steps": 23710, "total_steps": 38160, "loss": 0.0315, "lr": 1.8841513153642427e-05, "epoch": 12.426624737945493, "percentage": 62.13, "elapsed_time": "1:30:40", "remaining_time": "0:55:16", "throughput": 2848.25, "total_tokens": 15497312} {"current_steps": 23715, "total_steps": 38160, "loss": 0.0439, "lr": 1.8830431876660388e-05, "epoch": 12.429245283018869, "percentage": 62.15, "elapsed_time": "1:30:42", "remaining_time": "0:55:14", "throughput": 2848.23, "total_tokens": 15500416} {"current_steps": 23720, "total_steps": 38160, "loss": 0.0496, "lr": 1.8819351890281607e-05, "epoch": 12.431865828092244, "percentage": 62.16, "elapsed_time": "1:30:43", "remaining_time": "0:55:13", "throughput": 2848.23, "total_tokens": 15503520} {"current_steps": 23725, "total_steps": 38160, "loss": 0.0439, "lr": 1.880827319682391e-05, "epoch": 12.434486373165619, "percentage": 62.17, "elapsed_time": "1:30:44", "remaining_time": "0:55:12", "throughput": 2848.22, "total_tokens": 15506656} {"current_steps": 23730, "total_steps": 38160, "loss": 0.0405, "lr": 1.879719579860481e-05, "epoch": 12.437106918238994, "percentage": 62.19, "elapsed_time": "1:30:45", "remaining_time": "0:55:11", "throughput": 2848.25, "total_tokens": 15509792} {"current_steps": 23735, "total_steps": 38160, "loss": 0.0422, "lr": 1.878611969794159e-05, "epoch": 12.43972746331237, "percentage": 62.2, "elapsed_time": "1:30:46", "remaining_time": "0:55:10", "throughput": 2848.24, "total_tokens": 15512768} {"current_steps": 23740, "total_steps": 38160, "loss": 0.0844, "lr": 1.8775044897151232e-05, "epoch": 12.442348008385745, "percentage": 62.21, "elapsed_time": "1:30:47", "remaining_time": "0:55:08", "throughput": 2848.22, "total_tokens": 15515712} {"current_steps": 23745, "total_steps": 38160, "loss": 0.0727, "lr": 1.876397139855047e-05, "epoch": 12.44496855345912, "percentage": 62.22, "elapsed_time": "1:30:48", "remaining_time": "0:55:07", "throughput": 2848.19, "total_tokens": 15518528} {"current_steps": 23750, "total_steps": 38160, "loss": 0.0526, "lr": 1.875289920445574e-05, "epoch": 12.447589098532495, "percentage": 62.24, "elapsed_time": "1:30:49", "remaining_time": "0:55:06", "throughput": 2848.15, "total_tokens": 15521472} {"current_steps": 23755, "total_steps": 38160, "loss": 0.0166, "lr": 1.8741828317183234e-05, "epoch": 12.45020964360587, "percentage": 62.25, "elapsed_time": "1:30:50", "remaining_time": "0:55:05", "throughput": 2848.1, "total_tokens": 15524320} {"current_steps": 23760, "total_steps": 38160, "loss": 0.0396, "lr": 1.873075873904885e-05, "epoch": 12.452830188679245, "percentage": 62.26, "elapsed_time": "1:30:51", "remaining_time": "0:55:04", "throughput": 2848.06, "total_tokens": 15527168} {"current_steps": 23765, "total_steps": 38160, "loss": 0.0371, "lr": 1.87196904723682e-05, "epoch": 12.45545073375262, "percentage": 62.28, "elapsed_time": "1:30:53", "remaining_time": "0:55:03", "throughput": 2848.28, "total_tokens": 15532064} {"current_steps": 23770, "total_steps": 38160, "loss": 0.0251, "lr": 1.8708623519456665e-05, "epoch": 12.458071278825996, "percentage": 62.29, "elapsed_time": "1:30:54", "remaining_time": "0:55:01", "throughput": 2848.25, "total_tokens": 15534944} {"current_steps": 23775, "total_steps": 38160, "loss": 0.0387, "lr": 1.8697557882629308e-05, "epoch": 12.46069182389937, "percentage": 62.3, "elapsed_time": "1:30:55", "remaining_time": "0:55:00", "throughput": 2848.27, "total_tokens": 15538368} {"current_steps": 23780, "total_steps": 38160, "loss": 0.0803, "lr": 1.868649356420094e-05, "epoch": 12.463312368972746, "percentage": 62.32, "elapsed_time": "1:30:56", "remaining_time": "0:54:59", "throughput": 2848.22, "total_tokens": 15541280} {"current_steps": 23785, "total_steps": 38160, "loss": 0.0218, "lr": 1.86754305664861e-05, "epoch": 12.465932914046121, "percentage": 62.33, "elapsed_time": "1:30:57", "remaining_time": "0:54:58", "throughput": 2848.28, "total_tokens": 15544736} {"current_steps": 23790, "total_steps": 38160, "loss": 0.0657, "lr": 1.866436889179902e-05, "epoch": 12.468553459119496, "percentage": 62.34, "elapsed_time": "1:30:58", "remaining_time": "0:54:57", "throughput": 2848.52, "total_tokens": 15549568} {"current_steps": 23795, "total_steps": 38160, "loss": 0.0278, "lr": 1.865330854245369e-05, "epoch": 12.471174004192871, "percentage": 62.36, "elapsed_time": "1:31:00", "remaining_time": "0:54:56", "throughput": 2848.56, "total_tokens": 15553184} {"current_steps": 23800, "total_steps": 38160, "loss": 0.0408, "lr": 1.8642249520763804e-05, "epoch": 12.473794549266247, "percentage": 62.37, "elapsed_time": "1:31:01", "remaining_time": "0:54:55", "throughput": 2848.71, "total_tokens": 15557120} {"current_steps": 23805, "total_steps": 38160, "loss": 0.0604, "lr": 1.863119182904278e-05, "epoch": 12.476415094339623, "percentage": 62.38, "elapsed_time": "1:31:02", "remaining_time": "0:54:53", "throughput": 2848.89, "total_tokens": 15561632} {"current_steps": 23810, "total_steps": 38160, "loss": 0.038, "lr": 1.8620135469603777e-05, "epoch": 12.479035639412999, "percentage": 62.4, "elapsed_time": "1:31:04", "remaining_time": "0:54:53", "throughput": 2849.27, "total_tokens": 15568736} {"current_steps": 23815, "total_steps": 38160, "loss": 0.0371, "lr": 1.8609080444759653e-05, "epoch": 12.481656184486374, "percentage": 62.41, "elapsed_time": "1:31:05", "remaining_time": "0:54:51", "throughput": 2849.35, "total_tokens": 15572352} {"current_steps": 23820, "total_steps": 38160, "loss": 0.0405, "lr": 1.8598026756822978e-05, "epoch": 12.484276729559749, "percentage": 62.42, "elapsed_time": "1:31:06", "remaining_time": "0:54:50", "throughput": 2849.24, "total_tokens": 15574688} {"current_steps": 23825, "total_steps": 38160, "loss": 0.0262, "lr": 1.8586974408106074e-05, "epoch": 12.486897274633124, "percentage": 62.43, "elapsed_time": "1:31:07", "remaining_time": "0:54:49", "throughput": 2849.19, "total_tokens": 15577376} {"current_steps": 23830, "total_steps": 38160, "loss": 0.0531, "lr": 1.8575923400920954e-05, "epoch": 12.4895178197065, "percentage": 62.45, "elapsed_time": "1:31:08", "remaining_time": "0:54:48", "throughput": 2849.3, "total_tokens": 15581280} {"current_steps": 23835, "total_steps": 38160, "loss": 0.055, "lr": 1.856487373757937e-05, "epoch": 12.492138364779874, "percentage": 62.46, "elapsed_time": "1:31:09", "remaining_time": "0:54:47", "throughput": 2849.35, "total_tokens": 15584544} {"current_steps": 23840, "total_steps": 38160, "loss": 0.0626, "lr": 1.8553825420392792e-05, "epoch": 12.49475890985325, "percentage": 62.47, "elapsed_time": "1:31:10", "remaining_time": "0:54:46", "throughput": 2849.32, "total_tokens": 15587520} {"current_steps": 23845, "total_steps": 38160, "loss": 0.0987, "lr": 1.8542778451672385e-05, "epoch": 12.497379454926625, "percentage": 62.49, "elapsed_time": "1:31:11", "remaining_time": "0:54:44", "throughput": 2849.32, "total_tokens": 15590624} {"current_steps": 23850, "total_steps": 38160, "loss": 0.0497, "lr": 1.8531732833729063e-05, "epoch": 12.5, "percentage": 62.5, "elapsed_time": "1:31:12", "remaining_time": "0:54:43", "throughput": 2849.46, "total_tokens": 15594560} {"current_steps": 23855, "total_steps": 38160, "loss": 0.095, "lr": 1.852068856887343e-05, "epoch": 12.502620545073375, "percentage": 62.51, "elapsed_time": "1:31:13", "remaining_time": "0:54:42", "throughput": 2849.53, "total_tokens": 15598048} {"current_steps": 23860, "total_steps": 38160, "loss": 0.06, "lr": 1.8509645659415837e-05, "epoch": 12.50524109014675, "percentage": 62.53, "elapsed_time": "1:31:15", "remaining_time": "0:54:41", "throughput": 2849.68, "total_tokens": 15602048} {"current_steps": 23865, "total_steps": 38160, "loss": 0.0798, "lr": 1.849860410766632e-05, "epoch": 12.507861635220126, "percentage": 62.54, "elapsed_time": "1:31:16", "remaining_time": "0:54:40", "throughput": 2849.67, "total_tokens": 15605152} {"current_steps": 23870, "total_steps": 38160, "loss": 0.0506, "lr": 1.8487563915934664e-05, "epoch": 12.5104821802935, "percentage": 62.55, "elapsed_time": "1:31:17", "remaining_time": "0:54:38", "throughput": 2849.61, "total_tokens": 15607808} {"current_steps": 23875, "total_steps": 38160, "loss": 0.0354, "lr": 1.847652508653033e-05, "epoch": 12.513102725366876, "percentage": 62.57, "elapsed_time": "1:31:18", "remaining_time": "0:54:38", "throughput": 2849.81, "total_tokens": 15613344} {"current_steps": 23880, "total_steps": 38160, "loss": 0.0519, "lr": 1.846548762176252e-05, "epoch": 12.515723270440251, "percentage": 62.58, "elapsed_time": "1:31:19", "remaining_time": "0:54:36", "throughput": 2849.77, "total_tokens": 15616128} {"current_steps": 23885, "total_steps": 38160, "loss": 0.0961, "lr": 1.845445152394015e-05, "epoch": 12.518343815513626, "percentage": 62.59, "elapsed_time": "1:31:20", "remaining_time": "0:54:35", "throughput": 2849.78, "total_tokens": 15619328} {"current_steps": 23890, "total_steps": 38160, "loss": 0.0368, "lr": 1.8443416795371853e-05, "epoch": 12.520964360587001, "percentage": 62.6, "elapsed_time": "1:31:22", "remaining_time": "0:54:34", "throughput": 2849.8, "total_tokens": 15622624} {"current_steps": 23895, "total_steps": 38160, "loss": 0.0365, "lr": 1.8432383438365957e-05, "epoch": 12.523584905660378, "percentage": 62.62, "elapsed_time": "1:31:23", "remaining_time": "0:54:33", "throughput": 2849.92, "total_tokens": 15626560} {"current_steps": 23900, "total_steps": 38160, "loss": 0.1021, "lr": 1.8421351455230528e-05, "epoch": 12.526205450733752, "percentage": 62.63, "elapsed_time": "1:31:24", "remaining_time": "0:54:32", "throughput": 2849.99, "total_tokens": 15629888} {"current_steps": 23905, "total_steps": 38160, "loss": 0.0626, "lr": 1.8410320848273315e-05, "epoch": 12.528825995807129, "percentage": 62.64, "elapsed_time": "1:31:25", "remaining_time": "0:54:30", "throughput": 2850.04, "total_tokens": 15633312} {"current_steps": 23910, "total_steps": 38160, "loss": 0.0663, "lr": 1.8399291619801794e-05, "epoch": 12.531446540880504, "percentage": 62.66, "elapsed_time": "1:31:26", "remaining_time": "0:54:29", "throughput": 2849.97, "total_tokens": 15636096} {"current_steps": 23915, "total_steps": 38160, "loss": 0.0289, "lr": 1.838826377212317e-05, "epoch": 12.534067085953879, "percentage": 62.67, "elapsed_time": "1:31:27", "remaining_time": "0:54:28", "throughput": 2849.86, "total_tokens": 15638496} {"current_steps": 23920, "total_steps": 38160, "loss": 0.0563, "lr": 1.8377237307544326e-05, "epoch": 12.536687631027254, "percentage": 62.68, "elapsed_time": "1:31:28", "remaining_time": "0:54:27", "throughput": 2850.01, "total_tokens": 15642848} {"current_steps": 23925, "total_steps": 38160, "loss": 0.0869, "lr": 1.8366212228371894e-05, "epoch": 12.53930817610063, "percentage": 62.7, "elapsed_time": "1:31:29", "remaining_time": "0:54:26", "throughput": 2850.03, "total_tokens": 15646080} {"current_steps": 23930, "total_steps": 38160, "loss": 0.0604, "lr": 1.8355188536912173e-05, "epoch": 12.541928721174004, "percentage": 62.71, "elapsed_time": "1:31:30", "remaining_time": "0:54:25", "throughput": 2850.0, "total_tokens": 15648928} {"current_steps": 23935, "total_steps": 38160, "loss": 0.057, "lr": 1.83441662354712e-05, "epoch": 12.54454926624738, "percentage": 62.72, "elapsed_time": "1:31:32", "remaining_time": "0:54:24", "throughput": 2850.06, "total_tokens": 15652608} {"current_steps": 23940, "total_steps": 38160, "loss": 0.0453, "lr": 1.8333145326354722e-05, "epoch": 12.547169811320755, "percentage": 62.74, "elapsed_time": "1:31:33", "remaining_time": "0:54:22", "throughput": 2850.18, "total_tokens": 15656576} {"current_steps": 23945, "total_steps": 38160, "loss": 0.0286, "lr": 1.8322125811868175e-05, "epoch": 12.54979035639413, "percentage": 62.75, "elapsed_time": "1:31:34", "remaining_time": "0:54:21", "throughput": 2850.13, "total_tokens": 15659264} {"current_steps": 23950, "total_steps": 38160, "loss": 0.0682, "lr": 1.831110769431673e-05, "epoch": 12.552410901467505, "percentage": 62.76, "elapsed_time": "1:31:35", "remaining_time": "0:54:20", "throughput": 2850.12, "total_tokens": 15662272} {"current_steps": 23955, "total_steps": 38160, "loss": 0.0366, "lr": 1.8300090976005247e-05, "epoch": 12.55503144654088, "percentage": 62.78, "elapsed_time": "1:31:36", "remaining_time": "0:54:19", "throughput": 2850.11, "total_tokens": 15665184} {"current_steps": 23960, "total_steps": 38160, "loss": 0.0373, "lr": 1.8289075659238285e-05, "epoch": 12.557651991614255, "percentage": 62.79, "elapsed_time": "1:31:37", "remaining_time": "0:54:18", "throughput": 2850.16, "total_tokens": 15668832} {"current_steps": 23965, "total_steps": 38160, "loss": 0.1336, "lr": 1.8278061746320134e-05, "epoch": 12.56027253668763, "percentage": 62.8, "elapsed_time": "1:31:38", "remaining_time": "0:54:16", "throughput": 2850.18, "total_tokens": 15672160} {"current_steps": 23970, "total_steps": 38160, "loss": 0.0562, "lr": 1.8267049239554786e-05, "epoch": 12.562893081761006, "percentage": 62.81, "elapsed_time": "1:31:39", "remaining_time": "0:54:15", "throughput": 2850.22, "total_tokens": 15675296} {"current_steps": 23975, "total_steps": 38160, "loss": 0.0369, "lr": 1.8256038141245912e-05, "epoch": 12.565513626834381, "percentage": 62.83, "elapsed_time": "1:31:40", "remaining_time": "0:54:14", "throughput": 2850.24, "total_tokens": 15678784} {"current_steps": 23980, "total_steps": 38160, "loss": 0.0605, "lr": 1.824502845369693e-05, "epoch": 12.568134171907756, "percentage": 62.84, "elapsed_time": "1:31:41", "remaining_time": "0:54:13", "throughput": 2850.08, "total_tokens": 15680992} {"current_steps": 23985, "total_steps": 38160, "loss": 0.0349, "lr": 1.8234020179210938e-05, "epoch": 12.570754716981131, "percentage": 62.85, "elapsed_time": "1:31:42", "remaining_time": "0:54:12", "throughput": 2850.06, "total_tokens": 15683872} {"current_steps": 23990, "total_steps": 38160, "loss": 0.0972, "lr": 1.8223013320090715e-05, "epoch": 12.573375262054507, "percentage": 62.87, "elapsed_time": "1:31:44", "remaining_time": "0:54:11", "throughput": 2849.99, "total_tokens": 15686432} {"current_steps": 23995, "total_steps": 38160, "loss": 0.0336, "lr": 1.82120078786388e-05, "epoch": 12.575995807127882, "percentage": 62.88, "elapsed_time": "1:31:45", "remaining_time": "0:54:09", "throughput": 2850.19, "total_tokens": 15691296} {"current_steps": 24000, "total_steps": 38160, "loss": 0.0997, "lr": 1.820100385715739e-05, "epoch": 12.578616352201259, "percentage": 62.89, "elapsed_time": "1:31:46", "remaining_time": "0:54:08", "throughput": 2850.33, "total_tokens": 15695712} {"current_steps": 24005, "total_steps": 38160, "loss": 0.0274, "lr": 1.8190001257948414e-05, "epoch": 12.581236897274634, "percentage": 62.91, "elapsed_time": "1:31:47", "remaining_time": "0:54:07", "throughput": 2850.37, "total_tokens": 15699264} {"current_steps": 24010, "total_steps": 38160, "loss": 0.0652, "lr": 1.8179000083313483e-05, "epoch": 12.583857442348009, "percentage": 62.92, "elapsed_time": "1:31:48", "remaining_time": "0:54:06", "throughput": 2850.28, "total_tokens": 15701952} {"current_steps": 24015, "total_steps": 38160, "loss": 0.0434, "lr": 1.8168000335553907e-05, "epoch": 12.586477987421384, "percentage": 62.93, "elapsed_time": "1:31:49", "remaining_time": "0:54:05", "throughput": 2850.25, "total_tokens": 15704768} {"current_steps": 24020, "total_steps": 38160, "loss": 0.0838, "lr": 1.8157002016970723e-05, "epoch": 12.58909853249476, "percentage": 62.95, "elapsed_time": "1:31:51", "remaining_time": "0:54:04", "throughput": 2850.35, "total_tokens": 15708352} {"current_steps": 24025, "total_steps": 38160, "loss": 0.0381, "lr": 1.8146005129864644e-05, "epoch": 12.591719077568134, "percentage": 62.96, "elapsed_time": "1:31:52", "remaining_time": "0:54:03", "throughput": 2850.33, "total_tokens": 15711424} {"current_steps": 24030, "total_steps": 38160, "loss": 0.0557, "lr": 1.81350096765361e-05, "epoch": 12.59433962264151, "percentage": 62.97, "elapsed_time": "1:31:53", "remaining_time": "0:54:01", "throughput": 2850.37, "total_tokens": 15714848} {"current_steps": 24035, "total_steps": 38160, "loss": 0.0583, "lr": 1.812401565928521e-05, "epoch": 12.596960167714885, "percentage": 62.98, "elapsed_time": "1:31:54", "remaining_time": "0:54:00", "throughput": 2850.32, "total_tokens": 15717664} {"current_steps": 24040, "total_steps": 38160, "loss": 0.0545, "lr": 1.8113023080411806e-05, "epoch": 12.59958071278826, "percentage": 63.0, "elapsed_time": "1:31:55", "remaining_time": "0:53:59", "throughput": 2850.28, "total_tokens": 15720448} {"current_steps": 24045, "total_steps": 38160, "loss": 0.0449, "lr": 1.810203194221539e-05, "epoch": 12.602201257861635, "percentage": 63.01, "elapsed_time": "1:31:56", "remaining_time": "0:53:58", "throughput": 2850.29, "total_tokens": 15723552} {"current_steps": 24050, "total_steps": 38160, "loss": 0.0182, "lr": 1.8091042246995206e-05, "epoch": 12.60482180293501, "percentage": 63.02, "elapsed_time": "1:31:57", "remaining_time": "0:53:57", "throughput": 2850.43, "total_tokens": 15727616} {"current_steps": 24055, "total_steps": 38160, "loss": 0.0337, "lr": 1.8080053997050154e-05, "epoch": 12.607442348008385, "percentage": 63.04, "elapsed_time": "1:31:58", "remaining_time": "0:53:55", "throughput": 2850.35, "total_tokens": 15730240} {"current_steps": 24060, "total_steps": 38160, "loss": 0.0588, "lr": 1.8069067194678867e-05, "epoch": 12.61006289308176, "percentage": 63.05, "elapsed_time": "1:31:59", "remaining_time": "0:53:54", "throughput": 2850.45, "total_tokens": 15734048} {"current_steps": 24065, "total_steps": 38160, "loss": 0.0512, "lr": 1.8058081842179642e-05, "epoch": 12.612683438155136, "percentage": 63.06, "elapsed_time": "1:32:00", "remaining_time": "0:53:53", "throughput": 2850.43, "total_tokens": 15736896} {"current_steps": 24070, "total_steps": 38160, "loss": 0.0613, "lr": 1.804709794185051e-05, "epoch": 12.615303983228511, "percentage": 63.08, "elapsed_time": "1:32:01", "remaining_time": "0:53:52", "throughput": 2850.42, "total_tokens": 15739872} {"current_steps": 24075, "total_steps": 38160, "loss": 0.0463, "lr": 1.8036115495989164e-05, "epoch": 12.617924528301886, "percentage": 63.09, "elapsed_time": "1:32:03", "remaining_time": "0:53:51", "throughput": 2850.42, "total_tokens": 15743200} {"current_steps": 24080, "total_steps": 38160, "loss": 0.0613, "lr": 1.8025134506892997e-05, "epoch": 12.620545073375261, "percentage": 63.1, "elapsed_time": "1:32:04", "remaining_time": "0:53:50", "throughput": 2850.6, "total_tokens": 15748224} {"current_steps": 24085, "total_steps": 38160, "loss": 0.0336, "lr": 1.8014154976859126e-05, "epoch": 12.623165618448636, "percentage": 63.12, "elapsed_time": "1:32:05", "remaining_time": "0:53:49", "throughput": 2850.56, "total_tokens": 15751168} {"current_steps": 24090, "total_steps": 38160, "loss": 0.0633, "lr": 1.800317690818433e-05, "epoch": 12.625786163522012, "percentage": 63.13, "elapsed_time": "1:32:06", "remaining_time": "0:53:47", "throughput": 2850.61, "total_tokens": 15754592} {"current_steps": 24095, "total_steps": 38160, "loss": 0.0539, "lr": 1.799220030316511e-05, "epoch": 12.628406708595389, "percentage": 63.14, "elapsed_time": "1:32:07", "remaining_time": "0:53:46", "throughput": 2850.72, "total_tokens": 15758368} {"current_steps": 24100, "total_steps": 38160, "loss": 0.0424, "lr": 1.7981225164097633e-05, "epoch": 12.631027253668764, "percentage": 63.16, "elapsed_time": "1:32:09", "remaining_time": "0:53:45", "throughput": 2850.69, "total_tokens": 15761504} {"current_steps": 24105, "total_steps": 38160, "loss": 0.0618, "lr": 1.7970251493277774e-05, "epoch": 12.633647798742139, "percentage": 63.17, "elapsed_time": "1:32:10", "remaining_time": "0:53:44", "throughput": 2850.63, "total_tokens": 15764224} {"current_steps": 24110, "total_steps": 38160, "loss": 0.044, "lr": 1.7959279293001102e-05, "epoch": 12.636268343815514, "percentage": 63.18, "elapsed_time": "1:32:11", "remaining_time": "0:53:43", "throughput": 2850.6, "total_tokens": 15767072} {"current_steps": 24115, "total_steps": 38160, "loss": 0.1237, "lr": 1.7948308565562876e-05, "epoch": 12.63888888888889, "percentage": 63.19, "elapsed_time": "1:32:12", "remaining_time": "0:53:42", "throughput": 2850.58, "total_tokens": 15769920} {"current_steps": 24120, "total_steps": 38160, "loss": 0.0334, "lr": 1.793733931325805e-05, "epoch": 12.641509433962264, "percentage": 63.21, "elapsed_time": "1:32:13", "remaining_time": "0:53:40", "throughput": 2850.68, "total_tokens": 15773472} {"current_steps": 24125, "total_steps": 38160, "loss": 0.0422, "lr": 1.792637153838127e-05, "epoch": 12.64412997903564, "percentage": 63.22, "elapsed_time": "1:32:14", "remaining_time": "0:53:39", "throughput": 2850.58, "total_tokens": 15776064} {"current_steps": 24130, "total_steps": 38160, "loss": 0.0452, "lr": 1.7915405243226864e-05, "epoch": 12.646750524109015, "percentage": 63.23, "elapsed_time": "1:32:15", "remaining_time": "0:53:38", "throughput": 2850.62, "total_tokens": 15779552} {"current_steps": 24135, "total_steps": 38160, "loss": 0.0287, "lr": 1.7904440430088847e-05, "epoch": 12.64937106918239, "percentage": 63.25, "elapsed_time": "1:32:16", "remaining_time": "0:53:37", "throughput": 2850.59, "total_tokens": 15782272} {"current_steps": 24140, "total_steps": 38160, "loss": 0.0733, "lr": 1.7893477101260947e-05, "epoch": 12.651991614255765, "percentage": 63.26, "elapsed_time": "1:32:17", "remaining_time": "0:53:36", "throughput": 2850.52, "total_tokens": 15785024} {"current_steps": 24145, "total_steps": 38160, "loss": 0.0773, "lr": 1.7882515259036558e-05, "epoch": 12.65461215932914, "percentage": 63.27, "elapsed_time": "1:32:18", "remaining_time": "0:53:34", "throughput": 2850.51, "total_tokens": 15788128} {"current_steps": 24150, "total_steps": 38160, "loss": 0.0489, "lr": 1.787155490570878e-05, "epoch": 12.657232704402515, "percentage": 63.29, "elapsed_time": "1:32:19", "remaining_time": "0:53:33", "throughput": 2850.45, "total_tokens": 15790944} {"current_steps": 24155, "total_steps": 38160, "loss": 0.0586, "lr": 1.7860596043570398e-05, "epoch": 12.65985324947589, "percentage": 63.3, "elapsed_time": "1:32:20", "remaining_time": "0:53:32", "throughput": 2850.42, "total_tokens": 15793920} {"current_steps": 24160, "total_steps": 38160, "loss": 0.0472, "lr": 1.7849638674913863e-05, "epoch": 12.662473794549266, "percentage": 63.31, "elapsed_time": "1:32:22", "remaining_time": "0:53:31", "throughput": 2850.74, "total_tokens": 15799552} {"current_steps": 24165, "total_steps": 38160, "loss": 0.0363, "lr": 1.7838682802031344e-05, "epoch": 12.665094339622641, "percentage": 63.33, "elapsed_time": "1:32:23", "remaining_time": "0:53:30", "throughput": 2850.76, "total_tokens": 15802656} {"current_steps": 24170, "total_steps": 38160, "loss": 0.0501, "lr": 1.782772842721468e-05, "epoch": 12.667714884696016, "percentage": 63.34, "elapsed_time": "1:32:24", "remaining_time": "0:53:29", "throughput": 2850.83, "total_tokens": 15806112} {"current_steps": 24175, "total_steps": 38160, "loss": 0.0256, "lr": 1.7816775552755406e-05, "epoch": 12.670335429769391, "percentage": 63.35, "elapsed_time": "1:32:25", "remaining_time": "0:53:28", "throughput": 2850.74, "total_tokens": 15808928} {"current_steps": 24180, "total_steps": 38160, "loss": 0.0752, "lr": 1.780582418094473e-05, "epoch": 12.672955974842766, "percentage": 63.36, "elapsed_time": "1:32:26", "remaining_time": "0:53:26", "throughput": 2850.78, "total_tokens": 15812320} {"current_steps": 24185, "total_steps": 38160, "loss": 0.0306, "lr": 1.7794874314073573e-05, "epoch": 12.675576519916142, "percentage": 63.38, "elapsed_time": "1:32:27", "remaining_time": "0:53:25", "throughput": 2850.92, "total_tokens": 15816608} {"current_steps": 24190, "total_steps": 38160, "loss": 0.0659, "lr": 1.7783925954432503e-05, "epoch": 12.678197064989519, "percentage": 63.39, "elapsed_time": "1:32:28", "remaining_time": "0:53:24", "throughput": 2850.92, "total_tokens": 15819680} {"current_steps": 24195, "total_steps": 38160, "loss": 0.0528, "lr": 1.777297910431179e-05, "epoch": 12.680817610062894, "percentage": 63.4, "elapsed_time": "1:32:30", "remaining_time": "0:53:23", "throughput": 2850.92, "total_tokens": 15822848} {"current_steps": 24200, "total_steps": 38160, "loss": 0.055, "lr": 1.7762033766001402e-05, "epoch": 12.683438155136269, "percentage": 63.42, "elapsed_time": "1:32:31", "remaining_time": "0:53:22", "throughput": 2850.76, "total_tokens": 15825312} {"current_steps": 24205, "total_steps": 38160, "loss": 0.043, "lr": 1.7751089941790977e-05, "epoch": 12.686058700209644, "percentage": 63.43, "elapsed_time": "1:32:32", "remaining_time": "0:53:21", "throughput": 2850.74, "total_tokens": 15828672} {"current_steps": 24210, "total_steps": 38160, "loss": 0.0504, "lr": 1.7740147633969844e-05, "epoch": 12.68867924528302, "percentage": 63.44, "elapsed_time": "1:32:33", "remaining_time": "0:53:19", "throughput": 2850.73, "total_tokens": 15831648} {"current_steps": 24215, "total_steps": 38160, "loss": 0.0455, "lr": 1.772920684482699e-05, "epoch": 12.691299790356394, "percentage": 63.46, "elapsed_time": "1:32:34", "remaining_time": "0:53:18", "throughput": 2850.85, "total_tokens": 15835456} {"current_steps": 24220, "total_steps": 38160, "loss": 0.0765, "lr": 1.771826757665112e-05, "epoch": 12.69392033542977, "percentage": 63.47, "elapsed_time": "1:32:35", "remaining_time": "0:53:17", "throughput": 2850.94, "total_tokens": 15839008} {"current_steps": 24225, "total_steps": 38160, "loss": 0.0585, "lr": 1.770732983173059e-05, "epoch": 12.696540880503145, "percentage": 63.48, "elapsed_time": "1:32:36", "remaining_time": "0:53:16", "throughput": 2850.94, "total_tokens": 15842048} {"current_steps": 24230, "total_steps": 38160, "loss": 0.0367, "lr": 1.7696393612353467e-05, "epoch": 12.69916142557652, "percentage": 63.5, "elapsed_time": "1:32:37", "remaining_time": "0:53:15", "throughput": 2850.93, "total_tokens": 15844992} {"current_steps": 24235, "total_steps": 38160, "loss": 0.0328, "lr": 1.7685458920807474e-05, "epoch": 12.701781970649895, "percentage": 63.51, "elapsed_time": "1:32:38", "remaining_time": "0:53:14", "throughput": 2850.75, "total_tokens": 15847008} {"current_steps": 24240, "total_steps": 38160, "loss": 0.1013, "lr": 1.7674525759380033e-05, "epoch": 12.70440251572327, "percentage": 63.52, "elapsed_time": "1:32:39", "remaining_time": "0:53:12", "throughput": 2850.71, "total_tokens": 15849760} {"current_steps": 24245, "total_steps": 38160, "loss": 0.0299, "lr": 1.766359413035823e-05, "epoch": 12.707023060796645, "percentage": 63.54, "elapsed_time": "1:32:41", "remaining_time": "0:53:11", "throughput": 2850.66, "total_tokens": 15852608} {"current_steps": 24250, "total_steps": 38160, "loss": 0.0312, "lr": 1.7652664036028827e-05, "epoch": 12.70964360587002, "percentage": 63.55, "elapsed_time": "1:32:42", "remaining_time": "0:53:10", "throughput": 2850.69, "total_tokens": 15855904} {"current_steps": 24255, "total_steps": 38160, "loss": 0.0573, "lr": 1.7641735478678288e-05, "epoch": 12.712264150943396, "percentage": 63.56, "elapsed_time": "1:32:43", "remaining_time": "0:53:09", "throughput": 2850.84, "total_tokens": 15860224} {"current_steps": 24260, "total_steps": 38160, "loss": 0.0458, "lr": 1.763080846059274e-05, "epoch": 12.714884696016771, "percentage": 63.57, "elapsed_time": "1:32:44", "remaining_time": "0:53:08", "throughput": 2850.81, "total_tokens": 15863136} {"current_steps": 24265, "total_steps": 38160, "loss": 0.0595, "lr": 1.7619882984057987e-05, "epoch": 12.717505241090146, "percentage": 63.59, "elapsed_time": "1:32:45", "remaining_time": "0:53:06", "throughput": 2850.86, "total_tokens": 15866400} {"current_steps": 24270, "total_steps": 38160, "loss": 0.0305, "lr": 1.760895905135953e-05, "epoch": 12.720125786163521, "percentage": 63.6, "elapsed_time": "1:32:46", "remaining_time": "0:53:05", "throughput": 2850.75, "total_tokens": 15868896} {"current_steps": 24275, "total_steps": 38160, "loss": 0.0619, "lr": 1.7598036664782508e-05, "epoch": 12.722746331236896, "percentage": 63.61, "elapsed_time": "1:32:47", "remaining_time": "0:53:04", "throughput": 2850.64, "total_tokens": 15871232} {"current_steps": 24280, "total_steps": 38160, "loss": 0.0475, "lr": 1.7587115826611766e-05, "epoch": 12.725366876310272, "percentage": 63.63, "elapsed_time": "1:32:49", "remaining_time": "0:53:03", "throughput": 2850.86, "total_tokens": 15876800} {"current_steps": 24285, "total_steps": 38160, "loss": 0.0212, "lr": 1.7576196539131828e-05, "epoch": 12.727987421383649, "percentage": 63.64, "elapsed_time": "1:32:50", "remaining_time": "0:53:02", "throughput": 2850.78, "total_tokens": 15879520} {"current_steps": 24290, "total_steps": 38160, "loss": 0.0537, "lr": 1.7565278804626872e-05, "epoch": 12.730607966457024, "percentage": 63.65, "elapsed_time": "1:32:51", "remaining_time": "0:53:01", "throughput": 2850.76, "total_tokens": 15882432} {"current_steps": 24295, "total_steps": 38160, "loss": 0.0633, "lr": 1.755436262538078e-05, "epoch": 12.733228511530399, "percentage": 63.67, "elapsed_time": "1:32:52", "remaining_time": "0:53:00", "throughput": 2851.04, "total_tokens": 15887648} {"current_steps": 24300, "total_steps": 38160, "loss": 0.0462, "lr": 1.7543448003677082e-05, "epoch": 12.735849056603774, "percentage": 63.68, "elapsed_time": "1:32:53", "remaining_time": "0:52:59", "throughput": 2851.25, "total_tokens": 15892704} {"current_steps": 24305, "total_steps": 38160, "loss": 0.0299, "lr": 1.7532534941798985e-05, "epoch": 12.73846960167715, "percentage": 63.69, "elapsed_time": "1:32:55", "remaining_time": "0:52:58", "throughput": 2851.22, "total_tokens": 15895840} {"current_steps": 24310, "total_steps": 38160, "loss": 0.0699, "lr": 1.752162344202939e-05, "epoch": 12.741090146750524, "percentage": 63.71, "elapsed_time": "1:32:56", "remaining_time": "0:52:56", "throughput": 2851.31, "total_tokens": 15899488} {"current_steps": 24315, "total_steps": 38160, "loss": 0.0428, "lr": 1.751071350665085e-05, "epoch": 12.7437106918239, "percentage": 63.72, "elapsed_time": "1:32:57", "remaining_time": "0:52:55", "throughput": 2851.36, "total_tokens": 15902816} {"current_steps": 24320, "total_steps": 38160, "loss": 0.0477, "lr": 1.7499805137945602e-05, "epoch": 12.746331236897275, "percentage": 63.73, "elapsed_time": "1:32:58", "remaining_time": "0:52:54", "throughput": 2851.32, "total_tokens": 15905568} {"current_steps": 24325, "total_steps": 38160, "loss": 0.0421, "lr": 1.7488898338195566e-05, "epoch": 12.74895178197065, "percentage": 63.74, "elapsed_time": "1:32:59", "remaining_time": "0:52:53", "throughput": 2851.42, "total_tokens": 15909120} {"current_steps": 24330, "total_steps": 38160, "loss": 0.0344, "lr": 1.7477993109682288e-05, "epoch": 12.751572327044025, "percentage": 63.76, "elapsed_time": "1:33:00", "remaining_time": "0:52:52", "throughput": 2851.38, "total_tokens": 15911872} {"current_steps": 24335, "total_steps": 38160, "loss": 0.0598, "lr": 1.7467089454687043e-05, "epoch": 12.7541928721174, "percentage": 63.77, "elapsed_time": "1:33:01", "remaining_time": "0:52:50", "throughput": 2851.37, "total_tokens": 15914784} {"current_steps": 24340, "total_steps": 38160, "loss": 0.0818, "lr": 1.745618737549074e-05, "epoch": 12.756813417190775, "percentage": 63.78, "elapsed_time": "1:33:02", "remaining_time": "0:52:49", "throughput": 2851.52, "total_tokens": 15918944} {"current_steps": 24345, "total_steps": 38160, "loss": 0.0862, "lr": 1.7445286874373974e-05, "epoch": 12.75943396226415, "percentage": 63.8, "elapsed_time": "1:33:03", "remaining_time": "0:52:48", "throughput": 2851.42, "total_tokens": 15921312} {"current_steps": 24350, "total_steps": 38160, "loss": 0.0335, "lr": 1.743438795361701e-05, "epoch": 12.762054507337526, "percentage": 63.81, "elapsed_time": "1:33:04", "remaining_time": "0:52:47", "throughput": 2851.42, "total_tokens": 15924320} {"current_steps": 24355, "total_steps": 38160, "loss": 0.056, "lr": 1.742349061549978e-05, "epoch": 12.764675052410901, "percentage": 63.82, "elapsed_time": "1:33:05", "remaining_time": "0:52:46", "throughput": 2851.5, "total_tokens": 15927936} {"current_steps": 24360, "total_steps": 38160, "loss": 0.0997, "lr": 1.741259486230186e-05, "epoch": 12.767295597484276, "percentage": 63.84, "elapsed_time": "1:33:06", "remaining_time": "0:52:44", "throughput": 2851.51, "total_tokens": 15931104} {"current_steps": 24365, "total_steps": 38160, "loss": 0.0718, "lr": 1.7401700696302546e-05, "epoch": 12.769916142557651, "percentage": 63.85, "elapsed_time": "1:33:08", "remaining_time": "0:52:43", "throughput": 2851.64, "total_tokens": 15935008} {"current_steps": 24370, "total_steps": 38160, "loss": 0.047, "lr": 1.739080811978075e-05, "epoch": 12.772536687631026, "percentage": 63.86, "elapsed_time": "1:33:09", "remaining_time": "0:52:42", "throughput": 2851.57, "total_tokens": 15937824} {"current_steps": 24375, "total_steps": 38160, "loss": 0.0353, "lr": 1.7379917135015093e-05, "epoch": 12.775157232704402, "percentage": 63.88, "elapsed_time": "1:33:10", "remaining_time": "0:52:41", "throughput": 2851.57, "total_tokens": 15941056} {"current_steps": 24380, "total_steps": 38160, "loss": 0.0519, "lr": 1.736902774428384e-05, "epoch": 12.777777777777779, "percentage": 63.89, "elapsed_time": "1:33:11", "remaining_time": "0:52:40", "throughput": 2851.62, "total_tokens": 15944640} {"current_steps": 24385, "total_steps": 38160, "loss": 0.0442, "lr": 1.735813994986491e-05, "epoch": 12.780398322851154, "percentage": 63.9, "elapsed_time": "1:33:12", "remaining_time": "0:52:39", "throughput": 2851.72, "total_tokens": 15948384} {"current_steps": 24390, "total_steps": 38160, "loss": 0.0276, "lr": 1.7347253754035933e-05, "epoch": 12.783018867924529, "percentage": 63.92, "elapsed_time": "1:33:13", "remaining_time": "0:52:38", "throughput": 2851.68, "total_tokens": 15951232} {"current_steps": 24395, "total_steps": 38160, "loss": 0.0643, "lr": 1.7336369159074154e-05, "epoch": 12.785639412997904, "percentage": 63.93, "elapsed_time": "1:33:14", "remaining_time": "0:52:36", "throughput": 2851.75, "total_tokens": 15954816} {"current_steps": 24400, "total_steps": 38160, "loss": 0.2279, "lr": 1.7325486167256522e-05, "epoch": 12.78825995807128, "percentage": 63.94, "elapsed_time": "1:33:15", "remaining_time": "0:52:35", "throughput": 2851.82, "total_tokens": 15958336} {"current_steps": 24405, "total_steps": 38160, "loss": 0.0503, "lr": 1.7314604780859623e-05, "epoch": 12.790880503144654, "percentage": 63.95, "elapsed_time": "1:33:16", "remaining_time": "0:52:34", "throughput": 2851.89, "total_tokens": 15961984} {"current_steps": 24410, "total_steps": 38160, "loss": 0.0378, "lr": 1.730372500215973e-05, "epoch": 12.79350104821803, "percentage": 63.97, "elapsed_time": "1:33:18", "remaining_time": "0:52:33", "throughput": 2851.89, "total_tokens": 15965056} {"current_steps": 24415, "total_steps": 38160, "loss": 0.0507, "lr": 1.7292846833432763e-05, "epoch": 12.796121593291405, "percentage": 63.98, "elapsed_time": "1:33:19", "remaining_time": "0:52:32", "throughput": 2851.83, "total_tokens": 15967904} {"current_steps": 24420, "total_steps": 38160, "loss": 0.0253, "lr": 1.7281970276954305e-05, "epoch": 12.79874213836478, "percentage": 63.99, "elapsed_time": "1:33:20", "remaining_time": "0:52:30", "throughput": 2851.92, "total_tokens": 15971424} {"current_steps": 24425, "total_steps": 38160, "loss": 0.1404, "lr": 1.727109533499961e-05, "epoch": 12.801362683438155, "percentage": 64.01, "elapsed_time": "1:33:21", "remaining_time": "0:52:29", "throughput": 2851.89, "total_tokens": 15974272} {"current_steps": 24430, "total_steps": 38160, "loss": 0.0535, "lr": 1.72602220098436e-05, "epoch": 12.80398322851153, "percentage": 64.02, "elapsed_time": "1:33:22", "remaining_time": "0:52:28", "throughput": 2851.93, "total_tokens": 15977600} {"current_steps": 24435, "total_steps": 38160, "loss": 0.0461, "lr": 1.7249350303760846e-05, "epoch": 12.806603773584905, "percentage": 64.03, "elapsed_time": "1:33:23", "remaining_time": "0:52:27", "throughput": 2851.94, "total_tokens": 15980640} {"current_steps": 24440, "total_steps": 38160, "loss": 0.0583, "lr": 1.7238480219025593e-05, "epoch": 12.80922431865828, "percentage": 64.05, "elapsed_time": "1:33:24", "remaining_time": "0:52:26", "throughput": 2851.93, "total_tokens": 15983520} {"current_steps": 24445, "total_steps": 38160, "loss": 0.0385, "lr": 1.7227611757911723e-05, "epoch": 12.811844863731656, "percentage": 64.06, "elapsed_time": "1:33:25", "remaining_time": "0:52:25", "throughput": 2851.94, "total_tokens": 15986592} {"current_steps": 24450, "total_steps": 38160, "loss": 0.0406, "lr": 1.7216744922692794e-05, "epoch": 12.814465408805031, "percentage": 64.07, "elapsed_time": "1:33:26", "remaining_time": "0:52:23", "throughput": 2851.94, "total_tokens": 15989600} {"current_steps": 24455, "total_steps": 38160, "loss": 0.0434, "lr": 1.7205879715642037e-05, "epoch": 12.817085953878406, "percentage": 64.09, "elapsed_time": "1:33:27", "remaining_time": "0:52:22", "throughput": 2851.92, "total_tokens": 15992416} {"current_steps": 24460, "total_steps": 38160, "loss": 0.0456, "lr": 1.719501613903232e-05, "epoch": 12.819706498951781, "percentage": 64.1, "elapsed_time": "1:33:28", "remaining_time": "0:52:21", "throughput": 2851.79, "total_tokens": 15994816} {"current_steps": 24465, "total_steps": 38160, "loss": 0.0466, "lr": 1.7184154195136192e-05, "epoch": 12.822327044025156, "percentage": 64.11, "elapsed_time": "1:33:29", "remaining_time": "0:52:20", "throughput": 2851.74, "total_tokens": 15997536} {"current_steps": 24470, "total_steps": 38160, "loss": 0.0438, "lr": 1.7173293886225837e-05, "epoch": 12.824947589098532, "percentage": 64.12, "elapsed_time": "1:33:30", "remaining_time": "0:52:19", "throughput": 2851.85, "total_tokens": 16001344} {"current_steps": 24475, "total_steps": 38160, "loss": 0.0342, "lr": 1.71624352145731e-05, "epoch": 12.827568134171909, "percentage": 64.14, "elapsed_time": "1:33:32", "remaining_time": "0:52:17", "throughput": 2852.0, "total_tokens": 16005440} {"current_steps": 24480, "total_steps": 38160, "loss": 0.0451, "lr": 1.7151578182449508e-05, "epoch": 12.830188679245284, "percentage": 64.15, "elapsed_time": "1:33:33", "remaining_time": "0:52:16", "throughput": 2852.06, "total_tokens": 16008992} {"current_steps": 24485, "total_steps": 38160, "loss": 0.0308, "lr": 1.7140722792126212e-05, "epoch": 12.832809224318659, "percentage": 64.16, "elapsed_time": "1:33:34", "remaining_time": "0:52:15", "throughput": 2852.0, "total_tokens": 16011712} {"current_steps": 24490, "total_steps": 38160, "loss": 0.0379, "lr": 1.7129869045874053e-05, "epoch": 12.835429769392034, "percentage": 64.18, "elapsed_time": "1:33:35", "remaining_time": "0:52:14", "throughput": 2851.97, "total_tokens": 16014528} {"current_steps": 24495, "total_steps": 38160, "loss": 0.029, "lr": 1.7119016945963506e-05, "epoch": 12.83805031446541, "percentage": 64.19, "elapsed_time": "1:33:36", "remaining_time": "0:52:13", "throughput": 2851.82, "total_tokens": 16016736} {"current_steps": 24500, "total_steps": 38160, "loss": 0.0434, "lr": 1.7108166494664694e-05, "epoch": 12.840670859538784, "percentage": 64.2, "elapsed_time": "1:33:37", "remaining_time": "0:52:12", "throughput": 2851.86, "total_tokens": 16020128} {"current_steps": 24505, "total_steps": 38160, "loss": 0.038, "lr": 1.7097317694247417e-05, "epoch": 12.84329140461216, "percentage": 64.22, "elapsed_time": "1:33:38", "remaining_time": "0:52:10", "throughput": 2851.85, "total_tokens": 16023008} {"current_steps": 24510, "total_steps": 38160, "loss": 0.0508, "lr": 1.7086470546981122e-05, "epoch": 12.845911949685535, "percentage": 64.23, "elapsed_time": "1:33:39", "remaining_time": "0:52:09", "throughput": 2851.97, "total_tokens": 16026656} {"current_steps": 24515, "total_steps": 38160, "loss": 0.0478, "lr": 1.7075625055134904e-05, "epoch": 12.84853249475891, "percentage": 64.24, "elapsed_time": "1:33:40", "remaining_time": "0:52:08", "throughput": 2851.92, "total_tokens": 16029472} {"current_steps": 24520, "total_steps": 38160, "loss": 0.0607, "lr": 1.706478122097752e-05, "epoch": 12.851153039832285, "percentage": 64.26, "elapsed_time": "1:33:41", "remaining_time": "0:52:07", "throughput": 2852.06, "total_tokens": 16033504} {"current_steps": 24525, "total_steps": 38160, "loss": 0.0409, "lr": 1.7053939046777384e-05, "epoch": 12.85377358490566, "percentage": 64.27, "elapsed_time": "1:33:42", "remaining_time": "0:52:06", "throughput": 2852.02, "total_tokens": 16036480} {"current_steps": 24530, "total_steps": 38160, "loss": 0.0661, "lr": 1.7043098534802533e-05, "epoch": 12.856394129979035, "percentage": 64.28, "elapsed_time": "1:33:43", "remaining_time": "0:52:04", "throughput": 2851.94, "total_tokens": 16039072} {"current_steps": 24535, "total_steps": 38160, "loss": 0.0267, "lr": 1.7032259687320695e-05, "epoch": 12.85901467505241, "percentage": 64.3, "elapsed_time": "1:33:45", "remaining_time": "0:52:03", "throughput": 2851.91, "total_tokens": 16042144} {"current_steps": 24540, "total_steps": 38160, "loss": 0.0513, "lr": 1.7021422506599228e-05, "epoch": 12.861635220125786, "percentage": 64.31, "elapsed_time": "1:33:46", "remaining_time": "0:52:02", "throughput": 2851.83, "total_tokens": 16044672} {"current_steps": 24545, "total_steps": 38160, "loss": 0.0343, "lr": 1.7010586994905155e-05, "epoch": 12.864255765199161, "percentage": 64.32, "elapsed_time": "1:33:47", "remaining_time": "0:52:01", "throughput": 2851.7, "total_tokens": 16046912} {"current_steps": 24550, "total_steps": 38160, "loss": 0.0427, "lr": 1.6999753154505123e-05, "epoch": 12.866876310272536, "percentage": 64.33, "elapsed_time": "1:33:48", "remaining_time": "0:52:00", "throughput": 2851.67, "total_tokens": 16049920} {"current_steps": 24555, "total_steps": 38160, "loss": 0.0564, "lr": 1.6988920987665476e-05, "epoch": 12.869496855345911, "percentage": 64.35, "elapsed_time": "1:33:49", "remaining_time": "0:51:59", "throughput": 2851.8, "total_tokens": 16053952} {"current_steps": 24560, "total_steps": 38160, "loss": 0.0447, "lr": 1.6978090496652156e-05, "epoch": 12.872117400419286, "percentage": 64.36, "elapsed_time": "1:33:50", "remaining_time": "0:51:57", "throughput": 2851.68, "total_tokens": 16056352} {"current_steps": 24565, "total_steps": 38160, "loss": 0.0567, "lr": 1.6967261683730778e-05, "epoch": 12.874737945492662, "percentage": 64.37, "elapsed_time": "1:33:51", "remaining_time": "0:51:56", "throughput": 2851.81, "total_tokens": 16060608} {"current_steps": 24570, "total_steps": 38160, "loss": 0.076, "lr": 1.695643455116662e-05, "epoch": 12.877358490566039, "percentage": 64.39, "elapsed_time": "1:33:52", "remaining_time": "0:51:55", "throughput": 2851.85, "total_tokens": 16063904} {"current_steps": 24575, "total_steps": 38160, "loss": 0.0384, "lr": 1.694560910122458e-05, "epoch": 12.879979035639414, "percentage": 64.4, "elapsed_time": "1:33:53", "remaining_time": "0:51:54", "throughput": 2851.83, "total_tokens": 16067136} {"current_steps": 24580, "total_steps": 38160, "loss": 0.0251, "lr": 1.693478533616924e-05, "epoch": 12.882599580712789, "percentage": 64.41, "elapsed_time": "1:33:55", "remaining_time": "0:51:53", "throughput": 2851.7, "total_tokens": 16069696} {"current_steps": 24585, "total_steps": 38160, "loss": 0.0386, "lr": 1.692396325826479e-05, "epoch": 12.885220125786164, "percentage": 64.43, "elapsed_time": "1:33:56", "remaining_time": "0:51:52", "throughput": 2851.73, "total_tokens": 16072800} {"current_steps": 24590, "total_steps": 38160, "loss": 0.0523, "lr": 1.6913142869775088e-05, "epoch": 12.88784067085954, "percentage": 64.44, "elapsed_time": "1:33:57", "remaining_time": "0:51:50", "throughput": 2851.65, "total_tokens": 16075424} {"current_steps": 24595, "total_steps": 38160, "loss": 0.0838, "lr": 1.6902324172963635e-05, "epoch": 12.890461215932914, "percentage": 64.45, "elapsed_time": "1:33:58", "remaining_time": "0:51:49", "throughput": 2851.63, "total_tokens": 16078400} {"current_steps": 24600, "total_steps": 38160, "loss": 0.0797, "lr": 1.6891507170093586e-05, "epoch": 12.89308176100629, "percentage": 64.47, "elapsed_time": "1:34:00", "remaining_time": "0:51:49", "throughput": 2852.01, "total_tokens": 16086432} {"current_steps": 24605, "total_steps": 38160, "loss": 0.0712, "lr": 1.6880691863427725e-05, "epoch": 12.895702306079665, "percentage": 64.48, "elapsed_time": "1:34:01", "remaining_time": "0:51:47", "throughput": 2851.98, "total_tokens": 16089472} {"current_steps": 24610, "total_steps": 38160, "loss": 0.0299, "lr": 1.686987825522851e-05, "epoch": 12.89832285115304, "percentage": 64.49, "elapsed_time": "1:34:02", "remaining_time": "0:51:46", "throughput": 2852.03, "total_tokens": 16092800} {"current_steps": 24615, "total_steps": 38160, "loss": 0.0561, "lr": 1.6859066347758002e-05, "epoch": 12.900943396226415, "percentage": 64.5, "elapsed_time": "1:34:04", "remaining_time": "0:51:46", "throughput": 2852.49, "total_tokens": 16100992} {"current_steps": 24620, "total_steps": 38160, "loss": 0.0568, "lr": 1.6848256143277933e-05, "epoch": 12.90356394129979, "percentage": 64.52, "elapsed_time": "1:34:05", "remaining_time": "0:51:44", "throughput": 2852.56, "total_tokens": 16104320} {"current_steps": 24625, "total_steps": 38160, "loss": 0.0784, "lr": 1.683744764404968e-05, "epoch": 12.906184486373165, "percentage": 64.53, "elapsed_time": "1:34:06", "remaining_time": "0:51:43", "throughput": 2852.67, "total_tokens": 16108064} {"current_steps": 24630, "total_steps": 38160, "loss": 0.0713, "lr": 1.6826640852334257e-05, "epoch": 12.90880503144654, "percentage": 64.54, "elapsed_time": "1:34:07", "remaining_time": "0:51:42", "throughput": 2852.65, "total_tokens": 16111008} {"current_steps": 24635, "total_steps": 38160, "loss": 0.0368, "lr": 1.6815835770392324e-05, "epoch": 12.911425576519916, "percentage": 64.56, "elapsed_time": "1:34:08", "remaining_time": "0:51:41", "throughput": 2852.62, "total_tokens": 16114080} {"current_steps": 24640, "total_steps": 38160, "loss": 0.0453, "lr": 1.6805032400484184e-05, "epoch": 12.914046121593291, "percentage": 64.57, "elapsed_time": "1:34:09", "remaining_time": "0:51:40", "throughput": 2852.55, "total_tokens": 16116832} {"current_steps": 24645, "total_steps": 38160, "loss": 0.0282, "lr": 1.6794230744869767e-05, "epoch": 12.916666666666666, "percentage": 64.58, "elapsed_time": "1:34:11", "remaining_time": "0:51:38", "throughput": 2852.54, "total_tokens": 16119872} {"current_steps": 24650, "total_steps": 38160, "loss": 0.0845, "lr": 1.6783430805808658e-05, "epoch": 12.919287211740041, "percentage": 64.6, "elapsed_time": "1:34:12", "remaining_time": "0:51:37", "throughput": 2852.58, "total_tokens": 16123200} {"current_steps": 24655, "total_steps": 38160, "loss": 0.0358, "lr": 1.6772632585560084e-05, "epoch": 12.921907756813416, "percentage": 64.61, "elapsed_time": "1:34:13", "remaining_time": "0:51:36", "throughput": 2852.55, "total_tokens": 16126048} {"current_steps": 24660, "total_steps": 38160, "loss": 0.0498, "lr": 1.6761836086382908e-05, "epoch": 12.924528301886792, "percentage": 64.62, "elapsed_time": "1:34:14", "remaining_time": "0:51:35", "throughput": 2852.56, "total_tokens": 16129088} {"current_steps": 24665, "total_steps": 38160, "loss": 0.0797, "lr": 1.6751041310535653e-05, "epoch": 12.927148846960169, "percentage": 64.64, "elapsed_time": "1:34:15", "remaining_time": "0:51:34", "throughput": 2852.46, "total_tokens": 16131584} {"current_steps": 24670, "total_steps": 38160, "loss": 0.0742, "lr": 1.6740248260276437e-05, "epoch": 12.929769392033544, "percentage": 64.65, "elapsed_time": "1:34:16", "remaining_time": "0:51:33", "throughput": 2852.31, "total_tokens": 16133984} {"current_steps": 24675, "total_steps": 38160, "loss": 0.0319, "lr": 1.6729456937863047e-05, "epoch": 12.932389937106919, "percentage": 64.66, "elapsed_time": "1:34:17", "remaining_time": "0:51:31", "throughput": 2852.22, "total_tokens": 16136480} {"current_steps": 24680, "total_steps": 38160, "loss": 0.0186, "lr": 1.6718667345552918e-05, "epoch": 12.935010482180294, "percentage": 64.68, "elapsed_time": "1:34:18", "remaining_time": "0:51:30", "throughput": 2852.23, "total_tokens": 16139616} {"current_steps": 24685, "total_steps": 38160, "loss": 0.0283, "lr": 1.6707879485603097e-05, "epoch": 12.93763102725367, "percentage": 64.69, "elapsed_time": "1:34:19", "remaining_time": "0:51:29", "throughput": 2852.27, "total_tokens": 16143008} {"current_steps": 24690, "total_steps": 38160, "loss": 0.0574, "lr": 1.669709336027029e-05, "epoch": 12.940251572327044, "percentage": 64.7, "elapsed_time": "1:34:20", "remaining_time": "0:51:28", "throughput": 2852.32, "total_tokens": 16146304} {"current_steps": 24695, "total_steps": 38160, "loss": 0.0225, "lr": 1.6686308971810833e-05, "epoch": 12.94287211740042, "percentage": 64.71, "elapsed_time": "1:34:21", "remaining_time": "0:51:27", "throughput": 2852.31, "total_tokens": 16149184} {"current_steps": 24700, "total_steps": 38160, "loss": 0.0432, "lr": 1.6675526322480677e-05, "epoch": 12.945492662473795, "percentage": 64.73, "elapsed_time": "1:34:22", "remaining_time": "0:51:25", "throughput": 2852.26, "total_tokens": 16151968} {"current_steps": 24705, "total_steps": 38160, "loss": 0.0682, "lr": 1.6664745414535454e-05, "epoch": 12.94811320754717, "percentage": 64.74, "elapsed_time": "1:34:23", "remaining_time": "0:51:24", "throughput": 2852.24, "total_tokens": 16154848} {"current_steps": 24710, "total_steps": 38160, "loss": 0.0491, "lr": 1.665396625023039e-05, "epoch": 12.950733752620545, "percentage": 64.75, "elapsed_time": "1:34:24", "remaining_time": "0:51:23", "throughput": 2852.32, "total_tokens": 16158336} {"current_steps": 24715, "total_steps": 38160, "loss": 0.0564, "lr": 1.6643188831820375e-05, "epoch": 12.95335429769392, "percentage": 64.77, "elapsed_time": "1:34:26", "remaining_time": "0:51:22", "throughput": 2852.39, "total_tokens": 16161856} {"current_steps": 24720, "total_steps": 38160, "loss": 0.0361, "lr": 1.6632413161559912e-05, "epoch": 12.955974842767295, "percentage": 64.78, "elapsed_time": "1:34:27", "remaining_time": "0:51:21", "throughput": 2852.5, "total_tokens": 16165696} {"current_steps": 24725, "total_steps": 38160, "loss": 0.0625, "lr": 1.6621639241703162e-05, "epoch": 12.95859538784067, "percentage": 64.79, "elapsed_time": "1:34:28", "remaining_time": "0:51:20", "throughput": 2852.61, "total_tokens": 16169440} {"current_steps": 24730, "total_steps": 38160, "loss": 0.0249, "lr": 1.6610867074503893e-05, "epoch": 12.961215932914046, "percentage": 64.81, "elapsed_time": "1:34:29", "remaining_time": "0:51:18", "throughput": 2852.71, "total_tokens": 16173088} {"current_steps": 24735, "total_steps": 38160, "loss": 0.055, "lr": 1.660009666221552e-05, "epoch": 12.963836477987421, "percentage": 64.82, "elapsed_time": "1:34:30", "remaining_time": "0:51:17", "throughput": 2852.75, "total_tokens": 16176352} {"current_steps": 24740, "total_steps": 38160, "loss": 0.0296, "lr": 1.6589328007091093e-05, "epoch": 12.966457023060796, "percentage": 64.83, "elapsed_time": "1:34:31", "remaining_time": "0:51:16", "throughput": 2852.83, "total_tokens": 16180128} {"current_steps": 24745, "total_steps": 38160, "loss": 0.0838, "lr": 1.65785611113833e-05, "epoch": 12.969077568134171, "percentage": 64.85, "elapsed_time": "1:34:32", "remaining_time": "0:51:15", "throughput": 2852.78, "total_tokens": 16182880} {"current_steps": 24750, "total_steps": 38160, "loss": 0.0479, "lr": 1.6567795977344447e-05, "epoch": 12.971698113207546, "percentage": 64.86, "elapsed_time": "1:34:33", "remaining_time": "0:51:14", "throughput": 2852.91, "total_tokens": 16186880} {"current_steps": 24755, "total_steps": 38160, "loss": 0.0887, "lr": 1.6557032607226466e-05, "epoch": 12.974318658280922, "percentage": 64.87, "elapsed_time": "1:34:34", "remaining_time": "0:51:12", "throughput": 2852.84, "total_tokens": 16189600} {"current_steps": 24760, "total_steps": 38160, "loss": 0.1328, "lr": 1.654627100328095e-05, "epoch": 12.976939203354299, "percentage": 64.88, "elapsed_time": "1:34:36", "remaining_time": "0:51:12", "throughput": 2852.97, "total_tokens": 16194976} {"current_steps": 24765, "total_steps": 38160, "loss": 0.0354, "lr": 1.6535511167759085e-05, "epoch": 12.979559748427674, "percentage": 64.9, "elapsed_time": "1:34:37", "remaining_time": "0:51:10", "throughput": 2852.89, "total_tokens": 16197536} {"current_steps": 24770, "total_steps": 38160, "loss": 0.062, "lr": 1.652475310291172e-05, "epoch": 12.982180293501049, "percentage": 64.91, "elapsed_time": "1:34:38", "remaining_time": "0:51:09", "throughput": 2853.01, "total_tokens": 16201440} {"current_steps": 24775, "total_steps": 38160, "loss": 0.055, "lr": 1.6513996810989317e-05, "epoch": 12.984800838574424, "percentage": 64.92, "elapsed_time": "1:34:39", "remaining_time": "0:51:08", "throughput": 2853.0, "total_tokens": 16204448} {"current_steps": 24780, "total_steps": 38160, "loss": 0.0373, "lr": 1.6503242294241973e-05, "epoch": 12.9874213836478, "percentage": 64.94, "elapsed_time": "1:34:40", "remaining_time": "0:51:07", "throughput": 2853.03, "total_tokens": 16207584} {"current_steps": 24785, "total_steps": 38160, "loss": 0.0321, "lr": 1.6492489554919404e-05, "epoch": 12.990041928721174, "percentage": 64.95, "elapsed_time": "1:34:41", "remaining_time": "0:51:06", "throughput": 2852.9, "total_tokens": 16209920} {"current_steps": 24790, "total_steps": 38160, "loss": 0.0279, "lr": 1.6481738595270953e-05, "epoch": 12.99266247379455, "percentage": 64.96, "elapsed_time": "1:34:42", "remaining_time": "0:51:04", "throughput": 2852.86, "total_tokens": 16212736} {"current_steps": 24795, "total_steps": 38160, "loss": 0.0504, "lr": 1.6470989417545608e-05, "epoch": 12.995283018867925, "percentage": 64.98, "elapsed_time": "1:34:44", "remaining_time": "0:51:03", "throughput": 2852.93, "total_tokens": 16216480} {"current_steps": 24800, "total_steps": 38160, "loss": 0.0673, "lr": 1.646024202399197e-05, "epoch": 12.9979035639413, "percentage": 64.99, "elapsed_time": "1:34:45", "remaining_time": "0:51:02", "throughput": 2852.82, "total_tokens": 16218976} {"current_steps": 24804, "total_steps": 38160, "eval_loss": 1.1541403532028198, "epoch": 13.0, "percentage": 65.0, "elapsed_time": "1:34:57", "remaining_time": "0:51:08", "throughput": 2846.78, "total_tokens": 16220808} {"current_steps": 24805, "total_steps": 38160, "loss": 0.0367, "lr": 1.6449496416858284e-05, "epoch": 13.000524109014675, "percentage": 65.0, "elapsed_time": "1:35:01", "remaining_time": "0:51:09", "throughput": 2845.07, "total_tokens": 16221160} {"current_steps": 24810, "total_steps": 38160, "loss": 0.0437, "lr": 1.64387525983924e-05, "epoch": 13.00314465408805, "percentage": 65.02, "elapsed_time": "1:35:02", "remaining_time": "0:51:08", "throughput": 2844.99, "total_tokens": 16223848} {"current_steps": 24815, "total_steps": 38160, "loss": 0.0256, "lr": 1.6428010570841788e-05, "epoch": 13.005765199161425, "percentage": 65.03, "elapsed_time": "1:35:03", "remaining_time": "0:51:07", "throughput": 2844.92, "total_tokens": 16226856} {"current_steps": 24820, "total_steps": 38160, "loss": 0.0204, "lr": 1.6417270336453573e-05, "epoch": 13.0083857442348, "percentage": 65.04, "elapsed_time": "1:35:04", "remaining_time": "0:51:06", "throughput": 2844.86, "total_tokens": 16229736} {"current_steps": 24825, "total_steps": 38160, "loss": 0.0391, "lr": 1.6406531897474492e-05, "epoch": 13.011006289308176, "percentage": 65.06, "elapsed_time": "1:35:05", "remaining_time": "0:51:05", "throughput": 2844.93, "total_tokens": 16233064} {"current_steps": 24830, "total_steps": 38160, "loss": 0.0232, "lr": 1.639579525615089e-05, "epoch": 13.01362683438155, "percentage": 65.07, "elapsed_time": "1:35:07", "remaining_time": "0:51:03", "throughput": 2844.99, "total_tokens": 16236456} {"current_steps": 24835, "total_steps": 38160, "loss": 0.057, "lr": 1.638506041472877e-05, "epoch": 13.016247379454926, "percentage": 65.08, "elapsed_time": "1:35:08", "remaining_time": "0:51:02", "throughput": 2844.92, "total_tokens": 16239272} {"current_steps": 24840, "total_steps": 38160, "loss": 0.0115, "lr": 1.6374327375453724e-05, "epoch": 13.018867924528301, "percentage": 65.09, "elapsed_time": "1:35:09", "remaining_time": "0:51:01", "throughput": 2844.89, "total_tokens": 16242152} {"current_steps": 24845, "total_steps": 38160, "loss": 0.037, "lr": 1.6363596140570982e-05, "epoch": 13.021488469601676, "percentage": 65.11, "elapsed_time": "1:35:10", "remaining_time": "0:51:00", "throughput": 2844.96, "total_tokens": 16245832} {"current_steps": 24850, "total_steps": 38160, "loss": 0.0193, "lr": 1.6352866712325395e-05, "epoch": 13.024109014675052, "percentage": 65.12, "elapsed_time": "1:35:11", "remaining_time": "0:50:59", "throughput": 2844.98, "total_tokens": 16249064} {"current_steps": 24855, "total_steps": 38160, "loss": 0.037, "lr": 1.634213909296144e-05, "epoch": 13.026729559748428, "percentage": 65.13, "elapsed_time": "1:35:12", "remaining_time": "0:50:57", "throughput": 2844.95, "total_tokens": 16251944} {"current_steps": 24860, "total_steps": 38160, "loss": 0.0851, "lr": 1.6331413284723217e-05, "epoch": 13.029350104821804, "percentage": 65.15, "elapsed_time": "1:35:13", "remaining_time": "0:50:56", "throughput": 2844.99, "total_tokens": 16255368} {"current_steps": 24865, "total_steps": 38160, "loss": 0.0529, "lr": 1.6320689289854442e-05, "epoch": 13.031970649895179, "percentage": 65.16, "elapsed_time": "1:35:14", "remaining_time": "0:50:55", "throughput": 2844.92, "total_tokens": 16258152} {"current_steps": 24870, "total_steps": 38160, "loss": 0.0385, "lr": 1.6309967110598438e-05, "epoch": 13.034591194968554, "percentage": 65.17, "elapsed_time": "1:35:15", "remaining_time": "0:50:54", "throughput": 2845.02, "total_tokens": 16261672} {"current_steps": 24875, "total_steps": 38160, "loss": 0.0224, "lr": 1.6299246749198183e-05, "epoch": 13.03721174004193, "percentage": 65.19, "elapsed_time": "1:35:17", "remaining_time": "0:50:53", "throughput": 2845.08, "total_tokens": 16265416} {"current_steps": 24880, "total_steps": 38160, "loss": 0.0306, "lr": 1.6288528207896236e-05, "epoch": 13.039832285115304, "percentage": 65.2, "elapsed_time": "1:35:18", "remaining_time": "0:50:52", "throughput": 2845.0, "total_tokens": 16268008} {"current_steps": 24885, "total_steps": 38160, "loss": 0.0225, "lr": 1.627781148893481e-05, "epoch": 13.04245283018868, "percentage": 65.21, "elapsed_time": "1:35:19", "remaining_time": "0:50:50", "throughput": 2845.11, "total_tokens": 16271912} {"current_steps": 24890, "total_steps": 38160, "loss": 0.0222, "lr": 1.6267096594555703e-05, "epoch": 13.045073375262055, "percentage": 65.23, "elapsed_time": "1:35:20", "remaining_time": "0:50:49", "throughput": 2845.12, "total_tokens": 16275304} {"current_steps": 24895, "total_steps": 38160, "loss": 0.0295, "lr": 1.6256383527000372e-05, "epoch": 13.04769392033543, "percentage": 65.24, "elapsed_time": "1:35:21", "remaining_time": "0:50:48", "throughput": 2845.17, "total_tokens": 16279240} {"current_steps": 24900, "total_steps": 38160, "loss": 0.1096, "lr": 1.6245672288509843e-05, "epoch": 13.050314465408805, "percentage": 65.25, "elapsed_time": "1:35:22", "remaining_time": "0:50:47", "throughput": 2845.19, "total_tokens": 16282376} {"current_steps": 24905, "total_steps": 38160, "loss": 0.0214, "lr": 1.62349628813248e-05, "epoch": 13.05293501048218, "percentage": 65.26, "elapsed_time": "1:35:23", "remaining_time": "0:50:46", "throughput": 2845.13, "total_tokens": 16285000} {"current_steps": 24910, "total_steps": 38160, "loss": 0.0226, "lr": 1.6224255307685525e-05, "epoch": 13.055555555555555, "percentage": 65.28, "elapsed_time": "1:35:24", "remaining_time": "0:50:45", "throughput": 2845.13, "total_tokens": 16287976} {"current_steps": 24915, "total_steps": 38160, "loss": 0.0425, "lr": 1.6213549569831922e-05, "epoch": 13.05817610062893, "percentage": 65.29, "elapsed_time": "1:35:26", "remaining_time": "0:50:43", "throughput": 2845.1, "total_tokens": 16291080} {"current_steps": 24920, "total_steps": 38160, "loss": 0.0299, "lr": 1.62028456700035e-05, "epoch": 13.060796645702306, "percentage": 65.3, "elapsed_time": "1:35:27", "remaining_time": "0:50:42", "throughput": 2845.15, "total_tokens": 16294504} {"current_steps": 24925, "total_steps": 38160, "loss": 0.0411, "lr": 1.619214361043942e-05, "epoch": 13.06341719077568, "percentage": 65.32, "elapsed_time": "1:35:28", "remaining_time": "0:50:41", "throughput": 2845.31, "total_tokens": 16298696} {"current_steps": 24930, "total_steps": 38160, "loss": 0.0194, "lr": 1.61814433933784e-05, "epoch": 13.066037735849056, "percentage": 65.33, "elapsed_time": "1:35:29", "remaining_time": "0:50:40", "throughput": 2845.4, "total_tokens": 16302536} {"current_steps": 24935, "total_steps": 38160, "loss": 0.0249, "lr": 1.617074502105881e-05, "epoch": 13.068658280922431, "percentage": 65.34, "elapsed_time": "1:35:30", "remaining_time": "0:50:39", "throughput": 2845.4, "total_tokens": 16305992} {"current_steps": 24940, "total_steps": 38160, "loss": 0.0609, "lr": 1.616004849571864e-05, "epoch": 13.071278825995806, "percentage": 65.36, "elapsed_time": "1:35:31", "remaining_time": "0:50:38", "throughput": 2845.47, "total_tokens": 16309768} {"current_steps": 24945, "total_steps": 38160, "loss": 0.0459, "lr": 1.6149353819595463e-05, "epoch": 13.073899371069182, "percentage": 65.37, "elapsed_time": "1:35:32", "remaining_time": "0:50:37", "throughput": 2845.5, "total_tokens": 16313160} {"current_steps": 24950, "total_steps": 38160, "loss": 0.0309, "lr": 1.6138660994926508e-05, "epoch": 13.076519916142558, "percentage": 65.38, "elapsed_time": "1:35:34", "remaining_time": "0:50:35", "throughput": 2845.4, "total_tokens": 16315688} {"current_steps": 24955, "total_steps": 38160, "loss": 0.035, "lr": 1.612797002394857e-05, "epoch": 13.079140461215934, "percentage": 65.4, "elapsed_time": "1:35:35", "remaining_time": "0:50:34", "throughput": 2845.49, "total_tokens": 16319208} {"current_steps": 24960, "total_steps": 38160, "loss": 0.0397, "lr": 1.611728090889808e-05, "epoch": 13.081761006289309, "percentage": 65.41, "elapsed_time": "1:35:36", "remaining_time": "0:50:33", "throughput": 2845.55, "total_tokens": 16322600} {"current_steps": 24965, "total_steps": 38160, "loss": 0.0454, "lr": 1.610659365201109e-05, "epoch": 13.084381551362684, "percentage": 65.42, "elapsed_time": "1:35:37", "remaining_time": "0:50:32", "throughput": 2845.63, "total_tokens": 16326568} {"current_steps": 24970, "total_steps": 38160, "loss": 0.058, "lr": 1.609590825552324e-05, "epoch": 13.08700209643606, "percentage": 65.44, "elapsed_time": "1:35:38", "remaining_time": "0:50:31", "throughput": 2845.83, "total_tokens": 16331336} {"current_steps": 24975, "total_steps": 38160, "loss": 0.057, "lr": 1.6085224721669807e-05, "epoch": 13.089622641509434, "percentage": 65.45, "elapsed_time": "1:35:39", "remaining_time": "0:50:30", "throughput": 2845.88, "total_tokens": 16334824} {"current_steps": 24980, "total_steps": 38160, "loss": 0.0183, "lr": 1.607454305268566e-05, "epoch": 13.09224318658281, "percentage": 65.46, "elapsed_time": "1:35:40", "remaining_time": "0:50:29", "throughput": 2845.9, "total_tokens": 16337992} {"current_steps": 24985, "total_steps": 38160, "loss": 0.049, "lr": 1.606386325080528e-05, "epoch": 13.094863731656185, "percentage": 65.47, "elapsed_time": "1:35:41", "remaining_time": "0:50:27", "throughput": 2845.85, "total_tokens": 16340680} {"current_steps": 24990, "total_steps": 38160, "loss": 0.0176, "lr": 1.6053185318262746e-05, "epoch": 13.09748427672956, "percentage": 65.49, "elapsed_time": "1:35:42", "remaining_time": "0:50:26", "throughput": 2845.82, "total_tokens": 16343464} {"current_steps": 24995, "total_steps": 38160, "loss": 0.0511, "lr": 1.6042509257291783e-05, "epoch": 13.100104821802935, "percentage": 65.5, "elapsed_time": "1:35:44", "remaining_time": "0:50:25", "throughput": 2845.8, "total_tokens": 16346376} {"current_steps": 25000, "total_steps": 38160, "loss": 0.0221, "lr": 1.6031835070125685e-05, "epoch": 13.10272536687631, "percentage": 65.51, "elapsed_time": "1:35:45", "remaining_time": "0:50:24", "throughput": 2845.74, "total_tokens": 16349032} {"current_steps": 25005, "total_steps": 38160, "loss": 0.0415, "lr": 1.6021162758997382e-05, "epoch": 13.105345911949685, "percentage": 65.53, "elapsed_time": "1:35:46", "remaining_time": "0:50:23", "throughput": 2845.76, "total_tokens": 16352104} {"current_steps": 25010, "total_steps": 38160, "loss": 0.0608, "lr": 1.6010492326139398e-05, "epoch": 13.10796645702306, "percentage": 65.54, "elapsed_time": "1:35:47", "remaining_time": "0:50:21", "throughput": 2845.83, "total_tokens": 16355496} {"current_steps": 25015, "total_steps": 38160, "loss": 0.0318, "lr": 1.599982377378385e-05, "epoch": 13.110587002096436, "percentage": 65.55, "elapsed_time": "1:35:48", "remaining_time": "0:50:20", "throughput": 2845.86, "total_tokens": 16359080} {"current_steps": 25020, "total_steps": 38160, "loss": 0.0431, "lr": 1.5989157104162496e-05, "epoch": 13.11320754716981, "percentage": 65.57, "elapsed_time": "1:35:49", "remaining_time": "0:50:19", "throughput": 2845.87, "total_tokens": 16362408} {"current_steps": 25025, "total_steps": 38160, "loss": 0.0267, "lr": 1.5978492319506673e-05, "epoch": 13.115828092243186, "percentage": 65.58, "elapsed_time": "1:35:50", "remaining_time": "0:50:18", "throughput": 2845.82, "total_tokens": 16365384} {"current_steps": 25030, "total_steps": 38160, "loss": 0.0254, "lr": 1.596782942204733e-05, "epoch": 13.118448637316561, "percentage": 65.59, "elapsed_time": "1:35:51", "remaining_time": "0:50:17", "throughput": 2845.84, "total_tokens": 16368840} {"current_steps": 25035, "total_steps": 38160, "loss": 0.0209, "lr": 1.595716841401504e-05, "epoch": 13.121069182389936, "percentage": 65.61, "elapsed_time": "1:35:52", "remaining_time": "0:50:16", "throughput": 2845.88, "total_tokens": 16372296} {"current_steps": 25040, "total_steps": 38160, "loss": 0.013, "lr": 1.594650929763994e-05, "epoch": 13.123689727463312, "percentage": 65.62, "elapsed_time": "1:35:54", "remaining_time": "0:50:14", "throughput": 2845.86, "total_tokens": 16375400} {"current_steps": 25045, "total_steps": 38160, "loss": 0.0616, "lr": 1.5935852075151812e-05, "epoch": 13.126310272536688, "percentage": 65.63, "elapsed_time": "1:35:55", "remaining_time": "0:50:13", "throughput": 2845.89, "total_tokens": 16378728} {"current_steps": 25050, "total_steps": 38160, "loss": 0.0253, "lr": 1.5925196748780016e-05, "epoch": 13.128930817610064, "percentage": 65.64, "elapsed_time": "1:35:56", "remaining_time": "0:50:12", "throughput": 2845.84, "total_tokens": 16381672} {"current_steps": 25055, "total_steps": 38160, "loss": 0.0855, "lr": 1.5914543320753528e-05, "epoch": 13.131551362683439, "percentage": 65.66, "elapsed_time": "1:35:57", "remaining_time": "0:50:11", "throughput": 2845.84, "total_tokens": 16384744} {"current_steps": 25060, "total_steps": 38160, "loss": 0.1223, "lr": 1.5903891793300932e-05, "epoch": 13.134171907756814, "percentage": 65.67, "elapsed_time": "1:35:58", "remaining_time": "0:50:10", "throughput": 2845.83, "total_tokens": 16387816} {"current_steps": 25065, "total_steps": 38160, "loss": 0.0216, "lr": 1.5893242168650403e-05, "epoch": 13.13679245283019, "percentage": 65.68, "elapsed_time": "1:35:59", "remaining_time": "0:50:09", "throughput": 2845.77, "total_tokens": 16390600} {"current_steps": 25070, "total_steps": 38160, "loss": 0.0439, "lr": 1.5882594449029705e-05, "epoch": 13.139412997903564, "percentage": 65.7, "elapsed_time": "1:36:00", "remaining_time": "0:50:07", "throughput": 2845.8, "total_tokens": 16394280} {"current_steps": 25075, "total_steps": 38160, "loss": 0.0207, "lr": 1.587194863666624e-05, "epoch": 13.14203354297694, "percentage": 65.71, "elapsed_time": "1:36:01", "remaining_time": "0:50:06", "throughput": 2845.7, "total_tokens": 16396904} {"current_steps": 25080, "total_steps": 38160, "loss": 0.0998, "lr": 1.5861304733786974e-05, "epoch": 13.144654088050315, "percentage": 65.72, "elapsed_time": "1:36:03", "remaining_time": "0:50:05", "throughput": 2845.7, "total_tokens": 16400136} {"current_steps": 25085, "total_steps": 38160, "loss": 0.0086, "lr": 1.5850662742618505e-05, "epoch": 13.14727463312369, "percentage": 65.74, "elapsed_time": "1:36:04", "remaining_time": "0:50:04", "throughput": 2845.56, "total_tokens": 16402568} {"current_steps": 25090, "total_steps": 38160, "loss": 0.0338, "lr": 1.5840022665387004e-05, "epoch": 13.149895178197065, "percentage": 65.75, "elapsed_time": "1:36:05", "remaining_time": "0:50:03", "throughput": 2845.58, "total_tokens": 16405832} {"current_steps": 25095, "total_steps": 38160, "loss": 0.0602, "lr": 1.5829384504318268e-05, "epoch": 13.15251572327044, "percentage": 65.76, "elapsed_time": "1:36:06", "remaining_time": "0:50:02", "throughput": 2845.59, "total_tokens": 16409288} {"current_steps": 25100, "total_steps": 38160, "loss": 0.018, "lr": 1.5818748261637662e-05, "epoch": 13.155136268343815, "percentage": 65.78, "elapsed_time": "1:36:07", "remaining_time": "0:50:01", "throughput": 2845.61, "total_tokens": 16412584} {"current_steps": 25105, "total_steps": 38160, "loss": 0.0236, "lr": 1.5808113939570173e-05, "epoch": 13.15775681341719, "percentage": 65.79, "elapsed_time": "1:36:08", "remaining_time": "0:49:59", "throughput": 2845.53, "total_tokens": 16415080} {"current_steps": 25110, "total_steps": 38160, "loss": 0.0175, "lr": 1.5797481540340386e-05, "epoch": 13.160377358490566, "percentage": 65.8, "elapsed_time": "1:36:09", "remaining_time": "0:49:58", "throughput": 2845.55, "total_tokens": 16418184} {"current_steps": 25115, "total_steps": 38160, "loss": 0.0866, "lr": 1.5786851066172466e-05, "epoch": 13.16299790356394, "percentage": 65.81, "elapsed_time": "1:36:10", "remaining_time": "0:49:57", "throughput": 2845.61, "total_tokens": 16421672} {"current_steps": 25120, "total_steps": 38160, "loss": 0.021, "lr": 1.5776222519290208e-05, "epoch": 13.165618448637316, "percentage": 65.83, "elapsed_time": "1:36:12", "remaining_time": "0:49:56", "throughput": 2845.7, "total_tokens": 16425448} {"current_steps": 25125, "total_steps": 38160, "loss": 0.0496, "lr": 1.576559590191696e-05, "epoch": 13.168238993710691, "percentage": 65.84, "elapsed_time": "1:36:13", "remaining_time": "0:49:55", "throughput": 2845.71, "total_tokens": 16428872} {"current_steps": 25130, "total_steps": 38160, "loss": 0.1238, "lr": 1.5754971216275692e-05, "epoch": 13.170859538784066, "percentage": 65.85, "elapsed_time": "1:36:14", "remaining_time": "0:49:53", "throughput": 2845.64, "total_tokens": 16431560} {"current_steps": 25135, "total_steps": 38160, "loss": 0.0244, "lr": 1.5744348464588975e-05, "epoch": 13.173480083857442, "percentage": 65.87, "elapsed_time": "1:36:15", "remaining_time": "0:49:52", "throughput": 2845.68, "total_tokens": 16435048} {"current_steps": 25140, "total_steps": 38160, "loss": 0.0211, "lr": 1.5733727649078968e-05, "epoch": 13.176100628930818, "percentage": 65.88, "elapsed_time": "1:36:16", "remaining_time": "0:49:51", "throughput": 2845.71, "total_tokens": 16438248} {"current_steps": 25145, "total_steps": 38160, "loss": 0.037, "lr": 1.5723108771967414e-05, "epoch": 13.178721174004194, "percentage": 65.89, "elapsed_time": "1:36:17", "remaining_time": "0:49:50", "throughput": 2845.69, "total_tokens": 16441384} {"current_steps": 25150, "total_steps": 38160, "loss": 0.093, "lr": 1.5712491835475685e-05, "epoch": 13.181341719077569, "percentage": 65.91, "elapsed_time": "1:36:18", "remaining_time": "0:49:49", "throughput": 2845.91, "total_tokens": 16445992} {"current_steps": 25155, "total_steps": 38160, "loss": 0.0188, "lr": 1.5701876841824698e-05, "epoch": 13.183962264150944, "percentage": 65.92, "elapsed_time": "1:36:20", "remaining_time": "0:49:48", "throughput": 2845.91, "total_tokens": 16449416} {"current_steps": 25160, "total_steps": 38160, "loss": 0.0157, "lr": 1.5691263793234993e-05, "epoch": 13.18658280922432, "percentage": 65.93, "elapsed_time": "1:36:21", "remaining_time": "0:49:47", "throughput": 2846.12, "total_tokens": 16454472} {"current_steps": 25165, "total_steps": 38160, "loss": 0.02, "lr": 1.5680652691926706e-05, "epoch": 13.189203354297694, "percentage": 65.95, "elapsed_time": "1:36:22", "remaining_time": "0:49:45", "throughput": 2846.01, "total_tokens": 16456808} {"current_steps": 25170, "total_steps": 38160, "loss": 0.0387, "lr": 1.5670043540119553e-05, "epoch": 13.19182389937107, "percentage": 65.96, "elapsed_time": "1:36:23", "remaining_time": "0:49:44", "throughput": 2846.0, "total_tokens": 16459752} {"current_steps": 25175, "total_steps": 38160, "loss": 0.0243, "lr": 1.5659436340032855e-05, "epoch": 13.194444444444445, "percentage": 65.97, "elapsed_time": "1:36:24", "remaining_time": "0:49:43", "throughput": 2846.0, "total_tokens": 16462760} {"current_steps": 25180, "total_steps": 38160, "loss": 0.0295, "lr": 1.5648831093885515e-05, "epoch": 13.19706498951782, "percentage": 65.99, "elapsed_time": "1:36:25", "remaining_time": "0:49:42", "throughput": 2846.1, "total_tokens": 16466536} {"current_steps": 25185, "total_steps": 38160, "loss": 0.068, "lr": 1.5638227803896015e-05, "epoch": 13.199685534591195, "percentage": 66.0, "elapsed_time": "1:36:26", "remaining_time": "0:49:41", "throughput": 2846.04, "total_tokens": 16469384} {"current_steps": 25190, "total_steps": 38160, "loss": 0.0149, "lr": 1.562762647228246e-05, "epoch": 13.20230607966457, "percentage": 66.01, "elapsed_time": "1:36:27", "remaining_time": "0:49:40", "throughput": 2846.04, "total_tokens": 16472488} {"current_steps": 25195, "total_steps": 38160, "loss": 0.0301, "lr": 1.5617027101262515e-05, "epoch": 13.204926624737945, "percentage": 66.02, "elapsed_time": "1:36:28", "remaining_time": "0:49:38", "throughput": 2846.02, "total_tokens": 16475528} {"current_steps": 25200, "total_steps": 38160, "loss": 0.0234, "lr": 1.5606429693053463e-05, "epoch": 13.20754716981132, "percentage": 66.04, "elapsed_time": "1:36:30", "remaining_time": "0:49:37", "throughput": 2845.98, "total_tokens": 16478216} {"current_steps": 25205, "total_steps": 38160, "loss": 0.0834, "lr": 1.5595834249872145e-05, "epoch": 13.210167714884696, "percentage": 66.05, "elapsed_time": "1:36:31", "remaining_time": "0:49:36", "throughput": 2846.0, "total_tokens": 16481480} {"current_steps": 25210, "total_steps": 38160, "loss": 0.032, "lr": 1.558524077393502e-05, "epoch": 13.21278825995807, "percentage": 66.06, "elapsed_time": "1:36:32", "remaining_time": "0:49:35", "throughput": 2846.19, "total_tokens": 16485768} {"current_steps": 25215, "total_steps": 38160, "loss": 0.0225, "lr": 1.557464926745811e-05, "epoch": 13.215408805031446, "percentage": 66.08, "elapsed_time": "1:36:33", "remaining_time": "0:49:34", "throughput": 2846.34, "total_tokens": 16490152} {"current_steps": 25220, "total_steps": 38160, "loss": 0.0245, "lr": 1.5564059732657045e-05, "epoch": 13.218029350104821, "percentage": 66.09, "elapsed_time": "1:36:34", "remaining_time": "0:49:33", "throughput": 2846.32, "total_tokens": 16493096} {"current_steps": 25225, "total_steps": 38160, "loss": 0.0387, "lr": 1.555347217174703e-05, "epoch": 13.220649895178196, "percentage": 66.1, "elapsed_time": "1:36:35", "remaining_time": "0:49:31", "throughput": 2846.25, "total_tokens": 16495848} {"current_steps": 25230, "total_steps": 38160, "loss": 0.0731, "lr": 1.554288658694287e-05, "epoch": 13.223270440251572, "percentage": 66.12, "elapsed_time": "1:36:37", "remaining_time": "0:49:31", "throughput": 2846.57, "total_tokens": 16502888} {"current_steps": 25235, "total_steps": 38160, "loss": 0.0469, "lr": 1.553230298045895e-05, "epoch": 13.225890985324948, "percentage": 66.13, "elapsed_time": "1:36:38", "remaining_time": "0:49:29", "throughput": 2846.57, "total_tokens": 16505928} {"current_steps": 25240, "total_steps": 38160, "loss": 0.033, "lr": 1.5521721354509223e-05, "epoch": 13.228511530398324, "percentage": 66.14, "elapsed_time": "1:36:39", "remaining_time": "0:49:28", "throughput": 2846.52, "total_tokens": 16508648} {"current_steps": 25245, "total_steps": 38160, "loss": 0.0576, "lr": 1.5511141711307258e-05, "epoch": 13.231132075471699, "percentage": 66.16, "elapsed_time": "1:36:40", "remaining_time": "0:49:27", "throughput": 2846.67, "total_tokens": 16512968} {"current_steps": 25250, "total_steps": 38160, "loss": 0.051, "lr": 1.5500564053066184e-05, "epoch": 13.233752620545074, "percentage": 66.17, "elapsed_time": "1:36:41", "remaining_time": "0:49:26", "throughput": 2846.73, "total_tokens": 16516552} {"current_steps": 25255, "total_steps": 38160, "loss": 0.0391, "lr": 1.5489988381998743e-05, "epoch": 13.23637316561845, "percentage": 66.18, "elapsed_time": "1:36:43", "remaining_time": "0:49:25", "throughput": 2846.71, "total_tokens": 16519528} {"current_steps": 25260, "total_steps": 38160, "loss": 0.0373, "lr": 1.5479414700317237e-05, "epoch": 13.238993710691824, "percentage": 66.19, "elapsed_time": "1:36:44", "remaining_time": "0:49:24", "throughput": 2846.71, "total_tokens": 16522504} {"current_steps": 25265, "total_steps": 38160, "loss": 0.0756, "lr": 1.546884301023356e-05, "epoch": 13.2416142557652, "percentage": 66.21, "elapsed_time": "1:36:45", "remaining_time": "0:49:22", "throughput": 2846.67, "total_tokens": 16525384} {"current_steps": 25270, "total_steps": 38160, "loss": 0.0316, "lr": 1.5458273313959186e-05, "epoch": 13.244234800838575, "percentage": 66.22, "elapsed_time": "1:36:46", "remaining_time": "0:49:21", "throughput": 2846.74, "total_tokens": 16528840} {"current_steps": 25275, "total_steps": 38160, "loss": 0.0358, "lr": 1.5447705613705177e-05, "epoch": 13.24685534591195, "percentage": 66.23, "elapsed_time": "1:36:47", "remaining_time": "0:49:20", "throughput": 2846.79, "total_tokens": 16532648} {"current_steps": 25280, "total_steps": 38160, "loss": 0.0269, "lr": 1.5437139911682176e-05, "epoch": 13.249475890985325, "percentage": 66.25, "elapsed_time": "1:36:48", "remaining_time": "0:49:19", "throughput": 2846.78, "total_tokens": 16535720} {"current_steps": 25285, "total_steps": 38160, "loss": 0.0149, "lr": 1.54265762101004e-05, "epoch": 13.2520964360587, "percentage": 66.26, "elapsed_time": "1:36:49", "remaining_time": "0:49:18", "throughput": 2846.69, "total_tokens": 16538312} {"current_steps": 25290, "total_steps": 38160, "loss": 0.0864, "lr": 1.5416014511169663e-05, "epoch": 13.254716981132075, "percentage": 66.27, "elapsed_time": "1:36:50", "remaining_time": "0:49:17", "throughput": 2846.74, "total_tokens": 16541640} {"current_steps": 25295, "total_steps": 38160, "loss": 0.0774, "lr": 1.5405454817099363e-05, "epoch": 13.25733752620545, "percentage": 66.29, "elapsed_time": "1:36:51", "remaining_time": "0:49:15", "throughput": 2846.86, "total_tokens": 16545640} {"current_steps": 25300, "total_steps": 38160, "loss": 0.0209, "lr": 1.5394897130098446e-05, "epoch": 13.259958071278826, "percentage": 66.3, "elapsed_time": "1:36:52", "remaining_time": "0:49:14", "throughput": 2846.83, "total_tokens": 16548488} {"current_steps": 25305, "total_steps": 38160, "loss": 0.0269, "lr": 1.5384341452375465e-05, "epoch": 13.2625786163522, "percentage": 66.31, "elapsed_time": "1:36:54", "remaining_time": "0:49:13", "throughput": 2846.85, "total_tokens": 16551592} {"current_steps": 25310, "total_steps": 38160, "loss": 0.0433, "lr": 1.5373787786138556e-05, "epoch": 13.265199161425576, "percentage": 66.33, "elapsed_time": "1:36:55", "remaining_time": "0:49:12", "throughput": 2846.83, "total_tokens": 16554600} {"current_steps": 25315, "total_steps": 38160, "loss": 0.0392, "lr": 1.5363236133595416e-05, "epoch": 13.267819706498951, "percentage": 66.34, "elapsed_time": "1:36:56", "remaining_time": "0:49:11", "throughput": 2846.74, "total_tokens": 16557192} {"current_steps": 25320, "total_steps": 38160, "loss": 0.0352, "lr": 1.5352686496953344e-05, "epoch": 13.270440251572326, "percentage": 66.35, "elapsed_time": "1:36:57", "remaining_time": "0:49:09", "throughput": 2846.71, "total_tokens": 16560040} {"current_steps": 25325, "total_steps": 38160, "loss": 0.03, "lr": 1.534213887841919e-05, "epoch": 13.273060796645701, "percentage": 66.37, "elapsed_time": "1:36:58", "remaining_time": "0:49:08", "throughput": 2846.72, "total_tokens": 16563304} {"current_steps": 25330, "total_steps": 38160, "loss": 0.027, "lr": 1.5331593280199395e-05, "epoch": 13.275681341719078, "percentage": 66.38, "elapsed_time": "1:36:59", "remaining_time": "0:49:07", "throughput": 2846.71, "total_tokens": 16566312} {"current_steps": 25335, "total_steps": 38160, "loss": 0.0434, "lr": 1.532104970449999e-05, "epoch": 13.278301886792454, "percentage": 66.39, "elapsed_time": "1:37:00", "remaining_time": "0:49:06", "throughput": 2846.75, "total_tokens": 16569736} {"current_steps": 25340, "total_steps": 38160, "loss": 0.0309, "lr": 1.5310508153526555e-05, "epoch": 13.280922431865829, "percentage": 66.4, "elapsed_time": "1:37:01", "remaining_time": "0:49:05", "throughput": 2846.72, "total_tokens": 16572680} {"current_steps": 25345, "total_steps": 38160, "loss": 0.0213, "lr": 1.5299968629484276e-05, "epoch": 13.283542976939204, "percentage": 66.42, "elapsed_time": "1:37:02", "remaining_time": "0:49:04", "throughput": 2846.77, "total_tokens": 16576168} {"current_steps": 25350, "total_steps": 38160, "loss": 0.0153, "lr": 1.5289431134577904e-05, "epoch": 13.286163522012579, "percentage": 66.43, "elapsed_time": "1:37:03", "remaining_time": "0:49:02", "throughput": 2846.65, "total_tokens": 16578504} {"current_steps": 25355, "total_steps": 38160, "loss": 0.047, "lr": 1.527889567101174e-05, "epoch": 13.288784067085954, "percentage": 66.44, "elapsed_time": "1:37:04", "remaining_time": "0:49:01", "throughput": 2846.78, "total_tokens": 16582472} {"current_steps": 25360, "total_steps": 38160, "loss": 0.046, "lr": 1.5268362240989707e-05, "epoch": 13.29140461215933, "percentage": 66.46, "elapsed_time": "1:37:06", "remaining_time": "0:49:00", "throughput": 2846.7, "total_tokens": 16585128} {"current_steps": 25365, "total_steps": 38160, "loss": 0.0197, "lr": 1.525783084671526e-05, "epoch": 13.294025157232705, "percentage": 66.47, "elapsed_time": "1:37:07", "remaining_time": "0:48:59", "throughput": 2846.58, "total_tokens": 16587592} {"current_steps": 25370, "total_steps": 38160, "loss": 0.051, "lr": 1.5247301490391458e-05, "epoch": 13.29664570230608, "percentage": 66.48, "elapsed_time": "1:37:09", "remaining_time": "0:48:58", "throughput": 2846.84, "total_tokens": 16594600} {"current_steps": 25375, "total_steps": 38160, "loss": 0.0105, "lr": 1.5236774174220922e-05, "epoch": 13.299266247379455, "percentage": 66.5, "elapsed_time": "1:37:10", "remaining_time": "0:48:57", "throughput": 2846.89, "total_tokens": 16598120} {"current_steps": 25380, "total_steps": 38160, "loss": 0.0392, "lr": 1.5226248900405852e-05, "epoch": 13.30188679245283, "percentage": 66.51, "elapsed_time": "1:37:11", "remaining_time": "0:48:56", "throughput": 2846.91, "total_tokens": 16601768} {"current_steps": 25385, "total_steps": 38160, "loss": 0.0174, "lr": 1.5215725671147996e-05, "epoch": 13.304507337526205, "percentage": 66.52, "elapsed_time": "1:37:12", "remaining_time": "0:48:55", "throughput": 2846.91, "total_tokens": 16604776} {"current_steps": 25390, "total_steps": 38160, "loss": 0.0481, "lr": 1.5205204488648709e-05, "epoch": 13.30712788259958, "percentage": 66.54, "elapsed_time": "1:37:13", "remaining_time": "0:48:54", "throughput": 2846.88, "total_tokens": 16607688} {"current_steps": 25395, "total_steps": 38160, "loss": 0.0198, "lr": 1.5194685355108893e-05, "epoch": 13.309748427672956, "percentage": 66.55, "elapsed_time": "1:37:14", "remaining_time": "0:48:52", "throughput": 2846.88, "total_tokens": 16610920} {"current_steps": 25400, "total_steps": 38160, "loss": 0.0218, "lr": 1.518416827272904e-05, "epoch": 13.31236897274633, "percentage": 66.56, "elapsed_time": "1:37:15", "remaining_time": "0:48:51", "throughput": 2846.86, "total_tokens": 16614024} {"current_steps": 25405, "total_steps": 38160, "loss": 0.0355, "lr": 1.5173653243709207e-05, "epoch": 13.314989517819706, "percentage": 66.57, "elapsed_time": "1:37:16", "remaining_time": "0:48:50", "throughput": 2846.84, "total_tokens": 16616936} {"current_steps": 25410, "total_steps": 38160, "loss": 0.0642, "lr": 1.5163140270249e-05, "epoch": 13.317610062893081, "percentage": 66.59, "elapsed_time": "1:37:18", "remaining_time": "0:48:49", "throughput": 2846.74, "total_tokens": 16619432} {"current_steps": 25415, "total_steps": 38160, "loss": 0.044, "lr": 1.5152629354547626e-05, "epoch": 13.320230607966456, "percentage": 66.6, "elapsed_time": "1:37:19", "remaining_time": "0:48:48", "throughput": 2846.68, "total_tokens": 16622152} {"current_steps": 25420, "total_steps": 38160, "loss": 0.0422, "lr": 1.5142120498803842e-05, "epoch": 13.322851153039831, "percentage": 66.61, "elapsed_time": "1:37:20", "remaining_time": "0:48:46", "throughput": 2846.61, "total_tokens": 16624808} {"current_steps": 25425, "total_steps": 38160, "loss": 0.0389, "lr": 1.5131613705215991e-05, "epoch": 13.325471698113208, "percentage": 66.63, "elapsed_time": "1:37:21", "remaining_time": "0:48:45", "throughput": 2846.69, "total_tokens": 16628744} {"current_steps": 25430, "total_steps": 38160, "loss": 0.089, "lr": 1.5121108975981965e-05, "epoch": 13.328092243186584, "percentage": 66.64, "elapsed_time": "1:37:22", "remaining_time": "0:48:44", "throughput": 2846.62, "total_tokens": 16631368} {"current_steps": 25435, "total_steps": 38160, "loss": 0.0119, "lr": 1.5110606313299248e-05, "epoch": 13.330712788259959, "percentage": 66.65, "elapsed_time": "1:37:23", "remaining_time": "0:48:43", "throughput": 2846.64, "total_tokens": 16634536} {"current_steps": 25440, "total_steps": 38160, "loss": 0.0559, "lr": 1.5100105719364855e-05, "epoch": 13.333333333333334, "percentage": 66.67, "elapsed_time": "1:37:24", "remaining_time": "0:48:42", "throughput": 2846.63, "total_tokens": 16637544} {"current_steps": 25445, "total_steps": 38160, "loss": 0.023, "lr": 1.50896071963754e-05, "epoch": 13.335953878406709, "percentage": 66.68, "elapsed_time": "1:37:25", "remaining_time": "0:48:41", "throughput": 2846.69, "total_tokens": 16641096} {"current_steps": 25450, "total_steps": 38160, "loss": 0.0363, "lr": 1.5079110746527055e-05, "epoch": 13.338574423480084, "percentage": 66.69, "elapsed_time": "1:37:26", "remaining_time": "0:48:39", "throughput": 2846.59, "total_tokens": 16643688} {"current_steps": 25455, "total_steps": 38160, "loss": 0.0378, "lr": 1.5068616372015565e-05, "epoch": 13.34119496855346, "percentage": 66.71, "elapsed_time": "1:37:27", "remaining_time": "0:48:38", "throughput": 2846.61, "total_tokens": 16646888} {"current_steps": 25460, "total_steps": 38160, "loss": 0.0325, "lr": 1.5058124075036223e-05, "epoch": 13.343815513626835, "percentage": 66.72, "elapsed_time": "1:37:29", "remaining_time": "0:48:37", "throughput": 2846.63, "total_tokens": 16650312} {"current_steps": 25465, "total_steps": 38160, "loss": 0.0164, "lr": 1.5047633857783908e-05, "epoch": 13.34643605870021, "percentage": 66.73, "elapsed_time": "1:37:30", "remaining_time": "0:48:36", "throughput": 2846.7, "total_tokens": 16653896} {"current_steps": 25470, "total_steps": 38160, "loss": 0.0193, "lr": 1.5037145722453044e-05, "epoch": 13.349056603773585, "percentage": 66.75, "elapsed_time": "1:37:31", "remaining_time": "0:48:35", "throughput": 2846.78, "total_tokens": 16657320} {"current_steps": 25475, "total_steps": 38160, "loss": 0.036, "lr": 1.5026659671237624e-05, "epoch": 13.35167714884696, "percentage": 66.76, "elapsed_time": "1:37:32", "remaining_time": "0:48:34", "throughput": 2846.8, "total_tokens": 16660456} {"current_steps": 25480, "total_steps": 38160, "loss": 0.0247, "lr": 1.501617570633123e-05, "epoch": 13.354297693920335, "percentage": 66.77, "elapsed_time": "1:37:33", "remaining_time": "0:48:32", "throughput": 2846.92, "total_tokens": 16664424} {"current_steps": 25485, "total_steps": 38160, "loss": 0.0467, "lr": 1.500569382992697e-05, "epoch": 13.35691823899371, "percentage": 66.78, "elapsed_time": "1:37:34", "remaining_time": "0:48:31", "throughput": 2846.97, "total_tokens": 16667656} {"current_steps": 25490, "total_steps": 38160, "loss": 0.044, "lr": 1.4995214044217547e-05, "epoch": 13.359538784067086, "percentage": 66.8, "elapsed_time": "1:37:35", "remaining_time": "0:48:30", "throughput": 2847.1, "total_tokens": 16671688} {"current_steps": 25495, "total_steps": 38160, "loss": 0.037, "lr": 1.49847363513952e-05, "epoch": 13.36215932914046, "percentage": 66.81, "elapsed_time": "1:37:36", "remaining_time": "0:48:29", "throughput": 2847.13, "total_tokens": 16674856} {"current_steps": 25500, "total_steps": 38160, "loss": 0.0157, "lr": 1.4974260753651748e-05, "epoch": 13.364779874213836, "percentage": 66.82, "elapsed_time": "1:37:37", "remaining_time": "0:48:28", "throughput": 2847.12, "total_tokens": 16677864} {"current_steps": 25505, "total_steps": 38160, "loss": 0.026, "lr": 1.4963787253178568e-05, "epoch": 13.367400419287211, "percentage": 66.84, "elapsed_time": "1:37:38", "remaining_time": "0:48:27", "throughput": 2847.11, "total_tokens": 16680808} {"current_steps": 25510, "total_steps": 38160, "loss": 0.0221, "lr": 1.4953315852166594e-05, "epoch": 13.370020964360586, "percentage": 66.85, "elapsed_time": "1:37:39", "remaining_time": "0:48:25", "throughput": 2846.99, "total_tokens": 16683208} {"current_steps": 25515, "total_steps": 38160, "loss": 0.0299, "lr": 1.4942846552806322e-05, "epoch": 13.372641509433961, "percentage": 66.86, "elapsed_time": "1:37:41", "remaining_time": "0:48:24", "throughput": 2847.09, "total_tokens": 16686952} {"current_steps": 25520, "total_steps": 38160, "loss": 0.0285, "lr": 1.4932379357287829e-05, "epoch": 13.375262054507338, "percentage": 66.88, "elapsed_time": "1:37:42", "remaining_time": "0:48:23", "throughput": 2847.02, "total_tokens": 16689576} {"current_steps": 25525, "total_steps": 38160, "loss": 0.0364, "lr": 1.49219142678007e-05, "epoch": 13.377882599580714, "percentage": 66.89, "elapsed_time": "1:37:43", "remaining_time": "0:48:22", "throughput": 2847.1, "total_tokens": 16693320} {"current_steps": 25530, "total_steps": 38160, "loss": 0.0194, "lr": 1.4911451286534128e-05, "epoch": 13.380503144654089, "percentage": 66.9, "elapsed_time": "1:37:44", "remaining_time": "0:48:21", "throughput": 2847.27, "total_tokens": 16698344} {"current_steps": 25535, "total_steps": 38160, "loss": 0.0227, "lr": 1.490099041567686e-05, "epoch": 13.383123689727464, "percentage": 66.92, "elapsed_time": "1:37:45", "remaining_time": "0:48:20", "throughput": 2847.27, "total_tokens": 16701576} {"current_steps": 25540, "total_steps": 38160, "loss": 0.0233, "lr": 1.4890531657417176e-05, "epoch": 13.385744234800839, "percentage": 66.93, "elapsed_time": "1:37:46", "remaining_time": "0:48:18", "throughput": 2847.31, "total_tokens": 16704904} {"current_steps": 25545, "total_steps": 38160, "loss": 0.0382, "lr": 1.4880075013942938e-05, "epoch": 13.388364779874214, "percentage": 66.94, "elapsed_time": "1:37:48", "remaining_time": "0:48:17", "throughput": 2847.19, "total_tokens": 16707304} {"current_steps": 25550, "total_steps": 38160, "loss": 0.088, "lr": 1.4869620487441558e-05, "epoch": 13.39098532494759, "percentage": 66.95, "elapsed_time": "1:37:49", "remaining_time": "0:48:16", "throughput": 2847.15, "total_tokens": 16710120} {"current_steps": 25555, "total_steps": 38160, "loss": 0.0358, "lr": 1.4859168080099988e-05, "epoch": 13.393605870020965, "percentage": 66.97, "elapsed_time": "1:37:50", "remaining_time": "0:48:15", "throughput": 2847.22, "total_tokens": 16713736} {"current_steps": 25560, "total_steps": 38160, "loss": 0.0292, "lr": 1.484871779410477e-05, "epoch": 13.39622641509434, "percentage": 66.98, "elapsed_time": "1:37:51", "remaining_time": "0:48:14", "throughput": 2847.2, "total_tokens": 16716616} {"current_steps": 25565, "total_steps": 38160, "loss": 0.0701, "lr": 1.4838269631641971e-05, "epoch": 13.398846960167715, "percentage": 66.99, "elapsed_time": "1:37:52", "remaining_time": "0:48:13", "throughput": 2847.16, "total_tokens": 16719432} {"current_steps": 25570, "total_steps": 38160, "loss": 0.0423, "lr": 1.482782359489724e-05, "epoch": 13.40146750524109, "percentage": 67.01, "elapsed_time": "1:37:53", "remaining_time": "0:48:11", "throughput": 2847.27, "total_tokens": 16723176} {"current_steps": 25575, "total_steps": 38160, "loss": 0.0252, "lr": 1.4817379686055754e-05, "epoch": 13.404088050314465, "percentage": 67.02, "elapsed_time": "1:37:54", "remaining_time": "0:48:10", "throughput": 2847.17, "total_tokens": 16725608} {"current_steps": 25580, "total_steps": 38160, "loss": 0.039, "lr": 1.4806937907302282e-05, "epoch": 13.40670859538784, "percentage": 67.03, "elapsed_time": "1:37:55", "remaining_time": "0:48:09", "throughput": 2847.22, "total_tokens": 16729320} {"current_steps": 25585, "total_steps": 38160, "loss": 0.0299, "lr": 1.4796498260821103e-05, "epoch": 13.409329140461216, "percentage": 67.05, "elapsed_time": "1:37:56", "remaining_time": "0:48:08", "throughput": 2847.16, "total_tokens": 16731976} {"current_steps": 25590, "total_steps": 38160, "loss": 0.0218, "lr": 1.4786060748796076e-05, "epoch": 13.41194968553459, "percentage": 67.06, "elapsed_time": "1:37:57", "remaining_time": "0:48:07", "throughput": 2847.12, "total_tokens": 16734792} {"current_steps": 25595, "total_steps": 38160, "loss": 0.0366, "lr": 1.4775625373410617e-05, "epoch": 13.414570230607966, "percentage": 67.07, "elapsed_time": "1:37:58", "remaining_time": "0:48:06", "throughput": 2847.07, "total_tokens": 16737608} {"current_steps": 25600, "total_steps": 38160, "loss": 0.0396, "lr": 1.4765192136847685e-05, "epoch": 13.417190775681341, "percentage": 67.09, "elapsed_time": "1:38:00", "remaining_time": "0:48:04", "throughput": 2847.09, "total_tokens": 16741000} {"current_steps": 25605, "total_steps": 38160, "loss": 0.0226, "lr": 1.47547610412898e-05, "epoch": 13.419811320754716, "percentage": 67.1, "elapsed_time": "1:38:01", "remaining_time": "0:48:03", "throughput": 2847.07, "total_tokens": 16743944} {"current_steps": 25610, "total_steps": 38160, "loss": 0.0213, "lr": 1.4744332088919011e-05, "epoch": 13.422431865828091, "percentage": 67.11, "elapsed_time": "1:38:02", "remaining_time": "0:48:02", "throughput": 2847.1, "total_tokens": 16747176} {"current_steps": 25615, "total_steps": 38160, "loss": 0.0597, "lr": 1.4733905281916954e-05, "epoch": 13.425052410901468, "percentage": 67.13, "elapsed_time": "1:38:03", "remaining_time": "0:48:01", "throughput": 2847.07, "total_tokens": 16749928} {"current_steps": 25620, "total_steps": 38160, "loss": 0.0118, "lr": 1.472348062246478e-05, "epoch": 13.427672955974844, "percentage": 67.14, "elapsed_time": "1:38:04", "remaining_time": "0:48:00", "throughput": 2847.1, "total_tokens": 16753128} {"current_steps": 25625, "total_steps": 38160, "loss": 0.0318, "lr": 1.4713058112743228e-05, "epoch": 13.430293501048219, "percentage": 67.15, "elapsed_time": "1:38:05", "remaining_time": "0:47:58", "throughput": 2847.09, "total_tokens": 16756104} {"current_steps": 25630, "total_steps": 38160, "loss": 0.0508, "lr": 1.4702637754932553e-05, "epoch": 13.432914046121594, "percentage": 67.16, "elapsed_time": "1:38:06", "remaining_time": "0:47:57", "throughput": 2847.04, "total_tokens": 16758824} {"current_steps": 25635, "total_steps": 38160, "loss": 0.0255, "lr": 1.4692219551212587e-05, "epoch": 13.435534591194969, "percentage": 67.18, "elapsed_time": "1:38:07", "remaining_time": "0:47:56", "throughput": 2846.92, "total_tokens": 16761224} {"current_steps": 25640, "total_steps": 38160, "loss": 0.0343, "lr": 1.4681803503762695e-05, "epoch": 13.438155136268344, "percentage": 67.19, "elapsed_time": "1:38:08", "remaining_time": "0:47:55", "throughput": 2846.91, "total_tokens": 16764072} {"current_steps": 25645, "total_steps": 38160, "loss": 0.0362, "lr": 1.4671389614761788e-05, "epoch": 13.44077568134172, "percentage": 67.2, "elapsed_time": "1:38:09", "remaining_time": "0:47:54", "throughput": 2846.97, "total_tokens": 16767560} {"current_steps": 25650, "total_steps": 38160, "loss": 0.0176, "lr": 1.4660977886388339e-05, "epoch": 13.443396226415095, "percentage": 67.22, "elapsed_time": "1:38:10", "remaining_time": "0:47:52", "throughput": 2846.96, "total_tokens": 16770504} {"current_steps": 25655, "total_steps": 38160, "loss": 0.0441, "lr": 1.4650568320820362e-05, "epoch": 13.44601677148847, "percentage": 67.23, "elapsed_time": "1:38:11", "remaining_time": "0:47:51", "throughput": 2846.91, "total_tokens": 16773224} {"current_steps": 25660, "total_steps": 38160, "loss": 0.033, "lr": 1.4640160920235423e-05, "epoch": 13.448637316561845, "percentage": 67.24, "elapsed_time": "1:38:12", "remaining_time": "0:47:50", "throughput": 2846.83, "total_tokens": 16775880} {"current_steps": 25665, "total_steps": 38160, "loss": 0.0342, "lr": 1.4629755686810631e-05, "epoch": 13.45125786163522, "percentage": 67.26, "elapsed_time": "1:38:13", "remaining_time": "0:47:49", "throughput": 2846.83, "total_tokens": 16778920} {"current_steps": 25670, "total_steps": 38160, "loss": 0.0231, "lr": 1.4619352622722632e-05, "epoch": 13.453878406708595, "percentage": 67.27, "elapsed_time": "1:38:14", "remaining_time": "0:47:48", "throughput": 2846.75, "total_tokens": 16781544} {"current_steps": 25675, "total_steps": 38160, "loss": 0.0309, "lr": 1.4608951730147635e-05, "epoch": 13.45649895178197, "percentage": 67.28, "elapsed_time": "1:38:16", "remaining_time": "0:47:47", "throughput": 2846.7, "total_tokens": 16784264} {"current_steps": 25680, "total_steps": 38160, "loss": 0.0247, "lr": 1.4598553011261395e-05, "epoch": 13.459119496855346, "percentage": 67.3, "elapsed_time": "1:38:17", "remaining_time": "0:47:45", "throughput": 2846.69, "total_tokens": 16787176} {"current_steps": 25685, "total_steps": 38160, "loss": 0.0404, "lr": 1.4588156468239192e-05, "epoch": 13.46174004192872, "percentage": 67.31, "elapsed_time": "1:38:18", "remaining_time": "0:47:44", "throughput": 2846.71, "total_tokens": 16790376} {"current_steps": 25690, "total_steps": 38160, "loss": 0.0213, "lr": 1.4577762103255882e-05, "epoch": 13.464360587002096, "percentage": 67.32, "elapsed_time": "1:38:19", "remaining_time": "0:47:43", "throughput": 2846.73, "total_tokens": 16793608} {"current_steps": 25695, "total_steps": 38160, "loss": 0.0412, "lr": 1.4567369918485828e-05, "epoch": 13.466981132075471, "percentage": 67.33, "elapsed_time": "1:38:20", "remaining_time": "0:47:42", "throughput": 2846.71, "total_tokens": 16796552} {"current_steps": 25700, "total_steps": 38160, "loss": 0.0265, "lr": 1.4556979916102976e-05, "epoch": 13.469601677148846, "percentage": 67.35, "elapsed_time": "1:38:21", "remaining_time": "0:47:41", "throughput": 2846.67, "total_tokens": 16799432} {"current_steps": 25705, "total_steps": 38160, "loss": 0.0196, "lr": 1.454659209828077e-05, "epoch": 13.472222222222221, "percentage": 67.36, "elapsed_time": "1:38:22", "remaining_time": "0:47:39", "throughput": 2846.62, "total_tokens": 16802184} {"current_steps": 25710, "total_steps": 38160, "loss": 0.0202, "lr": 1.4536206467192243e-05, "epoch": 13.474842767295598, "percentage": 67.37, "elapsed_time": "1:38:24", "remaining_time": "0:47:39", "throughput": 2846.75, "total_tokens": 16807208} {"current_steps": 25715, "total_steps": 38160, "loss": 0.0363, "lr": 1.4525823025009944e-05, "epoch": 13.477463312368974, "percentage": 67.39, "elapsed_time": "1:38:25", "remaining_time": "0:47:37", "throughput": 2846.82, "total_tokens": 16810856} {"current_steps": 25720, "total_steps": 38160, "loss": 0.0189, "lr": 1.4515441773905983e-05, "epoch": 13.480083857442349, "percentage": 67.4, "elapsed_time": "1:38:26", "remaining_time": "0:47:36", "throughput": 2846.81, "total_tokens": 16813736} {"current_steps": 25725, "total_steps": 38160, "loss": 0.0332, "lr": 1.4505062716051988e-05, "epoch": 13.482704402515724, "percentage": 67.41, "elapsed_time": "1:38:27", "remaining_time": "0:47:35", "throughput": 2846.91, "total_tokens": 16817928} {"current_steps": 25730, "total_steps": 38160, "loss": 0.0182, "lr": 1.4494685853619133e-05, "epoch": 13.485324947589099, "percentage": 67.43, "elapsed_time": "1:38:28", "remaining_time": "0:47:34", "throughput": 2846.91, "total_tokens": 16820872} {"current_steps": 25735, "total_steps": 38160, "loss": 0.0407, "lr": 1.4484311188778143e-05, "epoch": 13.487945492662474, "percentage": 67.44, "elapsed_time": "1:38:29", "remaining_time": "0:47:33", "throughput": 2846.84, "total_tokens": 16823464} {"current_steps": 25740, "total_steps": 38160, "loss": 0.0439, "lr": 1.4473938723699285e-05, "epoch": 13.49056603773585, "percentage": 67.45, "elapsed_time": "1:38:30", "remaining_time": "0:47:31", "throughput": 2846.85, "total_tokens": 16826632} {"current_steps": 25745, "total_steps": 38160, "loss": 0.029, "lr": 1.4463568460552368e-05, "epoch": 13.493186582809225, "percentage": 67.47, "elapsed_time": "1:38:31", "remaining_time": "0:47:30", "throughput": 2846.86, "total_tokens": 16829640} {"current_steps": 25750, "total_steps": 38160, "loss": 0.0174, "lr": 1.4453200401506723e-05, "epoch": 13.4958071278826, "percentage": 67.48, "elapsed_time": "1:38:32", "remaining_time": "0:47:29", "throughput": 2846.83, "total_tokens": 16832456} {"current_steps": 25755, "total_steps": 38160, "loss": 0.0164, "lr": 1.4442834548731218e-05, "epoch": 13.498427672955975, "percentage": 67.49, "elapsed_time": "1:38:33", "remaining_time": "0:47:28", "throughput": 2846.8, "total_tokens": 16835208} {"current_steps": 25760, "total_steps": 38160, "loss": 0.0355, "lr": 1.4432470904394285e-05, "epoch": 13.50104821802935, "percentage": 67.51, "elapsed_time": "1:38:34", "remaining_time": "0:47:27", "throughput": 2846.88, "total_tokens": 16838632} {"current_steps": 25765, "total_steps": 38160, "loss": 0.0177, "lr": 1.4422109470663878e-05, "epoch": 13.503668763102725, "percentage": 67.52, "elapsed_time": "1:38:35", "remaining_time": "0:47:25", "throughput": 2846.94, "total_tokens": 16842088} {"current_steps": 25770, "total_steps": 38160, "loss": 0.0201, "lr": 1.441175024970749e-05, "epoch": 13.5062893081761, "percentage": 67.53, "elapsed_time": "1:38:36", "remaining_time": "0:47:24", "throughput": 2846.84, "total_tokens": 16844488} {"current_steps": 25775, "total_steps": 38160, "loss": 0.0647, "lr": 1.4401393243692163e-05, "epoch": 13.508909853249476, "percentage": 67.54, "elapsed_time": "1:38:38", "remaining_time": "0:47:23", "throughput": 2846.98, "total_tokens": 16848712} {"current_steps": 25780, "total_steps": 38160, "loss": 0.0306, "lr": 1.4391038454784455e-05, "epoch": 13.51153039832285, "percentage": 67.56, "elapsed_time": "1:38:39", "remaining_time": "0:47:22", "throughput": 2847.05, "total_tokens": 16852232} {"current_steps": 25785, "total_steps": 38160, "loss": 0.0558, "lr": 1.4380685885150458e-05, "epoch": 13.514150943396226, "percentage": 67.57, "elapsed_time": "1:38:40", "remaining_time": "0:47:21", "throughput": 2847.09, "total_tokens": 16855368} {"current_steps": 25790, "total_steps": 38160, "loss": 0.023, "lr": 1.437033553695582e-05, "epoch": 13.516771488469601, "percentage": 67.58, "elapsed_time": "1:38:41", "remaining_time": "0:47:20", "throughput": 2847.11, "total_tokens": 16858536} {"current_steps": 25795, "total_steps": 38160, "loss": 0.0301, "lr": 1.4359987412365721e-05, "epoch": 13.519392033542976, "percentage": 67.6, "elapsed_time": "1:38:42", "remaining_time": "0:47:18", "throughput": 2847.19, "total_tokens": 16862152} {"current_steps": 25800, "total_steps": 38160, "loss": 0.0312, "lr": 1.4349641513544876e-05, "epoch": 13.522012578616351, "percentage": 67.61, "elapsed_time": "1:38:43", "remaining_time": "0:47:17", "throughput": 2847.15, "total_tokens": 16864904} {"current_steps": 25805, "total_steps": 38160, "loss": 0.0537, "lr": 1.4339297842657523e-05, "epoch": 13.524633123689728, "percentage": 67.62, "elapsed_time": "1:38:44", "remaining_time": "0:47:16", "throughput": 2847.15, "total_tokens": 16868136} {"current_steps": 25810, "total_steps": 38160, "loss": 0.0222, "lr": 1.4328956401867427e-05, "epoch": 13.527253668763104, "percentage": 67.64, "elapsed_time": "1:38:45", "remaining_time": "0:47:15", "throughput": 2847.19, "total_tokens": 16871432} {"current_steps": 25815, "total_steps": 38160, "loss": 0.0587, "lr": 1.4318617193337908e-05, "epoch": 13.529874213836479, "percentage": 67.65, "elapsed_time": "1:38:46", "remaining_time": "0:47:14", "throughput": 2847.13, "total_tokens": 16874120} {"current_steps": 25820, "total_steps": 38160, "loss": 0.0564, "lr": 1.4308280219231812e-05, "epoch": 13.532494758909854, "percentage": 67.66, "elapsed_time": "1:38:47", "remaining_time": "0:47:13", "throughput": 2847.2, "total_tokens": 16878088} {"current_steps": 25825, "total_steps": 38160, "loss": 0.0373, "lr": 1.4297945481711527e-05, "epoch": 13.535115303983229, "percentage": 67.68, "elapsed_time": "1:38:49", "remaining_time": "0:47:11", "throughput": 2847.14, "total_tokens": 16880776} {"current_steps": 25830, "total_steps": 38160, "loss": 0.0311, "lr": 1.4287612982938946e-05, "epoch": 13.537735849056604, "percentage": 67.69, "elapsed_time": "1:38:50", "remaining_time": "0:47:10", "throughput": 2847.22, "total_tokens": 16884360} {"current_steps": 25835, "total_steps": 38160, "loss": 0.1038, "lr": 1.4277282725075523e-05, "epoch": 13.54035639412998, "percentage": 67.7, "elapsed_time": "1:38:51", "remaining_time": "0:47:09", "throughput": 2847.17, "total_tokens": 16887080} {"current_steps": 25840, "total_steps": 38160, "loss": 0.0584, "lr": 1.426695471028221e-05, "epoch": 13.542976939203355, "percentage": 67.71, "elapsed_time": "1:38:52", "remaining_time": "0:47:08", "throughput": 2847.21, "total_tokens": 16890536} {"current_steps": 25845, "total_steps": 38160, "loss": 0.0199, "lr": 1.4256628940719524e-05, "epoch": 13.54559748427673, "percentage": 67.73, "elapsed_time": "1:38:53", "remaining_time": "0:47:07", "throughput": 2847.26, "total_tokens": 16893992} {"current_steps": 25850, "total_steps": 38160, "loss": 0.0391, "lr": 1.42463054185475e-05, "epoch": 13.548218029350105, "percentage": 67.74, "elapsed_time": "1:38:54", "remaining_time": "0:47:06", "throughput": 2847.23, "total_tokens": 16896904} {"current_steps": 25855, "total_steps": 38160, "loss": 0.0168, "lr": 1.4235984145925705e-05, "epoch": 13.55083857442348, "percentage": 67.75, "elapsed_time": "1:38:55", "remaining_time": "0:47:04", "throughput": 2847.22, "total_tokens": 16899880} {"current_steps": 25860, "total_steps": 38160, "loss": 0.026, "lr": 1.4225665125013224e-05, "epoch": 13.553459119496855, "percentage": 67.77, "elapsed_time": "1:38:56", "remaining_time": "0:47:03", "throughput": 2847.29, "total_tokens": 16903528} {"current_steps": 25865, "total_steps": 38160, "loss": 0.0429, "lr": 1.4215348357968669e-05, "epoch": 13.55607966457023, "percentage": 67.78, "elapsed_time": "1:38:57", "remaining_time": "0:47:02", "throughput": 2847.16, "total_tokens": 16905736} {"current_steps": 25870, "total_steps": 38160, "loss": 0.0322, "lr": 1.42050338469502e-05, "epoch": 13.558700209643606, "percentage": 67.79, "elapsed_time": "1:38:59", "remaining_time": "0:47:01", "throughput": 2847.07, "total_tokens": 16909256} {"current_steps": 25875, "total_steps": 38160, "loss": 0.0248, "lr": 1.4194721594115495e-05, "epoch": 13.56132075471698, "percentage": 67.81, "elapsed_time": "1:39:00", "remaining_time": "0:47:00", "throughput": 2847.04, "total_tokens": 16911976} {"current_steps": 25880, "total_steps": 38160, "loss": 0.0134, "lr": 1.4184411601621769e-05, "epoch": 13.563941299790356, "percentage": 67.82, "elapsed_time": "1:39:01", "remaining_time": "0:46:59", "throughput": 2847.09, "total_tokens": 16915592} {"current_steps": 25885, "total_steps": 38160, "loss": 0.0329, "lr": 1.4174103871625738e-05, "epoch": 13.566561844863731, "percentage": 67.83, "elapsed_time": "1:39:02", "remaining_time": "0:46:57", "throughput": 2847.16, "total_tokens": 16919080} {"current_steps": 25890, "total_steps": 38160, "loss": 0.0258, "lr": 1.4163798406283674e-05, "epoch": 13.569182389937106, "percentage": 67.85, "elapsed_time": "1:39:03", "remaining_time": "0:46:56", "throughput": 2847.25, "total_tokens": 16922632} {"current_steps": 25895, "total_steps": 38160, "loss": 0.0299, "lr": 1.415349520775135e-05, "epoch": 13.571802935010481, "percentage": 67.86, "elapsed_time": "1:39:04", "remaining_time": "0:46:55", "throughput": 2847.23, "total_tokens": 16925736} {"current_steps": 25900, "total_steps": 38160, "loss": 0.0198, "lr": 1.4143194278184086e-05, "epoch": 13.574423480083858, "percentage": 67.87, "elapsed_time": "1:39:05", "remaining_time": "0:46:54", "throughput": 2847.3, "total_tokens": 16929448} {"current_steps": 25905, "total_steps": 38160, "loss": 0.0792, "lr": 1.4132895619736724e-05, "epoch": 13.577044025157234, "percentage": 67.89, "elapsed_time": "1:39:06", "remaining_time": "0:46:53", "throughput": 2847.31, "total_tokens": 16932584} {"current_steps": 25910, "total_steps": 38160, "loss": 0.0734, "lr": 1.4122599234563613e-05, "epoch": 13.579664570230609, "percentage": 67.9, "elapsed_time": "1:39:07", "remaining_time": "0:46:52", "throughput": 2847.4, "total_tokens": 16936072} {"current_steps": 25915, "total_steps": 38160, "loss": 0.0171, "lr": 1.4112305124818647e-05, "epoch": 13.582285115303984, "percentage": 67.91, "elapsed_time": "1:39:09", "remaining_time": "0:46:50", "throughput": 2847.44, "total_tokens": 16939464} {"current_steps": 25920, "total_steps": 38160, "loss": 0.0339, "lr": 1.4102013292655242e-05, "epoch": 13.584905660377359, "percentage": 67.92, "elapsed_time": "1:39:10", "remaining_time": "0:46:49", "throughput": 2847.65, "total_tokens": 16943912} {"current_steps": 25925, "total_steps": 38160, "loss": 0.0486, "lr": 1.409172374022632e-05, "epoch": 13.587526205450734, "percentage": 67.94, "elapsed_time": "1:39:11", "remaining_time": "0:46:48", "throughput": 2847.68, "total_tokens": 16947464} {"current_steps": 25930, "total_steps": 38160, "loss": 0.0237, "lr": 1.4081436469684339e-05, "epoch": 13.59014675052411, "percentage": 67.95, "elapsed_time": "1:39:12", "remaining_time": "0:46:47", "throughput": 2847.68, "total_tokens": 16950504} {"current_steps": 25935, "total_steps": 38160, "loss": 0.0612, "lr": 1.4071151483181294e-05, "epoch": 13.592767295597485, "percentage": 67.96, "elapsed_time": "1:39:13", "remaining_time": "0:46:46", "throughput": 2847.69, "total_tokens": 16953672} {"current_steps": 25940, "total_steps": 38160, "loss": 0.0148, "lr": 1.4060868782868669e-05, "epoch": 13.59538784067086, "percentage": 67.98, "elapsed_time": "1:39:14", "remaining_time": "0:46:45", "throughput": 2847.67, "total_tokens": 16956520} {"current_steps": 25945, "total_steps": 38160, "loss": 0.0865, "lr": 1.405058837089749e-05, "epoch": 13.598008385744235, "percentage": 67.99, "elapsed_time": "1:39:15", "remaining_time": "0:46:43", "throughput": 2847.56, "total_tokens": 16958888} {"current_steps": 25950, "total_steps": 38160, "loss": 0.0294, "lr": 1.404031024941832e-05, "epoch": 13.60062893081761, "percentage": 68.0, "elapsed_time": "1:39:16", "remaining_time": "0:46:42", "throughput": 2847.61, "total_tokens": 16962216} {"current_steps": 25955, "total_steps": 38160, "loss": 0.047, "lr": 1.40300344205812e-05, "epoch": 13.603249475890985, "percentage": 68.02, "elapsed_time": "1:39:17", "remaining_time": "0:46:41", "throughput": 2847.73, "total_tokens": 16966152} {"current_steps": 25960, "total_steps": 38160, "loss": 0.0617, "lr": 1.4019760886535738e-05, "epoch": 13.60587002096436, "percentage": 68.03, "elapsed_time": "1:39:18", "remaining_time": "0:46:40", "throughput": 2847.71, "total_tokens": 16969096} {"current_steps": 25965, "total_steps": 38160, "loss": 0.0328, "lr": 1.4009489649431018e-05, "epoch": 13.608490566037736, "percentage": 68.04, "elapsed_time": "1:39:19", "remaining_time": "0:46:39", "throughput": 2847.6, "total_tokens": 16971592} {"current_steps": 25970, "total_steps": 38160, "loss": 0.0316, "lr": 1.3999220711415675e-05, "epoch": 13.61111111111111, "percentage": 68.06, "elapsed_time": "1:39:21", "remaining_time": "0:46:38", "throughput": 2847.48, "total_tokens": 16974056} {"current_steps": 25975, "total_steps": 38160, "loss": 0.0109, "lr": 1.3988954074637867e-05, "epoch": 13.613731656184486, "percentage": 68.07, "elapsed_time": "1:39:22", "remaining_time": "0:46:36", "throughput": 2847.3, "total_tokens": 16976008} {"current_steps": 25980, "total_steps": 38160, "loss": 0.0381, "lr": 1.3978689741245238e-05, "epoch": 13.616352201257861, "percentage": 68.08, "elapsed_time": "1:39:23", "remaining_time": "0:46:35", "throughput": 2847.27, "total_tokens": 16979080} {"current_steps": 25985, "total_steps": 38160, "loss": 0.0508, "lr": 1.3968427713384986e-05, "epoch": 13.618972746331236, "percentage": 68.09, "elapsed_time": "1:39:24", "remaining_time": "0:46:34", "throughput": 2847.3, "total_tokens": 16982216} {"current_steps": 25990, "total_steps": 38160, "loss": 0.0304, "lr": 1.3958167993203791e-05, "epoch": 13.621593291404611, "percentage": 68.11, "elapsed_time": "1:39:25", "remaining_time": "0:46:33", "throughput": 2847.31, "total_tokens": 16985288} {"current_steps": 25995, "total_steps": 38160, "loss": 0.015, "lr": 1.3947910582847879e-05, "epoch": 13.624213836477988, "percentage": 68.12, "elapsed_time": "1:39:26", "remaining_time": "0:46:32", "throughput": 2847.29, "total_tokens": 16988264} {"current_steps": 26000, "total_steps": 38160, "loss": 0.0358, "lr": 1.3937655484462985e-05, "epoch": 13.626834381551364, "percentage": 68.13, "elapsed_time": "1:39:27", "remaining_time": "0:46:30", "throughput": 2847.22, "total_tokens": 16990920} {"current_steps": 26005, "total_steps": 38160, "loss": 0.0702, "lr": 1.392740270019437e-05, "epoch": 13.629454926624739, "percentage": 68.15, "elapsed_time": "1:39:28", "remaining_time": "0:46:29", "throughput": 2847.18, "total_tokens": 16993768} {"current_steps": 26010, "total_steps": 38160, "loss": 0.0354, "lr": 1.3917152232186776e-05, "epoch": 13.632075471698114, "percentage": 68.16, "elapsed_time": "1:39:29", "remaining_time": "0:46:28", "throughput": 2847.13, "total_tokens": 16996584} {"current_steps": 26015, "total_steps": 38160, "loss": 0.0334, "lr": 1.3906904082584504e-05, "epoch": 13.634696016771489, "percentage": 68.17, "elapsed_time": "1:39:30", "remaining_time": "0:46:27", "throughput": 2847.21, "total_tokens": 17000040} {"current_steps": 26020, "total_steps": 38160, "loss": 0.0234, "lr": 1.3896658253531334e-05, "epoch": 13.637316561844864, "percentage": 68.19, "elapsed_time": "1:39:31", "remaining_time": "0:46:26", "throughput": 2847.13, "total_tokens": 17002696} {"current_steps": 26025, "total_steps": 38160, "loss": 0.0298, "lr": 1.3886414747170581e-05, "epoch": 13.63993710691824, "percentage": 68.2, "elapsed_time": "1:39:32", "remaining_time": "0:46:25", "throughput": 2847.15, "total_tokens": 17005992} {"current_steps": 26030, "total_steps": 38160, "loss": 0.0478, "lr": 1.3876173565645072e-05, "epoch": 13.642557651991615, "percentage": 68.21, "elapsed_time": "1:39:34", "remaining_time": "0:46:23", "throughput": 2847.14, "total_tokens": 17008904} {"current_steps": 26035, "total_steps": 38160, "loss": 0.0262, "lr": 1.3865934711097156e-05, "epoch": 13.64517819706499, "percentage": 68.23, "elapsed_time": "1:39:35", "remaining_time": "0:46:22", "throughput": 2847.11, "total_tokens": 17011880} {"current_steps": 26040, "total_steps": 38160, "loss": 0.0221, "lr": 1.3855698185668675e-05, "epoch": 13.647798742138365, "percentage": 68.24, "elapsed_time": "1:39:36", "remaining_time": "0:46:21", "throughput": 2847.13, "total_tokens": 17015208} {"current_steps": 26045, "total_steps": 38160, "loss": 0.0284, "lr": 1.3845463991500985e-05, "epoch": 13.65041928721174, "percentage": 68.25, "elapsed_time": "1:39:37", "remaining_time": "0:46:20", "throughput": 2847.2, "total_tokens": 17018664} {"current_steps": 26050, "total_steps": 38160, "loss": 0.0321, "lr": 1.3835232130734968e-05, "epoch": 13.653039832285115, "percentage": 68.27, "elapsed_time": "1:39:38", "remaining_time": "0:46:19", "throughput": 2847.25, "total_tokens": 17022280} {"current_steps": 26055, "total_steps": 38160, "loss": 0.0527, "lr": 1.3825002605511017e-05, "epoch": 13.65566037735849, "percentage": 68.28, "elapsed_time": "1:39:39", "remaining_time": "0:46:18", "throughput": 2847.36, "total_tokens": 17026344} {"current_steps": 26060, "total_steps": 38160, "loss": 0.0189, "lr": 1.3814775417969037e-05, "epoch": 13.658280922431866, "percentage": 68.29, "elapsed_time": "1:39:40", "remaining_time": "0:46:16", "throughput": 2847.41, "total_tokens": 17030024} {"current_steps": 26065, "total_steps": 38160, "loss": 0.051, "lr": 1.3804550570248431e-05, "epoch": 13.66090146750524, "percentage": 68.3, "elapsed_time": "1:39:42", "remaining_time": "0:46:15", "throughput": 2847.53, "total_tokens": 17033992} {"current_steps": 26070, "total_steps": 38160, "loss": 0.0409, "lr": 1.3794328064488116e-05, "epoch": 13.663522012578616, "percentage": 68.32, "elapsed_time": "1:39:44", "remaining_time": "0:46:15", "throughput": 2847.72, "total_tokens": 17040936} {"current_steps": 26075, "total_steps": 38160, "loss": 0.0219, "lr": 1.3784107902826523e-05, "epoch": 13.666142557651991, "percentage": 68.33, "elapsed_time": "1:39:45", "remaining_time": "0:46:13", "throughput": 2847.61, "total_tokens": 17043432} {"current_steps": 26080, "total_steps": 38160, "loss": 0.0391, "lr": 1.3773890087401603e-05, "epoch": 13.668763102725366, "percentage": 68.34, "elapsed_time": "1:39:46", "remaining_time": "0:46:12", "throughput": 2847.52, "total_tokens": 17046184} {"current_steps": 26085, "total_steps": 38160, "loss": 0.0351, "lr": 1.3763674620350802e-05, "epoch": 13.671383647798741, "percentage": 68.36, "elapsed_time": "1:39:47", "remaining_time": "0:46:11", "throughput": 2847.5, "total_tokens": 17049160} {"current_steps": 26090, "total_steps": 38160, "loss": 0.0423, "lr": 1.3753461503811089e-05, "epoch": 13.674004192872118, "percentage": 68.37, "elapsed_time": "1:39:48", "remaining_time": "0:46:10", "throughput": 2847.54, "total_tokens": 17052584} {"current_steps": 26095, "total_steps": 38160, "loss": 0.0453, "lr": 1.3743250739918922e-05, "epoch": 13.676624737945493, "percentage": 68.38, "elapsed_time": "1:39:49", "remaining_time": "0:46:09", "throughput": 2847.55, "total_tokens": 17055624} {"current_steps": 26100, "total_steps": 38160, "loss": 0.0434, "lr": 1.3733042330810265e-05, "epoch": 13.679245283018869, "percentage": 68.4, "elapsed_time": "1:39:50", "remaining_time": "0:46:08", "throughput": 2847.48, "total_tokens": 17058280} {"current_steps": 26105, "total_steps": 38160, "loss": 0.0328, "lr": 1.3722836278620616e-05, "epoch": 13.681865828092244, "percentage": 68.41, "elapsed_time": "1:39:51", "remaining_time": "0:46:06", "throughput": 2847.49, "total_tokens": 17061256} {"current_steps": 26110, "total_steps": 38160, "loss": 0.059, "lr": 1.3712632585484957e-05, "epoch": 13.684486373165619, "percentage": 68.42, "elapsed_time": "1:39:52", "remaining_time": "0:46:05", "throughput": 2847.61, "total_tokens": 17065160} {"current_steps": 26115, "total_steps": 38160, "loss": 0.0214, "lr": 1.37024312535378e-05, "epoch": 13.687106918238994, "percentage": 68.44, "elapsed_time": "1:39:53", "remaining_time": "0:46:04", "throughput": 2847.53, "total_tokens": 17067816} {"current_steps": 26120, "total_steps": 38160, "loss": 0.0383, "lr": 1.3692232284913133e-05, "epoch": 13.68972746331237, "percentage": 68.45, "elapsed_time": "1:39:54", "remaining_time": "0:46:03", "throughput": 2847.55, "total_tokens": 17070952} {"current_steps": 26125, "total_steps": 38160, "loss": 0.0192, "lr": 1.3682035681744459e-05, "epoch": 13.692348008385745, "percentage": 68.46, "elapsed_time": "1:39:56", "remaining_time": "0:46:02", "throughput": 2847.54, "total_tokens": 17073928} {"current_steps": 26130, "total_steps": 38160, "loss": 0.02, "lr": 1.3671841446164795e-05, "epoch": 13.69496855345912, "percentage": 68.47, "elapsed_time": "1:39:57", "remaining_time": "0:46:01", "throughput": 2847.55, "total_tokens": 17077192} {"current_steps": 26135, "total_steps": 38160, "loss": 0.0236, "lr": 1.3661649580306669e-05, "epoch": 13.697589098532495, "percentage": 68.49, "elapsed_time": "1:39:58", "remaining_time": "0:45:59", "throughput": 2847.56, "total_tokens": 17080360} {"current_steps": 26140, "total_steps": 38160, "loss": 0.0254, "lr": 1.3651460086302087e-05, "epoch": 13.70020964360587, "percentage": 68.5, "elapsed_time": "1:39:59", "remaining_time": "0:45:58", "throughput": 2847.52, "total_tokens": 17083304} {"current_steps": 26145, "total_steps": 38160, "loss": 0.0503, "lr": 1.3641272966282609e-05, "epoch": 13.702830188679245, "percentage": 68.51, "elapsed_time": "1:40:00", "remaining_time": "0:45:57", "throughput": 2847.6, "total_tokens": 17086952} {"current_steps": 26150, "total_steps": 38160, "loss": 0.0284, "lr": 1.3631088222379218e-05, "epoch": 13.70545073375262, "percentage": 68.53, "elapsed_time": "1:40:01", "remaining_time": "0:45:56", "throughput": 2847.77, "total_tokens": 17091656} {"current_steps": 26155, "total_steps": 38160, "loss": 0.0355, "lr": 1.3620905856722468e-05, "epoch": 13.708071278825996, "percentage": 68.54, "elapsed_time": "1:40:02", "remaining_time": "0:45:55", "throughput": 2847.79, "total_tokens": 17094888} {"current_steps": 26160, "total_steps": 38160, "loss": 0.0625, "lr": 1.3610725871442392e-05, "epoch": 13.71069182389937, "percentage": 68.55, "elapsed_time": "1:40:03", "remaining_time": "0:45:54", "throughput": 2847.91, "total_tokens": 17098856} {"current_steps": 26165, "total_steps": 38160, "loss": 0.0198, "lr": 1.3600548268668532e-05, "epoch": 13.713312368972746, "percentage": 68.57, "elapsed_time": "1:40:05", "remaining_time": "0:45:52", "throughput": 2847.92, "total_tokens": 17101992} {"current_steps": 26170, "total_steps": 38160, "loss": 0.0446, "lr": 1.3590373050529927e-05, "epoch": 13.715932914046121, "percentage": 68.58, "elapsed_time": "1:40:06", "remaining_time": "0:45:51", "throughput": 2847.82, "total_tokens": 17104520} {"current_steps": 26175, "total_steps": 38160, "loss": 0.1029, "lr": 1.3580200219155116e-05, "epoch": 13.718553459119496, "percentage": 68.59, "elapsed_time": "1:40:07", "remaining_time": "0:45:50", "throughput": 2847.84, "total_tokens": 17107944} {"current_steps": 26180, "total_steps": 38160, "loss": 0.0372, "lr": 1.3570029776672122e-05, "epoch": 13.721174004192871, "percentage": 68.61, "elapsed_time": "1:40:08", "remaining_time": "0:45:49", "throughput": 2847.86, "total_tokens": 17111016} {"current_steps": 26185, "total_steps": 38160, "loss": 0.0447, "lr": 1.35598617252085e-05, "epoch": 13.723794549266248, "percentage": 68.62, "elapsed_time": "1:40:09", "remaining_time": "0:45:48", "throughput": 2847.77, "total_tokens": 17113544} {"current_steps": 26190, "total_steps": 38160, "loss": 0.0285, "lr": 1.354969606689129e-05, "epoch": 13.726415094339622, "percentage": 68.63, "elapsed_time": "1:40:10", "remaining_time": "0:45:47", "throughput": 2847.7, "total_tokens": 17116168} {"current_steps": 26195, "total_steps": 38160, "loss": 0.0386, "lr": 1.353953280384704e-05, "epoch": 13.729035639412999, "percentage": 68.65, "elapsed_time": "1:40:11", "remaining_time": "0:45:45", "throughput": 2847.83, "total_tokens": 17120264} {"current_steps": 26200, "total_steps": 38160, "loss": 0.0309, "lr": 1.352937193820177e-05, "epoch": 13.731656184486374, "percentage": 68.66, "elapsed_time": "1:40:12", "remaining_time": "0:45:44", "throughput": 2847.78, "total_tokens": 17123080} {"current_steps": 26205, "total_steps": 38160, "loss": 0.0405, "lr": 1.3519213472081038e-05, "epoch": 13.734276729559749, "percentage": 68.67, "elapsed_time": "1:40:13", "remaining_time": "0:45:43", "throughput": 2847.73, "total_tokens": 17125960} {"current_steps": 26210, "total_steps": 38160, "loss": 0.0345, "lr": 1.3509057407609854e-05, "epoch": 13.736897274633124, "percentage": 68.68, "elapsed_time": "1:40:14", "remaining_time": "0:45:42", "throughput": 2847.81, "total_tokens": 17129544} {"current_steps": 26215, "total_steps": 38160, "loss": 0.0297, "lr": 1.3498903746912769e-05, "epoch": 13.7395178197065, "percentage": 68.7, "elapsed_time": "1:40:16", "remaining_time": "0:45:41", "throughput": 2847.92, "total_tokens": 17133384} {"current_steps": 26220, "total_steps": 38160, "loss": 0.0393, "lr": 1.3488752492113807e-05, "epoch": 13.742138364779874, "percentage": 68.71, "elapsed_time": "1:40:17", "remaining_time": "0:45:40", "throughput": 2847.84, "total_tokens": 17136008} {"current_steps": 26225, "total_steps": 38160, "loss": 0.0679, "lr": 1.3478603645336508e-05, "epoch": 13.74475890985325, "percentage": 68.72, "elapsed_time": "1:40:18", "remaining_time": "0:45:38", "throughput": 2847.85, "total_tokens": 17139144} {"current_steps": 26230, "total_steps": 38160, "loss": 0.022, "lr": 1.3468457208703877e-05, "epoch": 13.747379454926625, "percentage": 68.74, "elapsed_time": "1:40:19", "remaining_time": "0:45:37", "throughput": 2847.86, "total_tokens": 17142280} {"current_steps": 26235, "total_steps": 38160, "loss": 0.0655, "lr": 1.3458313184338437e-05, "epoch": 13.75, "percentage": 68.75, "elapsed_time": "1:40:20", "remaining_time": "0:45:36", "throughput": 2848.03, "total_tokens": 17146664} {"current_steps": 26240, "total_steps": 38160, "loss": 0.0442, "lr": 1.3448171574362201e-05, "epoch": 13.752620545073375, "percentage": 68.76, "elapsed_time": "1:40:21", "remaining_time": "0:45:35", "throughput": 2847.97, "total_tokens": 17149384} {"current_steps": 26245, "total_steps": 38160, "loss": 0.0538, "lr": 1.3438032380896681e-05, "epoch": 13.75524109014675, "percentage": 68.78, "elapsed_time": "1:40:22", "remaining_time": "0:45:34", "throughput": 2847.97, "total_tokens": 17152328} {"current_steps": 26250, "total_steps": 38160, "loss": 0.0222, "lr": 1.342789560606289e-05, "epoch": 13.757861635220126, "percentage": 68.79, "elapsed_time": "1:40:23", "remaining_time": "0:45:33", "throughput": 2848.0, "total_tokens": 17155624} {"current_steps": 26255, "total_steps": 38160, "loss": 0.0265, "lr": 1.341776125198131e-05, "epoch": 13.7604821802935, "percentage": 68.8, "elapsed_time": "1:40:24", "remaining_time": "0:45:31", "throughput": 2847.95, "total_tokens": 17158376} {"current_steps": 26260, "total_steps": 38160, "loss": 0.0422, "lr": 1.3407629320771948e-05, "epoch": 13.763102725366876, "percentage": 68.82, "elapsed_time": "1:40:25", "remaining_time": "0:45:30", "throughput": 2847.94, "total_tokens": 17161320} {"current_steps": 26265, "total_steps": 38160, "loss": 0.0258, "lr": 1.3397499814554266e-05, "epoch": 13.765723270440251, "percentage": 68.83, "elapsed_time": "1:40:27", "remaining_time": "0:45:29", "throughput": 2848.05, "total_tokens": 17165288} {"current_steps": 26270, "total_steps": 38160, "loss": 0.0295, "lr": 1.3387372735447256e-05, "epoch": 13.768343815513626, "percentage": 68.84, "elapsed_time": "1:40:28", "remaining_time": "0:45:28", "throughput": 2848.08, "total_tokens": 17168456} {"current_steps": 26275, "total_steps": 38160, "loss": 0.0315, "lr": 1.3377248085569399e-05, "epoch": 13.770964360587001, "percentage": 68.85, "elapsed_time": "1:40:29", "remaining_time": "0:45:27", "throughput": 2848.08, "total_tokens": 17171496} {"current_steps": 26280, "total_steps": 38160, "loss": 0.0291, "lr": 1.336712586703863e-05, "epoch": 13.773584905660378, "percentage": 68.87, "elapsed_time": "1:40:30", "remaining_time": "0:45:25", "throughput": 2848.13, "total_tokens": 17174824} {"current_steps": 26285, "total_steps": 38160, "loss": 0.0863, "lr": 1.3357006081972414e-05, "epoch": 13.776205450733752, "percentage": 68.88, "elapsed_time": "1:40:31", "remaining_time": "0:45:24", "throughput": 2848.0, "total_tokens": 17177064} {"current_steps": 26290, "total_steps": 38160, "loss": 0.0091, "lr": 1.3346888732487706e-05, "epoch": 13.778825995807129, "percentage": 68.89, "elapsed_time": "1:40:32", "remaining_time": "0:45:23", "throughput": 2847.94, "total_tokens": 17179752} {"current_steps": 26295, "total_steps": 38160, "loss": 0.0447, "lr": 1.3336773820700921e-05, "epoch": 13.781446540880504, "percentage": 68.91, "elapsed_time": "1:40:33", "remaining_time": "0:45:22", "throughput": 2848.08, "total_tokens": 17184232} {"current_steps": 26300, "total_steps": 38160, "loss": 0.0339, "lr": 1.3326661348727992e-05, "epoch": 13.784067085953879, "percentage": 68.92, "elapsed_time": "1:40:34", "remaining_time": "0:45:21", "throughput": 2848.13, "total_tokens": 17187624} {"current_steps": 26305, "total_steps": 38160, "loss": 0.0165, "lr": 1.3316551318684342e-05, "epoch": 13.786687631027254, "percentage": 68.93, "elapsed_time": "1:40:35", "remaining_time": "0:45:20", "throughput": 2848.05, "total_tokens": 17190088} {"current_steps": 26310, "total_steps": 38160, "loss": 0.0354, "lr": 1.3306443732684854e-05, "epoch": 13.78930817610063, "percentage": 68.95, "elapsed_time": "1:40:36", "remaining_time": "0:45:19", "throughput": 2848.17, "total_tokens": 17194216} {"current_steps": 26315, "total_steps": 38160, "loss": 0.0311, "lr": 1.3296338592843929e-05, "epoch": 13.791928721174004, "percentage": 68.96, "elapsed_time": "1:40:38", "remaining_time": "0:45:17", "throughput": 2848.21, "total_tokens": 17197544} {"current_steps": 26320, "total_steps": 38160, "loss": 0.0404, "lr": 1.3286235901275457e-05, "epoch": 13.79454926624738, "percentage": 68.97, "elapsed_time": "1:40:39", "remaining_time": "0:45:16", "throughput": 2848.18, "total_tokens": 17200488} {"current_steps": 26325, "total_steps": 38160, "loss": 0.0171, "lr": 1.327613566009279e-05, "epoch": 13.797169811320755, "percentage": 68.99, "elapsed_time": "1:40:40", "remaining_time": "0:45:15", "throughput": 2848.07, "total_tokens": 17202824} {"current_steps": 26330, "total_steps": 38160, "loss": 0.0192, "lr": 1.3266037871408798e-05, "epoch": 13.79979035639413, "percentage": 69.0, "elapsed_time": "1:40:41", "remaining_time": "0:45:14", "throughput": 2848.16, "total_tokens": 17206632} {"current_steps": 26335, "total_steps": 38160, "loss": 0.0213, "lr": 1.3255942537335805e-05, "epoch": 13.802410901467505, "percentage": 69.01, "elapsed_time": "1:40:43", "remaining_time": "0:45:13", "throughput": 2848.31, "total_tokens": 17212648} {"current_steps": 26340, "total_steps": 38160, "loss": 0.0175, "lr": 1.3245849659985652e-05, "epoch": 13.80503144654088, "percentage": 69.03, "elapsed_time": "1:40:44", "remaining_time": "0:45:12", "throughput": 2848.22, "total_tokens": 17215176} {"current_steps": 26345, "total_steps": 38160, "loss": 0.0146, "lr": 1.3235759241469658e-05, "epoch": 13.807651991614255, "percentage": 69.04, "elapsed_time": "1:40:45", "remaining_time": "0:45:11", "throughput": 2848.14, "total_tokens": 17217672} {"current_steps": 26350, "total_steps": 38160, "loss": 0.0306, "lr": 1.322567128389861e-05, "epoch": 13.81027253668763, "percentage": 69.05, "elapsed_time": "1:40:46", "remaining_time": "0:45:09", "throughput": 2848.17, "total_tokens": 17221096} {"current_steps": 26355, "total_steps": 38160, "loss": 0.0226, "lr": 1.3215585789382812e-05, "epoch": 13.812893081761006, "percentage": 69.06, "elapsed_time": "1:40:47", "remaining_time": "0:45:08", "throughput": 2848.08, "total_tokens": 17223784} {"current_steps": 26360, "total_steps": 38160, "loss": 0.0316, "lr": 1.320550276003201e-05, "epoch": 13.815513626834381, "percentage": 69.08, "elapsed_time": "1:40:48", "remaining_time": "0:45:07", "throughput": 2848.15, "total_tokens": 17227496} {"current_steps": 26365, "total_steps": 38160, "loss": 0.041, "lr": 1.3195422197955473e-05, "epoch": 13.818134171907756, "percentage": 69.09, "elapsed_time": "1:40:49", "remaining_time": "0:45:06", "throughput": 2848.15, "total_tokens": 17230728} {"current_steps": 26370, "total_steps": 38160, "loss": 0.0259, "lr": 1.3185344105261937e-05, "epoch": 13.820754716981131, "percentage": 69.1, "elapsed_time": "1:40:50", "remaining_time": "0:45:05", "throughput": 2848.15, "total_tokens": 17233800} {"current_steps": 26375, "total_steps": 38160, "loss": 0.0183, "lr": 1.3175268484059639e-05, "epoch": 13.823375262054507, "percentage": 69.12, "elapsed_time": "1:40:51", "remaining_time": "0:45:04", "throughput": 2848.13, "total_tokens": 17236744} {"current_steps": 26380, "total_steps": 38160, "loss": 0.0502, "lr": 1.316519533645626e-05, "epoch": 13.825995807127882, "percentage": 69.13, "elapsed_time": "1:40:53", "remaining_time": "0:45:03", "throughput": 2848.27, "total_tokens": 17241224} {"current_steps": 26385, "total_steps": 38160, "loss": 0.0289, "lr": 1.3155124664559004e-05, "epoch": 13.828616352201259, "percentage": 69.14, "elapsed_time": "1:40:54", "remaining_time": "0:45:01", "throughput": 2848.36, "total_tokens": 17244808} {"current_steps": 26390, "total_steps": 38160, "loss": 0.0346, "lr": 1.3145056470474525e-05, "epoch": 13.831236897274634, "percentage": 69.16, "elapsed_time": "1:40:55", "remaining_time": "0:45:00", "throughput": 2848.4, "total_tokens": 17248168} {"current_steps": 26395, "total_steps": 38160, "loss": 0.0321, "lr": 1.313499075630899e-05, "epoch": 13.833857442348009, "percentage": 69.17, "elapsed_time": "1:40:56", "remaining_time": "0:44:59", "throughput": 2848.47, "total_tokens": 17252136} {"current_steps": 26400, "total_steps": 38160, "loss": 0.0519, "lr": 1.312492752416802e-05, "epoch": 13.836477987421384, "percentage": 69.18, "elapsed_time": "1:40:57", "remaining_time": "0:44:58", "throughput": 2848.54, "total_tokens": 17255880} {"current_steps": 26405, "total_steps": 38160, "loss": 0.0235, "lr": 1.3114866776156748e-05, "epoch": 13.83909853249476, "percentage": 69.2, "elapsed_time": "1:40:58", "remaining_time": "0:44:57", "throughput": 2848.5, "total_tokens": 17258728} {"current_steps": 26410, "total_steps": 38160, "loss": 0.045, "lr": 1.3104808514379748e-05, "epoch": 13.841719077568134, "percentage": 69.21, "elapsed_time": "1:40:59", "remaining_time": "0:44:56", "throughput": 2848.53, "total_tokens": 17261992} {"current_steps": 26415, "total_steps": 38160, "loss": 0.0253, "lr": 1.3094752740941094e-05, "epoch": 13.84433962264151, "percentage": 69.22, "elapsed_time": "1:41:01", "remaining_time": "0:44:54", "throughput": 2848.64, "total_tokens": 17265896} {"current_steps": 26420, "total_steps": 38160, "loss": 0.0514, "lr": 1.3084699457944344e-05, "epoch": 13.846960167714885, "percentage": 69.23, "elapsed_time": "1:41:02", "remaining_time": "0:44:53", "throughput": 2848.67, "total_tokens": 17269032} {"current_steps": 26425, "total_steps": 38160, "loss": 0.051, "lr": 1.3074648667492528e-05, "epoch": 13.84958071278826, "percentage": 69.25, "elapsed_time": "1:41:03", "remaining_time": "0:44:52", "throughput": 2848.73, "total_tokens": 17272456} {"current_steps": 26430, "total_steps": 38160, "loss": 0.0381, "lr": 1.3064600371688171e-05, "epoch": 13.852201257861635, "percentage": 69.26, "elapsed_time": "1:41:04", "remaining_time": "0:44:51", "throughput": 2848.74, "total_tokens": 17275496} {"current_steps": 26435, "total_steps": 38160, "loss": 0.0185, "lr": 1.3054554572633249e-05, "epoch": 13.85482180293501, "percentage": 69.27, "elapsed_time": "1:41:05", "remaining_time": "0:44:50", "throughput": 2848.61, "total_tokens": 17277672} {"current_steps": 26440, "total_steps": 38160, "loss": 0.0504, "lr": 1.3044511272429222e-05, "epoch": 13.857442348008385, "percentage": 69.29, "elapsed_time": "1:41:06", "remaining_time": "0:44:49", "throughput": 2848.72, "total_tokens": 17281768} {"current_steps": 26445, "total_steps": 38160, "loss": 0.0361, "lr": 1.3034470473177038e-05, "epoch": 13.86006289308176, "percentage": 69.3, "elapsed_time": "1:41:07", "remaining_time": "0:44:47", "throughput": 2848.65, "total_tokens": 17284616} {"current_steps": 26450, "total_steps": 38160, "loss": 0.0541, "lr": 1.3024432176977125e-05, "epoch": 13.862683438155136, "percentage": 69.31, "elapsed_time": "1:41:08", "remaining_time": "0:44:46", "throughput": 2848.67, "total_tokens": 17287848} {"current_steps": 26455, "total_steps": 38160, "loss": 0.0355, "lr": 1.3014396385929372e-05, "epoch": 13.865303983228511, "percentage": 69.33, "elapsed_time": "1:41:10", "remaining_time": "0:44:45", "throughput": 2848.92, "total_tokens": 17294312} {"current_steps": 26460, "total_steps": 38160, "loss": 0.0368, "lr": 1.3004363102133165e-05, "epoch": 13.867924528301886, "percentage": 69.34, "elapsed_time": "1:41:11", "remaining_time": "0:44:44", "throughput": 2848.93, "total_tokens": 17297672} {"current_steps": 26465, "total_steps": 38160, "loss": 0.0291, "lr": 1.2994332327687348e-05, "epoch": 13.870545073375261, "percentage": 69.35, "elapsed_time": "1:41:12", "remaining_time": "0:44:43", "throughput": 2848.99, "total_tokens": 17301032} {"current_steps": 26470, "total_steps": 38160, "loss": 0.0284, "lr": 1.2984304064690228e-05, "epoch": 13.873165618448636, "percentage": 69.37, "elapsed_time": "1:41:13", "remaining_time": "0:44:42", "throughput": 2849.02, "total_tokens": 17304200} {"current_steps": 26475, "total_steps": 38160, "loss": 0.0285, "lr": 1.2974278315239619e-05, "epoch": 13.875786163522012, "percentage": 69.38, "elapsed_time": "1:41:14", "remaining_time": "0:44:41", "throughput": 2848.96, "total_tokens": 17307208} {"current_steps": 26480, "total_steps": 38160, "loss": 0.0214, "lr": 1.2964255081432786e-05, "epoch": 13.878406708595389, "percentage": 69.39, "elapsed_time": "1:41:16", "remaining_time": "0:44:40", "throughput": 2848.92, "total_tokens": 17310056} {"current_steps": 26485, "total_steps": 38160, "loss": 0.0413, "lr": 1.2954234365366488e-05, "epoch": 13.881027253668764, "percentage": 69.41, "elapsed_time": "1:41:17", "remaining_time": "0:44:38", "throughput": 2849.03, "total_tokens": 17313960} {"current_steps": 26490, "total_steps": 38160, "loss": 0.0229, "lr": 1.2944216169136936e-05, "epoch": 13.883647798742139, "percentage": 69.42, "elapsed_time": "1:41:18", "remaining_time": "0:44:37", "throughput": 2848.97, "total_tokens": 17316712} {"current_steps": 26495, "total_steps": 38160, "loss": 0.0299, "lr": 1.2934200494839815e-05, "epoch": 13.886268343815514, "percentage": 69.43, "elapsed_time": "1:41:19", "remaining_time": "0:44:36", "throughput": 2849.09, "total_tokens": 17321096} {"current_steps": 26500, "total_steps": 38160, "loss": 0.047, "lr": 1.2924187344570293e-05, "epoch": 13.88888888888889, "percentage": 69.44, "elapsed_time": "1:41:20", "remaining_time": "0:44:35", "throughput": 2849.1, "total_tokens": 17324168} {"current_steps": 26505, "total_steps": 38160, "loss": 0.0339, "lr": 1.2914176720423011e-05, "epoch": 13.891509433962264, "percentage": 69.46, "elapsed_time": "1:41:21", "remaining_time": "0:44:34", "throughput": 2849.07, "total_tokens": 17327016} {"current_steps": 26510, "total_steps": 38160, "loss": 0.0323, "lr": 1.2904168624492088e-05, "epoch": 13.89412997903564, "percentage": 69.47, "elapsed_time": "1:41:22", "remaining_time": "0:44:33", "throughput": 2849.01, "total_tokens": 17330088} {"current_steps": 26515, "total_steps": 38160, "loss": 0.0107, "lr": 1.2894163058871092e-05, "epoch": 13.896750524109015, "percentage": 69.48, "elapsed_time": "1:41:23", "remaining_time": "0:44:31", "throughput": 2848.89, "total_tokens": 17332328} {"current_steps": 26520, "total_steps": 38160, "loss": 0.0346, "lr": 1.2884160025653064e-05, "epoch": 13.89937106918239, "percentage": 69.5, "elapsed_time": "1:41:25", "remaining_time": "0:44:30", "throughput": 2849.06, "total_tokens": 17336584} {"current_steps": 26525, "total_steps": 38160, "loss": 0.0358, "lr": 1.2874159526930532e-05, "epoch": 13.901991614255765, "percentage": 69.51, "elapsed_time": "1:41:26", "remaining_time": "0:44:29", "throughput": 2849.01, "total_tokens": 17339240} {"current_steps": 26530, "total_steps": 38160, "loss": 0.0563, "lr": 1.286416156479549e-05, "epoch": 13.90461215932914, "percentage": 69.52, "elapsed_time": "1:41:27", "remaining_time": "0:44:28", "throughput": 2849.17, "total_tokens": 17343688} {"current_steps": 26535, "total_steps": 38160, "loss": 0.0382, "lr": 1.2854166141339394e-05, "epoch": 13.907232704402515, "percentage": 69.54, "elapsed_time": "1:41:28", "remaining_time": "0:44:27", "throughput": 2849.25, "total_tokens": 17347336} {"current_steps": 26540, "total_steps": 38160, "loss": 0.0258, "lr": 1.2844173258653183e-05, "epoch": 13.90985324947589, "percentage": 69.55, "elapsed_time": "1:41:29", "remaining_time": "0:44:26", "throughput": 2849.31, "total_tokens": 17350952} {"current_steps": 26545, "total_steps": 38160, "loss": 0.0465, "lr": 1.2834182918827247e-05, "epoch": 13.912473794549266, "percentage": 69.56, "elapsed_time": "1:41:30", "remaining_time": "0:44:24", "throughput": 2849.38, "total_tokens": 17354376} {"current_steps": 26550, "total_steps": 38160, "loss": 0.0373, "lr": 1.282419512395144e-05, "epoch": 13.915094339622641, "percentage": 69.58, "elapsed_time": "1:41:31", "remaining_time": "0:44:23", "throughput": 2849.47, "total_tokens": 17358216} {"current_steps": 26555, "total_steps": 38160, "loss": 0.0302, "lr": 1.2814209876115102e-05, "epoch": 13.917714884696016, "percentage": 69.59, "elapsed_time": "1:41:32", "remaining_time": "0:44:22", "throughput": 2849.45, "total_tokens": 17361224} {"current_steps": 26560, "total_steps": 38160, "loss": 0.0474, "lr": 1.2804227177407038e-05, "epoch": 13.920335429769391, "percentage": 69.6, "elapsed_time": "1:41:33", "remaining_time": "0:44:21", "throughput": 2849.47, "total_tokens": 17364488} {"current_steps": 26565, "total_steps": 38160, "loss": 0.0576, "lr": 1.279424702991552e-05, "epoch": 13.922955974842766, "percentage": 69.61, "elapsed_time": "1:41:35", "remaining_time": "0:44:20", "throughput": 2849.61, "total_tokens": 17368936} {"current_steps": 26570, "total_steps": 38160, "loss": 0.0433, "lr": 1.2784269435728264e-05, "epoch": 13.925576519916142, "percentage": 69.63, "elapsed_time": "1:41:36", "remaining_time": "0:44:19", "throughput": 2849.58, "total_tokens": 17371912} {"current_steps": 26575, "total_steps": 38160, "loss": 0.0252, "lr": 1.2774294396932488e-05, "epoch": 13.928197064989519, "percentage": 69.64, "elapsed_time": "1:41:37", "remaining_time": "0:44:18", "throughput": 2849.56, "total_tokens": 17374856} {"current_steps": 26580, "total_steps": 38160, "loss": 0.0183, "lr": 1.2764321915614835e-05, "epoch": 13.930817610062894, "percentage": 69.65, "elapsed_time": "1:41:38", "remaining_time": "0:44:16", "throughput": 2849.55, "total_tokens": 17377832} {"current_steps": 26585, "total_steps": 38160, "loss": 0.0302, "lr": 1.2754351993861444e-05, "epoch": 13.933438155136269, "percentage": 69.67, "elapsed_time": "1:41:39", "remaining_time": "0:44:15", "throughput": 2849.58, "total_tokens": 17381064} {"current_steps": 26590, "total_steps": 38160, "loss": 0.0277, "lr": 1.2744384633757922e-05, "epoch": 13.936058700209644, "percentage": 69.68, "elapsed_time": "1:41:40", "remaining_time": "0:44:14", "throughput": 2849.71, "total_tokens": 17384968} {"current_steps": 26595, "total_steps": 38160, "loss": 0.046, "lr": 1.2734419837389306e-05, "epoch": 13.93867924528302, "percentage": 69.69, "elapsed_time": "1:41:41", "remaining_time": "0:44:13", "throughput": 2849.73, "total_tokens": 17388104} {"current_steps": 26600, "total_steps": 38160, "loss": 0.0415, "lr": 1.2724457606840123e-05, "epoch": 13.941299790356394, "percentage": 69.71, "elapsed_time": "1:41:42", "remaining_time": "0:44:12", "throughput": 2849.76, "total_tokens": 17391880} {"current_steps": 26605, "total_steps": 38160, "loss": 0.0426, "lr": 1.2714497944194376e-05, "epoch": 13.94392033542977, "percentage": 69.72, "elapsed_time": "1:41:44", "remaining_time": "0:44:11", "throughput": 2849.77, "total_tokens": 17395240} {"current_steps": 26610, "total_steps": 38160, "loss": 0.0338, "lr": 1.2704540851535484e-05, "epoch": 13.946540880503145, "percentage": 69.73, "elapsed_time": "1:41:45", "remaining_time": "0:44:10", "throughput": 2849.95, "total_tokens": 17400680} {"current_steps": 26615, "total_steps": 38160, "loss": 0.0459, "lr": 1.2694586330946376e-05, "epoch": 13.94916142557652, "percentage": 69.75, "elapsed_time": "1:41:46", "remaining_time": "0:44:08", "throughput": 2849.83, "total_tokens": 17403080} {"current_steps": 26620, "total_steps": 38160, "loss": 0.0271, "lr": 1.2684634384509427e-05, "epoch": 13.951781970649895, "percentage": 69.76, "elapsed_time": "1:41:47", "remaining_time": "0:44:07", "throughput": 2849.9, "total_tokens": 17406600} {"current_steps": 26625, "total_steps": 38160, "loss": 0.0404, "lr": 1.2674685014306456e-05, "epoch": 13.95440251572327, "percentage": 69.77, "elapsed_time": "1:41:48", "remaining_time": "0:44:06", "throughput": 2849.8, "total_tokens": 17409320} {"current_steps": 26630, "total_steps": 38160, "loss": 0.0301, "lr": 1.2664738222418776e-05, "epoch": 13.957023060796645, "percentage": 69.79, "elapsed_time": "1:41:50", "remaining_time": "0:44:05", "throughput": 2849.84, "total_tokens": 17412616} {"current_steps": 26635, "total_steps": 38160, "loss": 0.0242, "lr": 1.2654794010927118e-05, "epoch": 13.95964360587002, "percentage": 69.8, "elapsed_time": "1:41:51", "remaining_time": "0:44:04", "throughput": 2849.85, "total_tokens": 17415912} {"current_steps": 26640, "total_steps": 38160, "loss": 0.0223, "lr": 1.2644852381911715e-05, "epoch": 13.962264150943396, "percentage": 69.81, "elapsed_time": "1:41:52", "remaining_time": "0:44:03", "throughput": 2849.9, "total_tokens": 17419656} {"current_steps": 26645, "total_steps": 38160, "loss": 0.0257, "lr": 1.2634913337452248e-05, "epoch": 13.964884696016771, "percentage": 69.82, "elapsed_time": "1:41:53", "remaining_time": "0:44:02", "throughput": 2849.74, "total_tokens": 17421768} {"current_steps": 26650, "total_steps": 38160, "loss": 0.0116, "lr": 1.2624976879627832e-05, "epoch": 13.967505241090146, "percentage": 69.84, "elapsed_time": "1:41:54", "remaining_time": "0:44:00", "throughput": 2849.73, "total_tokens": 17424968} {"current_steps": 26655, "total_steps": 38160, "loss": 0.0307, "lr": 1.2615043010517069e-05, "epoch": 13.970125786163521, "percentage": 69.85, "elapsed_time": "1:41:55", "remaining_time": "0:43:59", "throughput": 2849.72, "total_tokens": 17427912} {"current_steps": 26660, "total_steps": 38160, "loss": 0.0256, "lr": 1.2605111732198027e-05, "epoch": 13.972746331236896, "percentage": 69.86, "elapsed_time": "1:41:56", "remaining_time": "0:43:58", "throughput": 2849.73, "total_tokens": 17431272} {"current_steps": 26665, "total_steps": 38160, "loss": 0.0191, "lr": 1.2595183046748188e-05, "epoch": 13.975366876310272, "percentage": 69.88, "elapsed_time": "1:41:57", "remaining_time": "0:43:57", "throughput": 2849.8, "total_tokens": 17434728} {"current_steps": 26670, "total_steps": 38160, "loss": 0.0239, "lr": 1.2585256956244545e-05, "epoch": 13.977987421383649, "percentage": 69.89, "elapsed_time": "1:41:59", "remaining_time": "0:43:56", "throughput": 2849.82, "total_tokens": 17438216} {"current_steps": 26675, "total_steps": 38160, "loss": 0.0617, "lr": 1.2575333462763506e-05, "epoch": 13.980607966457024, "percentage": 69.9, "elapsed_time": "1:42:00", "remaining_time": "0:43:55", "throughput": 2849.84, "total_tokens": 17441384} {"current_steps": 26680, "total_steps": 38160, "loss": 0.0236, "lr": 1.2565412568380957e-05, "epoch": 13.983228511530399, "percentage": 69.92, "elapsed_time": "1:42:01", "remaining_time": "0:43:53", "throughput": 2849.77, "total_tokens": 17444168} {"current_steps": 26685, "total_steps": 38160, "loss": 0.0398, "lr": 1.2555494275172237e-05, "epoch": 13.985849056603774, "percentage": 69.93, "elapsed_time": "1:42:02", "remaining_time": "0:43:52", "throughput": 2849.87, "total_tokens": 17448168} {"current_steps": 26690, "total_steps": 38160, "loss": 0.039, "lr": 1.2545578585212148e-05, "epoch": 13.98846960167715, "percentage": 69.94, "elapsed_time": "1:42:03", "remaining_time": "0:43:51", "throughput": 2849.8, "total_tokens": 17450824} {"current_steps": 26695, "total_steps": 38160, "loss": 0.0218, "lr": 1.2535665500574922e-05, "epoch": 13.991090146750524, "percentage": 69.96, "elapsed_time": "1:42:04", "remaining_time": "0:43:50", "throughput": 2849.78, "total_tokens": 17453832} {"current_steps": 26700, "total_steps": 38160, "loss": 0.0283, "lr": 1.2525755023334285e-05, "epoch": 13.9937106918239, "percentage": 69.97, "elapsed_time": "1:42:05", "remaining_time": "0:43:49", "throughput": 2849.86, "total_tokens": 17457704} {"current_steps": 26705, "total_steps": 38160, "loss": 0.0437, "lr": 1.251584715556337e-05, "epoch": 13.996331236897275, "percentage": 69.98, "elapsed_time": "1:42:06", "remaining_time": "0:43:48", "throughput": 2849.84, "total_tokens": 17460680} {"current_steps": 26710, "total_steps": 38160, "loss": 0.0278, "lr": 1.2505941899334805e-05, "epoch": 13.99895178197065, "percentage": 69.99, "elapsed_time": "1:42:08", "remaining_time": "0:43:46", "throughput": 2849.86, "total_tokens": 17464072} {"current_steps": 26712, "total_steps": 38160, "eval_loss": 1.2786608934402466, "epoch": 14.0, "percentage": 70.0, "elapsed_time": "1:42:20", "remaining_time": "0:43:51", "throughput": 2844.25, "total_tokens": 17464792} {"current_steps": 26715, "total_steps": 38160, "loss": 0.0145, "lr": 1.2496039256720665e-05, "epoch": 14.001572327044025, "percentage": 70.01, "elapsed_time": "1:42:24", "remaining_time": "0:43:52", "throughput": 2842.61, "total_tokens": 17466744} {"current_steps": 26720, "total_steps": 38160, "loss": 0.0303, "lr": 1.2486139229792452e-05, "epoch": 14.0041928721174, "percentage": 70.02, "elapsed_time": "1:42:25", "remaining_time": "0:43:51", "throughput": 2842.59, "total_tokens": 17470072} {"current_steps": 26725, "total_steps": 38160, "loss": 0.0078, "lr": 1.2476241820621152e-05, "epoch": 14.006813417190775, "percentage": 70.03, "elapsed_time": "1:42:26", "remaining_time": "0:43:50", "throughput": 2842.65, "total_tokens": 17473432} {"current_steps": 26730, "total_steps": 38160, "loss": 0.0195, "lr": 1.2466347031277176e-05, "epoch": 14.00943396226415, "percentage": 70.05, "elapsed_time": "1:42:27", "remaining_time": "0:43:48", "throughput": 2842.65, "total_tokens": 17476568} {"current_steps": 26735, "total_steps": 38160, "loss": 0.0097, "lr": 1.2456454863830411e-05, "epoch": 14.012054507337526, "percentage": 70.06, "elapsed_time": "1:42:29", "remaining_time": "0:43:47", "throughput": 2842.63, "total_tokens": 17479608} {"current_steps": 26740, "total_steps": 38160, "loss": 0.0284, "lr": 1.2446565320350185e-05, "epoch": 14.014675052410901, "percentage": 70.07, "elapsed_time": "1:42:30", "remaining_time": "0:43:46", "throughput": 2842.65, "total_tokens": 17482904} {"current_steps": 26745, "total_steps": 38160, "loss": 0.0071, "lr": 1.2436678402905283e-05, "epoch": 14.017295597484276, "percentage": 70.09, "elapsed_time": "1:42:31", "remaining_time": "0:43:45", "throughput": 2842.51, "total_tokens": 17485432} {"current_steps": 26750, "total_steps": 38160, "loss": 0.0074, "lr": 1.2426794113563933e-05, "epoch": 14.019916142557651, "percentage": 70.1, "elapsed_time": "1:42:32", "remaining_time": "0:43:44", "throughput": 2842.4, "total_tokens": 17487864} {"current_steps": 26755, "total_steps": 38160, "loss": 0.0378, "lr": 1.24169124543938e-05, "epoch": 14.022536687631026, "percentage": 70.11, "elapsed_time": "1:42:33", "remaining_time": "0:43:43", "throughput": 2842.33, "total_tokens": 17490424} {"current_steps": 26760, "total_steps": 38160, "loss": 0.006, "lr": 1.2407033427462026e-05, "epoch": 14.025157232704403, "percentage": 70.13, "elapsed_time": "1:42:34", "remaining_time": "0:43:41", "throughput": 2842.22, "total_tokens": 17492888} {"current_steps": 26765, "total_steps": 38160, "loss": 0.0141, "lr": 1.2397157034835192e-05, "epoch": 14.027777777777779, "percentage": 70.14, "elapsed_time": "1:42:35", "remaining_time": "0:43:40", "throughput": 2842.14, "total_tokens": 17495448} {"current_steps": 26770, "total_steps": 38160, "loss": 0.0221, "lr": 1.2387283278579325e-05, "epoch": 14.030398322851154, "percentage": 70.15, "elapsed_time": "1:42:36", "remaining_time": "0:43:39", "throughput": 2842.23, "total_tokens": 17499160} {"current_steps": 26775, "total_steps": 38160, "loss": 0.0236, "lr": 1.237741216075991e-05, "epoch": 14.033018867924529, "percentage": 70.17, "elapsed_time": "1:42:37", "remaining_time": "0:43:38", "throughput": 2842.16, "total_tokens": 17501880} {"current_steps": 26780, "total_steps": 38160, "loss": 0.038, "lr": 1.2367543683441868e-05, "epoch": 14.035639412997904, "percentage": 70.18, "elapsed_time": "1:42:39", "remaining_time": "0:43:37", "throughput": 2842.12, "total_tokens": 17504696} {"current_steps": 26785, "total_steps": 38160, "loss": 0.0233, "lr": 1.2357677848689558e-05, "epoch": 14.03825995807128, "percentage": 70.19, "elapsed_time": "1:42:40", "remaining_time": "0:43:36", "throughput": 2842.11, "total_tokens": 17507672} {"current_steps": 26790, "total_steps": 38160, "loss": 0.0112, "lr": 1.2347814658566811e-05, "epoch": 14.040880503144654, "percentage": 70.2, "elapsed_time": "1:42:41", "remaining_time": "0:43:34", "throughput": 2842.06, "total_tokens": 17510296} {"current_steps": 26795, "total_steps": 38160, "loss": 0.0274, "lr": 1.2337954115136894e-05, "epoch": 14.04350104821803, "percentage": 70.22, "elapsed_time": "1:42:42", "remaining_time": "0:43:33", "throughput": 2842.0, "total_tokens": 17512920} {"current_steps": 26800, "total_steps": 38160, "loss": 0.0212, "lr": 1.2328096220462529e-05, "epoch": 14.046121593291405, "percentage": 70.23, "elapsed_time": "1:42:43", "remaining_time": "0:43:32", "throughput": 2842.1, "total_tokens": 17516888} {"current_steps": 26805, "total_steps": 38160, "loss": 0.0215, "lr": 1.2318240976605865e-05, "epoch": 14.04874213836478, "percentage": 70.24, "elapsed_time": "1:42:44", "remaining_time": "0:43:31", "throughput": 2842.17, "total_tokens": 17520792} {"current_steps": 26810, "total_steps": 38160, "loss": 0.0163, "lr": 1.23083883856285e-05, "epoch": 14.051362683438155, "percentage": 70.26, "elapsed_time": "1:42:45", "remaining_time": "0:43:30", "throughput": 2842.18, "total_tokens": 17523896} {"current_steps": 26815, "total_steps": 38160, "loss": 0.0222, "lr": 1.229853844959149e-05, "epoch": 14.05398322851153, "percentage": 70.27, "elapsed_time": "1:42:46", "remaining_time": "0:43:29", "throughput": 2842.23, "total_tokens": 17527352} {"current_steps": 26820, "total_steps": 38160, "loss": 0.0059, "lr": 1.228869117055533e-05, "epoch": 14.056603773584905, "percentage": 70.28, "elapsed_time": "1:42:47", "remaining_time": "0:43:27", "throughput": 2842.28, "total_tokens": 17530872} {"current_steps": 26825, "total_steps": 38160, "loss": 0.0368, "lr": 1.227884655057997e-05, "epoch": 14.05922431865828, "percentage": 70.3, "elapsed_time": "1:42:48", "remaining_time": "0:43:26", "throughput": 2842.22, "total_tokens": 17533528} {"current_steps": 26830, "total_steps": 38160, "loss": 0.0254, "lr": 1.2269004591724777e-05, "epoch": 14.061844863731656, "percentage": 70.31, "elapsed_time": "1:42:50", "remaining_time": "0:43:25", "throughput": 2842.36, "total_tokens": 17537368} {"current_steps": 26835, "total_steps": 38160, "loss": 0.0106, "lr": 1.2259165296048575e-05, "epoch": 14.064465408805031, "percentage": 70.32, "elapsed_time": "1:42:51", "remaining_time": "0:43:24", "throughput": 2842.44, "total_tokens": 17541080} {"current_steps": 26840, "total_steps": 38160, "loss": 0.0216, "lr": 1.2249328665609638e-05, "epoch": 14.067085953878406, "percentage": 70.34, "elapsed_time": "1:42:52", "remaining_time": "0:43:23", "throughput": 2842.5, "total_tokens": 17545112} {"current_steps": 26845, "total_steps": 38160, "loss": 0.0221, "lr": 1.2239494702465676e-05, "epoch": 14.069706498951781, "percentage": 70.35, "elapsed_time": "1:42:53", "remaining_time": "0:43:22", "throughput": 2842.48, "total_tokens": 17547960} {"current_steps": 26850, "total_steps": 38160, "loss": 0.0152, "lr": 1.2229663408673842e-05, "epoch": 14.072327044025156, "percentage": 70.36, "elapsed_time": "1:42:54", "remaining_time": "0:43:20", "throughput": 2842.52, "total_tokens": 17551416} {"current_steps": 26855, "total_steps": 38160, "loss": 0.0256, "lr": 1.221983478629074e-05, "epoch": 14.074947589098532, "percentage": 70.37, "elapsed_time": "1:42:55", "remaining_time": "0:43:19", "throughput": 2842.63, "total_tokens": 17555096} {"current_steps": 26860, "total_steps": 38160, "loss": 0.0363, "lr": 1.22100088373724e-05, "epoch": 14.077568134171909, "percentage": 70.39, "elapsed_time": "1:42:56", "remaining_time": "0:43:18", "throughput": 2842.77, "total_tokens": 17559448} {"current_steps": 26865, "total_steps": 38160, "loss": 0.0187, "lr": 1.2200185563974283e-05, "epoch": 14.080188679245284, "percentage": 70.4, "elapsed_time": "1:42:57", "remaining_time": "0:43:17", "throughput": 2842.78, "total_tokens": 17562584} {"current_steps": 26870, "total_steps": 38160, "loss": 0.0108, "lr": 1.219036496815132e-05, "epoch": 14.082809224318659, "percentage": 70.41, "elapsed_time": "1:42:59", "remaining_time": "0:43:16", "throughput": 2842.89, "total_tokens": 17566776} {"current_steps": 26875, "total_steps": 38160, "loss": 0.0233, "lr": 1.2180547051957863e-05, "epoch": 14.085429769392034, "percentage": 70.43, "elapsed_time": "1:43:00", "remaining_time": "0:43:15", "throughput": 2842.84, "total_tokens": 17569368} {"current_steps": 26880, "total_steps": 38160, "loss": 0.0124, "lr": 1.2170731817447723e-05, "epoch": 14.08805031446541, "percentage": 70.44, "elapsed_time": "1:43:01", "remaining_time": "0:43:13", "throughput": 2842.74, "total_tokens": 17571928} {"current_steps": 26885, "total_steps": 38160, "loss": 0.0097, "lr": 1.216091926667412e-05, "epoch": 14.090670859538784, "percentage": 70.45, "elapsed_time": "1:43:02", "remaining_time": "0:43:12", "throughput": 2842.65, "total_tokens": 17574392} {"current_steps": 26890, "total_steps": 38160, "loss": 0.0386, "lr": 1.2151109401689723e-05, "epoch": 14.09329140461216, "percentage": 70.47, "elapsed_time": "1:43:03", "remaining_time": "0:43:11", "throughput": 2842.72, "total_tokens": 17578104} {"current_steps": 26895, "total_steps": 38160, "loss": 0.0116, "lr": 1.214130222454665e-05, "epoch": 14.095911949685535, "percentage": 70.48, "elapsed_time": "1:43:04", "remaining_time": "0:43:10", "throughput": 2842.76, "total_tokens": 17581368} {"current_steps": 26900, "total_steps": 38160, "loss": 0.0103, "lr": 1.2131497737296452e-05, "epoch": 14.09853249475891, "percentage": 70.49, "elapsed_time": "1:43:05", "remaining_time": "0:43:09", "throughput": 2842.69, "total_tokens": 17584024} {"current_steps": 26905, "total_steps": 38160, "loss": 0.0068, "lr": 1.2121695941990124e-05, "epoch": 14.101153039832285, "percentage": 70.51, "elapsed_time": "1:43:06", "remaining_time": "0:43:08", "throughput": 2842.54, "total_tokens": 17586168} {"current_steps": 26910, "total_steps": 38160, "loss": 0.0203, "lr": 1.2111896840678075e-05, "epoch": 14.10377358490566, "percentage": 70.52, "elapsed_time": "1:43:08", "remaining_time": "0:43:07", "throughput": 2842.72, "total_tokens": 17591096} {"current_steps": 26915, "total_steps": 38160, "loss": 0.0191, "lr": 1.210210043541018e-05, "epoch": 14.106394129979035, "percentage": 70.53, "elapsed_time": "1:43:09", "remaining_time": "0:43:05", "throughput": 2842.73, "total_tokens": 17594264} {"current_steps": 26920, "total_steps": 38160, "loss": 0.0124, "lr": 1.2092306728235717e-05, "epoch": 14.10901467505241, "percentage": 70.55, "elapsed_time": "1:43:10", "remaining_time": "0:43:04", "throughput": 2842.81, "total_tokens": 17597944} {"current_steps": 26925, "total_steps": 38160, "loss": 0.0188, "lr": 1.2082515721203427e-05, "epoch": 14.111635220125786, "percentage": 70.56, "elapsed_time": "1:43:11", "remaining_time": "0:43:03", "throughput": 2842.78, "total_tokens": 17600728} {"current_steps": 26930, "total_steps": 38160, "loss": 0.0245, "lr": 1.2072727416361479e-05, "epoch": 14.114255765199161, "percentage": 70.57, "elapsed_time": "1:43:12", "remaining_time": "0:43:02", "throughput": 2842.74, "total_tokens": 17603576} {"current_steps": 26935, "total_steps": 38160, "loss": 0.0198, "lr": 1.2062941815757484e-05, "epoch": 14.116876310272536, "percentage": 70.58, "elapsed_time": "1:43:13", "remaining_time": "0:43:01", "throughput": 2842.7, "total_tokens": 17606392} {"current_steps": 26940, "total_steps": 38160, "loss": 0.0325, "lr": 1.2053158921438454e-05, "epoch": 14.119496855345911, "percentage": 70.6, "elapsed_time": "1:43:14", "remaining_time": "0:42:59", "throughput": 2842.76, "total_tokens": 17609944} {"current_steps": 26945, "total_steps": 38160, "loss": 0.0464, "lr": 1.2043378735450885e-05, "epoch": 14.122117400419286, "percentage": 70.61, "elapsed_time": "1:43:15", "remaining_time": "0:42:58", "throughput": 2842.95, "total_tokens": 17614424} {"current_steps": 26950, "total_steps": 38160, "loss": 0.0174, "lr": 1.2033601259840657e-05, "epoch": 14.124737945492662, "percentage": 70.62, "elapsed_time": "1:43:16", "remaining_time": "0:42:57", "throughput": 2842.94, "total_tokens": 17617368} {"current_steps": 26955, "total_steps": 38160, "loss": 0.0313, "lr": 1.2023826496653118e-05, "epoch": 14.127358490566039, "percentage": 70.64, "elapsed_time": "1:43:17", "remaining_time": "0:42:56", "throughput": 2843.02, "total_tokens": 17620792} {"current_steps": 26960, "total_steps": 38160, "loss": 0.016, "lr": 1.2014054447933044e-05, "epoch": 14.129979035639414, "percentage": 70.65, "elapsed_time": "1:43:18", "remaining_time": "0:42:55", "throughput": 2843.08, "total_tokens": 17624152} {"current_steps": 26965, "total_steps": 38160, "loss": 0.0066, "lr": 1.200428511572462e-05, "epoch": 14.132599580712789, "percentage": 70.66, "elapsed_time": "1:43:19", "remaining_time": "0:42:54", "throughput": 2843.08, "total_tokens": 17627064} {"current_steps": 26970, "total_steps": 38160, "loss": 0.0377, "lr": 1.1994518502071484e-05, "epoch": 14.135220125786164, "percentage": 70.68, "elapsed_time": "1:43:21", "remaining_time": "0:42:52", "throughput": 2843.03, "total_tokens": 17629720} {"current_steps": 26975, "total_steps": 38160, "loss": 0.02, "lr": 1.1984754609016716e-05, "epoch": 14.13784067085954, "percentage": 70.69, "elapsed_time": "1:43:22", "remaining_time": "0:42:51", "throughput": 2843.07, "total_tokens": 17633048} {"current_steps": 26980, "total_steps": 38160, "loss": 0.0698, "lr": 1.1974993438602785e-05, "epoch": 14.140461215932914, "percentage": 70.7, "elapsed_time": "1:43:23", "remaining_time": "0:42:50", "throughput": 2843.12, "total_tokens": 17636472} {"current_steps": 26985, "total_steps": 38160, "loss": 0.0375, "lr": 1.1965234992871641e-05, "epoch": 14.14308176100629, "percentage": 70.72, "elapsed_time": "1:43:24", "remaining_time": "0:42:49", "throughput": 2843.19, "total_tokens": 17640120} {"current_steps": 26990, "total_steps": 38160, "loss": 0.0522, "lr": 1.195547927386462e-05, "epoch": 14.145702306079665, "percentage": 70.73, "elapsed_time": "1:43:25", "remaining_time": "0:42:48", "throughput": 2843.28, "total_tokens": 17643704} {"current_steps": 26995, "total_steps": 38160, "loss": 0.0463, "lr": 1.1945726283622514e-05, "epoch": 14.14832285115304, "percentage": 70.74, "elapsed_time": "1:43:26", "remaining_time": "0:42:47", "throughput": 2843.26, "total_tokens": 17646968} {"current_steps": 27000, "total_steps": 38160, "loss": 0.013, "lr": 1.1935976024185547e-05, "epoch": 14.150943396226415, "percentage": 70.75, "elapsed_time": "1:43:27", "remaining_time": "0:42:45", "throughput": 2843.32, "total_tokens": 17650552} {"current_steps": 27005, "total_steps": 38160, "loss": 0.0314, "lr": 1.1926228497593341e-05, "epoch": 14.15356394129979, "percentage": 70.77, "elapsed_time": "1:43:28", "remaining_time": "0:42:44", "throughput": 2843.32, "total_tokens": 17653528} {"current_steps": 27010, "total_steps": 38160, "loss": 0.0174, "lr": 1.1916483705884985e-05, "epoch": 14.156184486373165, "percentage": 70.78, "elapsed_time": "1:43:29", "remaining_time": "0:42:43", "throughput": 2843.31, "total_tokens": 17656536} {"current_steps": 27015, "total_steps": 38160, "loss": 0.0344, "lr": 1.1906741651098983e-05, "epoch": 14.15880503144654, "percentage": 70.79, "elapsed_time": "1:43:31", "remaining_time": "0:42:42", "throughput": 2843.46, "total_tokens": 17662200} {"current_steps": 27020, "total_steps": 38160, "loss": 0.0254, "lr": 1.1897002335273239e-05, "epoch": 14.161425576519916, "percentage": 70.81, "elapsed_time": "1:43:32", "remaining_time": "0:42:41", "throughput": 2843.47, "total_tokens": 17665592} {"current_steps": 27025, "total_steps": 38160, "loss": 0.0158, "lr": 1.1887265760445121e-05, "epoch": 14.164046121593291, "percentage": 70.82, "elapsed_time": "1:43:33", "remaining_time": "0:42:40", "throughput": 2843.43, "total_tokens": 17668376} {"current_steps": 27030, "total_steps": 38160, "loss": 0.0151, "lr": 1.1877531928651417e-05, "epoch": 14.166666666666666, "percentage": 70.83, "elapsed_time": "1:43:35", "remaining_time": "0:42:39", "throughput": 2843.56, "total_tokens": 17672760} {"current_steps": 27035, "total_steps": 38160, "loss": 0.0225, "lr": 1.1867800841928313e-05, "epoch": 14.169287211740041, "percentage": 70.85, "elapsed_time": "1:43:36", "remaining_time": "0:42:37", "throughput": 2843.49, "total_tokens": 17675480} {"current_steps": 27040, "total_steps": 38160, "loss": 0.02, "lr": 1.1858072502311465e-05, "epoch": 14.171907756813416, "percentage": 70.86, "elapsed_time": "1:43:37", "remaining_time": "0:42:36", "throughput": 2843.46, "total_tokens": 17678360} {"current_steps": 27045, "total_steps": 38160, "loss": 0.0155, "lr": 1.1848346911835908e-05, "epoch": 14.174528301886792, "percentage": 70.87, "elapsed_time": "1:43:38", "remaining_time": "0:42:35", "throughput": 2843.55, "total_tokens": 17682040} {"current_steps": 27050, "total_steps": 38160, "loss": 0.0303, "lr": 1.1838624072536137e-05, "epoch": 14.177148846960169, "percentage": 70.89, "elapsed_time": "1:43:39", "remaining_time": "0:42:34", "throughput": 2843.61, "total_tokens": 17685432} {"current_steps": 27055, "total_steps": 38160, "loss": 0.0114, "lr": 1.1828903986446055e-05, "epoch": 14.179769392033544, "percentage": 70.9, "elapsed_time": "1:43:40", "remaining_time": "0:42:33", "throughput": 2843.63, "total_tokens": 17688728} {"current_steps": 27060, "total_steps": 38160, "loss": 0.0471, "lr": 1.1819186655599007e-05, "epoch": 14.182389937106919, "percentage": 70.91, "elapsed_time": "1:43:41", "remaining_time": "0:42:32", "throughput": 2843.68, "total_tokens": 17692216} {"current_steps": 27065, "total_steps": 38160, "loss": 0.0082, "lr": 1.1809472082027734e-05, "epoch": 14.185010482180294, "percentage": 70.93, "elapsed_time": "1:43:42", "remaining_time": "0:42:30", "throughput": 2843.79, "total_tokens": 17696184} {"current_steps": 27070, "total_steps": 38160, "loss": 0.0115, "lr": 1.1799760267764407e-05, "epoch": 14.18763102725367, "percentage": 70.94, "elapsed_time": "1:43:43", "remaining_time": "0:42:29", "throughput": 2843.74, "total_tokens": 17698808} {"current_steps": 27075, "total_steps": 38160, "loss": 0.022, "lr": 1.1790051214840634e-05, "epoch": 14.190251572327044, "percentage": 70.95, "elapsed_time": "1:43:44", "remaining_time": "0:42:28", "throughput": 2843.83, "total_tokens": 17702648} {"current_steps": 27080, "total_steps": 38160, "loss": 0.0135, "lr": 1.1780344925287443e-05, "epoch": 14.19287211740042, "percentage": 70.96, "elapsed_time": "1:43:45", "remaining_time": "0:42:27", "throughput": 2843.81, "total_tokens": 17705464} {"current_steps": 27085, "total_steps": 38160, "loss": 0.0141, "lr": 1.1770641401135282e-05, "epoch": 14.195492662473795, "percentage": 70.98, "elapsed_time": "1:43:46", "remaining_time": "0:42:26", "throughput": 2843.72, "total_tokens": 17707864} {"current_steps": 27090, "total_steps": 38160, "loss": 0.0325, "lr": 1.1760940644414003e-05, "epoch": 14.19811320754717, "percentage": 70.99, "elapsed_time": "1:43:48", "remaining_time": "0:42:25", "throughput": 2843.83, "total_tokens": 17711736} {"current_steps": 27095, "total_steps": 38160, "loss": 0.0084, "lr": 1.1751242657152914e-05, "epoch": 14.200733752620545, "percentage": 71.0, "elapsed_time": "1:43:49", "remaining_time": "0:42:23", "throughput": 2843.98, "total_tokens": 17715992} {"current_steps": 27100, "total_steps": 38160, "loss": 0.0071, "lr": 1.1741547441380698e-05, "epoch": 14.20335429769392, "percentage": 71.02, "elapsed_time": "1:43:50", "remaining_time": "0:42:22", "throughput": 2843.91, "total_tokens": 17718616} {"current_steps": 27105, "total_steps": 38160, "loss": 0.0238, "lr": 1.17318549991255e-05, "epoch": 14.205974842767295, "percentage": 71.03, "elapsed_time": "1:43:51", "remaining_time": "0:42:21", "throughput": 2843.97, "total_tokens": 17721880} {"current_steps": 27110, "total_steps": 38160, "loss": 0.0278, "lr": 1.1722165332414863e-05, "epoch": 14.20859538784067, "percentage": 71.04, "elapsed_time": "1:43:52", "remaining_time": "0:42:20", "throughput": 2843.9, "total_tokens": 17724376} {"current_steps": 27115, "total_steps": 38160, "loss": 0.0231, "lr": 1.1712478443275768e-05, "epoch": 14.211215932914046, "percentage": 71.06, "elapsed_time": "1:43:53", "remaining_time": "0:42:19", "throughput": 2843.88, "total_tokens": 17727448} {"current_steps": 27120, "total_steps": 38160, "loss": 0.0152, "lr": 1.170279433373459e-05, "epoch": 14.213836477987421, "percentage": 71.07, "elapsed_time": "1:43:54", "remaining_time": "0:42:17", "throughput": 2843.92, "total_tokens": 17730808} {"current_steps": 27125, "total_steps": 38160, "loss": 0.0197, "lr": 1.1693113005817125e-05, "epoch": 14.216457023060796, "percentage": 71.08, "elapsed_time": "1:43:55", "remaining_time": "0:42:16", "throughput": 2843.86, "total_tokens": 17733464} {"current_steps": 27130, "total_steps": 38160, "loss": 0.0136, "lr": 1.1683434461548606e-05, "epoch": 14.219077568134171, "percentage": 71.1, "elapsed_time": "1:43:56", "remaining_time": "0:42:15", "throughput": 2843.87, "total_tokens": 17736600} {"current_steps": 27135, "total_steps": 38160, "loss": 0.024, "lr": 1.1673758702953675e-05, "epoch": 14.221698113207546, "percentage": 71.11, "elapsed_time": "1:43:57", "remaining_time": "0:42:14", "throughput": 2843.86, "total_tokens": 17739608} {"current_steps": 27140, "total_steps": 38160, "loss": 0.0117, "lr": 1.1664085732056398e-05, "epoch": 14.224318658280922, "percentage": 71.12, "elapsed_time": "1:43:58", "remaining_time": "0:42:13", "throughput": 2843.88, "total_tokens": 17742840} {"current_steps": 27145, "total_steps": 38160, "loss": 0.0151, "lr": 1.1654415550880243e-05, "epoch": 14.226939203354299, "percentage": 71.13, "elapsed_time": "1:44:00", "remaining_time": "0:42:12", "throughput": 2843.69, "total_tokens": 17744824} {"current_steps": 27150, "total_steps": 38160, "loss": 0.0104, "lr": 1.1644748161448088e-05, "epoch": 14.229559748427674, "percentage": 71.15, "elapsed_time": "1:44:01", "remaining_time": "0:42:10", "throughput": 2843.62, "total_tokens": 17747544} {"current_steps": 27155, "total_steps": 38160, "loss": 0.0202, "lr": 1.1635083565782257e-05, "epoch": 14.232180293501049, "percentage": 71.16, "elapsed_time": "1:44:02", "remaining_time": "0:42:09", "throughput": 2843.64, "total_tokens": 17750840} {"current_steps": 27160, "total_steps": 38160, "loss": 0.0844, "lr": 1.1625421765904465e-05, "epoch": 14.234800838574424, "percentage": 71.17, "elapsed_time": "1:44:03", "remaining_time": "0:42:08", "throughput": 2843.57, "total_tokens": 17753432} {"current_steps": 27165, "total_steps": 38160, "loss": 0.0274, "lr": 1.1615762763835858e-05, "epoch": 14.2374213836478, "percentage": 71.19, "elapsed_time": "1:44:04", "remaining_time": "0:42:07", "throughput": 2843.58, "total_tokens": 17756536} {"current_steps": 27170, "total_steps": 38160, "loss": 0.0168, "lr": 1.1606106561596993e-05, "epoch": 14.240041928721174, "percentage": 71.2, "elapsed_time": "1:44:05", "remaining_time": "0:42:06", "throughput": 2843.59, "total_tokens": 17759896} {"current_steps": 27175, "total_steps": 38160, "loss": 0.04, "lr": 1.1596453161207829e-05, "epoch": 14.24266247379455, "percentage": 71.21, "elapsed_time": "1:44:06", "remaining_time": "0:42:05", "throughput": 2843.65, "total_tokens": 17763352} {"current_steps": 27180, "total_steps": 38160, "loss": 0.0108, "lr": 1.1586802564687741e-05, "epoch": 14.245283018867925, "percentage": 71.23, "elapsed_time": "1:44:07", "remaining_time": "0:42:03", "throughput": 2843.57, "total_tokens": 17765816} {"current_steps": 27185, "total_steps": 38160, "loss": 0.0062, "lr": 1.1577154774055528e-05, "epoch": 14.2479035639413, "percentage": 71.24, "elapsed_time": "1:44:08", "remaining_time": "0:42:02", "throughput": 2843.46, "total_tokens": 17768056} {"current_steps": 27190, "total_steps": 38160, "loss": 0.0113, "lr": 1.1567509791329401e-05, "epoch": 14.250524109014675, "percentage": 71.25, "elapsed_time": "1:44:09", "remaining_time": "0:42:01", "throughput": 2843.54, "total_tokens": 17771896} {"current_steps": 27195, "total_steps": 38160, "loss": 0.0155, "lr": 1.155786761852699e-05, "epoch": 14.25314465408805, "percentage": 71.27, "elapsed_time": "1:44:11", "remaining_time": "0:42:00", "throughput": 2843.56, "total_tokens": 17775096} {"current_steps": 27200, "total_steps": 38160, "loss": 0.014, "lr": 1.1548228257665317e-05, "epoch": 14.255765199161425, "percentage": 71.28, "elapsed_time": "1:44:12", "remaining_time": "0:41:59", "throughput": 2843.58, "total_tokens": 17778392} {"current_steps": 27205, "total_steps": 38160, "loss": 0.0087, "lr": 1.1538591710760815e-05, "epoch": 14.2583857442348, "percentage": 71.29, "elapsed_time": "1:44:13", "remaining_time": "0:41:58", "throughput": 2843.53, "total_tokens": 17781176} {"current_steps": 27210, "total_steps": 38160, "loss": 0.0727, "lr": 1.1528957979829355e-05, "epoch": 14.261006289308176, "percentage": 71.31, "elapsed_time": "1:44:14", "remaining_time": "0:41:56", "throughput": 2843.66, "total_tokens": 17785272} {"current_steps": 27215, "total_steps": 38160, "loss": 0.0361, "lr": 1.1519327066886198e-05, "epoch": 14.26362683438155, "percentage": 71.32, "elapsed_time": "1:44:15", "remaining_time": "0:41:55", "throughput": 2843.66, "total_tokens": 17788280} {"current_steps": 27220, "total_steps": 38160, "loss": 0.0178, "lr": 1.1509698973946032e-05, "epoch": 14.266247379454926, "percentage": 71.33, "elapsed_time": "1:44:16", "remaining_time": "0:41:54", "throughput": 2843.63, "total_tokens": 17791064} {"current_steps": 27225, "total_steps": 38160, "loss": 0.0066, "lr": 1.1500073703022926e-05, "epoch": 14.268867924528301, "percentage": 71.34, "elapsed_time": "1:44:17", "remaining_time": "0:41:53", "throughput": 2843.58, "total_tokens": 17793656} {"current_steps": 27230, "total_steps": 38160, "loss": 0.0134, "lr": 1.1490451256130394e-05, "epoch": 14.271488469601676, "percentage": 71.36, "elapsed_time": "1:44:18", "remaining_time": "0:41:52", "throughput": 2843.55, "total_tokens": 17796536} {"current_steps": 27235, "total_steps": 38160, "loss": 0.0316, "lr": 1.1480831635281328e-05, "epoch": 14.274109014675052, "percentage": 71.37, "elapsed_time": "1:44:19", "remaining_time": "0:41:51", "throughput": 2843.74, "total_tokens": 17801304} {"current_steps": 27240, "total_steps": 38160, "loss": 0.0304, "lr": 1.1471214842488046e-05, "epoch": 14.276729559748428, "percentage": 71.38, "elapsed_time": "1:44:20", "remaining_time": "0:41:49", "throughput": 2843.74, "total_tokens": 17804472} {"current_steps": 27245, "total_steps": 38160, "loss": 0.027, "lr": 1.1461600879762277e-05, "epoch": 14.279350104821804, "percentage": 71.4, "elapsed_time": "1:44:22", "remaining_time": "0:41:48", "throughput": 2843.75, "total_tokens": 17807928} {"current_steps": 27250, "total_steps": 38160, "loss": 0.0269, "lr": 1.1451989749115157e-05, "epoch": 14.281970649895179, "percentage": 71.41, "elapsed_time": "1:44:23", "remaining_time": "0:41:47", "throughput": 2843.71, "total_tokens": 17810680} {"current_steps": 27255, "total_steps": 38160, "loss": 0.0132, "lr": 1.1442381452557219e-05, "epoch": 14.284591194968554, "percentage": 71.42, "elapsed_time": "1:44:24", "remaining_time": "0:41:46", "throughput": 2843.72, "total_tokens": 17814008} {"current_steps": 27260, "total_steps": 38160, "loss": 0.0133, "lr": 1.1432775992098397e-05, "epoch": 14.28721174004193, "percentage": 71.44, "elapsed_time": "1:44:25", "remaining_time": "0:41:45", "throughput": 2843.63, "total_tokens": 17816440} {"current_steps": 27265, "total_steps": 38160, "loss": 0.0236, "lr": 1.1423173369748056e-05, "epoch": 14.289832285115304, "percentage": 71.45, "elapsed_time": "1:44:26", "remaining_time": "0:41:44", "throughput": 2843.6, "total_tokens": 17819256} {"current_steps": 27270, "total_steps": 38160, "loss": 0.0193, "lr": 1.1413573587514952e-05, "epoch": 14.29245283018868, "percentage": 71.46, "elapsed_time": "1:44:27", "remaining_time": "0:41:42", "throughput": 2843.56, "total_tokens": 17822232} {"current_steps": 27275, "total_steps": 38160, "loss": 0.0172, "lr": 1.140397664740726e-05, "epoch": 14.295073375262055, "percentage": 71.48, "elapsed_time": "1:44:28", "remaining_time": "0:41:41", "throughput": 2843.58, "total_tokens": 17825432} {"current_steps": 27280, "total_steps": 38160, "loss": 0.0502, "lr": 1.1394382551432534e-05, "epoch": 14.29769392033543, "percentage": 71.49, "elapsed_time": "1:44:29", "remaining_time": "0:41:40", "throughput": 2843.63, "total_tokens": 17828952} {"current_steps": 27285, "total_steps": 38160, "loss": 0.018, "lr": 1.1384791301597767e-05, "epoch": 14.300314465408805, "percentage": 71.5, "elapsed_time": "1:44:30", "remaining_time": "0:41:39", "throughput": 2843.58, "total_tokens": 17831672} {"current_steps": 27290, "total_steps": 38160, "loss": 0.033, "lr": 1.1375202899909317e-05, "epoch": 14.30293501048218, "percentage": 71.51, "elapsed_time": "1:44:31", "remaining_time": "0:41:38", "throughput": 2843.67, "total_tokens": 17835384} {"current_steps": 27295, "total_steps": 38160, "loss": 0.0272, "lr": 1.1365617348372984e-05, "epoch": 14.305555555555555, "percentage": 71.53, "elapsed_time": "1:44:33", "remaining_time": "0:41:37", "throughput": 2843.65, "total_tokens": 17838552} {"current_steps": 27300, "total_steps": 38160, "loss": 0.0221, "lr": 1.135603464899396e-05, "epoch": 14.30817610062893, "percentage": 71.54, "elapsed_time": "1:44:34", "remaining_time": "0:41:35", "throughput": 2843.57, "total_tokens": 17841080} {"current_steps": 27305, "total_steps": 38160, "loss": 0.0355, "lr": 1.1346454803776821e-05, "epoch": 14.310796645702306, "percentage": 71.55, "elapsed_time": "1:44:36", "remaining_time": "0:41:35", "throughput": 2843.69, "total_tokens": 17847224} {"current_steps": 27310, "total_steps": 38160, "loss": 0.016, "lr": 1.1336877814725566e-05, "epoch": 14.31341719077568, "percentage": 71.57, "elapsed_time": "1:44:37", "remaining_time": "0:41:33", "throughput": 2843.77, "total_tokens": 17850840} {"current_steps": 27315, "total_steps": 38160, "loss": 0.0333, "lr": 1.1327303683843607e-05, "epoch": 14.316037735849056, "percentage": 71.58, "elapsed_time": "1:44:38", "remaining_time": "0:41:32", "throughput": 2843.68, "total_tokens": 17853176} {"current_steps": 27320, "total_steps": 38160, "loss": 0.0199, "lr": 1.1317732413133723e-05, "epoch": 14.318658280922431, "percentage": 71.59, "elapsed_time": "1:44:39", "remaining_time": "0:41:31", "throughput": 2843.7, "total_tokens": 17856280} {"current_steps": 27325, "total_steps": 38160, "loss": 0.0297, "lr": 1.1308164004598118e-05, "epoch": 14.321278825995806, "percentage": 71.61, "elapsed_time": "1:44:40", "remaining_time": "0:41:30", "throughput": 2843.68, "total_tokens": 17859064} {"current_steps": 27330, "total_steps": 38160, "loss": 0.0479, "lr": 1.129859846023841e-05, "epoch": 14.323899371069182, "percentage": 71.62, "elapsed_time": "1:44:41", "remaining_time": "0:41:29", "throughput": 2843.66, "total_tokens": 17861880} {"current_steps": 27335, "total_steps": 38160, "loss": 0.0693, "lr": 1.1289035782055582e-05, "epoch": 14.326519916142558, "percentage": 71.63, "elapsed_time": "1:44:43", "remaining_time": "0:41:28", "throughput": 2843.86, "total_tokens": 17868120} {"current_steps": 27340, "total_steps": 38160, "loss": 0.1162, "lr": 1.1279475972050044e-05, "epoch": 14.329140461215934, "percentage": 71.65, "elapsed_time": "1:44:44", "remaining_time": "0:41:27", "throughput": 2843.95, "total_tokens": 17871896} {"current_steps": 27345, "total_steps": 38160, "loss": 0.0256, "lr": 1.1269919032221612e-05, "epoch": 14.331761006289309, "percentage": 71.66, "elapsed_time": "1:44:45", "remaining_time": "0:41:25", "throughput": 2844.05, "total_tokens": 17875512} {"current_steps": 27350, "total_steps": 38160, "loss": 0.0286, "lr": 1.1260364964569466e-05, "epoch": 14.334381551362684, "percentage": 71.67, "elapsed_time": "1:44:46", "remaining_time": "0:41:24", "throughput": 2844.12, "total_tokens": 17879000} {"current_steps": 27355, "total_steps": 38160, "loss": 0.0164, "lr": 1.125081377109223e-05, "epoch": 14.33700209643606, "percentage": 71.69, "elapsed_time": "1:44:47", "remaining_time": "0:41:23", "throughput": 2844.02, "total_tokens": 17881368} {"current_steps": 27360, "total_steps": 38160, "loss": 0.0756, "lr": 1.1241265453787882e-05, "epoch": 14.339622641509434, "percentage": 71.7, "elapsed_time": "1:44:48", "remaining_time": "0:41:22", "throughput": 2844.02, "total_tokens": 17884408} {"current_steps": 27365, "total_steps": 38160, "loss": 0.025, "lr": 1.1231720014653837e-05, "epoch": 14.34224318658281, "percentage": 71.71, "elapsed_time": "1:44:49", "remaining_time": "0:41:21", "throughput": 2844.0, "total_tokens": 17887224} {"current_steps": 27370, "total_steps": 38160, "loss": 0.014, "lr": 1.1222177455686896e-05, "epoch": 14.344863731656185, "percentage": 71.72, "elapsed_time": "1:44:50", "remaining_time": "0:41:19", "throughput": 2843.91, "total_tokens": 17889720} {"current_steps": 27375, "total_steps": 38160, "loss": 0.0101, "lr": 1.1212637778883237e-05, "epoch": 14.34748427672956, "percentage": 71.74, "elapsed_time": "1:44:51", "remaining_time": "0:41:18", "throughput": 2843.9, "total_tokens": 17892888} {"current_steps": 27380, "total_steps": 38160, "loss": 0.0213, "lr": 1.1203100986238468e-05, "epoch": 14.350104821802935, "percentage": 71.75, "elapsed_time": "1:44:52", "remaining_time": "0:41:17", "throughput": 2843.92, "total_tokens": 17896056} {"current_steps": 27385, "total_steps": 38160, "loss": 0.0067, "lr": 1.1193567079747561e-05, "epoch": 14.35272536687631, "percentage": 71.76, "elapsed_time": "1:44:53", "remaining_time": "0:41:16", "throughput": 2843.85, "total_tokens": 17898840} {"current_steps": 27390, "total_steps": 38160, "loss": 0.0161, "lr": 1.1184036061404907e-05, "epoch": 14.355345911949685, "percentage": 71.78, "elapsed_time": "1:44:54", "remaining_time": "0:41:15", "throughput": 2843.82, "total_tokens": 17901560} {"current_steps": 27395, "total_steps": 38160, "loss": 0.0126, "lr": 1.117450793320429e-05, "epoch": 14.35796645702306, "percentage": 71.79, "elapsed_time": "1:44:55", "remaining_time": "0:41:14", "throughput": 2843.95, "total_tokens": 17905432} {"current_steps": 27400, "total_steps": 38160, "loss": 0.0615, "lr": 1.1164982697138893e-05, "epoch": 14.360587002096436, "percentage": 71.8, "elapsed_time": "1:44:57", "remaining_time": "0:41:12", "throughput": 2843.91, "total_tokens": 17908088} {"current_steps": 27405, "total_steps": 38160, "loss": 0.0167, "lr": 1.1155460355201267e-05, "epoch": 14.36320754716981, "percentage": 71.82, "elapsed_time": "1:44:58", "remaining_time": "0:41:11", "throughput": 2843.83, "total_tokens": 17910616} {"current_steps": 27410, "total_steps": 38160, "loss": 0.0192, "lr": 1.1145940909383399e-05, "epoch": 14.365828092243186, "percentage": 71.83, "elapsed_time": "1:44:59", "remaining_time": "0:41:10", "throughput": 2843.77, "total_tokens": 17913400} {"current_steps": 27415, "total_steps": 38160, "loss": 0.0276, "lr": 1.1136424361676626e-05, "epoch": 14.368448637316561, "percentage": 71.84, "elapsed_time": "1:45:00", "remaining_time": "0:41:09", "throughput": 2843.76, "total_tokens": 17916600} {"current_steps": 27420, "total_steps": 38160, "loss": 0.0225, "lr": 1.1126910714071711e-05, "epoch": 14.371069182389936, "percentage": 71.86, "elapsed_time": "1:45:01", "remaining_time": "0:41:08", "throughput": 2843.68, "total_tokens": 17919160} {"current_steps": 27425, "total_steps": 38160, "loss": 0.0173, "lr": 1.1117399968558806e-05, "epoch": 14.373689727463312, "percentage": 71.87, "elapsed_time": "1:45:02", "remaining_time": "0:41:06", "throughput": 2843.65, "total_tokens": 17921912} {"current_steps": 27430, "total_steps": 38160, "loss": 0.0251, "lr": 1.1107892127127454e-05, "epoch": 14.376310272536688, "percentage": 71.88, "elapsed_time": "1:45:03", "remaining_time": "0:41:05", "throughput": 2843.77, "total_tokens": 17926040} {"current_steps": 27435, "total_steps": 38160, "loss": 0.0306, "lr": 1.109838719176658e-05, "epoch": 14.378930817610064, "percentage": 71.89, "elapsed_time": "1:45:04", "remaining_time": "0:41:04", "throughput": 2843.87, "total_tokens": 17929656} {"current_steps": 27440, "total_steps": 38160, "loss": 0.0126, "lr": 1.1088885164464497e-05, "epoch": 14.381551362683439, "percentage": 71.91, "elapsed_time": "1:45:06", "remaining_time": "0:41:03", "throughput": 2844.03, "total_tokens": 17935704} {"current_steps": 27445, "total_steps": 38160, "loss": 0.0101, "lr": 1.1079386047208932e-05, "epoch": 14.384171907756814, "percentage": 71.92, "elapsed_time": "1:45:07", "remaining_time": "0:41:02", "throughput": 2843.97, "total_tokens": 17938328} {"current_steps": 27450, "total_steps": 38160, "loss": 0.0199, "lr": 1.1069889841986991e-05, "epoch": 14.38679245283019, "percentage": 71.93, "elapsed_time": "1:45:08", "remaining_time": "0:41:01", "throughput": 2843.94, "total_tokens": 17941240} {"current_steps": 27455, "total_steps": 38160, "loss": 0.0348, "lr": 1.1060396550785182e-05, "epoch": 14.389412997903564, "percentage": 71.95, "elapsed_time": "1:45:09", "remaining_time": "0:41:00", "throughput": 2844.02, "total_tokens": 17944728} {"current_steps": 27460, "total_steps": 38160, "loss": 0.0207, "lr": 1.1050906175589382e-05, "epoch": 14.39203354297694, "percentage": 71.96, "elapsed_time": "1:45:10", "remaining_time": "0:40:59", "throughput": 2844.15, "total_tokens": 17948536} {"current_steps": 27465, "total_steps": 38160, "loss": 0.0181, "lr": 1.1041418718384863e-05, "epoch": 14.394654088050315, "percentage": 71.97, "elapsed_time": "1:45:11", "remaining_time": "0:40:57", "throughput": 2844.13, "total_tokens": 17951448} {"current_steps": 27470, "total_steps": 38160, "loss": 0.0108, "lr": 1.1031934181156298e-05, "epoch": 14.39727463312369, "percentage": 71.99, "elapsed_time": "1:45:12", "remaining_time": "0:40:56", "throughput": 2844.17, "total_tokens": 17954776} {"current_steps": 27475, "total_steps": 38160, "loss": 0.0172, "lr": 1.1022452565887747e-05, "epoch": 14.399895178197065, "percentage": 72.0, "elapsed_time": "1:45:13", "remaining_time": "0:40:55", "throughput": 2844.28, "total_tokens": 17958712} {"current_steps": 27480, "total_steps": 38160, "loss": 0.022, "lr": 1.1012973874562657e-05, "epoch": 14.40251572327044, "percentage": 72.01, "elapsed_time": "1:45:15", "remaining_time": "0:40:54", "throughput": 2844.24, "total_tokens": 17961464} {"current_steps": 27485, "total_steps": 38160, "loss": 0.018, "lr": 1.1003498109163865e-05, "epoch": 14.405136268343815, "percentage": 72.03, "elapsed_time": "1:45:16", "remaining_time": "0:40:53", "throughput": 2844.32, "total_tokens": 17965176} {"current_steps": 27490, "total_steps": 38160, "loss": 0.0199, "lr": 1.0994025271673592e-05, "epoch": 14.40775681341719, "percentage": 72.04, "elapsed_time": "1:45:17", "remaining_time": "0:40:52", "throughput": 2844.33, "total_tokens": 17968440} {"current_steps": 27495, "total_steps": 38160, "loss": 0.0123, "lr": 1.0984555364073431e-05, "epoch": 14.410377358490566, "percentage": 72.05, "elapsed_time": "1:45:18", "remaining_time": "0:40:50", "throughput": 2844.31, "total_tokens": 17971416} {"current_steps": 27500, "total_steps": 38160, "loss": 0.023, "lr": 1.0975088388344393e-05, "epoch": 14.41299790356394, "percentage": 72.06, "elapsed_time": "1:45:19", "remaining_time": "0:40:49", "throughput": 2844.28, "total_tokens": 17974360} {"current_steps": 27505, "total_steps": 38160, "loss": 0.0256, "lr": 1.096562434646686e-05, "epoch": 14.415618448637316, "percentage": 72.08, "elapsed_time": "1:45:20", "remaining_time": "0:40:48", "throughput": 2844.33, "total_tokens": 17977912} {"current_steps": 27510, "total_steps": 38160, "loss": 0.0138, "lr": 1.0956163240420611e-05, "epoch": 14.418238993710691, "percentage": 72.09, "elapsed_time": "1:45:21", "remaining_time": "0:40:47", "throughput": 2844.31, "total_tokens": 17980792} {"current_steps": 27515, "total_steps": 38160, "loss": 0.0093, "lr": 1.094670507218479e-05, "epoch": 14.420859538784066, "percentage": 72.1, "elapsed_time": "1:45:22", "remaining_time": "0:40:46", "throughput": 2844.25, "total_tokens": 17983416} {"current_steps": 27520, "total_steps": 38160, "loss": 0.0103, "lr": 1.093724984373793e-05, "epoch": 14.423480083857442, "percentage": 72.12, "elapsed_time": "1:45:23", "remaining_time": "0:40:44", "throughput": 2844.24, "total_tokens": 17986328} {"current_steps": 27525, "total_steps": 38160, "loss": 0.0164, "lr": 1.0927797557057968e-05, "epoch": 14.426100628930818, "percentage": 72.13, "elapsed_time": "1:45:24", "remaining_time": "0:40:43", "throughput": 2844.37, "total_tokens": 17990584} {"current_steps": 27530, "total_steps": 38160, "loss": 0.0144, "lr": 1.0918348214122209e-05, "epoch": 14.428721174004194, "percentage": 72.14, "elapsed_time": "1:45:26", "remaining_time": "0:40:42", "throughput": 2844.4, "total_tokens": 17993848} {"current_steps": 27535, "total_steps": 38160, "loss": 0.025, "lr": 1.0908901816907366e-05, "epoch": 14.431341719077569, "percentage": 72.16, "elapsed_time": "1:45:27", "remaining_time": "0:40:41", "throughput": 2844.46, "total_tokens": 17997208} {"current_steps": 27540, "total_steps": 38160, "loss": 0.0091, "lr": 1.08994583673895e-05, "epoch": 14.433962264150944, "percentage": 72.17, "elapsed_time": "1:45:28", "remaining_time": "0:40:40", "throughput": 2844.43, "total_tokens": 18000056} {"current_steps": 27545, "total_steps": 38160, "loss": 0.0495, "lr": 1.0890017867544068e-05, "epoch": 14.43658280922432, "percentage": 72.18, "elapsed_time": "1:45:29", "remaining_time": "0:40:39", "throughput": 2844.43, "total_tokens": 18002968} {"current_steps": 27550, "total_steps": 38160, "loss": 0.0118, "lr": 1.088058031934592e-05, "epoch": 14.439203354297694, "percentage": 72.2, "elapsed_time": "1:45:30", "remaining_time": "0:40:37", "throughput": 2844.45, "total_tokens": 18006104} {"current_steps": 27555, "total_steps": 38160, "loss": 0.0901, "lr": 1.087114572476929e-05, "epoch": 14.44182389937107, "percentage": 72.21, "elapsed_time": "1:45:31", "remaining_time": "0:40:36", "throughput": 2844.55, "total_tokens": 18010040} {"current_steps": 27560, "total_steps": 38160, "loss": 0.0204, "lr": 1.0861714085787783e-05, "epoch": 14.444444444444445, "percentage": 72.22, "elapsed_time": "1:45:32", "remaining_time": "0:40:35", "throughput": 2844.6, "total_tokens": 18013720} {"current_steps": 27565, "total_steps": 38160, "loss": 0.0126, "lr": 1.0852285404374402e-05, "epoch": 14.44706498951782, "percentage": 72.24, "elapsed_time": "1:45:33", "remaining_time": "0:40:34", "throughput": 2844.61, "total_tokens": 18016696} {"current_steps": 27570, "total_steps": 38160, "loss": 0.0995, "lr": 1.0842859682501505e-05, "epoch": 14.449685534591195, "percentage": 72.25, "elapsed_time": "1:45:34", "remaining_time": "0:40:33", "throughput": 2844.65, "total_tokens": 18020024} {"current_steps": 27575, "total_steps": 38160, "loss": 0.0276, "lr": 1.0833436922140841e-05, "epoch": 14.45230607966457, "percentage": 72.26, "elapsed_time": "1:45:35", "remaining_time": "0:40:32", "throughput": 2844.69, "total_tokens": 18023352} {"current_steps": 27580, "total_steps": 38160, "loss": 0.0178, "lr": 1.0824017125263555e-05, "epoch": 14.454926624737945, "percentage": 72.27, "elapsed_time": "1:45:36", "remaining_time": "0:40:30", "throughput": 2844.71, "total_tokens": 18026648} {"current_steps": 27585, "total_steps": 38160, "loss": 0.0268, "lr": 1.0814600293840154e-05, "epoch": 14.45754716981132, "percentage": 72.29, "elapsed_time": "1:45:37", "remaining_time": "0:40:29", "throughput": 2844.7, "total_tokens": 18029624} {"current_steps": 27590, "total_steps": 38160, "loss": 0.0609, "lr": 1.080518642984055e-05, "epoch": 14.460167714884696, "percentage": 72.3, "elapsed_time": "1:45:39", "remaining_time": "0:40:28", "throughput": 2844.64, "total_tokens": 18032376} {"current_steps": 27595, "total_steps": 38160, "loss": 0.03, "lr": 1.0795775535233988e-05, "epoch": 14.46278825995807, "percentage": 72.31, "elapsed_time": "1:45:40", "remaining_time": "0:40:27", "throughput": 2844.62, "total_tokens": 18035448} {"current_steps": 27600, "total_steps": 38160, "loss": 0.0165, "lr": 1.0786367611989145e-05, "epoch": 14.465408805031446, "percentage": 72.33, "elapsed_time": "1:45:41", "remaining_time": "0:40:26", "throughput": 2844.7, "total_tokens": 18039576} {"current_steps": 27605, "total_steps": 38160, "loss": 0.013, "lr": 1.0776962662074031e-05, "epoch": 14.468029350104821, "percentage": 72.34, "elapsed_time": "1:45:42", "remaining_time": "0:40:25", "throughput": 2844.87, "total_tokens": 18044952} {"current_steps": 27610, "total_steps": 38160, "loss": 0.029, "lr": 1.0767560687456062e-05, "epoch": 14.470649895178196, "percentage": 72.35, "elapsed_time": "1:45:44", "remaining_time": "0:40:24", "throughput": 2844.94, "total_tokens": 18048472} {"current_steps": 27615, "total_steps": 38160, "loss": 0.0118, "lr": 1.0758161690102036e-05, "epoch": 14.473270440251572, "percentage": 72.37, "elapsed_time": "1:45:45", "remaining_time": "0:40:22", "throughput": 2845.0, "total_tokens": 18052088} {"current_steps": 27620, "total_steps": 38160, "loss": 0.0236, "lr": 1.0748765671978095e-05, "epoch": 14.475890985324948, "percentage": 72.38, "elapsed_time": "1:45:46", "remaining_time": "0:40:21", "throughput": 2844.96, "total_tokens": 18055000} {"current_steps": 27625, "total_steps": 38160, "loss": 0.0184, "lr": 1.0739372635049797e-05, "epoch": 14.478511530398324, "percentage": 72.39, "elapsed_time": "1:45:47", "remaining_time": "0:40:20", "throughput": 2845.04, "total_tokens": 18058712} {"current_steps": 27630, "total_steps": 38160, "loss": 0.0061, "lr": 1.0729982581282042e-05, "epoch": 14.481132075471699, "percentage": 72.41, "elapsed_time": "1:45:48", "remaining_time": "0:40:19", "throughput": 2845.14, "total_tokens": 18062616} {"current_steps": 27635, "total_steps": 38160, "loss": 0.0147, "lr": 1.0720595512639129e-05, "epoch": 14.483752620545074, "percentage": 72.42, "elapsed_time": "1:45:49", "remaining_time": "0:40:18", "throughput": 2845.25, "total_tokens": 18066360} {"current_steps": 27640, "total_steps": 38160, "loss": 0.0108, "lr": 1.0711211431084728e-05, "epoch": 14.48637316561845, "percentage": 72.43, "elapsed_time": "1:45:50", "remaining_time": "0:40:17", "throughput": 2845.33, "total_tokens": 18069848} {"current_steps": 27645, "total_steps": 38160, "loss": 0.0199, "lr": 1.0701830338581887e-05, "epoch": 14.488993710691824, "percentage": 72.44, "elapsed_time": "1:45:51", "remaining_time": "0:40:15", "throughput": 2845.25, "total_tokens": 18072504} {"current_steps": 27650, "total_steps": 38160, "loss": 0.0284, "lr": 1.069245223709301e-05, "epoch": 14.4916142557652, "percentage": 72.46, "elapsed_time": "1:45:52", "remaining_time": "0:40:14", "throughput": 2845.3, "total_tokens": 18075960} {"current_steps": 27655, "total_steps": 38160, "loss": 0.0247, "lr": 1.0683077128579904e-05, "epoch": 14.494234800838575, "percentage": 72.47, "elapsed_time": "1:45:54", "remaining_time": "0:40:13", "throughput": 2845.39, "total_tokens": 18079608} {"current_steps": 27660, "total_steps": 38160, "loss": 0.0237, "lr": 1.0673705015003718e-05, "epoch": 14.49685534591195, "percentage": 72.48, "elapsed_time": "1:45:55", "remaining_time": "0:40:12", "throughput": 2845.33, "total_tokens": 18082232} {"current_steps": 27665, "total_steps": 38160, "loss": 0.013, "lr": 1.0664335898325002e-05, "epoch": 14.499475890985325, "percentage": 72.5, "elapsed_time": "1:45:56", "remaining_time": "0:40:11", "throughput": 2845.35, "total_tokens": 18085432} {"current_steps": 27670, "total_steps": 38160, "loss": 0.0143, "lr": 1.065496978050367e-05, "epoch": 14.5020964360587, "percentage": 72.51, "elapsed_time": "1:45:57", "remaining_time": "0:40:10", "throughput": 2845.46, "total_tokens": 18089176} {"current_steps": 27675, "total_steps": 38160, "loss": 0.0249, "lr": 1.0645606663499e-05, "epoch": 14.504716981132075, "percentage": 72.52, "elapsed_time": "1:45:58", "remaining_time": "0:40:08", "throughput": 2845.5, "total_tokens": 18092600} {"current_steps": 27680, "total_steps": 38160, "loss": 0.0567, "lr": 1.0636246549269649e-05, "epoch": 14.50733752620545, "percentage": 72.54, "elapsed_time": "1:45:59", "remaining_time": "0:40:07", "throughput": 2845.53, "total_tokens": 18096056} {"current_steps": 27685, "total_steps": 38160, "loss": 0.0604, "lr": 1.062688943977366e-05, "epoch": 14.509958071278826, "percentage": 72.55, "elapsed_time": "1:46:00", "remaining_time": "0:40:06", "throughput": 2845.55, "total_tokens": 18099192} {"current_steps": 27690, "total_steps": 38160, "loss": 0.0552, "lr": 1.0617535336968413e-05, "epoch": 14.5125786163522, "percentage": 72.56, "elapsed_time": "1:46:02", "remaining_time": "0:40:05", "throughput": 2845.83, "total_tokens": 18106744} {"current_steps": 27695, "total_steps": 38160, "loss": 0.0209, "lr": 1.0608184242810698e-05, "epoch": 14.515199161425576, "percentage": 72.58, "elapsed_time": "1:46:03", "remaining_time": "0:40:04", "throughput": 2845.79, "total_tokens": 18109592} {"current_steps": 27700, "total_steps": 38160, "loss": 0.0085, "lr": 1.0598836159256642e-05, "epoch": 14.517819706498951, "percentage": 72.59, "elapsed_time": "1:46:04", "remaining_time": "0:40:03", "throughput": 2845.81, "total_tokens": 18112632} {"current_steps": 27705, "total_steps": 38160, "loss": 0.0443, "lr": 1.0589491088261763e-05, "epoch": 14.520440251572326, "percentage": 72.6, "elapsed_time": "1:46:05", "remaining_time": "0:40:02", "throughput": 2845.94, "total_tokens": 18116824} {"current_steps": 27710, "total_steps": 38160, "loss": 0.0407, "lr": 1.0580149031780945e-05, "epoch": 14.523060796645701, "percentage": 72.62, "elapsed_time": "1:46:06", "remaining_time": "0:40:01", "throughput": 2846.01, "total_tokens": 18120504} {"current_steps": 27715, "total_steps": 38160, "loss": 0.0144, "lr": 1.0570809991768447e-05, "epoch": 14.525681341719078, "percentage": 72.63, "elapsed_time": "1:46:08", "remaining_time": "0:39:59", "throughput": 2846.01, "total_tokens": 18123768} {"current_steps": 27720, "total_steps": 38160, "loss": 0.0246, "lr": 1.0561473970177873e-05, "epoch": 14.528301886792454, "percentage": 72.64, "elapsed_time": "1:46:09", "remaining_time": "0:39:58", "throughput": 2845.96, "total_tokens": 18126584} {"current_steps": 27725, "total_steps": 38160, "loss": 0.0312, "lr": 1.0552140968962232e-05, "epoch": 14.530922431865829, "percentage": 72.65, "elapsed_time": "1:46:10", "remaining_time": "0:39:57", "throughput": 2846.12, "total_tokens": 18131480} {"current_steps": 27730, "total_steps": 38160, "loss": 0.0389, "lr": 1.054281099007386e-05, "epoch": 14.533542976939204, "percentage": 72.67, "elapsed_time": "1:46:11", "remaining_time": "0:39:56", "throughput": 2846.21, "total_tokens": 18135224} {"current_steps": 27735, "total_steps": 38160, "loss": 0.0231, "lr": 1.0533484035464492e-05, "epoch": 14.536163522012579, "percentage": 72.68, "elapsed_time": "1:46:12", "remaining_time": "0:39:55", "throughput": 2846.2, "total_tokens": 18138232} {"current_steps": 27740, "total_steps": 38160, "loss": 0.023, "lr": 1.0524160107085231e-05, "epoch": 14.538784067085954, "percentage": 72.69, "elapsed_time": "1:46:13", "remaining_time": "0:39:54", "throughput": 2846.3, "total_tokens": 18142040} {"current_steps": 27745, "total_steps": 38160, "loss": 0.0287, "lr": 1.0514839206886518e-05, "epoch": 14.54140461215933, "percentage": 72.71, "elapsed_time": "1:46:14", "remaining_time": "0:39:53", "throughput": 2846.27, "total_tokens": 18144888} {"current_steps": 27750, "total_steps": 38160, "loss": 0.015, "lr": 1.0505521336818195e-05, "epoch": 14.544025157232705, "percentage": 72.72, "elapsed_time": "1:46:16", "remaining_time": "0:39:51", "throughput": 2846.21, "total_tokens": 18147672} {"current_steps": 27755, "total_steps": 38160, "loss": 0.0075, "lr": 1.0496206498829438e-05, "epoch": 14.54664570230608, "percentage": 72.73, "elapsed_time": "1:46:17", "remaining_time": "0:39:50", "throughput": 2846.21, "total_tokens": 18150808} {"current_steps": 27760, "total_steps": 38160, "loss": 0.017, "lr": 1.0486894694868814e-05, "epoch": 14.549266247379455, "percentage": 72.75, "elapsed_time": "1:46:18", "remaining_time": "0:39:49", "throughput": 2846.14, "total_tokens": 18153400} {"current_steps": 27765, "total_steps": 38160, "loss": 0.0131, "lr": 1.0477585926884246e-05, "epoch": 14.55188679245283, "percentage": 72.76, "elapsed_time": "1:46:19", "remaining_time": "0:39:48", "throughput": 2846.26, "total_tokens": 18157432} {"current_steps": 27770, "total_steps": 38160, "loss": 0.0177, "lr": 1.046828019682303e-05, "epoch": 14.554507337526205, "percentage": 72.77, "elapsed_time": "1:46:20", "remaining_time": "0:39:47", "throughput": 2846.26, "total_tokens": 18160472} {"current_steps": 27775, "total_steps": 38160, "loss": 0.0178, "lr": 1.0458977506631808e-05, "epoch": 14.55712788259958, "percentage": 72.79, "elapsed_time": "1:46:21", "remaining_time": "0:39:46", "throughput": 2846.27, "total_tokens": 18163608} {"current_steps": 27780, "total_steps": 38160, "loss": 0.0165, "lr": 1.0449677858256593e-05, "epoch": 14.559748427672956, "percentage": 72.8, "elapsed_time": "1:46:22", "remaining_time": "0:39:44", "throughput": 2846.33, "total_tokens": 18167736} {"current_steps": 27785, "total_steps": 38160, "loss": 0.0213, "lr": 1.0440381253642773e-05, "epoch": 14.56236897274633, "percentage": 72.81, "elapsed_time": "1:46:23", "remaining_time": "0:39:43", "throughput": 2846.36, "total_tokens": 18171160} {"current_steps": 27790, "total_steps": 38160, "loss": 0.0354, "lr": 1.0431087694735087e-05, "epoch": 14.564989517819706, "percentage": 72.82, "elapsed_time": "1:46:25", "remaining_time": "0:39:42", "throughput": 2846.34, "total_tokens": 18174168} {"current_steps": 27795, "total_steps": 38160, "loss": 0.0371, "lr": 1.0421797183477644e-05, "epoch": 14.567610062893081, "percentage": 72.84, "elapsed_time": "1:46:26", "remaining_time": "0:39:41", "throughput": 2846.33, "total_tokens": 18177080} {"current_steps": 27800, "total_steps": 38160, "loss": 0.0531, "lr": 1.041250972181392e-05, "epoch": 14.570230607966456, "percentage": 72.85, "elapsed_time": "1:46:27", "remaining_time": "0:39:40", "throughput": 2846.51, "total_tokens": 18181976} {"current_steps": 27805, "total_steps": 38160, "loss": 0.0438, "lr": 1.0403225311686743e-05, "epoch": 14.572851153039831, "percentage": 72.86, "elapsed_time": "1:46:28", "remaining_time": "0:39:39", "throughput": 2846.67, "total_tokens": 18186168} {"current_steps": 27810, "total_steps": 38160, "loss": 0.0199, "lr": 1.0393943955038293e-05, "epoch": 14.575471698113208, "percentage": 72.88, "elapsed_time": "1:46:29", "remaining_time": "0:39:38", "throughput": 2846.73, "total_tokens": 18189656} {"current_steps": 27815, "total_steps": 38160, "loss": 0.0209, "lr": 1.038466565381013e-05, "epoch": 14.578092243186584, "percentage": 72.89, "elapsed_time": "1:46:30", "remaining_time": "0:39:36", "throughput": 2846.59, "total_tokens": 18191768} {"current_steps": 27820, "total_steps": 38160, "loss": 0.0115, "lr": 1.0375390409943175e-05, "epoch": 14.580712788259959, "percentage": 72.9, "elapsed_time": "1:46:31", "remaining_time": "0:39:35", "throughput": 2846.51, "total_tokens": 18194296} {"current_steps": 27825, "total_steps": 38160, "loss": 0.0167, "lr": 1.0366118225377708e-05, "epoch": 14.583333333333334, "percentage": 72.92, "elapsed_time": "1:46:32", "remaining_time": "0:39:34", "throughput": 2846.56, "total_tokens": 18197528} {"current_steps": 27830, "total_steps": 38160, "loss": 0.0157, "lr": 1.0356849102053353e-05, "epoch": 14.585953878406709, "percentage": 72.93, "elapsed_time": "1:46:33", "remaining_time": "0:39:33", "throughput": 2846.58, "total_tokens": 18200600} {"current_steps": 27835, "total_steps": 38160, "loss": 0.0251, "lr": 1.0347583041909104e-05, "epoch": 14.588574423480084, "percentage": 72.94, "elapsed_time": "1:46:34", "remaining_time": "0:39:32", "throughput": 2846.6, "total_tokens": 18203864} {"current_steps": 27840, "total_steps": 38160, "loss": 0.021, "lr": 1.0338320046883315e-05, "epoch": 14.59119496855346, "percentage": 72.96, "elapsed_time": "1:46:35", "remaining_time": "0:39:30", "throughput": 2846.66, "total_tokens": 18207192} {"current_steps": 27845, "total_steps": 38160, "loss": 0.0193, "lr": 1.0329060118913705e-05, "epoch": 14.593815513626835, "percentage": 72.97, "elapsed_time": "1:46:37", "remaining_time": "0:39:29", "throughput": 2846.76, "total_tokens": 18211352} {"current_steps": 27850, "total_steps": 38160, "loss": 0.0207, "lr": 1.0319803259937353e-05, "epoch": 14.59643605870021, "percentage": 72.98, "elapsed_time": "1:46:38", "remaining_time": "0:39:28", "throughput": 2846.74, "total_tokens": 18214200} {"current_steps": 27855, "total_steps": 38160, "loss": 0.011, "lr": 1.0310549471890676e-05, "epoch": 14.599056603773585, "percentage": 73.0, "elapsed_time": "1:46:39", "remaining_time": "0:39:27", "throughput": 2846.69, "total_tokens": 18216920} {"current_steps": 27860, "total_steps": 38160, "loss": 0.0325, "lr": 1.0301298756709454e-05, "epoch": 14.60167714884696, "percentage": 73.01, "elapsed_time": "1:46:40", "remaining_time": "0:39:26", "throughput": 2846.73, "total_tokens": 18220184} {"current_steps": 27865, "total_steps": 38160, "loss": 0.0359, "lr": 1.0292051116328844e-05, "epoch": 14.604297693920335, "percentage": 73.02, "elapsed_time": "1:46:41", "remaining_time": "0:39:25", "throughput": 2846.79, "total_tokens": 18224280} {"current_steps": 27870, "total_steps": 38160, "loss": 0.0196, "lr": 1.028280655268334e-05, "epoch": 14.60691823899371, "percentage": 73.03, "elapsed_time": "1:46:42", "remaining_time": "0:39:24", "throughput": 2846.67, "total_tokens": 18226744} {"current_steps": 27875, "total_steps": 38160, "loss": 0.0301, "lr": 1.0273565067706806e-05, "epoch": 14.609538784067086, "percentage": 73.05, "elapsed_time": "1:46:44", "remaining_time": "0:39:22", "throughput": 2846.65, "total_tokens": 18230232} {"current_steps": 27880, "total_steps": 38160, "loss": 0.039, "lr": 1.0264326663332457e-05, "epoch": 14.61215932914046, "percentage": 73.06, "elapsed_time": "1:46:45", "remaining_time": "0:39:21", "throughput": 2846.74, "total_tokens": 18234040} {"current_steps": 27885, "total_steps": 38160, "loss": 0.0034, "lr": 1.0255091341492859e-05, "epoch": 14.614779874213836, "percentage": 73.07, "elapsed_time": "1:46:46", "remaining_time": "0:39:20", "throughput": 2846.67, "total_tokens": 18236632} {"current_steps": 27890, "total_steps": 38160, "loss": 0.0278, "lr": 1.0245859104119923e-05, "epoch": 14.617400419287211, "percentage": 73.09, "elapsed_time": "1:46:47", "remaining_time": "0:39:19", "throughput": 2846.64, "total_tokens": 18239640} {"current_steps": 27895, "total_steps": 38160, "loss": 0.0161, "lr": 1.0236629953144938e-05, "epoch": 14.620020964360586, "percentage": 73.1, "elapsed_time": "1:46:48", "remaining_time": "0:39:18", "throughput": 2846.64, "total_tokens": 18242648} {"current_steps": 27900, "total_steps": 38160, "loss": 0.0234, "lr": 1.0227403890498537e-05, "epoch": 14.622641509433961, "percentage": 73.11, "elapsed_time": "1:46:49", "remaining_time": "0:39:17", "throughput": 2846.71, "total_tokens": 18246584} {"current_steps": 27905, "total_steps": 38160, "loss": 0.0645, "lr": 1.021818091811072e-05, "epoch": 14.625262054507338, "percentage": 73.13, "elapsed_time": "1:46:50", "remaining_time": "0:39:15", "throughput": 2846.68, "total_tokens": 18249400} {"current_steps": 27910, "total_steps": 38160, "loss": 0.0202, "lr": 1.0208961037910813e-05, "epoch": 14.627882599580714, "percentage": 73.14, "elapsed_time": "1:46:51", "remaining_time": "0:39:14", "throughput": 2846.75, "total_tokens": 18252952} {"current_steps": 27915, "total_steps": 38160, "loss": 0.0583, "lr": 1.0199744251827503e-05, "epoch": 14.630503144654089, "percentage": 73.15, "elapsed_time": "1:46:52", "remaining_time": "0:39:13", "throughput": 2846.91, "total_tokens": 18257176} {"current_steps": 27920, "total_steps": 38160, "loss": 0.0364, "lr": 1.0190530561788845e-05, "epoch": 14.633123689727464, "percentage": 73.17, "elapsed_time": "1:46:54", "remaining_time": "0:39:12", "throughput": 2846.91, "total_tokens": 18260280} {"current_steps": 27925, "total_steps": 38160, "loss": 0.0198, "lr": 1.0181319969722236e-05, "epoch": 14.635744234800839, "percentage": 73.18, "elapsed_time": "1:46:55", "remaining_time": "0:39:11", "throughput": 2846.94, "total_tokens": 18263480} {"current_steps": 27930, "total_steps": 38160, "loss": 0.025, "lr": 1.0172112477554441e-05, "epoch": 14.638364779874214, "percentage": 73.19, "elapsed_time": "1:46:56", "remaining_time": "0:39:10", "throughput": 2847.04, "total_tokens": 18267128} {"current_steps": 27935, "total_steps": 38160, "loss": 0.0287, "lr": 1.016290808721154e-05, "epoch": 14.64098532494759, "percentage": 73.2, "elapsed_time": "1:46:57", "remaining_time": "0:39:08", "throughput": 2847.1, "total_tokens": 18270968} {"current_steps": 27940, "total_steps": 38160, "loss": 0.0374, "lr": 1.0153706800619007e-05, "epoch": 14.643605870020965, "percentage": 73.22, "elapsed_time": "1:46:58", "remaining_time": "0:39:07", "throughput": 2847.06, "total_tokens": 18273720} {"current_steps": 27945, "total_steps": 38160, "loss": 0.0183, "lr": 1.0144508619701623e-05, "epoch": 14.64622641509434, "percentage": 73.23, "elapsed_time": "1:46:59", "remaining_time": "0:39:06", "throughput": 2847.06, "total_tokens": 18276920} {"current_steps": 27950, "total_steps": 38160, "loss": 0.0271, "lr": 1.013531354638356e-05, "epoch": 14.648846960167715, "percentage": 73.24, "elapsed_time": "1:47:00", "remaining_time": "0:39:05", "throughput": 2847.18, "total_tokens": 18280952} {"current_steps": 27955, "total_steps": 38160, "loss": 0.0708, "lr": 1.0126121582588316e-05, "epoch": 14.65146750524109, "percentage": 73.26, "elapsed_time": "1:47:01", "remaining_time": "0:39:04", "throughput": 2847.2, "total_tokens": 18284120} {"current_steps": 27960, "total_steps": 38160, "loss": 0.0309, "lr": 1.0116932730238754e-05, "epoch": 14.654088050314465, "percentage": 73.27, "elapsed_time": "1:47:02", "remaining_time": "0:39:03", "throughput": 2847.35, "total_tokens": 18288120} {"current_steps": 27965, "total_steps": 38160, "loss": 0.0337, "lr": 1.0107746991257063e-05, "epoch": 14.65670859538784, "percentage": 73.28, "elapsed_time": "1:47:03", "remaining_time": "0:39:01", "throughput": 2847.36, "total_tokens": 18291224} {"current_steps": 27970, "total_steps": 38160, "loss": 0.0128, "lr": 1.0098564367564811e-05, "epoch": 14.659329140461216, "percentage": 73.3, "elapsed_time": "1:47:04", "remaining_time": "0:39:00", "throughput": 2847.4, "total_tokens": 18294520} {"current_steps": 27975, "total_steps": 38160, "loss": 0.0123, "lr": 1.0089384861082876e-05, "epoch": 14.66194968553459, "percentage": 73.31, "elapsed_time": "1:47:06", "remaining_time": "0:38:59", "throughput": 2847.49, "total_tokens": 18298296} {"current_steps": 27980, "total_steps": 38160, "loss": 0.0122, "lr": 1.0080208473731523e-05, "epoch": 14.664570230607966, "percentage": 73.32, "elapsed_time": "1:47:07", "remaining_time": "0:38:58", "throughput": 2847.44, "total_tokens": 18301016} {"current_steps": 27985, "total_steps": 38160, "loss": 0.0192, "lr": 1.0071035207430352e-05, "epoch": 14.667190775681341, "percentage": 73.34, "elapsed_time": "1:47:08", "remaining_time": "0:38:57", "throughput": 2847.49, "total_tokens": 18304728} {"current_steps": 27990, "total_steps": 38160, "loss": 0.0436, "lr": 1.0061865064098285e-05, "epoch": 14.669811320754716, "percentage": 73.35, "elapsed_time": "1:47:09", "remaining_time": "0:38:56", "throughput": 2847.49, "total_tokens": 18307736} {"current_steps": 27995, "total_steps": 38160, "loss": 0.0175, "lr": 1.0052698045653625e-05, "epoch": 14.672431865828091, "percentage": 73.36, "elapsed_time": "1:47:10", "remaining_time": "0:38:54", "throughput": 2847.47, "total_tokens": 18310744} {"current_steps": 28000, "total_steps": 38160, "loss": 0.0213, "lr": 1.0043534154014015e-05, "epoch": 14.675052410901468, "percentage": 73.38, "elapsed_time": "1:47:11", "remaining_time": "0:38:53", "throughput": 2847.37, "total_tokens": 18313336} {"current_steps": 28005, "total_steps": 38160, "loss": 0.04, "lr": 1.003437339109642e-05, "epoch": 14.677672955974844, "percentage": 73.39, "elapsed_time": "1:47:12", "remaining_time": "0:38:52", "throughput": 2847.31, "total_tokens": 18316120} {"current_steps": 28010, "total_steps": 38160, "loss": 0.0196, "lr": 1.0025215758817183e-05, "epoch": 14.680293501048219, "percentage": 73.4, "elapsed_time": "1:47:13", "remaining_time": "0:38:51", "throughput": 2847.35, "total_tokens": 18319480} {"current_steps": 28015, "total_steps": 38160, "loss": 0.0136, "lr": 1.0016061259091958e-05, "epoch": 14.682914046121594, "percentage": 73.41, "elapsed_time": "1:47:14", "remaining_time": "0:38:50", "throughput": 2847.46, "total_tokens": 18323288} {"current_steps": 28020, "total_steps": 38160, "loss": 0.0148, "lr": 1.000690989383577e-05, "epoch": 14.685534591194969, "percentage": 73.43, "elapsed_time": "1:47:16", "remaining_time": "0:38:49", "throughput": 2847.36, "total_tokens": 18325752} {"current_steps": 28025, "total_steps": 38160, "loss": 0.0249, "lr": 9.997761664962993e-06, "epoch": 14.688155136268344, "percentage": 73.44, "elapsed_time": "1:47:17", "remaining_time": "0:38:48", "throughput": 2847.52, "total_tokens": 18330424} {"current_steps": 28030, "total_steps": 38160, "loss": 0.0082, "lr": 9.988616574387314e-06, "epoch": 14.69077568134172, "percentage": 73.45, "elapsed_time": "1:47:18", "remaining_time": "0:38:46", "throughput": 2847.5, "total_tokens": 18333336} {"current_steps": 28035, "total_steps": 38160, "loss": 0.0226, "lr": 9.979474624021787e-06, "epoch": 14.693396226415095, "percentage": 73.47, "elapsed_time": "1:47:19", "remaining_time": "0:38:45", "throughput": 2847.56, "total_tokens": 18336760} {"current_steps": 28040, "total_steps": 38160, "loss": 0.0139, "lr": 9.970335815778815e-06, "epoch": 14.69601677148847, "percentage": 73.48, "elapsed_time": "1:47:20", "remaining_time": "0:38:44", "throughput": 2847.49, "total_tokens": 18339288} {"current_steps": 28045, "total_steps": 38160, "loss": 0.0695, "lr": 9.96120015157011e-06, "epoch": 14.698637316561845, "percentage": 73.49, "elapsed_time": "1:47:21", "remaining_time": "0:38:43", "throughput": 2847.52, "total_tokens": 18343064} {"current_steps": 28050, "total_steps": 38160, "loss": 0.0283, "lr": 9.952067633306767e-06, "epoch": 14.70125786163522, "percentage": 73.51, "elapsed_time": "1:47:22", "remaining_time": "0:38:42", "throughput": 2847.57, "total_tokens": 18346584} {"current_steps": 28055, "total_steps": 38160, "loss": 0.0187, "lr": 9.942938262899204e-06, "epoch": 14.703878406708595, "percentage": 73.52, "elapsed_time": "1:47:23", "remaining_time": "0:38:41", "throughput": 2847.58, "total_tokens": 18349752} {"current_steps": 28060, "total_steps": 38160, "loss": 0.0111, "lr": 9.93381204225717e-06, "epoch": 14.70649895178197, "percentage": 73.53, "elapsed_time": "1:47:25", "remaining_time": "0:38:39", "throughput": 2847.52, "total_tokens": 18352632} {"current_steps": 28065, "total_steps": 38160, "loss": 0.0476, "lr": 9.924688973289782e-06, "epoch": 14.709119496855346, "percentage": 73.55, "elapsed_time": "1:47:26", "remaining_time": "0:38:38", "throughput": 2847.59, "total_tokens": 18356280} {"current_steps": 28070, "total_steps": 38160, "loss": 0.0109, "lr": 9.915569057905463e-06, "epoch": 14.71174004192872, "percentage": 73.56, "elapsed_time": "1:47:27", "remaining_time": "0:38:37", "throughput": 2847.63, "total_tokens": 18359512} {"current_steps": 28075, "total_steps": 38160, "loss": 0.0249, "lr": 9.906452298012003e-06, "epoch": 14.714360587002096, "percentage": 73.57, "elapsed_time": "1:47:28", "remaining_time": "0:38:36", "throughput": 2847.55, "total_tokens": 18362072} {"current_steps": 28080, "total_steps": 38160, "loss": 0.0259, "lr": 9.897338695516529e-06, "epoch": 14.716981132075471, "percentage": 73.58, "elapsed_time": "1:47:29", "remaining_time": "0:38:35", "throughput": 2847.6, "total_tokens": 18365400} {"current_steps": 28085, "total_steps": 38160, "loss": 0.0331, "lr": 9.888228252325507e-06, "epoch": 14.719601677148846, "percentage": 73.6, "elapsed_time": "1:47:30", "remaining_time": "0:38:34", "throughput": 2847.67, "total_tokens": 18369176} {"current_steps": 28090, "total_steps": 38160, "loss": 0.0097, "lr": 9.87912097034473e-06, "epoch": 14.722222222222221, "percentage": 73.61, "elapsed_time": "1:47:31", "remaining_time": "0:38:32", "throughput": 2847.69, "total_tokens": 18372472} {"current_steps": 28095, "total_steps": 38160, "loss": 0.0342, "lr": 9.870016851479327e-06, "epoch": 14.724842767295598, "percentage": 73.62, "elapsed_time": "1:47:32", "remaining_time": "0:38:31", "throughput": 2847.69, "total_tokens": 18375608} {"current_steps": 28100, "total_steps": 38160, "loss": 0.0177, "lr": 9.860915897633791e-06, "epoch": 14.727463312368974, "percentage": 73.64, "elapsed_time": "1:47:33", "remaining_time": "0:38:30", "throughput": 2847.62, "total_tokens": 18378424} {"current_steps": 28105, "total_steps": 38160, "loss": 0.057, "lr": 9.85181811071193e-06, "epoch": 14.730083857442349, "percentage": 73.65, "elapsed_time": "1:47:35", "remaining_time": "0:38:29", "throughput": 2847.82, "total_tokens": 18383544} {"current_steps": 28110, "total_steps": 38160, "loss": 0.02, "lr": 9.842723492616913e-06, "epoch": 14.732704402515724, "percentage": 73.66, "elapsed_time": "1:47:36", "remaining_time": "0:38:28", "throughput": 2847.8, "total_tokens": 18386488} {"current_steps": 28115, "total_steps": 38160, "loss": 0.012, "lr": 9.833632045251207e-06, "epoch": 14.735324947589099, "percentage": 73.68, "elapsed_time": "1:47:37", "remaining_time": "0:38:27", "throughput": 2847.75, "total_tokens": 18389272} {"current_steps": 28120, "total_steps": 38160, "loss": 0.01, "lr": 9.824543770516656e-06, "epoch": 14.737945492662474, "percentage": 73.69, "elapsed_time": "1:47:38", "remaining_time": "0:38:25", "throughput": 2847.86, "total_tokens": 18393240} {"current_steps": 28125, "total_steps": 38160, "loss": 0.0235, "lr": 9.815458670314412e-06, "epoch": 14.74056603773585, "percentage": 73.7, "elapsed_time": "1:47:39", "remaining_time": "0:38:24", "throughput": 2847.9, "total_tokens": 18396504} {"current_steps": 28130, "total_steps": 38160, "loss": 0.0062, "lr": 9.80637674654498e-06, "epoch": 14.743186582809225, "percentage": 73.72, "elapsed_time": "1:47:40", "remaining_time": "0:38:23", "throughput": 2847.84, "total_tokens": 18399096} {"current_steps": 28135, "total_steps": 38160, "loss": 0.018, "lr": 9.797298001108193e-06, "epoch": 14.7458071278826, "percentage": 73.73, "elapsed_time": "1:47:41", "remaining_time": "0:38:22", "throughput": 2847.95, "total_tokens": 18402936} {"current_steps": 28140, "total_steps": 38160, "loss": 0.0181, "lr": 9.788222435903232e-06, "epoch": 14.748427672955975, "percentage": 73.74, "elapsed_time": "1:47:42", "remaining_time": "0:38:21", "throughput": 2847.93, "total_tokens": 18406008} {"current_steps": 28145, "total_steps": 38160, "loss": 0.0528, "lr": 9.779150052828596e-06, "epoch": 14.75104821802935, "percentage": 73.76, "elapsed_time": "1:47:44", "remaining_time": "0:38:20", "throughput": 2848.01, "total_tokens": 18409752} {"current_steps": 28150, "total_steps": 38160, "loss": 0.0184, "lr": 9.770080853782108e-06, "epoch": 14.753668763102725, "percentage": 73.77, "elapsed_time": "1:47:45", "remaining_time": "0:38:18", "throughput": 2847.97, "total_tokens": 18412408} {"current_steps": 28155, "total_steps": 38160, "loss": 0.0466, "lr": 9.76101484066095e-06, "epoch": 14.7562893081761, "percentage": 73.78, "elapsed_time": "1:47:46", "remaining_time": "0:38:17", "throughput": 2847.98, "total_tokens": 18415672} {"current_steps": 28160, "total_steps": 38160, "loss": 0.039, "lr": 9.751952015361637e-06, "epoch": 14.758909853249476, "percentage": 73.79, "elapsed_time": "1:47:47", "remaining_time": "0:38:16", "throughput": 2848.03, "total_tokens": 18418904} {"current_steps": 28165, "total_steps": 38160, "loss": 0.0173, "lr": 9.742892379780003e-06, "epoch": 14.76153039832285, "percentage": 73.81, "elapsed_time": "1:47:48", "remaining_time": "0:38:15", "throughput": 2848.01, "total_tokens": 18421816} {"current_steps": 28170, "total_steps": 38160, "loss": 0.0869, "lr": 9.733835935811237e-06, "epoch": 14.764150943396226, "percentage": 73.82, "elapsed_time": "1:47:49", "remaining_time": "0:38:14", "throughput": 2847.98, "total_tokens": 18424696} {"current_steps": 28175, "total_steps": 38160, "loss": 0.0471, "lr": 9.724782685349809e-06, "epoch": 14.766771488469601, "percentage": 73.83, "elapsed_time": "1:47:50", "remaining_time": "0:38:13", "throughput": 2847.96, "total_tokens": 18427864} {"current_steps": 28180, "total_steps": 38160, "loss": 0.0304, "lr": 9.715732630289576e-06, "epoch": 14.769392033542976, "percentage": 73.85, "elapsed_time": "1:47:51", "remaining_time": "0:38:11", "throughput": 2847.94, "total_tokens": 18430872} {"current_steps": 28185, "total_steps": 38160, "loss": 0.0142, "lr": 9.706685772523701e-06, "epoch": 14.772012578616351, "percentage": 73.86, "elapsed_time": "1:47:52", "remaining_time": "0:38:10", "throughput": 2847.86, "total_tokens": 18433400} {"current_steps": 28190, "total_steps": 38160, "loss": 0.0326, "lr": 9.697642113944692e-06, "epoch": 14.774633123689728, "percentage": 73.87, "elapsed_time": "1:47:53", "remaining_time": "0:38:09", "throughput": 2847.82, "total_tokens": 18436536} {"current_steps": 28195, "total_steps": 38160, "loss": 0.0229, "lr": 9.688601656444381e-06, "epoch": 14.777253668763104, "percentage": 73.89, "elapsed_time": "1:47:54", "remaining_time": "0:38:08", "throughput": 2847.86, "total_tokens": 18439896} {"current_steps": 28200, "total_steps": 38160, "loss": 0.0222, "lr": 9.679564401913921e-06, "epoch": 14.779874213836479, "percentage": 73.9, "elapsed_time": "1:47:56", "remaining_time": "0:38:07", "throughput": 2848.07, "total_tokens": 18445112} {"current_steps": 28205, "total_steps": 38160, "loss": 0.013, "lr": 9.670530352243798e-06, "epoch": 14.782494758909854, "percentage": 73.91, "elapsed_time": "1:47:57", "remaining_time": "0:38:06", "throughput": 2848.05, "total_tokens": 18448056} {"current_steps": 28210, "total_steps": 38160, "loss": 0.0246, "lr": 9.661499509323835e-06, "epoch": 14.785115303983229, "percentage": 73.93, "elapsed_time": "1:47:58", "remaining_time": "0:38:05", "throughput": 2848.08, "total_tokens": 18451320} {"current_steps": 28215, "total_steps": 38160, "loss": 0.0118, "lr": 9.652471875043182e-06, "epoch": 14.787735849056604, "percentage": 73.94, "elapsed_time": "1:47:59", "remaining_time": "0:38:03", "throughput": 2848.04, "total_tokens": 18454168} {"current_steps": 28220, "total_steps": 38160, "loss": 0.0269, "lr": 9.64344745129033e-06, "epoch": 14.79035639412998, "percentage": 73.95, "elapsed_time": "1:48:00", "remaining_time": "0:38:02", "throughput": 2848.05, "total_tokens": 18457144} {"current_steps": 28225, "total_steps": 38160, "loss": 0.0154, "lr": 9.634426239953073e-06, "epoch": 14.792976939203355, "percentage": 73.96, "elapsed_time": "1:48:01", "remaining_time": "0:38:01", "throughput": 2848.05, "total_tokens": 18460088} {"current_steps": 28230, "total_steps": 38160, "loss": 0.0513, "lr": 9.62540824291854e-06, "epoch": 14.79559748427673, "percentage": 73.98, "elapsed_time": "1:48:02", "remaining_time": "0:38:00", "throughput": 2848.12, "total_tokens": 18463800} {"current_steps": 28235, "total_steps": 38160, "loss": 0.0282, "lr": 9.616393462073197e-06, "epoch": 14.798218029350105, "percentage": 73.99, "elapsed_time": "1:48:03", "remaining_time": "0:37:59", "throughput": 2848.11, "total_tokens": 18466744} {"current_steps": 28240, "total_steps": 38160, "loss": 0.0457, "lr": 9.607381899302839e-06, "epoch": 14.80083857442348, "percentage": 74.0, "elapsed_time": "1:48:04", "remaining_time": "0:37:57", "throughput": 2848.12, "total_tokens": 18469848} {"current_steps": 28245, "total_steps": 38160, "loss": 0.032, "lr": 9.59837355649258e-06, "epoch": 14.803459119496855, "percentage": 74.02, "elapsed_time": "1:48:06", "remaining_time": "0:37:56", "throughput": 2848.2, "total_tokens": 18473496} {"current_steps": 28250, "total_steps": 38160, "loss": 0.021, "lr": 9.589368435526868e-06, "epoch": 14.80607966457023, "percentage": 74.03, "elapsed_time": "1:48:07", "remaining_time": "0:37:55", "throughput": 2848.27, "total_tokens": 18477048} {"current_steps": 28255, "total_steps": 38160, "loss": 0.0302, "lr": 9.580366538289468e-06, "epoch": 14.808700209643606, "percentage": 74.04, "elapsed_time": "1:48:08", "remaining_time": "0:37:54", "throughput": 2848.2, "total_tokens": 18479640} {"current_steps": 28260, "total_steps": 38160, "loss": 0.033, "lr": 9.57136786666346e-06, "epoch": 14.81132075471698, "percentage": 74.06, "elapsed_time": "1:48:09", "remaining_time": "0:37:53", "throughput": 2848.2, "total_tokens": 18482808} {"current_steps": 28265, "total_steps": 38160, "loss": 0.0151, "lr": 9.562372422531276e-06, "epoch": 14.813941299790356, "percentage": 74.07, "elapsed_time": "1:48:10", "remaining_time": "0:37:52", "throughput": 2848.12, "total_tokens": 18485496} {"current_steps": 28270, "total_steps": 38160, "loss": 0.0215, "lr": 9.553380207774662e-06, "epoch": 14.816561844863731, "percentage": 74.08, "elapsed_time": "1:48:11", "remaining_time": "0:37:51", "throughput": 2848.1, "total_tokens": 18488568} {"current_steps": 28275, "total_steps": 38160, "loss": 0.0177, "lr": 9.54439122427469e-06, "epoch": 14.819182389937106, "percentage": 74.1, "elapsed_time": "1:48:12", "remaining_time": "0:37:49", "throughput": 2848.04, "total_tokens": 18491256} {"current_steps": 28280, "total_steps": 38160, "loss": 0.0165, "lr": 9.535405473911748e-06, "epoch": 14.821802935010481, "percentage": 74.11, "elapsed_time": "1:48:13", "remaining_time": "0:37:48", "throughput": 2848.05, "total_tokens": 18494424} {"current_steps": 28285, "total_steps": 38160, "loss": 0.0262, "lr": 9.526422958565546e-06, "epoch": 14.824423480083858, "percentage": 74.12, "elapsed_time": "1:48:14", "remaining_time": "0:37:47", "throughput": 2848.05, "total_tokens": 18497496} {"current_steps": 28290, "total_steps": 38160, "loss": 0.0233, "lr": 9.517443680115124e-06, "epoch": 14.827044025157234, "percentage": 74.14, "elapsed_time": "1:48:15", "remaining_time": "0:37:46", "throughput": 2848.13, "total_tokens": 18501304} {"current_steps": 28295, "total_steps": 38160, "loss": 0.0072, "lr": 9.50846764043885e-06, "epoch": 14.829664570230609, "percentage": 74.15, "elapsed_time": "1:48:17", "remaining_time": "0:37:45", "throughput": 2848.21, "total_tokens": 18505048} {"current_steps": 28300, "total_steps": 38160, "loss": 0.0298, "lr": 9.499494841414422e-06, "epoch": 14.832285115303984, "percentage": 74.16, "elapsed_time": "1:48:18", "remaining_time": "0:37:44", "throughput": 2848.22, "total_tokens": 18508216} {"current_steps": 28305, "total_steps": 38160, "loss": 0.0122, "lr": 9.490525284918822e-06, "epoch": 14.834905660377359, "percentage": 74.17, "elapsed_time": "1:48:19", "remaining_time": "0:37:42", "throughput": 2848.18, "total_tokens": 18511192} {"current_steps": 28310, "total_steps": 38160, "loss": 0.0115, "lr": 9.4815589728284e-06, "epoch": 14.837526205450734, "percentage": 74.19, "elapsed_time": "1:48:20", "remaining_time": "0:37:41", "throughput": 2848.16, "total_tokens": 18514296} {"current_steps": 28315, "total_steps": 38160, "loss": 0.0577, "lr": 9.472595907018788e-06, "epoch": 14.84014675052411, "percentage": 74.2, "elapsed_time": "1:48:21", "remaining_time": "0:37:40", "throughput": 2848.16, "total_tokens": 18517560} {"current_steps": 28320, "total_steps": 38160, "loss": 0.0447, "lr": 9.463636089364968e-06, "epoch": 14.842767295597485, "percentage": 74.21, "elapsed_time": "1:48:22", "remaining_time": "0:37:39", "throughput": 2848.18, "total_tokens": 18520888} {"current_steps": 28325, "total_steps": 38160, "loss": 0.0177, "lr": 9.454679521741239e-06, "epoch": 14.84538784067086, "percentage": 74.23, "elapsed_time": "1:48:23", "remaining_time": "0:37:38", "throughput": 2848.3, "total_tokens": 18525016} {"current_steps": 28330, "total_steps": 38160, "loss": 0.0258, "lr": 9.445726206021194e-06, "epoch": 14.848008385744235, "percentage": 74.24, "elapsed_time": "1:48:25", "remaining_time": "0:37:37", "throughput": 2848.4, "total_tokens": 18529112} {"current_steps": 28335, "total_steps": 38160, "loss": 0.0225, "lr": 9.436776144077772e-06, "epoch": 14.85062893081761, "percentage": 74.25, "elapsed_time": "1:48:26", "remaining_time": "0:37:35", "throughput": 2848.44, "total_tokens": 18532344} {"current_steps": 28340, "total_steps": 38160, "loss": 0.0116, "lr": 9.427829337783237e-06, "epoch": 14.853249475890985, "percentage": 74.27, "elapsed_time": "1:48:27", "remaining_time": "0:37:34", "throughput": 2848.47, "total_tokens": 18535608} {"current_steps": 28345, "total_steps": 38160, "loss": 0.0221, "lr": 9.418885789009138e-06, "epoch": 14.85587002096436, "percentage": 74.28, "elapsed_time": "1:48:28", "remaining_time": "0:37:33", "throughput": 2848.41, "total_tokens": 18538200} {"current_steps": 28350, "total_steps": 38160, "loss": 0.0059, "lr": 9.409945499626374e-06, "epoch": 14.858490566037736, "percentage": 74.29, "elapsed_time": "1:48:29", "remaining_time": "0:37:32", "throughput": 2848.32, "total_tokens": 18540600} {"current_steps": 28355, "total_steps": 38160, "loss": 0.0091, "lr": 9.40100847150516e-06, "epoch": 14.86111111111111, "percentage": 74.31, "elapsed_time": "1:48:30", "remaining_time": "0:37:31", "throughput": 2848.25, "total_tokens": 18543192} {"current_steps": 28360, "total_steps": 38160, "loss": 0.022, "lr": 9.392074706515003e-06, "epoch": 14.863731656184486, "percentage": 74.32, "elapsed_time": "1:48:31", "remaining_time": "0:37:30", "throughput": 2848.27, "total_tokens": 18546488} {"current_steps": 28365, "total_steps": 38160, "loss": 0.0161, "lr": 9.383144206524753e-06, "epoch": 14.866352201257861, "percentage": 74.33, "elapsed_time": "1:48:32", "remaining_time": "0:37:28", "throughput": 2848.3, "total_tokens": 18549752} {"current_steps": 28370, "total_steps": 38160, "loss": 0.009, "lr": 9.374216973402575e-06, "epoch": 14.868972746331236, "percentage": 74.34, "elapsed_time": "1:48:33", "remaining_time": "0:37:27", "throughput": 2848.27, "total_tokens": 18552696} {"current_steps": 28375, "total_steps": 38160, "loss": 0.0304, "lr": 9.365293009015926e-06, "epoch": 14.871593291404611, "percentage": 74.36, "elapsed_time": "1:48:34", "remaining_time": "0:37:26", "throughput": 2848.23, "total_tokens": 18555416} {"current_steps": 28380, "total_steps": 38160, "loss": 0.0468, "lr": 9.356372315231623e-06, "epoch": 14.874213836477988, "percentage": 74.37, "elapsed_time": "1:48:35", "remaining_time": "0:37:25", "throughput": 2848.25, "total_tokens": 18558712} {"current_steps": 28385, "total_steps": 38160, "loss": 0.0165, "lr": 9.347454893915749e-06, "epoch": 14.876834381551364, "percentage": 74.38, "elapsed_time": "1:48:36", "remaining_time": "0:37:24", "throughput": 2848.28, "total_tokens": 18562072} {"current_steps": 28390, "total_steps": 38160, "loss": 0.0184, "lr": 9.338540746933741e-06, "epoch": 14.879454926624739, "percentage": 74.4, "elapsed_time": "1:48:38", "remaining_time": "0:37:23", "throughput": 2848.3, "total_tokens": 18565208} {"current_steps": 28395, "total_steps": 38160, "loss": 0.0333, "lr": 9.329629876150339e-06, "epoch": 14.882075471698114, "percentage": 74.41, "elapsed_time": "1:48:39", "remaining_time": "0:37:21", "throughput": 2848.35, "total_tokens": 18568568} {"current_steps": 28400, "total_steps": 38160, "loss": 0.0054, "lr": 9.320722283429581e-06, "epoch": 14.884696016771489, "percentage": 74.42, "elapsed_time": "1:48:40", "remaining_time": "0:37:20", "throughput": 2848.31, "total_tokens": 18571384} {"current_steps": 28405, "total_steps": 38160, "loss": 0.0142, "lr": 9.311817970634854e-06, "epoch": 14.887316561844864, "percentage": 74.44, "elapsed_time": "1:48:41", "remaining_time": "0:37:19", "throughput": 2848.32, "total_tokens": 18574680} {"current_steps": 28410, "total_steps": 38160, "loss": 0.0142, "lr": 9.302916939628814e-06, "epoch": 14.88993710691824, "percentage": 74.45, "elapsed_time": "1:48:42", "remaining_time": "0:37:18", "throughput": 2848.28, "total_tokens": 18577464} {"current_steps": 28415, "total_steps": 38160, "loss": 0.0098, "lr": 9.29401919227347e-06, "epoch": 14.892557651991615, "percentage": 74.46, "elapsed_time": "1:48:43", "remaining_time": "0:37:17", "throughput": 2848.22, "total_tokens": 18580024} {"current_steps": 28420, "total_steps": 38160, "loss": 0.0305, "lr": 9.28512473043013e-06, "epoch": 14.89517819706499, "percentage": 74.48, "elapsed_time": "1:48:44", "remaining_time": "0:37:16", "throughput": 2848.17, "total_tokens": 18582840} {"current_steps": 28425, "total_steps": 38160, "loss": 0.0748, "lr": 9.276233555959419e-06, "epoch": 14.897798742138365, "percentage": 74.49, "elapsed_time": "1:48:45", "remaining_time": "0:37:14", "throughput": 2848.16, "total_tokens": 18585880} {"current_steps": 28430, "total_steps": 38160, "loss": 0.0224, "lr": 9.267345670721254e-06, "epoch": 14.90041928721174, "percentage": 74.5, "elapsed_time": "1:48:46", "remaining_time": "0:37:13", "throughput": 2848.15, "total_tokens": 18588920} {"current_steps": 28435, "total_steps": 38160, "loss": 0.0169, "lr": 9.258461076574895e-06, "epoch": 14.903039832285115, "percentage": 74.52, "elapsed_time": "1:48:47", "remaining_time": "0:37:12", "throughput": 2848.13, "total_tokens": 18591736} {"current_steps": 28440, "total_steps": 38160, "loss": 0.0293, "lr": 9.24957977537888e-06, "epoch": 14.90566037735849, "percentage": 74.53, "elapsed_time": "1:48:48", "remaining_time": "0:37:11", "throughput": 2848.08, "total_tokens": 18594392} {"current_steps": 28445, "total_steps": 38160, "loss": 0.0273, "lr": 9.240701768991086e-06, "epoch": 14.908280922431866, "percentage": 74.54, "elapsed_time": "1:48:49", "remaining_time": "0:37:10", "throughput": 2848.18, "total_tokens": 18598424} {"current_steps": 28450, "total_steps": 38160, "loss": 0.0179, "lr": 9.231827059268692e-06, "epoch": 14.91090146750524, "percentage": 74.55, "elapsed_time": "1:48:51", "remaining_time": "0:37:09", "throughput": 2848.2, "total_tokens": 18601976} {"current_steps": 28455, "total_steps": 38160, "loss": 0.0181, "lr": 9.222955648068193e-06, "epoch": 14.913522012578616, "percentage": 74.57, "elapsed_time": "1:48:52", "remaining_time": "0:37:07", "throughput": 2848.12, "total_tokens": 18604568} {"current_steps": 28460, "total_steps": 38160, "loss": 0.0124, "lr": 9.214087537245378e-06, "epoch": 14.916142557651991, "percentage": 74.58, "elapsed_time": "1:48:53", "remaining_time": "0:37:06", "throughput": 2848.11, "total_tokens": 18607544} {"current_steps": 28465, "total_steps": 38160, "loss": 0.012, "lr": 9.205222728655344e-06, "epoch": 14.918763102725366, "percentage": 74.59, "elapsed_time": "1:48:54", "remaining_time": "0:37:05", "throughput": 2848.18, "total_tokens": 18611352} {"current_steps": 28470, "total_steps": 38160, "loss": 0.0144, "lr": 9.196361224152522e-06, "epoch": 14.921383647798741, "percentage": 74.61, "elapsed_time": "1:48:55", "remaining_time": "0:37:04", "throughput": 2848.38, "total_tokens": 18616920} {"current_steps": 28475, "total_steps": 38160, "loss": 0.0505, "lr": 9.187503025590632e-06, "epoch": 14.924004192872118, "percentage": 74.62, "elapsed_time": "1:48:57", "remaining_time": "0:37:03", "throughput": 2848.31, "total_tokens": 18619544} {"current_steps": 28480, "total_steps": 38160, "loss": 0.0264, "lr": 9.17864813482272e-06, "epoch": 14.926624737945493, "percentage": 74.63, "elapsed_time": "1:48:58", "remaining_time": "0:37:02", "throughput": 2848.21, "total_tokens": 18622072} {"current_steps": 28485, "total_steps": 38160, "loss": 0.0517, "lr": 9.169796553701122e-06, "epoch": 14.929245283018869, "percentage": 74.65, "elapsed_time": "1:48:59", "remaining_time": "0:37:01", "throughput": 2848.17, "total_tokens": 18624952} {"current_steps": 28490, "total_steps": 38160, "loss": 0.0726, "lr": 9.160948284077473e-06, "epoch": 14.931865828092244, "percentage": 74.66, "elapsed_time": "1:49:00", "remaining_time": "0:36:59", "throughput": 2848.11, "total_tokens": 18627672} {"current_steps": 28495, "total_steps": 38160, "loss": 0.0203, "lr": 9.152103327802738e-06, "epoch": 14.934486373165619, "percentage": 74.67, "elapsed_time": "1:49:01", "remaining_time": "0:36:58", "throughput": 2848.15, "total_tokens": 18631160} {"current_steps": 28500, "total_steps": 38160, "loss": 0.0351, "lr": 9.143261686727189e-06, "epoch": 14.937106918238994, "percentage": 74.69, "elapsed_time": "1:49:02", "remaining_time": "0:36:57", "throughput": 2848.15, "total_tokens": 18634168} {"current_steps": 28505, "total_steps": 38160, "loss": 0.0076, "lr": 9.134423362700392e-06, "epoch": 14.93972746331237, "percentage": 74.7, "elapsed_time": "1:49:03", "remaining_time": "0:36:56", "throughput": 2848.1, "total_tokens": 18636984} {"current_steps": 28510, "total_steps": 38160, "loss": 0.0306, "lr": 9.12558835757123e-06, "epoch": 14.942348008385745, "percentage": 74.71, "elapsed_time": "1:49:04", "remaining_time": "0:36:55", "throughput": 2848.09, "total_tokens": 18639864} {"current_steps": 28515, "total_steps": 38160, "loss": 0.0206, "lr": 9.116756673187878e-06, "epoch": 14.94496855345912, "percentage": 74.72, "elapsed_time": "1:49:05", "remaining_time": "0:36:54", "throughput": 2848.01, "total_tokens": 18642264} {"current_steps": 28520, "total_steps": 38160, "loss": 0.0309, "lr": 9.107928311397817e-06, "epoch": 14.947589098532495, "percentage": 74.74, "elapsed_time": "1:49:06", "remaining_time": "0:36:52", "throughput": 2848.1, "total_tokens": 18646072} {"current_steps": 28525, "total_steps": 38160, "loss": 0.0135, "lr": 9.09910327404785e-06, "epoch": 14.95020964360587, "percentage": 74.75, "elapsed_time": "1:49:07", "remaining_time": "0:36:51", "throughput": 2848.03, "total_tokens": 18648696} {"current_steps": 28530, "total_steps": 38160, "loss": 0.0233, "lr": 9.090281562984068e-06, "epoch": 14.952830188679245, "percentage": 74.76, "elapsed_time": "1:49:09", "remaining_time": "0:36:50", "throughput": 2847.98, "total_tokens": 18651608} {"current_steps": 28535, "total_steps": 38160, "loss": 0.0224, "lr": 9.081463180051883e-06, "epoch": 14.95545073375262, "percentage": 74.78, "elapsed_time": "1:49:10", "remaining_time": "0:36:49", "throughput": 2848.01, "total_tokens": 18655064} {"current_steps": 28540, "total_steps": 38160, "loss": 0.0181, "lr": 9.072648127095996e-06, "epoch": 14.958071278825996, "percentage": 74.79, "elapsed_time": "1:49:11", "remaining_time": "0:36:48", "throughput": 2848.0, "total_tokens": 18658040} {"current_steps": 28545, "total_steps": 38160, "loss": 0.0126, "lr": 9.0638364059604e-06, "epoch": 14.96069182389937, "percentage": 74.8, "elapsed_time": "1:49:12", "remaining_time": "0:36:47", "throughput": 2847.9, "total_tokens": 18660472} {"current_steps": 28550, "total_steps": 38160, "loss": 0.0193, "lr": 9.055028018488417e-06, "epoch": 14.963312368972746, "percentage": 74.82, "elapsed_time": "1:49:13", "remaining_time": "0:36:45", "throughput": 2847.97, "total_tokens": 18664216} {"current_steps": 28555, "total_steps": 38160, "loss": 0.0158, "lr": 9.046222966522665e-06, "epoch": 14.965932914046121, "percentage": 74.83, "elapsed_time": "1:49:14", "remaining_time": "0:36:44", "throughput": 2847.95, "total_tokens": 18667224} {"current_steps": 28560, "total_steps": 38160, "loss": 0.0265, "lr": 9.037421251905059e-06, "epoch": 14.968553459119496, "percentage": 74.84, "elapsed_time": "1:49:15", "remaining_time": "0:36:43", "throughput": 2847.92, "total_tokens": 18670008} {"current_steps": 28565, "total_steps": 38160, "loss": 0.0079, "lr": 9.028622876476833e-06, "epoch": 14.971174004192871, "percentage": 74.86, "elapsed_time": "1:49:16", "remaining_time": "0:36:42", "throughput": 2847.89, "total_tokens": 18672888} {"current_steps": 28570, "total_steps": 38160, "loss": 0.015, "lr": 9.019827842078474e-06, "epoch": 14.973794549266248, "percentage": 74.87, "elapsed_time": "1:49:17", "remaining_time": "0:36:41", "throughput": 2847.94, "total_tokens": 18676440} {"current_steps": 28575, "total_steps": 38160, "loss": 0.1736, "lr": 9.011036150549817e-06, "epoch": 14.976415094339622, "percentage": 74.88, "elapsed_time": "1:49:18", "remaining_time": "0:36:40", "throughput": 2847.93, "total_tokens": 18679480} {"current_steps": 28580, "total_steps": 38160, "loss": 0.0081, "lr": 9.002247803729987e-06, "epoch": 14.979035639412999, "percentage": 74.9, "elapsed_time": "1:49:20", "remaining_time": "0:36:38", "throughput": 2848.02, "total_tokens": 18683096} {"current_steps": 28585, "total_steps": 38160, "loss": 0.0316, "lr": 8.993462803457404e-06, "epoch": 14.981656184486374, "percentage": 74.91, "elapsed_time": "1:49:21", "remaining_time": "0:36:37", "throughput": 2847.89, "total_tokens": 18685304} {"current_steps": 28590, "total_steps": 38160, "loss": 0.0242, "lr": 8.984681151569799e-06, "epoch": 14.984276729559749, "percentage": 74.92, "elapsed_time": "1:49:22", "remaining_time": "0:36:36", "throughput": 2847.77, "total_tokens": 18687640} {"current_steps": 28595, "total_steps": 38160, "loss": 0.0157, "lr": 8.975902849904183e-06, "epoch": 14.986897274633124, "percentage": 74.93, "elapsed_time": "1:49:23", "remaining_time": "0:36:35", "throughput": 2847.86, "total_tokens": 18691832} {"current_steps": 28600, "total_steps": 38160, "loss": 0.038, "lr": 8.967127900296874e-06, "epoch": 14.9895178197065, "percentage": 74.95, "elapsed_time": "1:49:24", "remaining_time": "0:36:34", "throughput": 2847.82, "total_tokens": 18694744} {"current_steps": 28605, "total_steps": 38160, "loss": 0.0366, "lr": 8.95835630458349e-06, "epoch": 14.992138364779874, "percentage": 74.96, "elapsed_time": "1:49:25", "remaining_time": "0:36:33", "throughput": 2847.96, "total_tokens": 18699096} {"current_steps": 28610, "total_steps": 38160, "loss": 0.0295, "lr": 8.949588064598958e-06, "epoch": 14.99475890985325, "percentage": 74.97, "elapsed_time": "1:49:26", "remaining_time": "0:36:32", "throughput": 2847.93, "total_tokens": 18702168} {"current_steps": 28615, "total_steps": 38160, "loss": 0.0118, "lr": 8.940823182177499e-06, "epoch": 14.997379454926625, "percentage": 74.99, "elapsed_time": "1:49:28", "remaining_time": "0:36:30", "throughput": 2847.88, "total_tokens": 18704920} {"current_steps": 28620, "total_steps": 38160, "loss": 0.0165, "lr": 8.932061659152607e-06, "epoch": 15.0, "percentage": 75.0, "elapsed_time": "1:49:29", "remaining_time": "0:36:29", "throughput": 2847.68, "total_tokens": 18706976} {"current_steps": 28620, "total_steps": 38160, "eval_loss": 1.3870089054107666, "epoch": 15.0, "percentage": 75.0, "elapsed_time": "1:49:40", "remaining_time": "0:36:33", "throughput": 2842.62, "total_tokens": 18706976} {"current_steps": 28625, "total_steps": 38160, "loss": 0.01, "lr": 8.92330349735711e-06, "epoch": 15.002620545073375, "percentage": 75.01, "elapsed_time": "1:49:45", "remaining_time": "0:36:33", "throughput": 2841.27, "total_tokens": 18710720} {"current_steps": 28630, "total_steps": 38160, "loss": 0.0069, "lr": 8.914548698623104e-06, "epoch": 15.00524109014675, "percentage": 75.03, "elapsed_time": "1:49:46", "remaining_time": "0:36:32", "throughput": 2841.34, "total_tokens": 18714528} {"current_steps": 28635, "total_steps": 38160, "loss": 0.0072, "lr": 8.905797264781995e-06, "epoch": 15.007861635220126, "percentage": 75.04, "elapsed_time": "1:49:47", "remaining_time": "0:36:31", "throughput": 2841.26, "total_tokens": 18717120} {"current_steps": 28640, "total_steps": 38160, "loss": 0.0232, "lr": 8.89704919766449e-06, "epoch": 15.0104821802935, "percentage": 75.05, "elapsed_time": "1:49:48", "remaining_time": "0:36:30", "throughput": 2841.19, "total_tokens": 18719776} {"current_steps": 28645, "total_steps": 38160, "loss": 0.0073, "lr": 8.888304499100586e-06, "epoch": 15.013102725366876, "percentage": 75.07, "elapsed_time": "1:49:49", "remaining_time": "0:36:28", "throughput": 2841.18, "total_tokens": 18722976} {"current_steps": 28650, "total_steps": 38160, "loss": 0.0273, "lr": 8.879563170919566e-06, "epoch": 15.015723270440251, "percentage": 75.08, "elapsed_time": "1:49:51", "remaining_time": "0:36:27", "throughput": 2841.18, "total_tokens": 18726432} {"current_steps": 28655, "total_steps": 38160, "loss": 0.0156, "lr": 8.870825214950016e-06, "epoch": 15.018343815513626, "percentage": 75.09, "elapsed_time": "1:49:52", "remaining_time": "0:36:26", "throughput": 2841.15, "total_tokens": 18729440} {"current_steps": 28660, "total_steps": 38160, "loss": 0.0071, "lr": 8.862090633019818e-06, "epoch": 15.020964360587001, "percentage": 75.1, "elapsed_time": "1:49:53", "remaining_time": "0:36:25", "throughput": 2841.12, "total_tokens": 18732256} {"current_steps": 28665, "total_steps": 38160, "loss": 0.0387, "lr": 8.853359426956146e-06, "epoch": 15.023584905660377, "percentage": 75.12, "elapsed_time": "1:49:54", "remaining_time": "0:36:24", "throughput": 2841.2, "total_tokens": 18736480} {"current_steps": 28670, "total_steps": 38160, "loss": 0.0148, "lr": 8.844631598585482e-06, "epoch": 15.026205450733753, "percentage": 75.13, "elapsed_time": "1:49:55", "remaining_time": "0:36:23", "throughput": 2841.14, "total_tokens": 18739200} {"current_steps": 28675, "total_steps": 38160, "loss": 0.0162, "lr": 8.835907149733569e-06, "epoch": 15.028825995807129, "percentage": 75.14, "elapsed_time": "1:49:56", "remaining_time": "0:36:22", "throughput": 2841.02, "total_tokens": 18741536} {"current_steps": 28680, "total_steps": 38160, "loss": 0.0223, "lr": 8.827186082225477e-06, "epoch": 15.031446540880504, "percentage": 75.16, "elapsed_time": "1:49:57", "remaining_time": "0:36:20", "throughput": 2841.01, "total_tokens": 18744672} {"current_steps": 28685, "total_steps": 38160, "loss": 0.0291, "lr": 8.81846839788554e-06, "epoch": 15.034067085953879, "percentage": 75.17, "elapsed_time": "1:49:58", "remaining_time": "0:36:19", "throughput": 2841.03, "total_tokens": 18747904} {"current_steps": 28690, "total_steps": 38160, "loss": 0.0139, "lr": 8.809754098537407e-06, "epoch": 15.036687631027254, "percentage": 75.18, "elapsed_time": "1:50:00", "remaining_time": "0:36:18", "throughput": 2841.15, "total_tokens": 18752000} {"current_steps": 28695, "total_steps": 38160, "loss": 0.0121, "lr": 8.801043186004016e-06, "epoch": 15.03930817610063, "percentage": 75.2, "elapsed_time": "1:50:01", "remaining_time": "0:36:17", "throughput": 2841.19, "total_tokens": 18755616} {"current_steps": 28700, "total_steps": 38160, "loss": 0.013, "lr": 8.792335662107575e-06, "epoch": 15.041928721174004, "percentage": 75.21, "elapsed_time": "1:50:02", "remaining_time": "0:36:16", "throughput": 2841.12, "total_tokens": 18758240} {"current_steps": 28705, "total_steps": 38160, "loss": 0.0047, "lr": 8.783631528669605e-06, "epoch": 15.04454926624738, "percentage": 75.22, "elapsed_time": "1:50:03", "remaining_time": "0:36:15", "throughput": 2841.26, "total_tokens": 18762368} {"current_steps": 28710, "total_steps": 38160, "loss": 0.0075, "lr": 8.774930787510924e-06, "epoch": 15.047169811320755, "percentage": 75.24, "elapsed_time": "1:50:04", "remaining_time": "0:36:13", "throughput": 2841.23, "total_tokens": 18765152} {"current_steps": 28715, "total_steps": 38160, "loss": 0.0382, "lr": 8.766233440451608e-06, "epoch": 15.04979035639413, "percentage": 75.25, "elapsed_time": "1:50:05", "remaining_time": "0:36:12", "throughput": 2841.31, "total_tokens": 18768928} {"current_steps": 28720, "total_steps": 38160, "loss": 0.0067, "lr": 8.75753948931105e-06, "epoch": 15.052410901467505, "percentage": 75.26, "elapsed_time": "1:50:06", "remaining_time": "0:36:11", "throughput": 2841.23, "total_tokens": 18771488} {"current_steps": 28725, "total_steps": 38160, "loss": 0.0079, "lr": 8.748848935907936e-06, "epoch": 15.05503144654088, "percentage": 75.28, "elapsed_time": "1:50:07", "remaining_time": "0:36:10", "throughput": 2841.19, "total_tokens": 18774272} {"current_steps": 28730, "total_steps": 38160, "loss": 0.0081, "lr": 8.740161782060214e-06, "epoch": 15.057651991614255, "percentage": 75.29, "elapsed_time": "1:50:08", "remaining_time": "0:36:09", "throughput": 2841.11, "total_tokens": 18776704} {"current_steps": 28735, "total_steps": 38160, "loss": 0.0117, "lr": 8.731478029585144e-06, "epoch": 15.06027253668763, "percentage": 75.3, "elapsed_time": "1:50:09", "remaining_time": "0:36:08", "throughput": 2841.09, "total_tokens": 18779520} {"current_steps": 28740, "total_steps": 38160, "loss": 0.0078, "lr": 8.722797680299278e-06, "epoch": 15.062893081761006, "percentage": 75.31, "elapsed_time": "1:50:11", "remaining_time": "0:36:06", "throughput": 2841.07, "total_tokens": 18782336} {"current_steps": 28745, "total_steps": 38160, "loss": 0.0182, "lr": 8.71412073601843e-06, "epoch": 15.065513626834381, "percentage": 75.33, "elapsed_time": "1:50:12", "remaining_time": "0:36:05", "throughput": 2841.08, "total_tokens": 18785504} {"current_steps": 28750, "total_steps": 38160, "loss": 0.0078, "lr": 8.705447198557731e-06, "epoch": 15.068134171907756, "percentage": 75.34, "elapsed_time": "1:50:13", "remaining_time": "0:36:04", "throughput": 2841.07, "total_tokens": 18788480} {"current_steps": 28755, "total_steps": 38160, "loss": 0.0527, "lr": 8.696777069731574e-06, "epoch": 15.070754716981131, "percentage": 75.35, "elapsed_time": "1:50:14", "remaining_time": "0:36:03", "throughput": 2841.33, "total_tokens": 18794144} {"current_steps": 28760, "total_steps": 38160, "loss": 0.007, "lr": 8.688110351353654e-06, "epoch": 15.073375262054507, "percentage": 75.37, "elapsed_time": "1:50:15", "remaining_time": "0:36:02", "throughput": 2841.22, "total_tokens": 18797376} {"current_steps": 28765, "total_steps": 38160, "loss": 0.0258, "lr": 8.679447045236962e-06, "epoch": 15.075995807127883, "percentage": 75.38, "elapsed_time": "1:50:17", "remaining_time": "0:36:01", "throughput": 2841.25, "total_tokens": 18800672} {"current_steps": 28770, "total_steps": 38160, "loss": 0.0104, "lr": 8.670787153193746e-06, "epoch": 15.078616352201259, "percentage": 75.39, "elapsed_time": "1:50:18", "remaining_time": "0:36:00", "throughput": 2841.25, "total_tokens": 18803648} {"current_steps": 28775, "total_steps": 38160, "loss": 0.0108, "lr": 8.662130677035574e-06, "epoch": 15.081236897274634, "percentage": 75.41, "elapsed_time": "1:50:19", "remaining_time": "0:35:58", "throughput": 2841.17, "total_tokens": 18806144} {"current_steps": 28780, "total_steps": 38160, "loss": 0.019, "lr": 8.65347761857326e-06, "epoch": 15.083857442348009, "percentage": 75.42, "elapsed_time": "1:50:20", "remaining_time": "0:35:57", "throughput": 2841.18, "total_tokens": 18809152} {"current_steps": 28785, "total_steps": 38160, "loss": 0.0106, "lr": 8.64482797961694e-06, "epoch": 15.086477987421384, "percentage": 75.43, "elapsed_time": "1:50:21", "remaining_time": "0:35:56", "throughput": 2841.16, "total_tokens": 18812192} {"current_steps": 28790, "total_steps": 38160, "loss": 0.025, "lr": 8.636181761976016e-06, "epoch": 15.08909853249476, "percentage": 75.45, "elapsed_time": "1:50:22", "remaining_time": "0:35:55", "throughput": 2841.16, "total_tokens": 18815168} {"current_steps": 28795, "total_steps": 38160, "loss": 0.0222, "lr": 8.62753896745919e-06, "epoch": 15.091719077568134, "percentage": 75.46, "elapsed_time": "1:50:23", "remaining_time": "0:35:54", "throughput": 2841.27, "total_tokens": 18819072} {"current_steps": 28800, "total_steps": 38160, "loss": 0.0133, "lr": 8.618899597874413e-06, "epoch": 15.09433962264151, "percentage": 75.47, "elapsed_time": "1:50:24", "remaining_time": "0:35:52", "throughput": 2841.2, "total_tokens": 18821728} {"current_steps": 28805, "total_steps": 38160, "loss": 0.018, "lr": 8.610263655028964e-06, "epoch": 15.096960167714885, "percentage": 75.48, "elapsed_time": "1:50:25", "remaining_time": "0:35:51", "throughput": 2841.18, "total_tokens": 18824544} {"current_steps": 28810, "total_steps": 38160, "loss": 0.0117, "lr": 8.601631140729366e-06, "epoch": 15.09958071278826, "percentage": 75.5, "elapsed_time": "1:50:26", "remaining_time": "0:35:50", "throughput": 2841.16, "total_tokens": 18828032} {"current_steps": 28815, "total_steps": 38160, "loss": 0.016, "lr": 8.593002056781451e-06, "epoch": 15.102201257861635, "percentage": 75.51, "elapsed_time": "1:50:27", "remaining_time": "0:35:49", "throughput": 2841.11, "total_tokens": 18830688} {"current_steps": 28820, "total_steps": 38160, "loss": 0.0063, "lr": 8.584376404990326e-06, "epoch": 15.10482180293501, "percentage": 75.52, "elapsed_time": "1:50:29", "remaining_time": "0:35:48", "throughput": 2841.09, "total_tokens": 18833664} {"current_steps": 28825, "total_steps": 38160, "loss": 0.0107, "lr": 8.575754187160384e-06, "epoch": 15.107442348008385, "percentage": 75.54, "elapsed_time": "1:50:30", "remaining_time": "0:35:47", "throughput": 2841.19, "total_tokens": 18837536} {"current_steps": 28830, "total_steps": 38160, "loss": 0.0109, "lr": 8.567135405095291e-06, "epoch": 15.11006289308176, "percentage": 75.55, "elapsed_time": "1:50:31", "remaining_time": "0:35:46", "throughput": 2841.09, "total_tokens": 18840000} {"current_steps": 28835, "total_steps": 38160, "loss": 0.023, "lr": 8.558520060597985e-06, "epoch": 15.112683438155136, "percentage": 75.56, "elapsed_time": "1:50:32", "remaining_time": "0:35:44", "throughput": 2841.22, "total_tokens": 18844224} {"current_steps": 28840, "total_steps": 38160, "loss": 0.0129, "lr": 8.54990815547071e-06, "epoch": 15.115303983228511, "percentage": 75.58, "elapsed_time": "1:50:33", "remaining_time": "0:35:43", "throughput": 2841.2, "total_tokens": 18847104} {"current_steps": 28845, "total_steps": 38160, "loss": 0.0564, "lr": 8.541299691514974e-06, "epoch": 15.117924528301886, "percentage": 75.59, "elapsed_time": "1:50:34", "remaining_time": "0:35:42", "throughput": 2841.11, "total_tokens": 18849536} {"current_steps": 28850, "total_steps": 38160, "loss": 0.0082, "lr": 8.53269467053158e-06, "epoch": 15.120545073375261, "percentage": 75.6, "elapsed_time": "1:50:35", "remaining_time": "0:35:41", "throughput": 2841.25, "total_tokens": 18854528} {"current_steps": 28855, "total_steps": 38160, "loss": 0.0109, "lr": 8.524093094320593e-06, "epoch": 15.123165618448636, "percentage": 75.62, "elapsed_time": "1:50:37", "remaining_time": "0:35:40", "throughput": 2841.21, "total_tokens": 18857344} {"current_steps": 28860, "total_steps": 38160, "loss": 0.0089, "lr": 8.515494964681357e-06, "epoch": 15.125786163522013, "percentage": 75.63, "elapsed_time": "1:50:38", "remaining_time": "0:35:39", "throughput": 2841.11, "total_tokens": 18859872} {"current_steps": 28865, "total_steps": 38160, "loss": 0.0037, "lr": 8.506900283412506e-06, "epoch": 15.128406708595389, "percentage": 75.64, "elapsed_time": "1:50:39", "remaining_time": "0:35:37", "throughput": 2841.02, "total_tokens": 18862240} {"current_steps": 28870, "total_steps": 38160, "loss": 0.0072, "lr": 8.498309052311953e-06, "epoch": 15.131027253668764, "percentage": 75.66, "elapsed_time": "1:50:40", "remaining_time": "0:35:36", "throughput": 2841.04, "total_tokens": 18865472} {"current_steps": 28875, "total_steps": 38160, "loss": 0.0121, "lr": 8.489721273176887e-06, "epoch": 15.133647798742139, "percentage": 75.67, "elapsed_time": "1:50:41", "remaining_time": "0:35:35", "throughput": 2841.05, "total_tokens": 18868960} {"current_steps": 28880, "total_steps": 38160, "loss": 0.007, "lr": 8.481136947803777e-06, "epoch": 15.136268343815514, "percentage": 75.68, "elapsed_time": "1:50:42", "remaining_time": "0:35:34", "throughput": 2840.99, "total_tokens": 18871616} {"current_steps": 28885, "total_steps": 38160, "loss": 0.0254, "lr": 8.472556077988362e-06, "epoch": 15.13888888888889, "percentage": 75.69, "elapsed_time": "1:50:43", "remaining_time": "0:35:33", "throughput": 2841.04, "total_tokens": 18875040} {"current_steps": 28890, "total_steps": 38160, "loss": 0.021, "lr": 8.46397866552565e-06, "epoch": 15.141509433962264, "percentage": 75.71, "elapsed_time": "1:50:44", "remaining_time": "0:35:32", "throughput": 2840.96, "total_tokens": 18877632} {"current_steps": 28895, "total_steps": 38160, "loss": 0.0358, "lr": 8.455404712209952e-06, "epoch": 15.14412997903564, "percentage": 75.72, "elapsed_time": "1:50:45", "remaining_time": "0:35:30", "throughput": 2841.01, "total_tokens": 18881056} {"current_steps": 28900, "total_steps": 38160, "loss": 0.0191, "lr": 8.446834219834836e-06, "epoch": 15.146750524109015, "percentage": 75.73, "elapsed_time": "1:50:46", "remaining_time": "0:35:29", "throughput": 2840.96, "total_tokens": 18883616} {"current_steps": 28905, "total_steps": 38160, "loss": 0.0037, "lr": 8.43826719019316e-06, "epoch": 15.14937106918239, "percentage": 75.75, "elapsed_time": "1:50:48", "remaining_time": "0:35:28", "throughput": 2840.94, "total_tokens": 18886592} {"current_steps": 28910, "total_steps": 38160, "loss": 0.0115, "lr": 8.429703625077043e-06, "epoch": 15.151991614255765, "percentage": 75.76, "elapsed_time": "1:50:49", "remaining_time": "0:35:27", "throughput": 2841.1, "total_tokens": 18891104} {"current_steps": 28915, "total_steps": 38160, "loss": 0.0063, "lr": 8.421143526277875e-06, "epoch": 15.15461215932914, "percentage": 75.77, "elapsed_time": "1:50:50", "remaining_time": "0:35:26", "throughput": 2841.12, "total_tokens": 18894528} {"current_steps": 28920, "total_steps": 38160, "loss": 0.021, "lr": 8.41258689558634e-06, "epoch": 15.157232704402515, "percentage": 75.79, "elapsed_time": "1:50:51", "remaining_time": "0:35:25", "throughput": 2841.13, "total_tokens": 18897760} {"current_steps": 28925, "total_steps": 38160, "loss": 0.0149, "lr": 8.404033734792386e-06, "epoch": 15.15985324947589, "percentage": 75.8, "elapsed_time": "1:50:52", "remaining_time": "0:35:23", "throughput": 2841.15, "total_tokens": 18900800} {"current_steps": 28930, "total_steps": 38160, "loss": 0.023, "lr": 8.395484045685248e-06, "epoch": 15.162473794549266, "percentage": 75.81, "elapsed_time": "1:50:53", "remaining_time": "0:35:22", "throughput": 2841.13, "total_tokens": 18903680} {"current_steps": 28935, "total_steps": 38160, "loss": 0.0091, "lr": 8.386937830053412e-06, "epoch": 15.165094339622641, "percentage": 75.83, "elapsed_time": "1:50:54", "remaining_time": "0:35:21", "throughput": 2841.08, "total_tokens": 18906336} {"current_steps": 28940, "total_steps": 38160, "loss": 0.0184, "lr": 8.37839508968464e-06, "epoch": 15.167714884696016, "percentage": 75.84, "elapsed_time": "1:50:55", "remaining_time": "0:35:20", "throughput": 2841.16, "total_tokens": 18910112} {"current_steps": 28945, "total_steps": 38160, "loss": 0.0119, "lr": 8.369855826365988e-06, "epoch": 15.170335429769391, "percentage": 75.85, "elapsed_time": "1:50:56", "remaining_time": "0:35:19", "throughput": 2841.13, "total_tokens": 18912928} {"current_steps": 28950, "total_steps": 38160, "loss": 0.0129, "lr": 8.361320041883772e-06, "epoch": 15.172955974842766, "percentage": 75.86, "elapsed_time": "1:50:57", "remaining_time": "0:35:18", "throughput": 2841.2, "total_tokens": 18916416} {"current_steps": 28955, "total_steps": 38160, "loss": 0.0126, "lr": 8.352787738023576e-06, "epoch": 15.175576519916143, "percentage": 75.88, "elapsed_time": "1:50:58", "remaining_time": "0:35:16", "throughput": 2841.27, "total_tokens": 18919968} {"current_steps": 28960, "total_steps": 38160, "loss": 0.0158, "lr": 8.344258916570274e-06, "epoch": 15.178197064989519, "percentage": 75.89, "elapsed_time": "1:51:00", "remaining_time": "0:35:15", "throughput": 2841.31, "total_tokens": 18923392} {"current_steps": 28965, "total_steps": 38160, "loss": 0.0108, "lr": 8.335733579307988e-06, "epoch": 15.180817610062894, "percentage": 75.9, "elapsed_time": "1:51:01", "remaining_time": "0:35:14", "throughput": 2841.3, "total_tokens": 18926528} {"current_steps": 28970, "total_steps": 38160, "loss": 0.0069, "lr": 8.327211728020113e-06, "epoch": 15.183438155136269, "percentage": 75.92, "elapsed_time": "1:51:02", "remaining_time": "0:35:13", "throughput": 2841.3, "total_tokens": 18929696} {"current_steps": 28975, "total_steps": 38160, "loss": 0.0095, "lr": 8.31869336448933e-06, "epoch": 15.186058700209644, "percentage": 75.93, "elapsed_time": "1:51:03", "remaining_time": "0:35:12", "throughput": 2841.24, "total_tokens": 18932384} {"current_steps": 28980, "total_steps": 38160, "loss": 0.0071, "lr": 8.310178490497586e-06, "epoch": 15.18867924528302, "percentage": 75.94, "elapsed_time": "1:51:04", "remaining_time": "0:35:11", "throughput": 2841.16, "total_tokens": 18934880} {"current_steps": 28985, "total_steps": 38160, "loss": 0.0031, "lr": 8.301667107826103e-06, "epoch": 15.191299790356394, "percentage": 75.96, "elapsed_time": "1:51:05", "remaining_time": "0:35:09", "throughput": 2841.22, "total_tokens": 18938816} {"current_steps": 28990, "total_steps": 38160, "loss": 0.0168, "lr": 8.293159218255345e-06, "epoch": 15.19392033542977, "percentage": 75.97, "elapsed_time": "1:51:06", "remaining_time": "0:35:08", "throughput": 2841.19, "total_tokens": 18941824} {"current_steps": 28995, "total_steps": 38160, "loss": 0.0168, "lr": 8.284654823565088e-06, "epoch": 15.196540880503145, "percentage": 75.98, "elapsed_time": "1:51:07", "remaining_time": "0:35:07", "throughput": 2841.22, "total_tokens": 18945056} {"current_steps": 29000, "total_steps": 38160, "loss": 0.0165, "lr": 8.276153925534333e-06, "epoch": 15.19916142557652, "percentage": 76.0, "elapsed_time": "1:51:09", "remaining_time": "0:35:06", "throughput": 2841.24, "total_tokens": 18948256} {"current_steps": 29005, "total_steps": 38160, "loss": 0.0201, "lr": 8.267656525941383e-06, "epoch": 15.201781970649895, "percentage": 76.01, "elapsed_time": "1:51:10", "remaining_time": "0:35:05", "throughput": 2841.21, "total_tokens": 18951008} {"current_steps": 29010, "total_steps": 38160, "loss": 0.0132, "lr": 8.259162626563801e-06, "epoch": 15.20440251572327, "percentage": 76.02, "elapsed_time": "1:51:11", "remaining_time": "0:35:04", "throughput": 2841.26, "total_tokens": 18954464} {"current_steps": 29015, "total_steps": 38160, "loss": 0.0148, "lr": 8.250672229178402e-06, "epoch": 15.207023060796645, "percentage": 76.04, "elapsed_time": "1:51:12", "remaining_time": "0:35:03", "throughput": 2841.35, "total_tokens": 18958464} {"current_steps": 29020, "total_steps": 38160, "loss": 0.0039, "lr": 8.242185335561295e-06, "epoch": 15.20964360587002, "percentage": 76.05, "elapsed_time": "1:51:13", "remaining_time": "0:35:01", "throughput": 2841.27, "total_tokens": 18961152} {"current_steps": 29025, "total_steps": 38160, "loss": 0.0082, "lr": 8.23370194748782e-06, "epoch": 15.212264150943396, "percentage": 76.06, "elapsed_time": "1:51:14", "remaining_time": "0:35:00", "throughput": 2841.33, "total_tokens": 18964640} {"current_steps": 29030, "total_steps": 38160, "loss": 0.0162, "lr": 8.22522206673262e-06, "epoch": 15.214884696016771, "percentage": 76.07, "elapsed_time": "1:51:15", "remaining_time": "0:34:59", "throughput": 2841.34, "total_tokens": 18967616} {"current_steps": 29035, "total_steps": 38160, "loss": 0.0375, "lr": 8.216745695069589e-06, "epoch": 15.217505241090146, "percentage": 76.09, "elapsed_time": "1:51:16", "remaining_time": "0:34:58", "throughput": 2841.33, "total_tokens": 18971136} {"current_steps": 29040, "total_steps": 38160, "loss": 0.0319, "lr": 8.208272834271894e-06, "epoch": 15.220125786163521, "percentage": 76.1, "elapsed_time": "1:51:17", "remaining_time": "0:34:57", "throughput": 2841.34, "total_tokens": 18974208} {"current_steps": 29045, "total_steps": 38160, "loss": 0.0107, "lr": 8.19980348611194e-06, "epoch": 15.222746331236896, "percentage": 76.11, "elapsed_time": "1:51:19", "remaining_time": "0:34:56", "throughput": 2841.35, "total_tokens": 18977408} {"current_steps": 29050, "total_steps": 38160, "loss": 0.0179, "lr": 8.191337652361439e-06, "epoch": 15.225366876310272, "percentage": 76.13, "elapsed_time": "1:51:20", "remaining_time": "0:34:54", "throughput": 2841.31, "total_tokens": 18980288} {"current_steps": 29055, "total_steps": 38160, "loss": 0.0093, "lr": 8.182875334791332e-06, "epoch": 15.227987421383649, "percentage": 76.14, "elapsed_time": "1:51:21", "remaining_time": "0:34:53", "throughput": 2841.42, "total_tokens": 18984096} {"current_steps": 29060, "total_steps": 38160, "loss": 0.0346, "lr": 8.174416535171841e-06, "epoch": 15.230607966457024, "percentage": 76.15, "elapsed_time": "1:51:22", "remaining_time": "0:34:52", "throughput": 2841.48, "total_tokens": 18987648} {"current_steps": 29065, "total_steps": 38160, "loss": 0.0064, "lr": 8.165961255272467e-06, "epoch": 15.233228511530399, "percentage": 76.17, "elapsed_time": "1:51:23", "remaining_time": "0:34:51", "throughput": 2841.4, "total_tokens": 18990208} {"current_steps": 29070, "total_steps": 38160, "loss": 0.0083, "lr": 8.157509496861935e-06, "epoch": 15.235849056603774, "percentage": 76.18, "elapsed_time": "1:51:24", "remaining_time": "0:34:50", "throughput": 2841.43, "total_tokens": 18993440} {"current_steps": 29075, "total_steps": 38160, "loss": 0.0109, "lr": 8.149061261708266e-06, "epoch": 15.23846960167715, "percentage": 76.19, "elapsed_time": "1:51:25", "remaining_time": "0:34:49", "throughput": 2841.49, "total_tokens": 18997024} {"current_steps": 29080, "total_steps": 38160, "loss": 0.0069, "lr": 8.140616551578745e-06, "epoch": 15.241090146750524, "percentage": 76.21, "elapsed_time": "1:51:26", "remaining_time": "0:34:47", "throughput": 2841.59, "total_tokens": 19000864} {"current_steps": 29085, "total_steps": 38160, "loss": 0.0159, "lr": 8.13217536823989e-06, "epoch": 15.2437106918239, "percentage": 76.22, "elapsed_time": "1:51:27", "remaining_time": "0:34:46", "throughput": 2841.65, "total_tokens": 19004576} {"current_steps": 29090, "total_steps": 38160, "loss": 0.0079, "lr": 8.12373771345752e-06, "epoch": 15.246331236897275, "percentage": 76.23, "elapsed_time": "1:51:28", "remaining_time": "0:34:45", "throughput": 2841.71, "total_tokens": 19008128} {"current_steps": 29095, "total_steps": 38160, "loss": 0.0323, "lr": 8.115303588996676e-06, "epoch": 15.24895178197065, "percentage": 76.24, "elapsed_time": "1:51:30", "remaining_time": "0:34:44", "throughput": 2841.86, "total_tokens": 19013952} {"current_steps": 29100, "total_steps": 38160, "loss": 0.0098, "lr": 8.10687299662169e-06, "epoch": 15.251572327044025, "percentage": 76.26, "elapsed_time": "1:51:31", "remaining_time": "0:34:43", "throughput": 2841.89, "total_tokens": 19017216} {"current_steps": 29105, "total_steps": 38160, "loss": 0.0089, "lr": 8.098445938096147e-06, "epoch": 15.2541928721174, "percentage": 76.27, "elapsed_time": "1:51:32", "remaining_time": "0:34:42", "throughput": 2841.87, "total_tokens": 19020096} {"current_steps": 29110, "total_steps": 38160, "loss": 0.0132, "lr": 8.090022415182898e-06, "epoch": 15.256813417190775, "percentage": 76.28, "elapsed_time": "1:51:33", "remaining_time": "0:34:41", "throughput": 2841.89, "total_tokens": 19023456} {"current_steps": 29115, "total_steps": 38160, "loss": 0.017, "lr": 8.081602429644033e-06, "epoch": 15.25943396226415, "percentage": 76.3, "elapsed_time": "1:51:35", "remaining_time": "0:34:39", "throughput": 2841.97, "total_tokens": 19027424} {"current_steps": 29120, "total_steps": 38160, "loss": 0.0218, "lr": 8.073185983240932e-06, "epoch": 15.262054507337526, "percentage": 76.31, "elapsed_time": "1:51:36", "remaining_time": "0:34:38", "throughput": 2842.05, "total_tokens": 19030976} {"current_steps": 29125, "total_steps": 38160, "loss": 0.0127, "lr": 8.064773077734206e-06, "epoch": 15.264675052410901, "percentage": 76.32, "elapsed_time": "1:51:37", "remaining_time": "0:34:37", "throughput": 2842.13, "total_tokens": 19034976} {"current_steps": 29130, "total_steps": 38160, "loss": 0.0149, "lr": 8.05636371488374e-06, "epoch": 15.267295597484276, "percentage": 76.34, "elapsed_time": "1:51:38", "remaining_time": "0:34:36", "throughput": 2842.24, "total_tokens": 19038752} {"current_steps": 29135, "total_steps": 38160, "loss": 0.0206, "lr": 8.047957896448696e-06, "epoch": 15.269916142557651, "percentage": 76.35, "elapsed_time": "1:51:39", "remaining_time": "0:34:35", "throughput": 2842.19, "total_tokens": 19041536} {"current_steps": 29140, "total_steps": 38160, "loss": 0.0128, "lr": 8.039555624187451e-06, "epoch": 15.272536687631026, "percentage": 76.36, "elapsed_time": "1:51:40", "remaining_time": "0:34:34", "throughput": 2842.18, "total_tokens": 19044448} {"current_steps": 29145, "total_steps": 38160, "loss": 0.0254, "lr": 8.031156899857681e-06, "epoch": 15.275157232704402, "percentage": 76.38, "elapsed_time": "1:51:41", "remaining_time": "0:34:32", "throughput": 2842.25, "total_tokens": 19047904} {"current_steps": 29150, "total_steps": 38160, "loss": 0.0245, "lr": 8.022761725216288e-06, "epoch": 15.277777777777779, "percentage": 76.39, "elapsed_time": "1:51:42", "remaining_time": "0:34:31", "throughput": 2842.45, "total_tokens": 19052864} {"current_steps": 29155, "total_steps": 38160, "loss": 0.0747, "lr": 8.014370102019456e-06, "epoch": 15.280398322851154, "percentage": 76.4, "elapsed_time": "1:51:44", "remaining_time": "0:34:30", "throughput": 2842.37, "total_tokens": 19055456} {"current_steps": 29160, "total_steps": 38160, "loss": 0.0127, "lr": 8.005982032022616e-06, "epoch": 15.283018867924529, "percentage": 76.42, "elapsed_time": "1:51:45", "remaining_time": "0:34:29", "throughput": 2842.34, "total_tokens": 19058240} {"current_steps": 29165, "total_steps": 38160, "loss": 0.0127, "lr": 7.997597516980467e-06, "epoch": 15.285639412997904, "percentage": 76.43, "elapsed_time": "1:51:46", "remaining_time": "0:34:28", "throughput": 2842.47, "total_tokens": 19062336} {"current_steps": 29170, "total_steps": 38160, "loss": 0.0088, "lr": 7.989216558646942e-06, "epoch": 15.28825995807128, "percentage": 76.44, "elapsed_time": "1:51:47", "remaining_time": "0:34:27", "throughput": 2842.58, "total_tokens": 19066592} {"current_steps": 29175, "total_steps": 38160, "loss": 0.0118, "lr": 7.980839158775235e-06, "epoch": 15.290880503144654, "percentage": 76.45, "elapsed_time": "1:51:48", "remaining_time": "0:34:26", "throughput": 2842.6, "total_tokens": 19069888} {"current_steps": 29180, "total_steps": 38160, "loss": 0.01, "lr": 7.972465319117814e-06, "epoch": 15.29350104821803, "percentage": 76.47, "elapsed_time": "1:51:49", "remaining_time": "0:34:24", "throughput": 2842.65, "total_tokens": 19073152} {"current_steps": 29185, "total_steps": 38160, "loss": 0.0166, "lr": 7.964095041426386e-06, "epoch": 15.296121593291405, "percentage": 76.48, "elapsed_time": "1:51:50", "remaining_time": "0:34:23", "throughput": 2842.58, "total_tokens": 19075904} {"current_steps": 29190, "total_steps": 38160, "loss": 0.0657, "lr": 7.95572832745192e-06, "epoch": 15.29874213836478, "percentage": 76.49, "elapsed_time": "1:51:51", "remaining_time": "0:34:22", "throughput": 2842.63, "total_tokens": 19079584} {"current_steps": 29195, "total_steps": 38160, "loss": 0.0083, "lr": 7.947365178944643e-06, "epoch": 15.301362683438155, "percentage": 76.51, "elapsed_time": "1:51:53", "remaining_time": "0:34:21", "throughput": 2842.6, "total_tokens": 19082656} {"current_steps": 29200, "total_steps": 38160, "loss": 0.0143, "lr": 7.939005597654025e-06, "epoch": 15.30398322851153, "percentage": 76.52, "elapsed_time": "1:51:54", "remaining_time": "0:34:20", "throughput": 2842.66, "total_tokens": 19086208} {"current_steps": 29205, "total_steps": 38160, "loss": 0.0081, "lr": 7.930649585328787e-06, "epoch": 15.306603773584905, "percentage": 76.53, "elapsed_time": "1:51:55", "remaining_time": "0:34:19", "throughput": 2842.62, "total_tokens": 19089184} {"current_steps": 29210, "total_steps": 38160, "loss": 0.0118, "lr": 7.922297143716918e-06, "epoch": 15.30922431865828, "percentage": 76.55, "elapsed_time": "1:51:56", "remaining_time": "0:34:17", "throughput": 2842.76, "total_tokens": 19093664} {"current_steps": 29215, "total_steps": 38160, "loss": 0.0123, "lr": 7.913948274565652e-06, "epoch": 15.311844863731656, "percentage": 76.56, "elapsed_time": "1:51:57", "remaining_time": "0:34:16", "throughput": 2842.94, "total_tokens": 19098048} {"current_steps": 29220, "total_steps": 38160, "loss": 0.0117, "lr": 7.905602979621491e-06, "epoch": 15.314465408805031, "percentage": 76.57, "elapsed_time": "1:51:58", "remaining_time": "0:34:15", "throughput": 2843.03, "total_tokens": 19101760} {"current_steps": 29225, "total_steps": 38160, "loss": 0.0186, "lr": 7.897261260630159e-06, "epoch": 15.317085953878406, "percentage": 76.59, "elapsed_time": "1:52:00", "remaining_time": "0:34:14", "throughput": 2843.23, "total_tokens": 19106912} {"current_steps": 29230, "total_steps": 38160, "loss": 0.0106, "lr": 7.888923119336647e-06, "epoch": 15.319706498951781, "percentage": 76.6, "elapsed_time": "1:52:01", "remaining_time": "0:34:13", "throughput": 2843.28, "total_tokens": 19110272} {"current_steps": 29235, "total_steps": 38160, "loss": 0.0259, "lr": 7.880588557485203e-06, "epoch": 15.322327044025156, "percentage": 76.61, "elapsed_time": "1:52:02", "remaining_time": "0:34:12", "throughput": 2843.27, "total_tokens": 19113408} {"current_steps": 29240, "total_steps": 38160, "loss": 0.0199, "lr": 7.872257576819325e-06, "epoch": 15.324947589098532, "percentage": 76.62, "elapsed_time": "1:52:03", "remaining_time": "0:34:11", "throughput": 2843.33, "total_tokens": 19116864} {"current_steps": 29245, "total_steps": 38160, "loss": 0.0117, "lr": 7.863930179081769e-06, "epoch": 15.327568134171909, "percentage": 76.64, "elapsed_time": "1:52:04", "remaining_time": "0:34:09", "throughput": 2843.4, "total_tokens": 19120576} {"current_steps": 29250, "total_steps": 38160, "loss": 0.022, "lr": 7.855606366014517e-06, "epoch": 15.330188679245284, "percentage": 76.65, "elapsed_time": "1:52:05", "remaining_time": "0:34:08", "throughput": 2843.37, "total_tokens": 19123872} {"current_steps": 29255, "total_steps": 38160, "loss": 0.0112, "lr": 7.847286139358814e-06, "epoch": 15.332809224318659, "percentage": 76.66, "elapsed_time": "1:52:06", "remaining_time": "0:34:07", "throughput": 2843.32, "total_tokens": 19126688} {"current_steps": 29260, "total_steps": 38160, "loss": 0.0118, "lr": 7.838969500855162e-06, "epoch": 15.335429769392034, "percentage": 76.68, "elapsed_time": "1:52:07", "remaining_time": "0:34:06", "throughput": 2843.29, "total_tokens": 19129504} {"current_steps": 29265, "total_steps": 38160, "loss": 0.0145, "lr": 7.830656452243307e-06, "epoch": 15.33805031446541, "percentage": 76.69, "elapsed_time": "1:52:09", "remaining_time": "0:34:05", "throughput": 2843.22, "total_tokens": 19132064} {"current_steps": 29270, "total_steps": 38160, "loss": 0.0021, "lr": 7.822346995262241e-06, "epoch": 15.340670859538784, "percentage": 76.7, "elapsed_time": "1:52:10", "remaining_time": "0:34:04", "throughput": 2843.17, "total_tokens": 19134848} {"current_steps": 29275, "total_steps": 38160, "loss": 0.0194, "lr": 7.814041131650223e-06, "epoch": 15.34329140461216, "percentage": 76.72, "elapsed_time": "1:52:11", "remaining_time": "0:34:02", "throughput": 2843.14, "total_tokens": 19137632} {"current_steps": 29280, "total_steps": 38160, "loss": 0.0059, "lr": 7.805738863144731e-06, "epoch": 15.345911949685535, "percentage": 76.73, "elapsed_time": "1:52:12", "remaining_time": "0:34:01", "throughput": 2843.14, "total_tokens": 19140672} {"current_steps": 29285, "total_steps": 38160, "loss": 0.0144, "lr": 7.797440191482496e-06, "epoch": 15.34853249475891, "percentage": 76.74, "elapsed_time": "1:52:13", "remaining_time": "0:34:00", "throughput": 2843.19, "total_tokens": 19144192} {"current_steps": 29290, "total_steps": 38160, "loss": 0.0175, "lr": 7.789145118399518e-06, "epoch": 15.351153039832285, "percentage": 76.76, "elapsed_time": "1:52:14", "remaining_time": "0:33:59", "throughput": 2843.14, "total_tokens": 19146880} {"current_steps": 29295, "total_steps": 38160, "loss": 0.0151, "lr": 7.780853645631032e-06, "epoch": 15.35377358490566, "percentage": 76.77, "elapsed_time": "1:52:15", "remaining_time": "0:33:58", "throughput": 2843.19, "total_tokens": 19150400} {"current_steps": 29300, "total_steps": 38160, "loss": 0.0048, "lr": 7.772565774911522e-06, "epoch": 15.356394129979035, "percentage": 76.78, "elapsed_time": "1:52:16", "remaining_time": "0:33:57", "throughput": 2843.19, "total_tokens": 19153504} {"current_steps": 29305, "total_steps": 38160, "loss": 0.0081, "lr": 7.76428150797471e-06, "epoch": 15.35901467505241, "percentage": 76.8, "elapsed_time": "1:52:17", "remaining_time": "0:33:55", "throughput": 2843.24, "total_tokens": 19156960} {"current_steps": 29310, "total_steps": 38160, "loss": 0.0856, "lr": 7.756000846553562e-06, "epoch": 15.361635220125786, "percentage": 76.81, "elapsed_time": "1:52:18", "remaining_time": "0:33:54", "throughput": 2843.21, "total_tokens": 19159744} {"current_steps": 29315, "total_steps": 38160, "loss": 0.0094, "lr": 7.74772379238031e-06, "epoch": 15.364255765199161, "percentage": 76.82, "elapsed_time": "1:52:19", "remaining_time": "0:33:53", "throughput": 2843.33, "total_tokens": 19163808} {"current_steps": 29320, "total_steps": 38160, "loss": 0.0115, "lr": 7.739450347186417e-06, "epoch": 15.366876310272536, "percentage": 76.83, "elapsed_time": "1:52:21", "remaining_time": "0:33:52", "throughput": 2843.22, "total_tokens": 19166304} {"current_steps": 29325, "total_steps": 38160, "loss": 0.029, "lr": 7.731180512702599e-06, "epoch": 15.369496855345911, "percentage": 76.85, "elapsed_time": "1:52:22", "remaining_time": "0:33:51", "throughput": 2843.28, "total_tokens": 19169792} {"current_steps": 29330, "total_steps": 38160, "loss": 0.0154, "lr": 7.722914290658795e-06, "epoch": 15.372117400419286, "percentage": 76.86, "elapsed_time": "1:52:23", "remaining_time": "0:33:50", "throughput": 2843.22, "total_tokens": 19172448} {"current_steps": 29335, "total_steps": 38160, "loss": 0.0112, "lr": 7.714651682784224e-06, "epoch": 15.374737945492662, "percentage": 76.87, "elapsed_time": "1:52:24", "remaining_time": "0:33:48", "throughput": 2843.32, "total_tokens": 19176352} {"current_steps": 29340, "total_steps": 38160, "loss": 0.022, "lr": 7.706392690807313e-06, "epoch": 15.377358490566039, "percentage": 76.89, "elapsed_time": "1:52:25", "remaining_time": "0:33:47", "throughput": 2843.35, "total_tokens": 19179808} {"current_steps": 29345, "total_steps": 38160, "loss": 0.0111, "lr": 7.69813731645575e-06, "epoch": 15.379979035639414, "percentage": 76.9, "elapsed_time": "1:52:26", "remaining_time": "0:33:46", "throughput": 2843.45, "total_tokens": 19183872} {"current_steps": 29350, "total_steps": 38160, "loss": 0.0203, "lr": 7.689885561456475e-06, "epoch": 15.382599580712789, "percentage": 76.91, "elapsed_time": "1:52:27", "remaining_time": "0:33:45", "throughput": 2843.52, "total_tokens": 19187584} {"current_steps": 29355, "total_steps": 38160, "loss": 0.0114, "lr": 7.681637427535663e-06, "epoch": 15.385220125786164, "percentage": 76.93, "elapsed_time": "1:52:29", "remaining_time": "0:33:44", "throughput": 2843.67, "total_tokens": 19192320} {"current_steps": 29360, "total_steps": 38160, "loss": 0.0104, "lr": 7.673392916418715e-06, "epoch": 15.38784067085954, "percentage": 76.94, "elapsed_time": "1:52:30", "remaining_time": "0:33:43", "throughput": 2843.73, "total_tokens": 19195712} {"current_steps": 29365, "total_steps": 38160, "loss": 0.016, "lr": 7.665152029830303e-06, "epoch": 15.390461215932914, "percentage": 76.95, "elapsed_time": "1:52:31", "remaining_time": "0:33:42", "throughput": 2843.81, "total_tokens": 19199328} {"current_steps": 29370, "total_steps": 38160, "loss": 0.0276, "lr": 7.656914769494314e-06, "epoch": 15.39308176100629, "percentage": 76.97, "elapsed_time": "1:52:32", "remaining_time": "0:33:40", "throughput": 2843.82, "total_tokens": 19202368} {"current_steps": 29375, "total_steps": 38160, "loss": 0.0236, "lr": 7.648681137133892e-06, "epoch": 15.395702306079665, "percentage": 76.98, "elapsed_time": "1:52:33", "remaining_time": "0:33:39", "throughput": 2843.84, "total_tokens": 19205728} {"current_steps": 29380, "total_steps": 38160, "loss": 0.0045, "lr": 7.640451134471432e-06, "epoch": 15.39832285115304, "percentage": 76.99, "elapsed_time": "1:52:34", "remaining_time": "0:33:38", "throughput": 2843.82, "total_tokens": 19208768} {"current_steps": 29385, "total_steps": 38160, "loss": 0.0196, "lr": 7.632224763228538e-06, "epoch": 15.400943396226415, "percentage": 77.0, "elapsed_time": "1:52:35", "remaining_time": "0:33:37", "throughput": 2843.93, "total_tokens": 19213152} {"current_steps": 29390, "total_steps": 38160, "loss": 0.0086, "lr": 7.6240020251260896e-06, "epoch": 15.40356394129979, "percentage": 77.02, "elapsed_time": "1:52:36", "remaining_time": "0:33:36", "throughput": 2843.79, "total_tokens": 19215392} {"current_steps": 29395, "total_steps": 38160, "loss": 0.0176, "lr": 7.615782921884174e-06, "epoch": 15.406184486373165, "percentage": 77.03, "elapsed_time": "1:52:38", "remaining_time": "0:33:35", "throughput": 2843.84, "total_tokens": 19218944} {"current_steps": 29400, "total_steps": 38160, "loss": 0.0678, "lr": 7.607567455222142e-06, "epoch": 15.40880503144654, "percentage": 77.04, "elapsed_time": "1:52:39", "remaining_time": "0:33:33", "throughput": 2843.85, "total_tokens": 19221984} {"current_steps": 29405, "total_steps": 38160, "loss": 0.1259, "lr": 7.599355626858582e-06, "epoch": 15.411425576519916, "percentage": 77.06, "elapsed_time": "1:52:40", "remaining_time": "0:33:32", "throughput": 2843.87, "total_tokens": 19225376} {"current_steps": 29410, "total_steps": 38160, "loss": 0.0101, "lr": 7.591147438511298e-06, "epoch": 15.414046121593291, "percentage": 77.07, "elapsed_time": "1:52:41", "remaining_time": "0:33:31", "throughput": 2843.88, "total_tokens": 19228448} {"current_steps": 29415, "total_steps": 38160, "loss": 0.2129, "lr": 7.5829428918973625e-06, "epoch": 15.416666666666666, "percentage": 77.08, "elapsed_time": "1:52:42", "remaining_time": "0:33:30", "throughput": 2843.92, "total_tokens": 19231712} {"current_steps": 29420, "total_steps": 38160, "loss": 0.0195, "lr": 7.574741988733075e-06, "epoch": 15.419287211740041, "percentage": 77.1, "elapsed_time": "1:52:43", "remaining_time": "0:33:29", "throughput": 2843.84, "total_tokens": 19234144} {"current_steps": 29425, "total_steps": 38160, "loss": 0.0119, "lr": 7.56654473073396e-06, "epoch": 15.421907756813416, "percentage": 77.11, "elapsed_time": "1:52:44", "remaining_time": "0:33:28", "throughput": 2843.83, "total_tokens": 19237056} {"current_steps": 29430, "total_steps": 38160, "loss": 0.008, "lr": 7.558351119614796e-06, "epoch": 15.424528301886792, "percentage": 77.12, "elapsed_time": "1:52:45", "remaining_time": "0:33:26", "throughput": 2843.82, "total_tokens": 19239904} {"current_steps": 29435, "total_steps": 38160, "loss": 0.0135, "lr": 7.5501611570896e-06, "epoch": 15.427148846960169, "percentage": 77.14, "elapsed_time": "1:52:46", "remaining_time": "0:33:25", "throughput": 2843.9, "total_tokens": 19243552} {"current_steps": 29440, "total_steps": 38160, "loss": 0.0104, "lr": 7.541974844871602e-06, "epoch": 15.429769392033544, "percentage": 77.15, "elapsed_time": "1:52:47", "remaining_time": "0:33:24", "throughput": 2843.9, "total_tokens": 19246560} {"current_steps": 29445, "total_steps": 38160, "loss": 0.0256, "lr": 7.5337921846732965e-06, "epoch": 15.432389937106919, "percentage": 77.16, "elapsed_time": "1:52:48", "remaining_time": "0:33:23", "throughput": 2843.91, "total_tokens": 19249632} {"current_steps": 29450, "total_steps": 38160, "loss": 0.0134, "lr": 7.525613178206409e-06, "epoch": 15.435010482180294, "percentage": 77.18, "elapsed_time": "1:52:49", "remaining_time": "0:33:22", "throughput": 2843.94, "total_tokens": 19252736} {"current_steps": 29455, "total_steps": 38160, "loss": 0.0113, "lr": 7.517437827181878e-06, "epoch": 15.43763102725367, "percentage": 77.19, "elapsed_time": "1:52:50", "remaining_time": "0:33:21", "throughput": 2843.98, "total_tokens": 19255968} {"current_steps": 29460, "total_steps": 38160, "loss": 0.0304, "lr": 7.509266133309908e-06, "epoch": 15.440251572327044, "percentage": 77.2, "elapsed_time": "1:52:51", "remaining_time": "0:33:19", "throughput": 2844.05, "total_tokens": 19259680} {"current_steps": 29465, "total_steps": 38160, "loss": 0.0096, "lr": 7.501098098299914e-06, "epoch": 15.44287211740042, "percentage": 77.21, "elapsed_time": "1:52:52", "remaining_time": "0:33:18", "throughput": 2844.07, "total_tokens": 19262848} {"current_steps": 29470, "total_steps": 38160, "loss": 0.0077, "lr": 7.492933723860557e-06, "epoch": 15.445492662473795, "percentage": 77.23, "elapsed_time": "1:52:54", "remaining_time": "0:33:17", "throughput": 2844.01, "total_tokens": 19265536} {"current_steps": 29475, "total_steps": 38160, "loss": 0.0033, "lr": 7.4847730116997334e-06, "epoch": 15.44811320754717, "percentage": 77.24, "elapsed_time": "1:52:55", "remaining_time": "0:33:16", "throughput": 2843.99, "total_tokens": 19268384} {"current_steps": 29480, "total_steps": 38160, "loss": 0.0092, "lr": 7.476615963524583e-06, "epoch": 15.450733752620545, "percentage": 77.25, "elapsed_time": "1:52:56", "remaining_time": "0:33:15", "throughput": 2844.06, "total_tokens": 19272000} {"current_steps": 29485, "total_steps": 38160, "loss": 0.0248, "lr": 7.468462581041452e-06, "epoch": 15.45335429769392, "percentage": 77.27, "elapsed_time": "1:52:57", "remaining_time": "0:33:14", "throughput": 2844.08, "total_tokens": 19275360} {"current_steps": 29490, "total_steps": 38160, "loss": 0.0237, "lr": 7.460312865955932e-06, "epoch": 15.455974842767295, "percentage": 77.28, "elapsed_time": "1:52:58", "remaining_time": "0:33:12", "throughput": 2844.19, "total_tokens": 19279488} {"current_steps": 29495, "total_steps": 38160, "loss": 0.0049, "lr": 7.4521668199728584e-06, "epoch": 15.45859538784067, "percentage": 77.29, "elapsed_time": "1:52:59", "remaining_time": "0:33:11", "throughput": 2844.11, "total_tokens": 19282176} {"current_steps": 29500, "total_steps": 38160, "loss": 0.0075, "lr": 7.4440244447962884e-06, "epoch": 15.461215932914046, "percentage": 77.31, "elapsed_time": "1:53:00", "remaining_time": "0:33:10", "throughput": 2844.09, "total_tokens": 19285056} {"current_steps": 29505, "total_steps": 38160, "loss": 0.0095, "lr": 7.435885742129523e-06, "epoch": 15.463836477987421, "percentage": 77.32, "elapsed_time": "1:53:01", "remaining_time": "0:33:09", "throughput": 2844.17, "total_tokens": 19288704} {"current_steps": 29510, "total_steps": 38160, "loss": 0.0402, "lr": 7.427750713675071e-06, "epoch": 15.466457023060796, "percentage": 77.33, "elapsed_time": "1:53:02", "remaining_time": "0:33:08", "throughput": 2844.13, "total_tokens": 19291584} {"current_steps": 29515, "total_steps": 38160, "loss": 0.0051, "lr": 7.419619361134702e-06, "epoch": 15.469077568134171, "percentage": 77.35, "elapsed_time": "1:53:04", "remaining_time": "0:33:07", "throughput": 2844.17, "total_tokens": 19295072} {"current_steps": 29520, "total_steps": 38160, "loss": 0.0101, "lr": 7.411491686209387e-06, "epoch": 15.471698113207546, "percentage": 77.36, "elapsed_time": "1:53:05", "remaining_time": "0:33:05", "throughput": 2844.13, "total_tokens": 19298144} {"current_steps": 29525, "total_steps": 38160, "loss": 0.0221, "lr": 7.4033676905993525e-06, "epoch": 15.474318658280922, "percentage": 77.37, "elapsed_time": "1:53:06", "remaining_time": "0:33:04", "throughput": 2844.19, "total_tokens": 19301472} {"current_steps": 29530, "total_steps": 38160, "loss": 0.0205, "lr": 7.3952473760040444e-06, "epoch": 15.476939203354299, "percentage": 77.38, "elapsed_time": "1:53:07", "remaining_time": "0:33:03", "throughput": 2844.12, "total_tokens": 19303936} {"current_steps": 29535, "total_steps": 38160, "loss": 0.0183, "lr": 7.387130744122148e-06, "epoch": 15.479559748427674, "percentage": 77.4, "elapsed_time": "1:53:08", "remaining_time": "0:33:02", "throughput": 2844.23, "total_tokens": 19308416} {"current_steps": 29540, "total_steps": 38160, "loss": 0.0376, "lr": 7.379017796651558e-06, "epoch": 15.482180293501049, "percentage": 77.41, "elapsed_time": "1:53:09", "remaining_time": "0:33:01", "throughput": 2844.39, "total_tokens": 19312992} {"current_steps": 29545, "total_steps": 38160, "loss": 0.0079, "lr": 7.3709085352894085e-06, "epoch": 15.484800838574424, "percentage": 77.42, "elapsed_time": "1:53:11", "remaining_time": "0:33:00", "throughput": 2844.46, "total_tokens": 19317792} {"current_steps": 29550, "total_steps": 38160, "loss": 0.0275, "lr": 7.362802961732071e-06, "epoch": 15.4874213836478, "percentage": 77.44, "elapsed_time": "1:53:12", "remaining_time": "0:32:59", "throughput": 2844.49, "total_tokens": 19320928} {"current_steps": 29555, "total_steps": 38160, "loss": 0.0426, "lr": 7.354701077675136e-06, "epoch": 15.490041928721174, "percentage": 77.45, "elapsed_time": "1:53:13", "remaining_time": "0:32:57", "throughput": 2844.42, "total_tokens": 19323584} {"current_steps": 29560, "total_steps": 38160, "loss": 0.0057, "lr": 7.346602884813439e-06, "epoch": 15.49266247379455, "percentage": 77.46, "elapsed_time": "1:53:14", "remaining_time": "0:32:56", "throughput": 2844.34, "total_tokens": 19326112} {"current_steps": 29565, "total_steps": 38160, "loss": 0.0254, "lr": 7.338508384841014e-06, "epoch": 15.495283018867925, "percentage": 77.48, "elapsed_time": "1:53:15", "remaining_time": "0:32:55", "throughput": 2844.42, "total_tokens": 19329824} {"current_steps": 29570, "total_steps": 38160, "loss": 0.0073, "lr": 7.3304175794511345e-06, "epoch": 15.4979035639413, "percentage": 77.49, "elapsed_time": "1:53:16", "remaining_time": "0:32:54", "throughput": 2844.36, "total_tokens": 19332544} {"current_steps": 29575, "total_steps": 38160, "loss": 0.0082, "lr": 7.3223304703363135e-06, "epoch": 15.500524109014675, "percentage": 77.5, "elapsed_time": "1:53:17", "remaining_time": "0:32:53", "throughput": 2844.37, "total_tokens": 19335744} {"current_steps": 29580, "total_steps": 38160, "loss": 0.0436, "lr": 7.314247059188281e-06, "epoch": 15.50314465408805, "percentage": 77.52, "elapsed_time": "1:53:18", "remaining_time": "0:32:52", "throughput": 2844.46, "total_tokens": 19339456} {"current_steps": 29585, "total_steps": 38160, "loss": 0.018, "lr": 7.306167347697992e-06, "epoch": 15.505765199161425, "percentage": 77.53, "elapsed_time": "1:53:20", "remaining_time": "0:32:50", "throughput": 2844.47, "total_tokens": 19342752} {"current_steps": 29590, "total_steps": 38160, "loss": 0.0276, "lr": 7.29809133755564e-06, "epoch": 15.5083857442348, "percentage": 77.54, "elapsed_time": "1:53:21", "remaining_time": "0:32:49", "throughput": 2844.44, "total_tokens": 19345536} {"current_steps": 29595, "total_steps": 38160, "loss": 0.0195, "lr": 7.290019030450629e-06, "epoch": 15.511006289308176, "percentage": 77.56, "elapsed_time": "1:53:22", "remaining_time": "0:32:48", "throughput": 2844.47, "total_tokens": 19348768} {"current_steps": 29600, "total_steps": 38160, "loss": 0.0065, "lr": 7.2819504280715794e-06, "epoch": 15.51362683438155, "percentage": 77.57, "elapsed_time": "1:53:23", "remaining_time": "0:32:47", "throughput": 2844.5, "total_tokens": 19352128} {"current_steps": 29605, "total_steps": 38160, "loss": 0.0206, "lr": 7.273885532106364e-06, "epoch": 15.516247379454926, "percentage": 77.58, "elapsed_time": "1:53:24", "remaining_time": "0:32:46", "throughput": 2844.46, "total_tokens": 19354784} {"current_steps": 29610, "total_steps": 38160, "loss": 0.0145, "lr": 7.265824344242064e-06, "epoch": 15.518867924528301, "percentage": 77.59, "elapsed_time": "1:53:25", "remaining_time": "0:32:45", "throughput": 2844.53, "total_tokens": 19358528} {"current_steps": 29615, "total_steps": 38160, "loss": 0.0078, "lr": 7.257766866165e-06, "epoch": 15.521488469601676, "percentage": 77.61, "elapsed_time": "1:53:26", "remaining_time": "0:32:43", "throughput": 2844.56, "total_tokens": 19361760} {"current_steps": 29620, "total_steps": 38160, "loss": 0.0142, "lr": 7.24971309956069e-06, "epoch": 15.524109014675052, "percentage": 77.62, "elapsed_time": "1:53:27", "remaining_time": "0:32:42", "throughput": 2844.64, "total_tokens": 19365504} {"current_steps": 29625, "total_steps": 38160, "loss": 0.0058, "lr": 7.241663046113887e-06, "epoch": 15.526729559748428, "percentage": 77.63, "elapsed_time": "1:53:28", "remaining_time": "0:32:41", "throughput": 2844.73, "total_tokens": 19369344} {"current_steps": 29630, "total_steps": 38160, "loss": 0.0135, "lr": 7.233616707508576e-06, "epoch": 15.529350104821804, "percentage": 77.65, "elapsed_time": "1:53:29", "remaining_time": "0:32:40", "throughput": 2844.73, "total_tokens": 19372224} {"current_steps": 29635, "total_steps": 38160, "loss": 0.0056, "lr": 7.225574085427961e-06, "epoch": 15.531970649895179, "percentage": 77.66, "elapsed_time": "1:53:30", "remaining_time": "0:32:39", "throughput": 2844.7, "total_tokens": 19374976} {"current_steps": 29640, "total_steps": 38160, "loss": 0.0214, "lr": 7.217535181554474e-06, "epoch": 15.534591194968554, "percentage": 77.67, "elapsed_time": "1:53:31", "remaining_time": "0:32:38", "throughput": 2844.63, "total_tokens": 19377440} {"current_steps": 29645, "total_steps": 38160, "loss": 0.0088, "lr": 7.209499997569747e-06, "epoch": 15.53721174004193, "percentage": 77.69, "elapsed_time": "1:53:32", "remaining_time": "0:32:36", "throughput": 2844.57, "total_tokens": 19380032} {"current_steps": 29650, "total_steps": 38160, "loss": 0.0265, "lr": 7.201468535154663e-06, "epoch": 15.539832285115304, "percentage": 77.7, "elapsed_time": "1:53:34", "remaining_time": "0:32:35", "throughput": 2844.61, "total_tokens": 19383488} {"current_steps": 29655, "total_steps": 38160, "loss": 0.0122, "lr": 7.193440795989295e-06, "epoch": 15.54245283018868, "percentage": 77.71, "elapsed_time": "1:53:35", "remaining_time": "0:32:34", "throughput": 2844.62, "total_tokens": 19386560} {"current_steps": 29660, "total_steps": 38160, "loss": 0.03, "lr": 7.185416781752965e-06, "epoch": 15.545073375262055, "percentage": 77.73, "elapsed_time": "1:53:36", "remaining_time": "0:32:33", "throughput": 2844.57, "total_tokens": 19389216} {"current_steps": 29665, "total_steps": 38160, "loss": 0.0324, "lr": 7.177396494124206e-06, "epoch": 15.54769392033543, "percentage": 77.74, "elapsed_time": "1:53:37", "remaining_time": "0:32:32", "throughput": 2844.62, "total_tokens": 19393056} {"current_steps": 29670, "total_steps": 38160, "loss": 0.0232, "lr": 7.169379934780779e-06, "epoch": 15.550314465408805, "percentage": 77.75, "elapsed_time": "1:53:38", "remaining_time": "0:32:31", "throughput": 2844.69, "total_tokens": 19396672} {"current_steps": 29675, "total_steps": 38160, "loss": 0.0128, "lr": 7.161367105399644e-06, "epoch": 15.55293501048218, "percentage": 77.76, "elapsed_time": "1:53:39", "remaining_time": "0:32:29", "throughput": 2844.59, "total_tokens": 19399168} {"current_steps": 29680, "total_steps": 38160, "loss": 0.0176, "lr": 7.153358007656991e-06, "epoch": 15.555555555555555, "percentage": 77.78, "elapsed_time": "1:53:41", "remaining_time": "0:32:28", "throughput": 2844.75, "total_tokens": 19405248} {"current_steps": 29685, "total_steps": 38160, "loss": 0.0074, "lr": 7.145352643228237e-06, "epoch": 15.55817610062893, "percentage": 77.79, "elapsed_time": "1:53:42", "remaining_time": "0:32:27", "throughput": 2844.67, "total_tokens": 19407712} {"current_steps": 29690, "total_steps": 38160, "loss": 0.019, "lr": 7.137351013788013e-06, "epoch": 15.560796645702306, "percentage": 77.8, "elapsed_time": "1:53:43", "remaining_time": "0:32:26", "throughput": 2844.68, "total_tokens": 19410816} {"current_steps": 29695, "total_steps": 38160, "loss": 0.0104, "lr": 7.129353121010177e-06, "epoch": 15.56341719077568, "percentage": 77.82, "elapsed_time": "1:53:44", "remaining_time": "0:32:25", "throughput": 2844.66, "total_tokens": 19413888} {"current_steps": 29700, "total_steps": 38160, "loss": 0.0118, "lr": 7.121358966567779e-06, "epoch": 15.566037735849056, "percentage": 77.83, "elapsed_time": "1:53:45", "remaining_time": "0:32:24", "throughput": 2844.7, "total_tokens": 19417344} {"current_steps": 29705, "total_steps": 38160, "loss": 0.017, "lr": 7.113368552133126e-06, "epoch": 15.568658280922431, "percentage": 77.84, "elapsed_time": "1:53:46", "remaining_time": "0:32:23", "throughput": 2844.71, "total_tokens": 19420512} {"current_steps": 29710, "total_steps": 38160, "loss": 0.0048, "lr": 7.105381879377701e-06, "epoch": 15.571278825995806, "percentage": 77.86, "elapsed_time": "1:53:48", "remaining_time": "0:32:21", "throughput": 2844.66, "total_tokens": 19423328} {"current_steps": 29715, "total_steps": 38160, "loss": 0.0187, "lr": 7.097398949972234e-06, "epoch": 15.573899371069182, "percentage": 77.87, "elapsed_time": "1:53:49", "remaining_time": "0:32:20", "throughput": 2844.74, "total_tokens": 19427136} {"current_steps": 29720, "total_steps": 38160, "loss": 0.0179, "lr": 7.089419765586672e-06, "epoch": 15.576519916142558, "percentage": 77.88, "elapsed_time": "1:53:50", "remaining_time": "0:32:19", "throughput": 2844.77, "total_tokens": 19430496} {"current_steps": 29725, "total_steps": 38160, "loss": 0.0047, "lr": 7.081444327890152e-06, "epoch": 15.579140461215934, "percentage": 77.9, "elapsed_time": "1:53:51", "remaining_time": "0:32:18", "throughput": 2844.77, "total_tokens": 19433792} {"current_steps": 29730, "total_steps": 38160, "loss": 0.0035, "lr": 7.073472638551054e-06, "epoch": 15.581761006289309, "percentage": 77.91, "elapsed_time": "1:53:52", "remaining_time": "0:32:17", "throughput": 2844.69, "total_tokens": 19436384} {"current_steps": 29735, "total_steps": 38160, "loss": 0.0103, "lr": 7.065504699236969e-06, "epoch": 15.584381551362684, "percentage": 77.92, "elapsed_time": "1:53:53", "remaining_time": "0:32:16", "throughput": 2844.67, "total_tokens": 19439200} {"current_steps": 29740, "total_steps": 38160, "loss": 0.0065, "lr": 7.057540511614688e-06, "epoch": 15.58700209643606, "percentage": 77.94, "elapsed_time": "1:53:54", "remaining_time": "0:32:15", "throughput": 2844.68, "total_tokens": 19442400} {"current_steps": 29745, "total_steps": 38160, "loss": 0.0193, "lr": 7.049580077350232e-06, "epoch": 15.589622641509434, "percentage": 77.95, "elapsed_time": "1:53:55", "remaining_time": "0:32:13", "throughput": 2844.82, "total_tokens": 19446464} {"current_steps": 29750, "total_steps": 38160, "loss": 0.0182, "lr": 7.041623398108843e-06, "epoch": 15.59224318658281, "percentage": 77.96, "elapsed_time": "1:53:56", "remaining_time": "0:32:12", "throughput": 2844.83, "total_tokens": 19449600} {"current_steps": 29755, "total_steps": 38160, "loss": 0.0174, "lr": 7.033670475554949e-06, "epoch": 15.594863731656185, "percentage": 77.97, "elapsed_time": "1:53:57", "remaining_time": "0:32:11", "throughput": 2844.81, "total_tokens": 19452608} {"current_steps": 29760, "total_steps": 38160, "loss": 0.0072, "lr": 7.025721311352224e-06, "epoch": 15.59748427672956, "percentage": 77.99, "elapsed_time": "1:53:59", "remaining_time": "0:32:10", "throughput": 2844.86, "total_tokens": 19456832} {"current_steps": 29765, "total_steps": 38160, "loss": 0.0052, "lr": 7.017775907163546e-06, "epoch": 15.600104821802935, "percentage": 78.0, "elapsed_time": "1:54:00", "remaining_time": "0:32:09", "throughput": 2844.76, "total_tokens": 19459136} {"current_steps": 29770, "total_steps": 38160, "loss": 0.0138, "lr": 7.009834264650989e-06, "epoch": 15.60272536687631, "percentage": 78.01, "elapsed_time": "1:54:01", "remaining_time": "0:32:08", "throughput": 2844.9, "total_tokens": 19463360} {"current_steps": 29775, "total_steps": 38160, "loss": 0.0063, "lr": 7.001896385475867e-06, "epoch": 15.605345911949685, "percentage": 78.03, "elapsed_time": "1:54:02", "remaining_time": "0:32:06", "throughput": 2844.91, "total_tokens": 19466432} {"current_steps": 29780, "total_steps": 38160, "loss": 0.0233, "lr": 6.993962271298682e-06, "epoch": 15.60796645702306, "percentage": 78.04, "elapsed_time": "1:54:03", "remaining_time": "0:32:05", "throughput": 2845.02, "total_tokens": 19470592} {"current_steps": 29785, "total_steps": 38160, "loss": 0.0168, "lr": 6.986031923779166e-06, "epoch": 15.610587002096436, "percentage": 78.05, "elapsed_time": "1:54:04", "remaining_time": "0:32:04", "throughput": 2845.07, "total_tokens": 19474496} {"current_steps": 29790, "total_steps": 38160, "loss": 0.0168, "lr": 6.978105344576264e-06, "epoch": 15.61320754716981, "percentage": 78.07, "elapsed_time": "1:54:06", "remaining_time": "0:32:03", "throughput": 2845.11, "total_tokens": 19477792} {"current_steps": 29795, "total_steps": 38160, "loss": 0.0077, "lr": 6.970182535348111e-06, "epoch": 15.615828092243186, "percentage": 78.08, "elapsed_time": "1:54:07", "remaining_time": "0:32:02", "throughput": 2845.1, "total_tokens": 19480736} {"current_steps": 29800, "total_steps": 38160, "loss": 0.0273, "lr": 6.962263497752086e-06, "epoch": 15.618448637316561, "percentage": 78.09, "elapsed_time": "1:54:08", "remaining_time": "0:32:01", "throughput": 2845.26, "total_tokens": 19485312} {"current_steps": 29805, "total_steps": 38160, "loss": 0.0052, "lr": 6.9543482334447436e-06, "epoch": 15.621069182389936, "percentage": 78.11, "elapsed_time": "1:54:09", "remaining_time": "0:32:00", "throughput": 2845.25, "total_tokens": 19488544} {"current_steps": 29810, "total_steps": 38160, "loss": 0.0177, "lr": 6.946436744081875e-06, "epoch": 15.623689727463312, "percentage": 78.12, "elapsed_time": "1:54:10", "remaining_time": "0:31:58", "throughput": 2845.28, "total_tokens": 19491744} {"current_steps": 29815, "total_steps": 38160, "loss": 0.0175, "lr": 6.938529031318472e-06, "epoch": 15.626310272536688, "percentage": 78.13, "elapsed_time": "1:54:11", "remaining_time": "0:31:57", "throughput": 2845.31, "total_tokens": 19495136} {"current_steps": 29820, "total_steps": 38160, "loss": 0.0105, "lr": 6.9306250968087485e-06, "epoch": 15.628930817610064, "percentage": 78.14, "elapsed_time": "1:54:12", "remaining_time": "0:31:56", "throughput": 2845.32, "total_tokens": 19498272} {"current_steps": 29825, "total_steps": 38160, "loss": 0.0086, "lr": 6.922724942206102e-06, "epoch": 15.631551362683439, "percentage": 78.16, "elapsed_time": "1:54:13", "remaining_time": "0:31:55", "throughput": 2845.32, "total_tokens": 19501792} {"current_steps": 29830, "total_steps": 38160, "loss": 0.0601, "lr": 6.914828569163167e-06, "epoch": 15.634171907756814, "percentage": 78.17, "elapsed_time": "1:54:15", "remaining_time": "0:31:54", "throughput": 2845.28, "total_tokens": 19504640} {"current_steps": 29835, "total_steps": 38160, "loss": 0.0074, "lr": 6.906935979331763e-06, "epoch": 15.63679245283019, "percentage": 78.18, "elapsed_time": "1:54:16", "remaining_time": "0:31:53", "throughput": 2845.33, "total_tokens": 19508032} {"current_steps": 29840, "total_steps": 38160, "loss": 0.0116, "lr": 6.8990471743629356e-06, "epoch": 15.639412997903564, "percentage": 78.2, "elapsed_time": "1:54:17", "remaining_time": "0:31:51", "throughput": 2845.32, "total_tokens": 19511008} {"current_steps": 29845, "total_steps": 38160, "loss": 0.0197, "lr": 6.89116215590693e-06, "epoch": 15.64203354297694, "percentage": 78.21, "elapsed_time": "1:54:18", "remaining_time": "0:31:50", "throughput": 2845.34, "total_tokens": 19514240} {"current_steps": 29850, "total_steps": 38160, "loss": 0.0155, "lr": 6.8832809256132146e-06, "epoch": 15.644654088050315, "percentage": 78.22, "elapsed_time": "1:54:19", "remaining_time": "0:31:49", "throughput": 2845.3, "total_tokens": 19517056} {"current_steps": 29855, "total_steps": 38160, "loss": 0.0108, "lr": 6.875403485130444e-06, "epoch": 15.64727463312369, "percentage": 78.24, "elapsed_time": "1:54:20", "remaining_time": "0:31:48", "throughput": 2845.3, "total_tokens": 19520256} {"current_steps": 29860, "total_steps": 38160, "loss": 0.0033, "lr": 6.867529836106479e-06, "epoch": 15.649895178197065, "percentage": 78.25, "elapsed_time": "1:54:21", "remaining_time": "0:31:47", "throughput": 2845.26, "total_tokens": 19522976} {"current_steps": 29865, "total_steps": 38160, "loss": 0.0104, "lr": 6.8596599801884045e-06, "epoch": 15.65251572327044, "percentage": 78.26, "elapsed_time": "1:54:22", "remaining_time": "0:31:46", "throughput": 2845.35, "total_tokens": 19526784} {"current_steps": 29870, "total_steps": 38160, "loss": 0.0054, "lr": 6.851793919022509e-06, "epoch": 15.655136268343815, "percentage": 78.28, "elapsed_time": "1:54:23", "remaining_time": "0:31:44", "throughput": 2845.36, "total_tokens": 19529920} {"current_steps": 29875, "total_steps": 38160, "loss": 0.0134, "lr": 6.843931654254285e-06, "epoch": 15.65775681341719, "percentage": 78.29, "elapsed_time": "1:54:24", "remaining_time": "0:31:43", "throughput": 2845.32, "total_tokens": 19532608} {"current_steps": 29880, "total_steps": 38160, "loss": 0.0086, "lr": 6.836073187528425e-06, "epoch": 15.660377358490566, "percentage": 78.3, "elapsed_time": "1:54:25", "remaining_time": "0:31:42", "throughput": 2845.33, "total_tokens": 19535680} {"current_steps": 29885, "total_steps": 38160, "loss": 0.0078, "lr": 6.828218520488821e-06, "epoch": 15.66299790356394, "percentage": 78.31, "elapsed_time": "1:54:26", "remaining_time": "0:31:41", "throughput": 2845.24, "total_tokens": 19538144} {"current_steps": 29890, "total_steps": 38160, "loss": 0.0159, "lr": 6.820367654778589e-06, "epoch": 15.665618448637316, "percentage": 78.33, "elapsed_time": "1:54:28", "remaining_time": "0:31:40", "throughput": 2845.24, "total_tokens": 19541344} {"current_steps": 29895, "total_steps": 38160, "loss": 0.0427, "lr": 6.812520592040039e-06, "epoch": 15.668238993710691, "percentage": 78.34, "elapsed_time": "1:54:29", "remaining_time": "0:31:39", "throughput": 2845.27, "total_tokens": 19544640} {"current_steps": 29900, "total_steps": 38160, "loss": 0.0036, "lr": 6.804677333914689e-06, "epoch": 15.670859538784066, "percentage": 78.35, "elapsed_time": "1:54:30", "remaining_time": "0:31:37", "throughput": 2845.27, "total_tokens": 19547872} {"current_steps": 29905, "total_steps": 38160, "loss": 0.0147, "lr": 6.796837882043261e-06, "epoch": 15.673480083857442, "percentage": 78.37, "elapsed_time": "1:54:31", "remaining_time": "0:31:36", "throughput": 2845.24, "total_tokens": 19550880} {"current_steps": 29910, "total_steps": 38160, "loss": 0.0363, "lr": 6.7890022380656785e-06, "epoch": 15.676100628930818, "percentage": 78.38, "elapsed_time": "1:54:32", "remaining_time": "0:31:35", "throughput": 2845.26, "total_tokens": 19554112} {"current_steps": 29915, "total_steps": 38160, "loss": 0.0117, "lr": 6.781170403621056e-06, "epoch": 15.678721174004194, "percentage": 78.39, "elapsed_time": "1:54:33", "remaining_time": "0:31:34", "throughput": 2845.32, "total_tokens": 19557760} {"current_steps": 29920, "total_steps": 38160, "loss": 0.0098, "lr": 6.773342380347736e-06, "epoch": 15.681341719077569, "percentage": 78.41, "elapsed_time": "1:54:34", "remaining_time": "0:31:33", "throughput": 2845.38, "total_tokens": 19561312} {"current_steps": 29925, "total_steps": 38160, "loss": 0.0706, "lr": 6.765518169883248e-06, "epoch": 15.683962264150944, "percentage": 78.42, "elapsed_time": "1:54:35", "remaining_time": "0:31:32", "throughput": 2845.48, "total_tokens": 19565248} {"current_steps": 29930, "total_steps": 38160, "loss": 0.0266, "lr": 6.757697773864338e-06, "epoch": 15.68658280922432, "percentage": 78.43, "elapsed_time": "1:54:37", "remaining_time": "0:31:31", "throughput": 2845.4, "total_tokens": 19567808} {"current_steps": 29935, "total_steps": 38160, "loss": 0.0211, "lr": 6.749881193926932e-06, "epoch": 15.689203354297694, "percentage": 78.45, "elapsed_time": "1:54:38", "remaining_time": "0:31:29", "throughput": 2845.41, "total_tokens": 19570880} {"current_steps": 29940, "total_steps": 38160, "loss": 0.0119, "lr": 6.742068431706167e-06, "epoch": 15.69182389937107, "percentage": 78.46, "elapsed_time": "1:54:39", "remaining_time": "0:31:28", "throughput": 2845.35, "total_tokens": 19573536} {"current_steps": 29945, "total_steps": 38160, "loss": 0.0266, "lr": 6.734259488836386e-06, "epoch": 15.694444444444445, "percentage": 78.47, "elapsed_time": "1:54:40", "remaining_time": "0:31:27", "throughput": 2845.42, "total_tokens": 19577408} {"current_steps": 29950, "total_steps": 38160, "loss": 0.0206, "lr": 6.726454366951135e-06, "epoch": 15.69706498951782, "percentage": 78.49, "elapsed_time": "1:54:41", "remaining_time": "0:31:26", "throughput": 2845.47, "total_tokens": 19580960} {"current_steps": 29955, "total_steps": 38160, "loss": 0.1167, "lr": 6.7186530676831616e-06, "epoch": 15.699685534591195, "percentage": 78.5, "elapsed_time": "1:54:42", "remaining_time": "0:31:25", "throughput": 2845.52, "total_tokens": 19584448} {"current_steps": 29960, "total_steps": 38160, "loss": 0.0136, "lr": 6.710855592664403e-06, "epoch": 15.70230607966457, "percentage": 78.51, "elapsed_time": "1:54:43", "remaining_time": "0:31:24", "throughput": 2845.51, "total_tokens": 19587392} {"current_steps": 29965, "total_steps": 38160, "loss": 0.0079, "lr": 6.703061943525993e-06, "epoch": 15.704926624737945, "percentage": 78.52, "elapsed_time": "1:54:44", "remaining_time": "0:31:22", "throughput": 2845.49, "total_tokens": 19590240} {"current_steps": 29970, "total_steps": 38160, "loss": 0.007, "lr": 6.69527212189828e-06, "epoch": 15.70754716981132, "percentage": 78.54, "elapsed_time": "1:54:45", "remaining_time": "0:31:21", "throughput": 2845.46, "total_tokens": 19593056} {"current_steps": 29975, "total_steps": 38160, "loss": 0.0035, "lr": 6.687486129410811e-06, "epoch": 15.710167714884696, "percentage": 78.55, "elapsed_time": "1:54:46", "remaining_time": "0:31:20", "throughput": 2845.47, "total_tokens": 19596160} {"current_steps": 29980, "total_steps": 38160, "loss": 0.0143, "lr": 6.679703967692322e-06, "epoch": 15.71278825995807, "percentage": 78.56, "elapsed_time": "1:54:48", "remaining_time": "0:31:19", "throughput": 2845.67, "total_tokens": 19601184} {"current_steps": 29985, "total_steps": 38160, "loss": 0.0066, "lr": 6.67192563837076e-06, "epoch": 15.715408805031446, "percentage": 78.58, "elapsed_time": "1:54:49", "remaining_time": "0:31:18", "throughput": 2845.66, "total_tokens": 19604160} {"current_steps": 29990, "total_steps": 38160, "loss": 0.0047, "lr": 6.664151143073258e-06, "epoch": 15.718029350104821, "percentage": 78.59, "elapsed_time": "1:54:50", "remaining_time": "0:31:17", "throughput": 2845.73, "total_tokens": 19607872} {"current_steps": 29995, "total_steps": 38160, "loss": 0.0129, "lr": 6.656380483426141e-06, "epoch": 15.720649895178196, "percentage": 78.6, "elapsed_time": "1:54:51", "remaining_time": "0:31:15", "throughput": 2845.85, "total_tokens": 19612096} {"current_steps": 30000, "total_steps": 38160, "loss": 0.0107, "lr": 6.648613661054956e-06, "epoch": 15.723270440251572, "percentage": 78.62, "elapsed_time": "1:54:52", "remaining_time": "0:31:14", "throughput": 2845.81, "total_tokens": 19614976} {"current_steps": 30005, "total_steps": 38160, "loss": 0.0181, "lr": 6.6408506775844256e-06, "epoch": 15.725890985324948, "percentage": 78.63, "elapsed_time": "1:54:53", "remaining_time": "0:31:13", "throughput": 2845.88, "total_tokens": 19618624} {"current_steps": 30010, "total_steps": 38160, "loss": 0.0352, "lr": 6.633091534638492e-06, "epoch": 15.728511530398324, "percentage": 78.64, "elapsed_time": "1:54:54", "remaining_time": "0:31:12", "throughput": 2845.91, "total_tokens": 19621920} {"current_steps": 30015, "total_steps": 38160, "loss": 0.0061, "lr": 6.625336233840257e-06, "epoch": 15.731132075471699, "percentage": 78.66, "elapsed_time": "1:54:55", "remaining_time": "0:31:11", "throughput": 2845.82, "total_tokens": 19624352} {"current_steps": 30020, "total_steps": 38160, "loss": 0.0439, "lr": 6.617584776812064e-06, "epoch": 15.733752620545074, "percentage": 78.67, "elapsed_time": "1:54:57", "remaining_time": "0:31:10", "throughput": 2846.05, "total_tokens": 19631744} {"current_steps": 30025, "total_steps": 38160, "loss": 0.0078, "lr": 6.6098371651754085e-06, "epoch": 15.73637316561845, "percentage": 78.68, "elapsed_time": "1:54:58", "remaining_time": "0:31:09", "throughput": 2846.01, "total_tokens": 19634592} {"current_steps": 30030, "total_steps": 38160, "loss": 0.0118, "lr": 6.602093400551012e-06, "epoch": 15.738993710691824, "percentage": 78.69, "elapsed_time": "1:55:00", "remaining_time": "0:31:08", "throughput": 2845.99, "total_tokens": 19637472} {"current_steps": 30035, "total_steps": 38160, "loss": 0.0501, "lr": 6.59435348455879e-06, "epoch": 15.7416142557652, "percentage": 78.71, "elapsed_time": "1:55:01", "remaining_time": "0:31:06", "throughput": 2846.06, "total_tokens": 19641344} {"current_steps": 30040, "total_steps": 38160, "loss": 0.0111, "lr": 6.586617418817828e-06, "epoch": 15.744234800838575, "percentage": 78.72, "elapsed_time": "1:55:02", "remaining_time": "0:31:05", "throughput": 2846.06, "total_tokens": 19644320} {"current_steps": 30045, "total_steps": 38160, "loss": 0.0061, "lr": 6.578885204946439e-06, "epoch": 15.74685534591195, "percentage": 78.73, "elapsed_time": "1:55:03", "remaining_time": "0:31:04", "throughput": 2846.2, "total_tokens": 19648512} {"current_steps": 30050, "total_steps": 38160, "loss": 0.0393, "lr": 6.571156844562098e-06, "epoch": 15.749475890985325, "percentage": 78.75, "elapsed_time": "1:55:04", "remaining_time": "0:31:03", "throughput": 2846.16, "total_tokens": 19651296} {"current_steps": 30055, "total_steps": 38160, "loss": 0.0056, "lr": 6.563432339281497e-06, "epoch": 15.7520964360587, "percentage": 78.76, "elapsed_time": "1:55:05", "remaining_time": "0:31:02", "throughput": 2846.13, "total_tokens": 19654080} {"current_steps": 30060, "total_steps": 38160, "loss": 0.0298, "lr": 6.555711690720517e-06, "epoch": 15.754716981132075, "percentage": 78.77, "elapsed_time": "1:55:06", "remaining_time": "0:31:01", "throughput": 2846.26, "total_tokens": 19658240} {"current_steps": 30065, "total_steps": 38160, "loss": 0.0381, "lr": 6.547994900494234e-06, "epoch": 15.75733752620545, "percentage": 78.79, "elapsed_time": "1:55:07", "remaining_time": "0:30:59", "throughput": 2846.3, "total_tokens": 19661792} {"current_steps": 30070, "total_steps": 38160, "loss": 0.0039, "lr": 6.540281970216899e-06, "epoch": 15.759958071278826, "percentage": 78.8, "elapsed_time": "1:55:08", "remaining_time": "0:30:58", "throughput": 2846.22, "total_tokens": 19664288} {"current_steps": 30075, "total_steps": 38160, "loss": 0.1062, "lr": 6.5325729015019845e-06, "epoch": 15.7625786163522, "percentage": 78.81, "elapsed_time": "1:55:10", "remaining_time": "0:30:57", "throughput": 2846.44, "total_tokens": 19670656} {"current_steps": 30080, "total_steps": 38160, "loss": 0.0338, "lr": 6.524867695962122e-06, "epoch": 15.765199161425576, "percentage": 78.83, "elapsed_time": "1:55:11", "remaining_time": "0:30:56", "throughput": 2846.47, "total_tokens": 19674048} {"current_steps": 30085, "total_steps": 38160, "loss": 0.0085, "lr": 6.517166355209165e-06, "epoch": 15.767819706498951, "percentage": 78.84, "elapsed_time": "1:55:12", "remaining_time": "0:30:55", "throughput": 2846.45, "total_tokens": 19676896} {"current_steps": 30090, "total_steps": 38160, "loss": 0.0138, "lr": 6.50946888085415e-06, "epoch": 15.770440251572326, "percentage": 78.85, "elapsed_time": "1:55:13", "remaining_time": "0:30:54", "throughput": 2846.38, "total_tokens": 19679392} {"current_steps": 30095, "total_steps": 38160, "loss": 0.026, "lr": 6.5017752745072855e-06, "epoch": 15.773060796645701, "percentage": 78.87, "elapsed_time": "1:55:14", "remaining_time": "0:30:53", "throughput": 2846.38, "total_tokens": 19682560} {"current_steps": 30100, "total_steps": 38160, "loss": 0.0096, "lr": 6.494085537777994e-06, "epoch": 15.775681341719078, "percentage": 78.88, "elapsed_time": "1:55:16", "remaining_time": "0:30:51", "throughput": 2846.32, "total_tokens": 19685312} {"current_steps": 30105, "total_steps": 38160, "loss": 0.0066, "lr": 6.48639967227489e-06, "epoch": 15.778301886792454, "percentage": 78.89, "elapsed_time": "1:55:17", "remaining_time": "0:30:50", "throughput": 2846.27, "total_tokens": 19688064} {"current_steps": 30110, "total_steps": 38160, "loss": 0.0195, "lr": 6.47871767960575e-06, "epoch": 15.780922431865829, "percentage": 78.9, "elapsed_time": "1:55:18", "remaining_time": "0:30:49", "throughput": 2846.24, "total_tokens": 19690976} {"current_steps": 30115, "total_steps": 38160, "loss": 0.024, "lr": 6.471039561377581e-06, "epoch": 15.783542976939204, "percentage": 78.92, "elapsed_time": "1:55:19", "remaining_time": "0:30:48", "throughput": 2846.21, "total_tokens": 19693728} {"current_steps": 30120, "total_steps": 38160, "loss": 0.0322, "lr": 6.463365319196538e-06, "epoch": 15.786163522012579, "percentage": 78.93, "elapsed_time": "1:55:21", "remaining_time": "0:30:47", "throughput": 2846.45, "total_tokens": 19700864} {"current_steps": 30125, "total_steps": 38160, "loss": 0.0078, "lr": 6.4556949546679905e-06, "epoch": 15.788784067085954, "percentage": 78.94, "elapsed_time": "1:55:22", "remaining_time": "0:30:46", "throughput": 2846.39, "total_tokens": 19703488} {"current_steps": 30130, "total_steps": 38160, "loss": 0.0041, "lr": 6.448028469396497e-06, "epoch": 15.79140461215933, "percentage": 78.96, "elapsed_time": "1:55:23", "remaining_time": "0:30:45", "throughput": 2846.44, "total_tokens": 19706944} {"current_steps": 30135, "total_steps": 38160, "loss": 0.0077, "lr": 6.440365864985801e-06, "epoch": 15.794025157232705, "percentage": 78.97, "elapsed_time": "1:55:24", "remaining_time": "0:30:44", "throughput": 2846.47, "total_tokens": 19710400} {"current_steps": 30140, "total_steps": 38160, "loss": 0.0056, "lr": 6.432707143038818e-06, "epoch": 15.79664570230608, "percentage": 78.98, "elapsed_time": "1:55:25", "remaining_time": "0:30:42", "throughput": 2846.43, "total_tokens": 19713056} {"current_steps": 30145, "total_steps": 38160, "loss": 0.0183, "lr": 6.4250523051576834e-06, "epoch": 15.799266247379455, "percentage": 79.0, "elapsed_time": "1:55:26", "remaining_time": "0:30:41", "throughput": 2846.55, "total_tokens": 19717248} {"current_steps": 30150, "total_steps": 38160, "loss": 0.0086, "lr": 6.417401352943686e-06, "epoch": 15.80188679245283, "percentage": 79.01, "elapsed_time": "1:55:27", "remaining_time": "0:30:40", "throughput": 2846.45, "total_tokens": 19719552} {"current_steps": 30155, "total_steps": 38160, "loss": 0.0158, "lr": 6.409754287997322e-06, "epoch": 15.804507337526205, "percentage": 79.02, "elapsed_time": "1:55:28", "remaining_time": "0:30:39", "throughput": 2846.38, "total_tokens": 19722304} {"current_steps": 30160, "total_steps": 38160, "loss": 0.0213, "lr": 6.40211111191828e-06, "epoch": 15.80712788259958, "percentage": 79.04, "elapsed_time": "1:55:30", "remaining_time": "0:30:38", "throughput": 2846.36, "total_tokens": 19725440} {"current_steps": 30165, "total_steps": 38160, "loss": 0.0127, "lr": 6.394471826305409e-06, "epoch": 15.809748427672956, "percentage": 79.05, "elapsed_time": "1:55:31", "remaining_time": "0:30:37", "throughput": 2846.41, "total_tokens": 19728864} {"current_steps": 30170, "total_steps": 38160, "loss": 0.012, "lr": 6.3868364327567795e-06, "epoch": 15.81236897274633, "percentage": 79.06, "elapsed_time": "1:55:32", "remaining_time": "0:30:35", "throughput": 2846.43, "total_tokens": 19732192} {"current_steps": 30175, "total_steps": 38160, "loss": 0.0092, "lr": 6.379204932869606e-06, "epoch": 15.814989517819706, "percentage": 79.07, "elapsed_time": "1:55:33", "remaining_time": "0:30:34", "throughput": 2846.41, "total_tokens": 19735040} {"current_steps": 30180, "total_steps": 38160, "loss": 0.0062, "lr": 6.371577328240327e-06, "epoch": 15.817610062893081, "percentage": 79.09, "elapsed_time": "1:55:34", "remaining_time": "0:30:33", "throughput": 2846.43, "total_tokens": 19738368} {"current_steps": 30185, "total_steps": 38160, "loss": 0.0118, "lr": 6.363953620464547e-06, "epoch": 15.820230607966456, "percentage": 79.1, "elapsed_time": "1:55:35", "remaining_time": "0:30:32", "throughput": 2846.51, "total_tokens": 19742176} {"current_steps": 30190, "total_steps": 38160, "loss": 0.0092, "lr": 6.356333811137064e-06, "epoch": 15.822851153039831, "percentage": 79.11, "elapsed_time": "1:55:36", "remaining_time": "0:30:31", "throughput": 2846.56, "total_tokens": 19745760} {"current_steps": 30195, "total_steps": 38160, "loss": 0.0185, "lr": 6.34871790185185e-06, "epoch": 15.825471698113208, "percentage": 79.13, "elapsed_time": "1:55:37", "remaining_time": "0:30:30", "throughput": 2846.57, "total_tokens": 19748832} {"current_steps": 30200, "total_steps": 38160, "loss": 0.0237, "lr": 6.341105894202057e-06, "epoch": 15.828092243186584, "percentage": 79.14, "elapsed_time": "1:55:38", "remaining_time": "0:30:28", "throughput": 2846.56, "total_tokens": 19752000} {"current_steps": 30205, "total_steps": 38160, "loss": 0.0162, "lr": 6.333497789780041e-06, "epoch": 15.830712788259959, "percentage": 79.15, "elapsed_time": "1:55:40", "remaining_time": "0:30:27", "throughput": 2846.65, "total_tokens": 19755744} {"current_steps": 30210, "total_steps": 38160, "loss": 0.0186, "lr": 6.325893590177329e-06, "epoch": 15.833333333333334, "percentage": 79.17, "elapsed_time": "1:55:41", "remaining_time": "0:30:26", "throughput": 2846.68, "total_tokens": 19759072} {"current_steps": 30215, "total_steps": 38160, "loss": 0.0188, "lr": 6.318293296984631e-06, "epoch": 15.835953878406709, "percentage": 79.18, "elapsed_time": "1:55:42", "remaining_time": "0:30:25", "throughput": 2846.72, "total_tokens": 19762432} {"current_steps": 30220, "total_steps": 38160, "loss": 0.0186, "lr": 6.3106969117918495e-06, "epoch": 15.838574423480084, "percentage": 79.19, "elapsed_time": "1:55:43", "remaining_time": "0:30:24", "throughput": 2846.68, "total_tokens": 19765248} {"current_steps": 30225, "total_steps": 38160, "loss": 0.0263, "lr": 6.303104436188057e-06, "epoch": 15.84119496855346, "percentage": 79.21, "elapsed_time": "1:55:44", "remaining_time": "0:30:23", "throughput": 2846.63, "total_tokens": 19768224} {"current_steps": 30230, "total_steps": 38160, "loss": 0.0177, "lr": 6.2955158717615036e-06, "epoch": 15.843815513626835, "percentage": 79.22, "elapsed_time": "1:55:45", "remaining_time": "0:30:21", "throughput": 2846.58, "total_tokens": 19771232} {"current_steps": 30235, "total_steps": 38160, "loss": 0.0053, "lr": 6.287931220099638e-06, "epoch": 15.84643605870021, "percentage": 79.23, "elapsed_time": "1:55:46", "remaining_time": "0:30:20", "throughput": 2846.54, "total_tokens": 19774016} {"current_steps": 30240, "total_steps": 38160, "loss": 0.021, "lr": 6.280350482789082e-06, "epoch": 15.849056603773585, "percentage": 79.25, "elapsed_time": "1:55:47", "remaining_time": "0:30:19", "throughput": 2846.59, "total_tokens": 19777568} {"current_steps": 30245, "total_steps": 38160, "loss": 0.007, "lr": 6.272773661415645e-06, "epoch": 15.85167714884696, "percentage": 79.26, "elapsed_time": "1:55:48", "remaining_time": "0:30:18", "throughput": 2846.55, "total_tokens": 19780448} {"current_steps": 30250, "total_steps": 38160, "loss": 0.0102, "lr": 6.26520075756431e-06, "epoch": 15.854297693920335, "percentage": 79.27, "elapsed_time": "1:55:50", "remaining_time": "0:30:17", "throughput": 2846.57, "total_tokens": 19783808} {"current_steps": 30255, "total_steps": 38160, "loss": 0.0159, "lr": 6.2576317728192304e-06, "epoch": 15.85691823899371, "percentage": 79.28, "elapsed_time": "1:55:51", "remaining_time": "0:30:16", "throughput": 2846.59, "total_tokens": 19787136} {"current_steps": 30260, "total_steps": 38160, "loss": 0.0282, "lr": 6.250066708763761e-06, "epoch": 15.859538784067086, "percentage": 79.3, "elapsed_time": "1:55:52", "remaining_time": "0:30:15", "throughput": 2846.56, "total_tokens": 19789920} {"current_steps": 30265, "total_steps": 38160, "loss": 0.013, "lr": 6.242505566980422e-06, "epoch": 15.86215932914046, "percentage": 79.31, "elapsed_time": "1:55:53", "remaining_time": "0:30:13", "throughput": 2846.56, "total_tokens": 19793024} {"current_steps": 30270, "total_steps": 38160, "loss": 0.0054, "lr": 6.234948349050931e-06, "epoch": 15.864779874213836, "percentage": 79.32, "elapsed_time": "1:55:54", "remaining_time": "0:30:12", "throughput": 2846.6, "total_tokens": 19796672} {"current_steps": 30275, "total_steps": 38160, "loss": 0.0088, "lr": 6.227395056556162e-06, "epoch": 15.867400419287211, "percentage": 79.34, "elapsed_time": "1:55:55", "remaining_time": "0:30:11", "throughput": 2846.48, "total_tokens": 19798944} {"current_steps": 30280, "total_steps": 38160, "loss": 0.0087, "lr": 6.219845691076173e-06, "epoch": 15.870020964360586, "percentage": 79.35, "elapsed_time": "1:55:56", "remaining_time": "0:30:10", "throughput": 2846.41, "total_tokens": 19801664} {"current_steps": 30285, "total_steps": 38160, "loss": 0.0205, "lr": 6.212300254190206e-06, "epoch": 15.872641509433961, "percentage": 79.36, "elapsed_time": "1:55:57", "remaining_time": "0:30:09", "throughput": 2846.38, "total_tokens": 19804384} {"current_steps": 30290, "total_steps": 38160, "loss": 0.0132, "lr": 6.204758747476688e-06, "epoch": 15.875262054507338, "percentage": 79.38, "elapsed_time": "1:55:58", "remaining_time": "0:30:08", "throughput": 2846.41, "total_tokens": 19807744} {"current_steps": 30295, "total_steps": 38160, "loss": 0.0164, "lr": 6.1972211725132095e-06, "epoch": 15.877882599580714, "percentage": 79.39, "elapsed_time": "1:55:59", "remaining_time": "0:30:06", "throughput": 2846.36, "total_tokens": 19810336} {"current_steps": 30300, "total_steps": 38160, "loss": 0.0281, "lr": 6.189687530876559e-06, "epoch": 15.880503144654089, "percentage": 79.4, "elapsed_time": "1:56:00", "remaining_time": "0:30:05", "throughput": 2846.35, "total_tokens": 19813440} {"current_steps": 30305, "total_steps": 38160, "loss": 0.056, "lr": 6.182157824142676e-06, "epoch": 15.883123689727464, "percentage": 79.42, "elapsed_time": "1:56:02", "remaining_time": "0:30:04", "throughput": 2846.3, "total_tokens": 19816128} {"current_steps": 30310, "total_steps": 38160, "loss": 0.0102, "lr": 6.174632053886681e-06, "epoch": 15.885744234800839, "percentage": 79.43, "elapsed_time": "1:56:03", "remaining_time": "0:30:03", "throughput": 2846.24, "total_tokens": 19818656} {"current_steps": 30315, "total_steps": 38160, "loss": 0.0047, "lr": 6.167110221682893e-06, "epoch": 15.888364779874214, "percentage": 79.44, "elapsed_time": "1:56:04", "remaining_time": "0:30:02", "throughput": 2846.26, "total_tokens": 19821856} {"current_steps": 30320, "total_steps": 38160, "loss": 0.0125, "lr": 6.159592329104788e-06, "epoch": 15.89098532494759, "percentage": 79.45, "elapsed_time": "1:56:05", "remaining_time": "0:30:01", "throughput": 2846.26, "total_tokens": 19824864} {"current_steps": 30325, "total_steps": 38160, "loss": 0.0191, "lr": 6.152078377725032e-06, "epoch": 15.893605870020965, "percentage": 79.47, "elapsed_time": "1:56:06", "remaining_time": "0:29:59", "throughput": 2846.32, "total_tokens": 19828352} {"current_steps": 30330, "total_steps": 38160, "loss": 0.0076, "lr": 6.144568369115453e-06, "epoch": 15.89622641509434, "percentage": 79.48, "elapsed_time": "1:56:07", "remaining_time": "0:29:58", "throughput": 2846.25, "total_tokens": 19830848} {"current_steps": 30335, "total_steps": 38160, "loss": 0.0282, "lr": 6.137062304847046e-06, "epoch": 15.898846960167715, "percentage": 79.49, "elapsed_time": "1:56:08", "remaining_time": "0:29:57", "throughput": 2846.46, "total_tokens": 19836448} {"current_steps": 30340, "total_steps": 38160, "loss": 0.0093, "lr": 6.129560186490008e-06, "epoch": 15.90146750524109, "percentage": 79.51, "elapsed_time": "1:56:09", "remaining_time": "0:29:56", "throughput": 2846.45, "total_tokens": 19839296} {"current_steps": 30345, "total_steps": 38160, "loss": 0.006, "lr": 6.122062015613694e-06, "epoch": 15.904088050314465, "percentage": 79.52, "elapsed_time": "1:56:10", "remaining_time": "0:29:55", "throughput": 2846.44, "total_tokens": 19842176} {"current_steps": 30350, "total_steps": 38160, "loss": 0.0126, "lr": 6.114567793786641e-06, "epoch": 15.90670859538784, "percentage": 79.53, "elapsed_time": "1:56:11", "remaining_time": "0:29:54", "throughput": 2846.44, "total_tokens": 19845216} {"current_steps": 30355, "total_steps": 38160, "loss": 0.0309, "lr": 6.107077522576543e-06, "epoch": 15.909329140461216, "percentage": 79.55, "elapsed_time": "1:56:13", "remaining_time": "0:29:52", "throughput": 2846.4, "total_tokens": 19848064} {"current_steps": 30360, "total_steps": 38160, "loss": 0.0047, "lr": 6.099591203550292e-06, "epoch": 15.91194968553459, "percentage": 79.56, "elapsed_time": "1:56:14", "remaining_time": "0:29:51", "throughput": 2846.36, "total_tokens": 19850912} {"current_steps": 30365, "total_steps": 38160, "loss": 0.0349, "lr": 6.092108838273927e-06, "epoch": 15.914570230607966, "percentage": 79.57, "elapsed_time": "1:56:15", "remaining_time": "0:29:50", "throughput": 2846.46, "total_tokens": 19854688} {"current_steps": 30370, "total_steps": 38160, "loss": 0.0151, "lr": 6.08463042831268e-06, "epoch": 15.917190775681341, "percentage": 79.59, "elapsed_time": "1:56:16", "remaining_time": "0:29:49", "throughput": 2846.47, "total_tokens": 19857792} {"current_steps": 30375, "total_steps": 38160, "loss": 0.0103, "lr": 6.0771559752309496e-06, "epoch": 15.919811320754716, "percentage": 79.6, "elapsed_time": "1:56:17", "remaining_time": "0:29:48", "throughput": 2846.44, "total_tokens": 19860672} {"current_steps": 30380, "total_steps": 38160, "loss": 0.0147, "lr": 6.069685480592313e-06, "epoch": 15.922431865828091, "percentage": 79.61, "elapsed_time": "1:56:18", "remaining_time": "0:29:47", "throughput": 2846.42, "total_tokens": 19863584} {"current_steps": 30385, "total_steps": 38160, "loss": 0.011, "lr": 6.062218945959497e-06, "epoch": 15.925052410901468, "percentage": 79.63, "elapsed_time": "1:56:19", "remaining_time": "0:29:45", "throughput": 2846.46, "total_tokens": 19866912} {"current_steps": 30390, "total_steps": 38160, "loss": 0.0296, "lr": 6.054756372894435e-06, "epoch": 15.927672955974844, "percentage": 79.64, "elapsed_time": "1:56:20", "remaining_time": "0:29:44", "throughput": 2846.45, "total_tokens": 19869920} {"current_steps": 30395, "total_steps": 38160, "loss": 0.0596, "lr": 6.04729776295819e-06, "epoch": 15.930293501048219, "percentage": 79.65, "elapsed_time": "1:56:21", "remaining_time": "0:29:43", "throughput": 2846.4, "total_tokens": 19872736} {"current_steps": 30400, "total_steps": 38160, "loss": 0.0168, "lr": 6.0398431177110306e-06, "epoch": 15.932914046121594, "percentage": 79.66, "elapsed_time": "1:56:22", "remaining_time": "0:29:42", "throughput": 2846.33, "total_tokens": 19875584} {"current_steps": 30405, "total_steps": 38160, "loss": 0.0134, "lr": 6.032392438712389e-06, "epoch": 15.935534591194969, "percentage": 79.68, "elapsed_time": "1:56:24", "remaining_time": "0:29:41", "throughput": 2846.39, "total_tokens": 19879168} {"current_steps": 30410, "total_steps": 38160, "loss": 0.031, "lr": 6.024945727520847e-06, "epoch": 15.938155136268344, "percentage": 79.69, "elapsed_time": "1:56:25", "remaining_time": "0:29:40", "throughput": 2846.44, "total_tokens": 19882528} {"current_steps": 30415, "total_steps": 38160, "loss": 0.0145, "lr": 6.01750298569419e-06, "epoch": 15.94077568134172, "percentage": 79.7, "elapsed_time": "1:56:26", "remaining_time": "0:29:38", "throughput": 2846.43, "total_tokens": 19885440} {"current_steps": 30420, "total_steps": 38160, "loss": 0.0057, "lr": 6.010064214789335e-06, "epoch": 15.943396226415095, "percentage": 79.72, "elapsed_time": "1:56:27", "remaining_time": "0:29:37", "throughput": 2846.41, "total_tokens": 19888320} {"current_steps": 30425, "total_steps": 38160, "loss": 0.0162, "lr": 6.002629416362399e-06, "epoch": 15.94601677148847, "percentage": 79.73, "elapsed_time": "1:56:28", "remaining_time": "0:29:36", "throughput": 2846.44, "total_tokens": 19891520} {"current_steps": 30430, "total_steps": 38160, "loss": 0.0048, "lr": 5.995198591968662e-06, "epoch": 15.948637316561845, "percentage": 79.74, "elapsed_time": "1:56:29", "remaining_time": "0:29:35", "throughput": 2846.43, "total_tokens": 19894688} {"current_steps": 30435, "total_steps": 38160, "loss": 0.0176, "lr": 5.987771743162554e-06, "epoch": 15.95125786163522, "percentage": 79.76, "elapsed_time": "1:56:30", "remaining_time": "0:29:34", "throughput": 2846.38, "total_tokens": 19897408} {"current_steps": 30440, "total_steps": 38160, "loss": 0.0175, "lr": 5.9803488714976955e-06, "epoch": 15.953878406708595, "percentage": 79.77, "elapsed_time": "1:56:31", "remaining_time": "0:29:33", "throughput": 2846.47, "total_tokens": 19901056} {"current_steps": 30445, "total_steps": 38160, "loss": 0.0145, "lr": 5.972929978526872e-06, "epoch": 15.95649895178197, "percentage": 79.78, "elapsed_time": "1:56:32", "remaining_time": "0:29:32", "throughput": 2846.52, "total_tokens": 19905056} {"current_steps": 30450, "total_steps": 38160, "loss": 0.0062, "lr": 5.965515065802019e-06, "epoch": 15.959119496855346, "percentage": 79.8, "elapsed_time": "1:56:33", "remaining_time": "0:29:30", "throughput": 2846.51, "total_tokens": 19908160} {"current_steps": 30455, "total_steps": 38160, "loss": 0.0117, "lr": 5.958104134874254e-06, "epoch": 15.96174004192872, "percentage": 79.81, "elapsed_time": "1:56:34", "remaining_time": "0:29:29", "throughput": 2846.5, "total_tokens": 19911040} {"current_steps": 30460, "total_steps": 38160, "loss": 0.0206, "lr": 5.950697187293872e-06, "epoch": 15.964360587002096, "percentage": 79.82, "elapsed_time": "1:56:36", "remaining_time": "0:29:28", "throughput": 2846.54, "total_tokens": 19914720} {"current_steps": 30465, "total_steps": 38160, "loss": 0.0158, "lr": 5.943294224610305e-06, "epoch": 15.966981132075471, "percentage": 79.83, "elapsed_time": "1:56:37", "remaining_time": "0:29:27", "throughput": 2846.48, "total_tokens": 19917312} {"current_steps": 30470, "total_steps": 38160, "loss": 0.0207, "lr": 5.935895248372175e-06, "epoch": 15.969601677148846, "percentage": 79.85, "elapsed_time": "1:56:38", "remaining_time": "0:29:26", "throughput": 2846.51, "total_tokens": 19920480} {"current_steps": 30475, "total_steps": 38160, "loss": 0.0062, "lr": 5.928500260127273e-06, "epoch": 15.972222222222221, "percentage": 79.86, "elapsed_time": "1:56:39", "remaining_time": "0:29:25", "throughput": 2846.46, "total_tokens": 19923104} {"current_steps": 30480, "total_steps": 38160, "loss": 0.0159, "lr": 5.921109261422531e-06, "epoch": 15.974842767295598, "percentage": 79.87, "elapsed_time": "1:56:40", "remaining_time": "0:29:23", "throughput": 2846.5, "total_tokens": 19926688} {"current_steps": 30485, "total_steps": 38160, "loss": 0.0078, "lr": 5.913722253804071e-06, "epoch": 15.977463312368974, "percentage": 79.89, "elapsed_time": "1:56:41", "remaining_time": "0:29:22", "throughput": 2846.59, "total_tokens": 19930624} {"current_steps": 30490, "total_steps": 38160, "loss": 0.0058, "lr": 5.906339238817163e-06, "epoch": 15.980083857442349, "percentage": 79.9, "elapsed_time": "1:56:42", "remaining_time": "0:29:21", "throughput": 2846.61, "total_tokens": 19933984} {"current_steps": 30495, "total_steps": 38160, "loss": 0.006, "lr": 5.8989602180062554e-06, "epoch": 15.982704402515724, "percentage": 79.91, "elapsed_time": "1:56:43", "remaining_time": "0:29:20", "throughput": 2846.5, "total_tokens": 19936288} {"current_steps": 30500, "total_steps": 38160, "loss": 0.009, "lr": 5.891585192914953e-06, "epoch": 15.985324947589099, "percentage": 79.93, "elapsed_time": "1:56:44", "remaining_time": "0:29:19", "throughput": 2846.54, "total_tokens": 19939648} {"current_steps": 30505, "total_steps": 38160, "loss": 0.019, "lr": 5.884214165086036e-06, "epoch": 15.987945492662474, "percentage": 79.94, "elapsed_time": "1:56:45", "remaining_time": "0:29:18", "throughput": 2846.56, "total_tokens": 19942848} {"current_steps": 30510, "total_steps": 38160, "loss": 0.0389, "lr": 5.876847136061428e-06, "epoch": 15.99056603773585, "percentage": 79.95, "elapsed_time": "1:56:47", "remaining_time": "0:29:16", "throughput": 2846.59, "total_tokens": 19946176} {"current_steps": 30515, "total_steps": 38160, "loss": 0.0079, "lr": 5.869484107382228e-06, "epoch": 15.993186582809225, "percentage": 79.97, "elapsed_time": "1:56:48", "remaining_time": "0:29:15", "throughput": 2846.53, "total_tokens": 19948800} {"current_steps": 30520, "total_steps": 38160, "loss": 0.0111, "lr": 5.862125080588696e-06, "epoch": 15.9958071278826, "percentage": 79.98, "elapsed_time": "1:56:49", "remaining_time": "0:29:14", "throughput": 2846.58, "total_tokens": 19952288} {"current_steps": 30525, "total_steps": 38160, "loss": 0.0066, "lr": 5.854770057220263e-06, "epoch": 15.998427672955975, "percentage": 79.99, "elapsed_time": "1:56:50", "remaining_time": "0:29:13", "throughput": 2846.6, "total_tokens": 19955424} {"current_steps": 30528, "total_steps": 38160, "eval_loss": 1.4609568119049072, "epoch": 16.0, "percentage": 80.0, "elapsed_time": "1:57:02", "remaining_time": "0:29:15", "throughput": 2841.66, "total_tokens": 19956544} {"current_steps": 30530, "total_steps": 38160, "loss": 0.0114, "lr": 5.8474190388155216e-06, "epoch": 16.00104821802935, "percentage": 80.01, "elapsed_time": "1:57:06", "remaining_time": "0:29:16", "throughput": 2840.24, "total_tokens": 19957376} {"current_steps": 30535, "total_steps": 38160, "loss": 0.008, "lr": 5.840072026912205e-06, "epoch": 16.003668763102727, "percentage": 80.02, "elapsed_time": "1:57:07", "remaining_time": "0:29:14", "throughput": 2840.24, "total_tokens": 19960768} {"current_steps": 30540, "total_steps": 38160, "loss": 0.0061, "lr": 5.83272902304724e-06, "epoch": 16.0062893081761, "percentage": 80.03, "elapsed_time": "1:57:09", "remaining_time": "0:29:13", "throughput": 2840.27, "total_tokens": 19964416} {"current_steps": 30545, "total_steps": 38160, "loss": 0.0155, "lr": 5.825390028756683e-06, "epoch": 16.008909853249477, "percentage": 80.04, "elapsed_time": "1:57:10", "remaining_time": "0:29:12", "throughput": 2840.3, "total_tokens": 19967904} {"current_steps": 30550, "total_steps": 38160, "loss": 0.059, "lr": 5.818055045575776e-06, "epoch": 16.01153039832285, "percentage": 80.06, "elapsed_time": "1:57:11", "remaining_time": "0:29:11", "throughput": 2840.39, "total_tokens": 19971872} {"current_steps": 30555, "total_steps": 38160, "loss": 0.0123, "lr": 5.810724075038917e-06, "epoch": 16.014150943396228, "percentage": 80.07, "elapsed_time": "1:57:12", "remaining_time": "0:29:10", "throughput": 2840.39, "total_tokens": 19975072} {"current_steps": 30560, "total_steps": 38160, "loss": 0.0182, "lr": 5.803397118679665e-06, "epoch": 16.0167714884696, "percentage": 80.08, "elapsed_time": "1:57:13", "remaining_time": "0:29:09", "throughput": 2840.39, "total_tokens": 19978144} {"current_steps": 30565, "total_steps": 38160, "loss": 0.0072, "lr": 5.796074178030727e-06, "epoch": 16.019392033542978, "percentage": 80.1, "elapsed_time": "1:57:14", "remaining_time": "0:29:08", "throughput": 2840.4, "total_tokens": 19981216} {"current_steps": 30570, "total_steps": 38160, "loss": 0.0194, "lr": 5.788755254623976e-06, "epoch": 16.02201257861635, "percentage": 80.11, "elapsed_time": "1:57:15", "remaining_time": "0:29:06", "throughput": 2840.49, "total_tokens": 19984896} {"current_steps": 30575, "total_steps": 38160, "loss": 0.0055, "lr": 5.7814403499904525e-06, "epoch": 16.02463312368973, "percentage": 80.12, "elapsed_time": "1:57:16", "remaining_time": "0:29:05", "throughput": 2840.52, "total_tokens": 19988256} {"current_steps": 30580, "total_steps": 38160, "loss": 0.0086, "lr": 5.774129465660352e-06, "epoch": 16.0272536687631, "percentage": 80.14, "elapsed_time": "1:57:17", "remaining_time": "0:29:04", "throughput": 2840.57, "total_tokens": 19991744} {"current_steps": 30585, "total_steps": 38160, "loss": 0.009, "lr": 5.7668226031630246e-06, "epoch": 16.02987421383648, "percentage": 80.15, "elapsed_time": "1:57:19", "remaining_time": "0:29:03", "throughput": 2840.59, "total_tokens": 19995104} {"current_steps": 30590, "total_steps": 38160, "loss": 0.006, "lr": 5.759519764026999e-06, "epoch": 16.032494758909852, "percentage": 80.16, "elapsed_time": "1:57:20", "remaining_time": "0:29:02", "throughput": 2840.48, "total_tokens": 19997472} {"current_steps": 30595, "total_steps": 38160, "loss": 0.016, "lr": 5.7522209497799185e-06, "epoch": 16.03511530398323, "percentage": 80.18, "elapsed_time": "1:57:21", "remaining_time": "0:29:01", "throughput": 2840.38, "total_tokens": 19999776} {"current_steps": 30600, "total_steps": 38160, "loss": 0.0169, "lr": 5.7449261619486246e-06, "epoch": 16.037735849056602, "percentage": 80.19, "elapsed_time": "1:57:22", "remaining_time": "0:28:59", "throughput": 2840.38, "total_tokens": 20002848} {"current_steps": 30605, "total_steps": 38160, "loss": 0.0065, "lr": 5.737635402059105e-06, "epoch": 16.04035639412998, "percentage": 80.2, "elapsed_time": "1:57:23", "remaining_time": "0:28:58", "throughput": 2840.41, "total_tokens": 20006176} {"current_steps": 30610, "total_steps": 38160, "loss": 0.005, "lr": 5.730348671636501e-06, "epoch": 16.042976939203353, "percentage": 80.21, "elapsed_time": "1:57:24", "remaining_time": "0:28:57", "throughput": 2840.39, "total_tokens": 20009088} {"current_steps": 30615, "total_steps": 38160, "loss": 0.0102, "lr": 5.723065972205124e-06, "epoch": 16.04559748427673, "percentage": 80.23, "elapsed_time": "1:57:25", "remaining_time": "0:28:56", "throughput": 2840.36, "total_tokens": 20012000} {"current_steps": 30620, "total_steps": 38160, "loss": 0.0609, "lr": 5.715787305288423e-06, "epoch": 16.048218029350103, "percentage": 80.24, "elapsed_time": "1:57:26", "remaining_time": "0:28:55", "throughput": 2840.48, "total_tokens": 20016416} {"current_steps": 30625, "total_steps": 38160, "loss": 0.0095, "lr": 5.7085126724090024e-06, "epoch": 16.05083857442348, "percentage": 80.25, "elapsed_time": "1:57:27", "remaining_time": "0:28:54", "throughput": 2840.61, "total_tokens": 20020608} {"current_steps": 30630, "total_steps": 38160, "loss": 0.0053, "lr": 5.7012420750886445e-06, "epoch": 16.053459119496857, "percentage": 80.27, "elapsed_time": "1:57:29", "remaining_time": "0:28:52", "throughput": 2840.57, "total_tokens": 20023360} {"current_steps": 30635, "total_steps": 38160, "loss": 0.0119, "lr": 5.693975514848271e-06, "epoch": 16.05607966457023, "percentage": 80.28, "elapsed_time": "1:57:30", "remaining_time": "0:28:51", "throughput": 2840.53, "total_tokens": 20026240} {"current_steps": 30640, "total_steps": 38160, "loss": 0.0199, "lr": 5.686712993207971e-06, "epoch": 16.058700209643607, "percentage": 80.29, "elapsed_time": "1:57:31", "remaining_time": "0:28:50", "throughput": 2840.55, "total_tokens": 20029568} {"current_steps": 30645, "total_steps": 38160, "loss": 0.0275, "lr": 5.679454511686977e-06, "epoch": 16.06132075471698, "percentage": 80.31, "elapsed_time": "1:57:32", "remaining_time": "0:28:49", "throughput": 2840.51, "total_tokens": 20032288} {"current_steps": 30650, "total_steps": 38160, "loss": 0.0053, "lr": 5.672200071803671e-06, "epoch": 16.063941299790358, "percentage": 80.32, "elapsed_time": "1:57:33", "remaining_time": "0:28:48", "throughput": 2840.51, "total_tokens": 20035584} {"current_steps": 30655, "total_steps": 38160, "loss": 0.0053, "lr": 5.664949675075607e-06, "epoch": 16.06656184486373, "percentage": 80.33, "elapsed_time": "1:57:34", "remaining_time": "0:28:47", "throughput": 2840.52, "total_tokens": 20038912} {"current_steps": 30660, "total_steps": 38160, "loss": 0.0167, "lr": 5.657703323019486e-06, "epoch": 16.069182389937108, "percentage": 80.35, "elapsed_time": "1:57:35", "remaining_time": "0:28:45", "throughput": 2840.58, "total_tokens": 20042656} {"current_steps": 30665, "total_steps": 38160, "loss": 0.0163, "lr": 5.65046101715116e-06, "epoch": 16.07180293501048, "percentage": 80.36, "elapsed_time": "1:57:37", "remaining_time": "0:28:44", "throughput": 2840.65, "total_tokens": 20046528} {"current_steps": 30670, "total_steps": 38160, "loss": 0.0107, "lr": 5.643222758985644e-06, "epoch": 16.07442348008386, "percentage": 80.37, "elapsed_time": "1:57:38", "remaining_time": "0:28:43", "throughput": 2840.64, "total_tokens": 20049600} {"current_steps": 30675, "total_steps": 38160, "loss": 0.0171, "lr": 5.635988550037094e-06, "epoch": 16.07704402515723, "percentage": 80.39, "elapsed_time": "1:57:39", "remaining_time": "0:28:42", "throughput": 2840.61, "total_tokens": 20052480} {"current_steps": 30680, "total_steps": 38160, "loss": 0.0258, "lr": 5.628758391818817e-06, "epoch": 16.07966457023061, "percentage": 80.4, "elapsed_time": "1:57:40", "remaining_time": "0:28:41", "throughput": 2840.67, "total_tokens": 20056128} {"current_steps": 30685, "total_steps": 38160, "loss": 0.0063, "lr": 5.621532285843287e-06, "epoch": 16.082285115303982, "percentage": 80.41, "elapsed_time": "1:57:41", "remaining_time": "0:28:40", "throughput": 2840.67, "total_tokens": 20059264} {"current_steps": 30690, "total_steps": 38160, "loss": 0.0199, "lr": 5.614310233622119e-06, "epoch": 16.08490566037736, "percentage": 80.42, "elapsed_time": "1:57:42", "remaining_time": "0:28:39", "throughput": 2840.63, "total_tokens": 20062112} {"current_steps": 30695, "total_steps": 38160, "loss": 0.012, "lr": 5.607092236666093e-06, "epoch": 16.087526205450732, "percentage": 80.44, "elapsed_time": "1:57:43", "remaining_time": "0:28:37", "throughput": 2840.58, "total_tokens": 20064896} {"current_steps": 30700, "total_steps": 38160, "loss": 0.0073, "lr": 5.599878296485125e-06, "epoch": 16.09014675052411, "percentage": 80.45, "elapsed_time": "1:57:44", "remaining_time": "0:28:36", "throughput": 2840.56, "total_tokens": 20067776} {"current_steps": 30705, "total_steps": 38160, "loss": 0.0087, "lr": 5.592668414588284e-06, "epoch": 16.092767295597483, "percentage": 80.46, "elapsed_time": "1:57:45", "remaining_time": "0:28:35", "throughput": 2840.58, "total_tokens": 20071072} {"current_steps": 30710, "total_steps": 38160, "loss": 0.013, "lr": 5.585462592483801e-06, "epoch": 16.09538784067086, "percentage": 80.48, "elapsed_time": "1:57:46", "remaining_time": "0:28:34", "throughput": 2840.55, "total_tokens": 20073920} {"current_steps": 30715, "total_steps": 38160, "loss": 0.0129, "lr": 5.578260831679047e-06, "epoch": 16.098008385744233, "percentage": 80.49, "elapsed_time": "1:57:48", "remaining_time": "0:28:33", "throughput": 2840.65, "total_tokens": 20077952} {"current_steps": 30720, "total_steps": 38160, "loss": 0.023, "lr": 5.571063133680562e-06, "epoch": 16.10062893081761, "percentage": 80.5, "elapsed_time": "1:57:49", "remaining_time": "0:28:32", "throughput": 2840.67, "total_tokens": 20081472} {"current_steps": 30725, "total_steps": 38160, "loss": 0.0052, "lr": 5.563869499994004e-06, "epoch": 16.103249475890987, "percentage": 80.52, "elapsed_time": "1:57:50", "remaining_time": "0:28:30", "throughput": 2840.62, "total_tokens": 20084128} {"current_steps": 30730, "total_steps": 38160, "loss": 0.0147, "lr": 5.556679932124215e-06, "epoch": 16.10587002096436, "percentage": 80.53, "elapsed_time": "1:57:51", "remaining_time": "0:28:29", "throughput": 2840.67, "total_tokens": 20087488} {"current_steps": 30735, "total_steps": 38160, "loss": 0.0187, "lr": 5.549494431575159e-06, "epoch": 16.108490566037737, "percentage": 80.54, "elapsed_time": "1:57:52", "remaining_time": "0:28:28", "throughput": 2840.67, "total_tokens": 20090656} {"current_steps": 30740, "total_steps": 38160, "loss": 0.0068, "lr": 5.542312999849961e-06, "epoch": 16.11111111111111, "percentage": 80.56, "elapsed_time": "1:57:53", "remaining_time": "0:28:27", "throughput": 2840.65, "total_tokens": 20093632} {"current_steps": 30745, "total_steps": 38160, "loss": 0.0078, "lr": 5.5351356384509e-06, "epoch": 16.113731656184488, "percentage": 80.57, "elapsed_time": "1:57:54", "remaining_time": "0:28:26", "throughput": 2840.75, "total_tokens": 20097312} {"current_steps": 30750, "total_steps": 38160, "loss": 0.0213, "lr": 5.527962348879401e-06, "epoch": 16.11635220125786, "percentage": 80.58, "elapsed_time": "1:57:55", "remaining_time": "0:28:25", "throughput": 2840.78, "total_tokens": 20100832} {"current_steps": 30755, "total_steps": 38160, "loss": 0.0111, "lr": 5.520793132636027e-06, "epoch": 16.118972746331238, "percentage": 80.59, "elapsed_time": "1:57:57", "remaining_time": "0:28:23", "throughput": 2840.84, "total_tokens": 20104800} {"current_steps": 30760, "total_steps": 38160, "loss": 0.0079, "lr": 5.513627991220502e-06, "epoch": 16.12159329140461, "percentage": 80.61, "elapsed_time": "1:57:58", "remaining_time": "0:28:22", "throughput": 2840.93, "total_tokens": 20108544} {"current_steps": 30765, "total_steps": 38160, "loss": 0.0048, "lr": 5.506466926131684e-06, "epoch": 16.12421383647799, "percentage": 80.62, "elapsed_time": "1:57:59", "remaining_time": "0:28:21", "throughput": 2840.93, "total_tokens": 20111680} {"current_steps": 30770, "total_steps": 38160, "loss": 0.0031, "lr": 5.4993099388675916e-06, "epoch": 16.12683438155136, "percentage": 80.63, "elapsed_time": "1:58:00", "remaining_time": "0:28:20", "throughput": 2840.99, "total_tokens": 20115328} {"current_steps": 30775, "total_steps": 38160, "loss": 0.0042, "lr": 5.49215703092539e-06, "epoch": 16.12945492662474, "percentage": 80.65, "elapsed_time": "1:58:01", "remaining_time": "0:28:19", "throughput": 2841.03, "total_tokens": 20118752} {"current_steps": 30780, "total_steps": 38160, "loss": 0.0043, "lr": 5.4850082038013755e-06, "epoch": 16.132075471698112, "percentage": 80.66, "elapsed_time": "1:58:02", "remaining_time": "0:28:18", "throughput": 2841.0, "total_tokens": 20121504} {"current_steps": 30785, "total_steps": 38160, "loss": 0.0069, "lr": 5.4778634589910115e-06, "epoch": 16.13469601677149, "percentage": 80.67, "elapsed_time": "1:58:03", "remaining_time": "0:28:17", "throughput": 2841.08, "total_tokens": 20125440} {"current_steps": 30790, "total_steps": 38160, "loss": 0.0047, "lr": 5.4707227979888834e-06, "epoch": 16.137316561844862, "percentage": 80.69, "elapsed_time": "1:58:04", "remaining_time": "0:28:15", "throughput": 2841.04, "total_tokens": 20128288} {"current_steps": 30795, "total_steps": 38160, "loss": 0.0144, "lr": 5.463586222288747e-06, "epoch": 16.13993710691824, "percentage": 80.7, "elapsed_time": "1:58:05", "remaining_time": "0:28:14", "throughput": 2841.04, "total_tokens": 20131328} {"current_steps": 30800, "total_steps": 38160, "loss": 0.0055, "lr": 5.456453733383493e-06, "epoch": 16.142557651991613, "percentage": 80.71, "elapsed_time": "1:58:07", "remaining_time": "0:28:13", "throughput": 2841.1, "total_tokens": 20135616} {"current_steps": 30805, "total_steps": 38160, "loss": 0.0095, "lr": 5.449325332765151e-06, "epoch": 16.14517819706499, "percentage": 80.73, "elapsed_time": "1:58:08", "remaining_time": "0:28:12", "throughput": 2841.15, "total_tokens": 20139040} {"current_steps": 30810, "total_steps": 38160, "loss": 0.0151, "lr": 5.4422010219249e-06, "epoch": 16.147798742138363, "percentage": 80.74, "elapsed_time": "1:58:09", "remaining_time": "0:28:11", "throughput": 2841.13, "total_tokens": 20141984} {"current_steps": 30815, "total_steps": 38160, "loss": 0.0075, "lr": 5.435080802353077e-06, "epoch": 16.15041928721174, "percentage": 80.75, "elapsed_time": "1:58:10", "remaining_time": "0:28:10", "throughput": 2840.99, "total_tokens": 20144448} {"current_steps": 30820, "total_steps": 38160, "loss": 0.0285, "lr": 5.4279646755391325e-06, "epoch": 16.153039832285117, "percentage": 80.77, "elapsed_time": "1:58:12", "remaining_time": "0:28:09", "throughput": 2841.08, "total_tokens": 20150048} {"current_steps": 30825, "total_steps": 38160, "loss": 0.0092, "lr": 5.420852642971691e-06, "epoch": 16.15566037735849, "percentage": 80.78, "elapsed_time": "1:58:13", "remaining_time": "0:28:07", "throughput": 2841.1, "total_tokens": 20153600} {"current_steps": 30830, "total_steps": 38160, "loss": 0.0153, "lr": 5.41374470613851e-06, "epoch": 16.158280922431867, "percentage": 80.79, "elapsed_time": "1:58:14", "remaining_time": "0:28:06", "throughput": 2841.04, "total_tokens": 20156448} {"current_steps": 30835, "total_steps": 38160, "loss": 0.0287, "lr": 5.40664086652648e-06, "epoch": 16.16090146750524, "percentage": 80.8, "elapsed_time": "1:58:15", "remaining_time": "0:28:05", "throughput": 2841.09, "total_tokens": 20160256} {"current_steps": 30840, "total_steps": 38160, "loss": 0.006, "lr": 5.399541125621646e-06, "epoch": 16.163522012578618, "percentage": 80.82, "elapsed_time": "1:58:17", "remaining_time": "0:28:04", "throughput": 2841.06, "total_tokens": 20163168} {"current_steps": 30845, "total_steps": 38160, "loss": 0.0051, "lr": 5.392445484909203e-06, "epoch": 16.16614255765199, "percentage": 80.83, "elapsed_time": "1:58:18", "remaining_time": "0:28:03", "throughput": 2841.02, "total_tokens": 20166048} {"current_steps": 30850, "total_steps": 38160, "loss": 0.0229, "lr": 5.385353945873464e-06, "epoch": 16.168763102725368, "percentage": 80.84, "elapsed_time": "1:58:19", "remaining_time": "0:28:02", "throughput": 2841.08, "total_tokens": 20169632} {"current_steps": 30855, "total_steps": 38160, "loss": 0.031, "lr": 5.378266509997909e-06, "epoch": 16.17138364779874, "percentage": 80.86, "elapsed_time": "1:58:20", "remaining_time": "0:28:01", "throughput": 2841.2, "total_tokens": 20173920} {"current_steps": 30860, "total_steps": 38160, "loss": 0.0059, "lr": 5.371183178765135e-06, "epoch": 16.17400419287212, "percentage": 80.87, "elapsed_time": "1:58:21", "remaining_time": "0:27:59", "throughput": 2841.11, "total_tokens": 20176448} {"current_steps": 30865, "total_steps": 38160, "loss": 0.0093, "lr": 5.364103953656904e-06, "epoch": 16.17662473794549, "percentage": 80.88, "elapsed_time": "1:58:22", "remaining_time": "0:27:58", "throughput": 2841.2, "total_tokens": 20180448} {"current_steps": 30870, "total_steps": 38160, "loss": 0.0107, "lr": 5.35702883615411e-06, "epoch": 16.17924528301887, "percentage": 80.9, "elapsed_time": "1:58:23", "remaining_time": "0:27:57", "throughput": 2841.16, "total_tokens": 20183232} {"current_steps": 30875, "total_steps": 38160, "loss": 0.0055, "lr": 5.34995782773679e-06, "epoch": 16.181865828092242, "percentage": 80.91, "elapsed_time": "1:58:24", "remaining_time": "0:27:56", "throughput": 2841.16, "total_tokens": 20186240} {"current_steps": 30880, "total_steps": 38160, "loss": 0.0069, "lr": 5.3428909298841115e-06, "epoch": 16.18448637316562, "percentage": 80.92, "elapsed_time": "1:58:26", "remaining_time": "0:27:55", "throughput": 2841.22, "total_tokens": 20189888} {"current_steps": 30885, "total_steps": 38160, "loss": 0.0068, "lr": 5.335828144074384e-06, "epoch": 16.187106918238992, "percentage": 80.94, "elapsed_time": "1:58:27", "remaining_time": "0:27:54", "throughput": 2841.25, "total_tokens": 20193440} {"current_steps": 30890, "total_steps": 38160, "loss": 0.0079, "lr": 5.3287694717850695e-06, "epoch": 16.18972746331237, "percentage": 80.95, "elapsed_time": "1:58:28", "remaining_time": "0:27:52", "throughput": 2841.3, "total_tokens": 20197088} {"current_steps": 30895, "total_steps": 38160, "loss": 0.0098, "lr": 5.321714914492759e-06, "epoch": 16.192348008385743, "percentage": 80.96, "elapsed_time": "1:58:29", "remaining_time": "0:27:51", "throughput": 2841.35, "total_tokens": 20200736} {"current_steps": 30900, "total_steps": 38160, "loss": 0.011, "lr": 5.314664473673195e-06, "epoch": 16.19496855345912, "percentage": 80.97, "elapsed_time": "1:58:30", "remaining_time": "0:27:50", "throughput": 2841.35, "total_tokens": 20203712} {"current_steps": 30905, "total_steps": 38160, "loss": 0.0136, "lr": 5.307618150801239e-06, "epoch": 16.197589098532493, "percentage": 80.99, "elapsed_time": "1:58:31", "remaining_time": "0:27:49", "throughput": 2841.34, "total_tokens": 20206688} {"current_steps": 30910, "total_steps": 38160, "loss": 0.0373, "lr": 5.300575947350897e-06, "epoch": 16.20020964360587, "percentage": 81.0, "elapsed_time": "1:58:32", "remaining_time": "0:27:48", "throughput": 2841.4, "total_tokens": 20210112} {"current_steps": 30915, "total_steps": 38160, "loss": 0.0072, "lr": 5.293537864795325e-06, "epoch": 16.202830188679247, "percentage": 81.01, "elapsed_time": "1:58:33", "remaining_time": "0:27:47", "throughput": 2841.34, "total_tokens": 20212768} {"current_steps": 30920, "total_steps": 38160, "loss": 0.0239, "lr": 5.2865039046068075e-06, "epoch": 16.20545073375262, "percentage": 81.03, "elapsed_time": "1:58:34", "remaining_time": "0:27:45", "throughput": 2841.45, "total_tokens": 20216928} {"current_steps": 30925, "total_steps": 38160, "loss": 0.0016, "lr": 5.279474068256767e-06, "epoch": 16.208071278825997, "percentage": 81.04, "elapsed_time": "1:58:36", "remaining_time": "0:27:44", "throughput": 2841.36, "total_tokens": 20219488} {"current_steps": 30930, "total_steps": 38160, "loss": 0.0027, "lr": 5.272448357215779e-06, "epoch": 16.21069182389937, "percentage": 81.05, "elapsed_time": "1:58:37", "remaining_time": "0:27:43", "throughput": 2841.37, "total_tokens": 20222592} {"current_steps": 30935, "total_steps": 38160, "loss": 0.028, "lr": 5.26542677295353e-06, "epoch": 16.213312368972748, "percentage": 81.07, "elapsed_time": "1:58:38", "remaining_time": "0:27:42", "throughput": 2841.49, "total_tokens": 20227616} {"current_steps": 30940, "total_steps": 38160, "loss": 0.004, "lr": 5.258409316938848e-06, "epoch": 16.21593291404612, "percentage": 81.08, "elapsed_time": "1:58:39", "remaining_time": "0:27:41", "throughput": 2841.43, "total_tokens": 20230240} {"current_steps": 30945, "total_steps": 38160, "loss": 0.0076, "lr": 5.251395990639713e-06, "epoch": 16.218553459119498, "percentage": 81.09, "elapsed_time": "1:58:40", "remaining_time": "0:27:40", "throughput": 2841.37, "total_tokens": 20233120} {"current_steps": 30950, "total_steps": 38160, "loss": 0.0191, "lr": 5.244386795523235e-06, "epoch": 16.22117400419287, "percentage": 81.11, "elapsed_time": "1:58:41", "remaining_time": "0:27:39", "throughput": 2841.41, "total_tokens": 20236512} {"current_steps": 30955, "total_steps": 38160, "loss": 0.0059, "lr": 5.23738173305566e-06, "epoch": 16.22379454926625, "percentage": 81.12, "elapsed_time": "1:58:43", "remaining_time": "0:27:37", "throughput": 2841.59, "total_tokens": 20241024} {"current_steps": 30960, "total_steps": 38160, "loss": 0.0041, "lr": 5.230380804702362e-06, "epoch": 16.22641509433962, "percentage": 81.13, "elapsed_time": "1:58:44", "remaining_time": "0:27:36", "throughput": 2841.64, "total_tokens": 20244800} {"current_steps": 30965, "total_steps": 38160, "loss": 0.0177, "lr": 5.223384011927851e-06, "epoch": 16.229035639413, "percentage": 81.15, "elapsed_time": "1:58:45", "remaining_time": "0:27:35", "throughput": 2841.77, "total_tokens": 20249152} {"current_steps": 30970, "total_steps": 38160, "loss": 0.0054, "lr": 5.216391356195779e-06, "epoch": 16.231656184486372, "percentage": 81.16, "elapsed_time": "1:58:46", "remaining_time": "0:27:34", "throughput": 2841.8, "total_tokens": 20252512} {"current_steps": 30975, "total_steps": 38160, "loss": 0.0067, "lr": 5.209402838968935e-06, "epoch": 16.23427672955975, "percentage": 81.17, "elapsed_time": "1:58:47", "remaining_time": "0:27:33", "throughput": 2841.88, "total_tokens": 20256224} {"current_steps": 30980, "total_steps": 38160, "loss": 0.0095, "lr": 5.202418461709233e-06, "epoch": 16.236897274633122, "percentage": 81.18, "elapsed_time": "1:58:48", "remaining_time": "0:27:32", "throughput": 2841.79, "total_tokens": 20258656} {"current_steps": 30985, "total_steps": 38160, "loss": 0.0097, "lr": 5.195438225877738e-06, "epoch": 16.2395178197065, "percentage": 81.2, "elapsed_time": "1:58:49", "remaining_time": "0:27:31", "throughput": 2841.88, "total_tokens": 20262528} {"current_steps": 30990, "total_steps": 38160, "loss": 0.0132, "lr": 5.18846213293461e-06, "epoch": 16.242138364779873, "percentage": 81.21, "elapsed_time": "1:58:51", "remaining_time": "0:27:29", "throughput": 2841.93, "total_tokens": 20266176} {"current_steps": 30995, "total_steps": 38160, "loss": 0.0046, "lr": 5.181490184339185e-06, "epoch": 16.24475890985325, "percentage": 81.22, "elapsed_time": "1:58:52", "remaining_time": "0:27:28", "throughput": 2841.92, "total_tokens": 20269088} {"current_steps": 31000, "total_steps": 38160, "loss": 0.0044, "lr": 5.17452238154991e-06, "epoch": 16.247379454926623, "percentage": 81.24, "elapsed_time": "1:58:53", "remaining_time": "0:27:27", "throughput": 2841.95, "total_tokens": 20272384} {"current_steps": 31005, "total_steps": 38160, "loss": 0.038, "lr": 5.1675587260243715e-06, "epoch": 16.25, "percentage": 81.25, "elapsed_time": "1:58:54", "remaining_time": "0:27:26", "throughput": 2842.04, "total_tokens": 20276416} {"current_steps": 31010, "total_steps": 38160, "loss": 0.0122, "lr": 5.160599219219295e-06, "epoch": 16.252620545073377, "percentage": 81.26, "elapsed_time": "1:58:55", "remaining_time": "0:27:25", "throughput": 2842.09, "total_tokens": 20279904} {"current_steps": 31015, "total_steps": 38160, "loss": 0.0074, "lr": 5.1536438625905185e-06, "epoch": 16.25524109014675, "percentage": 81.28, "elapsed_time": "1:58:56", "remaining_time": "0:27:24", "throughput": 2842.11, "total_tokens": 20283200} {"current_steps": 31020, "total_steps": 38160, "loss": 0.0058, "lr": 5.146692657593025e-06, "epoch": 16.257861635220127, "percentage": 81.29, "elapsed_time": "1:58:57", "remaining_time": "0:27:22", "throughput": 2842.11, "total_tokens": 20286336} {"current_steps": 31025, "total_steps": 38160, "loss": 0.0054, "lr": 5.139745605680926e-06, "epoch": 16.2604821802935, "percentage": 81.3, "elapsed_time": "1:58:58", "remaining_time": "0:27:21", "throughput": 2842.07, "total_tokens": 20289024} {"current_steps": 31030, "total_steps": 38160, "loss": 0.0083, "lr": 5.132802708307469e-06, "epoch": 16.263102725366878, "percentage": 81.32, "elapsed_time": "1:58:59", "remaining_time": "0:27:20", "throughput": 2842.06, "total_tokens": 20291968} {"current_steps": 31035, "total_steps": 38160, "loss": 0.0043, "lr": 5.125863966925035e-06, "epoch": 16.26572327044025, "percentage": 81.33, "elapsed_time": "1:59:01", "remaining_time": "0:27:19", "throughput": 2842.05, "total_tokens": 20295072} {"current_steps": 31040, "total_steps": 38160, "loss": 0.0084, "lr": 5.118929382985116e-06, "epoch": 16.268343815513628, "percentage": 81.34, "elapsed_time": "1:59:02", "remaining_time": "0:27:18", "throughput": 2842.03, "total_tokens": 20298112} {"current_steps": 31045, "total_steps": 38160, "loss": 0.0113, "lr": 5.111998957938363e-06, "epoch": 16.270964360587, "percentage": 81.35, "elapsed_time": "1:59:03", "remaining_time": "0:27:17", "throughput": 2842.11, "total_tokens": 20301664} {"current_steps": 31050, "total_steps": 38160, "loss": 0.0063, "lr": 5.105072693234525e-06, "epoch": 16.27358490566038, "percentage": 81.37, "elapsed_time": "1:59:04", "remaining_time": "0:27:15", "throughput": 2842.1, "total_tokens": 20304608} {"current_steps": 31055, "total_steps": 38160, "loss": 0.0068, "lr": 5.098150590322506e-06, "epoch": 16.27620545073375, "percentage": 81.38, "elapsed_time": "1:59:05", "remaining_time": "0:27:14", "throughput": 2842.12, "total_tokens": 20307840} {"current_steps": 31060, "total_steps": 38160, "loss": 0.0039, "lr": 5.091232650650335e-06, "epoch": 16.27882599580713, "percentage": 81.39, "elapsed_time": "1:59:06", "remaining_time": "0:27:13", "throughput": 2842.09, "total_tokens": 20310784} {"current_steps": 31065, "total_steps": 38160, "loss": 0.0085, "lr": 5.0843188756651645e-06, "epoch": 16.281446540880502, "percentage": 81.41, "elapsed_time": "1:59:07", "remaining_time": "0:27:12", "throughput": 2842.03, "total_tokens": 20313344} {"current_steps": 31070, "total_steps": 38160, "loss": 0.0082, "lr": 5.077409266813276e-06, "epoch": 16.28406708595388, "percentage": 81.42, "elapsed_time": "1:59:08", "remaining_time": "0:27:11", "throughput": 2842.01, "total_tokens": 20316256} {"current_steps": 31075, "total_steps": 38160, "loss": 0.0163, "lr": 5.0705038255400765e-06, "epoch": 16.286687631027252, "percentage": 81.43, "elapsed_time": "1:59:09", "remaining_time": "0:27:10", "throughput": 2842.13, "total_tokens": 20320672} {"current_steps": 31080, "total_steps": 38160, "loss": 0.0139, "lr": 5.063602553290106e-06, "epoch": 16.28930817610063, "percentage": 81.45, "elapsed_time": "1:59:10", "remaining_time": "0:27:08", "throughput": 2842.15, "total_tokens": 20324128} {"current_steps": 31085, "total_steps": 38160, "loss": 0.0357, "lr": 5.056705451507035e-06, "epoch": 16.291928721174003, "percentage": 81.46, "elapsed_time": "1:59:12", "remaining_time": "0:27:08", "throughput": 2842.39, "total_tokens": 20331520} {"current_steps": 31090, "total_steps": 38160, "loss": 0.0079, "lr": 5.049812521633668e-06, "epoch": 16.29454926624738, "percentage": 81.47, "elapsed_time": "1:59:14", "remaining_time": "0:27:06", "throughput": 2842.38, "total_tokens": 20334560} {"current_steps": 31095, "total_steps": 38160, "loss": 0.0062, "lr": 5.042923765111907e-06, "epoch": 16.297169811320753, "percentage": 81.49, "elapsed_time": "1:59:15", "remaining_time": "0:27:05", "throughput": 2842.4, "total_tokens": 20337856} {"current_steps": 31100, "total_steps": 38160, "loss": 0.007, "lr": 5.036039183382821e-06, "epoch": 16.29979035639413, "percentage": 81.5, "elapsed_time": "1:59:16", "remaining_time": "0:27:04", "throughput": 2842.28, "total_tokens": 20340224} {"current_steps": 31105, "total_steps": 38160, "loss": 0.0121, "lr": 5.02915877788657e-06, "epoch": 16.302410901467507, "percentage": 81.51, "elapsed_time": "1:59:17", "remaining_time": "0:27:03", "throughput": 2842.38, "total_tokens": 20343968} {"current_steps": 31110, "total_steps": 38160, "loss": 0.0095, "lr": 5.0222825500624625e-06, "epoch": 16.30503144654088, "percentage": 81.53, "elapsed_time": "1:59:18", "remaining_time": "0:27:02", "throughput": 2842.48, "total_tokens": 20348096} {"current_steps": 31115, "total_steps": 38160, "loss": 0.0156, "lr": 5.015410501348935e-06, "epoch": 16.307651991614257, "percentage": 81.54, "elapsed_time": "1:59:19", "remaining_time": "0:27:01", "throughput": 2842.48, "total_tokens": 20351072} {"current_steps": 31120, "total_steps": 38160, "loss": 0.0091, "lr": 5.008542633183527e-06, "epoch": 16.31027253668763, "percentage": 81.55, "elapsed_time": "1:59:20", "remaining_time": "0:26:59", "throughput": 2842.53, "total_tokens": 20354528} {"current_steps": 31125, "total_steps": 38160, "loss": 0.0068, "lr": 5.001678947002927e-06, "epoch": 16.312893081761008, "percentage": 81.56, "elapsed_time": "1:59:21", "remaining_time": "0:26:58", "throughput": 2842.5, "total_tokens": 20357664} {"current_steps": 31130, "total_steps": 38160, "loss": 0.0125, "lr": 4.994819444242943e-06, "epoch": 16.31551362683438, "percentage": 81.58, "elapsed_time": "1:59:22", "remaining_time": "0:26:57", "throughput": 2842.55, "total_tokens": 20361056} {"current_steps": 31135, "total_steps": 38160, "loss": 0.004, "lr": 4.9879641263384956e-06, "epoch": 16.318134171907758, "percentage": 81.59, "elapsed_time": "1:59:24", "remaining_time": "0:26:56", "throughput": 2842.56, "total_tokens": 20364160} {"current_steps": 31140, "total_steps": 38160, "loss": 0.0161, "lr": 4.981112994723644e-06, "epoch": 16.32075471698113, "percentage": 81.6, "elapsed_time": "1:59:25", "remaining_time": "0:26:55", "throughput": 2842.54, "total_tokens": 20367072} {"current_steps": 31145, "total_steps": 38160, "loss": 0.0026, "lr": 4.974266050831572e-06, "epoch": 16.32337526205451, "percentage": 81.62, "elapsed_time": "1:59:26", "remaining_time": "0:26:54", "throughput": 2842.47, "total_tokens": 20369600} {"current_steps": 31150, "total_steps": 38160, "loss": 0.0062, "lr": 4.967423296094567e-06, "epoch": 16.32599580712788, "percentage": 81.63, "elapsed_time": "1:59:27", "remaining_time": "0:26:52", "throughput": 2842.45, "total_tokens": 20372768} {"current_steps": 31155, "total_steps": 38160, "loss": 0.0075, "lr": 4.960584731944076e-06, "epoch": 16.32861635220126, "percentage": 81.64, "elapsed_time": "1:59:28", "remaining_time": "0:26:51", "throughput": 2842.43, "total_tokens": 20375680} {"current_steps": 31160, "total_steps": 38160, "loss": 0.0025, "lr": 4.953750359810627e-06, "epoch": 16.331236897274632, "percentage": 81.66, "elapsed_time": "1:59:29", "remaining_time": "0:26:50", "throughput": 2842.36, "total_tokens": 20378272} {"current_steps": 31165, "total_steps": 38160, "loss": 0.0053, "lr": 4.946920181123904e-06, "epoch": 16.33385744234801, "percentage": 81.67, "elapsed_time": "1:59:30", "remaining_time": "0:26:49", "throughput": 2842.43, "total_tokens": 20381888} {"current_steps": 31170, "total_steps": 38160, "loss": 0.008, "lr": 4.940094197312709e-06, "epoch": 16.336477987421382, "percentage": 81.68, "elapsed_time": "1:59:31", "remaining_time": "0:26:48", "throughput": 2842.51, "total_tokens": 20385856} {"current_steps": 31175, "total_steps": 38160, "loss": 0.012, "lr": 4.933272409804946e-06, "epoch": 16.33909853249476, "percentage": 81.7, "elapsed_time": "1:59:32", "remaining_time": "0:26:47", "throughput": 2842.53, "total_tokens": 20389120} {"current_steps": 31180, "total_steps": 38160, "loss": 0.0056, "lr": 4.926454820027663e-06, "epoch": 16.341719077568133, "percentage": 81.71, "elapsed_time": "1:59:34", "remaining_time": "0:26:45", "throughput": 2842.58, "total_tokens": 20392672} {"current_steps": 31185, "total_steps": 38160, "loss": 0.0055, "lr": 4.919641429407024e-06, "epoch": 16.34433962264151, "percentage": 81.72, "elapsed_time": "1:59:35", "remaining_time": "0:26:44", "throughput": 2842.51, "total_tokens": 20395232} {"current_steps": 31190, "total_steps": 38160, "loss": 0.0041, "lr": 4.912832239368304e-06, "epoch": 16.346960167714883, "percentage": 81.73, "elapsed_time": "1:59:36", "remaining_time": "0:26:43", "throughput": 2842.52, "total_tokens": 20398368} {"current_steps": 31195, "total_steps": 38160, "loss": 0.007, "lr": 4.906027251335918e-06, "epoch": 16.34958071278826, "percentage": 81.75, "elapsed_time": "1:59:37", "remaining_time": "0:26:42", "throughput": 2842.44, "total_tokens": 20400768} {"current_steps": 31200, "total_steps": 38160, "loss": 0.0101, "lr": 4.899226466733381e-06, "epoch": 16.352201257861637, "percentage": 81.76, "elapsed_time": "1:59:38", "remaining_time": "0:26:41", "throughput": 2842.5, "total_tokens": 20404448} {"current_steps": 31205, "total_steps": 38160, "loss": 0.022, "lr": 4.892429886983346e-06, "epoch": 16.35482180293501, "percentage": 81.77, "elapsed_time": "1:59:39", "remaining_time": "0:26:40", "throughput": 2842.48, "total_tokens": 20407264} {"current_steps": 31210, "total_steps": 38160, "loss": 0.0032, "lr": 4.88563751350758e-06, "epoch": 16.357442348008387, "percentage": 81.79, "elapsed_time": "1:59:40", "remaining_time": "0:26:38", "throughput": 2842.49, "total_tokens": 20410272} {"current_steps": 31215, "total_steps": 38160, "loss": 0.0088, "lr": 4.878849347726977e-06, "epoch": 16.36006289308176, "percentage": 81.8, "elapsed_time": "1:59:41", "remaining_time": "0:26:37", "throughput": 2842.48, "total_tokens": 20413280} {"current_steps": 31220, "total_steps": 38160, "loss": 0.0075, "lr": 4.872065391061526e-06, "epoch": 16.362683438155138, "percentage": 81.81, "elapsed_time": "1:59:42", "remaining_time": "0:26:36", "throughput": 2842.41, "total_tokens": 20415776} {"current_steps": 31225, "total_steps": 38160, "loss": 0.0057, "lr": 4.865285644930373e-06, "epoch": 16.36530398322851, "percentage": 81.83, "elapsed_time": "1:59:43", "remaining_time": "0:26:35", "throughput": 2842.44, "total_tokens": 20418944} {"current_steps": 31230, "total_steps": 38160, "loss": 0.0288, "lr": 4.858510110751746e-06, "epoch": 16.367924528301888, "percentage": 81.84, "elapsed_time": "1:59:44", "remaining_time": "0:26:34", "throughput": 2842.47, "total_tokens": 20422112} {"current_steps": 31235, "total_steps": 38160, "loss": 0.0031, "lr": 4.851738789943019e-06, "epoch": 16.37054507337526, "percentage": 81.85, "elapsed_time": "1:59:45", "remaining_time": "0:26:33", "throughput": 2842.42, "total_tokens": 20424736} {"current_steps": 31240, "total_steps": 38160, "loss": 0.0109, "lr": 4.844971683920674e-06, "epoch": 16.37316561844864, "percentage": 81.87, "elapsed_time": "1:59:46", "remaining_time": "0:26:31", "throughput": 2842.47, "total_tokens": 20428288} {"current_steps": 31245, "total_steps": 38160, "loss": 0.0297, "lr": 4.838208794100316e-06, "epoch": 16.37578616352201, "percentage": 81.88, "elapsed_time": "1:59:47", "remaining_time": "0:26:30", "throughput": 2842.58, "total_tokens": 20432320} {"current_steps": 31250, "total_steps": 38160, "loss": 0.0031, "lr": 4.831450121896661e-06, "epoch": 16.37840670859539, "percentage": 81.89, "elapsed_time": "1:59:48", "remaining_time": "0:26:29", "throughput": 2842.54, "total_tokens": 20434976} {"current_steps": 31255, "total_steps": 38160, "loss": 0.0093, "lr": 4.824695668723542e-06, "epoch": 16.381027253668762, "percentage": 81.91, "elapsed_time": "1:59:50", "remaining_time": "0:26:28", "throughput": 2842.5, "total_tokens": 20437664} {"current_steps": 31260, "total_steps": 38160, "loss": 0.0096, "lr": 4.817945435993915e-06, "epoch": 16.38364779874214, "percentage": 81.92, "elapsed_time": "1:59:51", "remaining_time": "0:26:27", "throughput": 2842.51, "total_tokens": 20440896} {"current_steps": 31265, "total_steps": 38160, "loss": 0.0056, "lr": 4.811199425119853e-06, "epoch": 16.386268343815512, "percentage": 81.93, "elapsed_time": "1:59:52", "remaining_time": "0:26:26", "throughput": 2842.53, "total_tokens": 20444064} {"current_steps": 31270, "total_steps": 38160, "loss": 0.0027, "lr": 4.804457637512552e-06, "epoch": 16.38888888888889, "percentage": 81.94, "elapsed_time": "1:59:53", "remaining_time": "0:26:24", "throughput": 2842.5, "total_tokens": 20446944} {"current_steps": 31275, "total_steps": 38160, "loss": 0.0174, "lr": 4.79772007458231e-06, "epoch": 16.391509433962263, "percentage": 81.96, "elapsed_time": "1:59:54", "remaining_time": "0:26:23", "throughput": 2842.48, "total_tokens": 20449888} {"current_steps": 31280, "total_steps": 38160, "loss": 0.0046, "lr": 4.7909867377385424e-06, "epoch": 16.39412997903564, "percentage": 81.97, "elapsed_time": "1:59:55", "remaining_time": "0:26:22", "throughput": 2842.58, "total_tokens": 20453824} {"current_steps": 31285, "total_steps": 38160, "loss": 0.0686, "lr": 4.784257628389794e-06, "epoch": 16.396750524109013, "percentage": 81.98, "elapsed_time": "1:59:56", "remaining_time": "0:26:21", "throughput": 2842.62, "total_tokens": 20457184} {"current_steps": 31290, "total_steps": 38160, "loss": 0.0244, "lr": 4.7775327479437166e-06, "epoch": 16.39937106918239, "percentage": 82.0, "elapsed_time": "1:59:57", "remaining_time": "0:26:20", "throughput": 2842.69, "total_tokens": 20460864} {"current_steps": 31295, "total_steps": 38160, "loss": 0.0029, "lr": 4.770812097807076e-06, "epoch": 16.401991614255767, "percentage": 82.01, "elapsed_time": "1:59:58", "remaining_time": "0:26:19", "throughput": 2842.62, "total_tokens": 20463392} {"current_steps": 31300, "total_steps": 38160, "loss": 0.0147, "lr": 4.764095679385766e-06, "epoch": 16.40461215932914, "percentage": 82.02, "elapsed_time": "1:59:59", "remaining_time": "0:26:17", "throughput": 2842.61, "total_tokens": 20466432} {"current_steps": 31305, "total_steps": 38160, "loss": 0.0071, "lr": 4.7573834940847745e-06, "epoch": 16.407232704402517, "percentage": 82.04, "elapsed_time": "2:00:00", "remaining_time": "0:26:16", "throughput": 2842.58, "total_tokens": 20469312} {"current_steps": 31310, "total_steps": 38160, "loss": 0.0068, "lr": 4.750675543308212e-06, "epoch": 16.40985324947589, "percentage": 82.05, "elapsed_time": "2:00:02", "remaining_time": "0:26:15", "throughput": 2842.51, "total_tokens": 20471936} {"current_steps": 31315, "total_steps": 38160, "loss": 0.004, "lr": 4.743971828459307e-06, "epoch": 16.412473794549268, "percentage": 82.06, "elapsed_time": "2:00:03", "remaining_time": "0:26:14", "throughput": 2842.46, "total_tokens": 20474720} {"current_steps": 31320, "total_steps": 38160, "loss": 0.0273, "lr": 4.7372723509404025e-06, "epoch": 16.41509433962264, "percentage": 82.08, "elapsed_time": "2:00:04", "remaining_time": "0:26:13", "throughput": 2842.52, "total_tokens": 20478784} {"current_steps": 31325, "total_steps": 38160, "loss": 0.0038, "lr": 4.7305771121529615e-06, "epoch": 16.417714884696018, "percentage": 82.09, "elapsed_time": "2:00:05", "remaining_time": "0:26:12", "throughput": 2842.52, "total_tokens": 20481824} {"current_steps": 31330, "total_steps": 38160, "loss": 0.0108, "lr": 4.723886113497542e-06, "epoch": 16.42033542976939, "percentage": 82.1, "elapsed_time": "2:00:06", "remaining_time": "0:26:11", "throughput": 2842.49, "total_tokens": 20484704} {"current_steps": 31335, "total_steps": 38160, "loss": 0.0057, "lr": 4.7171993563738195e-06, "epoch": 16.42295597484277, "percentage": 82.11, "elapsed_time": "2:00:07", "remaining_time": "0:26:09", "throughput": 2842.49, "total_tokens": 20487936} {"current_steps": 31340, "total_steps": 38160, "loss": 0.0065, "lr": 4.7105168421805924e-06, "epoch": 16.42557651991614, "percentage": 82.13, "elapsed_time": "2:00:08", "remaining_time": "0:26:08", "throughput": 2842.51, "total_tokens": 20491264} {"current_steps": 31345, "total_steps": 38160, "loss": 0.0098, "lr": 4.703838572315767e-06, "epoch": 16.42819706498952, "percentage": 82.14, "elapsed_time": "2:00:09", "remaining_time": "0:26:07", "throughput": 2842.48, "total_tokens": 20494112} {"current_steps": 31350, "total_steps": 38160, "loss": 0.0137, "lr": 4.697164548176367e-06, "epoch": 16.430817610062892, "percentage": 82.15, "elapsed_time": "2:00:11", "remaining_time": "0:26:06", "throughput": 2842.48, "total_tokens": 20497184} {"current_steps": 31355, "total_steps": 38160, "loss": 0.007, "lr": 4.690494771158519e-06, "epoch": 16.43343815513627, "percentage": 82.17, "elapsed_time": "2:00:12", "remaining_time": "0:26:05", "throughput": 2842.55, "total_tokens": 20500864} {"current_steps": 31360, "total_steps": 38160, "loss": 0.0067, "lr": 4.683829242657453e-06, "epoch": 16.436058700209642, "percentage": 82.18, "elapsed_time": "2:00:13", "remaining_time": "0:26:04", "throughput": 2842.61, "total_tokens": 20504928} {"current_steps": 31365, "total_steps": 38160, "loss": 0.0055, "lr": 4.677167964067533e-06, "epoch": 16.43867924528302, "percentage": 82.19, "elapsed_time": "2:00:14", "remaining_time": "0:26:02", "throughput": 2842.58, "total_tokens": 20507776} {"current_steps": 31370, "total_steps": 38160, "loss": 0.0035, "lr": 4.670510936782216e-06, "epoch": 16.441299790356393, "percentage": 82.21, "elapsed_time": "2:00:15", "remaining_time": "0:26:01", "throughput": 2842.57, "total_tokens": 20510944} {"current_steps": 31375, "total_steps": 38160, "loss": 0.0074, "lr": 4.6638581621940815e-06, "epoch": 16.44392033542977, "percentage": 82.22, "elapsed_time": "2:00:16", "remaining_time": "0:26:00", "throughput": 2842.66, "total_tokens": 20514784} {"current_steps": 31380, "total_steps": 38160, "loss": 0.0161, "lr": 4.657209641694821e-06, "epoch": 16.446540880503143, "percentage": 82.23, "elapsed_time": "2:00:17", "remaining_time": "0:25:59", "throughput": 2842.54, "total_tokens": 20517248} {"current_steps": 31385, "total_steps": 38160, "loss": 0.0146, "lr": 4.65056537667522e-06, "epoch": 16.44916142557652, "percentage": 82.25, "elapsed_time": "2:00:19", "remaining_time": "0:25:58", "throughput": 2842.54, "total_tokens": 20520512} {"current_steps": 31390, "total_steps": 38160, "loss": 0.0111, "lr": 4.643925368525176e-06, "epoch": 16.451781970649897, "percentage": 82.26, "elapsed_time": "2:00:20", "remaining_time": "0:25:57", "throughput": 2842.5, "total_tokens": 20523328} {"current_steps": 31395, "total_steps": 38160, "loss": 0.0035, "lr": 4.637289618633711e-06, "epoch": 16.45440251572327, "percentage": 82.27, "elapsed_time": "2:00:21", "remaining_time": "0:25:56", "throughput": 2842.57, "total_tokens": 20527296} {"current_steps": 31400, "total_steps": 38160, "loss": 0.0051, "lr": 4.630658128388948e-06, "epoch": 16.457023060796647, "percentage": 82.29, "elapsed_time": "2:00:22", "remaining_time": "0:25:54", "throughput": 2842.51, "total_tokens": 20529952} {"current_steps": 31405, "total_steps": 38160, "loss": 0.0136, "lr": 4.624030899178125e-06, "epoch": 16.45964360587002, "percentage": 82.3, "elapsed_time": "2:00:23", "remaining_time": "0:25:53", "throughput": 2842.58, "total_tokens": 20533760} {"current_steps": 31410, "total_steps": 38160, "loss": 0.0075, "lr": 4.617407932387569e-06, "epoch": 16.462264150943398, "percentage": 82.31, "elapsed_time": "2:00:24", "remaining_time": "0:25:52", "throughput": 2842.5, "total_tokens": 20536384} {"current_steps": 31415, "total_steps": 38160, "loss": 0.0069, "lr": 4.610789229402743e-06, "epoch": 16.46488469601677, "percentage": 82.32, "elapsed_time": "2:00:25", "remaining_time": "0:25:51", "throughput": 2842.52, "total_tokens": 20539744} {"current_steps": 31420, "total_steps": 38160, "loss": 0.0121, "lr": 4.604174791608193e-06, "epoch": 16.467505241090148, "percentage": 82.34, "elapsed_time": "2:00:27", "remaining_time": "0:25:50", "throughput": 2842.63, "total_tokens": 20543904} {"current_steps": 31425, "total_steps": 38160, "loss": 0.0055, "lr": 4.597564620387587e-06, "epoch": 16.47012578616352, "percentage": 82.35, "elapsed_time": "2:00:28", "remaining_time": "0:25:49", "throughput": 2842.69, "total_tokens": 20547552} {"current_steps": 31430, "total_steps": 38160, "loss": 0.005, "lr": 4.590958717123708e-06, "epoch": 16.4727463312369, "percentage": 82.36, "elapsed_time": "2:00:29", "remaining_time": "0:25:47", "throughput": 2842.62, "total_tokens": 20549984} {"current_steps": 31435, "total_steps": 38160, "loss": 0.0049, "lr": 4.5843570831984174e-06, "epoch": 16.47536687631027, "percentage": 82.38, "elapsed_time": "2:00:30", "remaining_time": "0:25:46", "throughput": 2842.66, "total_tokens": 20553280} {"current_steps": 31440, "total_steps": 38160, "loss": 0.0163, "lr": 4.577759719992719e-06, "epoch": 16.47798742138365, "percentage": 82.39, "elapsed_time": "2:00:31", "remaining_time": "0:25:45", "throughput": 2842.78, "total_tokens": 20557376} {"current_steps": 31445, "total_steps": 38160, "loss": 0.0264, "lr": 4.571166628886692e-06, "epoch": 16.480607966457022, "percentage": 82.4, "elapsed_time": "2:00:32", "remaining_time": "0:25:44", "throughput": 2842.76, "total_tokens": 20560288} {"current_steps": 31450, "total_steps": 38160, "loss": 0.0175, "lr": 4.564577811259541e-06, "epoch": 16.4832285115304, "percentage": 82.42, "elapsed_time": "2:00:33", "remaining_time": "0:25:43", "throughput": 2842.76, "total_tokens": 20563392} {"current_steps": 31455, "total_steps": 38160, "loss": 0.0222, "lr": 4.557993268489574e-06, "epoch": 16.485849056603772, "percentage": 82.43, "elapsed_time": "2:00:34", "remaining_time": "0:25:42", "throughput": 2842.75, "total_tokens": 20566272} {"current_steps": 31460, "total_steps": 38160, "loss": 0.009, "lr": 4.551413001954205e-06, "epoch": 16.48846960167715, "percentage": 82.44, "elapsed_time": "2:00:35", "remaining_time": "0:25:40", "throughput": 2842.65, "total_tokens": 20568672} {"current_steps": 31465, "total_steps": 38160, "loss": 0.0184, "lr": 4.54483701302994e-06, "epoch": 16.491090146750523, "percentage": 82.46, "elapsed_time": "2:00:36", "remaining_time": "0:25:39", "throughput": 2842.69, "total_tokens": 20572096} {"current_steps": 31470, "total_steps": 38160, "loss": 0.0066, "lr": 4.538265303092415e-06, "epoch": 16.4937106918239, "percentage": 82.47, "elapsed_time": "2:00:37", "remaining_time": "0:25:38", "throughput": 2842.68, "total_tokens": 20575008} {"current_steps": 31475, "total_steps": 38160, "loss": 0.0147, "lr": 4.531697873516338e-06, "epoch": 16.496331236897273, "percentage": 82.48, "elapsed_time": "2:00:38", "remaining_time": "0:25:37", "throughput": 2842.72, "total_tokens": 20578304} {"current_steps": 31480, "total_steps": 38160, "loss": 0.0134, "lr": 4.525134725675556e-06, "epoch": 16.49895178197065, "percentage": 82.49, "elapsed_time": "2:00:40", "remaining_time": "0:25:36", "throughput": 2842.69, "total_tokens": 20581248} {"current_steps": 31485, "total_steps": 38160, "loss": 0.0026, "lr": 4.518575860943003e-06, "epoch": 16.501572327044027, "percentage": 82.51, "elapsed_time": "2:00:41", "remaining_time": "0:25:35", "throughput": 2842.63, "total_tokens": 20584032} {"current_steps": 31490, "total_steps": 38160, "loss": 0.0073, "lr": 4.512021280690712e-06, "epoch": 16.5041928721174, "percentage": 82.52, "elapsed_time": "2:00:42", "remaining_time": "0:25:34", "throughput": 2842.72, "total_tokens": 20587872} {"current_steps": 31495, "total_steps": 38160, "loss": 0.0131, "lr": 4.505470986289828e-06, "epoch": 16.506813417190777, "percentage": 82.53, "elapsed_time": "2:00:43", "remaining_time": "0:25:32", "throughput": 2842.71, "total_tokens": 20590880} {"current_steps": 31500, "total_steps": 38160, "loss": 0.0063, "lr": 4.498924979110605e-06, "epoch": 16.50943396226415, "percentage": 82.55, "elapsed_time": "2:00:44", "remaining_time": "0:25:31", "throughput": 2842.67, "total_tokens": 20593792} {"current_steps": 31505, "total_steps": 38160, "loss": 0.0057, "lr": 4.492383260522384e-06, "epoch": 16.512054507337528, "percentage": 82.56, "elapsed_time": "2:00:45", "remaining_time": "0:25:30", "throughput": 2842.67, "total_tokens": 20596992} {"current_steps": 31510, "total_steps": 38160, "loss": 0.0111, "lr": 4.485845831893626e-06, "epoch": 16.5146750524109, "percentage": 82.57, "elapsed_time": "2:00:46", "remaining_time": "0:25:29", "throughput": 2842.64, "total_tokens": 20599808} {"current_steps": 31515, "total_steps": 38160, "loss": 0.0046, "lr": 4.479312694591878e-06, "epoch": 16.517295597484278, "percentage": 82.59, "elapsed_time": "2:00:47", "remaining_time": "0:25:28", "throughput": 2842.66, "total_tokens": 20603136} {"current_steps": 31520, "total_steps": 38160, "loss": 0.0036, "lr": 4.4727838499838e-06, "epoch": 16.51991614255765, "percentage": 82.6, "elapsed_time": "2:00:48", "remaining_time": "0:25:27", "throughput": 2842.59, "total_tokens": 20605792} {"current_steps": 31525, "total_steps": 38160, "loss": 0.0065, "lr": 4.4662592994351545e-06, "epoch": 16.52253668763103, "percentage": 82.61, "elapsed_time": "2:00:50", "remaining_time": "0:25:25", "throughput": 2842.6, "total_tokens": 20608928} {"current_steps": 31530, "total_steps": 38160, "loss": 0.0052, "lr": 4.4597390443108065e-06, "epoch": 16.5251572327044, "percentage": 82.63, "elapsed_time": "2:00:51", "remaining_time": "0:25:24", "throughput": 2842.56, "total_tokens": 20611680} {"current_steps": 31535, "total_steps": 38160, "loss": 0.012, "lr": 4.453223085974712e-06, "epoch": 16.52777777777778, "percentage": 82.64, "elapsed_time": "2:00:52", "remaining_time": "0:25:23", "throughput": 2842.54, "total_tokens": 20614528} {"current_steps": 31540, "total_steps": 38160, "loss": 0.0088, "lr": 4.4467114257899425e-06, "epoch": 16.530398322851152, "percentage": 82.65, "elapsed_time": "2:00:53", "remaining_time": "0:25:22", "throughput": 2842.57, "total_tokens": 20617984} {"current_steps": 31545, "total_steps": 38160, "loss": 0.0051, "lr": 4.44020406511865e-06, "epoch": 16.53301886792453, "percentage": 82.67, "elapsed_time": "2:00:54", "remaining_time": "0:25:21", "throughput": 2842.69, "total_tokens": 20621952} {"current_steps": 31550, "total_steps": 38160, "loss": 0.0169, "lr": 4.43370100532211e-06, "epoch": 16.535639412997902, "percentage": 82.68, "elapsed_time": "2:00:55", "remaining_time": "0:25:20", "throughput": 2842.61, "total_tokens": 20624416} {"current_steps": 31555, "total_steps": 38160, "loss": 0.0033, "lr": 4.427202247760695e-06, "epoch": 16.53825995807128, "percentage": 82.69, "elapsed_time": "2:00:56", "remaining_time": "0:25:18", "throughput": 2842.61, "total_tokens": 20627456} {"current_steps": 31560, "total_steps": 38160, "loss": 0.0076, "lr": 4.420707793793854e-06, "epoch": 16.540880503144653, "percentage": 82.7, "elapsed_time": "2:00:57", "remaining_time": "0:25:17", "throughput": 2842.61, "total_tokens": 20630688} {"current_steps": 31565, "total_steps": 38160, "loss": 0.0247, "lr": 4.414217644780172e-06, "epoch": 16.54350104821803, "percentage": 82.72, "elapsed_time": "2:00:58", "remaining_time": "0:25:16", "throughput": 2842.78, "total_tokens": 20635552} {"current_steps": 31570, "total_steps": 38160, "loss": 0.0102, "lr": 4.407731802077294e-06, "epoch": 16.546121593291403, "percentage": 82.73, "elapsed_time": "2:00:59", "remaining_time": "0:25:15", "throughput": 2842.75, "total_tokens": 20638272} {"current_steps": 31575, "total_steps": 38160, "loss": 0.0126, "lr": 4.401250267041996e-06, "epoch": 16.54874213836478, "percentage": 82.74, "elapsed_time": "2:01:01", "remaining_time": "0:25:14", "throughput": 2842.76, "total_tokens": 20641536} {"current_steps": 31580, "total_steps": 38160, "loss": 0.0079, "lr": 4.394773041030137e-06, "epoch": 16.551362683438157, "percentage": 82.76, "elapsed_time": "2:01:02", "remaining_time": "0:25:13", "throughput": 2842.78, "total_tokens": 20644864} {"current_steps": 31585, "total_steps": 38160, "loss": 0.019, "lr": 4.388300125396685e-06, "epoch": 16.55398322851153, "percentage": 82.77, "elapsed_time": "2:01:03", "remaining_time": "0:25:11", "throughput": 2842.83, "total_tokens": 20648224} {"current_steps": 31590, "total_steps": 38160, "loss": 0.0072, "lr": 4.381831521495699e-06, "epoch": 16.556603773584907, "percentage": 82.78, "elapsed_time": "2:01:04", "remaining_time": "0:25:10", "throughput": 2842.96, "total_tokens": 20652800} {"current_steps": 31595, "total_steps": 38160, "loss": 0.0067, "lr": 4.37536723068033e-06, "epoch": 16.55922431865828, "percentage": 82.8, "elapsed_time": "2:01:05", "remaining_time": "0:25:09", "throughput": 2842.95, "total_tokens": 20655776} {"current_steps": 31600, "total_steps": 38160, "loss": 0.0101, "lr": 4.368907254302837e-06, "epoch": 16.561844863731658, "percentage": 82.81, "elapsed_time": "2:01:06", "remaining_time": "0:25:08", "throughput": 2842.97, "total_tokens": 20659040} {"current_steps": 31605, "total_steps": 38160, "loss": 0.0195, "lr": 4.3624515937145725e-06, "epoch": 16.56446540880503, "percentage": 82.82, "elapsed_time": "2:01:07", "remaining_time": "0:25:07", "throughput": 2843.03, "total_tokens": 20662560} {"current_steps": 31610, "total_steps": 38160, "loss": 0.003, "lr": 4.3560002502659905e-06, "epoch": 16.567085953878408, "percentage": 82.84, "elapsed_time": "2:01:08", "remaining_time": "0:25:06", "throughput": 2842.95, "total_tokens": 20664992} {"current_steps": 31615, "total_steps": 38160, "loss": 0.0069, "lr": 4.349553225306644e-06, "epoch": 16.56970649895178, "percentage": 82.85, "elapsed_time": "2:01:09", "remaining_time": "0:25:05", "throughput": 2842.88, "total_tokens": 20667488} {"current_steps": 31620, "total_steps": 38160, "loss": 0.0096, "lr": 4.343110520185167e-06, "epoch": 16.572327044025158, "percentage": 82.86, "elapsed_time": "2:01:10", "remaining_time": "0:25:03", "throughput": 2842.85, "total_tokens": 20670304} {"current_steps": 31625, "total_steps": 38160, "loss": 0.0181, "lr": 4.336672136249298e-06, "epoch": 16.57494758909853, "percentage": 82.87, "elapsed_time": "2:01:12", "remaining_time": "0:25:02", "throughput": 2842.91, "total_tokens": 20674080} {"current_steps": 31630, "total_steps": 38160, "loss": 0.0038, "lr": 4.33023807484588e-06, "epoch": 16.57756813417191, "percentage": 82.89, "elapsed_time": "2:01:13", "remaining_time": "0:25:01", "throughput": 2842.89, "total_tokens": 20676928} {"current_steps": 31635, "total_steps": 38160, "loss": 0.0052, "lr": 4.323808337320842e-06, "epoch": 16.580188679245282, "percentage": 82.9, "elapsed_time": "2:01:14", "remaining_time": "0:25:00", "throughput": 2842.79, "total_tokens": 20680096} {"current_steps": 31640, "total_steps": 38160, "loss": 0.0219, "lr": 4.31738292501922e-06, "epoch": 16.58280922431866, "percentage": 82.91, "elapsed_time": "2:01:15", "remaining_time": "0:24:59", "throughput": 2842.82, "total_tokens": 20683360} {"current_steps": 31645, "total_steps": 38160, "loss": 0.0036, "lr": 4.31096183928513e-06, "epoch": 16.585429769392032, "percentage": 82.93, "elapsed_time": "2:01:16", "remaining_time": "0:24:58", "throughput": 2842.75, "total_tokens": 20685920} {"current_steps": 31650, "total_steps": 38160, "loss": 0.0151, "lr": 4.304545081461783e-06, "epoch": 16.58805031446541, "percentage": 82.94, "elapsed_time": "2:01:17", "remaining_time": "0:24:56", "throughput": 2842.7, "total_tokens": 20688576} {"current_steps": 31655, "total_steps": 38160, "loss": 0.0045, "lr": 4.298132652891501e-06, "epoch": 16.590670859538783, "percentage": 82.95, "elapsed_time": "2:01:18", "remaining_time": "0:24:55", "throughput": 2842.66, "total_tokens": 20691424} {"current_steps": 31660, "total_steps": 38160, "loss": 0.0073, "lr": 4.291724554915688e-06, "epoch": 16.59329140461216, "percentage": 82.97, "elapsed_time": "2:01:19", "remaining_time": "0:24:54", "throughput": 2842.67, "total_tokens": 20694432} {"current_steps": 31665, "total_steps": 38160, "loss": 0.008, "lr": 4.285320788874853e-06, "epoch": 16.595911949685533, "percentage": 82.98, "elapsed_time": "2:01:21", "remaining_time": "0:24:53", "throughput": 2842.67, "total_tokens": 20697856} {"current_steps": 31670, "total_steps": 38160, "loss": 0.0084, "lr": 4.278921356108581e-06, "epoch": 16.59853249475891, "percentage": 82.99, "elapsed_time": "2:01:22", "remaining_time": "0:24:52", "throughput": 2842.72, "total_tokens": 20701504} {"current_steps": 31675, "total_steps": 38160, "loss": 0.0106, "lr": 4.272526257955556e-06, "epoch": 16.601153039832283, "percentage": 83.01, "elapsed_time": "2:01:23", "remaining_time": "0:24:51", "throughput": 2842.79, "total_tokens": 20705056} {"current_steps": 31680, "total_steps": 38160, "loss": 0.0048, "lr": 4.266135495753567e-06, "epoch": 16.60377358490566, "percentage": 83.02, "elapsed_time": "2:01:24", "remaining_time": "0:24:50", "throughput": 2842.75, "total_tokens": 20707872} {"current_steps": 31685, "total_steps": 38160, "loss": 0.0083, "lr": 4.259749070839491e-06, "epoch": 16.606394129979037, "percentage": 83.03, "elapsed_time": "2:01:25", "remaining_time": "0:24:48", "throughput": 2842.69, "total_tokens": 20710560} {"current_steps": 31690, "total_steps": 38160, "loss": 0.0617, "lr": 4.253366984549289e-06, "epoch": 16.60901467505241, "percentage": 83.05, "elapsed_time": "2:01:26", "remaining_time": "0:24:47", "throughput": 2842.75, "total_tokens": 20714016} {"current_steps": 31695, "total_steps": 38160, "loss": 0.0093, "lr": 4.24698923821803e-06, "epoch": 16.611635220125788, "percentage": 83.06, "elapsed_time": "2:01:27", "remaining_time": "0:24:46", "throughput": 2842.73, "total_tokens": 20717120} {"current_steps": 31700, "total_steps": 38160, "loss": 0.0114, "lr": 4.240615833179861e-06, "epoch": 16.61425576519916, "percentage": 83.07, "elapsed_time": "2:01:28", "remaining_time": "0:24:45", "throughput": 2842.72, "total_tokens": 20720160} {"current_steps": 31705, "total_steps": 38160, "loss": 0.0087, "lr": 4.234246770768016e-06, "epoch": 16.616876310272538, "percentage": 83.08, "elapsed_time": "2:01:29", "remaining_time": "0:24:44", "throughput": 2842.74, "total_tokens": 20723328} {"current_steps": 31710, "total_steps": 38160, "loss": 0.012, "lr": 4.227882052314841e-06, "epoch": 16.61949685534591, "percentage": 83.1, "elapsed_time": "2:01:30", "remaining_time": "0:24:43", "throughput": 2842.63, "total_tokens": 20725632} {"current_steps": 31715, "total_steps": 38160, "loss": 0.0177, "lr": 4.2215216791517575e-06, "epoch": 16.622117400419288, "percentage": 83.11, "elapsed_time": "2:01:32", "remaining_time": "0:24:41", "throughput": 2842.72, "total_tokens": 20729600} {"current_steps": 31720, "total_steps": 38160, "loss": 0.024, "lr": 4.215165652609293e-06, "epoch": 16.62473794549266, "percentage": 83.12, "elapsed_time": "2:01:33", "remaining_time": "0:24:40", "throughput": 2842.69, "total_tokens": 20732512} {"current_steps": 31725, "total_steps": 38160, "loss": 0.0121, "lr": 4.208813974017048e-06, "epoch": 16.62735849056604, "percentage": 83.14, "elapsed_time": "2:01:34", "remaining_time": "0:24:39", "throughput": 2842.76, "total_tokens": 20736544} {"current_steps": 31730, "total_steps": 38160, "loss": 0.0461, "lr": 4.202466644703712e-06, "epoch": 16.629979035639412, "percentage": 83.15, "elapsed_time": "2:01:35", "remaining_time": "0:24:38", "throughput": 2842.81, "total_tokens": 20739968} {"current_steps": 31735, "total_steps": 38160, "loss": 0.0072, "lr": 4.196123665997087e-06, "epoch": 16.63259958071279, "percentage": 83.16, "elapsed_time": "2:01:36", "remaining_time": "0:24:37", "throughput": 2842.8, "total_tokens": 20743296} {"current_steps": 31740, "total_steps": 38160, "loss": 0.0103, "lr": 4.189785039224045e-06, "epoch": 16.635220125786162, "percentage": 83.18, "elapsed_time": "2:01:37", "remaining_time": "0:24:36", "throughput": 2842.69, "total_tokens": 20745696} {"current_steps": 31745, "total_steps": 38160, "loss": 0.0373, "lr": 4.183450765710567e-06, "epoch": 16.63784067085954, "percentage": 83.19, "elapsed_time": "2:01:39", "remaining_time": "0:24:35", "throughput": 2842.84, "total_tokens": 20750272} {"current_steps": 31750, "total_steps": 38160, "loss": 0.018, "lr": 4.177120846781693e-06, "epoch": 16.640461215932913, "percentage": 83.2, "elapsed_time": "2:01:40", "remaining_time": "0:24:33", "throughput": 2842.87, "total_tokens": 20754112} {"current_steps": 31755, "total_steps": 38160, "loss": 0.0042, "lr": 4.170795283761583e-06, "epoch": 16.64308176100629, "percentage": 83.22, "elapsed_time": "2:01:41", "remaining_time": "0:24:32", "throughput": 2842.8, "total_tokens": 20756928} {"current_steps": 31760, "total_steps": 38160, "loss": 0.0771, "lr": 4.164474077973462e-06, "epoch": 16.645702306079663, "percentage": 83.23, "elapsed_time": "2:01:42", "remaining_time": "0:24:31", "throughput": 2842.78, "total_tokens": 20759968} {"current_steps": 31765, "total_steps": 38160, "loss": 0.0076, "lr": 4.158157230739659e-06, "epoch": 16.64832285115304, "percentage": 83.24, "elapsed_time": "2:01:43", "remaining_time": "0:24:30", "throughput": 2842.71, "total_tokens": 20762560} {"current_steps": 31770, "total_steps": 38160, "loss": 0.005, "lr": 4.151844743381589e-06, "epoch": 16.650943396226417, "percentage": 83.25, "elapsed_time": "2:01:44", "remaining_time": "0:24:29", "throughput": 2842.64, "total_tokens": 20765120} {"current_steps": 31775, "total_steps": 38160, "loss": 0.0036, "lr": 4.145536617219756e-06, "epoch": 16.65356394129979, "percentage": 83.27, "elapsed_time": "2:01:45", "remaining_time": "0:24:28", "throughput": 2842.6, "total_tokens": 20767840} {"current_steps": 31780, "total_steps": 38160, "loss": 0.0092, "lr": 4.139232853573735e-06, "epoch": 16.656184486373167, "percentage": 83.28, "elapsed_time": "2:01:47", "remaining_time": "0:24:26", "throughput": 2842.63, "total_tokens": 20771200} {"current_steps": 31785, "total_steps": 38160, "loss": 0.0074, "lr": 4.132933453762214e-06, "epoch": 16.65880503144654, "percentage": 83.29, "elapsed_time": "2:01:48", "remaining_time": "0:24:25", "throughput": 2842.63, "total_tokens": 20774336} {"current_steps": 31790, "total_steps": 38160, "loss": 0.0181, "lr": 4.126638419102946e-06, "epoch": 16.661425576519918, "percentage": 83.31, "elapsed_time": "2:01:49", "remaining_time": "0:24:24", "throughput": 2842.62, "total_tokens": 20777248} {"current_steps": 31795, "total_steps": 38160, "loss": 0.0089, "lr": 4.120347750912784e-06, "epoch": 16.66404612159329, "percentage": 83.32, "elapsed_time": "2:01:50", "remaining_time": "0:24:23", "throughput": 2842.61, "total_tokens": 20780288} {"current_steps": 31800, "total_steps": 38160, "loss": 0.0327, "lr": 4.1140614505076724e-06, "epoch": 16.666666666666668, "percentage": 83.33, "elapsed_time": "2:01:51", "remaining_time": "0:24:22", "throughput": 2842.54, "total_tokens": 20782848} {"current_steps": 31805, "total_steps": 38160, "loss": 0.0288, "lr": 4.10777951920262e-06, "epoch": 16.66928721174004, "percentage": 83.35, "elapsed_time": "2:01:52", "remaining_time": "0:24:21", "throughput": 2842.66, "total_tokens": 20787168} {"current_steps": 31810, "total_steps": 38160, "loss": 0.0114, "lr": 4.1015019583117455e-06, "epoch": 16.671907756813418, "percentage": 83.36, "elapsed_time": "2:01:53", "remaining_time": "0:24:19", "throughput": 2842.66, "total_tokens": 20790176} {"current_steps": 31815, "total_steps": 38160, "loss": 0.0053, "lr": 4.095228769148232e-06, "epoch": 16.67452830188679, "percentage": 83.37, "elapsed_time": "2:01:54", "remaining_time": "0:24:18", "throughput": 2842.62, "total_tokens": 20792864} {"current_steps": 31820, "total_steps": 38160, "loss": 0.0127, "lr": 4.088959953024368e-06, "epoch": 16.67714884696017, "percentage": 83.39, "elapsed_time": "2:01:55", "remaining_time": "0:24:17", "throughput": 2842.75, "total_tokens": 20797408} {"current_steps": 31825, "total_steps": 38160, "loss": 0.0031, "lr": 4.082695511251522e-06, "epoch": 16.679769392033542, "percentage": 83.4, "elapsed_time": "2:01:57", "remaining_time": "0:24:16", "throughput": 2842.71, "total_tokens": 20800128} {"current_steps": 31830, "total_steps": 38160, "loss": 0.0038, "lr": 4.076435445140131e-06, "epoch": 16.68238993710692, "percentage": 83.41, "elapsed_time": "2:01:58", "remaining_time": "0:24:15", "throughput": 2842.69, "total_tokens": 20803008} {"current_steps": 31835, "total_steps": 38160, "loss": 0.0445, "lr": 4.070179755999737e-06, "epoch": 16.685010482180292, "percentage": 83.43, "elapsed_time": "2:01:59", "remaining_time": "0:24:14", "throughput": 2842.71, "total_tokens": 20806144} {"current_steps": 31840, "total_steps": 38160, "loss": 0.0069, "lr": 4.063928445138962e-06, "epoch": 16.68763102725367, "percentage": 83.44, "elapsed_time": "2:02:00", "remaining_time": "0:24:13", "throughput": 2842.76, "total_tokens": 20809472} {"current_steps": 31845, "total_steps": 38160, "loss": 0.0064, "lr": 4.057681513865499e-06, "epoch": 16.690251572327043, "percentage": 83.45, "elapsed_time": "2:02:01", "remaining_time": "0:24:11", "throughput": 2842.74, "total_tokens": 20812288} {"current_steps": 31850, "total_steps": 38160, "loss": 0.007, "lr": 4.0514389634861426e-06, "epoch": 16.69287211740042, "percentage": 83.46, "elapsed_time": "2:02:02", "remaining_time": "0:24:10", "throughput": 2842.7, "total_tokens": 20815296} {"current_steps": 31855, "total_steps": 38160, "loss": 0.0313, "lr": 4.045200795306767e-06, "epoch": 16.695492662473793, "percentage": 83.48, "elapsed_time": "2:02:04", "remaining_time": "0:24:09", "throughput": 2842.97, "total_tokens": 20822656} {"current_steps": 31860, "total_steps": 38160, "loss": 0.0042, "lr": 4.038967010632314e-06, "epoch": 16.69811320754717, "percentage": 83.49, "elapsed_time": "2:02:05", "remaining_time": "0:24:08", "throughput": 2843.0, "total_tokens": 20826016} {"current_steps": 31865, "total_steps": 38160, "loss": 0.0073, "lr": 4.032737610766826e-06, "epoch": 16.700733752620543, "percentage": 83.5, "elapsed_time": "2:02:06", "remaining_time": "0:24:07", "throughput": 2843.08, "total_tokens": 20829824} {"current_steps": 31870, "total_steps": 38160, "loss": 0.0033, "lr": 4.026512597013429e-06, "epoch": 16.70335429769392, "percentage": 83.52, "elapsed_time": "2:02:07", "remaining_time": "0:24:06", "throughput": 2843.03, "total_tokens": 20832512} {"current_steps": 31875, "total_steps": 38160, "loss": 0.0079, "lr": 4.020291970674312e-06, "epoch": 16.705974842767297, "percentage": 83.53, "elapsed_time": "2:02:08", "remaining_time": "0:24:05", "throughput": 2843.1, "total_tokens": 20836000} {"current_steps": 31880, "total_steps": 38160, "loss": 0.0042, "lr": 4.0140757330507705e-06, "epoch": 16.70859538784067, "percentage": 83.54, "elapsed_time": "2:02:09", "remaining_time": "0:24:03", "throughput": 2843.09, "total_tokens": 20838976} {"current_steps": 31885, "total_steps": 38160, "loss": 0.0147, "lr": 4.007863885443161e-06, "epoch": 16.711215932914047, "percentage": 83.56, "elapsed_time": "2:02:10", "remaining_time": "0:24:02", "throughput": 2843.13, "total_tokens": 20842208} {"current_steps": 31890, "total_steps": 38160, "loss": 0.0109, "lr": 4.001656429150935e-06, "epoch": 16.71383647798742, "percentage": 83.57, "elapsed_time": "2:02:11", "remaining_time": "0:24:01", "throughput": 2843.23, "total_tokens": 20846272} {"current_steps": 31895, "total_steps": 38160, "loss": 0.0028, "lr": 3.9954533654726235e-06, "epoch": 16.716457023060798, "percentage": 83.58, "elapsed_time": "2:02:12", "remaining_time": "0:24:00", "throughput": 2843.16, "total_tokens": 20848896} {"current_steps": 31900, "total_steps": 38160, "loss": 0.0126, "lr": 3.989254695705841e-06, "epoch": 16.71907756813417, "percentage": 83.6, "elapsed_time": "2:02:14", "remaining_time": "0:23:59", "throughput": 2843.2, "total_tokens": 20852288} {"current_steps": 31905, "total_steps": 38160, "loss": 0.0076, "lr": 3.983060421147272e-06, "epoch": 16.721698113207548, "percentage": 83.61, "elapsed_time": "2:02:15", "remaining_time": "0:23:58", "throughput": 2843.18, "total_tokens": 20855136} {"current_steps": 31910, "total_steps": 38160, "loss": 0.0039, "lr": 3.976870543092684e-06, "epoch": 16.72431865828092, "percentage": 83.62, "elapsed_time": "2:02:16", "remaining_time": "0:23:56", "throughput": 2843.21, "total_tokens": 20858432} {"current_steps": 31915, "total_steps": 38160, "loss": 0.0064, "lr": 3.970685062836932e-06, "epoch": 16.7269392033543, "percentage": 83.63, "elapsed_time": "2:02:17", "remaining_time": "0:23:55", "throughput": 2843.18, "total_tokens": 20861280} {"current_steps": 31920, "total_steps": 38160, "loss": 0.0032, "lr": 3.96450398167395e-06, "epoch": 16.729559748427672, "percentage": 83.65, "elapsed_time": "2:02:18", "remaining_time": "0:23:54", "throughput": 2843.12, "total_tokens": 20863968} {"current_steps": 31925, "total_steps": 38160, "loss": 0.0204, "lr": 3.958327300896758e-06, "epoch": 16.73218029350105, "percentage": 83.66, "elapsed_time": "2:02:19", "remaining_time": "0:23:53", "throughput": 2842.99, "total_tokens": 20866112} {"current_steps": 31930, "total_steps": 38160, "loss": 0.0067, "lr": 3.952155021797429e-06, "epoch": 16.734800838574422, "percentage": 83.67, "elapsed_time": "2:02:20", "remaining_time": "0:23:52", "throughput": 2843.05, "total_tokens": 20869856} {"current_steps": 31935, "total_steps": 38160, "loss": 0.0089, "lr": 3.945987145667151e-06, "epoch": 16.7374213836478, "percentage": 83.69, "elapsed_time": "2:02:21", "remaining_time": "0:23:51", "throughput": 2842.99, "total_tokens": 20872448} {"current_steps": 31940, "total_steps": 38160, "loss": 0.0034, "lr": 3.939823673796162e-06, "epoch": 16.740041928721173, "percentage": 83.7, "elapsed_time": "2:02:22", "remaining_time": "0:23:49", "throughput": 2842.93, "total_tokens": 20875008} {"current_steps": 31945, "total_steps": 38160, "loss": 0.0207, "lr": 3.933664607473789e-06, "epoch": 16.74266247379455, "percentage": 83.71, "elapsed_time": "2:02:23", "remaining_time": "0:23:48", "throughput": 2842.94, "total_tokens": 20878144} {"current_steps": 31950, "total_steps": 38160, "loss": 0.0094, "lr": 3.927509947988445e-06, "epoch": 16.745283018867923, "percentage": 83.73, "elapsed_time": "2:02:25", "remaining_time": "0:23:47", "throughput": 2842.91, "total_tokens": 20881216} {"current_steps": 31955, "total_steps": 38160, "loss": 0.0067, "lr": 3.9213596966276164e-06, "epoch": 16.7479035639413, "percentage": 83.74, "elapsed_time": "2:02:26", "remaining_time": "0:23:46", "throughput": 2842.96, "total_tokens": 20885120} {"current_steps": 31960, "total_steps": 38160, "loss": 0.028, "lr": 3.9152138546778625e-06, "epoch": 16.750524109014677, "percentage": 83.75, "elapsed_time": "2:02:27", "remaining_time": "0:23:45", "throughput": 2842.91, "total_tokens": 20887808} {"current_steps": 31965, "total_steps": 38160, "loss": 0.0131, "lr": 3.9090724234248175e-06, "epoch": 16.75314465408805, "percentage": 83.77, "elapsed_time": "2:02:28", "remaining_time": "0:23:44", "throughput": 2842.89, "total_tokens": 20890720} {"current_steps": 31970, "total_steps": 38160, "loss": 0.0052, "lr": 3.902935404153202e-06, "epoch": 16.755765199161427, "percentage": 83.78, "elapsed_time": "2:02:29", "remaining_time": "0:23:43", "throughput": 2842.84, "total_tokens": 20893440} {"current_steps": 31975, "total_steps": 38160, "loss": 0.016, "lr": 3.896802798146809e-06, "epoch": 16.7583857442348, "percentage": 83.79, "elapsed_time": "2:02:30", "remaining_time": "0:23:41", "throughput": 2842.95, "total_tokens": 20897792} {"current_steps": 31980, "total_steps": 38160, "loss": 0.0141, "lr": 3.890674606688524e-06, "epoch": 16.761006289308177, "percentage": 83.81, "elapsed_time": "2:02:31", "remaining_time": "0:23:40", "throughput": 2842.82, "total_tokens": 20899936} {"current_steps": 31985, "total_steps": 38160, "loss": 0.0101, "lr": 3.88455083106028e-06, "epoch": 16.76362683438155, "percentage": 83.82, "elapsed_time": "2:02:33", "remaining_time": "0:23:39", "throughput": 2842.94, "total_tokens": 20905728} {"current_steps": 31990, "total_steps": 38160, "loss": 0.0458, "lr": 3.878431472543098e-06, "epoch": 16.766247379454928, "percentage": 83.83, "elapsed_time": "2:02:34", "remaining_time": "0:23:38", "throughput": 2843.01, "total_tokens": 20909376} {"current_steps": 31995, "total_steps": 38160, "loss": 0.0115, "lr": 3.872316532417086e-06, "epoch": 16.7688679245283, "percentage": 83.84, "elapsed_time": "2:02:35", "remaining_time": "0:23:37", "throughput": 2843.04, "total_tokens": 20913088} {"current_steps": 32000, "total_steps": 38160, "loss": 0.0092, "lr": 3.866206011961418e-06, "epoch": 16.771488469601678, "percentage": 83.86, "elapsed_time": "2:02:36", "remaining_time": "0:23:36", "throughput": 2842.98, "total_tokens": 20915808} {"current_steps": 32005, "total_steps": 38160, "loss": 0.0214, "lr": 3.860099912454346e-06, "epoch": 16.77410901467505, "percentage": 83.87, "elapsed_time": "2:02:38", "remaining_time": "0:23:35", "throughput": 2843.06, "total_tokens": 20920032} {"current_steps": 32010, "total_steps": 38160, "loss": 0.0044, "lr": 3.853998235173201e-06, "epoch": 16.77672955974843, "percentage": 83.88, "elapsed_time": "2:02:39", "remaining_time": "0:23:33", "throughput": 2843.02, "total_tokens": 20922912} {"current_steps": 32015, "total_steps": 38160, "loss": 0.0146, "lr": 3.847900981394379e-06, "epoch": 16.779350104821802, "percentage": 83.9, "elapsed_time": "2:02:40", "remaining_time": "0:23:32", "throughput": 2843.04, "total_tokens": 20926176} {"current_steps": 32020, "total_steps": 38160, "loss": 0.0038, "lr": 3.841808152393348e-06, "epoch": 16.78197064989518, "percentage": 83.91, "elapsed_time": "2:02:41", "remaining_time": "0:23:31", "throughput": 2843.0, "total_tokens": 20928896} {"current_steps": 32025, "total_steps": 38160, "loss": 0.0056, "lr": 3.835719749444666e-06, "epoch": 16.784591194968552, "percentage": 83.92, "elapsed_time": "2:02:42", "remaining_time": "0:23:30", "throughput": 2843.02, "total_tokens": 20931968} {"current_steps": 32030, "total_steps": 38160, "loss": 0.0071, "lr": 3.8296357738219606e-06, "epoch": 16.78721174004193, "percentage": 83.94, "elapsed_time": "2:02:43", "remaining_time": "0:23:29", "throughput": 2843.04, "total_tokens": 20935168} {"current_steps": 32035, "total_steps": 38160, "loss": 0.0036, "lr": 3.823556226797931e-06, "epoch": 16.789832285115303, "percentage": 83.95, "elapsed_time": "2:02:44", "remaining_time": "0:23:28", "throughput": 2842.99, "total_tokens": 20937856} {"current_steps": 32040, "total_steps": 38160, "loss": 0.0115, "lr": 3.817481109644344e-06, "epoch": 16.79245283018868, "percentage": 83.96, "elapsed_time": "2:02:45", "remaining_time": "0:23:26", "throughput": 2843.0, "total_tokens": 20941120} {"current_steps": 32045, "total_steps": 38160, "loss": 0.0094, "lr": 3.811410423632042e-06, "epoch": 16.795073375262053, "percentage": 83.98, "elapsed_time": "2:02:46", "remaining_time": "0:23:25", "throughput": 2843.01, "total_tokens": 20944416} {"current_steps": 32050, "total_steps": 38160, "loss": 0.0159, "lr": 3.8053441700309473e-06, "epoch": 16.79769392033543, "percentage": 83.99, "elapsed_time": "2:02:48", "remaining_time": "0:23:24", "throughput": 2843.1, "total_tokens": 20948384} {"current_steps": 32055, "total_steps": 38160, "loss": 0.0232, "lr": 3.7992823501100507e-06, "epoch": 16.800314465408803, "percentage": 84.0, "elapsed_time": "2:02:49", "remaining_time": "0:23:23", "throughput": 2843.06, "total_tokens": 20951328} {"current_steps": 32060, "total_steps": 38160, "loss": 0.0131, "lr": 3.7932249651374207e-06, "epoch": 16.80293501048218, "percentage": 84.01, "elapsed_time": "2:02:50", "remaining_time": "0:23:22", "throughput": 2843.04, "total_tokens": 20954304} {"current_steps": 32065, "total_steps": 38160, "loss": 0.0038, "lr": 3.787172016380183e-06, "epoch": 16.805555555555557, "percentage": 84.03, "elapsed_time": "2:02:51", "remaining_time": "0:23:21", "throughput": 2843.07, "total_tokens": 20957600} {"current_steps": 32070, "total_steps": 38160, "loss": 0.0066, "lr": 3.7811235051045558e-06, "epoch": 16.80817610062893, "percentage": 84.04, "elapsed_time": "2:02:52", "remaining_time": "0:23:20", "throughput": 2843.16, "total_tokens": 20961248} {"current_steps": 32075, "total_steps": 38160, "loss": 0.0087, "lr": 3.775079432575809e-06, "epoch": 16.810796645702307, "percentage": 84.05, "elapsed_time": "2:02:53", "remaining_time": "0:23:18", "throughput": 2843.24, "total_tokens": 20964864} {"current_steps": 32080, "total_steps": 38160, "loss": 0.0052, "lr": 3.7690398000582964e-06, "epoch": 16.81341719077568, "percentage": 84.07, "elapsed_time": "2:02:54", "remaining_time": "0:23:17", "throughput": 2843.25, "total_tokens": 20968160} {"current_steps": 32085, "total_steps": 38160, "loss": 0.0038, "lr": 3.763004608815443e-06, "epoch": 16.816037735849058, "percentage": 84.08, "elapsed_time": "2:02:55", "remaining_time": "0:23:16", "throughput": 2843.24, "total_tokens": 20971072} {"current_steps": 32090, "total_steps": 38160, "loss": 0.005, "lr": 3.756973860109747e-06, "epoch": 16.81865828092243, "percentage": 84.09, "elapsed_time": "2:02:56", "remaining_time": "0:23:15", "throughput": 2843.23, "total_tokens": 20974016} {"current_steps": 32095, "total_steps": 38160, "loss": 0.0048, "lr": 3.7509475552027663e-06, "epoch": 16.821278825995808, "percentage": 84.11, "elapsed_time": "2:02:57", "remaining_time": "0:23:14", "throughput": 2843.24, "total_tokens": 20977280} {"current_steps": 32100, "total_steps": 38160, "loss": 0.0142, "lr": 3.744925695355131e-06, "epoch": 16.82389937106918, "percentage": 84.12, "elapsed_time": "2:02:59", "remaining_time": "0:23:13", "throughput": 2843.26, "total_tokens": 20980704} {"current_steps": 32105, "total_steps": 38160, "loss": 0.0771, "lr": 3.7389082818265476e-06, "epoch": 16.82651991614256, "percentage": 84.13, "elapsed_time": "2:03:00", "remaining_time": "0:23:11", "throughput": 2843.21, "total_tokens": 20983552} {"current_steps": 32110, "total_steps": 38160, "loss": 0.0087, "lr": 3.732895315875792e-06, "epoch": 16.829140461215932, "percentage": 84.15, "elapsed_time": "2:03:01", "remaining_time": "0:23:10", "throughput": 2843.17, "total_tokens": 20986464} {"current_steps": 32115, "total_steps": 38160, "loss": 0.0193, "lr": 3.726886798760715e-06, "epoch": 16.83176100628931, "percentage": 84.16, "elapsed_time": "2:03:02", "remaining_time": "0:23:09", "throughput": 2843.22, "total_tokens": 20990112} {"current_steps": 32120, "total_steps": 38160, "loss": 0.0057, "lr": 3.720882731738215e-06, "epoch": 16.834381551362682, "percentage": 84.17, "elapsed_time": "2:03:03", "remaining_time": "0:23:08", "throughput": 2843.22, "total_tokens": 20993184} {"current_steps": 32125, "total_steps": 38160, "loss": 0.0121, "lr": 3.714883116064291e-06, "epoch": 16.83700209643606, "percentage": 84.19, "elapsed_time": "2:03:04", "remaining_time": "0:23:07", "throughput": 2843.19, "total_tokens": 20995936} {"current_steps": 32130, "total_steps": 38160, "loss": 0.0086, "lr": 3.708887952993978e-06, "epoch": 16.839622641509433, "percentage": 84.2, "elapsed_time": "2:03:05", "remaining_time": "0:23:06", "throughput": 2843.19, "total_tokens": 20999008} {"current_steps": 32135, "total_steps": 38160, "loss": 0.0205, "lr": 3.7028972437814057e-06, "epoch": 16.84224318658281, "percentage": 84.21, "elapsed_time": "2:03:06", "remaining_time": "0:23:04", "throughput": 2843.22, "total_tokens": 21002304} {"current_steps": 32140, "total_steps": 38160, "loss": 0.007, "lr": 3.696910989679764e-06, "epoch": 16.844863731656183, "percentage": 84.22, "elapsed_time": "2:03:07", "remaining_time": "0:23:03", "throughput": 2843.21, "total_tokens": 21005344} {"current_steps": 32145, "total_steps": 38160, "loss": 0.0073, "lr": 3.6909291919413003e-06, "epoch": 16.84748427672956, "percentage": 84.24, "elapsed_time": "2:03:09", "remaining_time": "0:23:02", "throughput": 2843.3, "total_tokens": 21009312} {"current_steps": 32150, "total_steps": 38160, "loss": 0.0047, "lr": 3.684951851817342e-06, "epoch": 16.850104821802937, "percentage": 84.25, "elapsed_time": "2:03:10", "remaining_time": "0:23:01", "throughput": 2843.31, "total_tokens": 21012544} {"current_steps": 32155, "total_steps": 38160, "loss": 0.0047, "lr": 3.678978970558286e-06, "epoch": 16.85272536687631, "percentage": 84.26, "elapsed_time": "2:03:11", "remaining_time": "0:23:00", "throughput": 2843.24, "total_tokens": 21015200} {"current_steps": 32160, "total_steps": 38160, "loss": 0.0072, "lr": 3.673010549413583e-06, "epoch": 16.855345911949687, "percentage": 84.28, "elapsed_time": "2:03:12", "remaining_time": "0:22:59", "throughput": 2843.18, "total_tokens": 21017696} {"current_steps": 32165, "total_steps": 38160, "loss": 0.0051, "lr": 3.6670465896317592e-06, "epoch": 16.85796645702306, "percentage": 84.29, "elapsed_time": "2:03:13", "remaining_time": "0:22:58", "throughput": 2843.17, "total_tokens": 21020800} {"current_steps": 32170, "total_steps": 38160, "loss": 0.0121, "lr": 3.661087092460419e-06, "epoch": 16.860587002096437, "percentage": 84.3, "elapsed_time": "2:03:14", "remaining_time": "0:22:56", "throughput": 2843.14, "total_tokens": 21023552} {"current_steps": 32175, "total_steps": 38160, "loss": 0.0071, "lr": 3.655132059146202e-06, "epoch": 16.86320754716981, "percentage": 84.32, "elapsed_time": "2:03:15", "remaining_time": "0:22:55", "throughput": 2843.12, "total_tokens": 21026656} {"current_steps": 32180, "total_steps": 38160, "loss": 0.01, "lr": 3.6491814909348526e-06, "epoch": 16.865828092243188, "percentage": 84.33, "elapsed_time": "2:03:16", "remaining_time": "0:22:54", "throughput": 2843.2, "total_tokens": 21030464} {"current_steps": 32185, "total_steps": 38160, "loss": 0.0112, "lr": 3.6432353890711424e-06, "epoch": 16.86844863731656, "percentage": 84.34, "elapsed_time": "2:03:17", "remaining_time": "0:22:53", "throughput": 2843.18, "total_tokens": 21033472} {"current_steps": 32190, "total_steps": 38160, "loss": 0.008, "lr": 3.6372937547989425e-06, "epoch": 16.871069182389938, "percentage": 84.36, "elapsed_time": "2:03:19", "remaining_time": "0:22:52", "throughput": 2843.16, "total_tokens": 21036512} {"current_steps": 32195, "total_steps": 38160, "loss": 0.0041, "lr": 3.631356589361173e-06, "epoch": 16.87368972746331, "percentage": 84.37, "elapsed_time": "2:03:20", "remaining_time": "0:22:51", "throughput": 2843.19, "total_tokens": 21039936} {"current_steps": 32200, "total_steps": 38160, "loss": 0.0301, "lr": 3.625423893999813e-06, "epoch": 16.87631027253669, "percentage": 84.38, "elapsed_time": "2:03:21", "remaining_time": "0:22:49", "throughput": 2843.22, "total_tokens": 21043360} {"current_steps": 32205, "total_steps": 38160, "loss": 0.0139, "lr": 3.6194956699559217e-06, "epoch": 16.878930817610062, "percentage": 84.39, "elapsed_time": "2:03:22", "remaining_time": "0:22:48", "throughput": 2843.28, "total_tokens": 21046880} {"current_steps": 32210, "total_steps": 38160, "loss": 0.0022, "lr": 3.6135719184696188e-06, "epoch": 16.88155136268344, "percentage": 84.41, "elapsed_time": "2:03:23", "remaining_time": "0:22:47", "throughput": 2843.23, "total_tokens": 21049664} {"current_steps": 32215, "total_steps": 38160, "loss": 0.008, "lr": 3.6076526407800766e-06, "epoch": 16.884171907756812, "percentage": 84.42, "elapsed_time": "2:03:24", "remaining_time": "0:22:46", "throughput": 2843.24, "total_tokens": 21052832} {"current_steps": 32220, "total_steps": 38160, "loss": 0.0094, "lr": 3.601737838125552e-06, "epoch": 16.88679245283019, "percentage": 84.43, "elapsed_time": "2:03:25", "remaining_time": "0:22:45", "throughput": 2843.37, "total_tokens": 21057120} {"current_steps": 32225, "total_steps": 38160, "loss": 0.0277, "lr": 3.595827511743341e-06, "epoch": 16.889412997903563, "percentage": 84.45, "elapsed_time": "2:03:26", "remaining_time": "0:22:44", "throughput": 2843.41, "total_tokens": 21060512} {"current_steps": 32230, "total_steps": 38160, "loss": 0.0041, "lr": 3.5899216628698217e-06, "epoch": 16.89203354297694, "percentage": 84.46, "elapsed_time": "2:03:27", "remaining_time": "0:22:42", "throughput": 2843.29, "total_tokens": 21062720} {"current_steps": 32235, "total_steps": 38160, "loss": 0.0038, "lr": 3.584020292740431e-06, "epoch": 16.894654088050313, "percentage": 84.47, "elapsed_time": "2:03:28", "remaining_time": "0:22:41", "throughput": 2843.24, "total_tokens": 21065504} {"current_steps": 32240, "total_steps": 38160, "loss": 0.0054, "lr": 3.578123402589675e-06, "epoch": 16.89727463312369, "percentage": 84.49, "elapsed_time": "2:03:30", "remaining_time": "0:22:40", "throughput": 2843.26, "total_tokens": 21069472} {"current_steps": 32245, "total_steps": 38160, "loss": 0.0073, "lr": 3.5722309936511044e-06, "epoch": 16.899895178197063, "percentage": 84.5, "elapsed_time": "2:03:31", "remaining_time": "0:22:39", "throughput": 2843.2, "total_tokens": 21072192} {"current_steps": 32250, "total_steps": 38160, "loss": 0.0056, "lr": 3.5663430671573572e-06, "epoch": 16.90251572327044, "percentage": 84.51, "elapsed_time": "2:03:32", "remaining_time": "0:22:38", "throughput": 2843.2, "total_tokens": 21075264} {"current_steps": 32255, "total_steps": 38160, "loss": 0.0069, "lr": 3.5604596243401038e-06, "epoch": 16.905136268343817, "percentage": 84.53, "elapsed_time": "2:03:33", "remaining_time": "0:22:37", "throughput": 2843.26, "total_tokens": 21079008} {"current_steps": 32260, "total_steps": 38160, "loss": 0.0057, "lr": 3.554580666430102e-06, "epoch": 16.90775681341719, "percentage": 84.54, "elapsed_time": "2:03:34", "remaining_time": "0:22:36", "throughput": 2843.22, "total_tokens": 21081888} {"current_steps": 32265, "total_steps": 38160, "loss": 0.0133, "lr": 3.5487061946571614e-06, "epoch": 16.910377358490567, "percentage": 84.55, "elapsed_time": "2:03:35", "remaining_time": "0:22:34", "throughput": 2843.18, "total_tokens": 21084608} {"current_steps": 32270, "total_steps": 38160, "loss": 0.0211, "lr": 3.542836210250161e-06, "epoch": 16.91299790356394, "percentage": 84.56, "elapsed_time": "2:03:36", "remaining_time": "0:22:33", "throughput": 2843.18, "total_tokens": 21087680} {"current_steps": 32275, "total_steps": 38160, "loss": 0.0089, "lr": 3.536970714437032e-06, "epoch": 16.915618448637318, "percentage": 84.58, "elapsed_time": "2:03:38", "remaining_time": "0:22:32", "throughput": 2843.21, "total_tokens": 21090944} {"current_steps": 32280, "total_steps": 38160, "loss": 0.0035, "lr": 3.5311097084447575e-06, "epoch": 16.91823899371069, "percentage": 84.59, "elapsed_time": "2:03:39", "remaining_time": "0:22:31", "throughput": 2843.25, "total_tokens": 21094272} {"current_steps": 32285, "total_steps": 38160, "loss": 0.0079, "lr": 3.5252531934994033e-06, "epoch": 16.920859538784068, "percentage": 84.6, "elapsed_time": "2:03:40", "remaining_time": "0:22:30", "throughput": 2843.28, "total_tokens": 21097952} {"current_steps": 32290, "total_steps": 38160, "loss": 0.0146, "lr": 3.5194011708260866e-06, "epoch": 16.92348008385744, "percentage": 84.62, "elapsed_time": "2:03:41", "remaining_time": "0:22:29", "throughput": 2843.34, "total_tokens": 21101408} {"current_steps": 32295, "total_steps": 38160, "loss": 0.0148, "lr": 3.513553641648984e-06, "epoch": 16.92610062893082, "percentage": 84.63, "elapsed_time": "2:03:42", "remaining_time": "0:22:28", "throughput": 2843.44, "total_tokens": 21105888} {"current_steps": 32300, "total_steps": 38160, "loss": 0.0066, "lr": 3.5077106071913307e-06, "epoch": 16.928721174004192, "percentage": 84.64, "elapsed_time": "2:03:43", "remaining_time": "0:22:26", "throughput": 2843.43, "total_tokens": 21108992} {"current_steps": 32305, "total_steps": 38160, "loss": 0.0027, "lr": 3.5018720686754133e-06, "epoch": 16.93134171907757, "percentage": 84.66, "elapsed_time": "2:03:44", "remaining_time": "0:22:25", "throughput": 2843.37, "total_tokens": 21111648} {"current_steps": 32310, "total_steps": 38160, "loss": 0.0169, "lr": 3.4960380273225985e-06, "epoch": 16.933962264150942, "percentage": 84.67, "elapsed_time": "2:03:46", "remaining_time": "0:22:24", "throughput": 2843.46, "total_tokens": 21115872} {"current_steps": 32315, "total_steps": 38160, "loss": 0.008, "lr": 3.490208484353297e-06, "epoch": 16.93658280922432, "percentage": 84.68, "elapsed_time": "2:03:47", "remaining_time": "0:22:23", "throughput": 2843.46, "total_tokens": 21118880} {"current_steps": 32320, "total_steps": 38160, "loss": 0.0053, "lr": 3.4843834409869824e-06, "epoch": 16.939203354297693, "percentage": 84.7, "elapsed_time": "2:03:48", "remaining_time": "0:22:22", "throughput": 2843.42, "total_tokens": 21121792} {"current_steps": 32325, "total_steps": 38160, "loss": 0.194, "lr": 3.4785628984421977e-06, "epoch": 16.94182389937107, "percentage": 84.71, "elapsed_time": "2:03:49", "remaining_time": "0:22:21", "throughput": 2843.43, "total_tokens": 21125024} {"current_steps": 32330, "total_steps": 38160, "loss": 0.0195, "lr": 3.4727468579365235e-06, "epoch": 16.944444444444443, "percentage": 84.72, "elapsed_time": "2:03:50", "remaining_time": "0:22:19", "throughput": 2843.41, "total_tokens": 21128000} {"current_steps": 32335, "total_steps": 38160, "loss": 0.0451, "lr": 3.466935320686604e-06, "epoch": 16.94706498951782, "percentage": 84.74, "elapsed_time": "2:03:51", "remaining_time": "0:22:18", "throughput": 2843.48, "total_tokens": 21131808} {"current_steps": 32340, "total_steps": 38160, "loss": 0.014, "lr": 3.4611282879081553e-06, "epoch": 16.949685534591197, "percentage": 84.75, "elapsed_time": "2:03:52", "remaining_time": "0:22:17", "throughput": 2843.52, "total_tokens": 21135488} {"current_steps": 32345, "total_steps": 38160, "loss": 0.0166, "lr": 3.455325760815939e-06, "epoch": 16.95230607966457, "percentage": 84.76, "elapsed_time": "2:03:53", "remaining_time": "0:22:16", "throughput": 2843.54, "total_tokens": 21138656} {"current_steps": 32350, "total_steps": 38160, "loss": 0.0047, "lr": 3.4495277406237843e-06, "epoch": 16.954926624737947, "percentage": 84.77, "elapsed_time": "2:03:54", "remaining_time": "0:22:15", "throughput": 2843.48, "total_tokens": 21141184} {"current_steps": 32355, "total_steps": 38160, "loss": 0.0068, "lr": 3.443734228544565e-06, "epoch": 16.95754716981132, "percentage": 84.79, "elapsed_time": "2:03:56", "remaining_time": "0:22:14", "throughput": 2843.47, "total_tokens": 21144288} {"current_steps": 32360, "total_steps": 38160, "loss": 0.0086, "lr": 3.437945225790215e-06, "epoch": 16.960167714884697, "percentage": 84.8, "elapsed_time": "2:03:57", "remaining_time": "0:22:12", "throughput": 2843.4, "total_tokens": 21146912} {"current_steps": 32365, "total_steps": 38160, "loss": 0.0119, "lr": 3.432160733571729e-06, "epoch": 16.96278825995807, "percentage": 84.81, "elapsed_time": "2:03:58", "remaining_time": "0:22:11", "throughput": 2843.43, "total_tokens": 21150304} {"current_steps": 32370, "total_steps": 38160, "loss": 0.0073, "lr": 3.4263807530991595e-06, "epoch": 16.965408805031448, "percentage": 84.83, "elapsed_time": "2:03:59", "remaining_time": "0:22:10", "throughput": 2843.45, "total_tokens": 21153760} {"current_steps": 32375, "total_steps": 38160, "loss": 0.0063, "lr": 3.4206052855816155e-06, "epoch": 16.96802935010482, "percentage": 84.84, "elapsed_time": "2:04:00", "remaining_time": "0:22:09", "throughput": 2843.45, "total_tokens": 21156960} {"current_steps": 32380, "total_steps": 38160, "loss": 0.0115, "lr": 3.4148343322272567e-06, "epoch": 16.970649895178198, "percentage": 84.85, "elapsed_time": "2:04:01", "remaining_time": "0:22:08", "throughput": 2843.42, "total_tokens": 21159744} {"current_steps": 32385, "total_steps": 38160, "loss": 0.0086, "lr": 3.4090678942432923e-06, "epoch": 16.97327044025157, "percentage": 84.87, "elapsed_time": "2:04:03", "remaining_time": "0:22:07", "throughput": 2843.65, "total_tokens": 21166304} {"current_steps": 32390, "total_steps": 38160, "loss": 0.0036, "lr": 3.4033059728360018e-06, "epoch": 16.97589098532495, "percentage": 84.88, "elapsed_time": "2:04:04", "remaining_time": "0:22:06", "throughput": 2843.65, "total_tokens": 21169440} {"current_steps": 32395, "total_steps": 38160, "loss": 0.0069, "lr": 3.397548569210715e-06, "epoch": 16.978511530398322, "percentage": 84.89, "elapsed_time": "2:04:05", "remaining_time": "0:22:05", "throughput": 2843.7, "total_tokens": 21173696} {"current_steps": 32400, "total_steps": 38160, "loss": 0.0095, "lr": 3.3917956845718136e-06, "epoch": 16.9811320754717, "percentage": 84.91, "elapsed_time": "2:04:06", "remaining_time": "0:22:03", "throughput": 2843.67, "total_tokens": 21176672} {"current_steps": 32405, "total_steps": 38160, "loss": 0.0051, "lr": 3.38604732012274e-06, "epoch": 16.983752620545072, "percentage": 84.92, "elapsed_time": "2:04:08", "remaining_time": "0:22:02", "throughput": 2843.71, "total_tokens": 21180064} {"current_steps": 32410, "total_steps": 38160, "loss": 0.0692, "lr": 3.3803034770659825e-06, "epoch": 16.98637316561845, "percentage": 84.93, "elapsed_time": "2:04:09", "remaining_time": "0:22:01", "throughput": 2843.77, "total_tokens": 21183680} {"current_steps": 32415, "total_steps": 38160, "loss": 0.0059, "lr": 3.3745641566030826e-06, "epoch": 16.988993710691823, "percentage": 84.94, "elapsed_time": "2:04:10", "remaining_time": "0:22:00", "throughput": 2843.83, "total_tokens": 21187072} {"current_steps": 32420, "total_steps": 38160, "loss": 0.0336, "lr": 3.3688293599346442e-06, "epoch": 16.9916142557652, "percentage": 84.96, "elapsed_time": "2:04:11", "remaining_time": "0:21:59", "throughput": 2843.96, "total_tokens": 21191776} {"current_steps": 32425, "total_steps": 38160, "loss": 0.0964, "lr": 3.3630990882603213e-06, "epoch": 16.994234800838573, "percentage": 84.97, "elapsed_time": "2:04:12", "remaining_time": "0:21:58", "throughput": 2844.1, "total_tokens": 21196288} {"current_steps": 32430, "total_steps": 38160, "loss": 0.009, "lr": 3.35737334277883e-06, "epoch": 16.99685534591195, "percentage": 84.98, "elapsed_time": "2:04:14", "remaining_time": "0:21:57", "throughput": 2844.2, "total_tokens": 21200992} {"current_steps": 32435, "total_steps": 38160, "loss": 0.0083, "lr": 3.351652124687918e-06, "epoch": 16.999475890985323, "percentage": 85.0, "elapsed_time": "2:04:15", "remaining_time": "0:21:55", "throughput": 2844.23, "total_tokens": 21204320} {"current_steps": 32436, "total_steps": 38160, "eval_loss": 1.514715552330017, "epoch": 17.0, "percentage": 85.0, "elapsed_time": "2:04:27", "remaining_time": "0:21:57", "throughput": 2839.59, "total_tokens": 21204416} {"current_steps": 32440, "total_steps": 38160, "loss": 0.0307, "lr": 3.345935435184408e-06, "epoch": 17.0020964360587, "percentage": 85.01, "elapsed_time": "2:04:31", "remaining_time": "0:21:57", "throughput": 2838.32, "total_tokens": 21206752} {"current_steps": 32445, "total_steps": 38160, "loss": 0.0089, "lr": 3.3402232754641576e-06, "epoch": 17.004716981132077, "percentage": 85.02, "elapsed_time": "2:04:32", "remaining_time": "0:21:56", "throughput": 2838.41, "total_tokens": 21210656} {"current_steps": 32450, "total_steps": 38160, "loss": 0.0195, "lr": 3.334515646722089e-06, "epoch": 17.00733752620545, "percentage": 85.04, "elapsed_time": "2:04:33", "remaining_time": "0:21:55", "throughput": 2838.34, "total_tokens": 21213216} {"current_steps": 32455, "total_steps": 38160, "loss": 0.0028, "lr": 3.32881255015218e-06, "epoch": 17.009958071278827, "percentage": 85.05, "elapsed_time": "2:04:34", "remaining_time": "0:21:53", "throughput": 2838.35, "total_tokens": 21216416} {"current_steps": 32460, "total_steps": 38160, "loss": 0.0023, "lr": 3.3231139869474433e-06, "epoch": 17.0125786163522, "percentage": 85.06, "elapsed_time": "2:04:36", "remaining_time": "0:21:52", "throughput": 2838.39, "total_tokens": 21220352} {"current_steps": 32465, "total_steps": 38160, "loss": 0.0021, "lr": 3.317419958299961e-06, "epoch": 17.015199161425578, "percentage": 85.08, "elapsed_time": "2:04:37", "remaining_time": "0:21:51", "throughput": 2838.37, "total_tokens": 21223296} {"current_steps": 32470, "total_steps": 38160, "loss": 0.0034, "lr": 3.31173046540085e-06, "epoch": 17.01781970649895, "percentage": 85.09, "elapsed_time": "2:04:38", "remaining_time": "0:21:50", "throughput": 2838.31, "total_tokens": 21225824} {"current_steps": 32475, "total_steps": 38160, "loss": 0.0043, "lr": 3.306045509440295e-06, "epoch": 17.020440251572328, "percentage": 85.1, "elapsed_time": "2:04:39", "remaining_time": "0:21:49", "throughput": 2838.27, "total_tokens": 21228704} {"current_steps": 32480, "total_steps": 38160, "loss": 0.0022, "lr": 3.300365091607521e-06, "epoch": 17.0230607966457, "percentage": 85.12, "elapsed_time": "2:04:40", "remaining_time": "0:21:48", "throughput": 2838.26, "total_tokens": 21231648} {"current_steps": 32485, "total_steps": 38160, "loss": 0.0165, "lr": 3.2946892130908127e-06, "epoch": 17.02568134171908, "percentage": 85.13, "elapsed_time": "2:04:41", "remaining_time": "0:21:47", "throughput": 2838.16, "total_tokens": 21234048} {"current_steps": 32490, "total_steps": 38160, "loss": 0.0063, "lr": 3.289017875077488e-06, "epoch": 17.028301886792452, "percentage": 85.14, "elapsed_time": "2:04:42", "remaining_time": "0:21:45", "throughput": 2838.22, "total_tokens": 21237568} {"current_steps": 32495, "total_steps": 38160, "loss": 0.0183, "lr": 3.283351078753938e-06, "epoch": 17.03092243186583, "percentage": 85.15, "elapsed_time": "2:04:43", "remaining_time": "0:21:44", "throughput": 2838.23, "total_tokens": 21240672} {"current_steps": 32500, "total_steps": 38160, "loss": 0.0074, "lr": 3.2776888253055777e-06, "epoch": 17.033542976939202, "percentage": 85.17, "elapsed_time": "2:04:44", "remaining_time": "0:21:43", "throughput": 2838.13, "total_tokens": 21243200} {"current_steps": 32505, "total_steps": 38160, "loss": 0.0049, "lr": 3.272031115916896e-06, "epoch": 17.03616352201258, "percentage": 85.18, "elapsed_time": "2:04:46", "remaining_time": "0:21:42", "throughput": 2838.26, "total_tokens": 21247936} {"current_steps": 32510, "total_steps": 38160, "loss": 0.0036, "lr": 3.2663779517714238e-06, "epoch": 17.038784067085953, "percentage": 85.19, "elapsed_time": "2:04:47", "remaining_time": "0:21:41", "throughput": 2838.19, "total_tokens": 21250560} {"current_steps": 32515, "total_steps": 38160, "loss": 0.0048, "lr": 3.260729334051729e-06, "epoch": 17.04140461215933, "percentage": 85.21, "elapsed_time": "2:04:48", "remaining_time": "0:21:40", "throughput": 2838.25, "total_tokens": 21254432} {"current_steps": 32520, "total_steps": 38160, "loss": 0.0052, "lr": 3.2550852639394446e-06, "epoch": 17.044025157232703, "percentage": 85.22, "elapsed_time": "2:04:49", "remaining_time": "0:21:38", "throughput": 2838.25, "total_tokens": 21257568} {"current_steps": 32525, "total_steps": 38160, "loss": 0.0092, "lr": 3.2494457426152452e-06, "epoch": 17.04664570230608, "percentage": 85.23, "elapsed_time": "2:04:50", "remaining_time": "0:21:37", "throughput": 2838.28, "total_tokens": 21260992} {"current_steps": 32530, "total_steps": 38160, "loss": 0.0042, "lr": 3.243810771258851e-06, "epoch": 17.049266247379453, "percentage": 85.25, "elapsed_time": "2:04:51", "remaining_time": "0:21:36", "throughput": 2838.19, "total_tokens": 21263328} {"current_steps": 32535, "total_steps": 38160, "loss": 0.0087, "lr": 3.2381803510490387e-06, "epoch": 17.05188679245283, "percentage": 85.26, "elapsed_time": "2:04:52", "remaining_time": "0:21:35", "throughput": 2838.23, "total_tokens": 21266752} {"current_steps": 32540, "total_steps": 38160, "loss": 0.0049, "lr": 3.2325544831636217e-06, "epoch": 17.054507337526207, "percentage": 85.27, "elapsed_time": "2:04:54", "remaining_time": "0:21:34", "throughput": 2838.21, "total_tokens": 21269728} {"current_steps": 32545, "total_steps": 38160, "loss": 0.0078, "lr": 3.22693316877947e-06, "epoch": 17.05712788259958, "percentage": 85.29, "elapsed_time": "2:04:55", "remaining_time": "0:21:33", "throughput": 2838.21, "total_tokens": 21272864} {"current_steps": 32550, "total_steps": 38160, "loss": 0.0026, "lr": 3.2213164090725057e-06, "epoch": 17.059748427672957, "percentage": 85.3, "elapsed_time": "2:04:56", "remaining_time": "0:21:31", "throughput": 2838.27, "total_tokens": 21276320} {"current_steps": 32555, "total_steps": 38160, "loss": 0.0028, "lr": 3.2157042052176763e-06, "epoch": 17.06236897274633, "percentage": 85.31, "elapsed_time": "2:04:57", "remaining_time": "0:21:30", "throughput": 2838.27, "total_tokens": 21279360} {"current_steps": 32560, "total_steps": 38160, "loss": 0.0027, "lr": 3.2100965583890003e-06, "epoch": 17.064989517819708, "percentage": 85.32, "elapsed_time": "2:04:58", "remaining_time": "0:21:29", "throughput": 2838.23, "total_tokens": 21282112} {"current_steps": 32565, "total_steps": 38160, "loss": 0.0099, "lr": 3.204493469759537e-06, "epoch": 17.06761006289308, "percentage": 85.34, "elapsed_time": "2:04:59", "remaining_time": "0:21:28", "throughput": 2838.17, "total_tokens": 21284832} {"current_steps": 32570, "total_steps": 38160, "loss": 0.0051, "lr": 3.1988949405013764e-06, "epoch": 17.070230607966458, "percentage": 85.35, "elapsed_time": "2:05:00", "remaining_time": "0:21:27", "throughput": 2838.19, "total_tokens": 21288256} {"current_steps": 32575, "total_steps": 38160, "loss": 0.0032, "lr": 3.193300971785676e-06, "epoch": 17.07285115303983, "percentage": 85.36, "elapsed_time": "2:05:01", "remaining_time": "0:21:26", "throughput": 2838.25, "total_tokens": 21291616} {"current_steps": 32580, "total_steps": 38160, "loss": 0.0061, "lr": 3.1877115647826335e-06, "epoch": 17.07547169811321, "percentage": 85.38, "elapsed_time": "2:05:02", "remaining_time": "0:21:25", "throughput": 2838.25, "total_tokens": 21294720} {"current_steps": 32585, "total_steps": 38160, "loss": 0.0054, "lr": 3.1821267206614797e-06, "epoch": 17.078092243186582, "percentage": 85.39, "elapsed_time": "2:05:03", "remaining_time": "0:21:23", "throughput": 2838.28, "total_tokens": 21298400} {"current_steps": 32590, "total_steps": 38160, "loss": 0.0064, "lr": 3.176546440590508e-06, "epoch": 17.08071278825996, "percentage": 85.4, "elapsed_time": "2:05:05", "remaining_time": "0:21:22", "throughput": 2838.27, "total_tokens": 21301376} {"current_steps": 32595, "total_steps": 38160, "loss": 0.0014, "lr": 3.170970725737041e-06, "epoch": 17.083333333333332, "percentage": 85.42, "elapsed_time": "2:05:06", "remaining_time": "0:21:21", "throughput": 2838.19, "total_tokens": 21303840} {"current_steps": 32600, "total_steps": 38160, "loss": 0.0049, "lr": 3.165399577267461e-06, "epoch": 17.08595387840671, "percentage": 85.43, "elapsed_time": "2:05:07", "remaining_time": "0:21:20", "throughput": 2838.22, "total_tokens": 21307136} {"current_steps": 32605, "total_steps": 38160, "loss": 0.0038, "lr": 3.159832996347184e-06, "epoch": 17.088574423480082, "percentage": 85.44, "elapsed_time": "2:05:08", "remaining_time": "0:21:19", "throughput": 2838.16, "total_tokens": 21309824} {"current_steps": 32610, "total_steps": 38160, "loss": 0.0051, "lr": 3.1542709841406865e-06, "epoch": 17.09119496855346, "percentage": 85.46, "elapsed_time": "2:05:09", "remaining_time": "0:21:18", "throughput": 2838.11, "total_tokens": 21312448} {"current_steps": 32615, "total_steps": 38160, "loss": 0.0037, "lr": 3.148713541811468e-06, "epoch": 17.093815513626833, "percentage": 85.47, "elapsed_time": "2:05:10", "remaining_time": "0:21:16", "throughput": 2838.04, "total_tokens": 21315040} {"current_steps": 32620, "total_steps": 38160, "loss": 0.0056, "lr": 3.1431606705220803e-06, "epoch": 17.09643605870021, "percentage": 85.48, "elapsed_time": "2:05:11", "remaining_time": "0:21:15", "throughput": 2837.98, "total_tokens": 21317696} {"current_steps": 32625, "total_steps": 38160, "loss": 0.0038, "lr": 3.1376123714341234e-06, "epoch": 17.099056603773583, "percentage": 85.5, "elapsed_time": "2:05:12", "remaining_time": "0:21:14", "throughput": 2837.91, "total_tokens": 21320320} {"current_steps": 32630, "total_steps": 38160, "loss": 0.0018, "lr": 3.1320686457082387e-06, "epoch": 17.10167714884696, "percentage": 85.51, "elapsed_time": "2:05:13", "remaining_time": "0:21:13", "throughput": 2837.88, "total_tokens": 21323136} {"current_steps": 32635, "total_steps": 38160, "loss": 0.0071, "lr": 3.126529494504113e-06, "epoch": 17.104297693920337, "percentage": 85.52, "elapsed_time": "2:05:14", "remaining_time": "0:21:12", "throughput": 2837.81, "total_tokens": 21325664} {"current_steps": 32640, "total_steps": 38160, "loss": 0.0078, "lr": 3.1209949189804744e-06, "epoch": 17.10691823899371, "percentage": 85.53, "elapsed_time": "2:05:15", "remaining_time": "0:21:11", "throughput": 2837.77, "total_tokens": 21328352} {"current_steps": 32645, "total_steps": 38160, "loss": 0.0138, "lr": 3.115464920295089e-06, "epoch": 17.109538784067087, "percentage": 85.55, "elapsed_time": "2:05:17", "remaining_time": "0:21:09", "throughput": 2837.9, "total_tokens": 21332704} {"current_steps": 32650, "total_steps": 38160, "loss": 0.0204, "lr": 3.1099394996047666e-06, "epoch": 17.11215932914046, "percentage": 85.56, "elapsed_time": "2:05:18", "remaining_time": "0:21:08", "throughput": 2837.95, "total_tokens": 21336352} {"current_steps": 32655, "total_steps": 38160, "loss": 0.0045, "lr": 3.104418658065367e-06, "epoch": 17.114779874213838, "percentage": 85.57, "elapsed_time": "2:05:19", "remaining_time": "0:21:07", "throughput": 2838.05, "total_tokens": 21340288} {"current_steps": 32660, "total_steps": 38160, "loss": 0.003, "lr": 3.098902396831782e-06, "epoch": 17.11740041928721, "percentage": 85.59, "elapsed_time": "2:05:20", "remaining_time": "0:21:06", "throughput": 2838.12, "total_tokens": 21344128} {"current_steps": 32665, "total_steps": 38160, "loss": 0.0186, "lr": 3.0933907170579646e-06, "epoch": 17.120020964360588, "percentage": 85.6, "elapsed_time": "2:05:21", "remaining_time": "0:21:05", "throughput": 2838.14, "total_tokens": 21347296} {"current_steps": 32670, "total_steps": 38160, "loss": 0.0054, "lr": 3.0878836198968835e-06, "epoch": 17.12264150943396, "percentage": 85.61, "elapsed_time": "2:05:22", "remaining_time": "0:21:04", "throughput": 2838.13, "total_tokens": 21350240} {"current_steps": 32675, "total_steps": 38160, "loss": 0.0043, "lr": 3.0823811065005564e-06, "epoch": 17.12526205450734, "percentage": 85.63, "elapsed_time": "2:05:23", "remaining_time": "0:21:02", "throughput": 2838.04, "total_tokens": 21352704} {"current_steps": 32680, "total_steps": 38160, "loss": 0.0083, "lr": 3.0768831780200542e-06, "epoch": 17.127882599580712, "percentage": 85.64, "elapsed_time": "2:05:24", "remaining_time": "0:21:01", "throughput": 2838.05, "total_tokens": 21355904} {"current_steps": 32685, "total_steps": 38160, "loss": 0.0081, "lr": 3.071389835605476e-06, "epoch": 17.13050314465409, "percentage": 85.65, "elapsed_time": "2:05:25", "remaining_time": "0:21:00", "throughput": 2838.07, "total_tokens": 21359136} {"current_steps": 32690, "total_steps": 38160, "loss": 0.0059, "lr": 3.065901080405978e-06, "epoch": 17.133123689727462, "percentage": 85.67, "elapsed_time": "2:05:27", "remaining_time": "0:20:59", "throughput": 2838.08, "total_tokens": 21362496} {"current_steps": 32695, "total_steps": 38160, "loss": 0.0034, "lr": 3.060416913569733e-06, "epoch": 17.13574423480084, "percentage": 85.68, "elapsed_time": "2:05:28", "remaining_time": "0:20:58", "throughput": 2837.99, "total_tokens": 21364928} {"current_steps": 32700, "total_steps": 38160, "loss": 0.0095, "lr": 3.054937336243968e-06, "epoch": 17.138364779874212, "percentage": 85.69, "elapsed_time": "2:05:29", "remaining_time": "0:20:57", "throughput": 2837.97, "total_tokens": 21367808} {"current_steps": 32705, "total_steps": 38160, "loss": 0.0072, "lr": 3.049462349574947e-06, "epoch": 17.14098532494759, "percentage": 85.7, "elapsed_time": "2:05:30", "remaining_time": "0:20:56", "throughput": 2838.0, "total_tokens": 21371040} {"current_steps": 32710, "total_steps": 38160, "loss": 0.0116, "lr": 3.043991954707981e-06, "epoch": 17.143605870020963, "percentage": 85.72, "elapsed_time": "2:05:31", "remaining_time": "0:20:54", "throughput": 2838.04, "total_tokens": 21374528} {"current_steps": 32715, "total_steps": 38160, "loss": 0.0047, "lr": 3.0385261527874075e-06, "epoch": 17.14622641509434, "percentage": 85.73, "elapsed_time": "2:05:32", "remaining_time": "0:20:53", "throughput": 2837.95, "total_tokens": 21376864} {"current_steps": 32720, "total_steps": 38160, "loss": 0.0051, "lr": 3.0330649449566205e-06, "epoch": 17.148846960167713, "percentage": 85.74, "elapsed_time": "2:05:33", "remaining_time": "0:20:52", "throughput": 2837.91, "total_tokens": 21379840} {"current_steps": 32725, "total_steps": 38160, "loss": 0.023, "lr": 3.027608332358034e-06, "epoch": 17.15146750524109, "percentage": 85.76, "elapsed_time": "2:05:34", "remaining_time": "0:20:51", "throughput": 2837.93, "total_tokens": 21383072} {"current_steps": 32730, "total_steps": 38160, "loss": 0.0074, "lr": 3.022156316133104e-06, "epoch": 17.154088050314467, "percentage": 85.77, "elapsed_time": "2:05:35", "remaining_time": "0:20:50", "throughput": 2837.92, "total_tokens": 21386080} {"current_steps": 32735, "total_steps": 38160, "loss": 0.0063, "lr": 3.016708897422335e-06, "epoch": 17.15670859538784, "percentage": 85.78, "elapsed_time": "2:05:36", "remaining_time": "0:20:49", "throughput": 2837.83, "total_tokens": 21388640} {"current_steps": 32740, "total_steps": 38160, "loss": 0.0047, "lr": 3.0112660773652685e-06, "epoch": 17.159329140461217, "percentage": 85.8, "elapsed_time": "2:05:38", "remaining_time": "0:20:47", "throughput": 2837.81, "total_tokens": 21391552} {"current_steps": 32745, "total_steps": 38160, "loss": 0.0091, "lr": 3.005827857100482e-06, "epoch": 17.16194968553459, "percentage": 85.81, "elapsed_time": "2:05:39", "remaining_time": "0:20:46", "throughput": 2837.86, "total_tokens": 21395040} {"current_steps": 32750, "total_steps": 38160, "loss": 0.0037, "lr": 3.000394237765586e-06, "epoch": 17.164570230607968, "percentage": 85.82, "elapsed_time": "2:05:40", "remaining_time": "0:20:45", "throughput": 2837.92, "total_tokens": 21398688} {"current_steps": 32755, "total_steps": 38160, "loss": 0.0085, "lr": 2.9949652204972254e-06, "epoch": 17.16719077568134, "percentage": 85.84, "elapsed_time": "2:05:41", "remaining_time": "0:20:44", "throughput": 2837.93, "total_tokens": 21402144} {"current_steps": 32760, "total_steps": 38160, "loss": 0.024, "lr": 2.989540806431093e-06, "epoch": 17.169811320754718, "percentage": 85.85, "elapsed_time": "2:05:42", "remaining_time": "0:20:43", "throughput": 2837.81, "total_tokens": 21404352} {"current_steps": 32765, "total_steps": 38160, "loss": 0.0023, "lr": 2.984120996701917e-06, "epoch": 17.17243186582809, "percentage": 85.86, "elapsed_time": "2:05:43", "remaining_time": "0:20:42", "throughput": 2837.86, "total_tokens": 21407808} {"current_steps": 32770, "total_steps": 38160, "loss": 0.0598, "lr": 2.9787057924434618e-06, "epoch": 17.17505241090147, "percentage": 85.88, "elapsed_time": "2:05:44", "remaining_time": "0:20:40", "throughput": 2837.87, "total_tokens": 21410976} {"current_steps": 32775, "total_steps": 38160, "loss": 0.0075, "lr": 2.9732951947885166e-06, "epoch": 17.177672955974842, "percentage": 85.89, "elapsed_time": "2:05:45", "remaining_time": "0:20:39", "throughput": 2837.99, "total_tokens": 21414976} {"current_steps": 32780, "total_steps": 38160, "loss": 0.0035, "lr": 2.967889204868929e-06, "epoch": 17.18029350104822, "percentage": 85.9, "elapsed_time": "2:05:46", "remaining_time": "0:20:38", "throughput": 2838.0, "total_tokens": 21418368} {"current_steps": 32785, "total_steps": 38160, "loss": 0.0029, "lr": 2.96248782381556e-06, "epoch": 17.182914046121592, "percentage": 85.91, "elapsed_time": "2:05:48", "remaining_time": "0:20:37", "throughput": 2838.0, "total_tokens": 21421664} {"current_steps": 32790, "total_steps": 38160, "loss": 0.0308, "lr": 2.957091052758321e-06, "epoch": 17.18553459119497, "percentage": 85.93, "elapsed_time": "2:05:50", "remaining_time": "0:20:36", "throughput": 2838.16, "total_tokens": 21428544} {"current_steps": 32795, "total_steps": 38160, "loss": 0.0031, "lr": 2.9516988928261517e-06, "epoch": 17.188155136268342, "percentage": 85.94, "elapsed_time": "2:05:51", "remaining_time": "0:20:35", "throughput": 2838.14, "total_tokens": 21431520} {"current_steps": 32800, "total_steps": 38160, "loss": 0.0083, "lr": 2.9463113451470403e-06, "epoch": 17.19077568134172, "percentage": 85.95, "elapsed_time": "2:05:52", "remaining_time": "0:20:34", "throughput": 2838.21, "total_tokens": 21435104} {"current_steps": 32805, "total_steps": 38160, "loss": 0.0067, "lr": 2.94092841084799e-06, "epoch": 17.193396226415093, "percentage": 85.97, "elapsed_time": "2:05:53", "remaining_time": "0:20:32", "throughput": 2838.17, "total_tokens": 21437888} {"current_steps": 32810, "total_steps": 38160, "loss": 0.0135, "lr": 2.9355500910550586e-06, "epoch": 17.19601677148847, "percentage": 85.98, "elapsed_time": "2:05:54", "remaining_time": "0:20:31", "throughput": 2838.2, "total_tokens": 21441280} {"current_steps": 32815, "total_steps": 38160, "loss": 0.0029, "lr": 2.9301763868933157e-06, "epoch": 17.198637316561843, "percentage": 85.99, "elapsed_time": "2:05:55", "remaining_time": "0:20:30", "throughput": 2838.26, "total_tokens": 21445472} {"current_steps": 32820, "total_steps": 38160, "loss": 0.0077, "lr": 2.9248072994868896e-06, "epoch": 17.20125786163522, "percentage": 86.01, "elapsed_time": "2:05:56", "remaining_time": "0:20:29", "throughput": 2838.15, "total_tokens": 21447872} {"current_steps": 32825, "total_steps": 38160, "loss": 0.0029, "lr": 2.919442829958932e-06, "epoch": 17.203878406708597, "percentage": 86.02, "elapsed_time": "2:05:58", "remaining_time": "0:20:28", "throughput": 2838.19, "total_tokens": 21451456} {"current_steps": 32830, "total_steps": 38160, "loss": 0.0077, "lr": 2.9140829794316234e-06, "epoch": 17.20649895178197, "percentage": 86.03, "elapsed_time": "2:05:59", "remaining_time": "0:20:27", "throughput": 2838.18, "total_tokens": 21454560} {"current_steps": 32835, "total_steps": 38160, "loss": 0.003, "lr": 2.908727749026191e-06, "epoch": 17.209119496855347, "percentage": 86.05, "elapsed_time": "2:06:00", "remaining_time": "0:20:26", "throughput": 2838.13, "total_tokens": 21457248} {"current_steps": 32840, "total_steps": 38160, "loss": 0.01, "lr": 2.9033771398628756e-06, "epoch": 17.21174004192872, "percentage": 86.06, "elapsed_time": "2:06:01", "remaining_time": "0:20:24", "throughput": 2838.19, "total_tokens": 21461056} {"current_steps": 32845, "total_steps": 38160, "loss": 0.031, "lr": 2.898031153060973e-06, "epoch": 17.214360587002098, "percentage": 86.07, "elapsed_time": "2:06:02", "remaining_time": "0:20:23", "throughput": 2838.37, "total_tokens": 21466176} {"current_steps": 32850, "total_steps": 38160, "loss": 0.0051, "lr": 2.8926897897388033e-06, "epoch": 17.21698113207547, "percentage": 86.08, "elapsed_time": "2:06:03", "remaining_time": "0:20:22", "throughput": 2838.43, "total_tokens": 21469824} {"current_steps": 32855, "total_steps": 38160, "loss": 0.0244, "lr": 2.8873530510137136e-06, "epoch": 17.219601677148848, "percentage": 86.1, "elapsed_time": "2:06:05", "remaining_time": "0:20:21", "throughput": 2838.48, "total_tokens": 21473472} {"current_steps": 32860, "total_steps": 38160, "loss": 0.0026, "lr": 2.8820209380020892e-06, "epoch": 17.22222222222222, "percentage": 86.11, "elapsed_time": "2:06:06", "remaining_time": "0:20:20", "throughput": 2838.48, "total_tokens": 21476640} {"current_steps": 32865, "total_steps": 38160, "loss": 0.0092, "lr": 2.8766934518193566e-06, "epoch": 17.2248427672956, "percentage": 86.12, "elapsed_time": "2:06:07", "remaining_time": "0:20:19", "throughput": 2838.47, "total_tokens": 21479712} {"current_steps": 32870, "total_steps": 38160, "loss": 0.0038, "lr": 2.87137059357995e-06, "epoch": 17.22746331236897, "percentage": 86.14, "elapsed_time": "2:06:08", "remaining_time": "0:20:18", "throughput": 2838.51, "total_tokens": 21483104} {"current_steps": 32875, "total_steps": 38160, "loss": 0.0075, "lr": 2.8660523643973618e-06, "epoch": 17.23008385744235, "percentage": 86.15, "elapsed_time": "2:06:09", "remaining_time": "0:20:16", "throughput": 2838.49, "total_tokens": 21486080} {"current_steps": 32880, "total_steps": 38160, "loss": 0.0054, "lr": 2.860738765384105e-06, "epoch": 17.232704402515722, "percentage": 86.16, "elapsed_time": "2:06:10", "remaining_time": "0:20:15", "throughput": 2838.57, "total_tokens": 21489792} {"current_steps": 32885, "total_steps": 38160, "loss": 0.0098, "lr": 2.8554297976517154e-06, "epoch": 17.2353249475891, "percentage": 86.18, "elapsed_time": "2:06:11", "remaining_time": "0:20:14", "throughput": 2838.56, "total_tokens": 21492704} {"current_steps": 32890, "total_steps": 38160, "loss": 0.0054, "lr": 2.8501254623107707e-06, "epoch": 17.237945492662472, "percentage": 86.19, "elapsed_time": "2:06:12", "remaining_time": "0:20:13", "throughput": 2838.65, "total_tokens": 21496992} {"current_steps": 32895, "total_steps": 38160, "loss": 0.0047, "lr": 2.84482576047089e-06, "epoch": 17.24056603773585, "percentage": 86.2, "elapsed_time": "2:06:14", "remaining_time": "0:20:12", "throughput": 2838.67, "total_tokens": 21500320} {"current_steps": 32900, "total_steps": 38160, "loss": 0.0134, "lr": 2.839530693240694e-06, "epoch": 17.243186582809223, "percentage": 86.22, "elapsed_time": "2:06:15", "remaining_time": "0:20:11", "throughput": 2838.7, "total_tokens": 21503584} {"current_steps": 32905, "total_steps": 38160, "loss": 0.0061, "lr": 2.8342402617278606e-06, "epoch": 17.2458071278826, "percentage": 86.23, "elapsed_time": "2:06:16", "remaining_time": "0:20:09", "throughput": 2838.64, "total_tokens": 21506240} {"current_steps": 32910, "total_steps": 38160, "loss": 0.0052, "lr": 2.82895446703908e-06, "epoch": 17.248427672955973, "percentage": 86.24, "elapsed_time": "2:06:17", "remaining_time": "0:20:08", "throughput": 2838.73, "total_tokens": 21510208} {"current_steps": 32915, "total_steps": 38160, "loss": 0.0041, "lr": 2.823673310280084e-06, "epoch": 17.25104821802935, "percentage": 86.26, "elapsed_time": "2:06:18", "remaining_time": "0:20:07", "throughput": 2838.72, "total_tokens": 21513344} {"current_steps": 32920, "total_steps": 38160, "loss": 0.0056, "lr": 2.8183967925556305e-06, "epoch": 17.253668763102727, "percentage": 86.27, "elapsed_time": "2:06:19", "remaining_time": "0:20:06", "throughput": 2838.67, "total_tokens": 21515968} {"current_steps": 32925, "total_steps": 38160, "loss": 0.0041, "lr": 2.8131249149695115e-06, "epoch": 17.2562893081761, "percentage": 86.28, "elapsed_time": "2:06:20", "remaining_time": "0:20:05", "throughput": 2838.69, "total_tokens": 21519200} {"current_steps": 32930, "total_steps": 38160, "loss": 0.0179, "lr": 2.8078576786245397e-06, "epoch": 17.258909853249477, "percentage": 86.29, "elapsed_time": "2:06:21", "remaining_time": "0:20:04", "throughput": 2838.69, "total_tokens": 21522368} {"current_steps": 32935, "total_steps": 38160, "loss": 0.0029, "lr": 2.8025950846225557e-06, "epoch": 17.26153039832285, "percentage": 86.31, "elapsed_time": "2:06:22", "remaining_time": "0:20:02", "throughput": 2838.68, "total_tokens": 21525280} {"current_steps": 32940, "total_steps": 38160, "loss": 0.0039, "lr": 2.7973371340644373e-06, "epoch": 17.264150943396228, "percentage": 86.32, "elapsed_time": "2:06:23", "remaining_time": "0:20:01", "throughput": 2838.73, "total_tokens": 21528736} {"current_steps": 32945, "total_steps": 38160, "loss": 0.0467, "lr": 2.7920838280500907e-06, "epoch": 17.2667714884696, "percentage": 86.33, "elapsed_time": "2:06:24", "remaining_time": "0:20:00", "throughput": 2838.75, "total_tokens": 21531904} {"current_steps": 32950, "total_steps": 38160, "loss": 0.0055, "lr": 2.7868351676784504e-06, "epoch": 17.269392033542978, "percentage": 86.35, "elapsed_time": "2:06:26", "remaining_time": "0:19:59", "throughput": 2838.71, "total_tokens": 21534592} {"current_steps": 32955, "total_steps": 38160, "loss": 0.0168, "lr": 2.7815911540474665e-06, "epoch": 17.27201257861635, "percentage": 86.36, "elapsed_time": "2:06:27", "remaining_time": "0:19:58", "throughput": 2838.84, "total_tokens": 21538880} {"current_steps": 32960, "total_steps": 38160, "loss": 0.0083, "lr": 2.7763517882541364e-06, "epoch": 17.27463312368973, "percentage": 86.37, "elapsed_time": "2:06:28", "remaining_time": "0:19:57", "throughput": 2838.93, "total_tokens": 21542688} {"current_steps": 32965, "total_steps": 38160, "loss": 0.0026, "lr": 2.771117071394466e-06, "epoch": 17.2772536687631, "percentage": 86.39, "elapsed_time": "2:06:29", "remaining_time": "0:19:56", "throughput": 2838.93, "total_tokens": 21545760} {"current_steps": 32970, "total_steps": 38160, "loss": 0.0133, "lr": 2.7658870045635055e-06, "epoch": 17.27987421383648, "percentage": 86.4, "elapsed_time": "2:06:30", "remaining_time": "0:19:54", "throughput": 2838.93, "total_tokens": 21548736} {"current_steps": 32975, "total_steps": 38160, "loss": 0.0192, "lr": 2.7606615888553234e-06, "epoch": 17.282494758909852, "percentage": 86.41, "elapsed_time": "2:06:31", "remaining_time": "0:19:53", "throughput": 2838.91, "total_tokens": 21551936} {"current_steps": 32980, "total_steps": 38160, "loss": 0.0147, "lr": 2.755440825363023e-06, "epoch": 17.28511530398323, "percentage": 86.43, "elapsed_time": "2:06:32", "remaining_time": "0:19:52", "throughput": 2838.93, "total_tokens": 21555296} {"current_steps": 32985, "total_steps": 38160, "loss": 0.0036, "lr": 2.75022471517872e-06, "epoch": 17.287735849056602, "percentage": 86.44, "elapsed_time": "2:06:33", "remaining_time": "0:19:51", "throughput": 2838.88, "total_tokens": 21558144} {"current_steps": 32990, "total_steps": 38160, "loss": 0.0166, "lr": 2.745013259393564e-06, "epoch": 17.29035639412998, "percentage": 86.45, "elapsed_time": "2:06:35", "remaining_time": "0:19:50", "throughput": 2838.95, "total_tokens": 21562048} {"current_steps": 32995, "total_steps": 38160, "loss": 0.0067, "lr": 2.739806459097735e-06, "epoch": 17.292976939203353, "percentage": 86.46, "elapsed_time": "2:06:36", "remaining_time": "0:19:49", "throughput": 2838.96, "total_tokens": 21565312} {"current_steps": 33000, "total_steps": 38160, "loss": 0.0074, "lr": 2.7346043153804403e-06, "epoch": 17.29559748427673, "percentage": 86.48, "elapsed_time": "2:06:37", "remaining_time": "0:19:47", "throughput": 2839.03, "total_tokens": 21568960} {"current_steps": 33005, "total_steps": 38160, "loss": 0.0022, "lr": 2.729406829329903e-06, "epoch": 17.298218029350103, "percentage": 86.49, "elapsed_time": "2:06:38", "remaining_time": "0:19:46", "throughput": 2839.03, "total_tokens": 21572064} {"current_steps": 33010, "total_steps": 38160, "loss": 0.0051, "lr": 2.72421400203339e-06, "epoch": 17.30083857442348, "percentage": 86.5, "elapsed_time": "2:06:39", "remaining_time": "0:19:45", "throughput": 2839.06, "total_tokens": 21575328} {"current_steps": 33015, "total_steps": 38160, "loss": 0.004, "lr": 2.719025834577163e-06, "epoch": 17.303459119496857, "percentage": 86.52, "elapsed_time": "2:06:40", "remaining_time": "0:19:44", "throughput": 2839.1, "total_tokens": 21578912} {"current_steps": 33020, "total_steps": 38160, "loss": 0.005, "lr": 2.713842328046537e-06, "epoch": 17.30607966457023, "percentage": 86.53, "elapsed_time": "2:06:41", "remaining_time": "0:19:43", "throughput": 2839.18, "total_tokens": 21582560} {"current_steps": 33025, "total_steps": 38160, "loss": 0.0041, "lr": 2.7086634835258416e-06, "epoch": 17.308700209643607, "percentage": 86.54, "elapsed_time": "2:06:42", "remaining_time": "0:19:42", "throughput": 2839.27, "total_tokens": 21586912} {"current_steps": 33030, "total_steps": 38160, "loss": 0.0056, "lr": 2.7034893020984333e-06, "epoch": 17.31132075471698, "percentage": 86.56, "elapsed_time": "2:06:44", "remaining_time": "0:19:41", "throughput": 2839.27, "total_tokens": 21589920} {"current_steps": 33035, "total_steps": 38160, "loss": 0.0058, "lr": 2.6983197848466952e-06, "epoch": 17.313941299790358, "percentage": 86.57, "elapsed_time": "2:06:45", "remaining_time": "0:19:39", "throughput": 2839.2, "total_tokens": 21592416} {"current_steps": 33040, "total_steps": 38160, "loss": 0.0253, "lr": 2.6931549328520265e-06, "epoch": 17.31656184486373, "percentage": 86.58, "elapsed_time": "2:06:46", "remaining_time": "0:19:38", "throughput": 2839.31, "total_tokens": 21596448} {"current_steps": 33045, "total_steps": 38160, "loss": 0.0108, "lr": 2.6879947471948523e-06, "epoch": 17.319182389937108, "percentage": 86.6, "elapsed_time": "2:06:47", "remaining_time": "0:19:37", "throughput": 2839.34, "total_tokens": 21599968} {"current_steps": 33050, "total_steps": 38160, "loss": 0.0022, "lr": 2.6828392289546285e-06, "epoch": 17.32180293501048, "percentage": 86.61, "elapsed_time": "2:06:48", "remaining_time": "0:19:36", "throughput": 2839.35, "total_tokens": 21603168} {"current_steps": 33055, "total_steps": 38160, "loss": 0.0158, "lr": 2.677688379209828e-06, "epoch": 17.32442348008386, "percentage": 86.62, "elapsed_time": "2:06:49", "remaining_time": "0:19:35", "throughput": 2839.36, "total_tokens": 21606336} {"current_steps": 33060, "total_steps": 38160, "loss": 0.007, "lr": 2.6725421990379586e-06, "epoch": 17.32704402515723, "percentage": 86.64, "elapsed_time": "2:06:50", "remaining_time": "0:19:34", "throughput": 2839.39, "total_tokens": 21609728} {"current_steps": 33065, "total_steps": 38160, "loss": 0.0092, "lr": 2.667400689515537e-06, "epoch": 17.32966457023061, "percentage": 86.65, "elapsed_time": "2:06:51", "remaining_time": "0:19:32", "throughput": 2839.35, "total_tokens": 21612448} {"current_steps": 33070, "total_steps": 38160, "loss": 0.0046, "lr": 2.6622638517181e-06, "epoch": 17.332285115303982, "percentage": 86.66, "elapsed_time": "2:06:52", "remaining_time": "0:19:31", "throughput": 2839.34, "total_tokens": 21615424} {"current_steps": 33075, "total_steps": 38160, "loss": 0.0058, "lr": 2.657131686720224e-06, "epoch": 17.33490566037736, "percentage": 86.67, "elapsed_time": "2:06:53", "remaining_time": "0:19:30", "throughput": 2839.32, "total_tokens": 21618400} {"current_steps": 33080, "total_steps": 38160, "loss": 0.0096, "lr": 2.652004195595498e-06, "epoch": 17.337526205450732, "percentage": 86.69, "elapsed_time": "2:06:55", "remaining_time": "0:19:29", "throughput": 2839.41, "total_tokens": 21622688} {"current_steps": 33085, "total_steps": 38160, "loss": 0.0051, "lr": 2.6468813794165356e-06, "epoch": 17.34014675052411, "percentage": 86.7, "elapsed_time": "2:06:56", "remaining_time": "0:19:28", "throughput": 2839.45, "total_tokens": 21626176} {"current_steps": 33090, "total_steps": 38160, "loss": 0.0026, "lr": 2.641763239254977e-06, "epoch": 17.342767295597483, "percentage": 86.71, "elapsed_time": "2:06:57", "remaining_time": "0:19:27", "throughput": 2839.47, "total_tokens": 21629440} {"current_steps": 33095, "total_steps": 38160, "loss": 0.0417, "lr": 2.6366497761814713e-06, "epoch": 17.34538784067086, "percentage": 86.73, "elapsed_time": "2:06:58", "remaining_time": "0:19:25", "throughput": 2839.38, "total_tokens": 21632000} {"current_steps": 33100, "total_steps": 38160, "loss": 0.0191, "lr": 2.631540991265691e-06, "epoch": 17.348008385744233, "percentage": 86.74, "elapsed_time": "2:06:59", "remaining_time": "0:19:24", "throughput": 2839.39, "total_tokens": 21635104} {"current_steps": 33105, "total_steps": 38160, "loss": 0.0198, "lr": 2.6264368855763443e-06, "epoch": 17.35062893081761, "percentage": 86.75, "elapsed_time": "2:07:00", "remaining_time": "0:19:23", "throughput": 2839.42, "total_tokens": 21638624} {"current_steps": 33110, "total_steps": 38160, "loss": 0.0067, "lr": 2.6213374601811504e-06, "epoch": 17.353249475890987, "percentage": 86.77, "elapsed_time": "2:07:01", "remaining_time": "0:19:22", "throughput": 2839.41, "total_tokens": 21641664} {"current_steps": 33115, "total_steps": 38160, "loss": 0.0067, "lr": 2.616242716146855e-06, "epoch": 17.35587002096436, "percentage": 86.78, "elapsed_time": "2:07:02", "remaining_time": "0:19:21", "throughput": 2839.39, "total_tokens": 21644672} {"current_steps": 33120, "total_steps": 38160, "loss": 0.0075, "lr": 2.6111526545392145e-06, "epoch": 17.358490566037737, "percentage": 86.79, "elapsed_time": "2:07:04", "remaining_time": "0:19:20", "throughput": 2839.32, "total_tokens": 21647328} {"current_steps": 33125, "total_steps": 38160, "loss": 0.0039, "lr": 2.6060672764230106e-06, "epoch": 17.36111111111111, "percentage": 86.81, "elapsed_time": "2:07:05", "remaining_time": "0:19:19", "throughput": 2839.29, "total_tokens": 21650368} {"current_steps": 33130, "total_steps": 38160, "loss": 0.0238, "lr": 2.600986582862047e-06, "epoch": 17.363731656184488, "percentage": 86.82, "elapsed_time": "2:07:06", "remaining_time": "0:19:17", "throughput": 2839.38, "total_tokens": 21654400} {"current_steps": 33135, "total_steps": 38160, "loss": 0.0049, "lr": 2.5959105749191498e-06, "epoch": 17.36635220125786, "percentage": 86.83, "elapsed_time": "2:07:07", "remaining_time": "0:19:16", "throughput": 2839.41, "total_tokens": 21657856} {"current_steps": 33140, "total_steps": 38160, "loss": 0.0025, "lr": 2.590839253656166e-06, "epoch": 17.368972746331238, "percentage": 86.84, "elapsed_time": "2:07:08", "remaining_time": "0:19:15", "throughput": 2839.42, "total_tokens": 21661088} {"current_steps": 33145, "total_steps": 38160, "loss": 0.004, "lr": 2.5857726201339473e-06, "epoch": 17.37159329140461, "percentage": 86.86, "elapsed_time": "2:07:10", "remaining_time": "0:19:14", "throughput": 2839.58, "total_tokens": 21666144} {"current_steps": 33150, "total_steps": 38160, "loss": 0.0053, "lr": 2.5807106754123873e-06, "epoch": 17.37421383647799, "percentage": 86.87, "elapsed_time": "2:07:11", "remaining_time": "0:19:13", "throughput": 2839.56, "total_tokens": 21669152} {"current_steps": 33155, "total_steps": 38160, "loss": 0.0122, "lr": 2.575653420550378e-06, "epoch": 17.37683438155136, "percentage": 86.88, "elapsed_time": "2:07:12", "remaining_time": "0:19:12", "throughput": 2839.52, "total_tokens": 21671840} {"current_steps": 33160, "total_steps": 38160, "loss": 0.003, "lr": 2.57060085660584e-06, "epoch": 17.37945492662474, "percentage": 86.9, "elapsed_time": "2:07:13", "remaining_time": "0:19:10", "throughput": 2839.43, "total_tokens": 21674400} {"current_steps": 33165, "total_steps": 38160, "loss": 0.0042, "lr": 2.565552984635716e-06, "epoch": 17.382075471698112, "percentage": 86.91, "elapsed_time": "2:07:14", "remaining_time": "0:19:09", "throughput": 2839.4, "total_tokens": 21677280} {"current_steps": 33170, "total_steps": 38160, "loss": 0.0093, "lr": 2.5605098056959652e-06, "epoch": 17.38469601677149, "percentage": 86.92, "elapsed_time": "2:07:15", "remaining_time": "0:19:08", "throughput": 2839.41, "total_tokens": 21680352} {"current_steps": 33175, "total_steps": 38160, "loss": 0.0309, "lr": 2.555471320841557e-06, "epoch": 17.387316561844862, "percentage": 86.94, "elapsed_time": "2:07:16", "remaining_time": "0:19:07", "throughput": 2839.51, "total_tokens": 21684768} {"current_steps": 33180, "total_steps": 38160, "loss": 0.0293, "lr": 2.55043753112649e-06, "epoch": 17.38993710691824, "percentage": 86.95, "elapsed_time": "2:07:17", "remaining_time": "0:19:06", "throughput": 2839.5, "total_tokens": 21687776} {"current_steps": 33185, "total_steps": 38160, "loss": 0.0042, "lr": 2.5454084376037717e-06, "epoch": 17.392557651991613, "percentage": 86.96, "elapsed_time": "2:07:19", "remaining_time": "0:19:05", "throughput": 2839.55, "total_tokens": 21691392} {"current_steps": 33190, "total_steps": 38160, "loss": 0.0117, "lr": 2.5403840413254304e-06, "epoch": 17.39517819706499, "percentage": 86.98, "elapsed_time": "2:07:20", "remaining_time": "0:19:04", "throughput": 2839.5, "total_tokens": 21694016} {"current_steps": 33195, "total_steps": 38160, "loss": 0.0083, "lr": 2.5353643433425196e-06, "epoch": 17.397798742138363, "percentage": 86.99, "elapsed_time": "2:07:21", "remaining_time": "0:19:02", "throughput": 2839.52, "total_tokens": 21697152} {"current_steps": 33200, "total_steps": 38160, "loss": 0.0153, "lr": 2.5303493447050965e-06, "epoch": 17.40041928721174, "percentage": 87.0, "elapsed_time": "2:07:22", "remaining_time": "0:19:01", "throughput": 2839.64, "total_tokens": 21701504} {"current_steps": 33205, "total_steps": 38160, "loss": 0.0193, "lr": 2.525339046462244e-06, "epoch": 17.403039832285117, "percentage": 87.02, "elapsed_time": "2:07:23", "remaining_time": "0:19:00", "throughput": 2839.65, "total_tokens": 21704640} {"current_steps": 33210, "total_steps": 38160, "loss": 0.0127, "lr": 2.5203334496620544e-06, "epoch": 17.40566037735849, "percentage": 87.03, "elapsed_time": "2:07:24", "remaining_time": "0:18:59", "throughput": 2839.69, "total_tokens": 21708160} {"current_steps": 33215, "total_steps": 38160, "loss": 0.003, "lr": 2.515332555351646e-06, "epoch": 17.408280922431867, "percentage": 87.04, "elapsed_time": "2:07:25", "remaining_time": "0:18:58", "throughput": 2839.67, "total_tokens": 21710976} {"current_steps": 33220, "total_steps": 38160, "loss": 0.051, "lr": 2.510336364577154e-06, "epoch": 17.41090146750524, "percentage": 87.05, "elapsed_time": "2:07:26", "remaining_time": "0:18:57", "throughput": 2839.71, "total_tokens": 21714368} {"current_steps": 33225, "total_steps": 38160, "loss": 0.0347, "lr": 2.5053448783837143e-06, "epoch": 17.413522012578618, "percentage": 87.07, "elapsed_time": "2:07:27", "remaining_time": "0:18:55", "throughput": 2839.62, "total_tokens": 21716896} {"current_steps": 33230, "total_steps": 38160, "loss": 0.0148, "lr": 2.5003580978154917e-06, "epoch": 17.41614255765199, "percentage": 87.08, "elapsed_time": "2:07:28", "remaining_time": "0:18:54", "throughput": 2839.56, "total_tokens": 21719488} {"current_steps": 33235, "total_steps": 38160, "loss": 0.0079, "lr": 2.4953760239156716e-06, "epoch": 17.418763102725368, "percentage": 87.09, "elapsed_time": "2:07:30", "remaining_time": "0:18:53", "throughput": 2839.69, "total_tokens": 21724000} {"current_steps": 33240, "total_steps": 38160, "loss": 0.0063, "lr": 2.4903986577264366e-06, "epoch": 17.42138364779874, "percentage": 87.11, "elapsed_time": "2:07:31", "remaining_time": "0:18:52", "throughput": 2839.75, "total_tokens": 21727424} {"current_steps": 33245, "total_steps": 38160, "loss": 0.0077, "lr": 2.4854260002889986e-06, "epoch": 17.42400419287212, "percentage": 87.12, "elapsed_time": "2:07:32", "remaining_time": "0:18:51", "throughput": 2839.9, "total_tokens": 21732032} {"current_steps": 33250, "total_steps": 38160, "loss": 0.0244, "lr": 2.480458052643586e-06, "epoch": 17.42662473794549, "percentage": 87.13, "elapsed_time": "2:07:33", "remaining_time": "0:18:50", "throughput": 2839.95, "total_tokens": 21735488} {"current_steps": 33255, "total_steps": 38160, "loss": 0.0026, "lr": 2.4754948158294293e-06, "epoch": 17.42924528301887, "percentage": 87.15, "elapsed_time": "2:07:34", "remaining_time": "0:18:49", "throughput": 2839.88, "total_tokens": 21737984} {"current_steps": 33260, "total_steps": 38160, "loss": 0.0154, "lr": 2.4705362908847814e-06, "epoch": 17.431865828092242, "percentage": 87.16, "elapsed_time": "2:07:35", "remaining_time": "0:18:47", "throughput": 2839.89, "total_tokens": 21741088} {"current_steps": 33265, "total_steps": 38160, "loss": 0.011, "lr": 2.4655824788469172e-06, "epoch": 17.43448637316562, "percentage": 87.17, "elapsed_time": "2:07:36", "remaining_time": "0:18:46", "throughput": 2839.96, "total_tokens": 21744928} {"current_steps": 33270, "total_steps": 38160, "loss": 0.0101, "lr": 2.4606333807521087e-06, "epoch": 17.437106918238992, "percentage": 87.19, "elapsed_time": "2:07:37", "remaining_time": "0:18:45", "throughput": 2839.97, "total_tokens": 21748288} {"current_steps": 33275, "total_steps": 38160, "loss": 0.0039, "lr": 2.455688997635658e-06, "epoch": 17.43972746331237, "percentage": 87.2, "elapsed_time": "2:07:39", "remaining_time": "0:18:44", "throughput": 2840.03, "total_tokens": 21751968} {"current_steps": 33280, "total_steps": 38160, "loss": 0.0097, "lr": 2.4507493305318652e-06, "epoch": 17.442348008385743, "percentage": 87.21, "elapsed_time": "2:07:40", "remaining_time": "0:18:43", "throughput": 2840.08, "total_tokens": 21755648} {"current_steps": 33285, "total_steps": 38160, "loss": 0.0071, "lr": 2.445814380474057e-06, "epoch": 17.44496855345912, "percentage": 87.22, "elapsed_time": "2:07:41", "remaining_time": "0:18:42", "throughput": 2840.13, "total_tokens": 21759040} {"current_steps": 33290, "total_steps": 38160, "loss": 0.0073, "lr": 2.4408841484945684e-06, "epoch": 17.447589098532493, "percentage": 87.24, "elapsed_time": "2:07:42", "remaining_time": "0:18:40", "throughput": 2840.15, "total_tokens": 21762272} {"current_steps": 33295, "total_steps": 38160, "loss": 0.0054, "lr": 2.435958635624755e-06, "epoch": 17.45020964360587, "percentage": 87.25, "elapsed_time": "2:07:43", "remaining_time": "0:18:39", "throughput": 2840.17, "total_tokens": 21765600} {"current_steps": 33300, "total_steps": 38160, "loss": 0.0094, "lr": 2.4310378428949678e-06, "epoch": 17.452830188679247, "percentage": 87.26, "elapsed_time": "2:07:44", "remaining_time": "0:18:38", "throughput": 2840.08, "total_tokens": 21768032} {"current_steps": 33305, "total_steps": 38160, "loss": 0.0051, "lr": 2.4261217713345804e-06, "epoch": 17.45545073375262, "percentage": 87.28, "elapsed_time": "2:07:45", "remaining_time": "0:18:37", "throughput": 2839.97, "total_tokens": 21770304} {"current_steps": 33310, "total_steps": 38160, "loss": 0.0044, "lr": 2.421210421971981e-06, "epoch": 17.458071278825997, "percentage": 87.29, "elapsed_time": "2:07:46", "remaining_time": "0:18:36", "throughput": 2840.02, "total_tokens": 21774016} {"current_steps": 33315, "total_steps": 38160, "loss": 0.0137, "lr": 2.416303795834571e-06, "epoch": 17.46069182389937, "percentage": 87.3, "elapsed_time": "2:07:48", "remaining_time": "0:18:35", "throughput": 2840.08, "total_tokens": 21778048} {"current_steps": 33320, "total_steps": 38160, "loss": 0.0019, "lr": 2.4114018939487615e-06, "epoch": 17.463312368972748, "percentage": 87.32, "elapsed_time": "2:07:49", "remaining_time": "0:18:34", "throughput": 2840.02, "total_tokens": 21780736} {"current_steps": 33325, "total_steps": 38160, "loss": 0.0261, "lr": 2.4065047173399662e-06, "epoch": 17.46593291404612, "percentage": 87.33, "elapsed_time": "2:07:50", "remaining_time": "0:18:32", "throughput": 2840.12, "total_tokens": 21784704} {"current_steps": 33330, "total_steps": 38160, "loss": 0.0067, "lr": 2.4016122670326295e-06, "epoch": 17.468553459119498, "percentage": 87.34, "elapsed_time": "2:07:51", "remaining_time": "0:18:31", "throughput": 2840.15, "total_tokens": 21788096} {"current_steps": 33335, "total_steps": 38160, "loss": 0.0056, "lr": 2.396724544050186e-06, "epoch": 17.47117400419287, "percentage": 87.36, "elapsed_time": "2:07:52", "remaining_time": "0:18:30", "throughput": 2840.19, "total_tokens": 21791808} {"current_steps": 33340, "total_steps": 38160, "loss": 0.0104, "lr": 2.3918415494150944e-06, "epoch": 17.47379454926625, "percentage": 87.37, "elapsed_time": "2:07:53", "remaining_time": "0:18:29", "throughput": 2840.2, "total_tokens": 21795072} {"current_steps": 33345, "total_steps": 38160, "loss": 0.0041, "lr": 2.3869632841488245e-06, "epoch": 17.47641509433962, "percentage": 87.38, "elapsed_time": "2:07:54", "remaining_time": "0:18:28", "throughput": 2840.19, "total_tokens": 21798016} {"current_steps": 33350, "total_steps": 38160, "loss": 0.0032, "lr": 2.382089749271857e-06, "epoch": 17.479035639413, "percentage": 87.4, "elapsed_time": "2:07:55", "remaining_time": "0:18:27", "throughput": 2840.27, "total_tokens": 21801632} {"current_steps": 33355, "total_steps": 38160, "loss": 0.001, "lr": 2.3772209458036737e-06, "epoch": 17.481656184486372, "percentage": 87.41, "elapsed_time": "2:07:56", "remaining_time": "0:18:25", "throughput": 2840.25, "total_tokens": 21804416} {"current_steps": 33360, "total_steps": 38160, "loss": 0.0066, "lr": 2.372356874762771e-06, "epoch": 17.48427672955975, "percentage": 87.42, "elapsed_time": "2:07:58", "remaining_time": "0:18:24", "throughput": 2840.31, "total_tokens": 21808160} {"current_steps": 33365, "total_steps": 38160, "loss": 0.0082, "lr": 2.36749753716666e-06, "epoch": 17.486897274633122, "percentage": 87.43, "elapsed_time": "2:07:59", "remaining_time": "0:18:23", "throughput": 2840.26, "total_tokens": 21810976} {"current_steps": 33370, "total_steps": 38160, "loss": 0.006, "lr": 2.3626429340318613e-06, "epoch": 17.4895178197065, "percentage": 87.45, "elapsed_time": "2:08:00", "remaining_time": "0:18:22", "throughput": 2840.29, "total_tokens": 21814880} {"current_steps": 33375, "total_steps": 38160, "loss": 0.0089, "lr": 2.357793066373901e-06, "epoch": 17.492138364779873, "percentage": 87.46, "elapsed_time": "2:08:01", "remaining_time": "0:18:21", "throughput": 2840.27, "total_tokens": 21817792} {"current_steps": 33380, "total_steps": 38160, "loss": 0.0044, "lr": 2.352947935207317e-06, "epoch": 17.49475890985325, "percentage": 87.47, "elapsed_time": "2:08:02", "remaining_time": "0:18:20", "throughput": 2840.31, "total_tokens": 21821312} {"current_steps": 33385, "total_steps": 38160, "loss": 0.0056, "lr": 2.3481075415456495e-06, "epoch": 17.497379454926623, "percentage": 87.49, "elapsed_time": "2:08:03", "remaining_time": "0:18:19", "throughput": 2840.44, "total_tokens": 21825664} {"current_steps": 33390, "total_steps": 38160, "loss": 0.0099, "lr": 2.3432718864014576e-06, "epoch": 17.5, "percentage": 87.5, "elapsed_time": "2:08:04", "remaining_time": "0:18:17", "throughput": 2840.49, "total_tokens": 21829088} {"current_steps": 33395, "total_steps": 38160, "loss": 0.0035, "lr": 2.338440970786304e-06, "epoch": 17.502620545073377, "percentage": 87.51, "elapsed_time": "2:08:06", "remaining_time": "0:18:16", "throughput": 2840.47, "total_tokens": 21832000} {"current_steps": 33400, "total_steps": 38160, "loss": 0.0025, "lr": 2.3336147957107644e-06, "epoch": 17.50524109014675, "percentage": 87.53, "elapsed_time": "2:08:07", "remaining_time": "0:18:15", "throughput": 2840.43, "total_tokens": 21834816} {"current_steps": 33405, "total_steps": 38160, "loss": 0.003, "lr": 2.3287933621844227e-06, "epoch": 17.507861635220127, "percentage": 87.54, "elapsed_time": "2:08:08", "remaining_time": "0:18:14", "throughput": 2840.31, "total_tokens": 21837184} {"current_steps": 33410, "total_steps": 38160, "loss": 0.0263, "lr": 2.3239766712158633e-06, "epoch": 17.5104821802935, "percentage": 87.55, "elapsed_time": "2:08:09", "remaining_time": "0:18:13", "throughput": 2840.44, "total_tokens": 21842080} {"current_steps": 33415, "total_steps": 38160, "loss": 0.0073, "lr": 2.319164723812675e-06, "epoch": 17.513102725366878, "percentage": 87.57, "elapsed_time": "2:08:10", "remaining_time": "0:18:12", "throughput": 2840.39, "total_tokens": 21844736} {"current_steps": 33420, "total_steps": 38160, "loss": 0.0077, "lr": 2.314357520981472e-06, "epoch": 17.51572327044025, "percentage": 87.58, "elapsed_time": "2:08:11", "remaining_time": "0:18:10", "throughput": 2840.5, "total_tokens": 21848736} {"current_steps": 33425, "total_steps": 38160, "loss": 0.0076, "lr": 2.309555063727864e-06, "epoch": 17.518343815513628, "percentage": 87.59, "elapsed_time": "2:08:13", "remaining_time": "0:18:09", "throughput": 2840.47, "total_tokens": 21851808} {"current_steps": 33430, "total_steps": 38160, "loss": 0.0013, "lr": 2.304757353056475e-06, "epoch": 17.520964360587, "percentage": 87.6, "elapsed_time": "2:08:14", "remaining_time": "0:18:08", "throughput": 2840.44, "total_tokens": 21854752} {"current_steps": 33435, "total_steps": 38160, "loss": 0.0021, "lr": 2.2999643899709267e-06, "epoch": 17.52358490566038, "percentage": 87.62, "elapsed_time": "2:08:15", "remaining_time": "0:18:07", "throughput": 2840.45, "total_tokens": 21858016} {"current_steps": 33440, "total_steps": 38160, "loss": 0.0044, "lr": 2.2951761754738456e-06, "epoch": 17.52620545073375, "percentage": 87.63, "elapsed_time": "2:08:16", "remaining_time": "0:18:06", "throughput": 2840.42, "total_tokens": 21860928} {"current_steps": 33445, "total_steps": 38160, "loss": 0.0017, "lr": 2.29039271056688e-06, "epoch": 17.52882599580713, "percentage": 87.64, "elapsed_time": "2:08:17", "remaining_time": "0:18:05", "throughput": 2840.45, "total_tokens": 21864416} {"current_steps": 33450, "total_steps": 38160, "loss": 0.0063, "lr": 2.285613996250674e-06, "epoch": 17.531446540880502, "percentage": 87.66, "elapsed_time": "2:08:18", "remaining_time": "0:18:04", "throughput": 2840.48, "total_tokens": 21867808} {"current_steps": 33455, "total_steps": 38160, "loss": 0.0107, "lr": 2.2808400335248865e-06, "epoch": 17.53406708595388, "percentage": 87.67, "elapsed_time": "2:08:19", "remaining_time": "0:18:02", "throughput": 2840.5, "total_tokens": 21871008} {"current_steps": 33460, "total_steps": 38160, "loss": 0.0055, "lr": 2.2760708233881654e-06, "epoch": 17.536687631027252, "percentage": 87.68, "elapsed_time": "2:08:20", "remaining_time": "0:18:01", "throughput": 2840.5, "total_tokens": 21873984} {"current_steps": 33465, "total_steps": 38160, "loss": 0.0034, "lr": 2.271306366838183e-06, "epoch": 17.53930817610063, "percentage": 87.7, "elapsed_time": "2:08:21", "remaining_time": "0:18:00", "throughput": 2840.52, "total_tokens": 21877216} {"current_steps": 33470, "total_steps": 38160, "loss": 0.0049, "lr": 2.266546664871602e-06, "epoch": 17.541928721174003, "percentage": 87.71, "elapsed_time": "2:08:22", "remaining_time": "0:17:59", "throughput": 2840.55, "total_tokens": 21880544} {"current_steps": 33475, "total_steps": 38160, "loss": 0.0272, "lr": 2.261791718484102e-06, "epoch": 17.54454926624738, "percentage": 87.72, "elapsed_time": "2:08:23", "remaining_time": "0:17:58", "throughput": 2840.52, "total_tokens": 21883296} {"current_steps": 33480, "total_steps": 38160, "loss": 0.0073, "lr": 2.257041528670362e-06, "epoch": 17.547169811320753, "percentage": 87.74, "elapsed_time": "2:08:25", "remaining_time": "0:17:57", "throughput": 2840.47, "total_tokens": 21885888} {"current_steps": 33485, "total_steps": 38160, "loss": 0.0052, "lr": 2.2522960964240753e-06, "epoch": 17.54979035639413, "percentage": 87.75, "elapsed_time": "2:08:26", "remaining_time": "0:17:55", "throughput": 2840.42, "total_tokens": 21888736} {"current_steps": 33490, "total_steps": 38160, "loss": 0.0077, "lr": 2.247555422737924e-06, "epoch": 17.552410901467507, "percentage": 87.76, "elapsed_time": "2:08:27", "remaining_time": "0:17:54", "throughput": 2840.35, "total_tokens": 21891264} {"current_steps": 33495, "total_steps": 38160, "loss": 0.0133, "lr": 2.2428195086036024e-06, "epoch": 17.55503144654088, "percentage": 87.78, "elapsed_time": "2:08:28", "remaining_time": "0:17:53", "throughput": 2840.26, "total_tokens": 21893760} {"current_steps": 33500, "total_steps": 38160, "loss": 0.0086, "lr": 2.238088355011811e-06, "epoch": 17.557651991614257, "percentage": 87.79, "elapsed_time": "2:08:29", "remaining_time": "0:17:52", "throughput": 2840.29, "total_tokens": 21897280} {"current_steps": 33505, "total_steps": 38160, "loss": 0.0048, "lr": 2.2333619629522518e-06, "epoch": 17.56027253668763, "percentage": 87.8, "elapsed_time": "2:08:30", "remaining_time": "0:17:51", "throughput": 2840.3, "total_tokens": 21900640} {"current_steps": 33510, "total_steps": 38160, "loss": 0.0067, "lr": 2.2286403334136424e-06, "epoch": 17.562893081761008, "percentage": 87.81, "elapsed_time": "2:08:31", "remaining_time": "0:17:50", "throughput": 2840.31, "total_tokens": 21903744} {"current_steps": 33515, "total_steps": 38160, "loss": 0.0018, "lr": 2.223923467383679e-06, "epoch": 17.56551362683438, "percentage": 87.83, "elapsed_time": "2:08:32", "remaining_time": "0:17:48", "throughput": 2840.19, "total_tokens": 21905984} {"current_steps": 33520, "total_steps": 38160, "loss": 0.0049, "lr": 2.2192113658490886e-06, "epoch": 17.568134171907758, "percentage": 87.84, "elapsed_time": "2:08:33", "remaining_time": "0:17:47", "throughput": 2840.33, "total_tokens": 21910272} {"current_steps": 33525, "total_steps": 38160, "loss": 0.0389, "lr": 2.2145040297955776e-06, "epoch": 17.57075471698113, "percentage": 87.85, "elapsed_time": "2:08:35", "remaining_time": "0:17:46", "throughput": 2840.31, "total_tokens": 21913216} {"current_steps": 33530, "total_steps": 38160, "loss": 0.0033, "lr": 2.209801460207875e-06, "epoch": 17.57337526205451, "percentage": 87.87, "elapsed_time": "2:08:36", "remaining_time": "0:17:45", "throughput": 2840.28, "total_tokens": 21916128} {"current_steps": 33535, "total_steps": 38160, "loss": 0.0025, "lr": 2.2051036580697042e-06, "epoch": 17.57599580712788, "percentage": 87.88, "elapsed_time": "2:08:37", "remaining_time": "0:17:44", "throughput": 2840.2, "total_tokens": 21918592} {"current_steps": 33540, "total_steps": 38160, "loss": 0.0069, "lr": 2.2004106243637885e-06, "epoch": 17.57861635220126, "percentage": 87.89, "elapsed_time": "2:08:38", "remaining_time": "0:17:43", "throughput": 2840.14, "total_tokens": 21921216} {"current_steps": 33545, "total_steps": 38160, "loss": 0.0076, "lr": 2.1957223600718587e-06, "epoch": 17.581236897274632, "percentage": 87.91, "elapsed_time": "2:08:39", "remaining_time": "0:17:42", "throughput": 2840.25, "total_tokens": 21925056} {"current_steps": 33550, "total_steps": 38160, "loss": 0.0056, "lr": 2.1910388661746493e-06, "epoch": 17.58385744234801, "percentage": 87.92, "elapsed_time": "2:08:40", "remaining_time": "0:17:40", "throughput": 2840.27, "total_tokens": 21928320} {"current_steps": 33555, "total_steps": 38160, "loss": 0.0204, "lr": 2.186360143651886e-06, "epoch": 17.586477987421382, "percentage": 87.93, "elapsed_time": "2:08:41", "remaining_time": "0:17:39", "throughput": 2840.33, "total_tokens": 21931968} {"current_steps": 33560, "total_steps": 38160, "loss": 0.0051, "lr": 2.1816861934823103e-06, "epoch": 17.58909853249476, "percentage": 87.95, "elapsed_time": "2:08:42", "remaining_time": "0:17:38", "throughput": 2840.32, "total_tokens": 21935008} {"current_steps": 33565, "total_steps": 38160, "loss": 0.0064, "lr": 2.1770170166436595e-06, "epoch": 17.591719077568133, "percentage": 87.96, "elapsed_time": "2:08:43", "remaining_time": "0:17:37", "throughput": 2840.22, "total_tokens": 21937344} {"current_steps": 33570, "total_steps": 38160, "loss": 0.0051, "lr": 2.172352614112669e-06, "epoch": 17.59433962264151, "percentage": 87.97, "elapsed_time": "2:08:44", "remaining_time": "0:17:36", "throughput": 2840.16, "total_tokens": 21939936} {"current_steps": 33575, "total_steps": 38160, "loss": 0.0028, "lr": 2.167692986865083e-06, "epoch": 17.596960167714883, "percentage": 87.98, "elapsed_time": "2:08:45", "remaining_time": "0:17:35", "throughput": 2840.08, "total_tokens": 21942400} {"current_steps": 33580, "total_steps": 38160, "loss": 0.0081, "lr": 2.1630381358756362e-06, "epoch": 17.59958071278826, "percentage": 88.0, "elapsed_time": "2:08:47", "remaining_time": "0:17:33", "throughput": 2840.08, "total_tokens": 21945632} {"current_steps": 33585, "total_steps": 38160, "loss": 0.0167, "lr": 2.158388062118072e-06, "epoch": 17.602201257861637, "percentage": 88.01, "elapsed_time": "2:08:48", "remaining_time": "0:17:32", "throughput": 2840.13, "total_tokens": 21949312} {"current_steps": 33590, "total_steps": 38160, "loss": 0.0231, "lr": 2.1537427665651393e-06, "epoch": 17.60482180293501, "percentage": 88.02, "elapsed_time": "2:08:50", "remaining_time": "0:17:31", "throughput": 2840.34, "total_tokens": 21955872} {"current_steps": 33595, "total_steps": 38160, "loss": 0.0092, "lr": 2.1491022501885726e-06, "epoch": 17.607442348008387, "percentage": 88.04, "elapsed_time": "2:08:51", "remaining_time": "0:17:30", "throughput": 2840.38, "total_tokens": 21959712} {"current_steps": 33600, "total_steps": 38160, "loss": 0.0092, "lr": 2.1444665139591174e-06, "epoch": 17.61006289308176, "percentage": 88.05, "elapsed_time": "2:08:52", "remaining_time": "0:17:29", "throughput": 2840.42, "total_tokens": 21963136} {"current_steps": 33605, "total_steps": 38160, "loss": 0.0518, "lr": 2.139835558846523e-06, "epoch": 17.612683438155138, "percentage": 88.06, "elapsed_time": "2:08:53", "remaining_time": "0:17:28", "throughput": 2840.5, "total_tokens": 21966912} {"current_steps": 33610, "total_steps": 38160, "loss": 0.0025, "lr": 2.1352093858195225e-06, "epoch": 17.61530398322851, "percentage": 88.08, "elapsed_time": "2:08:54", "remaining_time": "0:17:27", "throughput": 2840.4, "total_tokens": 21969152} {"current_steps": 33615, "total_steps": 38160, "loss": 0.0035, "lr": 2.1305879958458676e-06, "epoch": 17.617924528301888, "percentage": 88.09, "elapsed_time": "2:08:55", "remaining_time": "0:17:25", "throughput": 2840.32, "total_tokens": 21971744} {"current_steps": 33620, "total_steps": 38160, "loss": 0.002, "lr": 2.1259713898922894e-06, "epoch": 17.62054507337526, "percentage": 88.1, "elapsed_time": "2:08:56", "remaining_time": "0:17:24", "throughput": 2840.29, "total_tokens": 21974592} {"current_steps": 33625, "total_steps": 38160, "loss": 0.0124, "lr": 2.1213595689245386e-06, "epoch": 17.62316561844864, "percentage": 88.12, "elapsed_time": "2:08:58", "remaining_time": "0:17:23", "throughput": 2840.33, "total_tokens": 21978528} {"current_steps": 33630, "total_steps": 38160, "loss": 0.0034, "lr": 2.1167525339073513e-06, "epoch": 17.62578616352201, "percentage": 88.13, "elapsed_time": "2:08:59", "remaining_time": "0:17:22", "throughput": 2840.33, "total_tokens": 21981792} {"current_steps": 33635, "total_steps": 38160, "loss": 0.0043, "lr": 2.112150285804473e-06, "epoch": 17.62840670859539, "percentage": 88.14, "elapsed_time": "2:09:00", "remaining_time": "0:17:21", "throughput": 2840.38, "total_tokens": 21985344} {"current_steps": 33640, "total_steps": 38160, "loss": 0.0154, "lr": 2.107552825578632e-06, "epoch": 17.631027253668762, "percentage": 88.16, "elapsed_time": "2:09:01", "remaining_time": "0:17:20", "throughput": 2840.38, "total_tokens": 21988352} {"current_steps": 33645, "total_steps": 38160, "loss": 0.008, "lr": 2.102960154191572e-06, "epoch": 17.63364779874214, "percentage": 88.17, "elapsed_time": "2:09:02", "remaining_time": "0:17:19", "throughput": 2840.49, "total_tokens": 21992608} {"current_steps": 33650, "total_steps": 38160, "loss": 0.0162, "lr": 2.098372272604021e-06, "epoch": 17.636268343815512, "percentage": 88.18, "elapsed_time": "2:09:03", "remaining_time": "0:17:17", "throughput": 2840.54, "total_tokens": 21996160} {"current_steps": 33655, "total_steps": 38160, "loss": 0.0037, "lr": 2.0937891817757155e-06, "epoch": 17.63888888888889, "percentage": 88.19, "elapsed_time": "2:09:04", "remaining_time": "0:17:16", "throughput": 2840.56, "total_tokens": 21999712} {"current_steps": 33660, "total_steps": 38160, "loss": 0.0031, "lr": 2.089210882665385e-06, "epoch": 17.641509433962263, "percentage": 88.21, "elapsed_time": "2:09:05", "remaining_time": "0:17:15", "throughput": 2840.51, "total_tokens": 22002432} {"current_steps": 33665, "total_steps": 38160, "loss": 0.0117, "lr": 2.0846373762307635e-06, "epoch": 17.64412997903564, "percentage": 88.22, "elapsed_time": "2:09:07", "remaining_time": "0:17:14", "throughput": 2840.45, "total_tokens": 22004992} {"current_steps": 33670, "total_steps": 38160, "loss": 0.0049, "lr": 2.080068663428569e-06, "epoch": 17.646750524109013, "percentage": 88.23, "elapsed_time": "2:09:08", "remaining_time": "0:17:13", "throughput": 2840.5, "total_tokens": 22008480} {"current_steps": 33675, "total_steps": 38160, "loss": 0.0046, "lr": 2.075504745214521e-06, "epoch": 17.64937106918239, "percentage": 88.25, "elapsed_time": "2:09:09", "remaining_time": "0:17:12", "throughput": 2840.56, "total_tokens": 22011968} {"current_steps": 33680, "total_steps": 38160, "loss": 0.0144, "lr": 2.0709456225433437e-06, "epoch": 17.651991614255767, "percentage": 88.26, "elapsed_time": "2:09:10", "remaining_time": "0:17:10", "throughput": 2840.6, "total_tokens": 22015424} {"current_steps": 33685, "total_steps": 38160, "loss": 0.0089, "lr": 2.0663912963687554e-06, "epoch": 17.65461215932914, "percentage": 88.27, "elapsed_time": "2:09:11", "remaining_time": "0:17:09", "throughput": 2840.72, "total_tokens": 22019776} {"current_steps": 33690, "total_steps": 38160, "loss": 0.0055, "lr": 2.0618417676434713e-06, "epoch": 17.657232704402517, "percentage": 88.29, "elapsed_time": "2:09:12", "remaining_time": "0:17:08", "throughput": 2840.74, "total_tokens": 22023072} {"current_steps": 33695, "total_steps": 38160, "loss": 0.0058, "lr": 2.0572970373191975e-06, "epoch": 17.65985324947589, "percentage": 88.3, "elapsed_time": "2:09:13", "remaining_time": "0:17:07", "throughput": 2840.73, "total_tokens": 22026272} {"current_steps": 33700, "total_steps": 38160, "loss": 0.0072, "lr": 2.052757106346634e-06, "epoch": 17.662473794549268, "percentage": 88.31, "elapsed_time": "2:09:14", "remaining_time": "0:17:06", "throughput": 2840.7, "total_tokens": 22029216} {"current_steps": 33705, "total_steps": 38160, "loss": 0.0042, "lr": 2.048221975675488e-06, "epoch": 17.66509433962264, "percentage": 88.33, "elapsed_time": "2:09:15", "remaining_time": "0:17:05", "throughput": 2840.7, "total_tokens": 22032416} {"current_steps": 33710, "total_steps": 38160, "loss": 0.0024, "lr": 2.043691646254456e-06, "epoch": 17.667714884696018, "percentage": 88.34, "elapsed_time": "2:09:17", "remaining_time": "0:17:04", "throughput": 2840.67, "total_tokens": 22035488} {"current_steps": 33715, "total_steps": 38160, "loss": 0.0152, "lr": 2.039166119031233e-06, "epoch": 17.67033542976939, "percentage": 88.35, "elapsed_time": "2:09:18", "remaining_time": "0:17:02", "throughput": 2840.73, "total_tokens": 22039232} {"current_steps": 33720, "total_steps": 38160, "loss": 0.0032, "lr": 2.034645394952511e-06, "epoch": 17.67295597484277, "percentage": 88.36, "elapsed_time": "2:09:19", "remaining_time": "0:17:01", "throughput": 2840.67, "total_tokens": 22041888} {"current_steps": 33725, "total_steps": 38160, "loss": 0.0028, "lr": 2.030129474963971e-06, "epoch": 17.67557651991614, "percentage": 88.38, "elapsed_time": "2:09:20", "remaining_time": "0:17:00", "throughput": 2840.6, "total_tokens": 22044416} {"current_steps": 33730, "total_steps": 38160, "loss": 0.0016, "lr": 2.025618360010284e-06, "epoch": 17.67819706498952, "percentage": 88.39, "elapsed_time": "2:09:21", "remaining_time": "0:16:59", "throughput": 2840.6, "total_tokens": 22047552} {"current_steps": 33735, "total_steps": 38160, "loss": 0.0079, "lr": 2.0211120510351317e-06, "epoch": 17.680817610062892, "percentage": 88.4, "elapsed_time": "2:09:22", "remaining_time": "0:16:58", "throughput": 2840.51, "total_tokens": 22049856} {"current_steps": 33740, "total_steps": 38160, "loss": 0.0069, "lr": 2.0166105489811822e-06, "epoch": 17.68343815513627, "percentage": 88.42, "elapsed_time": "2:09:23", "remaining_time": "0:16:57", "throughput": 2840.48, "total_tokens": 22052672} {"current_steps": 33745, "total_steps": 38160, "loss": 0.0143, "lr": 2.0121138547901016e-06, "epoch": 17.686058700209642, "percentage": 88.43, "elapsed_time": "2:09:24", "remaining_time": "0:16:55", "throughput": 2840.45, "total_tokens": 22055392} {"current_steps": 33750, "total_steps": 38160, "loss": 0.008, "lr": 2.0076219694025427e-06, "epoch": 17.68867924528302, "percentage": 88.44, "elapsed_time": "2:09:25", "remaining_time": "0:16:54", "throughput": 2840.42, "total_tokens": 22058176} {"current_steps": 33755, "total_steps": 38160, "loss": 0.0033, "lr": 2.003134893758152e-06, "epoch": 17.691299790356393, "percentage": 88.46, "elapsed_time": "2:09:26", "remaining_time": "0:16:53", "throughput": 2840.42, "total_tokens": 22061152} {"current_steps": 33760, "total_steps": 38160, "loss": 0.0027, "lr": 1.9986526287955805e-06, "epoch": 17.69392033542977, "percentage": 88.47, "elapsed_time": "2:09:27", "remaining_time": "0:16:52", "throughput": 2840.44, "total_tokens": 22064288} {"current_steps": 33765, "total_steps": 38160, "loss": 0.0076, "lr": 1.9941751754524644e-06, "epoch": 17.696540880503143, "percentage": 88.48, "elapsed_time": "2:09:29", "remaining_time": "0:16:51", "throughput": 2840.39, "total_tokens": 22067008} {"current_steps": 33770, "total_steps": 38160, "loss": 0.0045, "lr": 1.9897025346654412e-06, "epoch": 17.69916142557652, "percentage": 88.5, "elapsed_time": "2:09:30", "remaining_time": "0:16:50", "throughput": 2840.41, "total_tokens": 22070400} {"current_steps": 33775, "total_steps": 38160, "loss": 0.0053, "lr": 1.985234707370134e-06, "epoch": 17.701781970649897, "percentage": 88.51, "elapsed_time": "2:09:31", "remaining_time": "0:16:48", "throughput": 2840.4, "total_tokens": 22073312} {"current_steps": 33780, "total_steps": 38160, "loss": 0.0086, "lr": 1.9807716945011544e-06, "epoch": 17.70440251572327, "percentage": 88.52, "elapsed_time": "2:09:32", "remaining_time": "0:16:47", "throughput": 2840.42, "total_tokens": 22076480} {"current_steps": 33785, "total_steps": 38160, "loss": 0.0018, "lr": 1.9763134969921215e-06, "epoch": 17.707023060796647, "percentage": 88.54, "elapsed_time": "2:09:33", "remaining_time": "0:16:46", "throughput": 2840.47, "total_tokens": 22079968} {"current_steps": 33790, "total_steps": 38160, "loss": 0.002, "lr": 1.971860115775634e-06, "epoch": 17.70964360587002, "percentage": 88.55, "elapsed_time": "2:09:34", "remaining_time": "0:16:45", "throughput": 2840.48, "total_tokens": 22083136} {"current_steps": 33795, "total_steps": 38160, "loss": 0.0105, "lr": 1.967411551783294e-06, "epoch": 17.712264150943398, "percentage": 88.56, "elapsed_time": "2:09:35", "remaining_time": "0:16:44", "throughput": 2840.52, "total_tokens": 22086400} {"current_steps": 33800, "total_steps": 38160, "loss": 0.0116, "lr": 1.9629678059456895e-06, "epoch": 17.71488469601677, "percentage": 88.57, "elapsed_time": "2:09:36", "remaining_time": "0:16:43", "throughput": 2840.54, "total_tokens": 22089632} {"current_steps": 33805, "total_steps": 38160, "loss": 0.0059, "lr": 1.9585288791924004e-06, "epoch": 17.717505241090148, "percentage": 88.59, "elapsed_time": "2:09:37", "remaining_time": "0:16:41", "throughput": 2840.52, "total_tokens": 22092576} {"current_steps": 33810, "total_steps": 38160, "loss": 0.0082, "lr": 1.9540947724519947e-06, "epoch": 17.72012578616352, "percentage": 88.6, "elapsed_time": "2:09:38", "remaining_time": "0:16:40", "throughput": 2840.6, "total_tokens": 22096768} {"current_steps": 33815, "total_steps": 38160, "loss": 0.0068, "lr": 1.9496654866520414e-06, "epoch": 17.7227463312369, "percentage": 88.61, "elapsed_time": "2:09:39", "remaining_time": "0:16:39", "throughput": 2840.54, "total_tokens": 22099296} {"current_steps": 33820, "total_steps": 38160, "loss": 0.0438, "lr": 1.9452410227190937e-06, "epoch": 17.72536687631027, "percentage": 88.63, "elapsed_time": "2:09:41", "remaining_time": "0:16:38", "throughput": 2840.49, "total_tokens": 22101888} {"current_steps": 33825, "total_steps": 38160, "loss": 0.0122, "lr": 1.9408213815787087e-06, "epoch": 17.72798742138365, "percentage": 88.64, "elapsed_time": "2:09:42", "remaining_time": "0:16:37", "throughput": 2840.51, "total_tokens": 22105568} {"current_steps": 33830, "total_steps": 38160, "loss": 0.012, "lr": 1.936406564155413e-06, "epoch": 17.730607966457022, "percentage": 88.65, "elapsed_time": "2:09:43", "remaining_time": "0:16:36", "throughput": 2840.58, "total_tokens": 22109248} {"current_steps": 33835, "total_steps": 38160, "loss": 0.0036, "lr": 1.9319965713727435e-06, "epoch": 17.7332285115304, "percentage": 88.67, "elapsed_time": "2:09:44", "remaining_time": "0:16:35", "throughput": 2840.59, "total_tokens": 22112352} {"current_steps": 33840, "total_steps": 38160, "loss": 0.0041, "lr": 1.9275914041532144e-06, "epoch": 17.735849056603772, "percentage": 88.68, "elapsed_time": "2:09:45", "remaining_time": "0:16:33", "throughput": 2840.58, "total_tokens": 22115200} {"current_steps": 33845, "total_steps": 38160, "loss": 0.0202, "lr": 1.9231910634183394e-06, "epoch": 17.73846960167715, "percentage": 88.69, "elapsed_time": "2:09:46", "remaining_time": "0:16:32", "throughput": 2840.6, "total_tokens": 22118272} {"current_steps": 33850, "total_steps": 38160, "loss": 0.0034, "lr": 1.918795550088623e-06, "epoch": 17.741090146750523, "percentage": 88.71, "elapsed_time": "2:09:47", "remaining_time": "0:16:31", "throughput": 2840.6, "total_tokens": 22121248} {"current_steps": 33855, "total_steps": 38160, "loss": 0.0094, "lr": 1.9144048650835496e-06, "epoch": 17.7437106918239, "percentage": 88.72, "elapsed_time": "2:09:48", "remaining_time": "0:16:30", "throughput": 2840.62, "total_tokens": 22124416} {"current_steps": 33860, "total_steps": 38160, "loss": 0.0039, "lr": 1.9100190093216093e-06, "epoch": 17.746331236897273, "percentage": 88.73, "elapsed_time": "2:09:49", "remaining_time": "0:16:29", "throughput": 2840.61, "total_tokens": 22127264} {"current_steps": 33865, "total_steps": 38160, "loss": 0.01, "lr": 1.9056379837202627e-06, "epoch": 17.74895178197065, "percentage": 88.74, "elapsed_time": "2:09:50", "remaining_time": "0:16:28", "throughput": 2840.68, "total_tokens": 22130816} {"current_steps": 33870, "total_steps": 38160, "loss": 0.0163, "lr": 1.9012617891959766e-06, "epoch": 17.751572327044027, "percentage": 88.76, "elapsed_time": "2:09:51", "remaining_time": "0:16:26", "throughput": 2840.79, "total_tokens": 22135200} {"current_steps": 33875, "total_steps": 38160, "loss": 0.0235, "lr": 1.8968904266641996e-06, "epoch": 17.7541928721174, "percentage": 88.77, "elapsed_time": "2:09:53", "remaining_time": "0:16:25", "throughput": 2840.79, "total_tokens": 22138304} {"current_steps": 33880, "total_steps": 38160, "loss": 0.0019, "lr": 1.892523897039372e-06, "epoch": 17.756813417190777, "percentage": 88.78, "elapsed_time": "2:09:54", "remaining_time": "0:16:24", "throughput": 2840.72, "total_tokens": 22141024} {"current_steps": 33885, "total_steps": 38160, "loss": 0.0156, "lr": 1.888162201234922e-06, "epoch": 17.75943396226415, "percentage": 88.8, "elapsed_time": "2:09:55", "remaining_time": "0:16:23", "throughput": 2840.79, "total_tokens": 22144800} {"current_steps": 33890, "total_steps": 38160, "loss": 0.0985, "lr": 1.8838053401632666e-06, "epoch": 17.762054507337528, "percentage": 88.81, "elapsed_time": "2:09:56", "remaining_time": "0:16:22", "throughput": 2840.8, "total_tokens": 22148256} {"current_steps": 33895, "total_steps": 38160, "loss": 0.0146, "lr": 1.8794533147358074e-06, "epoch": 17.7646750524109, "percentage": 88.82, "elapsed_time": "2:09:57", "remaining_time": "0:16:21", "throughput": 2840.82, "total_tokens": 22151840} {"current_steps": 33900, "total_steps": 38160, "loss": 0.009, "lr": 1.875106125862941e-06, "epoch": 17.767295597484278, "percentage": 88.84, "elapsed_time": "2:09:58", "remaining_time": "0:16:20", "throughput": 2840.89, "total_tokens": 22155616} {"current_steps": 33905, "total_steps": 38160, "loss": 0.0028, "lr": 1.870763774454057e-06, "epoch": 17.76991614255765, "percentage": 88.85, "elapsed_time": "2:09:59", "remaining_time": "0:16:18", "throughput": 2840.86, "total_tokens": 22158656} {"current_steps": 33910, "total_steps": 38160, "loss": 0.0035, "lr": 1.8664262614175115e-06, "epoch": 17.77253668763103, "percentage": 88.86, "elapsed_time": "2:10:01", "remaining_time": "0:16:17", "throughput": 2840.78, "total_tokens": 22161152} {"current_steps": 33915, "total_steps": 38160, "loss": 0.009, "lr": 1.862093587660671e-06, "epoch": 17.7751572327044, "percentage": 88.88, "elapsed_time": "2:10:02", "remaining_time": "0:16:16", "throughput": 2840.82, "total_tokens": 22164544} {"current_steps": 33920, "total_steps": 38160, "loss": 0.0121, "lr": 1.8577657540898851e-06, "epoch": 17.77777777777778, "percentage": 88.89, "elapsed_time": "2:10:03", "remaining_time": "0:16:15", "throughput": 2840.82, "total_tokens": 22167712} {"current_steps": 33925, "total_steps": 38160, "loss": 0.0116, "lr": 1.8534427616104798e-06, "epoch": 17.780398322851152, "percentage": 88.9, "elapsed_time": "2:10:04", "remaining_time": "0:16:14", "throughput": 2840.92, "total_tokens": 22171648} {"current_steps": 33930, "total_steps": 38160, "loss": 0.0838, "lr": 1.8491246111267846e-06, "epoch": 17.78301886792453, "percentage": 88.92, "elapsed_time": "2:10:06", "remaining_time": "0:16:13", "throughput": 2841.18, "total_tokens": 22178912} {"current_steps": 33935, "total_steps": 38160, "loss": 0.0227, "lr": 1.8448113035420934e-06, "epoch": 17.785639412997902, "percentage": 88.93, "elapsed_time": "2:10:07", "remaining_time": "0:16:12", "throughput": 2841.14, "total_tokens": 22181568} {"current_steps": 33940, "total_steps": 38160, "loss": 0.0036, "lr": 1.840502839758712e-06, "epoch": 17.78825995807128, "percentage": 88.94, "elapsed_time": "2:10:08", "remaining_time": "0:16:10", "throughput": 2841.15, "total_tokens": 22185408} {"current_steps": 33945, "total_steps": 38160, "loss": 0.0064, "lr": 1.8361992206779226e-06, "epoch": 17.790880503144653, "percentage": 88.95, "elapsed_time": "2:10:09", "remaining_time": "0:16:09", "throughput": 2841.12, "total_tokens": 22188224} {"current_steps": 33950, "total_steps": 38160, "loss": 0.0079, "lr": 1.8319004471999856e-06, "epoch": 17.79350104821803, "percentage": 88.97, "elapsed_time": "2:10:10", "remaining_time": "0:16:08", "throughput": 2841.05, "total_tokens": 22190688} {"current_steps": 33955, "total_steps": 38160, "loss": 0.0098, "lr": 1.8276065202241592e-06, "epoch": 17.796121593291403, "percentage": 88.98, "elapsed_time": "2:10:11", "remaining_time": "0:16:07", "throughput": 2840.97, "total_tokens": 22193184} {"current_steps": 33960, "total_steps": 38160, "loss": 0.0033, "lr": 1.8233174406486863e-06, "epoch": 17.79874213836478, "percentage": 88.99, "elapsed_time": "2:10:12", "remaining_time": "0:16:06", "throughput": 2840.88, "total_tokens": 22195520} {"current_steps": 33965, "total_steps": 38160, "loss": 0.0054, "lr": 1.8190332093707907e-06, "epoch": 17.801362683438157, "percentage": 89.01, "elapsed_time": "2:10:14", "remaining_time": "0:16:05", "throughput": 2840.82, "total_tokens": 22198208} {"current_steps": 33970, "total_steps": 38160, "loss": 0.0098, "lr": 1.8147538272866833e-06, "epoch": 17.80398322851153, "percentage": 89.02, "elapsed_time": "2:10:15", "remaining_time": "0:16:03", "throughput": 2840.87, "total_tokens": 22201792} {"current_steps": 33975, "total_steps": 38160, "loss": 0.0156, "lr": 1.8104792952915672e-06, "epoch": 17.806603773584907, "percentage": 89.03, "elapsed_time": "2:10:16", "remaining_time": "0:16:02", "throughput": 2840.92, "total_tokens": 22205632} {"current_steps": 33980, "total_steps": 38160, "loss": 0.003, "lr": 1.8062096142796192e-06, "epoch": 17.80922431865828, "percentage": 89.05, "elapsed_time": "2:10:17", "remaining_time": "0:16:01", "throughput": 2840.86, "total_tokens": 22208192} {"current_steps": 33985, "total_steps": 38160, "loss": 0.0112, "lr": 1.8019447851440163e-06, "epoch": 17.811844863731658, "percentage": 89.06, "elapsed_time": "2:10:18", "remaining_time": "0:16:00", "throughput": 2840.87, "total_tokens": 22211584} {"current_steps": 33990, "total_steps": 38160, "loss": 0.0204, "lr": 1.7976848087769032e-06, "epoch": 17.81446540880503, "percentage": 89.07, "elapsed_time": "2:10:19", "remaining_time": "0:15:59", "throughput": 2840.95, "total_tokens": 22215360} {"current_steps": 33995, "total_steps": 38160, "loss": 0.0202, "lr": 1.79342968606942e-06, "epoch": 17.817085953878408, "percentage": 89.09, "elapsed_time": "2:10:20", "remaining_time": "0:15:58", "throughput": 2840.97, "total_tokens": 22218848} {"current_steps": 34000, "total_steps": 38160, "loss": 0.0062, "lr": 1.7891794179116933e-06, "epoch": 17.81970649895178, "percentage": 89.1, "elapsed_time": "2:10:21", "remaining_time": "0:15:57", "throughput": 2841.1, "total_tokens": 22222880} {"current_steps": 34005, "total_steps": 38160, "loss": 0.0273, "lr": 1.7849340051928316e-06, "epoch": 17.822327044025158, "percentage": 89.11, "elapsed_time": "2:10:23", "remaining_time": "0:15:55", "throughput": 2841.27, "total_tokens": 22229120} {"current_steps": 34010, "total_steps": 38160, "loss": 0.008, "lr": 1.780693448800927e-06, "epoch": 17.82494758909853, "percentage": 89.12, "elapsed_time": "2:10:24", "remaining_time": "0:15:54", "throughput": 2841.29, "total_tokens": 22232352} {"current_steps": 34015, "total_steps": 38160, "loss": 0.0078, "lr": 1.7764577496230478e-06, "epoch": 17.82756813417191, "percentage": 89.14, "elapsed_time": "2:10:26", "remaining_time": "0:15:53", "throughput": 2841.44, "total_tokens": 22237856} {"current_steps": 34020, "total_steps": 38160, "loss": 0.0131, "lr": 1.7722269085452602e-06, "epoch": 17.830188679245282, "percentage": 89.15, "elapsed_time": "2:10:27", "remaining_time": "0:15:52", "throughput": 2841.44, "total_tokens": 22240992} {"current_steps": 34025, "total_steps": 38160, "loss": 0.0023, "lr": 1.7680009264526038e-06, "epoch": 17.83280922431866, "percentage": 89.16, "elapsed_time": "2:10:28", "remaining_time": "0:15:51", "throughput": 2841.39, "total_tokens": 22243776} {"current_steps": 34030, "total_steps": 38160, "loss": 0.0018, "lr": 1.7637798042291126e-06, "epoch": 17.835429769392032, "percentage": 89.18, "elapsed_time": "2:10:29", "remaining_time": "0:15:50", "throughput": 2841.33, "total_tokens": 22246592} {"current_steps": 34035, "total_steps": 38160, "loss": 0.0038, "lr": 1.7595635427577944e-06, "epoch": 17.83805031446541, "percentage": 89.19, "elapsed_time": "2:10:30", "remaining_time": "0:15:49", "throughput": 2841.33, "total_tokens": 22249664} {"current_steps": 34040, "total_steps": 38160, "loss": 0.0041, "lr": 1.7553521429206465e-06, "epoch": 17.840670859538783, "percentage": 89.2, "elapsed_time": "2:10:31", "remaining_time": "0:15:47", "throughput": 2841.4, "total_tokens": 22253312} {"current_steps": 34045, "total_steps": 38160, "loss": 0.0152, "lr": 1.7511456055986335e-06, "epoch": 17.84329140461216, "percentage": 89.22, "elapsed_time": "2:10:33", "remaining_time": "0:15:46", "throughput": 2841.4, "total_tokens": 22256768} {"current_steps": 34050, "total_steps": 38160, "loss": 0.0029, "lr": 1.746943931671724e-06, "epoch": 17.845911949685533, "percentage": 89.23, "elapsed_time": "2:10:34", "remaining_time": "0:15:45", "throughput": 2841.43, "total_tokens": 22260224} {"current_steps": 34055, "total_steps": 38160, "loss": 0.0103, "lr": 1.742747122018859e-06, "epoch": 17.84853249475891, "percentage": 89.24, "elapsed_time": "2:10:35", "remaining_time": "0:15:44", "throughput": 2841.4, "total_tokens": 22262912} {"current_steps": 34060, "total_steps": 38160, "loss": 0.0047, "lr": 1.738555177517967e-06, "epoch": 17.851153039832283, "percentage": 89.26, "elapsed_time": "2:10:36", "remaining_time": "0:15:43", "throughput": 2841.42, "total_tokens": 22266240} {"current_steps": 34065, "total_steps": 38160, "loss": 0.0118, "lr": 1.734368099045952e-06, "epoch": 17.85377358490566, "percentage": 89.27, "elapsed_time": "2:10:37", "remaining_time": "0:15:42", "throughput": 2841.43, "total_tokens": 22269472} {"current_steps": 34070, "total_steps": 38160, "loss": 0.0062, "lr": 1.730185887478697e-06, "epoch": 17.856394129979037, "percentage": 89.28, "elapsed_time": "2:10:38", "remaining_time": "0:15:40", "throughput": 2841.48, "total_tokens": 22273184} {"current_steps": 34075, "total_steps": 38160, "loss": 0.0238, "lr": 1.7260085436910794e-06, "epoch": 17.85901467505241, "percentage": 89.3, "elapsed_time": "2:10:40", "remaining_time": "0:15:39", "throughput": 2841.66, "total_tokens": 22280032} {"current_steps": 34080, "total_steps": 38160, "loss": 0.0177, "lr": 1.7218360685569506e-06, "epoch": 17.861635220125788, "percentage": 89.31, "elapsed_time": "2:10:41", "remaining_time": "0:15:38", "throughput": 2841.76, "total_tokens": 22284128} {"current_steps": 34085, "total_steps": 38160, "loss": 0.003, "lr": 1.7176684629491513e-06, "epoch": 17.86425576519916, "percentage": 89.32, "elapsed_time": "2:10:42", "remaining_time": "0:15:37", "throughput": 2841.72, "total_tokens": 22286880} {"current_steps": 34090, "total_steps": 38160, "loss": 0.0031, "lr": 1.7135057277394868e-06, "epoch": 17.866876310272538, "percentage": 89.33, "elapsed_time": "2:10:43", "remaining_time": "0:15:36", "throughput": 2841.71, "total_tokens": 22290016} {"current_steps": 34095, "total_steps": 38160, "loss": 0.0156, "lr": 1.7093478637987548e-06, "epoch": 17.86949685534591, "percentage": 89.35, "elapsed_time": "2:10:45", "remaining_time": "0:15:35", "throughput": 2841.83, "total_tokens": 22294688} {"current_steps": 34100, "total_steps": 38160, "loss": 0.0068, "lr": 1.7051948719967375e-06, "epoch": 17.872117400419288, "percentage": 89.36, "elapsed_time": "2:10:46", "remaining_time": "0:15:34", "throughput": 2841.85, "total_tokens": 22297856} {"current_steps": 34105, "total_steps": 38160, "loss": 0.0154, "lr": 1.7010467532021901e-06, "epoch": 17.87473794549266, "percentage": 89.37, "elapsed_time": "2:10:47", "remaining_time": "0:15:33", "throughput": 2841.87, "total_tokens": 22301024} {"current_steps": 34110, "total_steps": 38160, "loss": 0.0061, "lr": 1.6969035082828544e-06, "epoch": 17.87735849056604, "percentage": 89.39, "elapsed_time": "2:10:48", "remaining_time": "0:15:31", "throughput": 2841.8, "total_tokens": 22303456} {"current_steps": 34115, "total_steps": 38160, "loss": 0.0038, "lr": 1.692765138105451e-06, "epoch": 17.879979035639412, "percentage": 89.4, "elapsed_time": "2:10:49", "remaining_time": "0:15:30", "throughput": 2841.78, "total_tokens": 22306528} {"current_steps": 34120, "total_steps": 38160, "loss": 0.0069, "lr": 1.6886316435356792e-06, "epoch": 17.88259958071279, "percentage": 89.41, "elapsed_time": "2:10:50", "remaining_time": "0:15:29", "throughput": 2841.82, "total_tokens": 22309824} {"current_steps": 34125, "total_steps": 38160, "loss": 0.003, "lr": 1.6845030254382138e-06, "epoch": 17.885220125786162, "percentage": 89.43, "elapsed_time": "2:10:51", "remaining_time": "0:15:28", "throughput": 2841.84, "total_tokens": 22313024} {"current_steps": 34130, "total_steps": 38160, "loss": 0.0052, "lr": 1.6803792846767197e-06, "epoch": 17.88784067085954, "percentage": 89.44, "elapsed_time": "2:10:52", "remaining_time": "0:15:27", "throughput": 2841.79, "total_tokens": 22315584} {"current_steps": 34135, "total_steps": 38160, "loss": 0.0045, "lr": 1.6762604221138316e-06, "epoch": 17.890461215932913, "percentage": 89.45, "elapsed_time": "2:10:53", "remaining_time": "0:15:26", "throughput": 2841.73, "total_tokens": 22318144} {"current_steps": 34140, "total_steps": 38160, "loss": 0.0058, "lr": 1.6721464386111774e-06, "epoch": 17.89308176100629, "percentage": 89.47, "elapsed_time": "2:10:54", "remaining_time": "0:15:24", "throughput": 2841.68, "total_tokens": 22320800} {"current_steps": 34145, "total_steps": 38160, "loss": 0.119, "lr": 1.6680373350293516e-06, "epoch": 17.895702306079663, "percentage": 89.48, "elapsed_time": "2:10:55", "remaining_time": "0:15:23", "throughput": 2841.7, "total_tokens": 22324064} {"current_steps": 34150, "total_steps": 38160, "loss": 0.0022, "lr": 1.6639331122279223e-06, "epoch": 17.89832285115304, "percentage": 89.49, "elapsed_time": "2:10:57", "remaining_time": "0:15:22", "throughput": 2841.67, "total_tokens": 22327104} {"current_steps": 34155, "total_steps": 38160, "loss": 0.0035, "lr": 1.6598337710654583e-06, "epoch": 17.900943396226417, "percentage": 89.5, "elapsed_time": "2:10:58", "remaining_time": "0:15:21", "throughput": 2841.72, "total_tokens": 22330528} {"current_steps": 34160, "total_steps": 38160, "loss": 0.0055, "lr": 1.6557393123994874e-06, "epoch": 17.90356394129979, "percentage": 89.52, "elapsed_time": "2:10:59", "remaining_time": "0:15:20", "throughput": 2841.71, "total_tokens": 22333472} {"current_steps": 34165, "total_steps": 38160, "loss": 0.0041, "lr": 1.651649737086533e-06, "epoch": 17.906184486373167, "percentage": 89.53, "elapsed_time": "2:11:00", "remaining_time": "0:15:19", "throughput": 2841.68, "total_tokens": 22336192} {"current_steps": 34170, "total_steps": 38160, "loss": 0.0052, "lr": 1.6475650459820774e-06, "epoch": 17.90880503144654, "percentage": 89.54, "elapsed_time": "2:11:01", "remaining_time": "0:15:17", "throughput": 2841.6, "total_tokens": 22338720} {"current_steps": 34175, "total_steps": 38160, "loss": 0.004, "lr": 1.643485239940598e-06, "epoch": 17.911425576519918, "percentage": 89.56, "elapsed_time": "2:11:02", "remaining_time": "0:15:16", "throughput": 2841.53, "total_tokens": 22341152} {"current_steps": 34180, "total_steps": 38160, "loss": 0.0068, "lr": 1.6394103198155375e-06, "epoch": 17.91404612159329, "percentage": 89.57, "elapsed_time": "2:11:03", "remaining_time": "0:15:15", "throughput": 2841.52, "total_tokens": 22344352} {"current_steps": 34185, "total_steps": 38160, "loss": 0.0023, "lr": 1.6353402864593276e-06, "epoch": 17.916666666666668, "percentage": 89.58, "elapsed_time": "2:11:04", "remaining_time": "0:15:14", "throughput": 2841.47, "total_tokens": 22346944} {"current_steps": 34190, "total_steps": 38160, "loss": 0.012, "lr": 1.6312751407233706e-06, "epoch": 17.91928721174004, "percentage": 89.6, "elapsed_time": "2:11:05", "remaining_time": "0:15:13", "throughput": 2841.56, "total_tokens": 22351040} {"current_steps": 34195, "total_steps": 38160, "loss": 0.0217, "lr": 1.6272148834580559e-06, "epoch": 17.921907756813418, "percentage": 89.61, "elapsed_time": "2:11:06", "remaining_time": "0:15:12", "throughput": 2841.52, "total_tokens": 22353728} {"current_steps": 34200, "total_steps": 38160, "loss": 0.0098, "lr": 1.6231595155127317e-06, "epoch": 17.92452830188679, "percentage": 89.62, "elapsed_time": "2:11:07", "remaining_time": "0:15:11", "throughput": 2841.54, "total_tokens": 22356928} {"current_steps": 34205, "total_steps": 38160, "loss": 0.0023, "lr": 1.6191090377357414e-06, "epoch": 17.92714884696017, "percentage": 89.64, "elapsed_time": "2:11:08", "remaining_time": "0:15:09", "throughput": 2841.43, "total_tokens": 22359168} {"current_steps": 34210, "total_steps": 38160, "loss": 0.0061, "lr": 1.6150634509743939e-06, "epoch": 17.929769392033542, "percentage": 89.65, "elapsed_time": "2:11:10", "remaining_time": "0:15:08", "throughput": 2841.43, "total_tokens": 22362400} {"current_steps": 34215, "total_steps": 38160, "loss": 0.0036, "lr": 1.611022756074984e-06, "epoch": 17.93238993710692, "percentage": 89.66, "elapsed_time": "2:11:11", "remaining_time": "0:15:07", "throughput": 2841.44, "total_tokens": 22365408} {"current_steps": 34220, "total_steps": 38160, "loss": 0.0078, "lr": 1.606986953882783e-06, "epoch": 17.935010482180292, "percentage": 89.68, "elapsed_time": "2:11:12", "remaining_time": "0:15:06", "throughput": 2841.43, "total_tokens": 22368768} {"current_steps": 34225, "total_steps": 38160, "loss": 0.0239, "lr": 1.6029560452420238e-06, "epoch": 17.93763102725367, "percentage": 89.69, "elapsed_time": "2:11:13", "remaining_time": "0:15:05", "throughput": 2841.47, "total_tokens": 22372128} {"current_steps": 34230, "total_steps": 38160, "loss": 0.0029, "lr": 1.5989300309959377e-06, "epoch": 17.940251572327043, "percentage": 89.7, "elapsed_time": "2:11:14", "remaining_time": "0:15:04", "throughput": 2841.51, "total_tokens": 22375520} {"current_steps": 34235, "total_steps": 38160, "loss": 0.0214, "lr": 1.5949089119867116e-06, "epoch": 17.94287211740042, "percentage": 89.71, "elapsed_time": "2:11:15", "remaining_time": "0:15:02", "throughput": 2841.51, "total_tokens": 22378656} {"current_steps": 34240, "total_steps": 38160, "loss": 0.0069, "lr": 1.5908926890555204e-06, "epoch": 17.945492662473793, "percentage": 89.73, "elapsed_time": "2:11:16", "remaining_time": "0:15:01", "throughput": 2841.52, "total_tokens": 22381888} {"current_steps": 34245, "total_steps": 38160, "loss": 0.0051, "lr": 1.5868813630425167e-06, "epoch": 17.94811320754717, "percentage": 89.74, "elapsed_time": "2:11:17", "remaining_time": "0:15:00", "throughput": 2841.52, "total_tokens": 22384928} {"current_steps": 34250, "total_steps": 38160, "loss": 0.0021, "lr": 1.5828749347868183e-06, "epoch": 17.950733752620543, "percentage": 89.75, "elapsed_time": "2:11:18", "remaining_time": "0:14:59", "throughput": 2841.52, "total_tokens": 22388096} {"current_steps": 34255, "total_steps": 38160, "loss": 0.0026, "lr": 1.5788734051265268e-06, "epoch": 17.95335429769392, "percentage": 89.77, "elapsed_time": "2:11:20", "remaining_time": "0:14:58", "throughput": 2841.69, "total_tokens": 22393632} {"current_steps": 34260, "total_steps": 38160, "loss": 0.0071, "lr": 1.5748767748987231e-06, "epoch": 17.955974842767297, "percentage": 89.78, "elapsed_time": "2:11:21", "remaining_time": "0:14:57", "throughput": 2841.68, "total_tokens": 22396768} {"current_steps": 34265, "total_steps": 38160, "loss": 0.0031, "lr": 1.5708850449394436e-06, "epoch": 17.95859538784067, "percentage": 89.79, "elapsed_time": "2:11:22", "remaining_time": "0:14:56", "throughput": 2841.66, "total_tokens": 22399776} {"current_steps": 34270, "total_steps": 38160, "loss": 0.0119, "lr": 1.5668982160837176e-06, "epoch": 17.961215932914047, "percentage": 89.81, "elapsed_time": "2:11:23", "remaining_time": "0:14:54", "throughput": 2841.7, "total_tokens": 22403104} {"current_steps": 34275, "total_steps": 38160, "loss": 0.0036, "lr": 1.562916289165553e-06, "epoch": 17.96383647798742, "percentage": 89.82, "elapsed_time": "2:11:24", "remaining_time": "0:14:53", "throughput": 2841.69, "total_tokens": 22406592} {"current_steps": 34280, "total_steps": 38160, "loss": 0.0122, "lr": 1.5589392650179114e-06, "epoch": 17.966457023060798, "percentage": 89.83, "elapsed_time": "2:11:26", "remaining_time": "0:14:52", "throughput": 2841.86, "total_tokens": 22411264} {"current_steps": 34285, "total_steps": 38160, "loss": 0.0062, "lr": 1.5549671444727437e-06, "epoch": 17.96907756813417, "percentage": 89.85, "elapsed_time": "2:11:27", "remaining_time": "0:14:51", "throughput": 2841.92, "total_tokens": 22414976} {"current_steps": 34290, "total_steps": 38160, "loss": 0.0318, "lr": 1.55099992836098e-06, "epoch": 17.971698113207548, "percentage": 89.86, "elapsed_time": "2:11:28", "remaining_time": "0:14:50", "throughput": 2841.87, "total_tokens": 22418016} {"current_steps": 34295, "total_steps": 38160, "loss": 0.0131, "lr": 1.5470376175125061e-06, "epoch": 17.97431865828092, "percentage": 89.87, "elapsed_time": "2:11:29", "remaining_time": "0:14:49", "throughput": 2841.92, "total_tokens": 22421408} {"current_steps": 34300, "total_steps": 38160, "loss": 0.0638, "lr": 1.5430802127562038e-06, "epoch": 17.9769392033543, "percentage": 89.88, "elapsed_time": "2:11:30", "remaining_time": "0:14:47", "throughput": 2841.81, "total_tokens": 22423744} {"current_steps": 34305, "total_steps": 38160, "loss": 0.0057, "lr": 1.5391277149199023e-06, "epoch": 17.979559748427672, "percentage": 89.9, "elapsed_time": "2:11:32", "remaining_time": "0:14:46", "throughput": 2841.9, "total_tokens": 22428672} {"current_steps": 34310, "total_steps": 38160, "loss": 0.0045, "lr": 1.5351801248304292e-06, "epoch": 17.98218029350105, "percentage": 89.91, "elapsed_time": "2:11:33", "remaining_time": "0:14:45", "throughput": 2841.88, "total_tokens": 22431648} {"current_steps": 34315, "total_steps": 38160, "loss": 0.0022, "lr": 1.5312374433135767e-06, "epoch": 17.984800838574422, "percentage": 89.92, "elapsed_time": "2:11:34", "remaining_time": "0:14:44", "throughput": 2841.82, "total_tokens": 22434496} {"current_steps": 34320, "total_steps": 38160, "loss": 0.002, "lr": 1.5272996711941018e-06, "epoch": 17.9874213836478, "percentage": 89.94, "elapsed_time": "2:11:35", "remaining_time": "0:14:43", "throughput": 2841.89, "total_tokens": 22438432} {"current_steps": 34325, "total_steps": 38160, "loss": 0.0062, "lr": 1.5233668092957482e-06, "epoch": 17.990041928721173, "percentage": 89.95, "elapsed_time": "2:11:36", "remaining_time": "0:14:42", "throughput": 2841.9, "total_tokens": 22441600} {"current_steps": 34330, "total_steps": 38160, "loss": 0.0023, "lr": 1.5194388584412217e-06, "epoch": 17.99266247379455, "percentage": 89.96, "elapsed_time": "2:11:37", "remaining_time": "0:14:41", "throughput": 2841.82, "total_tokens": 22444160} {"current_steps": 34335, "total_steps": 38160, "loss": 0.0045, "lr": 1.5155158194522013e-06, "epoch": 17.995283018867923, "percentage": 89.98, "elapsed_time": "2:11:38", "remaining_time": "0:14:39", "throughput": 2841.81, "total_tokens": 22447328} {"current_steps": 34340, "total_steps": 38160, "loss": 0.0047, "lr": 1.5115976931493498e-06, "epoch": 17.9979035639413, "percentage": 89.99, "elapsed_time": "2:11:40", "remaining_time": "0:14:38", "throughput": 2841.77, "total_tokens": 22450112} {"current_steps": 34344, "total_steps": 38160, "eval_loss": 1.5930230617523193, "epoch": 18.0, "percentage": 90.0, "elapsed_time": "2:11:52", "remaining_time": "0:14:39", "throughput": 2837.42, "total_tokens": 22451928} {"current_steps": 34345, "total_steps": 38160, "loss": 0.0024, "lr": 1.5076844803522922e-06, "epoch": 18.000524109014677, "percentage": 90.0, "elapsed_time": "2:11:56", "remaining_time": "0:14:39", "throughput": 2836.18, "total_tokens": 22452408} {"current_steps": 34350, "total_steps": 38160, "loss": 0.0125, "lr": 1.5037761818796236e-06, "epoch": 18.00314465408805, "percentage": 90.02, "elapsed_time": "2:11:57", "remaining_time": "0:14:38", "throughput": 2836.22, "total_tokens": 22456184} {"current_steps": 34355, "total_steps": 38160, "loss": 0.0032, "lr": 1.4998727985489235e-06, "epoch": 18.005765199161427, "percentage": 90.03, "elapsed_time": "2:11:58", "remaining_time": "0:14:37", "throughput": 2836.17, "total_tokens": 22458968} {"current_steps": 34360, "total_steps": 38160, "loss": 0.0072, "lr": 1.4959743311767249e-06, "epoch": 18.0083857442348, "percentage": 90.04, "elapsed_time": "2:11:59", "remaining_time": "0:14:35", "throughput": 2836.22, "total_tokens": 22462392} {"current_steps": 34365, "total_steps": 38160, "loss": 0.0081, "lr": 1.4920807805785502e-06, "epoch": 18.011006289308177, "percentage": 90.06, "elapsed_time": "2:12:01", "remaining_time": "0:14:34", "throughput": 2836.29, "total_tokens": 22466360} {"current_steps": 34370, "total_steps": 38160, "loss": 0.0052, "lr": 1.4881921475688815e-06, "epoch": 18.01362683438155, "percentage": 90.07, "elapsed_time": "2:12:02", "remaining_time": "0:14:33", "throughput": 2836.33, "total_tokens": 22470104} {"current_steps": 34375, "total_steps": 38160, "loss": 0.0038, "lr": 1.4843084329611844e-06, "epoch": 18.016247379454928, "percentage": 90.08, "elapsed_time": "2:12:03", "remaining_time": "0:14:32", "throughput": 2836.32, "total_tokens": 22473144} {"current_steps": 34380, "total_steps": 38160, "loss": 0.0224, "lr": 1.480429637567879e-06, "epoch": 18.0188679245283, "percentage": 90.09, "elapsed_time": "2:12:04", "remaining_time": "0:14:31", "throughput": 2836.23, "total_tokens": 22475640} {"current_steps": 34385, "total_steps": 38160, "loss": 0.0022, "lr": 1.4765557622003684e-06, "epoch": 18.021488469601678, "percentage": 90.11, "elapsed_time": "2:12:05", "remaining_time": "0:14:30", "throughput": 2836.21, "total_tokens": 22478712} {"current_steps": 34390, "total_steps": 38160, "loss": 0.0167, "lr": 1.4726868076690186e-06, "epoch": 18.02410901467505, "percentage": 90.12, "elapsed_time": "2:12:06", "remaining_time": "0:14:28", "throughput": 2836.16, "total_tokens": 22481624} {"current_steps": 34395, "total_steps": 38160, "loss": 0.0032, "lr": 1.4688227747831767e-06, "epoch": 18.02672955974843, "percentage": 90.13, "elapsed_time": "2:12:07", "remaining_time": "0:14:27", "throughput": 2836.16, "total_tokens": 22484664} {"current_steps": 34400, "total_steps": 38160, "loss": 0.0029, "lr": 1.4649636643511573e-06, "epoch": 18.029350104821802, "percentage": 90.15, "elapsed_time": "2:12:08", "remaining_time": "0:14:26", "throughput": 2836.08, "total_tokens": 22487128} {"current_steps": 34405, "total_steps": 38160, "loss": 0.0051, "lr": 1.4611094771802364e-06, "epoch": 18.03197064989518, "percentage": 90.16, "elapsed_time": "2:12:10", "remaining_time": "0:14:25", "throughput": 2836.0, "total_tokens": 22489528} {"current_steps": 34410, "total_steps": 38160, "loss": 0.0495, "lr": 1.457260214076664e-06, "epoch": 18.034591194968552, "percentage": 90.17, "elapsed_time": "2:12:11", "remaining_time": "0:14:24", "throughput": 2836.13, "total_tokens": 22493560} {"current_steps": 34415, "total_steps": 38160, "loss": 0.004, "lr": 1.4534158758456623e-06, "epoch": 18.03721174004193, "percentage": 90.19, "elapsed_time": "2:12:12", "remaining_time": "0:14:23", "throughput": 2836.1, "total_tokens": 22496408} {"current_steps": 34420, "total_steps": 38160, "loss": 0.0043, "lr": 1.4495764632914271e-06, "epoch": 18.039832285115303, "percentage": 90.2, "elapsed_time": "2:12:13", "remaining_time": "0:14:22", "throughput": 2836.14, "total_tokens": 22500440} {"current_steps": 34425, "total_steps": 38160, "loss": 0.0035, "lr": 1.4457419772171215e-06, "epoch": 18.04245283018868, "percentage": 90.21, "elapsed_time": "2:12:14", "remaining_time": "0:14:20", "throughput": 2836.16, "total_tokens": 22503640} {"current_steps": 34430, "total_steps": 38160, "loss": 0.0257, "lr": 1.4419124184248733e-06, "epoch": 18.045073375262053, "percentage": 90.23, "elapsed_time": "2:12:15", "remaining_time": "0:14:19", "throughput": 2836.28, "total_tokens": 22507768} {"current_steps": 34435, "total_steps": 38160, "loss": 0.0041, "lr": 1.4380877877157834e-06, "epoch": 18.04769392033543, "percentage": 90.24, "elapsed_time": "2:12:16", "remaining_time": "0:14:18", "throughput": 2836.34, "total_tokens": 22511256} {"current_steps": 34440, "total_steps": 38160, "loss": 0.0148, "lr": 1.4342680858899143e-06, "epoch": 18.050314465408807, "percentage": 90.25, "elapsed_time": "2:12:17", "remaining_time": "0:14:17", "throughput": 2836.4, "total_tokens": 22514872} {"current_steps": 34445, "total_steps": 38160, "loss": 0.0018, "lr": 1.4304533137463134e-06, "epoch": 18.05293501048218, "percentage": 90.26, "elapsed_time": "2:12:18", "remaining_time": "0:14:16", "throughput": 2836.42, "total_tokens": 22518008} {"current_steps": 34450, "total_steps": 38160, "loss": 0.0022, "lr": 1.4266434720829808e-06, "epoch": 18.055555555555557, "percentage": 90.28, "elapsed_time": "2:12:19", "remaining_time": "0:14:15", "throughput": 2836.36, "total_tokens": 22520664} {"current_steps": 34455, "total_steps": 38160, "loss": 0.004, "lr": 1.4228385616968987e-06, "epoch": 18.05817610062893, "percentage": 90.29, "elapsed_time": "2:12:21", "remaining_time": "0:14:13", "throughput": 2836.28, "total_tokens": 22523096} {"current_steps": 34460, "total_steps": 38160, "loss": 0.0126, "lr": 1.419038583384008e-06, "epoch": 18.060796645702307, "percentage": 90.3, "elapsed_time": "2:12:22", "remaining_time": "0:14:12", "throughput": 2836.31, "total_tokens": 22526616} {"current_steps": 34465, "total_steps": 38160, "loss": 0.0056, "lr": 1.4152435379392148e-06, "epoch": 18.06341719077568, "percentage": 90.32, "elapsed_time": "2:12:23", "remaining_time": "0:14:11", "throughput": 2836.29, "total_tokens": 22529560} {"current_steps": 34470, "total_steps": 38160, "loss": 0.0126, "lr": 1.411453426156406e-06, "epoch": 18.066037735849058, "percentage": 90.33, "elapsed_time": "2:12:24", "remaining_time": "0:14:10", "throughput": 2836.32, "total_tokens": 22533016} {"current_steps": 34475, "total_steps": 38160, "loss": 0.0047, "lr": 1.4076682488284282e-06, "epoch": 18.06865828092243, "percentage": 90.34, "elapsed_time": "2:12:25", "remaining_time": "0:14:09", "throughput": 2836.2, "total_tokens": 22535416} {"current_steps": 34480, "total_steps": 38160, "loss": 0.0033, "lr": 1.4038880067470978e-06, "epoch": 18.071278825995808, "percentage": 90.36, "elapsed_time": "2:12:27", "remaining_time": "0:14:08", "throughput": 2836.1, "total_tokens": 22538936} {"current_steps": 34485, "total_steps": 38160, "loss": 0.0056, "lr": 1.400112700703196e-06, "epoch": 18.07389937106918, "percentage": 90.37, "elapsed_time": "2:12:28", "remaining_time": "0:14:07", "throughput": 2836.09, "total_tokens": 22541944} {"current_steps": 34490, "total_steps": 38160, "loss": 0.0058, "lr": 1.3963423314864805e-06, "epoch": 18.07651991614256, "percentage": 90.38, "elapsed_time": "2:12:29", "remaining_time": "0:14:05", "throughput": 2836.02, "total_tokens": 22544568} {"current_steps": 34495, "total_steps": 38160, "loss": 0.0022, "lr": 1.3925768998856587e-06, "epoch": 18.079140461215932, "percentage": 90.4, "elapsed_time": "2:12:30", "remaining_time": "0:14:04", "throughput": 2836.04, "total_tokens": 22547768} {"current_steps": 34500, "total_steps": 38160, "loss": 0.0048, "lr": 1.388816406688423e-06, "epoch": 18.08176100628931, "percentage": 90.41, "elapsed_time": "2:12:31", "remaining_time": "0:14:03", "throughput": 2836.02, "total_tokens": 22550776} {"current_steps": 34505, "total_steps": 38160, "loss": 0.0023, "lr": 1.3850608526814246e-06, "epoch": 18.084381551362682, "percentage": 90.42, "elapsed_time": "2:12:32", "remaining_time": "0:14:02", "throughput": 2836.06, "total_tokens": 22554392} {"current_steps": 34510, "total_steps": 38160, "loss": 0.0037, "lr": 1.3813102386502853e-06, "epoch": 18.08700209643606, "percentage": 90.44, "elapsed_time": "2:12:33", "remaining_time": "0:14:01", "throughput": 2836.03, "total_tokens": 22557304} {"current_steps": 34515, "total_steps": 38160, "loss": 0.0039, "lr": 1.3775645653795881e-06, "epoch": 18.089622641509433, "percentage": 90.45, "elapsed_time": "2:12:34", "remaining_time": "0:14:00", "throughput": 2836.05, "total_tokens": 22560536} {"current_steps": 34520, "total_steps": 38160, "loss": 0.0027, "lr": 1.373823833652882e-06, "epoch": 18.09224318658281, "percentage": 90.46, "elapsed_time": "2:12:36", "remaining_time": "0:13:58", "throughput": 2836.07, "total_tokens": 22563832} {"current_steps": 34525, "total_steps": 38160, "loss": 0.0035, "lr": 1.3700880442526876e-06, "epoch": 18.094863731656183, "percentage": 90.47, "elapsed_time": "2:12:37", "remaining_time": "0:13:57", "throughput": 2836.03, "total_tokens": 22566616} {"current_steps": 34530, "total_steps": 38160, "loss": 0.0203, "lr": 1.3663571979604884e-06, "epoch": 18.09748427672956, "percentage": 90.49, "elapsed_time": "2:12:38", "remaining_time": "0:13:56", "throughput": 2836.05, "total_tokens": 22569976} {"current_steps": 34535, "total_steps": 38160, "loss": 0.008, "lr": 1.3626312955567406e-06, "epoch": 18.100104821802937, "percentage": 90.5, "elapsed_time": "2:12:39", "remaining_time": "0:13:55", "throughput": 2836.06, "total_tokens": 22573112} {"current_steps": 34540, "total_steps": 38160, "loss": 0.0141, "lr": 1.358910337820854e-06, "epoch": 18.10272536687631, "percentage": 90.51, "elapsed_time": "2:12:40", "remaining_time": "0:13:54", "throughput": 2836.07, "total_tokens": 22576152} {"current_steps": 34545, "total_steps": 38160, "loss": 0.0154, "lr": 1.3551943255312172e-06, "epoch": 18.105345911949687, "percentage": 90.53, "elapsed_time": "2:12:41", "remaining_time": "0:13:53", "throughput": 2836.11, "total_tokens": 22579672} {"current_steps": 34550, "total_steps": 38160, "loss": 0.0049, "lr": 1.3514832594651694e-06, "epoch": 18.10796645702306, "percentage": 90.54, "elapsed_time": "2:12:42", "remaining_time": "0:13:51", "throughput": 2836.15, "total_tokens": 22583096} {"current_steps": 34555, "total_steps": 38160, "loss": 0.0147, "lr": 1.347777140399026e-06, "epoch": 18.110587002096437, "percentage": 90.55, "elapsed_time": "2:12:43", "remaining_time": "0:13:50", "throughput": 2836.26, "total_tokens": 22587256} {"current_steps": 34560, "total_steps": 38160, "loss": 0.0221, "lr": 1.344075969108069e-06, "epoch": 18.11320754716981, "percentage": 90.57, "elapsed_time": "2:12:45", "remaining_time": "0:13:49", "throughput": 2836.32, "total_tokens": 22591352} {"current_steps": 34565, "total_steps": 38160, "loss": 0.0019, "lr": 1.3403797463665352e-06, "epoch": 18.115828092243188, "percentage": 90.58, "elapsed_time": "2:12:46", "remaining_time": "0:13:48", "throughput": 2836.29, "total_tokens": 22594040} {"current_steps": 34570, "total_steps": 38160, "loss": 0.0988, "lr": 1.3366884729476365e-06, "epoch": 18.11844863731656, "percentage": 90.59, "elapsed_time": "2:12:47", "remaining_time": "0:13:47", "throughput": 2836.27, "total_tokens": 22597208} {"current_steps": 34575, "total_steps": 38160, "loss": 0.0021, "lr": 1.3330021496235467e-06, "epoch": 18.121069182389938, "percentage": 90.61, "elapsed_time": "2:12:48", "remaining_time": "0:13:46", "throughput": 2836.31, "total_tokens": 22600536} {"current_steps": 34580, "total_steps": 38160, "loss": 0.0047, "lr": 1.3293207771653965e-06, "epoch": 18.12368972746331, "percentage": 90.62, "elapsed_time": "2:12:49", "remaining_time": "0:13:45", "throughput": 2836.25, "total_tokens": 22603160} {"current_steps": 34585, "total_steps": 38160, "loss": 0.0021, "lr": 1.3256443563432891e-06, "epoch": 18.12631027253669, "percentage": 90.63, "elapsed_time": "2:12:50", "remaining_time": "0:13:43", "throughput": 2836.25, "total_tokens": 22606328} {"current_steps": 34590, "total_steps": 38160, "loss": 0.0064, "lr": 1.3219728879262956e-06, "epoch": 18.128930817610062, "percentage": 90.64, "elapsed_time": "2:12:51", "remaining_time": "0:13:42", "throughput": 2836.28, "total_tokens": 22609624} {"current_steps": 34595, "total_steps": 38160, "loss": 0.0242, "lr": 1.3183063726824375e-06, "epoch": 18.13155136268344, "percentage": 90.66, "elapsed_time": "2:12:52", "remaining_time": "0:13:41", "throughput": 2836.27, "total_tokens": 22612728} {"current_steps": 34600, "total_steps": 38160, "loss": 0.0353, "lr": 1.3146448113787151e-06, "epoch": 18.134171907756812, "percentage": 90.67, "elapsed_time": "2:12:53", "remaining_time": "0:13:40", "throughput": 2836.25, "total_tokens": 22615640} {"current_steps": 34605, "total_steps": 38160, "loss": 0.0041, "lr": 1.3109882047810773e-06, "epoch": 18.13679245283019, "percentage": 90.68, "elapsed_time": "2:12:54", "remaining_time": "0:13:39", "throughput": 2836.2, "total_tokens": 22618360} {"current_steps": 34610, "total_steps": 38160, "loss": 0.006, "lr": 1.307336553654448e-06, "epoch": 18.139412997903563, "percentage": 90.7, "elapsed_time": "2:12:55", "remaining_time": "0:13:38", "throughput": 2836.26, "total_tokens": 22621976} {"current_steps": 34615, "total_steps": 38160, "loss": 0.0066, "lr": 1.303689858762716e-06, "epoch": 18.14203354297694, "percentage": 90.71, "elapsed_time": "2:12:57", "remaining_time": "0:13:36", "throughput": 2836.32, "total_tokens": 22626008} {"current_steps": 34620, "total_steps": 38160, "loss": 0.004, "lr": 1.3000481208687188e-06, "epoch": 18.144654088050313, "percentage": 90.72, "elapsed_time": "2:12:58", "remaining_time": "0:13:35", "throughput": 2836.32, "total_tokens": 22629368} {"current_steps": 34625, "total_steps": 38160, "loss": 0.0053, "lr": 1.2964113407342743e-06, "epoch": 18.14727463312369, "percentage": 90.74, "elapsed_time": "2:12:59", "remaining_time": "0:13:34", "throughput": 2836.28, "total_tokens": 22632440} {"current_steps": 34630, "total_steps": 38160, "loss": 0.0045, "lr": 1.292779519120152e-06, "epoch": 18.149895178197063, "percentage": 90.75, "elapsed_time": "2:13:00", "remaining_time": "0:13:33", "throughput": 2836.23, "total_tokens": 22635160} {"current_steps": 34635, "total_steps": 38160, "loss": 0.0183, "lr": 1.2891526567860856e-06, "epoch": 18.15251572327044, "percentage": 90.76, "elapsed_time": "2:13:01", "remaining_time": "0:13:32", "throughput": 2836.4, "total_tokens": 22639896} {"current_steps": 34640, "total_steps": 38160, "loss": 0.0042, "lr": 1.2855307544907825e-06, "epoch": 18.155136268343817, "percentage": 90.78, "elapsed_time": "2:13:03", "remaining_time": "0:13:31", "throughput": 2836.39, "total_tokens": 22642968} {"current_steps": 34645, "total_steps": 38160, "loss": 0.0038, "lr": 1.281913812991889e-06, "epoch": 18.15775681341719, "percentage": 90.79, "elapsed_time": "2:13:04", "remaining_time": "0:13:30", "throughput": 2836.42, "total_tokens": 22646456} {"current_steps": 34650, "total_steps": 38160, "loss": 0.0109, "lr": 1.2783018330460389e-06, "epoch": 18.160377358490567, "percentage": 90.8, "elapsed_time": "2:13:05", "remaining_time": "0:13:28", "throughput": 2836.53, "total_tokens": 22650648} {"current_steps": 34655, "total_steps": 38160, "loss": 0.0017, "lr": 1.2746948154088111e-06, "epoch": 18.16299790356394, "percentage": 90.81, "elapsed_time": "2:13:06", "remaining_time": "0:13:27", "throughput": 2836.56, "total_tokens": 22654296} {"current_steps": 34660, "total_steps": 38160, "loss": 0.0045, "lr": 1.2710927608347605e-06, "epoch": 18.165618448637318, "percentage": 90.83, "elapsed_time": "2:13:07", "remaining_time": "0:13:26", "throughput": 2836.61, "total_tokens": 22658072} {"current_steps": 34665, "total_steps": 38160, "loss": 0.0027, "lr": 1.2674956700773872e-06, "epoch": 18.16823899371069, "percentage": 90.84, "elapsed_time": "2:13:09", "remaining_time": "0:13:25", "throughput": 2836.6, "total_tokens": 22661752} {"current_steps": 34670, "total_steps": 38160, "loss": 0.0105, "lr": 1.2639035438891666e-06, "epoch": 18.170859538784068, "percentage": 90.85, "elapsed_time": "2:13:10", "remaining_time": "0:13:24", "throughput": 2836.64, "total_tokens": 22665112} {"current_steps": 34675, "total_steps": 38160, "loss": 0.0018, "lr": 1.260316383021526e-06, "epoch": 18.17348008385744, "percentage": 90.87, "elapsed_time": "2:13:11", "remaining_time": "0:13:23", "throughput": 2836.58, "total_tokens": 22667640} {"current_steps": 34680, "total_steps": 38160, "loss": 0.0076, "lr": 1.2567341882248645e-06, "epoch": 18.17610062893082, "percentage": 90.88, "elapsed_time": "2:13:12", "remaining_time": "0:13:21", "throughput": 2836.6, "total_tokens": 22670840} {"current_steps": 34685, "total_steps": 38160, "loss": 0.0042, "lr": 1.2531569602485305e-06, "epoch": 18.178721174004192, "percentage": 90.89, "elapsed_time": "2:13:13", "remaining_time": "0:13:20", "throughput": 2836.59, "total_tokens": 22673720} {"current_steps": 34690, "total_steps": 38160, "loss": 0.0081, "lr": 1.2495846998408445e-06, "epoch": 18.18134171907757, "percentage": 90.91, "elapsed_time": "2:13:14", "remaining_time": "0:13:19", "throughput": 2836.63, "total_tokens": 22676984} {"current_steps": 34695, "total_steps": 38160, "loss": 0.0141, "lr": 1.246017407749084e-06, "epoch": 18.183962264150942, "percentage": 90.92, "elapsed_time": "2:13:15", "remaining_time": "0:13:18", "throughput": 2836.67, "total_tokens": 22680216} {"current_steps": 34700, "total_steps": 38160, "loss": 0.0023, "lr": 1.2424550847194739e-06, "epoch": 18.18658280922432, "percentage": 90.93, "elapsed_time": "2:13:16", "remaining_time": "0:13:17", "throughput": 2836.71, "total_tokens": 22683448} {"current_steps": 34705, "total_steps": 38160, "loss": 0.0273, "lr": 1.2388977314972238e-06, "epoch": 18.189203354297693, "percentage": 90.95, "elapsed_time": "2:13:18", "remaining_time": "0:13:16", "throughput": 2836.88, "total_tokens": 22689912} {"current_steps": 34710, "total_steps": 38160, "loss": 0.0021, "lr": 1.235345348826486e-06, "epoch": 18.19182389937107, "percentage": 90.96, "elapsed_time": "2:13:19", "remaining_time": "0:13:15", "throughput": 2836.86, "total_tokens": 22692696} {"current_steps": 34715, "total_steps": 38160, "loss": 0.0021, "lr": 1.2317979374503825e-06, "epoch": 18.194444444444443, "percentage": 90.97, "elapsed_time": "2:13:20", "remaining_time": "0:13:13", "throughput": 2836.77, "total_tokens": 22695032} {"current_steps": 34720, "total_steps": 38160, "loss": 0.0041, "lr": 1.228255498110989e-06, "epoch": 18.19706498951782, "percentage": 90.99, "elapsed_time": "2:13:21", "remaining_time": "0:13:12", "throughput": 2836.82, "total_tokens": 22698712} {"current_steps": 34725, "total_steps": 38160, "loss": 0.0133, "lr": 1.224718031549338e-06, "epoch": 18.199685534591197, "percentage": 91.0, "elapsed_time": "2:13:22", "remaining_time": "0:13:11", "throughput": 2836.87, "total_tokens": 22702200} {"current_steps": 34730, "total_steps": 38160, "loss": 0.0015, "lr": 1.2211855385054344e-06, "epoch": 18.20230607966457, "percentage": 91.01, "elapsed_time": "2:13:23", "remaining_time": "0:13:10", "throughput": 2836.83, "total_tokens": 22704888} {"current_steps": 34735, "total_steps": 38160, "loss": 0.0036, "lr": 1.217658019718232e-06, "epoch": 18.204926624737947, "percentage": 91.02, "elapsed_time": "2:13:24", "remaining_time": "0:13:09", "throughput": 2836.82, "total_tokens": 22708280} {"current_steps": 34740, "total_steps": 38160, "loss": 0.0035, "lr": 1.2141354759256484e-06, "epoch": 18.20754716981132, "percentage": 91.04, "elapsed_time": "2:13:25", "remaining_time": "0:13:08", "throughput": 2836.83, "total_tokens": 22711384} {"current_steps": 34745, "total_steps": 38160, "loss": 0.0115, "lr": 1.2106179078645641e-06, "epoch": 18.210167714884697, "percentage": 91.05, "elapsed_time": "2:13:26", "remaining_time": "0:13:06", "throughput": 2836.86, "total_tokens": 22714712} {"current_steps": 34750, "total_steps": 38160, "loss": 0.0033, "lr": 1.2071053162708096e-06, "epoch": 18.21278825995807, "percentage": 91.06, "elapsed_time": "2:13:28", "remaining_time": "0:13:05", "throughput": 2836.83, "total_tokens": 22717432} {"current_steps": 34755, "total_steps": 38160, "loss": 0.0033, "lr": 1.203597701879175e-06, "epoch": 18.215408805031448, "percentage": 91.08, "elapsed_time": "2:13:29", "remaining_time": "0:13:04", "throughput": 2836.81, "total_tokens": 22720312} {"current_steps": 34760, "total_steps": 38160, "loss": 0.0284, "lr": 1.2000950654234177e-06, "epoch": 18.21802935010482, "percentage": 91.09, "elapsed_time": "2:13:31", "remaining_time": "0:13:03", "throughput": 2837.03, "total_tokens": 22727928} {"current_steps": 34765, "total_steps": 38160, "loss": 0.0027, "lr": 1.1965974076362491e-06, "epoch": 18.220649895178198, "percentage": 91.1, "elapsed_time": "2:13:32", "remaining_time": "0:13:02", "throughput": 2836.97, "total_tokens": 22730456} {"current_steps": 34770, "total_steps": 38160, "loss": 0.0104, "lr": 1.193104729249342e-06, "epoch": 18.22327044025157, "percentage": 91.12, "elapsed_time": "2:13:33", "remaining_time": "0:13:01", "throughput": 2836.94, "total_tokens": 22733240} {"current_steps": 34775, "total_steps": 38160, "loss": 0.0035, "lr": 1.189617030993323e-06, "epoch": 18.22589098532495, "percentage": 91.13, "elapsed_time": "2:13:34", "remaining_time": "0:13:00", "throughput": 2836.94, "total_tokens": 22736344} {"current_steps": 34780, "total_steps": 38160, "loss": 0.0043, "lr": 1.1861343135977753e-06, "epoch": 18.228511530398322, "percentage": 91.14, "elapsed_time": "2:13:35", "remaining_time": "0:12:58", "throughput": 2836.94, "total_tokens": 22739320} {"current_steps": 34785, "total_steps": 38160, "loss": 0.0059, "lr": 1.182656577791244e-06, "epoch": 18.2311320754717, "percentage": 91.16, "elapsed_time": "2:13:36", "remaining_time": "0:12:57", "throughput": 2836.99, "total_tokens": 22743000} {"current_steps": 34790, "total_steps": 38160, "loss": 0.0018, "lr": 1.1791838243012359e-06, "epoch": 18.233752620545072, "percentage": 91.17, "elapsed_time": "2:13:37", "remaining_time": "0:12:56", "throughput": 2836.95, "total_tokens": 22745752} {"current_steps": 34795, "total_steps": 38160, "loss": 0.0705, "lr": 1.1757160538542117e-06, "epoch": 18.23637316561845, "percentage": 91.18, "elapsed_time": "2:13:38", "remaining_time": "0:12:55", "throughput": 2836.91, "total_tokens": 22748504} {"current_steps": 34800, "total_steps": 38160, "loss": 0.004, "lr": 1.1722532671755882e-06, "epoch": 18.238993710691823, "percentage": 91.19, "elapsed_time": "2:13:39", "remaining_time": "0:12:54", "throughput": 2836.91, "total_tokens": 22751704} {"current_steps": 34805, "total_steps": 38160, "loss": 0.005, "lr": 1.168795464989736e-06, "epoch": 18.2416142557652, "percentage": 91.21, "elapsed_time": "2:13:40", "remaining_time": "0:12:53", "throughput": 2836.96, "total_tokens": 22755256} {"current_steps": 34810, "total_steps": 38160, "loss": 0.0244, "lr": 1.165342648019993e-06, "epoch": 18.244234800838573, "percentage": 91.22, "elapsed_time": "2:13:42", "remaining_time": "0:12:52", "throughput": 2837.01, "total_tokens": 22758616} {"current_steps": 34815, "total_steps": 38160, "loss": 0.0018, "lr": 1.1618948169886457e-06, "epoch": 18.24685534591195, "percentage": 91.23, "elapsed_time": "2:13:43", "remaining_time": "0:12:50", "throughput": 2836.96, "total_tokens": 22761432} {"current_steps": 34820, "total_steps": 38160, "loss": 0.016, "lr": 1.1584519726169446e-06, "epoch": 18.249475890985323, "percentage": 91.25, "elapsed_time": "2:13:44", "remaining_time": "0:12:49", "throughput": 2836.95, "total_tokens": 22764376} {"current_steps": 34825, "total_steps": 38160, "loss": 0.0074, "lr": 1.1550141156250942e-06, "epoch": 18.2520964360587, "percentage": 91.26, "elapsed_time": "2:13:45", "remaining_time": "0:12:48", "throughput": 2837.0, "total_tokens": 22768056} {"current_steps": 34830, "total_steps": 38160, "loss": 0.0229, "lr": 1.1515812467322556e-06, "epoch": 18.254716981132077, "percentage": 91.27, "elapsed_time": "2:13:46", "remaining_time": "0:12:47", "throughput": 2837.0, "total_tokens": 22771128} {"current_steps": 34835, "total_steps": 38160, "loss": 0.0018, "lr": 1.1481533666565375e-06, "epoch": 18.25733752620545, "percentage": 91.29, "elapsed_time": "2:13:47", "remaining_time": "0:12:46", "throughput": 2837.02, "total_tokens": 22774360} {"current_steps": 34840, "total_steps": 38160, "loss": 0.0051, "lr": 1.144730476115019e-06, "epoch": 18.259958071278827, "percentage": 91.3, "elapsed_time": "2:13:48", "remaining_time": "0:12:45", "throughput": 2837.15, "total_tokens": 22778712} {"current_steps": 34845, "total_steps": 38160, "loss": 0.0026, "lr": 1.1413125758237304e-06, "epoch": 18.2625786163522, "percentage": 91.31, "elapsed_time": "2:13:49", "remaining_time": "0:12:43", "throughput": 2837.09, "total_tokens": 22781368} {"current_steps": 34850, "total_steps": 38160, "loss": 0.0021, "lr": 1.1378996664976577e-06, "epoch": 18.265199161425578, "percentage": 91.33, "elapsed_time": "2:13:50", "remaining_time": "0:12:42", "throughput": 2837.04, "total_tokens": 22784120} {"current_steps": 34855, "total_steps": 38160, "loss": 0.01, "lr": 1.134491748850741e-06, "epoch": 18.26781970649895, "percentage": 91.34, "elapsed_time": "2:13:52", "remaining_time": "0:12:41", "throughput": 2837.03, "total_tokens": 22787160} {"current_steps": 34860, "total_steps": 38160, "loss": 0.0185, "lr": 1.13108882359588e-06, "epoch": 18.270440251572328, "percentage": 91.35, "elapsed_time": "2:13:53", "remaining_time": "0:12:40", "throughput": 2837.05, "total_tokens": 22790584} {"current_steps": 34865, "total_steps": 38160, "loss": 0.0028, "lr": 1.127690891444924e-06, "epoch": 18.2730607966457, "percentage": 91.37, "elapsed_time": "2:13:54", "remaining_time": "0:12:39", "throughput": 2837.09, "total_tokens": 22794168} {"current_steps": 34870, "total_steps": 38160, "loss": 0.0035, "lr": 1.1242979531086829e-06, "epoch": 18.27568134171908, "percentage": 91.38, "elapsed_time": "2:13:55", "remaining_time": "0:12:38", "throughput": 2837.02, "total_tokens": 22796600} {"current_steps": 34875, "total_steps": 38160, "loss": 0.0058, "lr": 1.1209100092969244e-06, "epoch": 18.278301886792452, "percentage": 91.39, "elapsed_time": "2:13:56", "remaining_time": "0:12:36", "throughput": 2837.04, "total_tokens": 22799896} {"current_steps": 34880, "total_steps": 38160, "loss": 0.0131, "lr": 1.1175270607183625e-06, "epoch": 18.28092243186583, "percentage": 91.4, "elapsed_time": "2:13:57", "remaining_time": "0:12:35", "throughput": 2837.06, "total_tokens": 22803416} {"current_steps": 34885, "total_steps": 38160, "loss": 0.0054, "lr": 1.114149108080678e-06, "epoch": 18.283542976939202, "percentage": 91.42, "elapsed_time": "2:13:58", "remaining_time": "0:12:34", "throughput": 2837.08, "total_tokens": 22806552} {"current_steps": 34890, "total_steps": 38160, "loss": 0.0082, "lr": 1.1107761520904925e-06, "epoch": 18.28616352201258, "percentage": 91.43, "elapsed_time": "2:13:59", "remaining_time": "0:12:33", "throughput": 2837.08, "total_tokens": 22809496} {"current_steps": 34895, "total_steps": 38160, "loss": 0.0108, "lr": 1.1074081934533908e-06, "epoch": 18.288784067085953, "percentage": 91.44, "elapsed_time": "2:14:00", "remaining_time": "0:12:32", "throughput": 2837.09, "total_tokens": 22812664} {"current_steps": 34900, "total_steps": 38160, "loss": 0.0026, "lr": 1.1040452328739153e-06, "epoch": 18.29140461215933, "percentage": 91.46, "elapsed_time": "2:14:01", "remaining_time": "0:12:31", "throughput": 2837.11, "total_tokens": 22815992} {"current_steps": 34905, "total_steps": 38160, "loss": 0.0042, "lr": 1.1006872710555615e-06, "epoch": 18.294025157232703, "percentage": 91.47, "elapsed_time": "2:14:03", "remaining_time": "0:12:30", "throughput": 2837.12, "total_tokens": 22818968} {"current_steps": 34910, "total_steps": 38160, "loss": 0.0031, "lr": 1.0973343087007703e-06, "epoch": 18.29664570230608, "percentage": 91.48, "elapsed_time": "2:14:04", "remaining_time": "0:12:28", "throughput": 2837.07, "total_tokens": 22821624} {"current_steps": 34915, "total_steps": 38160, "loss": 0.0236, "lr": 1.0939863465109473e-06, "epoch": 18.299266247379457, "percentage": 91.5, "elapsed_time": "2:14:05", "remaining_time": "0:12:27", "throughput": 2837.08, "total_tokens": 22824696} {"current_steps": 34920, "total_steps": 38160, "loss": 0.0029, "lr": 1.0906433851864433e-06, "epoch": 18.30188679245283, "percentage": 91.51, "elapsed_time": "2:14:06", "remaining_time": "0:12:26", "throughput": 2837.11, "total_tokens": 22827864} {"current_steps": 34925, "total_steps": 38160, "loss": 0.0198, "lr": 1.0873054254265713e-06, "epoch": 18.304507337526207, "percentage": 91.52, "elapsed_time": "2:14:07", "remaining_time": "0:12:25", "throughput": 2837.14, "total_tokens": 22831384} {"current_steps": 34930, "total_steps": 38160, "loss": 0.0142, "lr": 1.0839724679295976e-06, "epoch": 18.30712788259958, "percentage": 91.54, "elapsed_time": "2:14:08", "remaining_time": "0:12:24", "throughput": 2837.25, "total_tokens": 22835928} {"current_steps": 34935, "total_steps": 38160, "loss": 0.005, "lr": 1.0806445133927311e-06, "epoch": 18.309748427672957, "percentage": 91.55, "elapsed_time": "2:14:09", "remaining_time": "0:12:23", "throughput": 2837.22, "total_tokens": 22838776} {"current_steps": 34940, "total_steps": 38160, "loss": 0.0038, "lr": 1.0773215625121457e-06, "epoch": 18.31236897274633, "percentage": 91.56, "elapsed_time": "2:14:10", "remaining_time": "0:12:21", "throughput": 2837.24, "total_tokens": 22842008} {"current_steps": 34945, "total_steps": 38160, "loss": 0.0189, "lr": 1.0740036159829715e-06, "epoch": 18.314989517819708, "percentage": 91.57, "elapsed_time": "2:14:11", "remaining_time": "0:12:20", "throughput": 2837.33, "total_tokens": 22846040} {"current_steps": 34950, "total_steps": 38160, "loss": 0.004, "lr": 1.0706906744992724e-06, "epoch": 18.31761006289308, "percentage": 91.59, "elapsed_time": "2:14:13", "remaining_time": "0:12:19", "throughput": 2837.39, "total_tokens": 22850328} {"current_steps": 34955, "total_steps": 38160, "loss": 0.0034, "lr": 1.0673827387540857e-06, "epoch": 18.320230607966458, "percentage": 91.6, "elapsed_time": "2:14:14", "remaining_time": "0:12:18", "throughput": 2837.42, "total_tokens": 22853624} {"current_steps": 34960, "total_steps": 38160, "loss": 0.0136, "lr": 1.0640798094393916e-06, "epoch": 18.32285115303983, "percentage": 91.61, "elapsed_time": "2:14:15", "remaining_time": "0:12:17", "throughput": 2837.46, "total_tokens": 22857240} {"current_steps": 34965, "total_steps": 38160, "loss": 0.0046, "lr": 1.060781887246126e-06, "epoch": 18.32547169811321, "percentage": 91.63, "elapsed_time": "2:14:16", "remaining_time": "0:12:16", "throughput": 2837.46, "total_tokens": 22860216} {"current_steps": 34970, "total_steps": 38160, "loss": 0.0011, "lr": 1.057488972864179e-06, "epoch": 18.328092243186582, "percentage": 91.64, "elapsed_time": "2:14:18", "remaining_time": "0:12:15", "throughput": 2837.5, "total_tokens": 22864920} {"current_steps": 34975, "total_steps": 38160, "loss": 0.0047, "lr": 1.0542010669823855e-06, "epoch": 18.33071278825996, "percentage": 91.65, "elapsed_time": "2:14:19", "remaining_time": "0:12:13", "throughput": 2837.5, "total_tokens": 22867928} {"current_steps": 34980, "total_steps": 38160, "loss": 0.0036, "lr": 1.0509181702885395e-06, "epoch": 18.333333333333332, "percentage": 91.67, "elapsed_time": "2:14:20", "remaining_time": "0:12:12", "throughput": 2837.54, "total_tokens": 22871256} {"current_steps": 34985, "total_steps": 38160, "loss": 0.0172, "lr": 1.047640283469392e-06, "epoch": 18.33595387840671, "percentage": 91.68, "elapsed_time": "2:14:21", "remaining_time": "0:12:11", "throughput": 2837.66, "total_tokens": 22875544} {"current_steps": 34990, "total_steps": 38160, "loss": 0.0119, "lr": 1.0443674072106308e-06, "epoch": 18.338574423480082, "percentage": 91.69, "elapsed_time": "2:14:22", "remaining_time": "0:12:10", "throughput": 2837.63, "total_tokens": 22878456} {"current_steps": 34995, "total_steps": 38160, "loss": 0.0084, "lr": 1.041099542196905e-06, "epoch": 18.34119496855346, "percentage": 91.71, "elapsed_time": "2:14:23", "remaining_time": "0:12:09", "throughput": 2837.72, "total_tokens": 22882168} {"current_steps": 35000, "total_steps": 38160, "loss": 0.0036, "lr": 1.0378366891118234e-06, "epoch": 18.343815513626833, "percentage": 91.72, "elapsed_time": "2:14:24", "remaining_time": "0:12:08", "throughput": 2837.66, "total_tokens": 22884824} {"current_steps": 35005, "total_steps": 38160, "loss": 0.004, "lr": 1.0345788486379265e-06, "epoch": 18.34643605870021, "percentage": 91.73, "elapsed_time": "2:14:25", "remaining_time": "0:12:06", "throughput": 2837.67, "total_tokens": 22887864} {"current_steps": 35010, "total_steps": 38160, "loss": 0.0466, "lr": 1.0313260214567272e-06, "epoch": 18.349056603773583, "percentage": 91.75, "elapsed_time": "2:14:26", "remaining_time": "0:12:05", "throughput": 2837.76, "total_tokens": 22892184} {"current_steps": 35015, "total_steps": 38160, "loss": 0.0073, "lr": 1.0280782082486729e-06, "epoch": 18.35167714884696, "percentage": 91.76, "elapsed_time": "2:14:28", "remaining_time": "0:12:04", "throughput": 2837.75, "total_tokens": 22895096} {"current_steps": 35020, "total_steps": 38160, "loss": 0.0026, "lr": 1.02483540969317e-06, "epoch": 18.354297693920337, "percentage": 91.77, "elapsed_time": "2:14:29", "remaining_time": "0:12:03", "throughput": 2837.75, "total_tokens": 22898168} {"current_steps": 35025, "total_steps": 38160, "loss": 0.0016, "lr": 1.0215976264685763e-06, "epoch": 18.35691823899371, "percentage": 91.78, "elapsed_time": "2:14:30", "remaining_time": "0:12:02", "throughput": 2837.78, "total_tokens": 22901368} {"current_steps": 35030, "total_steps": 38160, "loss": 0.0068, "lr": 1.0183648592522021e-06, "epoch": 18.359538784067087, "percentage": 91.8, "elapsed_time": "2:14:31", "remaining_time": "0:12:01", "throughput": 2837.83, "total_tokens": 22905048} {"current_steps": 35035, "total_steps": 38160, "loss": 0.0034, "lr": 1.0151371087203015e-06, "epoch": 18.36215932914046, "percentage": 91.81, "elapsed_time": "2:14:32", "remaining_time": "0:12:00", "throughput": 2837.8, "total_tokens": 22907800} {"current_steps": 35040, "total_steps": 38160, "loss": 0.0071, "lr": 1.0119143755480815e-06, "epoch": 18.364779874213838, "percentage": 91.82, "elapsed_time": "2:14:33", "remaining_time": "0:11:58", "throughput": 2837.86, "total_tokens": 22911480} {"current_steps": 35045, "total_steps": 38160, "loss": 0.0046, "lr": 1.0086966604097026e-06, "epoch": 18.36740041928721, "percentage": 91.84, "elapsed_time": "2:14:34", "remaining_time": "0:11:57", "throughput": 2837.91, "total_tokens": 22914936} {"current_steps": 35050, "total_steps": 38160, "loss": 0.0059, "lr": 1.0054839639782766e-06, "epoch": 18.370020964360588, "percentage": 91.85, "elapsed_time": "2:14:35", "remaining_time": "0:11:56", "throughput": 2837.93, "total_tokens": 22918424} {"current_steps": 35055, "total_steps": 38160, "loss": 0.0048, "lr": 1.00227628692586e-06, "epoch": 18.37264150943396, "percentage": 91.86, "elapsed_time": "2:14:36", "remaining_time": "0:11:55", "throughput": 2837.88, "total_tokens": 22921112} {"current_steps": 35060, "total_steps": 38160, "loss": 0.0298, "lr": 9.990736299234692e-07, "epoch": 18.37526205450734, "percentage": 91.88, "elapsed_time": "2:14:37", "remaining_time": "0:11:54", "throughput": 2837.86, "total_tokens": 22924024} {"current_steps": 35065, "total_steps": 38160, "loss": 0.0045, "lr": 9.958759936410573e-07, "epoch": 18.377882599580712, "percentage": 91.89, "elapsed_time": "2:14:38", "remaining_time": "0:11:53", "throughput": 2837.88, "total_tokens": 22927128} {"current_steps": 35070, "total_steps": 38160, "loss": 0.0024, "lr": 9.926833787475304e-07, "epoch": 18.38050314465409, "percentage": 91.9, "elapsed_time": "2:14:40", "remaining_time": "0:11:51", "throughput": 2837.85, "total_tokens": 22929912} {"current_steps": 35075, "total_steps": 38160, "loss": 0.0027, "lr": 9.89495785910749e-07, "epoch": 18.383123689727462, "percentage": 91.92, "elapsed_time": "2:14:41", "remaining_time": "0:11:50", "throughput": 2837.8, "total_tokens": 22932504} {"current_steps": 35080, "total_steps": 38160, "loss": 0.0075, "lr": 9.86313215797524e-07, "epoch": 18.38574423480084, "percentage": 91.93, "elapsed_time": "2:14:42", "remaining_time": "0:11:49", "throughput": 2837.9, "total_tokens": 22936600} {"current_steps": 35085, "total_steps": 38160, "loss": 0.0199, "lr": 9.831356690736149e-07, "epoch": 18.388364779874212, "percentage": 91.94, "elapsed_time": "2:14:43", "remaining_time": "0:11:48", "throughput": 2837.9, "total_tokens": 22939864} {"current_steps": 35090, "total_steps": 38160, "loss": 0.0309, "lr": 9.799631464037256e-07, "epoch": 18.39098532494759, "percentage": 91.95, "elapsed_time": "2:14:44", "remaining_time": "0:11:47", "throughput": 2837.95, "total_tokens": 22943480} {"current_steps": 35095, "total_steps": 38160, "loss": 0.0038, "lr": 9.76795648451509e-07, "epoch": 18.393605870020963, "percentage": 91.97, "elapsed_time": "2:14:45", "remaining_time": "0:11:46", "throughput": 2837.99, "total_tokens": 22946712} {"current_steps": 35100, "total_steps": 38160, "loss": 0.0056, "lr": 9.73633175879568e-07, "epoch": 18.39622641509434, "percentage": 91.98, "elapsed_time": "2:14:46", "remaining_time": "0:11:44", "throughput": 2838.03, "total_tokens": 22950392} {"current_steps": 35105, "total_steps": 38160, "loss": 0.0177, "lr": 9.704757293494627e-07, "epoch": 18.398846960167713, "percentage": 91.99, "elapsed_time": "2:14:47", "remaining_time": "0:11:43", "throughput": 2838.08, "total_tokens": 22954264} {"current_steps": 35110, "total_steps": 38160, "loss": 0.0057, "lr": 9.673233095216922e-07, "epoch": 18.40146750524109, "percentage": 92.01, "elapsed_time": "2:14:49", "remaining_time": "0:11:42", "throughput": 2838.14, "total_tokens": 22958232} {"current_steps": 35115, "total_steps": 38160, "loss": 0.0181, "lr": 9.641759170557068e-07, "epoch": 18.404088050314467, "percentage": 92.02, "elapsed_time": "2:14:50", "remaining_time": "0:11:41", "throughput": 2838.11, "total_tokens": 22961208} {"current_steps": 35120, "total_steps": 38160, "loss": 0.0027, "lr": 9.610335526099024e-07, "epoch": 18.40670859538784, "percentage": 92.03, "elapsed_time": "2:14:51", "remaining_time": "0:11:40", "throughput": 2838.23, "total_tokens": 22966296} {"current_steps": 35125, "total_steps": 38160, "loss": 0.0012, "lr": 9.578962168416278e-07, "epoch": 18.409329140461217, "percentage": 92.05, "elapsed_time": "2:14:52", "remaining_time": "0:11:39", "throughput": 2838.18, "total_tokens": 22968856} {"current_steps": 35130, "total_steps": 38160, "loss": 0.0022, "lr": 9.547639104071775e-07, "epoch": 18.41194968553459, "percentage": 92.06, "elapsed_time": "2:14:53", "remaining_time": "0:11:38", "throughput": 2838.2, "total_tokens": 22972056} {"current_steps": 35135, "total_steps": 38160, "loss": 0.002, "lr": 9.516366339617944e-07, "epoch": 18.414570230607968, "percentage": 92.07, "elapsed_time": "2:14:54", "remaining_time": "0:11:36", "throughput": 2838.18, "total_tokens": 22974840} {"current_steps": 35140, "total_steps": 38160, "loss": 0.0454, "lr": 9.485143881596714e-07, "epoch": 18.41719077568134, "percentage": 92.09, "elapsed_time": "2:14:56", "remaining_time": "0:11:35", "throughput": 2838.21, "total_tokens": 22978520} {"current_steps": 35145, "total_steps": 38160, "loss": 0.0085, "lr": 9.453971736539447e-07, "epoch": 18.419811320754718, "percentage": 92.1, "elapsed_time": "2:14:57", "remaining_time": "0:11:34", "throughput": 2838.26, "total_tokens": 22982136} {"current_steps": 35150, "total_steps": 38160, "loss": 0.0023, "lr": 9.42284991096698e-07, "epoch": 18.42243186582809, "percentage": 92.11, "elapsed_time": "2:14:58", "remaining_time": "0:11:33", "throughput": 2838.26, "total_tokens": 22985304} {"current_steps": 35155, "total_steps": 38160, "loss": 0.0059, "lr": 9.391778411389634e-07, "epoch": 18.42505241090147, "percentage": 92.13, "elapsed_time": "2:14:59", "remaining_time": "0:11:32", "throughput": 2838.31, "total_tokens": 22988856} {"current_steps": 35160, "total_steps": 38160, "loss": 0.0036, "lr": 9.360757244307267e-07, "epoch": 18.427672955974842, "percentage": 92.14, "elapsed_time": "2:15:00", "remaining_time": "0:11:31", "throughput": 2838.31, "total_tokens": 22991896} {"current_steps": 35165, "total_steps": 38160, "loss": 0.0141, "lr": 9.329786416209157e-07, "epoch": 18.43029350104822, "percentage": 92.15, "elapsed_time": "2:15:01", "remaining_time": "0:11:30", "throughput": 2838.28, "total_tokens": 22994808} {"current_steps": 35170, "total_steps": 38160, "loss": 0.0026, "lr": 9.298865933574014e-07, "epoch": 18.432914046121592, "percentage": 92.16, "elapsed_time": "2:15:02", "remaining_time": "0:11:28", "throughput": 2838.23, "total_tokens": 22997560} {"current_steps": 35175, "total_steps": 38160, "loss": 0.0421, "lr": 9.267995802870022e-07, "epoch": 18.43553459119497, "percentage": 92.18, "elapsed_time": "2:15:03", "remaining_time": "0:11:27", "throughput": 2838.21, "total_tokens": 23000696} {"current_steps": 35180, "total_steps": 38160, "loss": 0.0044, "lr": 9.237176030554878e-07, "epoch": 18.438155136268342, "percentage": 92.19, "elapsed_time": "2:15:05", "remaining_time": "0:11:26", "throughput": 2838.16, "total_tokens": 23003320} {"current_steps": 35185, "total_steps": 38160, "loss": 0.0044, "lr": 9.206406623075758e-07, "epoch": 18.44077568134172, "percentage": 92.2, "elapsed_time": "2:15:06", "remaining_time": "0:11:25", "throughput": 2838.15, "total_tokens": 23006456} {"current_steps": 35190, "total_steps": 38160, "loss": 0.0047, "lr": 9.175687586869292e-07, "epoch": 18.443396226415093, "percentage": 92.22, "elapsed_time": "2:15:07", "remaining_time": "0:11:24", "throughput": 2838.24, "total_tokens": 23010712} {"current_steps": 35195, "total_steps": 38160, "loss": 0.0061, "lr": 9.145018928361476e-07, "epoch": 18.44601677148847, "percentage": 92.23, "elapsed_time": "2:15:08", "remaining_time": "0:11:23", "throughput": 2838.31, "total_tokens": 23014232} {"current_steps": 35200, "total_steps": 38160, "loss": 0.0035, "lr": 9.114400653967903e-07, "epoch": 18.448637316561843, "percentage": 92.24, "elapsed_time": "2:15:09", "remaining_time": "0:11:21", "throughput": 2838.26, "total_tokens": 23016952} {"current_steps": 35205, "total_steps": 38160, "loss": 0.0318, "lr": 9.083832770093531e-07, "epoch": 18.45125786163522, "percentage": 92.26, "elapsed_time": "2:15:10", "remaining_time": "0:11:20", "throughput": 2838.24, "total_tokens": 23019832} {"current_steps": 35210, "total_steps": 38160, "loss": 0.0041, "lr": 9.053315283132802e-07, "epoch": 18.453878406708597, "percentage": 92.27, "elapsed_time": "2:15:11", "remaining_time": "0:11:19", "throughput": 2838.15, "total_tokens": 23022264} {"current_steps": 35215, "total_steps": 38160, "loss": 0.0063, "lr": 9.022848199469663e-07, "epoch": 18.45649895178197, "percentage": 92.28, "elapsed_time": "2:15:12", "remaining_time": "0:11:18", "throughput": 2838.19, "total_tokens": 23025912} {"current_steps": 35220, "total_steps": 38160, "loss": 0.0035, "lr": 8.992431525477518e-07, "epoch": 18.459119496855347, "percentage": 92.3, "elapsed_time": "2:15:13", "remaining_time": "0:11:17", "throughput": 2838.25, "total_tokens": 23029560} {"current_steps": 35225, "total_steps": 38160, "loss": 0.0075, "lr": 8.962065267519082e-07, "epoch": 18.46174004192872, "percentage": 92.31, "elapsed_time": "2:15:15", "remaining_time": "0:11:16", "throughput": 2838.31, "total_tokens": 23033176} {"current_steps": 35230, "total_steps": 38160, "loss": 0.0034, "lr": 8.931749431946718e-07, "epoch": 18.464360587002098, "percentage": 92.32, "elapsed_time": "2:15:16", "remaining_time": "0:11:15", "throughput": 2838.31, "total_tokens": 23036568} {"current_steps": 35235, "total_steps": 38160, "loss": 0.0018, "lr": 8.901484025102103e-07, "epoch": 18.46698113207547, "percentage": 92.33, "elapsed_time": "2:15:17", "remaining_time": "0:11:13", "throughput": 2838.27, "total_tokens": 23039448} {"current_steps": 35240, "total_steps": 38160, "loss": 0.0045, "lr": 8.871269053316422e-07, "epoch": 18.469601677148848, "percentage": 92.35, "elapsed_time": "2:15:18", "remaining_time": "0:11:12", "throughput": 2838.33, "total_tokens": 23043384} {"current_steps": 35245, "total_steps": 38160, "loss": 0.0472, "lr": 8.841104522910343e-07, "epoch": 18.47222222222222, "percentage": 92.36, "elapsed_time": "2:15:19", "remaining_time": "0:11:11", "throughput": 2838.39, "total_tokens": 23047128} {"current_steps": 35250, "total_steps": 38160, "loss": 0.0075, "lr": 8.8109904401939e-07, "epoch": 18.4748427672956, "percentage": 92.37, "elapsed_time": "2:15:20", "remaining_time": "0:11:10", "throughput": 2838.39, "total_tokens": 23050072} {"current_steps": 35255, "total_steps": 38160, "loss": 0.005, "lr": 8.780926811466639e-07, "epoch": 18.47746331236897, "percentage": 92.39, "elapsed_time": "2:15:21", "remaining_time": "0:11:09", "throughput": 2838.45, "total_tokens": 23053688} {"current_steps": 35260, "total_steps": 38160, "loss": 0.003, "lr": 8.7509136430175e-07, "epoch": 18.48008385744235, "percentage": 92.4, "elapsed_time": "2:15:22", "remaining_time": "0:11:08", "throughput": 2838.43, "total_tokens": 23056440} {"current_steps": 35265, "total_steps": 38160, "loss": 0.0064, "lr": 8.720950941124877e-07, "epoch": 18.482704402515722, "percentage": 92.41, "elapsed_time": "2:15:24", "remaining_time": "0:11:06", "throughput": 2838.5, "total_tokens": 23060120} {"current_steps": 35270, "total_steps": 38160, "loss": 0.0079, "lr": 8.691038712056732e-07, "epoch": 18.4853249475891, "percentage": 92.43, "elapsed_time": "2:15:25", "remaining_time": "0:11:05", "throughput": 2838.56, "total_tokens": 23063544} {"current_steps": 35275, "total_steps": 38160, "loss": 0.0031, "lr": 8.66117696207025e-07, "epoch": 18.487945492662472, "percentage": 92.44, "elapsed_time": "2:15:26", "remaining_time": "0:11:04", "throughput": 2838.63, "total_tokens": 23067096} {"current_steps": 35280, "total_steps": 38160, "loss": 0.0017, "lr": 8.631365697412186e-07, "epoch": 18.49056603773585, "percentage": 92.45, "elapsed_time": "2:15:27", "remaining_time": "0:11:03", "throughput": 2838.63, "total_tokens": 23070328} {"current_steps": 35285, "total_steps": 38160, "loss": 0.0155, "lr": 8.601604924318802e-07, "epoch": 18.493186582809223, "percentage": 92.47, "elapsed_time": "2:15:28", "remaining_time": "0:11:02", "throughput": 2838.74, "total_tokens": 23074648} {"current_steps": 35290, "total_steps": 38160, "loss": 0.0037, "lr": 8.571894649015588e-07, "epoch": 18.4958071278826, "percentage": 92.48, "elapsed_time": "2:15:29", "remaining_time": "0:11:01", "throughput": 2838.71, "total_tokens": 23077400} {"current_steps": 35295, "total_steps": 38160, "loss": 0.0108, "lr": 8.542234877717686e-07, "epoch": 18.498427672955973, "percentage": 92.49, "elapsed_time": "2:15:30", "remaining_time": "0:10:59", "throughput": 2838.64, "total_tokens": 23079992} {"current_steps": 35300, "total_steps": 38160, "loss": 0.0023, "lr": 8.512625616629549e-07, "epoch": 18.50104821802935, "percentage": 92.51, "elapsed_time": "2:15:31", "remaining_time": "0:10:58", "throughput": 2838.62, "total_tokens": 23082936} {"current_steps": 35305, "total_steps": 38160, "loss": 0.0036, "lr": 8.483066871945083e-07, "epoch": 18.503668763102727, "percentage": 92.52, "elapsed_time": "2:15:32", "remaining_time": "0:10:57", "throughput": 2838.53, "total_tokens": 23085528} {"current_steps": 35310, "total_steps": 38160, "loss": 0.0076, "lr": 8.453558649847676e-07, "epoch": 18.5062893081761, "percentage": 92.53, "elapsed_time": "2:15:34", "remaining_time": "0:10:56", "throughput": 2838.55, "total_tokens": 23089016} {"current_steps": 35315, "total_steps": 38160, "loss": 0.0074, "lr": 8.424100956510112e-07, "epoch": 18.508909853249477, "percentage": 92.54, "elapsed_time": "2:15:35", "remaining_time": "0:10:55", "throughput": 2838.48, "total_tokens": 23091512} {"current_steps": 35320, "total_steps": 38160, "loss": 0.0072, "lr": 8.394693798094544e-07, "epoch": 18.51153039832285, "percentage": 92.56, "elapsed_time": "2:15:36", "remaining_time": "0:10:54", "throughput": 2838.51, "total_tokens": 23095096} {"current_steps": 35325, "total_steps": 38160, "loss": 0.0047, "lr": 8.365337180752691e-07, "epoch": 18.514150943396228, "percentage": 92.57, "elapsed_time": "2:15:37", "remaining_time": "0:10:53", "throughput": 2838.58, "total_tokens": 23098904} {"current_steps": 35330, "total_steps": 38160, "loss": 0.0048, "lr": 8.336031110625558e-07, "epoch": 18.5167714884696, "percentage": 92.58, "elapsed_time": "2:15:38", "remaining_time": "0:10:51", "throughput": 2838.57, "total_tokens": 23101944} {"current_steps": 35335, "total_steps": 38160, "loss": 0.0061, "lr": 8.306775593843657e-07, "epoch": 18.519392033542978, "percentage": 92.6, "elapsed_time": "2:15:39", "remaining_time": "0:10:50", "throughput": 2838.61, "total_tokens": 23105816} {"current_steps": 35340, "total_steps": 38160, "loss": 0.0101, "lr": 8.277570636526955e-07, "epoch": 18.52201257861635, "percentage": 92.61, "elapsed_time": "2:15:40", "remaining_time": "0:10:49", "throughput": 2838.64, "total_tokens": 23109304} {"current_steps": 35345, "total_steps": 38160, "loss": 0.0062, "lr": 8.24841624478473e-07, "epoch": 18.52463312368973, "percentage": 92.62, "elapsed_time": "2:15:42", "remaining_time": "0:10:48", "throughput": 2838.67, "total_tokens": 23112984} {"current_steps": 35350, "total_steps": 38160, "loss": 0.002, "lr": 8.219312424715825e-07, "epoch": 18.5272536687631, "percentage": 92.64, "elapsed_time": "2:15:43", "remaining_time": "0:10:47", "throughput": 2838.66, "total_tokens": 23115832} {"current_steps": 35355, "total_steps": 38160, "loss": 0.0031, "lr": 8.190259182408345e-07, "epoch": 18.52987421383648, "percentage": 92.65, "elapsed_time": "2:15:44", "remaining_time": "0:10:46", "throughput": 2838.66, "total_tokens": 23118872} {"current_steps": 35360, "total_steps": 38160, "loss": 0.0097, "lr": 8.161256523939925e-07, "epoch": 18.532494758909852, "percentage": 92.66, "elapsed_time": "2:15:45", "remaining_time": "0:10:44", "throughput": 2838.66, "total_tokens": 23121880} {"current_steps": 35365, "total_steps": 38160, "loss": 0.0112, "lr": 8.132304455377576e-07, "epoch": 18.53511530398323, "percentage": 92.68, "elapsed_time": "2:15:46", "remaining_time": "0:10:43", "throughput": 2838.73, "total_tokens": 23125528} {"current_steps": 35370, "total_steps": 38160, "loss": 0.0256, "lr": 8.103402982777813e-07, "epoch": 18.537735849056602, "percentage": 92.69, "elapsed_time": "2:15:47", "remaining_time": "0:10:42", "throughput": 2838.87, "total_tokens": 23130360} {"current_steps": 35375, "total_steps": 38160, "loss": 0.0091, "lr": 8.07455211218644e-07, "epoch": 18.54035639412998, "percentage": 92.7, "elapsed_time": "2:15:48", "remaining_time": "0:10:41", "throughput": 2838.92, "total_tokens": 23133912} {"current_steps": 35380, "total_steps": 38160, "loss": 0.0027, "lr": 8.045751849638738e-07, "epoch": 18.542976939203353, "percentage": 92.71, "elapsed_time": "2:15:49", "remaining_time": "0:10:40", "throughput": 2838.86, "total_tokens": 23136440} {"current_steps": 35385, "total_steps": 38160, "loss": 0.0077, "lr": 8.017002201159363e-07, "epoch": 18.54559748427673, "percentage": 92.73, "elapsed_time": "2:15:50", "remaining_time": "0:10:39", "throughput": 2838.88, "total_tokens": 23139544} {"current_steps": 35390, "total_steps": 38160, "loss": 0.0134, "lr": 7.988303172762418e-07, "epoch": 18.548218029350103, "percentage": 92.74, "elapsed_time": "2:15:52", "remaining_time": "0:10:38", "throughput": 2839.04, "total_tokens": 23144408} {"current_steps": 35395, "total_steps": 38160, "loss": 0.004, "lr": 7.959654770451463e-07, "epoch": 18.55083857442348, "percentage": 92.75, "elapsed_time": "2:15:53", "remaining_time": "0:10:36", "throughput": 2839.08, "total_tokens": 23147960} {"current_steps": 35400, "total_steps": 38160, "loss": 0.004, "lr": 7.9310570002194e-07, "epoch": 18.553459119496857, "percentage": 92.77, "elapsed_time": "2:15:54", "remaining_time": "0:10:35", "throughput": 2839.08, "total_tokens": 23151096} {"current_steps": 35405, "total_steps": 38160, "loss": 0.005, "lr": 7.902509868048552e-07, "epoch": 18.55607966457023, "percentage": 92.78, "elapsed_time": "2:15:55", "remaining_time": "0:10:34", "throughput": 2839.12, "total_tokens": 23154424} {"current_steps": 35410, "total_steps": 38160, "loss": 0.0026, "lr": 7.874013379910616e-07, "epoch": 18.558700209643607, "percentage": 92.79, "elapsed_time": "2:15:56", "remaining_time": "0:10:33", "throughput": 2839.08, "total_tokens": 23157048} {"current_steps": 35415, "total_steps": 38160, "loss": 0.0078, "lr": 7.845567541766769e-07, "epoch": 18.56132075471698, "percentage": 92.81, "elapsed_time": "2:15:57", "remaining_time": "0:10:32", "throughput": 2839.1, "total_tokens": 23160792} {"current_steps": 35420, "total_steps": 38160, "loss": 0.0044, "lr": 7.817172359567526e-07, "epoch": 18.563941299790358, "percentage": 92.82, "elapsed_time": "2:15:58", "remaining_time": "0:10:31", "throughput": 2839.12, "total_tokens": 23164248} {"current_steps": 35425, "total_steps": 38160, "loss": 0.0187, "lr": 7.788827839252888e-07, "epoch": 18.56656184486373, "percentage": 92.83, "elapsed_time": "2:16:00", "remaining_time": "0:10:30", "throughput": 2839.15, "total_tokens": 23167832} {"current_steps": 35430, "total_steps": 38160, "loss": 0.0025, "lr": 7.760533986752222e-07, "epoch": 18.569182389937108, "percentage": 92.85, "elapsed_time": "2:16:01", "remaining_time": "0:10:28", "throughput": 2839.25, "total_tokens": 23172152} {"current_steps": 35435, "total_steps": 38160, "loss": 0.0025, "lr": 7.732290807984155e-07, "epoch": 18.57180293501048, "percentage": 92.86, "elapsed_time": "2:16:02", "remaining_time": "0:10:27", "throughput": 2839.24, "total_tokens": 23175000} {"current_steps": 35440, "total_steps": 38160, "loss": 0.0035, "lr": 7.704098308856933e-07, "epoch": 18.57442348008386, "percentage": 92.87, "elapsed_time": "2:16:03", "remaining_time": "0:10:26", "throughput": 2839.23, "total_tokens": 23177976} {"current_steps": 35445, "total_steps": 38160, "loss": 0.0028, "lr": 7.675956495268088e-07, "epoch": 18.57704402515723, "percentage": 92.89, "elapsed_time": "2:16:04", "remaining_time": "0:10:25", "throughput": 2839.2, "total_tokens": 23180792} {"current_steps": 35450, "total_steps": 38160, "loss": 0.0093, "lr": 7.647865373104551e-07, "epoch": 18.57966457023061, "percentage": 92.9, "elapsed_time": "2:16:05", "remaining_time": "0:10:24", "throughput": 2839.26, "total_tokens": 23184344} {"current_steps": 35455, "total_steps": 38160, "loss": 0.003, "lr": 7.619824948242732e-07, "epoch": 18.582285115303982, "percentage": 92.91, "elapsed_time": "2:16:06", "remaining_time": "0:10:23", "throughput": 2839.28, "total_tokens": 23187640} {"current_steps": 35460, "total_steps": 38160, "loss": 0.0168, "lr": 7.5918352265483e-07, "epoch": 18.58490566037736, "percentage": 92.92, "elapsed_time": "2:16:07", "remaining_time": "0:10:21", "throughput": 2839.33, "total_tokens": 23191256} {"current_steps": 35465, "total_steps": 38160, "loss": 0.0058, "lr": 7.563896213876348e-07, "epoch": 18.587526205450732, "percentage": 92.94, "elapsed_time": "2:16:08", "remaining_time": "0:10:20", "throughput": 2839.28, "total_tokens": 23193944} {"current_steps": 35470, "total_steps": 38160, "loss": 0.0054, "lr": 7.53600791607148e-07, "epoch": 18.59014675052411, "percentage": 92.95, "elapsed_time": "2:16:10", "remaining_time": "0:10:19", "throughput": 2839.33, "total_tokens": 23197464} {"current_steps": 35475, "total_steps": 38160, "loss": 0.0068, "lr": 7.508170338967585e-07, "epoch": 18.592767295597483, "percentage": 92.96, "elapsed_time": "2:16:11", "remaining_time": "0:10:18", "throughput": 2839.28, "total_tokens": 23200024} {"current_steps": 35480, "total_steps": 38160, "loss": 0.0031, "lr": 7.480383488387976e-07, "epoch": 18.59538784067086, "percentage": 92.98, "elapsed_time": "2:16:12", "remaining_time": "0:10:17", "throughput": 2839.25, "total_tokens": 23202968} {"current_steps": 35485, "total_steps": 38160, "loss": 0.0018, "lr": 7.452647370145338e-07, "epoch": 18.598008385744233, "percentage": 92.99, "elapsed_time": "2:16:13", "remaining_time": "0:10:16", "throughput": 2839.29, "total_tokens": 23206296} {"current_steps": 35490, "total_steps": 38160, "loss": 0.0048, "lr": 7.424961990041696e-07, "epoch": 18.60062893081761, "percentage": 93.0, "elapsed_time": "2:16:14", "remaining_time": "0:10:14", "throughput": 2839.29, "total_tokens": 23209304} {"current_steps": 35495, "total_steps": 38160, "loss": 0.0035, "lr": 7.397327353868583e-07, "epoch": 18.603249475890987, "percentage": 93.02, "elapsed_time": "2:16:15", "remaining_time": "0:10:13", "throughput": 2839.36, "total_tokens": 23213080} {"current_steps": 35500, "total_steps": 38160, "loss": 0.0028, "lr": 7.369743467406848e-07, "epoch": 18.60587002096436, "percentage": 93.03, "elapsed_time": "2:16:16", "remaining_time": "0:10:12", "throughput": 2839.33, "total_tokens": 23215928} {"current_steps": 35505, "total_steps": 38160, "loss": 0.0049, "lr": 7.34221033642668e-07, "epoch": 18.608490566037737, "percentage": 93.04, "elapsed_time": "2:16:17", "remaining_time": "0:10:11", "throughput": 2839.36, "total_tokens": 23219320} {"current_steps": 35510, "total_steps": 38160, "loss": 0.0041, "lr": 7.314727966687751e-07, "epoch": 18.61111111111111, "percentage": 93.06, "elapsed_time": "2:16:18", "remaining_time": "0:10:10", "throughput": 2839.34, "total_tokens": 23222296} {"current_steps": 35515, "total_steps": 38160, "loss": 0.0086, "lr": 7.287296363939045e-07, "epoch": 18.613731656184488, "percentage": 93.07, "elapsed_time": "2:16:19", "remaining_time": "0:10:09", "throughput": 2839.27, "total_tokens": 23224728} {"current_steps": 35520, "total_steps": 38160, "loss": 0.0036, "lr": 7.259915533918888e-07, "epoch": 18.61635220125786, "percentage": 93.08, "elapsed_time": "2:16:20", "remaining_time": "0:10:08", "throughput": 2839.33, "total_tokens": 23228248} {"current_steps": 35525, "total_steps": 38160, "loss": 0.0065, "lr": 7.232585482355086e-07, "epoch": 18.618972746331238, "percentage": 93.09, "elapsed_time": "2:16:22", "remaining_time": "0:10:06", "throughput": 2839.46, "total_tokens": 23232600} {"current_steps": 35530, "total_steps": 38160, "loss": 0.0039, "lr": 7.205306214964736e-07, "epoch": 18.62159329140461, "percentage": 93.11, "elapsed_time": "2:16:23", "remaining_time": "0:10:05", "throughput": 2839.42, "total_tokens": 23235384} {"current_steps": 35535, "total_steps": 38160, "loss": 0.0036, "lr": 7.178077737454436e-07, "epoch": 18.62421383647799, "percentage": 93.12, "elapsed_time": "2:16:24", "remaining_time": "0:10:04", "throughput": 2839.47, "total_tokens": 23238744} {"current_steps": 35540, "total_steps": 38160, "loss": 0.0153, "lr": 7.150900055519993e-07, "epoch": 18.62683438155136, "percentage": 93.13, "elapsed_time": "2:16:25", "remaining_time": "0:10:03", "throughput": 2839.47, "total_tokens": 23241720} {"current_steps": 35545, "total_steps": 38160, "loss": 0.015, "lr": 7.123773174846693e-07, "epoch": 18.62945492662474, "percentage": 93.15, "elapsed_time": "2:16:26", "remaining_time": "0:10:02", "throughput": 2839.46, "total_tokens": 23244696} {"current_steps": 35550, "total_steps": 38160, "loss": 0.0062, "lr": 7.096697101109134e-07, "epoch": 18.632075471698112, "percentage": 93.16, "elapsed_time": "2:16:27", "remaining_time": "0:10:01", "throughput": 2839.55, "total_tokens": 23248536} {"current_steps": 35555, "total_steps": 38160, "loss": 0.0022, "lr": 7.069671839971371e-07, "epoch": 18.63469601677149, "percentage": 93.17, "elapsed_time": "2:16:28", "remaining_time": "0:09:59", "throughput": 2839.52, "total_tokens": 23251352} {"current_steps": 35560, "total_steps": 38160, "loss": 0.0109, "lr": 7.042697397086795e-07, "epoch": 18.637316561844862, "percentage": 93.19, "elapsed_time": "2:16:29", "remaining_time": "0:09:58", "throughput": 2839.54, "total_tokens": 23254520} {"current_steps": 35565, "total_steps": 38160, "loss": 0.0234, "lr": 7.015773778098089e-07, "epoch": 18.63993710691824, "percentage": 93.2, "elapsed_time": "2:16:31", "remaining_time": "0:09:57", "throughput": 2839.76, "total_tokens": 23261752} {"current_steps": 35570, "total_steps": 38160, "loss": 0.0139, "lr": 6.988900988637415e-07, "epoch": 18.642557651991613, "percentage": 93.21, "elapsed_time": "2:16:32", "remaining_time": "0:09:56", "throughput": 2839.8, "total_tokens": 23265176} {"current_steps": 35575, "total_steps": 38160, "loss": 0.0018, "lr": 6.962079034326218e-07, "epoch": 18.64517819706499, "percentage": 93.23, "elapsed_time": "2:16:33", "remaining_time": "0:09:55", "throughput": 2839.76, "total_tokens": 23267800} {"current_steps": 35580, "total_steps": 38160, "loss": 0.0026, "lr": 6.935307920775346e-07, "epoch": 18.647798742138363, "percentage": 93.24, "elapsed_time": "2:16:34", "remaining_time": "0:09:54", "throughput": 2839.72, "total_tokens": 23270488} {"current_steps": 35585, "total_steps": 38160, "loss": 0.0099, "lr": 6.90858765358507e-07, "epoch": 18.65041928721174, "percentage": 93.25, "elapsed_time": "2:16:35", "remaining_time": "0:09:53", "throughput": 2839.77, "total_tokens": 23274008} {"current_steps": 35590, "total_steps": 38160, "loss": 0.0022, "lr": 6.881918238344915e-07, "epoch": 18.653039832285117, "percentage": 93.27, "elapsed_time": "2:16:36", "remaining_time": "0:09:51", "throughput": 2839.79, "total_tokens": 23277240} {"current_steps": 35595, "total_steps": 38160, "loss": 0.002, "lr": 6.855299680633808e-07, "epoch": 18.65566037735849, "percentage": 93.28, "elapsed_time": "2:16:37", "remaining_time": "0:09:50", "throughput": 2839.74, "total_tokens": 23279768} {"current_steps": 35600, "total_steps": 38160, "loss": 0.0111, "lr": 6.828731986020104e-07, "epoch": 18.658280922431867, "percentage": 93.29, "elapsed_time": "2:16:38", "remaining_time": "0:09:49", "throughput": 2839.77, "total_tokens": 23283128} {"current_steps": 35605, "total_steps": 38160, "loss": 0.005, "lr": 6.802215160061381e-07, "epoch": 18.66090146750524, "percentage": 93.3, "elapsed_time": "2:16:40", "remaining_time": "0:09:48", "throughput": 2839.79, "total_tokens": 23286424} {"current_steps": 35610, "total_steps": 38160, "loss": 0.0139, "lr": 6.775749208304704e-07, "epoch": 18.663522012578618, "percentage": 93.32, "elapsed_time": "2:16:41", "remaining_time": "0:09:47", "throughput": 2839.8, "total_tokens": 23289880} {"current_steps": 35615, "total_steps": 38160, "loss": 0.0075, "lr": 6.749334136286478e-07, "epoch": 18.66614255765199, "percentage": 93.33, "elapsed_time": "2:16:42", "remaining_time": "0:09:46", "throughput": 2839.85, "total_tokens": 23293528} {"current_steps": 35620, "total_steps": 38160, "loss": 0.0028, "lr": 6.722969949532365e-07, "epoch": 18.668763102725368, "percentage": 93.34, "elapsed_time": "2:16:43", "remaining_time": "0:09:44", "throughput": 2839.87, "total_tokens": 23296952} {"current_steps": 35625, "total_steps": 38160, "loss": 0.0035, "lr": 6.69665665355751e-07, "epoch": 18.67138364779874, "percentage": 93.36, "elapsed_time": "2:16:44", "remaining_time": "0:09:43", "throughput": 2839.78, "total_tokens": 23299384} {"current_steps": 35630, "total_steps": 38160, "loss": 0.0057, "lr": 6.670394253866314e-07, "epoch": 18.67400419287212, "percentage": 93.37, "elapsed_time": "2:16:46", "remaining_time": "0:09:42", "throughput": 2840.0, "total_tokens": 23306232} {"current_steps": 35635, "total_steps": 38160, "loss": 0.0064, "lr": 6.644182755952605e-07, "epoch": 18.67662473794549, "percentage": 93.38, "elapsed_time": "2:16:47", "remaining_time": "0:09:41", "throughput": 2839.98, "total_tokens": 23309144} {"current_steps": 35640, "total_steps": 38160, "loss": 0.0028, "lr": 6.618022165299526e-07, "epoch": 18.67924528301887, "percentage": 93.4, "elapsed_time": "2:16:48", "remaining_time": "0:09:40", "throughput": 2840.02, "total_tokens": 23312472} {"current_steps": 35645, "total_steps": 38160, "loss": 0.0017, "lr": 6.591912487379531e-07, "epoch": 18.681865828092242, "percentage": 93.41, "elapsed_time": "2:16:49", "remaining_time": "0:09:39", "throughput": 2839.99, "total_tokens": 23315320} {"current_steps": 35650, "total_steps": 38160, "loss": 0.0018, "lr": 6.565853727654503e-07, "epoch": 18.68448637316562, "percentage": 93.42, "elapsed_time": "2:16:50", "remaining_time": "0:09:38", "throughput": 2839.99, "total_tokens": 23318360} {"current_steps": 35655, "total_steps": 38160, "loss": 0.0036, "lr": 6.539845891575636e-07, "epoch": 18.687106918238992, "percentage": 93.44, "elapsed_time": "2:16:51", "remaining_time": "0:09:36", "throughput": 2839.91, "total_tokens": 23320824} {"current_steps": 35660, "total_steps": 38160, "loss": 0.0047, "lr": 6.513888984583466e-07, "epoch": 18.68972746331237, "percentage": 93.45, "elapsed_time": "2:16:52", "remaining_time": "0:09:35", "throughput": 2839.95, "total_tokens": 23324216} {"current_steps": 35665, "total_steps": 38160, "loss": 0.0153, "lr": 6.487983012107873e-07, "epoch": 18.692348008385743, "percentage": 93.46, "elapsed_time": "2:16:53", "remaining_time": "0:09:34", "throughput": 2839.9, "total_tokens": 23326840} {"current_steps": 35670, "total_steps": 38160, "loss": 0.0028, "lr": 6.462127979568133e-07, "epoch": 18.69496855345912, "percentage": 93.47, "elapsed_time": "2:16:55", "remaining_time": "0:09:33", "throughput": 2839.86, "total_tokens": 23329464} {"current_steps": 35675, "total_steps": 38160, "loss": 0.0042, "lr": 6.436323892372781e-07, "epoch": 18.697589098532493, "percentage": 93.49, "elapsed_time": "2:16:56", "remaining_time": "0:09:32", "throughput": 2839.84, "total_tokens": 23332280} {"current_steps": 35680, "total_steps": 38160, "loss": 0.0079, "lr": 6.410570755919721e-07, "epoch": 18.70020964360587, "percentage": 93.5, "elapsed_time": "2:16:57", "remaining_time": "0:09:31", "throughput": 2839.86, "total_tokens": 23335384} {"current_steps": 35685, "total_steps": 38160, "loss": 0.0025, "lr": 6.384868575596281e-07, "epoch": 18.702830188679247, "percentage": 93.51, "elapsed_time": "2:16:58", "remaining_time": "0:09:29", "throughput": 2839.91, "total_tokens": 23338776} {"current_steps": 35690, "total_steps": 38160, "loss": 0.0128, "lr": 6.359217356779024e-07, "epoch": 18.70545073375262, "percentage": 93.53, "elapsed_time": "2:16:59", "remaining_time": "0:09:28", "throughput": 2839.87, "total_tokens": 23341624} {"current_steps": 35695, "total_steps": 38160, "loss": 0.0048, "lr": 6.333617104833878e-07, "epoch": 18.708071278825997, "percentage": 93.54, "elapsed_time": "2:17:00", "remaining_time": "0:09:27", "throughput": 2839.91, "total_tokens": 23345144} {"current_steps": 35700, "total_steps": 38160, "loss": 0.0039, "lr": 6.308067825116142e-07, "epoch": 18.71069182389937, "percentage": 93.55, "elapsed_time": "2:17:01", "remaining_time": "0:09:26", "throughput": 2840.05, "total_tokens": 23350328} {"current_steps": 35705, "total_steps": 38160, "loss": 0.005, "lr": 6.282569522970433e-07, "epoch": 18.713312368972748, "percentage": 93.57, "elapsed_time": "2:17:02", "remaining_time": "0:09:25", "throughput": 2840.03, "total_tokens": 23353240} {"current_steps": 35710, "total_steps": 38160, "loss": 0.0048, "lr": 6.257122203730731e-07, "epoch": 18.71593291404612, "percentage": 93.58, "elapsed_time": "2:17:04", "remaining_time": "0:09:24", "throughput": 2839.99, "total_tokens": 23356120} {"current_steps": 35715, "total_steps": 38160, "loss": 0.0173, "lr": 6.231725872720251e-07, "epoch": 18.718553459119498, "percentage": 93.59, "elapsed_time": "2:17:05", "remaining_time": "0:09:23", "throughput": 2839.97, "total_tokens": 23359032} {"current_steps": 35720, "total_steps": 38160, "loss": 0.0056, "lr": 6.206380535251716e-07, "epoch": 18.72117400419287, "percentage": 93.61, "elapsed_time": "2:17:06", "remaining_time": "0:09:21", "throughput": 2840.07, "total_tokens": 23363064} {"current_steps": 35725, "total_steps": 38160, "loss": 0.0036, "lr": 6.181086196626995e-07, "epoch": 18.72379454926625, "percentage": 93.62, "elapsed_time": "2:17:07", "remaining_time": "0:09:20", "throughput": 2840.0, "total_tokens": 23365432} {"current_steps": 35730, "total_steps": 38160, "loss": 0.0092, "lr": 6.155842862137384e-07, "epoch": 18.72641509433962, "percentage": 93.63, "elapsed_time": "2:17:08", "remaining_time": "0:09:19", "throughput": 2839.95, "total_tokens": 23368120} {"current_steps": 35735, "total_steps": 38160, "loss": 0.0079, "lr": 6.130650537063548e-07, "epoch": 18.729035639413, "percentage": 93.65, "elapsed_time": "2:17:09", "remaining_time": "0:09:18", "throughput": 2839.99, "total_tokens": 23371576} {"current_steps": 35740, "total_steps": 38160, "loss": 0.0047, "lr": 6.105509226675438e-07, "epoch": 18.731656184486372, "percentage": 93.66, "elapsed_time": "2:17:10", "remaining_time": "0:09:17", "throughput": 2840.13, "total_tokens": 23376216} {"current_steps": 35745, "total_steps": 38160, "loss": 0.0021, "lr": 6.08041893623229e-07, "epoch": 18.73427672955975, "percentage": 93.67, "elapsed_time": "2:17:11", "remaining_time": "0:09:16", "throughput": 2840.13, "total_tokens": 23379256} {"current_steps": 35750, "total_steps": 38160, "loss": 0.0121, "lr": 6.055379670982713e-07, "epoch": 18.736897274633122, "percentage": 93.68, "elapsed_time": "2:17:12", "remaining_time": "0:09:14", "throughput": 2840.09, "total_tokens": 23381912} {"current_steps": 35755, "total_steps": 38160, "loss": 0.0021, "lr": 6.030391436164628e-07, "epoch": 18.7395178197065, "percentage": 93.7, "elapsed_time": "2:17:13", "remaining_time": "0:09:13", "throughput": 2840.04, "total_tokens": 23384568} {"current_steps": 35760, "total_steps": 38160, "loss": 0.0081, "lr": 6.005454237005298e-07, "epoch": 18.742138364779873, "percentage": 93.71, "elapsed_time": "2:17:14", "remaining_time": "0:09:12", "throughput": 2840.0, "total_tokens": 23387320} {"current_steps": 35765, "total_steps": 38160, "loss": 0.0018, "lr": 5.980568078721327e-07, "epoch": 18.74475890985325, "percentage": 93.72, "elapsed_time": "2:17:16", "remaining_time": "0:09:11", "throughput": 2839.97, "total_tokens": 23390168} {"current_steps": 35770, "total_steps": 38160, "loss": 0.0063, "lr": 5.955732966518606e-07, "epoch": 18.747379454926623, "percentage": 93.74, "elapsed_time": "2:17:17", "remaining_time": "0:09:10", "throughput": 2839.96, "total_tokens": 23393080} {"current_steps": 35775, "total_steps": 38160, "loss": 0.0028, "lr": 5.930948905592343e-07, "epoch": 18.75, "percentage": 93.75, "elapsed_time": "2:17:18", "remaining_time": "0:09:09", "throughput": 2839.91, "total_tokens": 23395800} {"current_steps": 35780, "total_steps": 38160, "loss": 0.0023, "lr": 5.906215901127054e-07, "epoch": 18.752620545073377, "percentage": 93.76, "elapsed_time": "2:17:19", "remaining_time": "0:09:08", "throughput": 2839.87, "total_tokens": 23398424} {"current_steps": 35785, "total_steps": 38160, "loss": 0.0078, "lr": 5.881533958296631e-07, "epoch": 18.75524109014675, "percentage": 93.78, "elapsed_time": "2:17:20", "remaining_time": "0:09:06", "throughput": 2839.82, "total_tokens": 23400984} {"current_steps": 35790, "total_steps": 38160, "loss": 0.0086, "lr": 5.856903082264248e-07, "epoch": 18.757861635220127, "percentage": 93.79, "elapsed_time": "2:17:21", "remaining_time": "0:09:05", "throughput": 2839.9, "total_tokens": 23404952} {"current_steps": 35795, "total_steps": 38160, "loss": 0.0081, "lr": 5.832323278182422e-07, "epoch": 18.7604821802935, "percentage": 93.8, "elapsed_time": "2:17:22", "remaining_time": "0:09:04", "throughput": 2839.99, "total_tokens": 23409048} {"current_steps": 35800, "total_steps": 38160, "loss": 0.0047, "lr": 5.807794551192986e-07, "epoch": 18.763102725366878, "percentage": 93.82, "elapsed_time": "2:17:23", "remaining_time": "0:09:03", "throughput": 2839.95, "total_tokens": 23411864} {"current_steps": 35805, "total_steps": 38160, "loss": 0.0045, "lr": 5.783316906427e-07, "epoch": 18.76572327044025, "percentage": 93.83, "elapsed_time": "2:17:24", "remaining_time": "0:09:02", "throughput": 2839.94, "total_tokens": 23414936} {"current_steps": 35810, "total_steps": 38160, "loss": 0.0082, "lr": 5.758890349004925e-07, "epoch": 18.768343815513628, "percentage": 93.84, "elapsed_time": "2:17:25", "remaining_time": "0:09:01", "throughput": 2839.94, "total_tokens": 23417976} {"current_steps": 35815, "total_steps": 38160, "loss": 0.0036, "lr": 5.734514884036563e-07, "epoch": 18.770964360587, "percentage": 93.85, "elapsed_time": "2:17:27", "remaining_time": "0:08:59", "throughput": 2839.89, "total_tokens": 23420984} {"current_steps": 35820, "total_steps": 38160, "loss": 0.0021, "lr": 5.710190516620945e-07, "epoch": 18.77358490566038, "percentage": 93.87, "elapsed_time": "2:17:28", "remaining_time": "0:08:58", "throughput": 2839.89, "total_tokens": 23424120} {"current_steps": 35825, "total_steps": 38160, "loss": 0.0296, "lr": 5.685917251846501e-07, "epoch": 18.77620545073375, "percentage": 93.88, "elapsed_time": "2:17:29", "remaining_time": "0:08:57", "throughput": 2839.81, "total_tokens": 23426584} {"current_steps": 35830, "total_steps": 38160, "loss": 0.003, "lr": 5.661695094790892e-07, "epoch": 18.77882599580713, "percentage": 93.89, "elapsed_time": "2:17:30", "remaining_time": "0:08:56", "throughput": 2839.81, "total_tokens": 23429880} {"current_steps": 35835, "total_steps": 38160, "loss": 0.0021, "lr": 5.637524050521064e-07, "epoch": 18.781446540880502, "percentage": 93.91, "elapsed_time": "2:17:31", "remaining_time": "0:08:55", "throughput": 2839.77, "total_tokens": 23432728} {"current_steps": 35840, "total_steps": 38160, "loss": 0.0182, "lr": 5.613404124093391e-07, "epoch": 18.78406708595388, "percentage": 93.92, "elapsed_time": "2:17:32", "remaining_time": "0:08:54", "throughput": 2839.76, "total_tokens": 23435704} {"current_steps": 35845, "total_steps": 38160, "loss": 0.0042, "lr": 5.589335320553446e-07, "epoch": 18.786687631027252, "percentage": 93.93, "elapsed_time": "2:17:33", "remaining_time": "0:08:53", "throughput": 2839.81, "total_tokens": 23439416} {"current_steps": 35850, "total_steps": 38160, "loss": 0.0086, "lr": 5.565317644936202e-07, "epoch": 18.78930817610063, "percentage": 93.95, "elapsed_time": "2:17:34", "remaining_time": "0:08:51", "throughput": 2839.74, "total_tokens": 23441880} {"current_steps": 35855, "total_steps": 38160, "loss": 0.0067, "lr": 5.541351102265863e-07, "epoch": 18.791928721174003, "percentage": 93.96, "elapsed_time": "2:17:36", "remaining_time": "0:08:50", "throughput": 2839.81, "total_tokens": 23445560} {"current_steps": 35860, "total_steps": 38160, "loss": 0.0027, "lr": 5.51743569755589e-07, "epoch": 18.79454926624738, "percentage": 93.97, "elapsed_time": "2:17:37", "remaining_time": "0:08:49", "throughput": 2839.82, "total_tokens": 23448760} {"current_steps": 35865, "total_steps": 38160, "loss": 0.0021, "lr": 5.493571435809197e-07, "epoch": 18.797169811320753, "percentage": 93.99, "elapsed_time": "2:17:38", "remaining_time": "0:08:48", "throughput": 2839.84, "total_tokens": 23451864} {"current_steps": 35870, "total_steps": 38160, "loss": 0.0283, "lr": 5.469758322017849e-07, "epoch": 18.79979035639413, "percentage": 94.0, "elapsed_time": "2:17:39", "remaining_time": "0:08:47", "throughput": 2840.05, "total_tokens": 23458552} {"current_steps": 35875, "total_steps": 38160, "loss": 0.0077, "lr": 5.445996361163358e-07, "epoch": 18.802410901467507, "percentage": 94.01, "elapsed_time": "2:17:40", "remaining_time": "0:08:46", "throughput": 2840.07, "total_tokens": 23461656} {"current_steps": 35880, "total_steps": 38160, "loss": 0.0279, "lr": 5.422285558216389e-07, "epoch": 18.80503144654088, "percentage": 94.03, "elapsed_time": "2:17:42", "remaining_time": "0:08:45", "throughput": 2840.05, "total_tokens": 23464664} {"current_steps": 35885, "total_steps": 38160, "loss": 0.0076, "lr": 5.398625918137001e-07, "epoch": 18.807651991614257, "percentage": 94.04, "elapsed_time": "2:17:43", "remaining_time": "0:08:43", "throughput": 2840.11, "total_tokens": 23468216} {"current_steps": 35890, "total_steps": 38160, "loss": 0.0066, "lr": 5.375017445874486e-07, "epoch": 18.81027253668763, "percentage": 94.05, "elapsed_time": "2:17:44", "remaining_time": "0:08:42", "throughput": 2840.05, "total_tokens": 23471064} {"current_steps": 35895, "total_steps": 38160, "loss": 0.0026, "lr": 5.351460146367504e-07, "epoch": 18.812893081761008, "percentage": 94.06, "elapsed_time": "2:17:45", "remaining_time": "0:08:41", "throughput": 2840.05, "total_tokens": 23474264} {"current_steps": 35900, "total_steps": 38160, "loss": 0.0064, "lr": 5.327954024543946e-07, "epoch": 18.81551362683438, "percentage": 94.08, "elapsed_time": "2:17:46", "remaining_time": "0:08:40", "throughput": 2840.08, "total_tokens": 23477720} {"current_steps": 35905, "total_steps": 38160, "loss": 0.0017, "lr": 5.304499085321074e-07, "epoch": 18.818134171907758, "percentage": 94.09, "elapsed_time": "2:17:47", "remaining_time": "0:08:39", "throughput": 2840.03, "total_tokens": 23480344} {"current_steps": 35910, "total_steps": 38160, "loss": 0.0044, "lr": 5.281095333605352e-07, "epoch": 18.82075471698113, "percentage": 94.1, "elapsed_time": "2:17:48", "remaining_time": "0:08:38", "throughput": 2840.04, "total_tokens": 23483544} {"current_steps": 35915, "total_steps": 38160, "loss": 0.0031, "lr": 5.257742774292556e-07, "epoch": 18.82337526205451, "percentage": 94.12, "elapsed_time": "2:17:49", "remaining_time": "0:08:36", "throughput": 2840.03, "total_tokens": 23486392} {"current_steps": 35920, "total_steps": 38160, "loss": 0.0103, "lr": 5.234441412267837e-07, "epoch": 18.82599580712788, "percentage": 94.13, "elapsed_time": "2:17:50", "remaining_time": "0:08:35", "throughput": 2840.09, "total_tokens": 23490200} {"current_steps": 35925, "total_steps": 38160, "loss": 0.0029, "lr": 5.211191252405517e-07, "epoch": 18.82861635220126, "percentage": 94.14, "elapsed_time": "2:17:52", "remaining_time": "0:08:34", "throughput": 2840.06, "total_tokens": 23493048} {"current_steps": 35930, "total_steps": 38160, "loss": 0.0169, "lr": 5.187992299569316e-07, "epoch": 18.831236897274632, "percentage": 94.16, "elapsed_time": "2:17:53", "remaining_time": "0:08:33", "throughput": 2840.09, "total_tokens": 23496440} {"current_steps": 35935, "total_steps": 38160, "loss": 0.0053, "lr": 5.164844558612131e-07, "epoch": 18.83385744234801, "percentage": 94.17, "elapsed_time": "2:17:54", "remaining_time": "0:08:32", "throughput": 2840.11, "total_tokens": 23499832} {"current_steps": 35940, "total_steps": 38160, "loss": 0.0082, "lr": 5.141748034376254e-07, "epoch": 18.836477987421382, "percentage": 94.18, "elapsed_time": "2:17:55", "remaining_time": "0:08:31", "throughput": 2840.16, "total_tokens": 23503416} {"current_steps": 35945, "total_steps": 38160, "loss": 0.0034, "lr": 5.118702731693209e-07, "epoch": 18.83909853249476, "percentage": 94.2, "elapsed_time": "2:17:56", "remaining_time": "0:08:30", "throughput": 2840.17, "total_tokens": 23506616} {"current_steps": 35950, "total_steps": 38160, "loss": 0.0057, "lr": 5.095708655383751e-07, "epoch": 18.841719077568133, "percentage": 94.21, "elapsed_time": "2:17:57", "remaining_time": "0:08:28", "throughput": 2840.19, "total_tokens": 23509912} {"current_steps": 35955, "total_steps": 38160, "loss": 0.0036, "lr": 5.07276581025809e-07, "epoch": 18.84433962264151, "percentage": 94.22, "elapsed_time": "2:17:58", "remaining_time": "0:08:27", "throughput": 2840.23, "total_tokens": 23513272} {"current_steps": 35960, "total_steps": 38160, "loss": 0.0055, "lr": 5.049874201115495e-07, "epoch": 18.846960167714883, "percentage": 94.23, "elapsed_time": "2:17:59", "remaining_time": "0:08:26", "throughput": 2840.2, "total_tokens": 23515992} {"current_steps": 35965, "total_steps": 38160, "loss": 0.0054, "lr": 5.027033832744693e-07, "epoch": 18.84958071278826, "percentage": 94.25, "elapsed_time": "2:18:00", "remaining_time": "0:08:25", "throughput": 2840.2, "total_tokens": 23519032} {"current_steps": 35970, "total_steps": 38160, "loss": 0.0046, "lr": 5.004244709923639e-07, "epoch": 18.852201257861637, "percentage": 94.26, "elapsed_time": "2:18:01", "remaining_time": "0:08:24", "throughput": 2840.24, "total_tokens": 23522392} {"current_steps": 35975, "total_steps": 38160, "loss": 0.0046, "lr": 4.981506837419519e-07, "epoch": 18.85482180293501, "percentage": 94.27, "elapsed_time": "2:18:02", "remaining_time": "0:08:23", "throughput": 2840.22, "total_tokens": 23525240} {"current_steps": 35980, "total_steps": 38160, "loss": 0.0117, "lr": 4.958820219988836e-07, "epoch": 18.857442348008387, "percentage": 94.29, "elapsed_time": "2:18:04", "remaining_time": "0:08:21", "throughput": 2840.23, "total_tokens": 23528568} {"current_steps": 35985, "total_steps": 38160, "loss": 0.0065, "lr": 4.936184862377402e-07, "epoch": 18.86006289308176, "percentage": 94.3, "elapsed_time": "2:18:05", "remaining_time": "0:08:20", "throughput": 2840.2, "total_tokens": 23531288} {"current_steps": 35990, "total_steps": 38160, "loss": 0.0044, "lr": 4.913600769320237e-07, "epoch": 18.862683438155138, "percentage": 94.31, "elapsed_time": "2:18:06", "remaining_time": "0:08:19", "throughput": 2840.23, "total_tokens": 23534520} {"current_steps": 35995, "total_steps": 38160, "loss": 0.0045, "lr": 4.891067945541728e-07, "epoch": 18.86530398322851, "percentage": 94.33, "elapsed_time": "2:18:07", "remaining_time": "0:08:18", "throughput": 2840.28, "total_tokens": 23537880} {"current_steps": 36000, "total_steps": 38160, "loss": 0.0036, "lr": 4.868586395755437e-07, "epoch": 18.867924528301888, "percentage": 94.34, "elapsed_time": "2:18:08", "remaining_time": "0:08:17", "throughput": 2840.32, "total_tokens": 23541464} {"current_steps": 36005, "total_steps": 38160, "loss": 0.0067, "lr": 4.846156124664242e-07, "epoch": 18.87054507337526, "percentage": 94.35, "elapsed_time": "2:18:09", "remaining_time": "0:08:16", "throughput": 2840.35, "total_tokens": 23544760} {"current_steps": 36010, "total_steps": 38160, "loss": 0.0037, "lr": 4.823777136960362e-07, "epoch": 18.87316561844864, "percentage": 94.37, "elapsed_time": "2:18:10", "remaining_time": "0:08:14", "throughput": 2840.33, "total_tokens": 23547832} {"current_steps": 36015, "total_steps": 38160, "loss": 0.0013, "lr": 4.801449437325162e-07, "epoch": 18.87578616352201, "percentage": 94.38, "elapsed_time": "2:18:11", "remaining_time": "0:08:13", "throughput": 2840.34, "total_tokens": 23550968} {"current_steps": 36020, "total_steps": 38160, "loss": 0.0065, "lr": 4.779173030429379e-07, "epoch": 18.87840670859539, "percentage": 94.39, "elapsed_time": "2:18:12", "remaining_time": "0:08:12", "throughput": 2840.39, "total_tokens": 23554680} {"current_steps": 36025, "total_steps": 38160, "loss": 0.0028, "lr": 4.7569479209329804e-07, "epoch": 18.881027253668762, "percentage": 94.41, "elapsed_time": "2:18:13", "remaining_time": "0:08:11", "throughput": 2840.43, "total_tokens": 23558168} {"current_steps": 36030, "total_steps": 38160, "loss": 0.0039, "lr": 4.734774113485163e-07, "epoch": 18.88364779874214, "percentage": 94.42, "elapsed_time": "2:18:14", "remaining_time": "0:08:10", "throughput": 2840.39, "total_tokens": 23560952} {"current_steps": 36035, "total_steps": 38160, "loss": 0.0027, "lr": 4.7126516127244945e-07, "epoch": 18.886268343815512, "percentage": 94.43, "elapsed_time": "2:18:16", "remaining_time": "0:08:09", "throughput": 2840.28, "total_tokens": 23563096} {"current_steps": 36040, "total_steps": 38160, "loss": 0.0298, "lr": 4.690580423278718e-07, "epoch": 18.88888888888889, "percentage": 94.44, "elapsed_time": "2:18:17", "remaining_time": "0:08:08", "throughput": 2840.19, "total_tokens": 23565400} {"current_steps": 36045, "total_steps": 38160, "loss": 0.0038, "lr": 4.668560549764861e-07, "epoch": 18.891509433962263, "percentage": 94.46, "elapsed_time": "2:18:18", "remaining_time": "0:08:06", "throughput": 2840.27, "total_tokens": 23569016} {"current_steps": 36050, "total_steps": 38160, "loss": 0.0035, "lr": 4.646591996789268e-07, "epoch": 18.89412997903564, "percentage": 94.47, "elapsed_time": "2:18:19", "remaining_time": "0:08:05", "throughput": 2840.27, "total_tokens": 23572216} {"current_steps": 36055, "total_steps": 38160, "loss": 0.0096, "lr": 4.6246747689474847e-07, "epoch": 18.896750524109013, "percentage": 94.48, "elapsed_time": "2:18:20", "remaining_time": "0:08:04", "throughput": 2840.34, "total_tokens": 23576056} {"current_steps": 36060, "total_steps": 38160, "loss": 0.0147, "lr": 4.6028088708243434e-07, "epoch": 18.89937106918239, "percentage": 94.5, "elapsed_time": "2:18:21", "remaining_time": "0:08:03", "throughput": 2840.34, "total_tokens": 23579096} {"current_steps": 36065, "total_steps": 38160, "loss": 0.0034, "lr": 4.580994306993991e-07, "epoch": 18.901991614255767, "percentage": 94.51, "elapsed_time": "2:18:22", "remaining_time": "0:08:02", "throughput": 2840.27, "total_tokens": 23581720} {"current_steps": 36070, "total_steps": 38160, "loss": 0.0134, "lr": 4.5592310820196936e-07, "epoch": 18.90461215932914, "percentage": 94.52, "elapsed_time": "2:18:23", "remaining_time": "0:08:01", "throughput": 2840.28, "total_tokens": 23584824} {"current_steps": 36075, "total_steps": 38160, "loss": 0.0024, "lr": 4.537519200454116e-07, "epoch": 18.907232704402517, "percentage": 94.54, "elapsed_time": "2:18:24", "remaining_time": "0:07:59", "throughput": 2840.27, "total_tokens": 23587800} {"current_steps": 36080, "total_steps": 38160, "loss": 0.0852, "lr": 4.515858666839151e-07, "epoch": 18.90985324947589, "percentage": 94.55, "elapsed_time": "2:18:25", "remaining_time": "0:07:58", "throughput": 2840.24, "total_tokens": 23590584} {"current_steps": 36085, "total_steps": 38160, "loss": 0.0629, "lr": 4.494249485705926e-07, "epoch": 18.912473794549268, "percentage": 94.56, "elapsed_time": "2:18:27", "remaining_time": "0:07:57", "throughput": 2840.27, "total_tokens": 23594392} {"current_steps": 36090, "total_steps": 38160, "loss": 0.0026, "lr": 4.472691661574824e-07, "epoch": 18.91509433962264, "percentage": 94.58, "elapsed_time": "2:18:28", "remaining_time": "0:07:56", "throughput": 2840.24, "total_tokens": 23597176} {"current_steps": 36095, "total_steps": 38160, "loss": 0.0026, "lr": 4.4511851989555156e-07, "epoch": 18.917714884696018, "percentage": 94.59, "elapsed_time": "2:18:29", "remaining_time": "0:07:55", "throughput": 2840.27, "total_tokens": 23600600} {"current_steps": 36100, "total_steps": 38160, "loss": 0.0051, "lr": 4.429730102346874e-07, "epoch": 18.92033542976939, "percentage": 94.6, "elapsed_time": "2:18:30", "remaining_time": "0:07:54", "throughput": 2840.24, "total_tokens": 23603480} {"current_steps": 36105, "total_steps": 38160, "loss": 0.0023, "lr": 4.4083263762370873e-07, "epoch": 18.92295597484277, "percentage": 94.61, "elapsed_time": "2:18:31", "remaining_time": "0:07:53", "throughput": 2840.12, "total_tokens": 23605784} {"current_steps": 36110, "total_steps": 38160, "loss": 0.0045, "lr": 4.386974025103574e-07, "epoch": 18.92557651991614, "percentage": 94.63, "elapsed_time": "2:18:32", "remaining_time": "0:07:51", "throughput": 2840.15, "total_tokens": 23609144} {"current_steps": 36115, "total_steps": 38160, "loss": 0.0116, "lr": 4.365673053413011e-07, "epoch": 18.92819706498952, "percentage": 94.64, "elapsed_time": "2:18:33", "remaining_time": "0:07:50", "throughput": 2840.12, "total_tokens": 23611960} {"current_steps": 36120, "total_steps": 38160, "loss": 0.0029, "lr": 4.34442346562125e-07, "epoch": 18.930817610062892, "percentage": 94.65, "elapsed_time": "2:18:34", "remaining_time": "0:07:49", "throughput": 2840.07, "total_tokens": 23614680} {"current_steps": 36125, "total_steps": 38160, "loss": 0.0098, "lr": 4.323225266173542e-07, "epoch": 18.93343815513627, "percentage": 94.67, "elapsed_time": "2:18:35", "remaining_time": "0:07:48", "throughput": 2840.04, "total_tokens": 23617592} {"current_steps": 36130, "total_steps": 38160, "loss": 0.0068, "lr": 4.302078459504283e-07, "epoch": 18.936058700209642, "percentage": 94.68, "elapsed_time": "2:18:37", "remaining_time": "0:07:47", "throughput": 2839.98, "total_tokens": 23620440} {"current_steps": 36135, "total_steps": 38160, "loss": 0.0014, "lr": 4.2809830500371294e-07, "epoch": 18.93867924528302, "percentage": 94.69, "elapsed_time": "2:18:38", "remaining_time": "0:07:46", "throughput": 2839.96, "total_tokens": 23623320} {"current_steps": 36140, "total_steps": 38160, "loss": 0.0029, "lr": 4.2599390421850236e-07, "epoch": 18.941299790356393, "percentage": 94.71, "elapsed_time": "2:18:39", "remaining_time": "0:07:44", "throughput": 2839.95, "total_tokens": 23626168} {"current_steps": 36145, "total_steps": 38160, "loss": 0.0202, "lr": 4.2389464403501113e-07, "epoch": 18.94392033542977, "percentage": 94.72, "elapsed_time": "2:18:40", "remaining_time": "0:07:43", "throughput": 2839.94, "total_tokens": 23629240} {"current_steps": 36150, "total_steps": 38160, "loss": 0.0043, "lr": 4.218005248923823e-07, "epoch": 18.946540880503143, "percentage": 94.73, "elapsed_time": "2:18:41", "remaining_time": "0:07:42", "throughput": 2839.97, "total_tokens": 23632472} {"current_steps": 36155, "total_steps": 38160, "loss": 0.005, "lr": 4.1971154722867946e-07, "epoch": 18.94916142557652, "percentage": 94.75, "elapsed_time": "2:18:42", "remaining_time": "0:07:41", "throughput": 2839.96, "total_tokens": 23635864} {"current_steps": 36160, "total_steps": 38160, "loss": 0.006, "lr": 4.176277114808946e-07, "epoch": 18.951781970649897, "percentage": 94.76, "elapsed_time": "2:18:43", "remaining_time": "0:07:40", "throughput": 2839.91, "total_tokens": 23638712} {"current_steps": 36165, "total_steps": 38160, "loss": 0.004, "lr": 4.155490180849431e-07, "epoch": 18.95440251572327, "percentage": 94.77, "elapsed_time": "2:18:44", "remaining_time": "0:07:39", "throughput": 2839.89, "total_tokens": 23641592} {"current_steps": 36170, "total_steps": 38160, "loss": 0.0081, "lr": 4.1347546747566304e-07, "epoch": 18.957023060796647, "percentage": 94.79, "elapsed_time": "2:18:46", "remaining_time": "0:07:38", "throughput": 2839.95, "total_tokens": 23645912} {"current_steps": 36175, "total_steps": 38160, "loss": 0.0033, "lr": 4.114070600868131e-07, "epoch": 18.95964360587002, "percentage": 94.8, "elapsed_time": "2:18:47", "remaining_time": "0:07:36", "throughput": 2839.93, "total_tokens": 23648824} {"current_steps": 36180, "total_steps": 38160, "loss": 0.0013, "lr": 4.093437963510888e-07, "epoch": 18.962264150943398, "percentage": 94.81, "elapsed_time": "2:18:48", "remaining_time": "0:07:35", "throughput": 2839.82, "total_tokens": 23651096} {"current_steps": 36185, "total_steps": 38160, "loss": 0.0083, "lr": 4.072856767000949e-07, "epoch": 18.96488469601677, "percentage": 94.82, "elapsed_time": "2:18:49", "remaining_time": "0:07:34", "throughput": 2839.85, "total_tokens": 23654616} {"current_steps": 36190, "total_steps": 38160, "loss": 0.0122, "lr": 4.052327015643703e-07, "epoch": 18.967505241090148, "percentage": 94.84, "elapsed_time": "2:18:50", "remaining_time": "0:07:33", "throughput": 2839.88, "total_tokens": 23658200} {"current_steps": 36195, "total_steps": 38160, "loss": 0.0041, "lr": 4.031848713733744e-07, "epoch": 18.97012578616352, "percentage": 94.85, "elapsed_time": "2:18:51", "remaining_time": "0:07:32", "throughput": 2839.82, "total_tokens": 23660856} {"current_steps": 36200, "total_steps": 38160, "loss": 0.0029, "lr": 4.011421865554837e-07, "epoch": 18.9727463312369, "percentage": 94.86, "elapsed_time": "2:18:52", "remaining_time": "0:07:31", "throughput": 2839.82, "total_tokens": 23664056} {"current_steps": 36205, "total_steps": 38160, "loss": 0.0057, "lr": 3.9910464753801224e-07, "epoch": 18.97536687631027, "percentage": 94.88, "elapsed_time": "2:18:54", "remaining_time": "0:07:30", "throughput": 2839.81, "total_tokens": 23667256} {"current_steps": 36210, "total_steps": 38160, "loss": 0.0089, "lr": 3.9707225474718557e-07, "epoch": 18.97798742138365, "percentage": 94.89, "elapsed_time": "2:18:55", "remaining_time": "0:07:28", "throughput": 2839.82, "total_tokens": 23670456} {"current_steps": 36215, "total_steps": 38160, "loss": 0.0017, "lr": 3.950450086081553e-07, "epoch": 18.980607966457022, "percentage": 94.9, "elapsed_time": "2:18:56", "remaining_time": "0:07:27", "throughput": 2839.83, "total_tokens": 23673656} {"current_steps": 36220, "total_steps": 38160, "loss": 0.0154, "lr": 3.930229095450072e-07, "epoch": 18.9832285115304, "percentage": 94.92, "elapsed_time": "2:18:57", "remaining_time": "0:07:26", "throughput": 2839.83, "total_tokens": 23676824} {"current_steps": 36225, "total_steps": 38160, "loss": 0.0061, "lr": 3.9100595798073345e-07, "epoch": 18.985849056603772, "percentage": 94.93, "elapsed_time": "2:18:58", "remaining_time": "0:07:25", "throughput": 2839.8, "total_tokens": 23679832} {"current_steps": 36230, "total_steps": 38160, "loss": 0.0067, "lr": 3.8899415433725493e-07, "epoch": 18.98846960167715, "percentage": 94.94, "elapsed_time": "2:18:59", "remaining_time": "0:07:24", "throughput": 2839.79, "total_tokens": 23682808} {"current_steps": 36235, "total_steps": 38160, "loss": 0.0043, "lr": 3.8698749903542666e-07, "epoch": 18.991090146750523, "percentage": 94.96, "elapsed_time": "2:19:00", "remaining_time": "0:07:23", "throughput": 2839.78, "total_tokens": 23685976} {"current_steps": 36240, "total_steps": 38160, "loss": 0.0116, "lr": 3.8498599249501e-07, "epoch": 18.9937106918239, "percentage": 94.97, "elapsed_time": "2:19:01", "remaining_time": "0:07:21", "throughput": 2839.76, "total_tokens": 23688952} {"current_steps": 36245, "total_steps": 38160, "loss": 0.0051, "lr": 3.8298963513470345e-07, "epoch": 18.996331236897273, "percentage": 94.98, "elapsed_time": "2:19:02", "remaining_time": "0:07:20", "throughput": 2839.75, "total_tokens": 23691832} {"current_steps": 36250, "total_steps": 38160, "loss": 0.0037, "lr": 3.8099842737211734e-07, "epoch": 18.99895178197065, "percentage": 94.99, "elapsed_time": "2:19:04", "remaining_time": "0:07:19", "throughput": 2839.8, "total_tokens": 23695544} {"current_steps": 36252, "total_steps": 38160, "eval_loss": 1.618476152420044, "epoch": 19.0, "percentage": 95.0, "elapsed_time": "2:19:16", "remaining_time": "0:07:19", "throughput": 2835.68, "total_tokens": 23696296} {"current_steps": 36255, "total_steps": 38160, "loss": 0.0038, "lr": 3.7901236962379627e-07, "epoch": 19.001572327044027, "percentage": 95.01, "elapsed_time": "2:19:20", "remaining_time": "0:07:19", "throughput": 2834.46, "total_tokens": 23697768} {"current_steps": 36260, "total_steps": 38160, "loss": 0.0017, "lr": 3.7703146230519126e-07, "epoch": 19.0041928721174, "percentage": 95.02, "elapsed_time": "2:19:21", "remaining_time": "0:07:18", "throughput": 2834.37, "total_tokens": 23700072} {"current_steps": 36265, "total_steps": 38160, "loss": 0.0087, "lr": 3.7505570583069306e-07, "epoch": 19.006813417190777, "percentage": 95.03, "elapsed_time": "2:19:22", "remaining_time": "0:07:16", "throughput": 2834.35, "total_tokens": 23702856} {"current_steps": 36270, "total_steps": 38160, "loss": 0.0068, "lr": 3.7308510061360435e-07, "epoch": 19.00943396226415, "percentage": 95.05, "elapsed_time": "2:19:23", "remaining_time": "0:07:15", "throughput": 2834.37, "total_tokens": 23706184} {"current_steps": 36275, "total_steps": 38160, "loss": 0.0045, "lr": 3.7111964706615374e-07, "epoch": 19.012054507337528, "percentage": 95.06, "elapsed_time": "2:19:24", "remaining_time": "0:07:14", "throughput": 2834.37, "total_tokens": 23709128} {"current_steps": 36280, "total_steps": 38160, "loss": 0.0155, "lr": 3.691593455994929e-07, "epoch": 19.0146750524109, "percentage": 95.07, "elapsed_time": "2:19:26", "remaining_time": "0:07:13", "throughput": 2834.42, "total_tokens": 23712808} {"current_steps": 36285, "total_steps": 38160, "loss": 0.0038, "lr": 3.672041966236911e-07, "epoch": 19.017295597484278, "percentage": 95.09, "elapsed_time": "2:19:27", "remaining_time": "0:07:12", "throughput": 2834.45, "total_tokens": 23716168} {"current_steps": 36290, "total_steps": 38160, "loss": 0.0021, "lr": 3.6525420054774884e-07, "epoch": 19.01991614255765, "percentage": 95.1, "elapsed_time": "2:19:28", "remaining_time": "0:07:11", "throughput": 2834.48, "total_tokens": 23719688} {"current_steps": 36295, "total_steps": 38160, "loss": 0.0071, "lr": 3.6330935777957597e-07, "epoch": 19.02253668763103, "percentage": 95.11, "elapsed_time": "2:19:29", "remaining_time": "0:07:10", "throughput": 2834.54, "total_tokens": 23723752} {"current_steps": 36300, "total_steps": 38160, "loss": 0.0039, "lr": 3.613696687260193e-07, "epoch": 19.0251572327044, "percentage": 95.13, "elapsed_time": "2:19:30", "remaining_time": "0:07:08", "throughput": 2834.6, "total_tokens": 23727432} {"current_steps": 36305, "total_steps": 38160, "loss": 0.0019, "lr": 3.59435133792832e-07, "epoch": 19.02777777777778, "percentage": 95.14, "elapsed_time": "2:19:31", "remaining_time": "0:07:07", "throughput": 2834.57, "total_tokens": 23730312} {"current_steps": 36310, "total_steps": 38160, "loss": 0.0037, "lr": 3.575057533847043e-07, "epoch": 19.030398322851152, "percentage": 95.15, "elapsed_time": "2:19:32", "remaining_time": "0:07:06", "throughput": 2834.58, "total_tokens": 23733448} {"current_steps": 36315, "total_steps": 38160, "loss": 0.0036, "lr": 3.555815279052327e-07, "epoch": 19.03301886792453, "percentage": 95.17, "elapsed_time": "2:19:34", "remaining_time": "0:07:05", "throughput": 2834.63, "total_tokens": 23737320} {"current_steps": 36320, "total_steps": 38160, "loss": 0.0034, "lr": 3.5366245775694805e-07, "epoch": 19.035639412997902, "percentage": 95.18, "elapsed_time": "2:19:35", "remaining_time": "0:07:04", "throughput": 2834.55, "total_tokens": 23739752} {"current_steps": 36325, "total_steps": 38160, "loss": 0.0029, "lr": 3.517485433412987e-07, "epoch": 19.03825995807128, "percentage": 95.19, "elapsed_time": "2:19:36", "remaining_time": "0:07:03", "throughput": 2834.46, "total_tokens": 23742152} {"current_steps": 36330, "total_steps": 38160, "loss": 0.0094, "lr": 3.4983978505865044e-07, "epoch": 19.040880503144653, "percentage": 95.2, "elapsed_time": "2:19:37", "remaining_time": "0:07:01", "throughput": 2834.47, "total_tokens": 23745448} {"current_steps": 36335, "total_steps": 38160, "loss": 0.0159, "lr": 3.47936183308295e-07, "epoch": 19.04350104821803, "percentage": 95.22, "elapsed_time": "2:19:38", "remaining_time": "0:07:00", "throughput": 2834.58, "total_tokens": 23749864} {"current_steps": 36340, "total_steps": 38160, "loss": 0.0106, "lr": 3.460377384884472e-07, "epoch": 19.046121593291403, "percentage": 95.23, "elapsed_time": "2:19:39", "remaining_time": "0:06:59", "throughput": 2834.53, "total_tokens": 23752552} {"current_steps": 36345, "total_steps": 38160, "loss": 0.0134, "lr": 3.4414445099623384e-07, "epoch": 19.04874213836478, "percentage": 95.24, "elapsed_time": "2:19:40", "remaining_time": "0:06:58", "throughput": 2834.51, "total_tokens": 23755528} {"current_steps": 36350, "total_steps": 38160, "loss": 0.0032, "lr": 3.42256321227713e-07, "epoch": 19.051362683438157, "percentage": 95.26, "elapsed_time": "2:19:41", "remaining_time": "0:06:57", "throughput": 2834.51, "total_tokens": 23758600} {"current_steps": 36355, "total_steps": 38160, "loss": 0.0024, "lr": 3.403733495778605e-07, "epoch": 19.05398322851153, "percentage": 95.27, "elapsed_time": "2:19:43", "remaining_time": "0:06:56", "throughput": 2834.47, "total_tokens": 23761480} {"current_steps": 36360, "total_steps": 38160, "loss": 0.0065, "lr": 3.3849553644056955e-07, "epoch": 19.056603773584907, "percentage": 95.28, "elapsed_time": "2:19:44", "remaining_time": "0:06:55", "throughput": 2834.4, "total_tokens": 23764168} {"current_steps": 36365, "total_steps": 38160, "loss": 0.0026, "lr": 3.36622882208662e-07, "epoch": 19.05922431865828, "percentage": 95.3, "elapsed_time": "2:19:45", "remaining_time": "0:06:53", "throughput": 2834.36, "total_tokens": 23766920} {"current_steps": 36370, "total_steps": 38160, "loss": 0.0027, "lr": 3.347553872738718e-07, "epoch": 19.061844863731658, "percentage": 95.31, "elapsed_time": "2:19:46", "remaining_time": "0:06:52", "throughput": 2834.34, "total_tokens": 23770056} {"current_steps": 36375, "total_steps": 38160, "loss": 0.0017, "lr": 3.3289305202685583e-07, "epoch": 19.06446540880503, "percentage": 95.32, "elapsed_time": "2:19:47", "remaining_time": "0:06:51", "throughput": 2834.33, "total_tokens": 23773096} {"current_steps": 36380, "total_steps": 38160, "loss": 0.0068, "lr": 3.310358768571997e-07, "epoch": 19.067085953878408, "percentage": 95.34, "elapsed_time": "2:19:48", "remaining_time": "0:06:50", "throughput": 2834.26, "total_tokens": 23775496} {"current_steps": 36385, "total_steps": 38160, "loss": 0.0052, "lr": 3.2918386215339827e-07, "epoch": 19.06970649895178, "percentage": 95.35, "elapsed_time": "2:19:49", "remaining_time": "0:06:49", "throughput": 2834.26, "total_tokens": 23778600} {"current_steps": 36390, "total_steps": 38160, "loss": 0.0095, "lr": 3.2733700830287205e-07, "epoch": 19.072327044025158, "percentage": 95.36, "elapsed_time": "2:19:51", "remaining_time": "0:06:48", "throughput": 2834.34, "total_tokens": 23783688} {"current_steps": 36395, "total_steps": 38160, "loss": 0.038, "lr": 3.254953156919649e-07, "epoch": 19.07494758909853, "percentage": 95.37, "elapsed_time": "2:19:52", "remaining_time": "0:06:46", "throughput": 2834.3, "total_tokens": 23786440} {"current_steps": 36400, "total_steps": 38160, "loss": 0.0202, "lr": 3.2365878470593527e-07, "epoch": 19.07756813417191, "percentage": 95.39, "elapsed_time": "2:19:53", "remaining_time": "0:06:45", "throughput": 2834.33, "total_tokens": 23789768} {"current_steps": 36405, "total_steps": 38160, "loss": 0.0036, "lr": 3.2182741572896747e-07, "epoch": 19.080188679245282, "percentage": 95.4, "elapsed_time": "2:19:54", "remaining_time": "0:06:44", "throughput": 2834.27, "total_tokens": 23792264} {"current_steps": 36410, "total_steps": 38160, "loss": 0.0032, "lr": 3.2000120914415786e-07, "epoch": 19.08280922431866, "percentage": 95.41, "elapsed_time": "2:19:55", "remaining_time": "0:06:43", "throughput": 2834.34, "total_tokens": 23795816} {"current_steps": 36415, "total_steps": 38160, "loss": 0.0429, "lr": 3.181801653335315e-07, "epoch": 19.085429769392032, "percentage": 95.43, "elapsed_time": "2:19:56", "remaining_time": "0:06:42", "throughput": 2834.34, "total_tokens": 23798984} {"current_steps": 36420, "total_steps": 38160, "loss": 0.0045, "lr": 3.163642846780307e-07, "epoch": 19.08805031446541, "percentage": 95.44, "elapsed_time": "2:19:57", "remaining_time": "0:06:41", "throughput": 2834.34, "total_tokens": 23802056} {"current_steps": 36425, "total_steps": 38160, "loss": 0.002, "lr": 3.1455356755751565e-07, "epoch": 19.090670859538783, "percentage": 95.45, "elapsed_time": "2:19:58", "remaining_time": "0:06:40", "throughput": 2834.27, "total_tokens": 23804424} {"current_steps": 36430, "total_steps": 38160, "loss": 0.0046, "lr": 3.127480143507666e-07, "epoch": 19.09329140461216, "percentage": 95.47, "elapsed_time": "2:19:59", "remaining_time": "0:06:38", "throughput": 2834.23, "total_tokens": 23807112} {"current_steps": 36435, "total_steps": 38160, "loss": 0.0118, "lr": 3.1094762543548704e-07, "epoch": 19.095911949685533, "percentage": 95.48, "elapsed_time": "2:20:00", "remaining_time": "0:06:37", "throughput": 2834.23, "total_tokens": 23810184} {"current_steps": 36440, "total_steps": 38160, "loss": 0.0032, "lr": 3.091524011882951e-07, "epoch": 19.09853249475891, "percentage": 95.49, "elapsed_time": "2:20:02", "remaining_time": "0:06:36", "throughput": 2834.15, "total_tokens": 23812776} {"current_steps": 36445, "total_steps": 38160, "loss": 0.0038, "lr": 3.073623419847349e-07, "epoch": 19.101153039832287, "percentage": 95.51, "elapsed_time": "2:20:03", "remaining_time": "0:06:35", "throughput": 2834.18, "total_tokens": 23816296} {"current_steps": 36450, "total_steps": 38160, "loss": 0.0025, "lr": 3.0557744819926235e-07, "epoch": 19.10377358490566, "percentage": 95.52, "elapsed_time": "2:20:04", "remaining_time": "0:06:34", "throughput": 2834.2, "total_tokens": 23819432} {"current_steps": 36455, "total_steps": 38160, "loss": 0.005, "lr": 3.037977202052594e-07, "epoch": 19.106394129979037, "percentage": 95.53, "elapsed_time": "2:20:05", "remaining_time": "0:06:33", "throughput": 2834.2, "total_tokens": 23822600} {"current_steps": 36460, "total_steps": 38160, "loss": 0.0033, "lr": 3.020231583750255e-07, "epoch": 19.10901467505241, "percentage": 95.55, "elapsed_time": "2:20:06", "remaining_time": "0:06:31", "throughput": 2834.16, "total_tokens": 23825512} {"current_steps": 36465, "total_steps": 38160, "loss": 0.0051, "lr": 3.002537630797747e-07, "epoch": 19.111635220125788, "percentage": 95.56, "elapsed_time": "2:20:07", "remaining_time": "0:06:30", "throughput": 2834.15, "total_tokens": 23828456} {"current_steps": 36470, "total_steps": 38160, "loss": 0.0036, "lr": 2.984895346896499e-07, "epoch": 19.11425576519916, "percentage": 95.57, "elapsed_time": "2:20:08", "remaining_time": "0:06:29", "throughput": 2834.17, "total_tokens": 23831656} {"current_steps": 36475, "total_steps": 38160, "loss": 0.0023, "lr": 2.967304735737031e-07, "epoch": 19.116876310272538, "percentage": 95.58, "elapsed_time": "2:20:09", "remaining_time": "0:06:28", "throughput": 2834.11, "total_tokens": 23834312} {"current_steps": 36480, "total_steps": 38160, "loss": 0.0051, "lr": 2.9497658009991214e-07, "epoch": 19.11949685534591, "percentage": 95.6, "elapsed_time": "2:20:10", "remaining_time": "0:06:27", "throughput": 2834.06, "total_tokens": 23836968} {"current_steps": 36485, "total_steps": 38160, "loss": 0.0183, "lr": 2.932278546351724e-07, "epoch": 19.122117400419288, "percentage": 95.61, "elapsed_time": "2:20:12", "remaining_time": "0:06:26", "throughput": 2834.11, "total_tokens": 23840616} {"current_steps": 36490, "total_steps": 38160, "loss": 0.0062, "lr": 2.9148429754529137e-07, "epoch": 19.12473794549266, "percentage": 95.62, "elapsed_time": "2:20:13", "remaining_time": "0:06:25", "throughput": 2834.17, "total_tokens": 23844168} {"current_steps": 36495, "total_steps": 38160, "loss": 0.0072, "lr": 2.897459091950078e-07, "epoch": 19.12735849056604, "percentage": 95.64, "elapsed_time": "2:20:14", "remaining_time": "0:06:23", "throughput": 2834.13, "total_tokens": 23846888} {"current_steps": 36500, "total_steps": 38160, "loss": 0.0063, "lr": 2.880126899479724e-07, "epoch": 19.129979035639412, "percentage": 95.65, "elapsed_time": "2:20:15", "remaining_time": "0:06:22", "throughput": 2834.23, "total_tokens": 23850856} {"current_steps": 36505, "total_steps": 38160, "loss": 0.0044, "lr": 2.862846401667507e-07, "epoch": 19.13259958071279, "percentage": 95.66, "elapsed_time": "2:20:16", "remaining_time": "0:06:21", "throughput": 2834.23, "total_tokens": 23853992} {"current_steps": 36510, "total_steps": 38160, "loss": 0.005, "lr": 2.8456176021283697e-07, "epoch": 19.135220125786162, "percentage": 95.68, "elapsed_time": "2:20:17", "remaining_time": "0:06:20", "throughput": 2834.3, "total_tokens": 23857864} {"current_steps": 36515, "total_steps": 38160, "loss": 0.0022, "lr": 2.8284405044662897e-07, "epoch": 19.13784067085954, "percentage": 95.69, "elapsed_time": "2:20:18", "remaining_time": "0:06:19", "throughput": 2834.34, "total_tokens": 23861480} {"current_steps": 36520, "total_steps": 38160, "loss": 0.0036, "lr": 2.8113151122745874e-07, "epoch": 19.140461215932913, "percentage": 95.7, "elapsed_time": "2:20:19", "remaining_time": "0:06:18", "throughput": 2834.33, "total_tokens": 23864424} {"current_steps": 36525, "total_steps": 38160, "loss": 0.0038, "lr": 2.7942414291357023e-07, "epoch": 19.14308176100629, "percentage": 95.72, "elapsed_time": "2:20:20", "remaining_time": "0:06:16", "throughput": 2834.31, "total_tokens": 23867272} {"current_steps": 36530, "total_steps": 38160, "loss": 0.006, "lr": 2.777219458621222e-07, "epoch": 19.145702306079663, "percentage": 95.73, "elapsed_time": "2:20:21", "remaining_time": "0:06:15", "throughput": 2834.4, "total_tokens": 23871272} {"current_steps": 36535, "total_steps": 38160, "loss": 0.0017, "lr": 2.7602492042919923e-07, "epoch": 19.14832285115304, "percentage": 95.74, "elapsed_time": "2:20:23", "remaining_time": "0:06:14", "throughput": 2834.41, "total_tokens": 23874376} {"current_steps": 36540, "total_steps": 38160, "loss": 0.0119, "lr": 2.7433306696979523e-07, "epoch": 19.150943396226417, "percentage": 95.75, "elapsed_time": "2:20:24", "remaining_time": "0:06:13", "throughput": 2834.37, "total_tokens": 23877096} {"current_steps": 36545, "total_steps": 38160, "loss": 0.0022, "lr": 2.7264638583782973e-07, "epoch": 19.15356394129979, "percentage": 95.77, "elapsed_time": "2:20:25", "remaining_time": "0:06:12", "throughput": 2834.44, "total_tokens": 23880776} {"current_steps": 36550, "total_steps": 38160, "loss": 0.0022, "lr": 2.7096487738613177e-07, "epoch": 19.156184486373167, "percentage": 95.78, "elapsed_time": "2:20:26", "remaining_time": "0:06:11", "throughput": 2834.56, "total_tokens": 23885000} {"current_steps": 36555, "total_steps": 38160, "loss": 0.0023, "lr": 2.6928854196646147e-07, "epoch": 19.15880503144654, "percentage": 95.79, "elapsed_time": "2:20:27", "remaining_time": "0:06:10", "throughput": 2834.53, "total_tokens": 23887720} {"current_steps": 36560, "total_steps": 38160, "loss": 0.0042, "lr": 2.6761737992948565e-07, "epoch": 19.161425576519918, "percentage": 95.81, "elapsed_time": "2:20:28", "remaining_time": "0:06:08", "throughput": 2834.53, "total_tokens": 23890760} {"current_steps": 36565, "total_steps": 38160, "loss": 0.0033, "lr": 2.6595139162479134e-07, "epoch": 19.16404612159329, "percentage": 95.82, "elapsed_time": "2:20:29", "remaining_time": "0:06:07", "throughput": 2834.5, "total_tokens": 23893640} {"current_steps": 36570, "total_steps": 38160, "loss": 0.0036, "lr": 2.6429057740088303e-07, "epoch": 19.166666666666668, "percentage": 95.83, "elapsed_time": "2:20:30", "remaining_time": "0:06:06", "throughput": 2834.49, "total_tokens": 23896584} {"current_steps": 36575, "total_steps": 38160, "loss": 0.0081, "lr": 2.6263493760518564e-07, "epoch": 19.16928721174004, "percentage": 95.85, "elapsed_time": "2:20:31", "remaining_time": "0:06:05", "throughput": 2834.63, "total_tokens": 23901480} {"current_steps": 36580, "total_steps": 38160, "loss": 0.005, "lr": 2.6098447258404157e-07, "epoch": 19.171907756813418, "percentage": 95.86, "elapsed_time": "2:20:33", "remaining_time": "0:06:04", "throughput": 2834.64, "total_tokens": 23904680} {"current_steps": 36585, "total_steps": 38160, "loss": 0.0015, "lr": 2.593391826827107e-07, "epoch": 19.17452830188679, "percentage": 95.87, "elapsed_time": "2:20:34", "remaining_time": "0:06:03", "throughput": 2834.58, "total_tokens": 23907144} {"current_steps": 36590, "total_steps": 38160, "loss": 0.0062, "lr": 2.5769906824536225e-07, "epoch": 19.17714884696017, "percentage": 95.89, "elapsed_time": "2:20:35", "remaining_time": "0:06:01", "throughput": 2834.64, "total_tokens": 23910888} {"current_steps": 36595, "total_steps": 38160, "loss": 0.011, "lr": 2.560641296150967e-07, "epoch": 19.179769392033542, "percentage": 95.9, "elapsed_time": "2:20:36", "remaining_time": "0:06:00", "throughput": 2834.67, "total_tokens": 23914184} {"current_steps": 36600, "total_steps": 38160, "loss": 0.0116, "lr": 2.544343671339211e-07, "epoch": 19.18238993710692, "percentage": 95.91, "elapsed_time": "2:20:37", "remaining_time": "0:05:59", "throughput": 2834.7, "total_tokens": 23917608} {"current_steps": 36605, "total_steps": 38160, "loss": 0.0086, "lr": 2.5280978114276264e-07, "epoch": 19.185010482180292, "percentage": 95.93, "elapsed_time": "2:20:38", "remaining_time": "0:05:58", "throughput": 2834.81, "total_tokens": 23922312} {"current_steps": 36610, "total_steps": 38160, "loss": 0.0027, "lr": 2.511903719814662e-07, "epoch": 19.18763102725367, "percentage": 95.94, "elapsed_time": "2:20:39", "remaining_time": "0:05:57", "throughput": 2834.78, "total_tokens": 23925096} {"current_steps": 36615, "total_steps": 38160, "loss": 0.0027, "lr": 2.4957613998879695e-07, "epoch": 19.190251572327043, "percentage": 95.95, "elapsed_time": "2:20:40", "remaining_time": "0:05:56", "throughput": 2834.77, "total_tokens": 23927976} {"current_steps": 36620, "total_steps": 38160, "loss": 0.0263, "lr": 2.479670855024291e-07, "epoch": 19.19287211740042, "percentage": 95.96, "elapsed_time": "2:20:42", "remaining_time": "0:05:55", "throughput": 2834.98, "total_tokens": 23934760} {"current_steps": 36625, "total_steps": 38160, "loss": 0.0077, "lr": 2.463632088589629e-07, "epoch": 19.195492662473793, "percentage": 95.98, "elapsed_time": "2:20:43", "remaining_time": "0:05:53", "throughput": 2834.99, "total_tokens": 23937960} {"current_steps": 36630, "total_steps": 38160, "loss": 0.0022, "lr": 2.447645103939078e-07, "epoch": 19.19811320754717, "percentage": 95.99, "elapsed_time": "2:20:44", "remaining_time": "0:05:52", "throughput": 2834.97, "total_tokens": 23940904} {"current_steps": 36635, "total_steps": 38160, "loss": 0.0017, "lr": 2.431709904416962e-07, "epoch": 19.200733752620547, "percentage": 96.0, "elapsed_time": "2:20:45", "remaining_time": "0:05:51", "throughput": 2834.97, "total_tokens": 23943848} {"current_steps": 36640, "total_steps": 38160, "loss": 0.0044, "lr": 2.4158264933567264e-07, "epoch": 19.20335429769392, "percentage": 96.02, "elapsed_time": "2:20:46", "remaining_time": "0:05:50", "throughput": 2835.0, "total_tokens": 23947112} {"current_steps": 36645, "total_steps": 38160, "loss": 0.0026, "lr": 2.399994874080963e-07, "epoch": 19.205974842767297, "percentage": 96.03, "elapsed_time": "2:20:48", "remaining_time": "0:05:49", "throughput": 2834.99, "total_tokens": 23950056} {"current_steps": 36650, "total_steps": 38160, "loss": 0.0048, "lr": 2.3842150499015504e-07, "epoch": 19.20859538784067, "percentage": 96.04, "elapsed_time": "2:20:49", "remaining_time": "0:05:48", "throughput": 2835.02, "total_tokens": 23953320} {"current_steps": 36655, "total_steps": 38160, "loss": 0.0014, "lr": 2.368487024119348e-07, "epoch": 19.211215932914047, "percentage": 96.06, "elapsed_time": "2:20:50", "remaining_time": "0:05:46", "throughput": 2834.99, "total_tokens": 23956168} {"current_steps": 36660, "total_steps": 38160, "loss": 0.0043, "lr": 2.3528108000245573e-07, "epoch": 19.21383647798742, "percentage": 96.07, "elapsed_time": "2:20:51", "remaining_time": "0:05:45", "throughput": 2835.04, "total_tokens": 23959528} {"current_steps": 36665, "total_steps": 38160, "loss": 0.0035, "lr": 2.3371863808964445e-07, "epoch": 19.216457023060798, "percentage": 96.08, "elapsed_time": "2:20:52", "remaining_time": "0:05:44", "throughput": 2835.03, "total_tokens": 23962504} {"current_steps": 36670, "total_steps": 38160, "loss": 0.0068, "lr": 2.32161377000345e-07, "epoch": 19.21907756813417, "percentage": 96.1, "elapsed_time": "2:20:53", "remaining_time": "0:05:43", "throughput": 2835.04, "total_tokens": 23965736} {"current_steps": 36675, "total_steps": 38160, "loss": 0.002, "lr": 2.306092970603163e-07, "epoch": 19.221698113207548, "percentage": 96.11, "elapsed_time": "2:20:54", "remaining_time": "0:05:42", "throughput": 2834.98, "total_tokens": 23968328} {"current_steps": 36680, "total_steps": 38160, "loss": 0.0056, "lr": 2.2906239859424306e-07, "epoch": 19.22431865828092, "percentage": 96.12, "elapsed_time": "2:20:55", "remaining_time": "0:05:41", "throughput": 2835.07, "total_tokens": 23972360} {"current_steps": 36685, "total_steps": 38160, "loss": 0.0117, "lr": 2.2752068192571084e-07, "epoch": 19.2269392033543, "percentage": 96.13, "elapsed_time": "2:20:56", "remaining_time": "0:05:40", "throughput": 2835.09, "total_tokens": 23975688} {"current_steps": 36690, "total_steps": 38160, "loss": 0.0053, "lr": 2.2598414737723396e-07, "epoch": 19.229559748427672, "percentage": 96.15, "elapsed_time": "2:20:57", "remaining_time": "0:05:38", "throughput": 2835.18, "total_tokens": 23979656} {"current_steps": 36695, "total_steps": 38160, "loss": 0.0154, "lr": 2.2445279527023578e-07, "epoch": 19.23218029350105, "percentage": 96.16, "elapsed_time": "2:20:59", "remaining_time": "0:05:37", "throughput": 2835.15, "total_tokens": 23982568} {"current_steps": 36700, "total_steps": 38160, "loss": 0.0106, "lr": 2.2292662592506007e-07, "epoch": 19.234800838574422, "percentage": 96.17, "elapsed_time": "2:21:00", "remaining_time": "0:05:36", "throughput": 2835.15, "total_tokens": 23985640} {"current_steps": 36705, "total_steps": 38160, "loss": 0.0047, "lr": 2.2140563966095985e-07, "epoch": 19.2374213836478, "percentage": 96.19, "elapsed_time": "2:21:01", "remaining_time": "0:05:35", "throughput": 2835.17, "total_tokens": 23989000} {"current_steps": 36710, "total_steps": 38160, "loss": 0.0048, "lr": 2.1988983679611386e-07, "epoch": 19.240041928721173, "percentage": 96.2, "elapsed_time": "2:21:02", "remaining_time": "0:05:34", "throughput": 2835.11, "total_tokens": 23991784} {"current_steps": 36715, "total_steps": 38160, "loss": 0.0053, "lr": 2.1837921764760462e-07, "epoch": 19.24266247379455, "percentage": 96.21, "elapsed_time": "2:21:03", "remaining_time": "0:05:33", "throughput": 2835.2, "total_tokens": 23996328} {"current_steps": 36720, "total_steps": 38160, "loss": 0.0222, "lr": 2.1687378253144043e-07, "epoch": 19.245283018867923, "percentage": 96.23, "elapsed_time": "2:21:04", "remaining_time": "0:05:31", "throughput": 2835.24, "total_tokens": 23999816} {"current_steps": 36725, "total_steps": 38160, "loss": 0.0227, "lr": 2.153735317625416e-07, "epoch": 19.2479035639413, "percentage": 96.24, "elapsed_time": "2:21:05", "remaining_time": "0:05:30", "throughput": 2835.19, "total_tokens": 24002472} {"current_steps": 36730, "total_steps": 38160, "loss": 0.0009, "lr": 2.1387846565474045e-07, "epoch": 19.250524109014677, "percentage": 96.25, "elapsed_time": "2:21:07", "remaining_time": "0:05:29", "throughput": 2835.15, "total_tokens": 24005256} {"current_steps": 36735, "total_steps": 38160, "loss": 0.0039, "lr": 2.123885845207896e-07, "epoch": 19.25314465408805, "percentage": 96.27, "elapsed_time": "2:21:08", "remaining_time": "0:05:28", "throughput": 2835.2, "total_tokens": 24008776} {"current_steps": 36740, "total_steps": 38160, "loss": 0.0023, "lr": 2.1090388867235356e-07, "epoch": 19.255765199161427, "percentage": 96.28, "elapsed_time": "2:21:09", "remaining_time": "0:05:27", "throughput": 2835.3, "total_tokens": 24012904} {"current_steps": 36745, "total_steps": 38160, "loss": 0.0059, "lr": 2.0942437842001728e-07, "epoch": 19.2583857442348, "percentage": 96.29, "elapsed_time": "2:21:10", "remaining_time": "0:05:26", "throughput": 2835.32, "total_tokens": 24016040} {"current_steps": 36750, "total_steps": 38160, "loss": 0.0032, "lr": 2.0795005407327483e-07, "epoch": 19.261006289308177, "percentage": 96.31, "elapsed_time": "2:21:11", "remaining_time": "0:05:25", "throughput": 2835.29, "total_tokens": 24018760} {"current_steps": 36755, "total_steps": 38160, "loss": 0.0156, "lr": 2.0648091594053508e-07, "epoch": 19.26362683438155, "percentage": 96.32, "elapsed_time": "2:21:12", "remaining_time": "0:05:23", "throughput": 2835.32, "total_tokens": 24022088} {"current_steps": 36760, "total_steps": 38160, "loss": 0.0027, "lr": 2.0501696432913275e-07, "epoch": 19.266247379454928, "percentage": 96.33, "elapsed_time": "2:21:13", "remaining_time": "0:05:22", "throughput": 2835.32, "total_tokens": 24025064} {"current_steps": 36765, "total_steps": 38160, "loss": 0.0042, "lr": 2.035581995453034e-07, "epoch": 19.2688679245283, "percentage": 96.34, "elapsed_time": "2:21:14", "remaining_time": "0:05:21", "throughput": 2835.32, "total_tokens": 24028264} {"current_steps": 36770, "total_steps": 38160, "loss": 0.0055, "lr": 2.0210462189420577e-07, "epoch": 19.271488469601678, "percentage": 96.36, "elapsed_time": "2:21:15", "remaining_time": "0:05:20", "throughput": 2835.33, "total_tokens": 24031560} {"current_steps": 36775, "total_steps": 38160, "loss": 0.0104, "lr": 2.006562316799132e-07, "epoch": 19.27410901467505, "percentage": 96.37, "elapsed_time": "2:21:16", "remaining_time": "0:05:19", "throughput": 2835.44, "total_tokens": 24035944} {"current_steps": 36780, "total_steps": 38160, "loss": 0.0221, "lr": 1.992130292054084e-07, "epoch": 19.27672955974843, "percentage": 96.38, "elapsed_time": "2:21:18", "remaining_time": "0:05:18", "throughput": 2835.49, "total_tokens": 24039912} {"current_steps": 36785, "total_steps": 38160, "loss": 0.0032, "lr": 1.9777501477259708e-07, "epoch": 19.279350104821802, "percentage": 96.4, "elapsed_time": "2:21:19", "remaining_time": "0:05:16", "throughput": 2835.48, "total_tokens": 24042792} {"current_steps": 36790, "total_steps": 38160, "loss": 0.0085, "lr": 1.9634218868229414e-07, "epoch": 19.28197064989518, "percentage": 96.41, "elapsed_time": "2:21:20", "remaining_time": "0:05:15", "throughput": 2835.49, "total_tokens": 24046184} {"current_steps": 36795, "total_steps": 38160, "loss": 0.0066, "lr": 1.9491455123423207e-07, "epoch": 19.284591194968552, "percentage": 96.42, "elapsed_time": "2:21:21", "remaining_time": "0:05:14", "throughput": 2835.52, "total_tokens": 24049576} {"current_steps": 36800, "total_steps": 38160, "loss": 0.0018, "lr": 1.9349210272705253e-07, "epoch": 19.28721174004193, "percentage": 96.44, "elapsed_time": "2:21:22", "remaining_time": "0:05:13", "throughput": 2835.45, "total_tokens": 24051944} {"current_steps": 36805, "total_steps": 38160, "loss": 0.0076, "lr": 1.920748434583175e-07, "epoch": 19.289832285115303, "percentage": 96.45, "elapsed_time": "2:21:23", "remaining_time": "0:05:12", "throughput": 2835.46, "total_tokens": 24055112} {"current_steps": 36810, "total_steps": 38160, "loss": 0.0043, "lr": 1.906627737245009e-07, "epoch": 19.29245283018868, "percentage": 96.46, "elapsed_time": "2:21:24", "remaining_time": "0:05:11", "throughput": 2835.53, "total_tokens": 24058888} {"current_steps": 36815, "total_steps": 38160, "loss": 0.0041, "lr": 1.8925589382099152e-07, "epoch": 19.295073375262053, "percentage": 96.48, "elapsed_time": "2:21:25", "remaining_time": "0:05:10", "throughput": 2835.58, "total_tokens": 24062728} {"current_steps": 36820, "total_steps": 38160, "loss": 0.094, "lr": 1.8785420404209553e-07, "epoch": 19.29769392033543, "percentage": 96.49, "elapsed_time": "2:21:27", "remaining_time": "0:05:08", "throughput": 2835.65, "total_tokens": 24066504} {"current_steps": 36825, "total_steps": 38160, "loss": 0.0064, "lr": 1.864577046810284e-07, "epoch": 19.300314465408803, "percentage": 96.5, "elapsed_time": "2:21:28", "remaining_time": "0:05:07", "throughput": 2835.63, "total_tokens": 24069256} {"current_steps": 36830, "total_steps": 38160, "loss": 0.0019, "lr": 1.8506639602992038e-07, "epoch": 19.30293501048218, "percentage": 96.51, "elapsed_time": "2:21:29", "remaining_time": "0:05:06", "throughput": 2835.56, "total_tokens": 24071720} {"current_steps": 36835, "total_steps": 38160, "loss": 0.0036, "lr": 1.836802783798164e-07, "epoch": 19.305555555555557, "percentage": 96.53, "elapsed_time": "2:21:30", "remaining_time": "0:05:05", "throughput": 2835.64, "total_tokens": 24075720} {"current_steps": 36840, "total_steps": 38160, "loss": 0.0058, "lr": 1.822993520206817e-07, "epoch": 19.30817610062893, "percentage": 96.54, "elapsed_time": "2:21:31", "remaining_time": "0:05:04", "throughput": 2835.65, "total_tokens": 24078920} {"current_steps": 36845, "total_steps": 38160, "loss": 0.0044, "lr": 1.8092361724138528e-07, "epoch": 19.310796645702307, "percentage": 96.55, "elapsed_time": "2:21:32", "remaining_time": "0:05:03", "throughput": 2835.69, "total_tokens": 24082376} {"current_steps": 36850, "total_steps": 38160, "loss": 0.002, "lr": 1.7955307432971914e-07, "epoch": 19.31341719077568, "percentage": 96.57, "elapsed_time": "2:21:33", "remaining_time": "0:05:01", "throughput": 2835.75, "total_tokens": 24085928} {"current_steps": 36855, "total_steps": 38160, "loss": 0.0061, "lr": 1.7818772357238445e-07, "epoch": 19.316037735849058, "percentage": 96.58, "elapsed_time": "2:21:34", "remaining_time": "0:05:00", "throughput": 2835.72, "total_tokens": 24088648} {"current_steps": 36860, "total_steps": 38160, "loss": 0.005, "lr": 1.7682756525499166e-07, "epoch": 19.31865828092243, "percentage": 96.59, "elapsed_time": "2:21:35", "remaining_time": "0:04:59", "throughput": 2835.77, "total_tokens": 24092136} {"current_steps": 36865, "total_steps": 38160, "loss": 0.0034, "lr": 1.7547259966207708e-07, "epoch": 19.321278825995808, "percentage": 96.61, "elapsed_time": "2:21:36", "remaining_time": "0:04:58", "throughput": 2835.69, "total_tokens": 24094632} {"current_steps": 36870, "total_steps": 38160, "loss": 0.0045, "lr": 1.7412282707708062e-07, "epoch": 19.32389937106918, "percentage": 96.62, "elapsed_time": "2:21:38", "remaining_time": "0:04:57", "throughput": 2835.74, "total_tokens": 24098248} {"current_steps": 36875, "total_steps": 38160, "loss": 0.0051, "lr": 1.7277824778235974e-07, "epoch": 19.32651991614256, "percentage": 96.63, "elapsed_time": "2:21:39", "remaining_time": "0:04:56", "throughput": 2835.71, "total_tokens": 24100872} {"current_steps": 36880, "total_steps": 38160, "loss": 0.0095, "lr": 1.714388620591867e-07, "epoch": 19.329140461215932, "percentage": 96.65, "elapsed_time": "2:21:40", "remaining_time": "0:04:55", "throughput": 2835.76, "total_tokens": 24104520} {"current_steps": 36885, "total_steps": 38160, "loss": 0.0065, "lr": 1.701046701877429e-07, "epoch": 19.33176100628931, "percentage": 96.66, "elapsed_time": "2:21:41", "remaining_time": "0:04:53", "throughput": 2835.94, "total_tokens": 24111048} {"current_steps": 36890, "total_steps": 38160, "loss": 0.0022, "lr": 1.6877567244713011e-07, "epoch": 19.334381551362682, "percentage": 96.67, "elapsed_time": "2:21:43", "remaining_time": "0:04:52", "throughput": 2835.87, "total_tokens": 24113448} {"current_steps": 36895, "total_steps": 38160, "loss": 0.0033, "lr": 1.6745186911535372e-07, "epoch": 19.33700209643606, "percentage": 96.69, "elapsed_time": "2:21:44", "remaining_time": "0:04:51", "throughput": 2835.85, "total_tokens": 24116264} {"current_steps": 36900, "total_steps": 38160, "loss": 0.0028, "lr": 1.6613326046934497e-07, "epoch": 19.339622641509433, "percentage": 96.7, "elapsed_time": "2:21:45", "remaining_time": "0:04:50", "throughput": 2835.79, "total_tokens": 24118888} {"current_steps": 36905, "total_steps": 38160, "loss": 0.0036, "lr": 1.64819846784936e-07, "epoch": 19.34224318658281, "percentage": 96.71, "elapsed_time": "2:21:46", "remaining_time": "0:04:49", "throughput": 2835.81, "total_tokens": 24122056} {"current_steps": 36910, "total_steps": 38160, "loss": 0.0149, "lr": 1.6351162833688204e-07, "epoch": 19.344863731656183, "percentage": 96.72, "elapsed_time": "2:21:47", "remaining_time": "0:04:48", "throughput": 2835.82, "total_tokens": 24125288} {"current_steps": 36915, "total_steps": 38160, "loss": 0.0036, "lr": 1.6220860539884475e-07, "epoch": 19.34748427672956, "percentage": 96.74, "elapsed_time": "2:21:48", "remaining_time": "0:04:46", "throughput": 2835.88, "total_tokens": 24128904} {"current_steps": 36920, "total_steps": 38160, "loss": 0.0038, "lr": 1.6091077824340327e-07, "epoch": 19.350104821802937, "percentage": 96.75, "elapsed_time": "2:21:49", "remaining_time": "0:04:45", "throughput": 2835.88, "total_tokens": 24131880} {"current_steps": 36925, "total_steps": 38160, "loss": 0.0032, "lr": 1.5961814714204605e-07, "epoch": 19.35272536687631, "percentage": 96.76, "elapsed_time": "2:21:50", "remaining_time": "0:04:44", "throughput": 2835.82, "total_tokens": 24134600} {"current_steps": 36930, "total_steps": 38160, "loss": 0.002, "lr": 1.5833071236518172e-07, "epoch": 19.355345911949687, "percentage": 96.78, "elapsed_time": "2:21:51", "remaining_time": "0:04:43", "throughput": 2835.8, "total_tokens": 24137448} {"current_steps": 36935, "total_steps": 38160, "loss": 0.0138, "lr": 1.5704847418212266e-07, "epoch": 19.35796645702306, "percentage": 96.79, "elapsed_time": "2:21:52", "remaining_time": "0:04:42", "throughput": 2835.85, "total_tokens": 24141064} {"current_steps": 36940, "total_steps": 38160, "loss": 0.0039, "lr": 1.5577143286109875e-07, "epoch": 19.360587002096437, "percentage": 96.8, "elapsed_time": "2:21:53", "remaining_time": "0:04:41", "throughput": 2835.79, "total_tokens": 24143688} {"current_steps": 36945, "total_steps": 38160, "loss": 0.002, "lr": 1.5449958866925185e-07, "epoch": 19.36320754716981, "percentage": 96.82, "elapsed_time": "2:21:54", "remaining_time": "0:04:40", "throughput": 2835.82, "total_tokens": 24146984} {"current_steps": 36950, "total_steps": 38160, "loss": 0.0162, "lr": 1.532329418726386e-07, "epoch": 19.365828092243188, "percentage": 96.83, "elapsed_time": "2:21:56", "remaining_time": "0:04:38", "throughput": 2835.95, "total_tokens": 24151784} {"current_steps": 36955, "total_steps": 38160, "loss": 0.0066, "lr": 1.5197149273623036e-07, "epoch": 19.36844863731656, "percentage": 96.84, "elapsed_time": "2:21:57", "remaining_time": "0:04:37", "throughput": 2835.96, "total_tokens": 24154792} {"current_steps": 36960, "total_steps": 38160, "loss": 0.003, "lr": 1.5071524152389936e-07, "epoch": 19.371069182389938, "percentage": 96.86, "elapsed_time": "2:21:58", "remaining_time": "0:04:36", "throughput": 2835.92, "total_tokens": 24157512} {"current_steps": 36965, "total_steps": 38160, "loss": 0.0032, "lr": 1.4946418849844934e-07, "epoch": 19.37368972746331, "percentage": 96.87, "elapsed_time": "2:21:59", "remaining_time": "0:04:35", "throughput": 2835.91, "total_tokens": 24160392} {"current_steps": 36970, "total_steps": 38160, "loss": 0.0026, "lr": 1.4821833392157923e-07, "epoch": 19.37631027253669, "percentage": 96.88, "elapsed_time": "2:22:00", "remaining_time": "0:04:34", "throughput": 2835.93, "total_tokens": 24163656} {"current_steps": 36975, "total_steps": 38160, "loss": 0.0032, "lr": 1.4697767805390838e-07, "epoch": 19.378930817610062, "percentage": 96.89, "elapsed_time": "2:22:01", "remaining_time": "0:04:33", "throughput": 2835.92, "total_tokens": 24166632} {"current_steps": 36980, "total_steps": 38160, "loss": 0.0062, "lr": 1.4574222115497084e-07, "epoch": 19.38155136268344, "percentage": 96.91, "elapsed_time": "2:22:02", "remaining_time": "0:04:31", "throughput": 2835.86, "total_tokens": 24169320} {"current_steps": 36985, "total_steps": 38160, "loss": 0.0106, "lr": 1.4451196348320706e-07, "epoch": 19.384171907756812, "percentage": 96.92, "elapsed_time": "2:22:03", "remaining_time": "0:04:30", "throughput": 2835.88, "total_tokens": 24172520} {"current_steps": 36990, "total_steps": 38160, "loss": 0.0028, "lr": 1.4328690529597232e-07, "epoch": 19.38679245283019, "percentage": 96.93, "elapsed_time": "2:22:04", "remaining_time": "0:04:29", "throughput": 2835.96, "total_tokens": 24176232} {"current_steps": 36995, "total_steps": 38160, "loss": 0.0061, "lr": 1.4206704684953943e-07, "epoch": 19.389412997903563, "percentage": 96.95, "elapsed_time": "2:22:05", "remaining_time": "0:04:28", "throughput": 2835.97, "total_tokens": 24179400} {"current_steps": 37000, "total_steps": 38160, "loss": 0.0055, "lr": 1.4085238839908476e-07, "epoch": 19.39203354297694, "percentage": 96.96, "elapsed_time": "2:22:07", "remaining_time": "0:04:27", "throughput": 2835.96, "total_tokens": 24182568} {"current_steps": 37005, "total_steps": 38160, "loss": 0.0049, "lr": 1.3964293019870235e-07, "epoch": 19.394654088050313, "percentage": 96.97, "elapsed_time": "2:22:08", "remaining_time": "0:04:26", "throughput": 2835.98, "total_tokens": 24185640} {"current_steps": 37010, "total_steps": 38160, "loss": 0.0049, "lr": 1.3843867250139807e-07, "epoch": 19.39727463312369, "percentage": 96.99, "elapsed_time": "2:22:09", "remaining_time": "0:04:25", "throughput": 2836.02, "total_tokens": 24189256} {"current_steps": 37015, "total_steps": 38160, "loss": 0.0091, "lr": 1.3723961555908715e-07, "epoch": 19.399895178197063, "percentage": 97.0, "elapsed_time": "2:22:10", "remaining_time": "0:04:23", "throughput": 2836.06, "total_tokens": 24192744} {"current_steps": 37020, "total_steps": 38160, "loss": 0.027, "lr": 1.3604575962259947e-07, "epoch": 19.40251572327044, "percentage": 97.01, "elapsed_time": "2:22:11", "remaining_time": "0:04:22", "throughput": 2836.15, "total_tokens": 24197128} {"current_steps": 37025, "total_steps": 38160, "loss": 0.0029, "lr": 1.3485710494167692e-07, "epoch": 19.405136268343817, "percentage": 97.03, "elapsed_time": "2:22:12", "remaining_time": "0:04:21", "throughput": 2836.18, "total_tokens": 24200552} {"current_steps": 37030, "total_steps": 38160, "loss": 0.0022, "lr": 1.3367365176496783e-07, "epoch": 19.40775681341719, "percentage": 97.04, "elapsed_time": "2:22:13", "remaining_time": "0:04:20", "throughput": 2836.19, "total_tokens": 24203880} {"current_steps": 37035, "total_steps": 38160, "loss": 0.0055, "lr": 1.324954003400436e-07, "epoch": 19.410377358490567, "percentage": 97.05, "elapsed_time": "2:22:14", "remaining_time": "0:04:19", "throughput": 2836.3, "total_tokens": 24207752} {"current_steps": 37040, "total_steps": 38160, "loss": 0.0066, "lr": 1.313223509133793e-07, "epoch": 19.41299790356394, "percentage": 97.06, "elapsed_time": "2:22:16", "remaining_time": "0:04:18", "throughput": 2836.38, "total_tokens": 24211752} {"current_steps": 37045, "total_steps": 38160, "loss": 0.0039, "lr": 1.301545037303592e-07, "epoch": 19.415618448637318, "percentage": 97.08, "elapsed_time": "2:22:17", "remaining_time": "0:04:16", "throughput": 2836.28, "total_tokens": 24213992} {"current_steps": 37050, "total_steps": 38160, "loss": 0.02, "lr": 1.2899185903529066e-07, "epoch": 19.41823899371069, "percentage": 97.09, "elapsed_time": "2:22:18", "remaining_time": "0:04:15", "throughput": 2836.23, "total_tokens": 24216584} {"current_steps": 37055, "total_steps": 38160, "loss": 0.0026, "lr": 1.278344170713791e-07, "epoch": 19.420859538784068, "percentage": 97.1, "elapsed_time": "2:22:19", "remaining_time": "0:04:14", "throughput": 2836.2, "total_tokens": 24219336} {"current_steps": 37060, "total_steps": 38160, "loss": 0.0048, "lr": 1.2668217808075033e-07, "epoch": 19.42348008385744, "percentage": 97.12, "elapsed_time": "2:22:20", "remaining_time": "0:04:13", "throughput": 2836.16, "total_tokens": 24222024} {"current_steps": 37065, "total_steps": 38160, "loss": 0.0029, "lr": 1.255351423044393e-07, "epoch": 19.42610062893082, "percentage": 97.13, "elapsed_time": "2:22:21", "remaining_time": "0:04:12", "throughput": 2836.2, "total_tokens": 24225384} {"current_steps": 37070, "total_steps": 38160, "loss": 0.0026, "lr": 1.2439330998239572e-07, "epoch": 19.428721174004192, "percentage": 97.14, "elapsed_time": "2:22:22", "remaining_time": "0:04:11", "throughput": 2836.16, "total_tokens": 24228232} {"current_steps": 37075, "total_steps": 38160, "loss": 0.0032, "lr": 1.2325668135347578e-07, "epoch": 19.43134171907757, "percentage": 97.16, "elapsed_time": "2:22:23", "remaining_time": "0:04:10", "throughput": 2836.17, "total_tokens": 24231432} {"current_steps": 37080, "total_steps": 38160, "loss": 0.0121, "lr": 1.221252566554476e-07, "epoch": 19.433962264150942, "percentage": 97.17, "elapsed_time": "2:22:24", "remaining_time": "0:04:08", "throughput": 2836.2, "total_tokens": 24234952} {"current_steps": 37085, "total_steps": 38160, "loss": 0.0038, "lr": 1.2099903612499685e-07, "epoch": 19.43658280922432, "percentage": 97.18, "elapsed_time": "2:22:25", "remaining_time": "0:04:07", "throughput": 2836.19, "total_tokens": 24237768} {"current_steps": 37090, "total_steps": 38160, "loss": 0.0098, "lr": 1.198780199977101e-07, "epoch": 19.439203354297693, "percentage": 97.2, "elapsed_time": "2:22:27", "remaining_time": "0:04:06", "throughput": 2836.19, "total_tokens": 24241032} {"current_steps": 37095, "total_steps": 38160, "loss": 0.0067, "lr": 1.1876220850809416e-07, "epoch": 19.44182389937107, "percentage": 97.21, "elapsed_time": "2:22:28", "remaining_time": "0:04:05", "throughput": 2836.29, "total_tokens": 24245416} {"current_steps": 37100, "total_steps": 38160, "loss": 0.0034, "lr": 1.1765160188956514e-07, "epoch": 19.444444444444443, "percentage": 97.22, "elapsed_time": "2:22:29", "remaining_time": "0:04:04", "throughput": 2836.34, "total_tokens": 24249128} {"current_steps": 37105, "total_steps": 38160, "loss": 0.002, "lr": 1.1654620037445107e-07, "epoch": 19.44706498951782, "percentage": 97.24, "elapsed_time": "2:22:30", "remaining_time": "0:04:03", "throughput": 2836.34, "total_tokens": 24252200} {"current_steps": 37110, "total_steps": 38160, "loss": 0.0037, "lr": 1.1544600419398088e-07, "epoch": 19.449685534591197, "percentage": 97.25, "elapsed_time": "2:22:31", "remaining_time": "0:04:01", "throughput": 2836.3, "total_tokens": 24255112} {"current_steps": 37115, "total_steps": 38160, "loss": 0.0099, "lr": 1.1435101357831213e-07, "epoch": 19.45230607966457, "percentage": 97.26, "elapsed_time": "2:22:32", "remaining_time": "0:04:00", "throughput": 2836.34, "total_tokens": 24258504} {"current_steps": 37120, "total_steps": 38160, "loss": 0.0018, "lr": 1.1326122875650047e-07, "epoch": 19.454926624737947, "percentage": 97.27, "elapsed_time": "2:22:33", "remaining_time": "0:03:59", "throughput": 2836.26, "total_tokens": 24260776} {"current_steps": 37125, "total_steps": 38160, "loss": 0.0049, "lr": 1.1217664995651633e-07, "epoch": 19.45754716981132, "percentage": 97.29, "elapsed_time": "2:22:34", "remaining_time": "0:03:58", "throughput": 2836.28, "total_tokens": 24263976} {"current_steps": 37130, "total_steps": 38160, "loss": 0.0022, "lr": 1.1109727740523935e-07, "epoch": 19.460167714884697, "percentage": 97.3, "elapsed_time": "2:22:35", "remaining_time": "0:03:57", "throughput": 2836.29, "total_tokens": 24267144} {"current_steps": 37135, "total_steps": 38160, "loss": 0.0031, "lr": 1.1002311132846944e-07, "epoch": 19.46278825995807, "percentage": 97.31, "elapsed_time": "2:22:37", "remaining_time": "0:03:56", "throughput": 2836.29, "total_tokens": 24270312} {"current_steps": 37140, "total_steps": 38160, "loss": 0.0032, "lr": 1.0895415195090186e-07, "epoch": 19.465408805031448, "percentage": 97.33, "elapsed_time": "2:22:38", "remaining_time": "0:03:55", "throughput": 2836.32, "total_tokens": 24274632} {"current_steps": 37145, "total_steps": 38160, "loss": 0.021, "lr": 1.0789039949615221e-07, "epoch": 19.46802935010482, "percentage": 97.34, "elapsed_time": "2:22:39", "remaining_time": "0:03:53", "throughput": 2836.45, "total_tokens": 24279144} {"current_steps": 37150, "total_steps": 38160, "loss": 0.0036, "lr": 1.0683185418674801e-07, "epoch": 19.470649895178198, "percentage": 97.35, "elapsed_time": "2:22:40", "remaining_time": "0:03:52", "throughput": 2836.42, "total_tokens": 24282024} {"current_steps": 37155, "total_steps": 38160, "loss": 0.0073, "lr": 1.0577851624412604e-07, "epoch": 19.47327044025157, "percentage": 97.37, "elapsed_time": "2:22:41", "remaining_time": "0:03:51", "throughput": 2836.44, "total_tokens": 24285288} {"current_steps": 37160, "total_steps": 38160, "loss": 0.0055, "lr": 1.0473038588862672e-07, "epoch": 19.47589098532495, "percentage": 97.38, "elapsed_time": "2:22:43", "remaining_time": "0:03:50", "throughput": 2836.53, "total_tokens": 24289384} {"current_steps": 37165, "total_steps": 38160, "loss": 0.0479, "lr": 1.0368746333951351e-07, "epoch": 19.478511530398322, "percentage": 97.39, "elapsed_time": "2:22:44", "remaining_time": "0:03:49", "throughput": 2836.46, "total_tokens": 24291848} {"current_steps": 37170, "total_steps": 38160, "loss": 0.0038, "lr": 1.0264974881494805e-07, "epoch": 19.4811320754717, "percentage": 97.41, "elapsed_time": "2:22:45", "remaining_time": "0:03:48", "throughput": 2836.57, "total_tokens": 24296296} {"current_steps": 37175, "total_steps": 38160, "loss": 0.0438, "lr": 1.0161724253201222e-07, "epoch": 19.483752620545072, "percentage": 97.42, "elapsed_time": "2:22:46", "remaining_time": "0:03:46", "throughput": 2836.55, "total_tokens": 24299176} {"current_steps": 37180, "total_steps": 38160, "loss": 0.0058, "lr": 1.0058994470669436e-07, "epoch": 19.48637316561845, "percentage": 97.43, "elapsed_time": "2:22:47", "remaining_time": "0:03:45", "throughput": 2836.56, "total_tokens": 24302216} {"current_steps": 37185, "total_steps": 38160, "loss": 0.0042, "lr": 9.956785555388926e-08, "epoch": 19.488993710691823, "percentage": 97.44, "elapsed_time": "2:22:48", "remaining_time": "0:03:44", "throughput": 2836.49, "total_tokens": 24304648} {"current_steps": 37190, "total_steps": 38160, "loss": 0.0055, "lr": 9.855097528741475e-08, "epoch": 19.4916142557652, "percentage": 97.46, "elapsed_time": "2:22:49", "remaining_time": "0:03:43", "throughput": 2836.54, "total_tokens": 24308712} {"current_steps": 37195, "total_steps": 38160, "loss": 0.0043, "lr": 9.753930411998402e-08, "epoch": 19.494234800838573, "percentage": 97.47, "elapsed_time": "2:22:50", "remaining_time": "0:03:42", "throughput": 2836.56, "total_tokens": 24312072} {"current_steps": 37200, "total_steps": 38160, "loss": 0.0053, "lr": 9.653284226322501e-08, "epoch": 19.49685534591195, "percentage": 97.48, "elapsed_time": "2:22:52", "remaining_time": "0:03:41", "throughput": 2836.72, "total_tokens": 24318312} {"current_steps": 37205, "total_steps": 38160, "loss": 0.0032, "lr": 9.553158992768318e-08, "epoch": 19.499475890985323, "percentage": 97.5, "elapsed_time": "2:22:53", "remaining_time": "0:03:40", "throughput": 2836.69, "total_tokens": 24321128} {"current_steps": 37210, "total_steps": 38160, "loss": 0.0032, "lr": 9.453554732281044e-08, "epoch": 19.5020964360587, "percentage": 97.51, "elapsed_time": "2:22:54", "remaining_time": "0:03:38", "throughput": 2836.73, "total_tokens": 24324392} {"current_steps": 37215, "total_steps": 38160, "loss": 0.0065, "lr": 9.354471465696236e-08, "epoch": 19.504716981132077, "percentage": 97.52, "elapsed_time": "2:22:55", "remaining_time": "0:03:37", "throughput": 2836.73, "total_tokens": 24327560} {"current_steps": 37220, "total_steps": 38160, "loss": 0.0422, "lr": 9.255909213741199e-08, "epoch": 19.50733752620545, "percentage": 97.54, "elapsed_time": "2:22:56", "remaining_time": "0:03:36", "throughput": 2836.72, "total_tokens": 24330504} {"current_steps": 37225, "total_steps": 38160, "loss": 0.0062, "lr": 9.157867997034164e-08, "epoch": 19.509958071278827, "percentage": 97.55, "elapsed_time": "2:22:58", "remaining_time": "0:03:35", "throughput": 2836.73, "total_tokens": 24333800} {"current_steps": 37230, "total_steps": 38160, "loss": 0.0066, "lr": 9.060347836084004e-08, "epoch": 19.5125786163522, "percentage": 97.56, "elapsed_time": "2:22:59", "remaining_time": "0:03:34", "throughput": 2836.68, "total_tokens": 24336264} {"current_steps": 37235, "total_steps": 38160, "loss": 0.0195, "lr": 8.96334875129079e-08, "epoch": 19.515199161425578, "percentage": 97.58, "elapsed_time": "2:23:00", "remaining_time": "0:03:33", "throughput": 2836.6, "total_tokens": 24338696} {"current_steps": 37240, "total_steps": 38160, "loss": 0.0024, "lr": 8.866870762946067e-08, "epoch": 19.51781970649895, "percentage": 97.59, "elapsed_time": "2:23:01", "remaining_time": "0:03:31", "throughput": 2836.62, "total_tokens": 24342056} {"current_steps": 37245, "total_steps": 38160, "loss": 0.0084, "lr": 8.77091389123147e-08, "epoch": 19.520440251572328, "percentage": 97.6, "elapsed_time": "2:23:02", "remaining_time": "0:03:30", "throughput": 2836.67, "total_tokens": 24345480} {"current_steps": 37250, "total_steps": 38160, "loss": 0.0138, "lr": 8.675478156220385e-08, "epoch": 19.5230607966457, "percentage": 97.62, "elapsed_time": "2:23:03", "remaining_time": "0:03:29", "throughput": 2836.68, "total_tokens": 24348680} {"current_steps": 37255, "total_steps": 38160, "loss": 0.0075, "lr": 8.580563577876566e-08, "epoch": 19.52568134171908, "percentage": 97.63, "elapsed_time": "2:23:04", "remaining_time": "0:03:28", "throughput": 2836.67, "total_tokens": 24351624} {"current_steps": 37260, "total_steps": 38160, "loss": 0.0089, "lr": 8.486170176055242e-08, "epoch": 19.528301886792452, "percentage": 97.64, "elapsed_time": "2:23:05", "remaining_time": "0:03:27", "throughput": 2836.85, "total_tokens": 24356552} {"current_steps": 37265, "total_steps": 38160, "loss": 0.0028, "lr": 8.392297970502282e-08, "epoch": 19.53092243186583, "percentage": 97.65, "elapsed_time": "2:23:06", "remaining_time": "0:03:26", "throughput": 2836.85, "total_tokens": 24359688} {"current_steps": 37270, "total_steps": 38160, "loss": 0.0078, "lr": 8.298946980855315e-08, "epoch": 19.533542976939202, "percentage": 97.67, "elapsed_time": "2:23:08", "remaining_time": "0:03:25", "throughput": 2836.97, "total_tokens": 24364328} {"current_steps": 37275, "total_steps": 38160, "loss": 0.0014, "lr": 8.206117226641497e-08, "epoch": 19.53616352201258, "percentage": 97.68, "elapsed_time": "2:23:09", "remaining_time": "0:03:23", "throughput": 2837.02, "total_tokens": 24367752} {"current_steps": 37280, "total_steps": 38160, "loss": 0.0049, "lr": 8.113808727280015e-08, "epoch": 19.538784067085953, "percentage": 97.69, "elapsed_time": "2:23:10", "remaining_time": "0:03:22", "throughput": 2837.08, "total_tokens": 24371208} {"current_steps": 37285, "total_steps": 38160, "loss": 0.0065, "lr": 8.022021502080979e-08, "epoch": 19.54140461215933, "percentage": 97.71, "elapsed_time": "2:23:11", "remaining_time": "0:03:21", "throughput": 2837.14, "total_tokens": 24374824} {"current_steps": 37290, "total_steps": 38160, "loss": 0.0047, "lr": 7.930755570244863e-08, "epoch": 19.544025157232703, "percentage": 97.72, "elapsed_time": "2:23:12", "remaining_time": "0:03:20", "throughput": 2837.19, "total_tokens": 24378408} {"current_steps": 37295, "total_steps": 38160, "loss": 0.0049, "lr": 7.840010950863619e-08, "epoch": 19.54664570230608, "percentage": 97.73, "elapsed_time": "2:23:13", "remaining_time": "0:03:19", "throughput": 2837.15, "total_tokens": 24381160} {"current_steps": 37300, "total_steps": 38160, "loss": 0.0095, "lr": 7.749787662920116e-08, "epoch": 19.549266247379457, "percentage": 97.75, "elapsed_time": "2:23:14", "remaining_time": "0:03:18", "throughput": 2837.12, "total_tokens": 24384072} {"current_steps": 37305, "total_steps": 38160, "loss": 0.0035, "lr": 7.660085725288146e-08, "epoch": 19.55188679245283, "percentage": 97.76, "elapsed_time": "2:23:15", "remaining_time": "0:03:17", "throughput": 2837.11, "total_tokens": 24386952} {"current_steps": 37310, "total_steps": 38160, "loss": 0.0039, "lr": 7.570905156731867e-08, "epoch": 19.554507337526207, "percentage": 97.77, "elapsed_time": "2:23:16", "remaining_time": "0:03:15", "throughput": 2837.16, "total_tokens": 24390600} {"current_steps": 37315, "total_steps": 38160, "loss": 0.006, "lr": 7.482245975907188e-08, "epoch": 19.55712788259958, "percentage": 97.79, "elapsed_time": "2:23:17", "remaining_time": "0:03:14", "throughput": 2837.14, "total_tokens": 24393416} {"current_steps": 37320, "total_steps": 38160, "loss": 0.0028, "lr": 7.394108201360383e-08, "epoch": 19.559748427672957, "percentage": 97.8, "elapsed_time": "2:23:18", "remaining_time": "0:03:13", "throughput": 2837.12, "total_tokens": 24396328} {"current_steps": 37325, "total_steps": 38160, "loss": 0.0278, "lr": 7.306491851529206e-08, "epoch": 19.56236897274633, "percentage": 97.81, "elapsed_time": "2:23:21", "remaining_time": "0:03:12", "throughput": 2837.35, "total_tokens": 24404040} {"current_steps": 37330, "total_steps": 38160, "loss": 0.0122, "lr": 7.219396944741774e-08, "epoch": 19.564989517819708, "percentage": 97.82, "elapsed_time": "2:23:22", "remaining_time": "0:03:11", "throughput": 2837.37, "total_tokens": 24407304} {"current_steps": 37335, "total_steps": 38160, "loss": 0.0132, "lr": 7.132823499217123e-08, "epoch": 19.56761006289308, "percentage": 97.84, "elapsed_time": "2:23:23", "remaining_time": "0:03:10", "throughput": 2837.5, "total_tokens": 24411496} {"current_steps": 37340, "total_steps": 38160, "loss": 0.0019, "lr": 7.046771533065766e-08, "epoch": 19.570230607966458, "percentage": 97.85, "elapsed_time": "2:23:24", "remaining_time": "0:03:08", "throughput": 2837.48, "total_tokens": 24414280} {"current_steps": 37345, "total_steps": 38160, "loss": 0.0026, "lr": 6.961241064288859e-08, "epoch": 19.57285115303983, "percentage": 97.86, "elapsed_time": "2:23:25", "remaining_time": "0:03:07", "throughput": 2837.48, "total_tokens": 24417352} {"current_steps": 37350, "total_steps": 38160, "loss": 0.0052, "lr": 6.876232110778202e-08, "epoch": 19.57547169811321, "percentage": 97.88, "elapsed_time": "2:23:26", "remaining_time": "0:03:06", "throughput": 2837.58, "total_tokens": 24421192} {"current_steps": 37355, "total_steps": 38160, "loss": 0.0038, "lr": 6.791744690316515e-08, "epoch": 19.578092243186582, "percentage": 97.89, "elapsed_time": "2:23:27", "remaining_time": "0:03:05", "throughput": 2837.62, "total_tokens": 24424744} {"current_steps": 37360, "total_steps": 38160, "loss": 0.011, "lr": 6.707778820577715e-08, "epoch": 19.58071278825996, "percentage": 97.9, "elapsed_time": "2:23:28", "remaining_time": "0:03:04", "throughput": 2837.59, "total_tokens": 24427592} {"current_steps": 37365, "total_steps": 38160, "loss": 0.0049, "lr": 6.624334519126919e-08, "epoch": 19.583333333333332, "percentage": 97.92, "elapsed_time": "2:23:29", "remaining_time": "0:03:03", "throughput": 2837.57, "total_tokens": 24430600} {"current_steps": 37370, "total_steps": 38160, "loss": 0.0075, "lr": 6.541411803419329e-08, "epoch": 19.58595387840671, "percentage": 97.93, "elapsed_time": "2:23:30", "remaining_time": "0:03:02", "throughput": 2837.52, "total_tokens": 24433160} {"current_steps": 37375, "total_steps": 38160, "loss": 0.0025, "lr": 6.459010690801626e-08, "epoch": 19.588574423480082, "percentage": 97.94, "elapsed_time": "2:23:31", "remaining_time": "0:03:00", "throughput": 2837.44, "total_tokens": 24435656} {"current_steps": 37380, "total_steps": 38160, "loss": 0.0086, "lr": 6.377131198510855e-08, "epoch": 19.59119496855346, "percentage": 97.96, "elapsed_time": "2:23:32", "remaining_time": "0:02:59", "throughput": 2837.41, "total_tokens": 24438440} {"current_steps": 37385, "total_steps": 38160, "loss": 0.0039, "lr": 6.295773343675537e-08, "epoch": 19.593815513626833, "percentage": 97.97, "elapsed_time": "2:23:34", "remaining_time": "0:02:58", "throughput": 2837.39, "total_tokens": 24441416} {"current_steps": 37390, "total_steps": 38160, "loss": 0.0022, "lr": 6.214937143314837e-08, "epoch": 19.59643605870021, "percentage": 97.98, "elapsed_time": "2:23:35", "remaining_time": "0:02:57", "throughput": 2837.27, "total_tokens": 24444328} {"current_steps": 37395, "total_steps": 38160, "loss": 0.0037, "lr": 6.134622614338559e-08, "epoch": 19.599056603773583, "percentage": 98.0, "elapsed_time": "2:23:36", "remaining_time": "0:02:56", "throughput": 2837.16, "total_tokens": 24446472} {"current_steps": 37400, "total_steps": 38160, "loss": 0.013, "lr": 6.05482977354771e-08, "epoch": 19.60167714884696, "percentage": 98.01, "elapsed_time": "2:23:37", "remaining_time": "0:02:55", "throughput": 2837.17, "total_tokens": 24449544} {"current_steps": 37405, "total_steps": 38160, "loss": 0.0111, "lr": 5.975558637634215e-08, "epoch": 19.604297693920337, "percentage": 98.02, "elapsed_time": "2:23:38", "remaining_time": "0:02:53", "throughput": 2837.19, "total_tokens": 24452776} {"current_steps": 37410, "total_steps": 38160, "loss": 0.0024, "lr": 5.896809223180366e-08, "epoch": 19.60691823899371, "percentage": 98.03, "elapsed_time": "2:23:39", "remaining_time": "0:02:52", "throughput": 2837.16, "total_tokens": 24455560} {"current_steps": 37415, "total_steps": 38160, "loss": 0.0019, "lr": 5.8185815466596516e-08, "epoch": 19.609538784067087, "percentage": 98.05, "elapsed_time": "2:23:40", "remaining_time": "0:02:51", "throughput": 2837.14, "total_tokens": 24458408} {"current_steps": 37420, "total_steps": 38160, "loss": 0.0061, "lr": 5.7408756244370365e-08, "epoch": 19.61215932914046, "percentage": 98.06, "elapsed_time": "2:23:41", "remaining_time": "0:02:50", "throughput": 2837.14, "total_tokens": 24461576} {"current_steps": 37425, "total_steps": 38160, "loss": 0.005, "lr": 5.663691472766741e-08, "epoch": 19.614779874213838, "percentage": 98.07, "elapsed_time": "2:23:42", "remaining_time": "0:02:49", "throughput": 2837.17, "total_tokens": 24464840} {"current_steps": 37430, "total_steps": 38160, "loss": 0.0018, "lr": 5.587029107795572e-08, "epoch": 19.61740041928721, "percentage": 98.09, "elapsed_time": "2:23:44", "remaining_time": "0:02:48", "throughput": 2837.2, "total_tokens": 24468200} {"current_steps": 37435, "total_steps": 38160, "loss": 0.0026, "lr": 5.510888545559867e-08, "epoch": 19.620020964360588, "percentage": 98.1, "elapsed_time": "2:23:45", "remaining_time": "0:02:47", "throughput": 2837.2, "total_tokens": 24471176} {"current_steps": 37440, "total_steps": 38160, "loss": 0.002, "lr": 5.435269801987997e-08, "epoch": 19.62264150943396, "percentage": 98.11, "elapsed_time": "2:23:46", "remaining_time": "0:02:45", "throughput": 2837.18, "total_tokens": 24473960} {"current_steps": 37445, "total_steps": 38160, "loss": 0.0043, "lr": 5.360172892897863e-08, "epoch": 19.62526205450734, "percentage": 98.13, "elapsed_time": "2:23:47", "remaining_time": "0:02:44", "throughput": 2837.16, "total_tokens": 24476776} {"current_steps": 37450, "total_steps": 38160, "loss": 0.0053, "lr": 5.285597833999401e-08, "epoch": 19.627882599580712, "percentage": 98.14, "elapsed_time": "2:23:48", "remaining_time": "0:02:43", "throughput": 2837.22, "total_tokens": 24480456} {"current_steps": 37455, "total_steps": 38160, "loss": 0.0031, "lr": 5.2115446408926295e-08, "epoch": 19.63050314465409, "percentage": 98.15, "elapsed_time": "2:23:49", "remaining_time": "0:02:42", "throughput": 2837.21, "total_tokens": 24483400} {"current_steps": 37460, "total_steps": 38160, "loss": 0.0115, "lr": 5.138013329068769e-08, "epoch": 19.633123689727462, "percentage": 98.17, "elapsed_time": "2:23:50", "remaining_time": "0:02:41", "throughput": 2837.22, "total_tokens": 24486536} {"current_steps": 37465, "total_steps": 38160, "loss": 0.0057, "lr": 5.065003913909405e-08, "epoch": 19.63574423480084, "percentage": 98.18, "elapsed_time": "2:23:51", "remaining_time": "0:02:40", "throughput": 2837.25, "total_tokens": 24490056} {"current_steps": 37470, "total_steps": 38160, "loss": 0.004, "lr": 4.9925164106875975e-08, "epoch": 19.638364779874212, "percentage": 98.19, "elapsed_time": "2:23:52", "remaining_time": "0:02:38", "throughput": 2837.27, "total_tokens": 24493160} {"current_steps": 37475, "total_steps": 38160, "loss": 0.0054, "lr": 4.9205508345670506e-08, "epoch": 19.64098532494759, "percentage": 98.2, "elapsed_time": "2:23:53", "remaining_time": "0:02:37", "throughput": 2837.26, "total_tokens": 24496200} {"current_steps": 37480, "total_steps": 38160, "loss": 0.0079, "lr": 4.8491072006015546e-08, "epoch": 19.643605870020963, "percentage": 98.22, "elapsed_time": "2:23:55", "remaining_time": "0:02:36", "throughput": 2837.35, "total_tokens": 24500680} {"current_steps": 37485, "total_steps": 38160, "loss": 0.0632, "lr": 4.778185523736933e-08, "epoch": 19.64622641509434, "percentage": 98.23, "elapsed_time": "2:23:56", "remaining_time": "0:02:35", "throughput": 2837.34, "total_tokens": 24503720} {"current_steps": 37490, "total_steps": 38160, "loss": 0.0063, "lr": 4.7077858188085414e-08, "epoch": 19.648846960167717, "percentage": 98.24, "elapsed_time": "2:23:57", "remaining_time": "0:02:34", "throughput": 2837.31, "total_tokens": 24506440} {"current_steps": 37495, "total_steps": 38160, "loss": 0.0037, "lr": 4.6379081005437644e-08, "epoch": 19.65146750524109, "percentage": 98.26, "elapsed_time": "2:23:58", "remaining_time": "0:02:33", "throughput": 2837.3, "total_tokens": 24509384} {"current_steps": 37500, "total_steps": 38160, "loss": 0.0045, "lr": 4.568552383560076e-08, "epoch": 19.654088050314467, "percentage": 98.27, "elapsed_time": "2:23:59", "remaining_time": "0:02:32", "throughput": 2837.22, "total_tokens": 24511720} {"current_steps": 37505, "total_steps": 38160, "loss": 0.0027, "lr": 4.4997186823655945e-08, "epoch": 19.65670859538784, "percentage": 98.28, "elapsed_time": "2:24:00", "remaining_time": "0:02:30", "throughput": 2837.17, "total_tokens": 24514472} {"current_steps": 37510, "total_steps": 38160, "loss": 0.003, "lr": 4.431407011360189e-08, "epoch": 19.659329140461217, "percentage": 98.3, "elapsed_time": "2:24:01", "remaining_time": "0:02:29", "throughput": 2837.14, "total_tokens": 24517224} {"current_steps": 37515, "total_steps": 38160, "loss": 0.0056, "lr": 4.3636173848332627e-08, "epoch": 19.66194968553459, "percentage": 98.31, "elapsed_time": "2:24:02", "remaining_time": "0:02:28", "throughput": 2837.08, "total_tokens": 24519944} {"current_steps": 37520, "total_steps": 38160, "loss": 0.01, "lr": 4.2963498169656946e-08, "epoch": 19.664570230607968, "percentage": 98.32, "elapsed_time": "2:24:03", "remaining_time": "0:02:27", "throughput": 2837.21, "total_tokens": 24524840} {"current_steps": 37525, "total_steps": 38160, "loss": 0.0025, "lr": 4.229604321829561e-08, "epoch": 19.66719077568134, "percentage": 98.34, "elapsed_time": "2:24:05", "remaining_time": "0:02:26", "throughput": 2837.21, "total_tokens": 24527912} {"current_steps": 37530, "total_steps": 38160, "loss": 0.0047, "lr": 4.16338091338675e-08, "epoch": 19.669811320754718, "percentage": 98.35, "elapsed_time": "2:24:06", "remaining_time": "0:02:25", "throughput": 2837.14, "total_tokens": 24530696} {"current_steps": 37535, "total_steps": 38160, "loss": 0.0011, "lr": 4.097679605490623e-08, "epoch": 19.67243186582809, "percentage": 98.36, "elapsed_time": "2:24:07", "remaining_time": "0:02:23", "throughput": 2837.08, "total_tokens": 24533256} {"current_steps": 37540, "total_steps": 38160, "loss": 0.0049, "lr": 4.032500411885465e-08, "epoch": 19.67505241090147, "percentage": 98.38, "elapsed_time": "2:24:08", "remaining_time": "0:02:22", "throughput": 2837.09, "total_tokens": 24536552} {"current_steps": 37545, "total_steps": 38160, "loss": 0.0044, "lr": 3.967843346205369e-08, "epoch": 19.677672955974842, "percentage": 98.39, "elapsed_time": "2:24:09", "remaining_time": "0:02:21", "throughput": 2837.08, "total_tokens": 24539464} {"current_steps": 37550, "total_steps": 38160, "loss": 0.0021, "lr": 3.903708421976182e-08, "epoch": 19.68029350104822, "percentage": 98.4, "elapsed_time": "2:24:10", "remaining_time": "0:02:20", "throughput": 2837.06, "total_tokens": 24542312} {"current_steps": 37555, "total_steps": 38160, "loss": 0.0024, "lr": 3.840095652614395e-08, "epoch": 19.682914046121592, "percentage": 98.41, "elapsed_time": "2:24:11", "remaining_time": "0:02:19", "throughput": 2837.11, "total_tokens": 24546056} {"current_steps": 37560, "total_steps": 38160, "loss": 0.0064, "lr": 3.777005051426863e-08, "epoch": 19.68553459119497, "percentage": 98.43, "elapsed_time": "2:24:12", "remaining_time": "0:02:18", "throughput": 2837.14, "total_tokens": 24549512} {"current_steps": 37565, "total_steps": 38160, "loss": 0.003, "lr": 3.71443663161164e-08, "epoch": 19.688155136268342, "percentage": 98.44, "elapsed_time": "2:24:13", "remaining_time": "0:02:17", "throughput": 2837.19, "total_tokens": 24553000} {"current_steps": 37570, "total_steps": 38160, "loss": 0.1698, "lr": 3.652390406256867e-08, "epoch": 19.69077568134172, "percentage": 98.45, "elapsed_time": "2:24:15", "remaining_time": "0:02:15", "throughput": 2837.17, "total_tokens": 24555944} {"current_steps": 37575, "total_steps": 38160, "loss": 0.0034, "lr": 3.5908663883421624e-08, "epoch": 19.693396226415093, "percentage": 98.47, "elapsed_time": "2:24:16", "remaining_time": "0:02:14", "throughput": 2837.11, "total_tokens": 24558600} {"current_steps": 37580, "total_steps": 38160, "loss": 0.0032, "lr": 3.529864590737786e-08, "epoch": 19.69601677148847, "percentage": 98.48, "elapsed_time": "2:24:17", "remaining_time": "0:02:13", "throughput": 2837.15, "total_tokens": 24562440} {"current_steps": 37585, "total_steps": 38160, "loss": 0.0303, "lr": 3.4693850262046415e-08, "epoch": 19.698637316561843, "percentage": 98.49, "elapsed_time": "2:24:18", "remaining_time": "0:02:12", "throughput": 2837.18, "total_tokens": 24565736} {"current_steps": 37590, "total_steps": 38160, "loss": 0.0039, "lr": 3.409427707394275e-08, "epoch": 19.70125786163522, "percentage": 98.51, "elapsed_time": "2:24:19", "remaining_time": "0:02:11", "throughput": 2837.19, "total_tokens": 24569064} {"current_steps": 37595, "total_steps": 38160, "loss": 0.0039, "lr": 3.349992646848599e-08, "epoch": 19.703878406708597, "percentage": 98.52, "elapsed_time": "2:24:20", "remaining_time": "0:02:10", "throughput": 2837.24, "total_tokens": 24572584} {"current_steps": 37600, "total_steps": 38160, "loss": 0.0255, "lr": 3.291079857001556e-08, "epoch": 19.70649895178197, "percentage": 98.53, "elapsed_time": "2:24:21", "remaining_time": "0:02:09", "throughput": 2837.18, "total_tokens": 24575240} {"current_steps": 37605, "total_steps": 38160, "loss": 0.0346, "lr": 3.2326893501763436e-08, "epoch": 19.709119496855347, "percentage": 98.55, "elapsed_time": "2:24:22", "remaining_time": "0:02:07", "throughput": 2837.21, "total_tokens": 24578408} {"current_steps": 37610, "total_steps": 38160, "loss": 0.0092, "lr": 3.174821138588191e-08, "epoch": 19.71174004192872, "percentage": 98.56, "elapsed_time": "2:24:23", "remaining_time": "0:02:06", "throughput": 2837.16, "total_tokens": 24581064} {"current_steps": 37615, "total_steps": 38160, "loss": 0.004, "lr": 3.11747523434186e-08, "epoch": 19.714360587002098, "percentage": 98.57, "elapsed_time": "2:24:25", "remaining_time": "0:02:05", "throughput": 2837.16, "total_tokens": 24584200} {"current_steps": 37620, "total_steps": 38160, "loss": 0.0045, "lr": 3.060651649434143e-08, "epoch": 19.71698113207547, "percentage": 98.58, "elapsed_time": "2:24:26", "remaining_time": "0:02:04", "throughput": 2837.18, "total_tokens": 24587400} {"current_steps": 37625, "total_steps": 38160, "loss": 0.0033, "lr": 3.004350395751088e-08, "epoch": 19.719601677148848, "percentage": 98.6, "elapsed_time": "2:24:27", "remaining_time": "0:02:03", "throughput": 2837.15, "total_tokens": 24590088} {"current_steps": 37630, "total_steps": 38160, "loss": 0.0163, "lr": 2.94857148507105e-08, "epoch": 19.72222222222222, "percentage": 98.61, "elapsed_time": "2:24:28", "remaining_time": "0:02:02", "throughput": 2837.13, "total_tokens": 24593064} {"current_steps": 37635, "total_steps": 38160, "loss": 0.0037, "lr": 2.893314929061641e-08, "epoch": 19.7248427672956, "percentage": 98.62, "elapsed_time": "2:24:29", "remaining_time": "0:02:00", "throughput": 2837.1, "total_tokens": 24595816} {"current_steps": 37640, "total_steps": 38160, "loss": 0.0051, "lr": 2.8385807392825037e-08, "epoch": 19.72746331236897, "percentage": 98.64, "elapsed_time": "2:24:30", "remaining_time": "0:01:59", "throughput": 2837.1, "total_tokens": 24598824} {"current_steps": 37645, "total_steps": 38160, "loss": 0.0133, "lr": 2.7843689271830897e-08, "epoch": 19.73008385744235, "percentage": 98.65, "elapsed_time": "2:24:31", "remaining_time": "0:01:58", "throughput": 2837.06, "total_tokens": 24601480} {"current_steps": 37650, "total_steps": 38160, "loss": 0.0021, "lr": 2.7306795041040502e-08, "epoch": 19.732704402515722, "percentage": 98.66, "elapsed_time": "2:24:32", "remaining_time": "0:01:57", "throughput": 2837.04, "total_tokens": 24604296} {"current_steps": 37655, "total_steps": 38160, "loss": 0.0048, "lr": 2.677512481276401e-08, "epoch": 19.7353249475891, "percentage": 98.68, "elapsed_time": "2:24:33", "remaining_time": "0:01:56", "throughput": 2837.04, "total_tokens": 24607336} {"current_steps": 37660, "total_steps": 38160, "loss": 0.0101, "lr": 2.6248678698220785e-08, "epoch": 19.737945492662472, "percentage": 98.69, "elapsed_time": "2:24:34", "remaining_time": "0:01:55", "throughput": 2837.1, "total_tokens": 24610984} {"current_steps": 37665, "total_steps": 38160, "loss": 0.0013, "lr": 2.5727456807542183e-08, "epoch": 19.74056603773585, "percentage": 98.7, "elapsed_time": "2:24:35", "remaining_time": "0:01:54", "throughput": 2837.07, "total_tokens": 24613800} {"current_steps": 37670, "total_steps": 38160, "loss": 0.0042, "lr": 2.5211459249754875e-08, "epoch": 19.743186582809223, "percentage": 98.72, "elapsed_time": "2:24:36", "remaining_time": "0:01:52", "throughput": 2837.08, "total_tokens": 24617064} {"current_steps": 37675, "total_steps": 38160, "loss": 0.0033, "lr": 2.4700686132803076e-08, "epoch": 19.7458071278826, "percentage": 98.73, "elapsed_time": "2:24:38", "remaining_time": "0:01:51", "throughput": 2837.19, "total_tokens": 24621416} {"current_steps": 37680, "total_steps": 38160, "loss": 0.0185, "lr": 2.4195137563534643e-08, "epoch": 19.748427672955973, "percentage": 98.74, "elapsed_time": "2:24:39", "remaining_time": "0:01:50", "throughput": 2837.26, "total_tokens": 24625160} {"current_steps": 37685, "total_steps": 38160, "loss": 0.0072, "lr": 2.369481364770387e-08, "epoch": 19.75104821802935, "percentage": 98.76, "elapsed_time": "2:24:40", "remaining_time": "0:01:49", "throughput": 2837.29, "total_tokens": 24628520} {"current_steps": 37690, "total_steps": 38160, "loss": 0.0408, "lr": 2.3199714489974266e-08, "epoch": 19.753668763102727, "percentage": 98.77, "elapsed_time": "2:24:41", "remaining_time": "0:01:48", "throughput": 2837.29, "total_tokens": 24631528} {"current_steps": 37695, "total_steps": 38160, "loss": 0.0028, "lr": 2.2709840193912978e-08, "epoch": 19.7562893081761, "percentage": 98.78, "elapsed_time": "2:24:42", "remaining_time": "0:01:47", "throughput": 2837.28, "total_tokens": 24634440} {"current_steps": 37700, "total_steps": 38160, "loss": 0.0026, "lr": 2.2225190861999146e-08, "epoch": 19.758909853249477, "percentage": 98.79, "elapsed_time": "2:24:43", "remaining_time": "0:01:45", "throughput": 2837.28, "total_tokens": 24637704} {"current_steps": 37705, "total_steps": 38160, "loss": 0.0045, "lr": 2.1745766595612783e-08, "epoch": 19.76153039832285, "percentage": 98.81, "elapsed_time": "2:24:44", "remaining_time": "0:01:44", "throughput": 2837.29, "total_tokens": 24640776} {"current_steps": 37710, "total_steps": 38160, "loss": 0.0018, "lr": 2.1271567495045886e-08, "epoch": 19.764150943396228, "percentage": 98.82, "elapsed_time": "2:24:45", "remaining_time": "0:01:43", "throughput": 2837.26, "total_tokens": 24643624} {"current_steps": 37715, "total_steps": 38160, "loss": 0.0074, "lr": 2.0802593659491333e-08, "epoch": 19.7667714884696, "percentage": 98.83, "elapsed_time": "2:24:46", "remaining_time": "0:01:42", "throughput": 2837.31, "total_tokens": 24647496} {"current_steps": 37720, "total_steps": 38160, "loss": 0.0073, "lr": 2.0338845187059528e-08, "epoch": 19.769392033542978, "percentage": 98.85, "elapsed_time": "2:24:48", "remaining_time": "0:01:41", "throughput": 2837.34, "total_tokens": 24651048} {"current_steps": 37725, "total_steps": 38160, "loss": 0.0327, "lr": 1.988032217475899e-08, "epoch": 19.77201257861635, "percentage": 98.86, "elapsed_time": "2:24:49", "remaining_time": "0:01:40", "throughput": 2837.29, "total_tokens": 24653736} {"current_steps": 37730, "total_steps": 38160, "loss": 0.0159, "lr": 1.942702471850466e-08, "epoch": 19.77463312368973, "percentage": 98.87, "elapsed_time": "2:24:50", "remaining_time": "0:01:39", "throughput": 2837.32, "total_tokens": 24657032} {"current_steps": 37735, "total_steps": 38160, "loss": 0.0061, "lr": 1.897895291312346e-08, "epoch": 19.7772536687631, "percentage": 98.89, "elapsed_time": "2:24:51", "remaining_time": "0:01:37", "throughput": 2837.32, "total_tokens": 24660136} {"current_steps": 37740, "total_steps": 38160, "loss": 0.0234, "lr": 1.8536106852348746e-08, "epoch": 19.77987421383648, "percentage": 98.9, "elapsed_time": "2:24:52", "remaining_time": "0:01:36", "throughput": 2837.3, "total_tokens": 24663048} {"current_steps": 37745, "total_steps": 38160, "loss": 0.0146, "lr": 1.8098486628814748e-08, "epoch": 19.782494758909852, "percentage": 98.91, "elapsed_time": "2:24:53", "remaining_time": "0:01:35", "throughput": 2837.37, "total_tokens": 24667016} {"current_steps": 37750, "total_steps": 38160, "loss": 0.0108, "lr": 1.7666092334067684e-08, "epoch": 19.78511530398323, "percentage": 98.93, "elapsed_time": "2:24:54", "remaining_time": "0:01:34", "throughput": 2837.42, "total_tokens": 24670568} {"current_steps": 37755, "total_steps": 38160, "loss": 0.007, "lr": 1.7238924058562977e-08, "epoch": 19.787735849056602, "percentage": 98.94, "elapsed_time": "2:24:55", "remaining_time": "0:01:33", "throughput": 2837.46, "total_tokens": 24674024} {"current_steps": 37760, "total_steps": 38160, "loss": 0.0079, "lr": 1.6816981891656924e-08, "epoch": 19.79035639412998, "percentage": 98.95, "elapsed_time": "2:24:56", "remaining_time": "0:01:32", "throughput": 2837.46, "total_tokens": 24677320} {"current_steps": 37765, "total_steps": 38160, "loss": 0.0027, "lr": 1.6400265921615032e-08, "epoch": 19.792976939203353, "percentage": 98.96, "elapsed_time": "2:24:58", "remaining_time": "0:01:30", "throughput": 2837.5, "total_tokens": 24681096} {"current_steps": 37770, "total_steps": 38160, "loss": 0.0028, "lr": 1.598877623560924e-08, "epoch": 19.79559748427673, "percentage": 98.98, "elapsed_time": "2:24:59", "remaining_time": "0:01:29", "throughput": 2837.47, "total_tokens": 24684168} {"current_steps": 37775, "total_steps": 38160, "loss": 0.0024, "lr": 1.5582512919717908e-08, "epoch": 19.798218029350103, "percentage": 98.99, "elapsed_time": "2:25:00", "remaining_time": "0:01:28", "throughput": 2837.5, "total_tokens": 24687464} {"current_steps": 37780, "total_steps": 38160, "loss": 0.0265, "lr": 1.5181476058928613e-08, "epoch": 19.80083857442348, "percentage": 99.0, "elapsed_time": "2:25:01", "remaining_time": "0:01:27", "throughput": 2837.55, "total_tokens": 24690920} {"current_steps": 37785, "total_steps": 38160, "loss": 0.0027, "lr": 1.4785665737129805e-08, "epoch": 19.803459119496857, "percentage": 99.02, "elapsed_time": "2:25:02", "remaining_time": "0:01:26", "throughput": 2837.53, "total_tokens": 24693768} {"current_steps": 37790, "total_steps": 38160, "loss": 0.0102, "lr": 1.4395082037127471e-08, "epoch": 19.80607966457023, "percentage": 99.03, "elapsed_time": "2:25:03", "remaining_time": "0:01:25", "throughput": 2837.49, "total_tokens": 24696552} {"current_steps": 37795, "total_steps": 38160, "loss": 0.0043, "lr": 1.4009725040620148e-08, "epoch": 19.808700209643607, "percentage": 99.04, "elapsed_time": "2:25:04", "remaining_time": "0:01:24", "throughput": 2837.5, "total_tokens": 24699656} {"current_steps": 37800, "total_steps": 38160, "loss": 0.0103, "lr": 1.3629594828223902e-08, "epoch": 19.81132075471698, "percentage": 99.06, "elapsed_time": "2:25:05", "remaining_time": "0:01:22", "throughput": 2837.56, "total_tokens": 24703496} {"current_steps": 37805, "total_steps": 38160, "loss": 0.0128, "lr": 1.3254691479458458e-08, "epoch": 19.813941299790358, "percentage": 99.07, "elapsed_time": "2:25:07", "remaining_time": "0:01:21", "throughput": 2837.57, "total_tokens": 24706760} {"current_steps": 37810, "total_steps": 38160, "loss": 0.012, "lr": 1.2885015072747197e-08, "epoch": 19.81656184486373, "percentage": 99.08, "elapsed_time": "2:25:08", "remaining_time": "0:01:20", "throughput": 2837.63, "total_tokens": 24710952} {"current_steps": 37815, "total_steps": 38160, "loss": 0.0032, "lr": 1.2520565685419927e-08, "epoch": 19.819182389937108, "percentage": 99.1, "elapsed_time": "2:25:09", "remaining_time": "0:01:19", "throughput": 2837.61, "total_tokens": 24714088} {"current_steps": 37820, "total_steps": 38160, "loss": 0.0048, "lr": 1.2161343393721214e-08, "epoch": 19.82180293501048, "percentage": 99.11, "elapsed_time": "2:25:10", "remaining_time": "0:01:18", "throughput": 2837.61, "total_tokens": 24717064} {"current_steps": 37825, "total_steps": 38160, "loss": 0.0149, "lr": 1.1807348272790952e-08, "epoch": 19.82442348008386, "percentage": 99.12, "elapsed_time": "2:25:11", "remaining_time": "0:01:17", "throughput": 2837.63, "total_tokens": 24720712} {"current_steps": 37830, "total_steps": 38160, "loss": 0.0121, "lr": 1.1458580396683794e-08, "epoch": 19.82704402515723, "percentage": 99.14, "elapsed_time": "2:25:12", "remaining_time": "0:01:16", "throughput": 2837.61, "total_tokens": 24723560} {"current_steps": 37835, "total_steps": 38160, "loss": 0.0241, "lr": 1.1115039838358044e-08, "epoch": 19.82966457023061, "percentage": 99.15, "elapsed_time": "2:25:14", "remaining_time": "0:01:14", "throughput": 2837.84, "total_tokens": 24731656} {"current_steps": 37840, "total_steps": 38160, "loss": 0.0149, "lr": 1.0776726669678439e-08, "epoch": 19.832285115303982, "percentage": 99.16, "elapsed_time": "2:25:16", "remaining_time": "0:01:13", "throughput": 2837.79, "total_tokens": 24734280} {"current_steps": 37845, "total_steps": 38160, "loss": 0.0063, "lr": 1.044364096141337e-08, "epoch": 19.83490566037736, "percentage": 99.17, "elapsed_time": "2:25:17", "remaining_time": "0:01:12", "throughput": 2837.75, "total_tokens": 24736840} {"current_steps": 37850, "total_steps": 38160, "loss": 0.0034, "lr": 1.0115782783243211e-08, "epoch": 19.837526205450732, "percentage": 99.19, "elapsed_time": "2:25:18", "remaining_time": "0:01:11", "throughput": 2837.79, "total_tokens": 24740200} {"current_steps": 37855, "total_steps": 38160, "loss": 0.0065, "lr": 9.793152203751988e-09, "epoch": 19.84014675052411, "percentage": 99.2, "elapsed_time": "2:25:19", "remaining_time": "0:01:10", "throughput": 2837.84, "total_tokens": 24743592} {"current_steps": 37860, "total_steps": 38160, "loss": 0.0114, "lr": 9.475749290430158e-09, "epoch": 19.842767295597483, "percentage": 99.21, "elapsed_time": "2:25:20", "remaining_time": "0:01:09", "throughput": 2837.82, "total_tokens": 24746344} {"current_steps": 37865, "total_steps": 38160, "loss": 0.0028, "lr": 9.16357410967461e-09, "epoch": 19.84538784067086, "percentage": 99.23, "elapsed_time": "2:25:21", "remaining_time": "0:01:07", "throughput": 2837.75, "total_tokens": 24748712} {"current_steps": 37870, "total_steps": 38160, "loss": 0.0039, "lr": 8.856626726788664e-09, "epoch": 19.848008385744233, "percentage": 99.24, "elapsed_time": "2:25:22", "remaining_time": "0:01:06", "throughput": 2837.81, "total_tokens": 24752264} {"current_steps": 37875, "total_steps": 38160, "loss": 0.0016, "lr": 8.554907205982066e-09, "epoch": 19.85062893081761, "percentage": 99.25, "elapsed_time": "2:25:23", "remaining_time": "0:01:05", "throughput": 2837.81, "total_tokens": 24755816} {"current_steps": 37880, "total_steps": 38160, "loss": 0.0044, "lr": 8.258415610373772e-09, "epoch": 19.853249475890987, "percentage": 99.27, "elapsed_time": "2:25:24", "remaining_time": "0:01:04", "throughput": 2837.81, "total_tokens": 24758792} {"current_steps": 37885, "total_steps": 38160, "loss": 0.0092, "lr": 7.967152001980838e-09, "epoch": 19.85587002096436, "percentage": 99.28, "elapsed_time": "2:25:25", "remaining_time": "0:01:03", "throughput": 2837.88, "total_tokens": 24762504} {"current_steps": 37890, "total_steps": 38160, "loss": 0.0816, "lr": 7.681116441737856e-09, "epoch": 19.858490566037737, "percentage": 99.29, "elapsed_time": "2:25:26", "remaining_time": "0:01:02", "throughput": 2837.97, "total_tokens": 24766760} {"current_steps": 37895, "total_steps": 38160, "loss": 0.0023, "lr": 7.4003089894747464e-09, "epoch": 19.86111111111111, "percentage": 99.31, "elapsed_time": "2:25:28", "remaining_time": "0:01:01", "throughput": 2838.01, "total_tokens": 24770536} {"current_steps": 37900, "total_steps": 38160, "loss": 0.0016, "lr": 7.12472970393896e-09, "epoch": 19.863731656184488, "percentage": 99.32, "elapsed_time": "2:25:29", "remaining_time": "0:00:59", "throughput": 2838.05, "total_tokens": 24773960} {"current_steps": 37905, "total_steps": 38160, "loss": 0.0032, "lr": 6.854378642776049e-09, "epoch": 19.86635220125786, "percentage": 99.33, "elapsed_time": "2:25:30", "remaining_time": "0:00:58", "throughput": 2838.02, "total_tokens": 24776744} {"current_steps": 37910, "total_steps": 38160, "loss": 0.0083, "lr": 6.589255862538002e-09, "epoch": 19.868972746331238, "percentage": 99.34, "elapsed_time": "2:25:31", "remaining_time": "0:00:57", "throughput": 2838.13, "total_tokens": 24781128} {"current_steps": 37915, "total_steps": 38160, "loss": 0.0015, "lr": 6.32936141869156e-09, "epoch": 19.87159329140461, "percentage": 99.36, "elapsed_time": "2:25:32", "remaining_time": "0:00:56", "throughput": 2838.12, "total_tokens": 24784072} {"current_steps": 37920, "total_steps": 38160, "loss": 0.0198, "lr": 6.074695365596017e-09, "epoch": 19.87421383647799, "percentage": 99.37, "elapsed_time": "2:25:33", "remaining_time": "0:00:55", "throughput": 2838.14, "total_tokens": 24787304} {"current_steps": 37925, "total_steps": 38160, "loss": 0.0028, "lr": 5.8252577565309775e-09, "epoch": 19.87683438155136, "percentage": 99.38, "elapsed_time": "2:25:34", "remaining_time": "0:00:54", "throughput": 2838.13, "total_tokens": 24790216} {"current_steps": 37930, "total_steps": 38160, "loss": 0.008, "lr": 5.581048643671371e-09, "epoch": 19.87945492662474, "percentage": 99.4, "elapsed_time": "2:25:35", "remaining_time": "0:00:52", "throughput": 2838.2, "total_tokens": 24794024} {"current_steps": 37935, "total_steps": 38160, "loss": 0.003, "lr": 5.342068078106888e-09, "epoch": 19.882075471698112, "percentage": 99.41, "elapsed_time": "2:25:36", "remaining_time": "0:00:51", "throughput": 2838.19, "total_tokens": 24797032} {"current_steps": 37940, "total_steps": 38160, "loss": 0.0029, "lr": 5.1083161098253175e-09, "epoch": 19.88469601677149, "percentage": 99.42, "elapsed_time": "2:25:37", "remaining_time": "0:00:50", "throughput": 2838.14, "total_tokens": 24799592} {"current_steps": 37945, "total_steps": 38160, "loss": 0.0068, "lr": 4.87979278772921e-09, "epoch": 19.887316561844862, "percentage": 99.44, "elapsed_time": "2:25:39", "remaining_time": "0:00:49", "throughput": 2838.23, "total_tokens": 24803944} {"current_steps": 37950, "total_steps": 38160, "loss": 0.0035, "lr": 4.656498159619216e-09, "epoch": 19.88993710691824, "percentage": 99.45, "elapsed_time": "2:25:40", "remaining_time": "0:00:48", "throughput": 2838.32, "total_tokens": 24807816} {"current_steps": 37955, "total_steps": 38160, "loss": 0.0031, "lr": 4.438432272210746e-09, "epoch": 19.892557651991613, "percentage": 99.46, "elapsed_time": "2:25:41", "remaining_time": "0:00:47", "throughput": 2838.35, "total_tokens": 24811272} {"current_steps": 37960, "total_steps": 38160, "loss": 0.0025, "lr": 4.225595171114538e-09, "epoch": 19.89517819706499, "percentage": 99.48, "elapsed_time": "2:25:42", "remaining_time": "0:00:46", "throughput": 2838.42, "total_tokens": 24815048} {"current_steps": 37965, "total_steps": 38160, "loss": 0.0119, "lr": 4.017986900858861e-09, "epoch": 19.897798742138363, "percentage": 99.49, "elapsed_time": "2:25:43", "remaining_time": "0:00:44", "throughput": 2838.43, "total_tokens": 24818120} {"current_steps": 37970, "total_steps": 38160, "loss": 0.005, "lr": 3.815607504870089e-09, "epoch": 19.90041928721174, "percentage": 99.5, "elapsed_time": "2:25:44", "remaining_time": "0:00:43", "throughput": 2838.51, "total_tokens": 24822280} {"current_steps": 37975, "total_steps": 38160, "loss": 0.0042, "lr": 3.618457025486577e-09, "epoch": 19.903039832285117, "percentage": 99.52, "elapsed_time": "2:25:45", "remaining_time": "0:00:42", "throughput": 2838.64, "total_tokens": 24826568} {"current_steps": 37980, "total_steps": 38160, "loss": 0.0039, "lr": 3.426535503947559e-09, "epoch": 19.90566037735849, "percentage": 99.53, "elapsed_time": "2:25:47", "remaining_time": "0:00:41", "throughput": 2838.65, "total_tokens": 24829768} {"current_steps": 37985, "total_steps": 38160, "loss": 0.0076, "lr": 3.2398429803986997e-09, "epoch": 19.908280922431867, "percentage": 99.54, "elapsed_time": "2:25:48", "remaining_time": "0:00:40", "throughput": 2838.6, "total_tokens": 24832392} {"current_steps": 37990, "total_steps": 38160, "loss": 0.0067, "lr": 3.058379493900421e-09, "epoch": 19.91090146750524, "percentage": 99.55, "elapsed_time": "2:25:49", "remaining_time": "0:00:39", "throughput": 2838.54, "total_tokens": 24834856} {"current_steps": 37995, "total_steps": 38160, "loss": 0.0166, "lr": 2.882145082405696e-09, "epoch": 19.913522012578618, "percentage": 99.57, "elapsed_time": "2:25:50", "remaining_time": "0:00:37", "throughput": 2838.57, "total_tokens": 24838248} {"current_steps": 38000, "total_steps": 38160, "loss": 0.0028, "lr": 2.711139782785033e-09, "epoch": 19.91614255765199, "percentage": 99.58, "elapsed_time": "2:25:51", "remaining_time": "0:00:36", "throughput": 2838.62, "total_tokens": 24841864} {"current_steps": 38005, "total_steps": 38160, "loss": 0.003, "lr": 2.5453636308098163e-09, "epoch": 19.918763102725368, "percentage": 99.59, "elapsed_time": "2:25:52", "remaining_time": "0:00:35", "throughput": 2838.6, "total_tokens": 24844776} {"current_steps": 38010, "total_steps": 38160, "loss": 0.0055, "lr": 2.3848166611606383e-09, "epoch": 19.92138364779874, "percentage": 99.61, "elapsed_time": "2:25:53", "remaining_time": "0:00:34", "throughput": 2838.6, "total_tokens": 24848360} {"current_steps": 38015, "total_steps": 38160, "loss": 0.0086, "lr": 2.2294989074161943e-09, "epoch": 19.92400419287212, "percentage": 99.62, "elapsed_time": "2:25:54", "remaining_time": "0:00:33", "throughput": 2838.58, "total_tokens": 24851496} {"current_steps": 38020, "total_steps": 38160, "loss": 0.0069, "lr": 2.0794104020727125e-09, "epoch": 19.92662473794549, "percentage": 99.63, "elapsed_time": "2:25:56", "remaining_time": "0:00:32", "throughput": 2838.63, "total_tokens": 24855144} {"current_steps": 38025, "total_steps": 38160, "loss": 0.0056, "lr": 1.9345511765272993e-09, "epoch": 19.92924528301887, "percentage": 99.65, "elapsed_time": "2:25:57", "remaining_time": "0:00:31", "throughput": 2838.61, "total_tokens": 24858120} {"current_steps": 38030, "total_steps": 38160, "loss": 0.0052, "lr": 1.794921261077942e-09, "epoch": 19.931865828092242, "percentage": 99.66, "elapsed_time": "2:25:58", "remaining_time": "0:00:29", "throughput": 2838.72, "total_tokens": 24862248} {"current_steps": 38035, "total_steps": 38160, "loss": 0.0047, "lr": 1.6605206849373833e-09, "epoch": 19.93448637316562, "percentage": 99.67, "elapsed_time": "2:25:59", "remaining_time": "0:00:28", "throughput": 2838.66, "total_tokens": 24864776} {"current_steps": 38040, "total_steps": 38160, "loss": 0.003, "lr": 1.531349476219246e-09, "epoch": 19.937106918238992, "percentage": 99.69, "elapsed_time": "2:26:00", "remaining_time": "0:00:27", "throughput": 2838.68, "total_tokens": 24868200} {"current_steps": 38045, "total_steps": 38160, "loss": 0.0038, "lr": 1.4074076619463584e-09, "epoch": 19.93972746331237, "percentage": 99.7, "elapsed_time": "2:26:01", "remaining_time": "0:00:26", "throughput": 2838.63, "total_tokens": 24870824} {"current_steps": 38050, "total_steps": 38160, "loss": 0.0027, "lr": 1.2886952680452036e-09, "epoch": 19.942348008385743, "percentage": 99.71, "elapsed_time": "2:26:02", "remaining_time": "0:00:25", "throughput": 2838.65, "total_tokens": 24874056} {"current_steps": 38055, "total_steps": 38160, "loss": 0.0097, "lr": 1.1752123193459197e-09, "epoch": 19.94496855345912, "percentage": 99.72, "elapsed_time": "2:26:03", "remaining_time": "0:00:24", "throughput": 2838.65, "total_tokens": 24877096} {"current_steps": 38060, "total_steps": 38160, "loss": 0.0038, "lr": 1.0669588395934017e-09, "epoch": 19.947589098532493, "percentage": 99.74, "elapsed_time": "2:26:04", "remaining_time": "0:00:23", "throughput": 2838.65, "total_tokens": 24880104} {"current_steps": 38065, "total_steps": 38160, "loss": 0.0108, "lr": 9.639348514278722e-10, "epoch": 19.95020964360587, "percentage": 99.75, "elapsed_time": "2:26:05", "remaining_time": "0:00:21", "throughput": 2838.64, "total_tokens": 24883112} {"current_steps": 38070, "total_steps": 38160, "loss": 0.0074, "lr": 8.661403764043119e-10, "epoch": 19.952830188679247, "percentage": 99.76, "elapsed_time": "2:26:06", "remaining_time": "0:00:20", "throughput": 2838.7, "total_tokens": 24886824} {"current_steps": 38075, "total_steps": 38160, "loss": 0.0029, "lr": 7.735754349785795e-10, "epoch": 19.95545073375262, "percentage": 99.78, "elapsed_time": "2:26:08", "remaining_time": "0:00:19", "throughput": 2838.62, "total_tokens": 24889096} {"current_steps": 38080, "total_steps": 38160, "loss": 0.0131, "lr": 6.862400465157403e-10, "epoch": 19.958071278825997, "percentage": 99.79, "elapsed_time": "2:26:09", "remaining_time": "0:00:18", "throughput": 2838.73, "total_tokens": 24893640} {"current_steps": 38085, "total_steps": 38160, "loss": 0.0065, "lr": 6.041342292817387e-10, "epoch": 19.96069182389937, "percentage": 99.8, "elapsed_time": "2:26:10", "remaining_time": "0:00:17", "throughput": 2838.68, "total_tokens": 24896264} {"current_steps": 38090, "total_steps": 38160, "loss": 0.0057, "lr": 5.272580004572758e-10, "epoch": 19.963312368972748, "percentage": 99.82, "elapsed_time": "2:26:11", "remaining_time": "0:00:16", "throughput": 2838.66, "total_tokens": 24899080} {"current_steps": 38095, "total_steps": 38160, "loss": 0.0059, "lr": 4.556113761211567e-10, "epoch": 19.96593291404612, "percentage": 99.83, "elapsed_time": "2:26:12", "remaining_time": "0:00:14", "throughput": 2838.66, "total_tokens": 24902024} {"current_steps": 38100, "total_steps": 38160, "loss": 0.0034, "lr": 3.8919437125861657e-10, "epoch": 19.968553459119498, "percentage": 99.84, "elapsed_time": "2:26:13", "remaining_time": "0:00:13", "throughput": 2838.75, "total_tokens": 24906088} {"current_steps": 38105, "total_steps": 38160, "loss": 0.0062, "lr": 3.280069997696478e-10, "epoch": 19.97117400419287, "percentage": 99.86, "elapsed_time": "2:26:14", "remaining_time": "0:00:12", "throughput": 2838.73, "total_tokens": 24908968} {"current_steps": 38110, "total_steps": 38160, "loss": 0.022, "lr": 2.720492744467951e-10, "epoch": 19.97379454926625, "percentage": 99.87, "elapsed_time": "2:26:15", "remaining_time": "0:00:11", "throughput": 2838.74, "total_tokens": 24912104} {"current_steps": 38115, "total_steps": 38160, "loss": 0.0049, "lr": 2.2132120700291136e-10, "epoch": 19.97641509433962, "percentage": 99.88, "elapsed_time": "2:26:16", "remaining_time": "0:00:10", "throughput": 2838.79, "total_tokens": 24915464} {"current_steps": 38120, "total_steps": 38160, "loss": 0.0032, "lr": 1.7582280804340213e-10, "epoch": 19.979035639413, "percentage": 99.9, "elapsed_time": "2:26:17", "remaining_time": "0:00:09", "throughput": 2838.79, "total_tokens": 24918632} {"current_steps": 38125, "total_steps": 38160, "loss": 0.0043, "lr": 1.3555408708842977e-10, "epoch": 19.981656184486372, "percentage": 99.91, "elapsed_time": "2:26:19", "remaining_time": "0:00:08", "throughput": 2838.7, "total_tokens": 24921032} {"current_steps": 38130, "total_steps": 38160, "loss": 0.0017, "lr": 1.0051505256458704e-10, "epoch": 19.98427672955975, "percentage": 99.92, "elapsed_time": "2:26:20", "remaining_time": "0:00:06", "throughput": 2838.69, "total_tokens": 24923912} {"current_steps": 38135, "total_steps": 38160, "loss": 0.0067, "lr": 7.070571179657037e-11, "epoch": 19.986897274633122, "percentage": 99.93, "elapsed_time": "2:26:21", "remaining_time": "0:00:05", "throughput": 2838.69, "total_tokens": 24926952} {"current_steps": 38140, "total_steps": 38160, "loss": 0.0068, "lr": 4.612607102383315e-11, "epoch": 19.9895178197065, "percentage": 99.95, "elapsed_time": "2:26:22", "remaining_time": "0:00:04", "throughput": 2838.76, "total_tokens": 24930984} {"current_steps": 38145, "total_steps": 38160, "loss": 0.0053, "lr": 2.677613538670798e-11, "epoch": 19.992138364779873, "percentage": 99.96, "elapsed_time": "2:26:23", "remaining_time": "0:00:03", "throughput": 2838.73, "total_tokens": 24933832} {"current_steps": 38150, "total_steps": 38160, "loss": 0.003, "lr": 1.2655908931957782e-11, "epoch": 19.99475890985325, "percentage": 99.97, "elapsed_time": "2:26:24", "remaining_time": "0:00:02", "throughput": 2838.68, "total_tokens": 24936584} {"current_steps": 38155, "total_steps": 38160, "loss": 0.0028, "lr": 3.765394615551366e-12, "epoch": 19.997379454926623, "percentage": 99.99, "elapsed_time": "2:26:25", "remaining_time": "0:00:01", "throughput": 2838.66, "total_tokens": 24939432} {"current_steps": 38160, "total_steps": 38160, "loss": 0.0408, "lr": 1.0459429711229262e-13, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "2:26:26", "remaining_time": "0:00:00", "throughput": 2838.57, "total_tokens": 24941912} {"current_steps": 38160, "total_steps": 38160, "eval_loss": 1.629987120628357, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "2:26:38", "remaining_time": "0:00:00", "throughput": 2834.78, "total_tokens": 24941912} {"current_steps": 38160, "total_steps": 38160, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "2:26:41", "remaining_time": "0:00:00", "throughput": 2833.69, "total_tokens": 24941912}