| { | |
| "best_metric": 0.007734560873359442, | |
| "best_model_checkpoint": "autotrain-5zkp2-pa5ot/checkpoint-2871", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 2871, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02612330198537095, | |
| "grad_norm": 3.338355302810669, | |
| "learning_rate": 4.340277777777778e-06, | |
| "loss": 1.1122, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0522466039707419, | |
| "grad_norm": 1.7776278257369995, | |
| "learning_rate": 8.680555555555556e-06, | |
| "loss": 1.0796, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07836990595611286, | |
| "grad_norm": 3.9048593044281006, | |
| "learning_rate": 1.3020833333333334e-05, | |
| "loss": 1.0438, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1044932079414838, | |
| "grad_norm": 4.985559940338135, | |
| "learning_rate": 1.736111111111111e-05, | |
| "loss": 0.944, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.13061650992685475, | |
| "grad_norm": 6.691493988037109, | |
| "learning_rate": 2.170138888888889e-05, | |
| "loss": 0.8765, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.15673981191222572, | |
| "grad_norm": 15.063920974731445, | |
| "learning_rate": 2.604166666666667e-05, | |
| "loss": 0.5913, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.18286311389759666, | |
| "grad_norm": 55.3206901550293, | |
| "learning_rate": 3.0381944444444444e-05, | |
| "loss": 0.3799, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.2089864158829676, | |
| "grad_norm": 8.026313781738281, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.3776, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.23510971786833856, | |
| "grad_norm": 3.5273993015289307, | |
| "learning_rate": 3.90625e-05, | |
| "loss": 0.2117, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.2612330198537095, | |
| "grad_norm": 0.12634535133838654, | |
| "learning_rate": 4.340277777777778e-05, | |
| "loss": 0.2089, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.28735632183908044, | |
| "grad_norm": 0.2070770412683487, | |
| "learning_rate": 4.774305555555556e-05, | |
| "loss": 0.1633, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.31347962382445144, | |
| "grad_norm": 62.55227279663086, | |
| "learning_rate": 4.9767711962833916e-05, | |
| "loss": 0.1345, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3396029258098224, | |
| "grad_norm": 0.017617134377360344, | |
| "learning_rate": 4.928377855207124e-05, | |
| "loss": 0.0022, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.3657262277951933, | |
| "grad_norm": 0.02495918981730938, | |
| "learning_rate": 4.879984514130856e-05, | |
| "loss": 0.0762, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.39184952978056425, | |
| "grad_norm": 23.060834884643555, | |
| "learning_rate": 4.831591173054588e-05, | |
| "loss": 0.0773, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.4179728317659352, | |
| "grad_norm": 0.018387485295534134, | |
| "learning_rate": 4.78319783197832e-05, | |
| "loss": 0.0877, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4440961337513062, | |
| "grad_norm": 0.08322528004646301, | |
| "learning_rate": 4.734804490902052e-05, | |
| "loss": 0.1489, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.4702194357366771, | |
| "grad_norm": 0.018301822245121002, | |
| "learning_rate": 4.686411149825784e-05, | |
| "loss": 0.1955, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.49634273772204807, | |
| "grad_norm": 159.80633544921875, | |
| "learning_rate": 4.638017808749516e-05, | |
| "loss": 0.1085, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.522466039707419, | |
| "grad_norm": 0.010405668057501316, | |
| "learning_rate": 4.5896244676732484e-05, | |
| "loss": 0.0424, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.54858934169279, | |
| "grad_norm": 0.016250956803560257, | |
| "learning_rate": 4.5412311265969805e-05, | |
| "loss": 0.0995, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.5747126436781609, | |
| "grad_norm": 6.8752760887146, | |
| "learning_rate": 4.4928377855207126e-05, | |
| "loss": 0.1536, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.6008359456635318, | |
| "grad_norm": 0.012155416421592236, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.0141, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.6269592476489029, | |
| "grad_norm": 0.008480357006192207, | |
| "learning_rate": 4.396051103368177e-05, | |
| "loss": 0.002, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6530825496342738, | |
| "grad_norm": 0.010472940281033516, | |
| "learning_rate": 4.347657762291909e-05, | |
| "loss": 0.0437, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.6792058516196448, | |
| "grad_norm": 0.021664993837475777, | |
| "learning_rate": 4.299264421215641e-05, | |
| "loss": 0.0272, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.7053291536050157, | |
| "grad_norm": 0.006474316120147705, | |
| "learning_rate": 4.250871080139373e-05, | |
| "loss": 0.0324, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.7314524555903866, | |
| "grad_norm": 0.0071400972083210945, | |
| "learning_rate": 4.202477739063105e-05, | |
| "loss": 0.0674, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.7575757575757576, | |
| "grad_norm": 0.05537139251828194, | |
| "learning_rate": 4.154084397986837e-05, | |
| "loss": 0.1479, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.7836990595611285, | |
| "grad_norm": 0.03653930872678757, | |
| "learning_rate": 4.105691056910569e-05, | |
| "loss": 0.0746, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.8098223615464994, | |
| "grad_norm": 0.030840527266263962, | |
| "learning_rate": 4.0572977158343014e-05, | |
| "loss": 0.0381, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.8359456635318704, | |
| "grad_norm": 0.02931591309607029, | |
| "learning_rate": 4.0089043747580335e-05, | |
| "loss": 0.0491, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.8620689655172413, | |
| "grad_norm": 0.01176014170050621, | |
| "learning_rate": 3.9605110336817656e-05, | |
| "loss": 0.0348, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.8881922675026124, | |
| "grad_norm": 0.03229213505983353, | |
| "learning_rate": 3.912117692605498e-05, | |
| "loss": 0.0834, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.9143155694879833, | |
| "grad_norm": 0.015275160782039165, | |
| "learning_rate": 3.86372435152923e-05, | |
| "loss": 0.05, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.9404388714733543, | |
| "grad_norm": 0.013074109330773354, | |
| "learning_rate": 3.815331010452962e-05, | |
| "loss": 0.0012, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.9665621734587252, | |
| "grad_norm": 0.007205578964203596, | |
| "learning_rate": 3.766937669376694e-05, | |
| "loss": 0.0006, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.9926854754440961, | |
| "grad_norm": 0.023728761821985245, | |
| "learning_rate": 3.718544328300426e-05, | |
| "loss": 0.0409, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9973863042341872, | |
| "eval_f1_macro": 0.9973126862743199, | |
| "eval_f1_micro": 0.9973863042341872, | |
| "eval_f1_weighted": 0.9973863333834622, | |
| "eval_loss": 0.020341886207461357, | |
| "eval_precision_macro": 0.9963851515122331, | |
| "eval_precision_micro": 0.9973863042341872, | |
| "eval_precision_weighted": 0.9974001038510532, | |
| "eval_recall_macro": 0.9982547993019196, | |
| "eval_recall_micro": 0.9973863042341872, | |
| "eval_recall_weighted": 0.9973863042341872, | |
| "eval_runtime": 209.7986, | |
| "eval_samples_per_second": 9.118, | |
| "eval_steps_per_second": 0.572, | |
| "step": 957 | |
| }, | |
| { | |
| "epoch": 1.0188087774294672, | |
| "grad_norm": 0.01665070652961731, | |
| "learning_rate": 3.670150987224158e-05, | |
| "loss": 0.0121, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 1.044932079414838, | |
| "grad_norm": 0.00787193700671196, | |
| "learning_rate": 3.62175764614789e-05, | |
| "loss": 0.0374, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.071055381400209, | |
| "grad_norm": 0.004602901637554169, | |
| "learning_rate": 3.5733643050716224e-05, | |
| "loss": 0.0029, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 1.09717868338558, | |
| "grad_norm": 0.0053739468567073345, | |
| "learning_rate": 3.5249709639953545e-05, | |
| "loss": 0.0004, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.123301985370951, | |
| "grad_norm": 0.0077377124689519405, | |
| "learning_rate": 3.4765776229190865e-05, | |
| "loss": 0.0003, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 1.1494252873563218, | |
| "grad_norm": 0.005279259290546179, | |
| "learning_rate": 3.4281842818428186e-05, | |
| "loss": 0.0798, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.1755485893416928, | |
| "grad_norm": 0.005335587542504072, | |
| "learning_rate": 3.379790940766551e-05, | |
| "loss": 0.0008, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 1.2016718913270636, | |
| "grad_norm": 0.013302076607942581, | |
| "learning_rate": 3.331397599690283e-05, | |
| "loss": 0.0007, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.2277951933124347, | |
| "grad_norm": 0.060083452612161636, | |
| "learning_rate": 3.283004258614015e-05, | |
| "loss": 0.1174, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 1.2539184952978055, | |
| "grad_norm": 0.005654782988131046, | |
| "learning_rate": 3.234610917537747e-05, | |
| "loss": 0.0008, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.2800417972831766, | |
| "grad_norm": 0.004458857234567404, | |
| "learning_rate": 3.186217576461479e-05, | |
| "loss": 0.0004, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 1.3061650992685476, | |
| "grad_norm": 0.005284965503960848, | |
| "learning_rate": 3.137824235385211e-05, | |
| "loss": 0.0396, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.3322884012539185, | |
| "grad_norm": 0.008645354770123959, | |
| "learning_rate": 3.089430894308943e-05, | |
| "loss": 0.0007, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 1.3584117032392895, | |
| "grad_norm": 0.0050517115741968155, | |
| "learning_rate": 3.041037553232675e-05, | |
| "loss": 0.0126, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.3845350052246603, | |
| "grad_norm": 0.013066472485661507, | |
| "learning_rate": 2.9926442121564075e-05, | |
| "loss": 0.0831, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 1.4106583072100314, | |
| "grad_norm": 0.017604809254407883, | |
| "learning_rate": 2.9442508710801396e-05, | |
| "loss": 0.0012, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.4367816091954024, | |
| "grad_norm": 0.006513866595923901, | |
| "learning_rate": 2.8958575300038713e-05, | |
| "loss": 0.0416, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 1.4629049111807733, | |
| "grad_norm": 0.012942259199917316, | |
| "learning_rate": 2.8474641889276038e-05, | |
| "loss": 0.0007, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.489028213166144, | |
| "grad_norm": 344.988037109375, | |
| "learning_rate": 2.7990708478513355e-05, | |
| "loss": 0.0425, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 1.5151515151515151, | |
| "grad_norm": 0.03896530717611313, | |
| "learning_rate": 2.750677506775068e-05, | |
| "loss": 0.064, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.5412748171368862, | |
| "grad_norm": 0.009162936359643936, | |
| "learning_rate": 2.7022841656988e-05, | |
| "loss": 0.001, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 1.567398119122257, | |
| "grad_norm": 0.010370401665568352, | |
| "learning_rate": 2.6538908246225318e-05, | |
| "loss": 0.0365, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.5935214211076278, | |
| "grad_norm": 0.009396117180585861, | |
| "learning_rate": 2.6054974835462642e-05, | |
| "loss": 0.0466, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 1.619644723092999, | |
| "grad_norm": 0.016944007948040962, | |
| "learning_rate": 2.5571041424699967e-05, | |
| "loss": 0.0008, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.64576802507837, | |
| "grad_norm": 0.008113248273730278, | |
| "learning_rate": 2.5087108013937284e-05, | |
| "loss": 0.034, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 1.671891327063741, | |
| "grad_norm": 0.008707555942237377, | |
| "learning_rate": 2.4603174603174602e-05, | |
| "loss": 0.0007, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.6980146290491118, | |
| "grad_norm": 0.06956545263528824, | |
| "learning_rate": 2.4119241192411926e-05, | |
| "loss": 0.0005, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 1.7241379310344827, | |
| "grad_norm": 0.010159909725189209, | |
| "learning_rate": 2.3635307781649247e-05, | |
| "loss": 0.0822, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.7502612330198537, | |
| "grad_norm": 0.007952134124934673, | |
| "learning_rate": 2.3151374370886568e-05, | |
| "loss": 0.0768, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 1.7763845350052248, | |
| "grad_norm": 0.022700520232319832, | |
| "learning_rate": 2.2667440960123886e-05, | |
| "loss": 0.0325, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.8025078369905956, | |
| "grad_norm": 0.04925369843840599, | |
| "learning_rate": 2.218350754936121e-05, | |
| "loss": 0.0832, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 1.8286311389759664, | |
| "grad_norm": 0.010277110151946545, | |
| "learning_rate": 2.169957413859853e-05, | |
| "loss": 0.0007, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.8547544409613375, | |
| "grad_norm": 0.009189656004309654, | |
| "learning_rate": 2.1215640727835852e-05, | |
| "loss": 0.0004, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 1.8808777429467085, | |
| "grad_norm": 0.00968814454972744, | |
| "learning_rate": 2.073170731707317e-05, | |
| "loss": 0.0429, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.9070010449320796, | |
| "grad_norm": 0.009455765597522259, | |
| "learning_rate": 2.0247773906310494e-05, | |
| "loss": 0.0874, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 1.9331243469174504, | |
| "grad_norm": 0.00541004678234458, | |
| "learning_rate": 1.9763840495547815e-05, | |
| "loss": 0.0019, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.9592476489028212, | |
| "grad_norm": 0.027987977489829063, | |
| "learning_rate": 1.9279907084785136e-05, | |
| "loss": 0.0375, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 1.9853709508881923, | |
| "grad_norm": 0.012382814660668373, | |
| "learning_rate": 1.8795973674022453e-05, | |
| "loss": 0.0006, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9952953476215368, | |
| "eval_f1_macro": 0.9958184083774263, | |
| "eval_f1_micro": 0.9952953476215368, | |
| "eval_f1_weighted": 0.995297723057706, | |
| "eval_loss": 0.03401019424200058, | |
| "eval_precision_macro": 0.9948206725776819, | |
| "eval_precision_micro": 0.9952953476215368, | |
| "eval_precision_weighted": 0.9953490671179285, | |
| "eval_recall_macro": 0.9968586387434555, | |
| "eval_recall_micro": 0.9952953476215368, | |
| "eval_recall_weighted": 0.9952953476215368, | |
| "eval_runtime": 204.9069, | |
| "eval_samples_per_second": 9.336, | |
| "eval_steps_per_second": 0.586, | |
| "step": 1914 | |
| }, | |
| { | |
| "epoch": 2.0114942528735633, | |
| "grad_norm": 0.01057450845837593, | |
| "learning_rate": 1.8312040263259778e-05, | |
| "loss": 0.0421, | |
| "step": 1925 | |
| }, | |
| { | |
| "epoch": 2.0376175548589344, | |
| "grad_norm": 0.005483025684952736, | |
| "learning_rate": 1.78281068524971e-05, | |
| "loss": 0.0004, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 2.063740856844305, | |
| "grad_norm": 0.0031655074562877417, | |
| "learning_rate": 1.734417344173442e-05, | |
| "loss": 0.0065, | |
| "step": 1975 | |
| }, | |
| { | |
| "epoch": 2.089864158829676, | |
| "grad_norm": 0.0039079682901501656, | |
| "learning_rate": 1.6860240030971737e-05, | |
| "loss": 0.0003, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.115987460815047, | |
| "grad_norm": 6.877926826477051, | |
| "learning_rate": 1.6376306620209058e-05, | |
| "loss": 0.0447, | |
| "step": 2025 | |
| }, | |
| { | |
| "epoch": 2.142110762800418, | |
| "grad_norm": 0.006742693949490786, | |
| "learning_rate": 1.5892373209446382e-05, | |
| "loss": 0.0387, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 2.1682340647857887, | |
| "grad_norm": 0.005568367429077625, | |
| "learning_rate": 1.5408439798683703e-05, | |
| "loss": 0.0004, | |
| "step": 2075 | |
| }, | |
| { | |
| "epoch": 2.19435736677116, | |
| "grad_norm": 0.010062599554657936, | |
| "learning_rate": 1.4924506387921023e-05, | |
| "loss": 0.0003, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.220480668756531, | |
| "grad_norm": 0.0033714643213897943, | |
| "learning_rate": 1.4440572977158342e-05, | |
| "loss": 0.0002, | |
| "step": 2125 | |
| }, | |
| { | |
| "epoch": 2.246603970741902, | |
| "grad_norm": 0.0053630974143743515, | |
| "learning_rate": 1.3956639566395666e-05, | |
| "loss": 0.0002, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2.2727272727272725, | |
| "grad_norm": 0.012313129380345345, | |
| "learning_rate": 1.3472706155632985e-05, | |
| "loss": 0.0803, | |
| "step": 2175 | |
| }, | |
| { | |
| "epoch": 2.2988505747126435, | |
| "grad_norm": 0.010815066285431385, | |
| "learning_rate": 1.2988772744870306e-05, | |
| "loss": 0.0014, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.3249738766980146, | |
| "grad_norm": 0.002910745795816183, | |
| "learning_rate": 1.2504839334107627e-05, | |
| "loss": 0.0014, | |
| "step": 2225 | |
| }, | |
| { | |
| "epoch": 2.3510971786833856, | |
| "grad_norm": 0.003235210431739688, | |
| "learning_rate": 1.2020905923344948e-05, | |
| "loss": 0.0004, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.3772204806687567, | |
| "grad_norm": 0.002846105257049203, | |
| "learning_rate": 1.1536972512582269e-05, | |
| "loss": 0.0002, | |
| "step": 2275 | |
| }, | |
| { | |
| "epoch": 2.4033437826541273, | |
| "grad_norm": 0.0029369164258241653, | |
| "learning_rate": 1.105303910181959e-05, | |
| "loss": 0.0326, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.4294670846394983, | |
| "grad_norm": 0.002867381554096937, | |
| "learning_rate": 1.0569105691056911e-05, | |
| "loss": 0.0547, | |
| "step": 2325 | |
| }, | |
| { | |
| "epoch": 2.4555903866248694, | |
| "grad_norm": 0.0030547629576176405, | |
| "learning_rate": 1.0085172280294232e-05, | |
| "loss": 0.0002, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 2.4817136886102404, | |
| "grad_norm": 0.003066838486120105, | |
| "learning_rate": 9.601238869531553e-06, | |
| "loss": 0.0002, | |
| "step": 2375 | |
| }, | |
| { | |
| "epoch": 2.507836990595611, | |
| "grad_norm": 0.003202056046575308, | |
| "learning_rate": 9.117305458768874e-06, | |
| "loss": 0.0002, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.533960292580982, | |
| "grad_norm": 0.002831035992130637, | |
| "learning_rate": 8.633372048006195e-06, | |
| "loss": 0.0002, | |
| "step": 2425 | |
| }, | |
| { | |
| "epoch": 2.560083594566353, | |
| "grad_norm": 0.0025005133356899023, | |
| "learning_rate": 8.149438637243516e-06, | |
| "loss": 0.0002, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 2.586206896551724, | |
| "grad_norm": 0.0023419370409101248, | |
| "learning_rate": 7.665505226480837e-06, | |
| "loss": 0.0002, | |
| "step": 2475 | |
| }, | |
| { | |
| "epoch": 2.6123301985370952, | |
| "grad_norm": 0.004286649636924267, | |
| "learning_rate": 7.181571815718158e-06, | |
| "loss": 0.022, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.6384535005224663, | |
| "grad_norm": 0.0027705898974090815, | |
| "learning_rate": 6.697638404955478e-06, | |
| "loss": 0.0002, | |
| "step": 2525 | |
| }, | |
| { | |
| "epoch": 2.664576802507837, | |
| "grad_norm": 0.002411492168903351, | |
| "learning_rate": 6.2137049941927995e-06, | |
| "loss": 0.0301, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 2.690700104493208, | |
| "grad_norm": 0.003571214620023966, | |
| "learning_rate": 5.7297715834301205e-06, | |
| "loss": 0.0002, | |
| "step": 2575 | |
| }, | |
| { | |
| "epoch": 2.716823406478579, | |
| "grad_norm": 0.002616529120132327, | |
| "learning_rate": 5.245838172667441e-06, | |
| "loss": 0.0002, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.7429467084639496, | |
| "grad_norm": 0.002348940121009946, | |
| "learning_rate": 4.7619047619047615e-06, | |
| "loss": 0.0454, | |
| "step": 2625 | |
| }, | |
| { | |
| "epoch": 2.7690700104493207, | |
| "grad_norm": 0.0026359122712165117, | |
| "learning_rate": 4.2779713511420825e-06, | |
| "loss": 0.0195, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 2.7951933124346917, | |
| "grad_norm": 0.002935645403340459, | |
| "learning_rate": 3.794037940379404e-06, | |
| "loss": 0.0508, | |
| "step": 2675 | |
| }, | |
| { | |
| "epoch": 2.8213166144200628, | |
| "grad_norm": 0.009833462536334991, | |
| "learning_rate": 3.3101045296167248e-06, | |
| "loss": 0.0002, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.847439916405434, | |
| "grad_norm": 6.756618976593018, | |
| "learning_rate": 2.8261711188540457e-06, | |
| "loss": 0.1122, | |
| "step": 2725 | |
| }, | |
| { | |
| "epoch": 2.873563218390805, | |
| "grad_norm": 0.005804854445159435, | |
| "learning_rate": 2.3422377080913667e-06, | |
| "loss": 0.0002, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 2.8996865203761755, | |
| "grad_norm": 0.005187211558222771, | |
| "learning_rate": 1.8583042973286876e-06, | |
| "loss": 0.0003, | |
| "step": 2775 | |
| }, | |
| { | |
| "epoch": 2.9258098223615465, | |
| "grad_norm": 0.0601598359644413, | |
| "learning_rate": 1.3743708865660086e-06, | |
| "loss": 0.0002, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.9519331243469176, | |
| "grad_norm": 0.0032336723525077105, | |
| "learning_rate": 8.904374758033296e-07, | |
| "loss": 0.0318, | |
| "step": 2825 | |
| }, | |
| { | |
| "epoch": 2.978056426332288, | |
| "grad_norm": 0.003166941227391362, | |
| "learning_rate": 4.0650406504065046e-07, | |
| "loss": 0.0004, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9989545216936748, | |
| "eval_f1_macro": 0.9991256596070146, | |
| "eval_f1_micro": 0.9989545216936748, | |
| "eval_f1_weighted": 0.9989547969603347, | |
| "eval_loss": 0.007734560873359442, | |
| "eval_precision_macro": 0.9989517819706499, | |
| "eval_precision_micro": 0.9989545216936748, | |
| "eval_precision_weighted": 0.9989578093613047, | |
| "eval_recall_macro": 0.9993019197207679, | |
| "eval_recall_micro": 0.9989545216936748, | |
| "eval_recall_weighted": 0.9989545216936748, | |
| "eval_runtime": 176.5223, | |
| "eval_samples_per_second": 10.837, | |
| "eval_steps_per_second": 0.68, | |
| "step": 2871 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 2871, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 0.01 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1509810569277696.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |