| { | |
| "best_metric": 0.15773314237594604, | |
| "best_model_checkpoint": "frostsolutions/frost-vision-v2-google_vit-base-patch16-224-v2024-11-14/checkpoint-1000", | |
| "epoch": 30.0, | |
| "eval_steps": 100, | |
| "global_step": 2430, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.12345679012345678, | |
| "grad_norm": 2.0258209705352783, | |
| "learning_rate": 2.05761316872428e-06, | |
| "loss": 0.7157, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24691358024691357, | |
| "grad_norm": 1.8047471046447754, | |
| "learning_rate": 4.11522633744856e-06, | |
| "loss": 0.6777, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.37037037037037035, | |
| "grad_norm": 1.81009840965271, | |
| "learning_rate": 6.172839506172839e-06, | |
| "loss": 0.6489, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.49382716049382713, | |
| "grad_norm": 1.4138026237487793, | |
| "learning_rate": 8.23045267489712e-06, | |
| "loss": 0.5874, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6172839506172839, | |
| "grad_norm": 1.4049081802368164, | |
| "learning_rate": 1.02880658436214e-05, | |
| "loss": 0.5259, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7407407407407407, | |
| "grad_norm": 1.0964142084121704, | |
| "learning_rate": 1.2345679012345678e-05, | |
| "loss": 0.4743, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.8641975308641975, | |
| "grad_norm": 0.8998202681541443, | |
| "learning_rate": 1.440329218106996e-05, | |
| "loss": 0.4258, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.9876543209876543, | |
| "grad_norm": 1.0498803853988647, | |
| "learning_rate": 1.646090534979424e-05, | |
| "loss": 0.4061, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 0.8372374773025513, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.3647, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.2345679012345678, | |
| "grad_norm": 0.9855860471725464, | |
| "learning_rate": 2.05761316872428e-05, | |
| "loss": 0.3381, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.2345679012345678, | |
| "eval_accuracy": 0.8660493827160494, | |
| "eval_f1": 0.5668662674650699, | |
| "eval_loss": 0.3270835876464844, | |
| "eval_precision": 0.8045325779036827, | |
| "eval_recall": 0.43759630200308164, | |
| "eval_runtime": 2.3341, | |
| "eval_samples_per_second": 138.812, | |
| "eval_steps_per_second": 17.566, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.3580246913580247, | |
| "grad_norm": 0.8622191548347473, | |
| "learning_rate": 2.2633744855967078e-05, | |
| "loss": 0.3148, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.4814814814814814, | |
| "grad_norm": 0.9625290036201477, | |
| "learning_rate": 2.4691358024691357e-05, | |
| "loss": 0.3021, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.6049382716049383, | |
| "grad_norm": 0.9755824208259583, | |
| "learning_rate": 2.6748971193415638e-05, | |
| "loss": 0.2781, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.7283950617283952, | |
| "grad_norm": 0.7279321551322937, | |
| "learning_rate": 2.880658436213992e-05, | |
| "loss": 0.245, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.8518518518518519, | |
| "grad_norm": 0.8370109796524048, | |
| "learning_rate": 3.08641975308642e-05, | |
| "loss": 0.2747, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.9753086419753085, | |
| "grad_norm": 0.9776009917259216, | |
| "learning_rate": 3.292181069958848e-05, | |
| "loss": 0.2741, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.0987654320987654, | |
| "grad_norm": 0.7717245221138, | |
| "learning_rate": 3.497942386831276e-05, | |
| "loss": 0.2285, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 0.9406857490539551, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.2179, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.3456790123456788, | |
| "grad_norm": 0.9723733067512512, | |
| "learning_rate": 3.909465020576132e-05, | |
| "loss": 0.2213, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.4691358024691357, | |
| "grad_norm": 1.2755147218704224, | |
| "learning_rate": 4.11522633744856e-05, | |
| "loss": 0.2067, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.4691358024691357, | |
| "eval_accuracy": 0.9194444444444444, | |
| "eval_f1": 0.7826810990840966, | |
| "eval_loss": 0.20802636444568634, | |
| "eval_precision": 0.8514492753623188, | |
| "eval_recall": 0.724191063174114, | |
| "eval_runtime": 2.6756, | |
| "eval_samples_per_second": 121.096, | |
| "eval_steps_per_second": 15.324, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.5925925925925926, | |
| "grad_norm": 0.6742503643035889, | |
| "learning_rate": 4.3209876543209875e-05, | |
| "loss": 0.1916, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.7160493827160495, | |
| "grad_norm": 0.9410703182220459, | |
| "learning_rate": 4.5267489711934157e-05, | |
| "loss": 0.1932, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.8395061728395063, | |
| "grad_norm": 1.5295264720916748, | |
| "learning_rate": 4.732510288065844e-05, | |
| "loss": 0.1991, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.962962962962963, | |
| "grad_norm": 1.7802011966705322, | |
| "learning_rate": 4.938271604938271e-05, | |
| "loss": 0.2272, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.0864197530864197, | |
| "grad_norm": 1.6310603618621826, | |
| "learning_rate": 4.983996342021033e-05, | |
| "loss": 0.1905, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.2098765432098766, | |
| "grad_norm": 0.588090181350708, | |
| "learning_rate": 4.9611339734796525e-05, | |
| "loss": 0.1577, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 0.7364725470542908, | |
| "learning_rate": 4.938271604938271e-05, | |
| "loss": 0.1972, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.45679012345679, | |
| "grad_norm": 0.9553163647651672, | |
| "learning_rate": 4.9154092363968915e-05, | |
| "loss": 0.1468, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 3.580246913580247, | |
| "grad_norm": 0.9130911827087402, | |
| "learning_rate": 4.89254686785551e-05, | |
| "loss": 0.1894, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 3.7037037037037037, | |
| "grad_norm": 0.895966649055481, | |
| "learning_rate": 4.86968449931413e-05, | |
| "loss": 0.1745, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.7037037037037037, | |
| "eval_accuracy": 0.9228395061728395, | |
| "eval_f1": 0.8003194888178914, | |
| "eval_loss": 0.18639631569385529, | |
| "eval_precision": 0.8308457711442786, | |
| "eval_recall": 0.7719568567026194, | |
| "eval_runtime": 3.3226, | |
| "eval_samples_per_second": 97.513, | |
| "eval_steps_per_second": 12.34, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.8271604938271606, | |
| "grad_norm": 0.9509402513504028, | |
| "learning_rate": 4.8468221307727485e-05, | |
| "loss": 0.1948, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.950617283950617, | |
| "grad_norm": 0.959931492805481, | |
| "learning_rate": 4.823959762231367e-05, | |
| "loss": 0.1824, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.074074074074074, | |
| "grad_norm": 0.6884809732437134, | |
| "learning_rate": 4.801097393689987e-05, | |
| "loss": 0.156, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.197530864197531, | |
| "grad_norm": 0.9225603342056274, | |
| "learning_rate": 4.7782350251486056e-05, | |
| "loss": 0.1333, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.320987654320987, | |
| "grad_norm": 1.0396263599395752, | |
| "learning_rate": 4.755372656607225e-05, | |
| "loss": 0.1715, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": 0.6264840364456177, | |
| "learning_rate": 4.732510288065844e-05, | |
| "loss": 0.1491, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.567901234567901, | |
| "grad_norm": 0.756226658821106, | |
| "learning_rate": 4.709647919524463e-05, | |
| "loss": 0.1563, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 4.6913580246913575, | |
| "grad_norm": 0.9274685382843018, | |
| "learning_rate": 4.686785550983082e-05, | |
| "loss": 0.1746, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 4.814814814814815, | |
| "grad_norm": 0.8389601111412048, | |
| "learning_rate": 4.6639231824417016e-05, | |
| "loss": 0.14, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "grad_norm": 0.7658799290657043, | |
| "learning_rate": 4.6410608139003203e-05, | |
| "loss": 0.1724, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.938271604938271, | |
| "eval_accuracy": 0.9299382716049382, | |
| "eval_f1": 0.8188347964884277, | |
| "eval_loss": 0.17921936511993408, | |
| "eval_precision": 0.8493377483443708, | |
| "eval_recall": 0.7904468412942989, | |
| "eval_runtime": 2.4889, | |
| "eval_samples_per_second": 130.176, | |
| "eval_steps_per_second": 16.473, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.061728395061729, | |
| "grad_norm": 0.47751790285110474, | |
| "learning_rate": 4.618198445358939e-05, | |
| "loss": 0.1397, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.185185185185185, | |
| "grad_norm": 0.8206377625465393, | |
| "learning_rate": 4.5953360768175586e-05, | |
| "loss": 0.1332, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 5.308641975308642, | |
| "grad_norm": 1.053655743598938, | |
| "learning_rate": 4.5724737082761774e-05, | |
| "loss": 0.1524, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 5.432098765432099, | |
| "grad_norm": 0.8656085729598999, | |
| "learning_rate": 4.549611339734797e-05, | |
| "loss": 0.1215, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 5.555555555555555, | |
| "grad_norm": 0.7634124755859375, | |
| "learning_rate": 4.5267489711934157e-05, | |
| "loss": 0.1291, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.679012345679013, | |
| "grad_norm": 0.6214159727096558, | |
| "learning_rate": 4.503886602652035e-05, | |
| "loss": 0.1314, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 5.802469135802469, | |
| "grad_norm": 1.1487807035446167, | |
| "learning_rate": 4.481024234110654e-05, | |
| "loss": 0.1372, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 5.925925925925926, | |
| "grad_norm": 0.7788066864013672, | |
| "learning_rate": 4.4581618655692734e-05, | |
| "loss": 0.1399, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.049382716049383, | |
| "grad_norm": 0.6658753156661987, | |
| "learning_rate": 4.435299497027892e-05, | |
| "loss": 0.1463, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 6.172839506172839, | |
| "grad_norm": 1.125616192817688, | |
| "learning_rate": 4.412437128486511e-05, | |
| "loss": 0.128, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.172839506172839, | |
| "eval_accuracy": 0.932716049382716, | |
| "eval_f1": 0.829153605015674, | |
| "eval_loss": 0.17359426617622375, | |
| "eval_precision": 0.8437001594896332, | |
| "eval_recall": 0.8151001540832049, | |
| "eval_runtime": 2.3597, | |
| "eval_samples_per_second": 137.303, | |
| "eval_steps_per_second": 17.375, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.296296296296296, | |
| "grad_norm": 0.8468999862670898, | |
| "learning_rate": 4.3895747599451304e-05, | |
| "loss": 0.1085, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 6.419753086419753, | |
| "grad_norm": 0.8319602012634277, | |
| "learning_rate": 4.366712391403749e-05, | |
| "loss": 0.1436, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 6.54320987654321, | |
| "grad_norm": 1.0661511421203613, | |
| "learning_rate": 4.343850022862369e-05, | |
| "loss": 0.1258, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 1.0158193111419678, | |
| "learning_rate": 4.3209876543209875e-05, | |
| "loss": 0.1173, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 6.790123456790123, | |
| "grad_norm": 0.996032178401947, | |
| "learning_rate": 4.298125285779607e-05, | |
| "loss": 0.123, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 6.91358024691358, | |
| "grad_norm": 0.8598793148994446, | |
| "learning_rate": 4.2752629172382264e-05, | |
| "loss": 0.0955, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 7.037037037037037, | |
| "grad_norm": 0.7240075469017029, | |
| "learning_rate": 4.252400548696845e-05, | |
| "loss": 0.1133, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 7.160493827160494, | |
| "grad_norm": 1.5954258441925049, | |
| "learning_rate": 4.229538180155465e-05, | |
| "loss": 0.1092, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 7.283950617283951, | |
| "grad_norm": 0.41076725721359253, | |
| "learning_rate": 4.2066758116140835e-05, | |
| "loss": 0.1059, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 7.407407407407407, | |
| "grad_norm": 1.1242218017578125, | |
| "learning_rate": 4.183813443072703e-05, | |
| "loss": 0.1034, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.407407407407407, | |
| "eval_accuracy": 0.9354938271604938, | |
| "eval_f1": 0.8347826086956521, | |
| "eval_loss": 0.16716818511486053, | |
| "eval_precision": 0.8571428571428571, | |
| "eval_recall": 0.8135593220338984, | |
| "eval_runtime": 2.3423, | |
| "eval_samples_per_second": 138.328, | |
| "eval_steps_per_second": 17.504, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 7.530864197530864, | |
| "grad_norm": 0.97056645154953, | |
| "learning_rate": 4.160951074531322e-05, | |
| "loss": 0.1239, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 7.654320987654321, | |
| "grad_norm": 0.8477165102958679, | |
| "learning_rate": 4.138088705989941e-05, | |
| "loss": 0.1164, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 7.777777777777778, | |
| "grad_norm": 0.7572548389434814, | |
| "learning_rate": 4.11522633744856e-05, | |
| "loss": 0.1156, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 7.901234567901234, | |
| "grad_norm": 1.5163884162902832, | |
| "learning_rate": 4.092363968907179e-05, | |
| "loss": 0.1195, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 8.024691358024691, | |
| "grad_norm": 0.7944018840789795, | |
| "learning_rate": 4.069501600365798e-05, | |
| "loss": 0.1086, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 8.148148148148149, | |
| "grad_norm": 1.1152986288070679, | |
| "learning_rate": 4.046639231824417e-05, | |
| "loss": 0.1101, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 8.271604938271604, | |
| "grad_norm": 0.7614450454711914, | |
| "learning_rate": 4.0237768632830365e-05, | |
| "loss": 0.1004, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 8.395061728395062, | |
| "grad_norm": 0.6931539177894592, | |
| "learning_rate": 4.000914494741655e-05, | |
| "loss": 0.1047, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 8.518518518518519, | |
| "grad_norm": 0.6190685629844666, | |
| "learning_rate": 3.978052126200275e-05, | |
| "loss": 0.0811, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 8.641975308641975, | |
| "grad_norm": 0.814577579498291, | |
| "learning_rate": 3.9551897576588936e-05, | |
| "loss": 0.0944, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 8.641975308641975, | |
| "eval_accuracy": 0.9391975308641975, | |
| "eval_f1": 0.845247446975648, | |
| "eval_loss": 0.15788604319095612, | |
| "eval_precision": 0.8621794871794872, | |
| "eval_recall": 0.8289676425269645, | |
| "eval_runtime": 2.3023, | |
| "eval_samples_per_second": 140.727, | |
| "eval_steps_per_second": 17.808, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 8.765432098765432, | |
| "grad_norm": 0.6677612066268921, | |
| "learning_rate": 3.932327389117513e-05, | |
| "loss": 0.0907, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 8.88888888888889, | |
| "grad_norm": 1.435887098312378, | |
| "learning_rate": 3.909465020576132e-05, | |
| "loss": 0.0941, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 9.012345679012345, | |
| "grad_norm": 0.8256314992904663, | |
| "learning_rate": 3.8866026520347506e-05, | |
| "loss": 0.1155, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 9.135802469135802, | |
| "grad_norm": 0.7372011542320251, | |
| "learning_rate": 3.86374028349337e-05, | |
| "loss": 0.0868, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 9.25925925925926, | |
| "grad_norm": 0.6247950196266174, | |
| "learning_rate": 3.840877914951989e-05, | |
| "loss": 0.0791, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 9.382716049382717, | |
| "grad_norm": 0.7330453395843506, | |
| "learning_rate": 3.8180155464106083e-05, | |
| "loss": 0.0766, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 9.506172839506172, | |
| "grad_norm": 0.946180522441864, | |
| "learning_rate": 3.795153177869227e-05, | |
| "loss": 0.092, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 9.62962962962963, | |
| "grad_norm": 0.6986804008483887, | |
| "learning_rate": 3.7722908093278466e-05, | |
| "loss": 0.0695, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 9.753086419753087, | |
| "grad_norm": 0.4678453505039215, | |
| "learning_rate": 3.7494284407864654e-05, | |
| "loss": 0.0896, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 9.876543209876543, | |
| "grad_norm": 0.8175441026687622, | |
| "learning_rate": 3.726566072245085e-05, | |
| "loss": 0.0919, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 9.876543209876543, | |
| "eval_accuracy": 0.9364197530864198, | |
| "eval_f1": 0.8346709470304976, | |
| "eval_loss": 0.16307669878005981, | |
| "eval_precision": 0.8710217755443886, | |
| "eval_recall": 0.8012326656394453, | |
| "eval_runtime": 2.5754, | |
| "eval_samples_per_second": 125.805, | |
| "eval_steps_per_second": 15.92, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.7374185919761658, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.1001, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 10.123456790123457, | |
| "grad_norm": 0.5478447079658508, | |
| "learning_rate": 3.6808413351623224e-05, | |
| "loss": 0.0939, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 10.246913580246913, | |
| "grad_norm": 0.8081673979759216, | |
| "learning_rate": 3.657978966620942e-05, | |
| "loss": 0.0704, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 10.37037037037037, | |
| "grad_norm": 0.7327490448951721, | |
| "learning_rate": 3.635116598079561e-05, | |
| "loss": 0.0742, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 10.493827160493828, | |
| "grad_norm": 0.6625596284866333, | |
| "learning_rate": 3.612254229538181e-05, | |
| "loss": 0.0784, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 10.617283950617283, | |
| "grad_norm": 1.724616289138794, | |
| "learning_rate": 3.5893918609967996e-05, | |
| "loss": 0.0848, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 10.74074074074074, | |
| "grad_norm": 0.6218889951705933, | |
| "learning_rate": 3.566529492455419e-05, | |
| "loss": 0.0752, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 10.864197530864198, | |
| "grad_norm": 1.1755985021591187, | |
| "learning_rate": 3.543667123914038e-05, | |
| "loss": 0.0751, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 10.987654320987655, | |
| "grad_norm": 1.2024366855621338, | |
| "learning_rate": 3.520804755372657e-05, | |
| "loss": 0.0827, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 11.11111111111111, | |
| "grad_norm": 1.065391182899475, | |
| "learning_rate": 3.497942386831276e-05, | |
| "loss": 0.0791, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 11.11111111111111, | |
| "eval_accuracy": 0.937962962962963, | |
| "eval_f1": 0.8382944489139179, | |
| "eval_loss": 0.15917660295963287, | |
| "eval_precision": 0.877104377104377, | |
| "eval_recall": 0.802773497688752, | |
| "eval_runtime": 2.965, | |
| "eval_samples_per_second": 109.275, | |
| "eval_steps_per_second": 13.828, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 11.234567901234568, | |
| "grad_norm": 0.6627580523490906, | |
| "learning_rate": 3.475080018289895e-05, | |
| "loss": 0.0758, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 11.358024691358025, | |
| "grad_norm": 0.5924692749977112, | |
| "learning_rate": 3.4522176497485144e-05, | |
| "loss": 0.0672, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 11.481481481481481, | |
| "grad_norm": 0.5990743637084961, | |
| "learning_rate": 3.429355281207133e-05, | |
| "loss": 0.0822, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 11.604938271604938, | |
| "grad_norm": 0.9133488535881042, | |
| "learning_rate": 3.406492912665753e-05, | |
| "loss": 0.0883, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 11.728395061728396, | |
| "grad_norm": 1.091486930847168, | |
| "learning_rate": 3.3836305441243715e-05, | |
| "loss": 0.0639, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 11.851851851851851, | |
| "grad_norm": 0.3895137310028076, | |
| "learning_rate": 3.360768175582991e-05, | |
| "loss": 0.0687, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 11.975308641975309, | |
| "grad_norm": 0.5844981074333191, | |
| "learning_rate": 3.33790580704161e-05, | |
| "loss": 0.0576, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 12.098765432098766, | |
| "grad_norm": 0.3059285879135132, | |
| "learning_rate": 3.3150434385002285e-05, | |
| "loss": 0.0689, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 12.222222222222221, | |
| "grad_norm": 0.6075615286827087, | |
| "learning_rate": 3.292181069958848e-05, | |
| "loss": 0.0525, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 12.345679012345679, | |
| "grad_norm": 0.8529097437858582, | |
| "learning_rate": 3.269318701417467e-05, | |
| "loss": 0.0684, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 12.345679012345679, | |
| "eval_accuracy": 0.9388888888888889, | |
| "eval_f1": 0.8436018957345972, | |
| "eval_loss": 0.15773314237594604, | |
| "eval_precision": 0.8654781199351702, | |
| "eval_recall": 0.8228043143297381, | |
| "eval_runtime": 3.556, | |
| "eval_samples_per_second": 91.114, | |
| "eval_steps_per_second": 11.53, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 12.469135802469136, | |
| "grad_norm": 0.2871643602848053, | |
| "learning_rate": 3.246456332876086e-05, | |
| "loss": 0.0721, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 12.592592592592592, | |
| "grad_norm": 1.031972050666809, | |
| "learning_rate": 3.223593964334705e-05, | |
| "loss": 0.0762, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 12.716049382716049, | |
| "grad_norm": 0.8951663374900818, | |
| "learning_rate": 3.2007315957933245e-05, | |
| "loss": 0.078, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 12.839506172839506, | |
| "grad_norm": 0.38367488980293274, | |
| "learning_rate": 3.177869227251943e-05, | |
| "loss": 0.0629, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 12.962962962962964, | |
| "grad_norm": 1.0400196313858032, | |
| "learning_rate": 3.155006858710563e-05, | |
| "loss": 0.0755, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 13.08641975308642, | |
| "grad_norm": 0.9411855340003967, | |
| "learning_rate": 3.1321444901691816e-05, | |
| "loss": 0.0624, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 13.209876543209877, | |
| "grad_norm": 0.9051506519317627, | |
| "learning_rate": 3.1092821216278004e-05, | |
| "loss": 0.0573, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "grad_norm": 1.214126706123352, | |
| "learning_rate": 3.08641975308642e-05, | |
| "loss": 0.0658, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 13.45679012345679, | |
| "grad_norm": 0.8709390163421631, | |
| "learning_rate": 3.0635573845450386e-05, | |
| "loss": 0.0626, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 13.580246913580247, | |
| "grad_norm": 1.0249199867248535, | |
| "learning_rate": 3.0406950160036577e-05, | |
| "loss": 0.0737, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 13.580246913580247, | |
| "eval_accuracy": 0.937962962962963, | |
| "eval_f1": 0.8416075650118203, | |
| "eval_loss": 0.16777929663658142, | |
| "eval_precision": 0.8612903225806452, | |
| "eval_recall": 0.8228043143297381, | |
| "eval_runtime": 2.5879, | |
| "eval_samples_per_second": 125.2, | |
| "eval_steps_per_second": 15.843, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 13.703703703703704, | |
| "grad_norm": 0.6229693293571472, | |
| "learning_rate": 3.017832647462277e-05, | |
| "loss": 0.0611, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 13.82716049382716, | |
| "grad_norm": 0.29374879598617554, | |
| "learning_rate": 2.994970278920896e-05, | |
| "loss": 0.0616, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 13.950617283950617, | |
| "grad_norm": 0.5640215277671814, | |
| "learning_rate": 2.972107910379515e-05, | |
| "loss": 0.0703, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 14.074074074074074, | |
| "grad_norm": 0.44930121302604675, | |
| "learning_rate": 2.949245541838135e-05, | |
| "loss": 0.0523, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 14.197530864197532, | |
| "grad_norm": 0.3680154085159302, | |
| "learning_rate": 2.926383173296754e-05, | |
| "loss": 0.0608, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 14.320987654320987, | |
| "grad_norm": 0.5697309374809265, | |
| "learning_rate": 2.903520804755373e-05, | |
| "loss": 0.0581, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 14.444444444444445, | |
| "grad_norm": 0.6320594549179077, | |
| "learning_rate": 2.880658436213992e-05, | |
| "loss": 0.0557, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 14.567901234567902, | |
| "grad_norm": 0.8799903988838196, | |
| "learning_rate": 2.857796067672611e-05, | |
| "loss": 0.0556, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 14.691358024691358, | |
| "grad_norm": 0.7066503167152405, | |
| "learning_rate": 2.8349336991312303e-05, | |
| "loss": 0.0574, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 14.814814814814815, | |
| "grad_norm": 1.6003211736679077, | |
| "learning_rate": 2.8120713305898494e-05, | |
| "loss": 0.0625, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 14.814814814814815, | |
| "eval_accuracy": 0.9425925925925925, | |
| "eval_f1": 0.85423197492163, | |
| "eval_loss": 0.16456876695156097, | |
| "eval_precision": 0.8692185007974481, | |
| "eval_recall": 0.8397534668721109, | |
| "eval_runtime": 3.5694, | |
| "eval_samples_per_second": 90.771, | |
| "eval_steps_per_second": 11.486, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 14.938271604938272, | |
| "grad_norm": 0.6639634966850281, | |
| "learning_rate": 2.7892089620484685e-05, | |
| "loss": 0.0612, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 15.061728395061728, | |
| "grad_norm": 1.4719339609146118, | |
| "learning_rate": 2.7663465935070876e-05, | |
| "loss": 0.0537, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 15.185185185185185, | |
| "grad_norm": 0.6944316625595093, | |
| "learning_rate": 2.7434842249657068e-05, | |
| "loss": 0.0669, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 15.308641975308642, | |
| "grad_norm": 0.43684977293014526, | |
| "learning_rate": 2.720621856424326e-05, | |
| "loss": 0.0475, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 15.432098765432098, | |
| "grad_norm": 0.3456471264362335, | |
| "learning_rate": 2.6977594878829447e-05, | |
| "loss": 0.0391, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 15.555555555555555, | |
| "grad_norm": 0.9245675206184387, | |
| "learning_rate": 2.6748971193415638e-05, | |
| "loss": 0.0564, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 15.679012345679013, | |
| "grad_norm": 1.1026465892791748, | |
| "learning_rate": 2.652034750800183e-05, | |
| "loss": 0.0628, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 15.802469135802468, | |
| "grad_norm": 0.5103587508201599, | |
| "learning_rate": 2.629172382258802e-05, | |
| "loss": 0.0554, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 15.925925925925926, | |
| "grad_norm": 0.6337056159973145, | |
| "learning_rate": 2.6063100137174212e-05, | |
| "loss": 0.0569, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 16.049382716049383, | |
| "grad_norm": 1.0704419612884521, | |
| "learning_rate": 2.5834476451760403e-05, | |
| "loss": 0.0591, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 16.049382716049383, | |
| "eval_accuracy": 0.9432098765432099, | |
| "eval_f1": 0.8548895899053628, | |
| "eval_loss": 0.16249051690101624, | |
| "eval_precision": 0.875605815831987, | |
| "eval_recall": 0.8351309707241911, | |
| "eval_runtime": 2.3147, | |
| "eval_samples_per_second": 139.976, | |
| "eval_steps_per_second": 17.713, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 16.17283950617284, | |
| "grad_norm": 1.0367881059646606, | |
| "learning_rate": 2.5605852766346595e-05, | |
| "loss": 0.0414, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 16.296296296296298, | |
| "grad_norm": 0.8111926317214966, | |
| "learning_rate": 2.5377229080932786e-05, | |
| "loss": 0.0649, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 16.419753086419753, | |
| "grad_norm": 0.42399314045906067, | |
| "learning_rate": 2.5148605395518977e-05, | |
| "loss": 0.0534, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 16.54320987654321, | |
| "grad_norm": 0.4055217206478119, | |
| "learning_rate": 2.4919981710105165e-05, | |
| "loss": 0.0451, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 16.666666666666668, | |
| "grad_norm": 0.33903083205223083, | |
| "learning_rate": 2.4691358024691357e-05, | |
| "loss": 0.0599, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 16.790123456790123, | |
| "grad_norm": 0.4832461476325989, | |
| "learning_rate": 2.446273433927755e-05, | |
| "loss": 0.0388, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 16.91358024691358, | |
| "grad_norm": 1.0101662874221802, | |
| "learning_rate": 2.4234110653863743e-05, | |
| "loss": 0.0523, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 17.037037037037038, | |
| "grad_norm": 0.7684808969497681, | |
| "learning_rate": 2.4005486968449934e-05, | |
| "loss": 0.0569, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 17.160493827160494, | |
| "grad_norm": 0.5816587209701538, | |
| "learning_rate": 2.3776863283036125e-05, | |
| "loss": 0.0471, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 17.28395061728395, | |
| "grad_norm": 0.5327761769294739, | |
| "learning_rate": 2.3548239597622316e-05, | |
| "loss": 0.0464, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 17.28395061728395, | |
| "eval_accuracy": 0.9385802469135802, | |
| "eval_f1": 0.8421887390959556, | |
| "eval_loss": 0.1721687614917755, | |
| "eval_precision": 0.8676470588235294, | |
| "eval_recall": 0.8181818181818182, | |
| "eval_runtime": 2.3252, | |
| "eval_samples_per_second": 139.345, | |
| "eval_steps_per_second": 17.633, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 17.40740740740741, | |
| "grad_norm": 1.4246679544448853, | |
| "learning_rate": 2.3319615912208508e-05, | |
| "loss": 0.0593, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 17.530864197530864, | |
| "grad_norm": 0.6948336958885193, | |
| "learning_rate": 2.3090992226794696e-05, | |
| "loss": 0.0368, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 17.65432098765432, | |
| "grad_norm": 0.7839669585227966, | |
| "learning_rate": 2.2862368541380887e-05, | |
| "loss": 0.0662, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 17.77777777777778, | |
| "grad_norm": 0.6608372330665588, | |
| "learning_rate": 2.2633744855967078e-05, | |
| "loss": 0.0457, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 17.901234567901234, | |
| "grad_norm": 1.2672737836837769, | |
| "learning_rate": 2.240512117055327e-05, | |
| "loss": 0.0517, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 18.02469135802469, | |
| "grad_norm": 0.8855928778648376, | |
| "learning_rate": 2.217649748513946e-05, | |
| "loss": 0.0524, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 18.14814814814815, | |
| "grad_norm": 0.7090869545936584, | |
| "learning_rate": 2.1947873799725652e-05, | |
| "loss": 0.0449, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 18.271604938271604, | |
| "grad_norm": 0.5972793698310852, | |
| "learning_rate": 2.1719250114311843e-05, | |
| "loss": 0.0358, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 18.395061728395063, | |
| "grad_norm": 0.2597953677177429, | |
| "learning_rate": 2.1490626428898035e-05, | |
| "loss": 0.0599, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 18.51851851851852, | |
| "grad_norm": 0.5771777629852295, | |
| "learning_rate": 2.1262002743484226e-05, | |
| "loss": 0.048, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 18.51851851851852, | |
| "eval_accuracy": 0.9401234567901234, | |
| "eval_f1": 0.8472440944881889, | |
| "eval_loss": 0.16935202479362488, | |
| "eval_precision": 0.8663446054750402, | |
| "eval_recall": 0.8289676425269645, | |
| "eval_runtime": 2.5549, | |
| "eval_samples_per_second": 126.816, | |
| "eval_steps_per_second": 16.048, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 18.641975308641975, | |
| "grad_norm": 1.0612865686416626, | |
| "learning_rate": 2.1033379058070417e-05, | |
| "loss": 0.0458, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 18.765432098765434, | |
| "grad_norm": 1.0192160606384277, | |
| "learning_rate": 2.080475537265661e-05, | |
| "loss": 0.045, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 18.88888888888889, | |
| "grad_norm": 0.8331177830696106, | |
| "learning_rate": 2.05761316872428e-05, | |
| "loss": 0.0458, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 19.012345679012345, | |
| "grad_norm": 0.5867314338684082, | |
| "learning_rate": 2.034750800182899e-05, | |
| "loss": 0.0462, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 19.135802469135804, | |
| "grad_norm": 0.2448338121175766, | |
| "learning_rate": 2.0118884316415183e-05, | |
| "loss": 0.0404, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 19.25925925925926, | |
| "grad_norm": 0.7374415397644043, | |
| "learning_rate": 1.9890260631001374e-05, | |
| "loss": 0.0442, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 19.382716049382715, | |
| "grad_norm": 0.6374390125274658, | |
| "learning_rate": 1.9661636945587565e-05, | |
| "loss": 0.0435, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 19.506172839506174, | |
| "grad_norm": 0.6881589889526367, | |
| "learning_rate": 1.9433013260173753e-05, | |
| "loss": 0.0498, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 19.62962962962963, | |
| "grad_norm": 0.26705750823020935, | |
| "learning_rate": 1.9204389574759944e-05, | |
| "loss": 0.0415, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 19.753086419753085, | |
| "grad_norm": 0.7690613269805908, | |
| "learning_rate": 1.8975765889346136e-05, | |
| "loss": 0.0353, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 19.753086419753085, | |
| "eval_accuracy": 0.9391975308641975, | |
| "eval_f1": 0.8462138953942233, | |
| "eval_loss": 0.17146864533424377, | |
| "eval_precision": 0.8575949367088608, | |
| "eval_recall": 0.8351309707241911, | |
| "eval_runtime": 2.9802, | |
| "eval_samples_per_second": 108.717, | |
| "eval_steps_per_second": 13.757, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 19.876543209876544, | |
| "grad_norm": 0.630096971988678, | |
| "learning_rate": 1.8747142203932327e-05, | |
| "loss": 0.0385, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 0.6776329874992371, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.0465, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 20.123456790123456, | |
| "grad_norm": 0.8204653859138489, | |
| "learning_rate": 1.828989483310471e-05, | |
| "loss": 0.037, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 20.246913580246915, | |
| "grad_norm": 0.11897799372673035, | |
| "learning_rate": 1.8061271147690904e-05, | |
| "loss": 0.0308, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 20.37037037037037, | |
| "grad_norm": 0.6061619520187378, | |
| "learning_rate": 1.7832647462277096e-05, | |
| "loss": 0.0456, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 20.493827160493826, | |
| "grad_norm": 0.24529418349266052, | |
| "learning_rate": 1.7604023776863283e-05, | |
| "loss": 0.0374, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 20.617283950617285, | |
| "grad_norm": 0.9412081241607666, | |
| "learning_rate": 1.7375400091449475e-05, | |
| "loss": 0.0455, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 20.74074074074074, | |
| "grad_norm": 0.39813077449798584, | |
| "learning_rate": 1.7146776406035666e-05, | |
| "loss": 0.0395, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 20.864197530864196, | |
| "grad_norm": 0.36594846844673157, | |
| "learning_rate": 1.6918152720621857e-05, | |
| "loss": 0.0376, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 20.987654320987655, | |
| "grad_norm": 0.7182625532150269, | |
| "learning_rate": 1.668952903520805e-05, | |
| "loss": 0.0434, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 20.987654320987655, | |
| "eval_accuracy": 0.937037037037037, | |
| "eval_f1": 0.8386075949367089, | |
| "eval_loss": 0.18171226978302002, | |
| "eval_precision": 0.8617886178861789, | |
| "eval_recall": 0.8166409861325116, | |
| "eval_runtime": 2.6381, | |
| "eval_samples_per_second": 122.816, | |
| "eval_steps_per_second": 15.541, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 21.11111111111111, | |
| "grad_norm": 0.6655898094177246, | |
| "learning_rate": 1.646090534979424e-05, | |
| "loss": 0.0327, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 21.234567901234566, | |
| "grad_norm": 0.5218392610549927, | |
| "learning_rate": 1.623228166438043e-05, | |
| "loss": 0.0452, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 21.358024691358025, | |
| "grad_norm": 0.6255172491073608, | |
| "learning_rate": 1.6003657978966623e-05, | |
| "loss": 0.033, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 21.48148148148148, | |
| "grad_norm": 0.6865390539169312, | |
| "learning_rate": 1.5775034293552814e-05, | |
| "loss": 0.046, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 21.604938271604937, | |
| "grad_norm": 0.577601432800293, | |
| "learning_rate": 1.5546410608139002e-05, | |
| "loss": 0.0367, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 21.728395061728396, | |
| "grad_norm": 0.5450471639633179, | |
| "learning_rate": 1.5317786922725193e-05, | |
| "loss": 0.038, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 21.85185185185185, | |
| "grad_norm": 0.8480527997016907, | |
| "learning_rate": 1.5089163237311384e-05, | |
| "loss": 0.0399, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 21.97530864197531, | |
| "grad_norm": 0.3345847427845001, | |
| "learning_rate": 1.4860539551897576e-05, | |
| "loss": 0.0333, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 22.098765432098766, | |
| "grad_norm": 0.47660622000694275, | |
| "learning_rate": 1.463191586648377e-05, | |
| "loss": 0.0404, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 22.22222222222222, | |
| "grad_norm": 0.42594680190086365, | |
| "learning_rate": 1.440329218106996e-05, | |
| "loss": 0.0332, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 22.22222222222222, | |
| "eval_accuracy": 0.9382716049382716, | |
| "eval_f1": 0.8422712933753943, | |
| "eval_loss": 0.17968803644180298, | |
| "eval_precision": 0.8626817447495961, | |
| "eval_recall": 0.8228043143297381, | |
| "eval_runtime": 2.3118, | |
| "eval_samples_per_second": 140.152, | |
| "eval_steps_per_second": 17.735, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 22.34567901234568, | |
| "grad_norm": 0.23526711761951447, | |
| "learning_rate": 1.4174668495656151e-05, | |
| "loss": 0.0336, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 22.469135802469136, | |
| "grad_norm": 0.30145469307899475, | |
| "learning_rate": 1.3946044810242343e-05, | |
| "loss": 0.033, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 22.59259259259259, | |
| "grad_norm": 0.4943447709083557, | |
| "learning_rate": 1.3717421124828534e-05, | |
| "loss": 0.0336, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 22.71604938271605, | |
| "grad_norm": 0.5769455432891846, | |
| "learning_rate": 1.3488797439414723e-05, | |
| "loss": 0.0328, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 22.839506172839506, | |
| "grad_norm": 1.038840651512146, | |
| "learning_rate": 1.3260173754000915e-05, | |
| "loss": 0.0382, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 22.962962962962962, | |
| "grad_norm": 0.4028635323047638, | |
| "learning_rate": 1.3031550068587106e-05, | |
| "loss": 0.0315, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 23.08641975308642, | |
| "grad_norm": 0.10601099580526352, | |
| "learning_rate": 1.2802926383173297e-05, | |
| "loss": 0.0282, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 23.209876543209877, | |
| "grad_norm": 0.5546613931655884, | |
| "learning_rate": 1.2574302697759489e-05, | |
| "loss": 0.0506, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 23.333333333333332, | |
| "grad_norm": 0.3614629805088043, | |
| "learning_rate": 1.2345679012345678e-05, | |
| "loss": 0.0248, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 23.45679012345679, | |
| "grad_norm": 0.47462597489356995, | |
| "learning_rate": 1.2117055326931871e-05, | |
| "loss": 0.0283, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 23.45679012345679, | |
| "eval_accuracy": 0.9401234567901234, | |
| "eval_f1": 0.8482003129890454, | |
| "eval_loss": 0.18097253143787384, | |
| "eval_precision": 0.8616852146263911, | |
| "eval_recall": 0.8351309707241911, | |
| "eval_runtime": 3.0694, | |
| "eval_samples_per_second": 105.557, | |
| "eval_steps_per_second": 13.358, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 23.580246913580247, | |
| "grad_norm": 0.18128247559070587, | |
| "learning_rate": 1.1888431641518063e-05, | |
| "loss": 0.0338, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 23.703703703703702, | |
| "grad_norm": 0.23011884093284607, | |
| "learning_rate": 1.1659807956104254e-05, | |
| "loss": 0.0453, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 23.82716049382716, | |
| "grad_norm": 0.3289709985256195, | |
| "learning_rate": 1.1431184270690443e-05, | |
| "loss": 0.0279, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 23.950617283950617, | |
| "grad_norm": 0.13935135304927826, | |
| "learning_rate": 1.1202560585276635e-05, | |
| "loss": 0.0307, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 24.074074074074073, | |
| "grad_norm": 0.6951057314872742, | |
| "learning_rate": 1.0973936899862826e-05, | |
| "loss": 0.0382, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 24.19753086419753, | |
| "grad_norm": 1.6290189027786255, | |
| "learning_rate": 1.0745313214449017e-05, | |
| "loss": 0.0388, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 24.320987654320987, | |
| "grad_norm": 0.18432094156742096, | |
| "learning_rate": 1.0516689529035209e-05, | |
| "loss": 0.0303, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 24.444444444444443, | |
| "grad_norm": 0.47055086493492126, | |
| "learning_rate": 1.02880658436214e-05, | |
| "loss": 0.0308, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 24.567901234567902, | |
| "grad_norm": 0.41197624802589417, | |
| "learning_rate": 1.0059442158207591e-05, | |
| "loss": 0.0338, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 24.691358024691358, | |
| "grad_norm": 0.4777185916900635, | |
| "learning_rate": 9.830818472793783e-06, | |
| "loss": 0.0474, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 24.691358024691358, | |
| "eval_accuracy": 0.9398148148148148, | |
| "eval_f1": 0.845360824742268, | |
| "eval_loss": 0.17648009955883026, | |
| "eval_precision": 0.8709150326797386, | |
| "eval_recall": 0.8212634822804314, | |
| "eval_runtime": 2.9138, | |
| "eval_samples_per_second": 111.195, | |
| "eval_steps_per_second": 14.071, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 24.814814814814813, | |
| "grad_norm": 0.45768871903419495, | |
| "learning_rate": 9.602194787379972e-06, | |
| "loss": 0.0269, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 24.938271604938272, | |
| "grad_norm": 0.9567142128944397, | |
| "learning_rate": 9.373571101966163e-06, | |
| "loss": 0.0335, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 25.061728395061728, | |
| "grad_norm": 0.5306533575057983, | |
| "learning_rate": 9.144947416552355e-06, | |
| "loss": 0.0229, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 25.185185185185187, | |
| "grad_norm": 0.5475009083747864, | |
| "learning_rate": 8.916323731138548e-06, | |
| "loss": 0.0245, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 25.308641975308642, | |
| "grad_norm": 0.611080527305603, | |
| "learning_rate": 8.687700045724737e-06, | |
| "loss": 0.029, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 25.432098765432098, | |
| "grad_norm": 0.4131525158882141, | |
| "learning_rate": 8.459076360310929e-06, | |
| "loss": 0.034, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 25.555555555555557, | |
| "grad_norm": 1.0216596126556396, | |
| "learning_rate": 8.23045267489712e-06, | |
| "loss": 0.0345, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 25.679012345679013, | |
| "grad_norm": 0.6425824165344238, | |
| "learning_rate": 8.001828989483311e-06, | |
| "loss": 0.0416, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 25.80246913580247, | |
| "grad_norm": 0.9126815795898438, | |
| "learning_rate": 7.773205304069501e-06, | |
| "loss": 0.0402, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 25.925925925925927, | |
| "grad_norm": 0.35245445370674133, | |
| "learning_rate": 7.544581618655692e-06, | |
| "loss": 0.0365, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 25.925925925925927, | |
| "eval_accuracy": 0.941358024691358, | |
| "eval_f1": 0.8515625, | |
| "eval_loss": 0.18350541591644287, | |
| "eval_precision": 0.8637083993660856, | |
| "eval_recall": 0.8397534668721109, | |
| "eval_runtime": 3.2348, | |
| "eval_samples_per_second": 100.161, | |
| "eval_steps_per_second": 12.675, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 26.049382716049383, | |
| "grad_norm": 0.654412031173706, | |
| "learning_rate": 7.315957933241885e-06, | |
| "loss": 0.0312, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 26.17283950617284, | |
| "grad_norm": 1.0009406805038452, | |
| "learning_rate": 7.087334247828076e-06, | |
| "loss": 0.0336, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 26.296296296296298, | |
| "grad_norm": 0.28231924772262573, | |
| "learning_rate": 6.858710562414267e-06, | |
| "loss": 0.0408, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 26.419753086419753, | |
| "grad_norm": 0.6254132390022278, | |
| "learning_rate": 6.630086877000457e-06, | |
| "loss": 0.0298, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 26.54320987654321, | |
| "grad_norm": 1.2474095821380615, | |
| "learning_rate": 6.401463191586649e-06, | |
| "loss": 0.0382, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 26.666666666666668, | |
| "grad_norm": 0.5490561723709106, | |
| "learning_rate": 6.172839506172839e-06, | |
| "loss": 0.0283, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 26.790123456790123, | |
| "grad_norm": 0.9913358688354492, | |
| "learning_rate": 5.944215820759031e-06, | |
| "loss": 0.0339, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 26.91358024691358, | |
| "grad_norm": 0.9252423644065857, | |
| "learning_rate": 5.715592135345222e-06, | |
| "loss": 0.0286, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 27.037037037037038, | |
| "grad_norm": 0.5318057537078857, | |
| "learning_rate": 5.486968449931413e-06, | |
| "loss": 0.0316, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 27.160493827160494, | |
| "grad_norm": 0.3603754937648773, | |
| "learning_rate": 5.258344764517604e-06, | |
| "loss": 0.0244, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 27.160493827160494, | |
| "eval_accuracy": 0.9404320987654321, | |
| "eval_f1": 0.8479117415287628, | |
| "eval_loss": 0.18215233087539673, | |
| "eval_precision": 0.867741935483871, | |
| "eval_recall": 0.8289676425269645, | |
| "eval_runtime": 3.1643, | |
| "eval_samples_per_second": 102.391, | |
| "eval_steps_per_second": 12.957, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 27.28395061728395, | |
| "grad_norm": 0.6729068756103516, | |
| "learning_rate": 5.029721079103796e-06, | |
| "loss": 0.0396, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 27.40740740740741, | |
| "grad_norm": 0.8200917840003967, | |
| "learning_rate": 4.801097393689986e-06, | |
| "loss": 0.0297, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 27.530864197530864, | |
| "grad_norm": 0.9590497612953186, | |
| "learning_rate": 4.572473708276177e-06, | |
| "loss": 0.0371, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 27.65432098765432, | |
| "grad_norm": 0.23443204164505005, | |
| "learning_rate": 4.343850022862369e-06, | |
| "loss": 0.0305, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 27.77777777777778, | |
| "grad_norm": 0.18787816166877747, | |
| "learning_rate": 4.11522633744856e-06, | |
| "loss": 0.0298, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 27.901234567901234, | |
| "grad_norm": 0.32972452044487, | |
| "learning_rate": 3.8866026520347504e-06, | |
| "loss": 0.023, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 28.02469135802469, | |
| "grad_norm": 0.16079440712928772, | |
| "learning_rate": 3.6579789666209426e-06, | |
| "loss": 0.0225, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 28.14814814814815, | |
| "grad_norm": 1.2685606479644775, | |
| "learning_rate": 3.4293552812071335e-06, | |
| "loss": 0.0329, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 28.271604938271604, | |
| "grad_norm": 0.6398904323577881, | |
| "learning_rate": 3.2007315957933243e-06, | |
| "loss": 0.0307, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 28.395061728395063, | |
| "grad_norm": 0.6520938873291016, | |
| "learning_rate": 2.9721079103795156e-06, | |
| "loss": 0.0242, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 28.395061728395063, | |
| "eval_accuracy": 0.9407407407407408, | |
| "eval_f1": 0.8483412322274881, | |
| "eval_loss": 0.18079863488674164, | |
| "eval_precision": 0.8703403565640194, | |
| "eval_recall": 0.827426810477658, | |
| "eval_runtime": 2.3949, | |
| "eval_samples_per_second": 135.29, | |
| "eval_steps_per_second": 17.12, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 28.51851851851852, | |
| "grad_norm": 0.20304135978221893, | |
| "learning_rate": 2.7434842249657065e-06, | |
| "loss": 0.0225, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 28.641975308641975, | |
| "grad_norm": 0.9393714070320129, | |
| "learning_rate": 2.514860539551898e-06, | |
| "loss": 0.0294, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 28.765432098765434, | |
| "grad_norm": 0.3730199933052063, | |
| "learning_rate": 2.2862368541380887e-06, | |
| "loss": 0.0339, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 28.88888888888889, | |
| "grad_norm": 0.6354162096977234, | |
| "learning_rate": 2.05761316872428e-06, | |
| "loss": 0.028, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 29.012345679012345, | |
| "grad_norm": 0.3703112006187439, | |
| "learning_rate": 1.8289894833104713e-06, | |
| "loss": 0.0314, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 29.135802469135804, | |
| "grad_norm": 0.5848723649978638, | |
| "learning_rate": 1.6003657978966622e-06, | |
| "loss": 0.0361, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 29.25925925925926, | |
| "grad_norm": 0.5978838205337524, | |
| "learning_rate": 1.3717421124828533e-06, | |
| "loss": 0.0406, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 29.382716049382715, | |
| "grad_norm": 0.280225545167923, | |
| "learning_rate": 1.1431184270690443e-06, | |
| "loss": 0.0319, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 29.506172839506174, | |
| "grad_norm": 0.39151689410209656, | |
| "learning_rate": 9.144947416552356e-07, | |
| "loss": 0.0263, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 29.62962962962963, | |
| "grad_norm": 0.5079048871994019, | |
| "learning_rate": 6.858710562414266e-07, | |
| "loss": 0.0296, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 29.62962962962963, | |
| "eval_accuracy": 0.9401234567901234, | |
| "eval_f1": 0.847723704866562, | |
| "eval_loss": 0.18171092867851257, | |
| "eval_precision": 0.864, | |
| "eval_recall": 0.8320493066255779, | |
| "eval_runtime": 2.4278, | |
| "eval_samples_per_second": 133.453, | |
| "eval_steps_per_second": 16.888, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 29.753086419753085, | |
| "grad_norm": 0.5158771276473999, | |
| "learning_rate": 4.572473708276178e-07, | |
| "loss": 0.026, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 29.876543209876544, | |
| "grad_norm": 0.7846933603286743, | |
| "learning_rate": 2.286236854138089e-07, | |
| "loss": 0.0275, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 0.403104305267334, | |
| "learning_rate": 0.0, | |
| "loss": 0.0277, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "step": 2430, | |
| "total_flos": 3.008454731998249e+18, | |
| "train_loss": 0.09584075045070531, | |
| "train_runtime": 684.1699, | |
| "train_samples_per_second": 56.74, | |
| "train_steps_per_second": 3.552 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2430, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.008454731998249e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |