| { | |
| "best_metric": 0.8743740573152337, | |
| "best_model_checkpoint": "resnet-50-finetuned-barkley\\checkpoint-950", | |
| "epoch": 27.0, | |
| "eval_steps": 500, | |
| "global_step": 1026, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "train_accuracy": 0.16611842105263158 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.3611191511154175, | |
| "learning_rate": 1.3823166234831842e-06, | |
| "loss": 1.6171, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.17376068376068377, | |
| "eval_error_rate": 0.8262393162393162, | |
| "eval_f1": 0.06643250805361339, | |
| "eval_loss": 1.619532585144043, | |
| "eval_precision": 0.06626276231021362, | |
| "eval_recall": 0.1513157894736842, | |
| "eval_runtime": 26.7886, | |
| "eval_samples_per_second": 5.674, | |
| "eval_steps_per_second": 0.187, | |
| "eval_top1_accuracy": 0.1513157894736842, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "train_accuracy": 0.15862573099415206 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.6634056568145752, | |
| "learning_rate": 3.058622191852561e-06, | |
| "loss": 1.6149, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.17853192559074912, | |
| "eval_error_rate": 0.8214680744092508, | |
| "eval_f1": 0.08020327273951958, | |
| "eval_loss": 1.6160310506820679, | |
| "eval_precision": 0.29525518341307816, | |
| "eval_recall": 0.15789473684210525, | |
| "eval_runtime": 26.6794, | |
| "eval_samples_per_second": 5.697, | |
| "eval_steps_per_second": 0.187, | |
| "eval_top1_accuracy": 0.15789473684210525, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "train_accuracy": 0.1783625730994152 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 1.5223407745361328, | |
| "learning_rate": 5.625554080420859e-06, | |
| "loss": 1.6119, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.1771794871794872, | |
| "eval_error_rate": 0.8228205128205128, | |
| "eval_f1": 0.08341165413533834, | |
| "eval_loss": 1.6111546754837036, | |
| "eval_precision": 0.08044783010156971, | |
| "eval_recall": 0.15789473684210525, | |
| "eval_runtime": 26.2938, | |
| "eval_samples_per_second": 5.781, | |
| "eval_steps_per_second": 0.19, | |
| "eval_top1_accuracy": 0.15789473684210525, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "train_accuracy": 0.20833333333333334 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 1.3961833715438843, | |
| "learning_rate": 8.771702474591739e-06, | |
| "loss": 1.6041, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.21552538964303675, | |
| "eval_error_rate": 0.7844746103569633, | |
| "eval_f1": 0.14610577502522265, | |
| "eval_loss": 1.6015431880950928, | |
| "eval_precision": 0.4161313363641264, | |
| "eval_recall": 0.19736842105263158, | |
| "eval_runtime": 28.8611, | |
| "eval_samples_per_second": 5.267, | |
| "eval_steps_per_second": 0.173, | |
| "eval_top1_accuracy": 0.19736842105263158, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "train_accuracy": 0.24926900584795322 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 1.5497902631759644, | |
| "learning_rate": 1.2115389351475484e-05, | |
| "loss": 1.5945, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.30917043740573147, | |
| "eval_error_rate": 0.6908295625942685, | |
| "eval_f1": 0.24280704310495774, | |
| "eval_loss": 1.5894904136657715, | |
| "eval_precision": 0.40893317853457173, | |
| "eval_recall": 0.2894736842105263, | |
| "eval_runtime": 27.1975, | |
| "eval_samples_per_second": 5.589, | |
| "eval_steps_per_second": 0.184, | |
| "eval_top1_accuracy": 0.2894736842105263, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "train_accuracy": 0.33260233918128657 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 1.6292859315872192, | |
| "learning_rate": 1.5250972116877936e-05, | |
| "loss": 1.5777, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.4663499245852186, | |
| "eval_error_rate": 0.5336500754147814, | |
| "eval_f1": 0.39436167836929775, | |
| "eval_loss": 1.5709806680679321, | |
| "eval_precision": 0.5764411027568922, | |
| "eval_recall": 0.4407894736842105, | |
| "eval_runtime": 26.1121, | |
| "eval_samples_per_second": 5.821, | |
| "eval_steps_per_second": 0.191, | |
| "eval_top1_accuracy": 0.4407894736842105, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "train_accuracy": 0.4093567251461988 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 1.4761221408843994, | |
| "learning_rate": 1.7798054527340503e-05, | |
| "loss": 1.561, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.5173303167420814, | |
| "eval_error_rate": 0.4826696832579186, | |
| "eval_f1": 0.45158707610515547, | |
| "eval_loss": 1.5490015745162964, | |
| "eval_precision": 0.6013273211996122, | |
| "eval_recall": 0.4934210526315789, | |
| "eval_runtime": 27.8381, | |
| "eval_samples_per_second": 5.46, | |
| "eval_steps_per_second": 0.18, | |
| "eval_top1_accuracy": 0.5, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "train_accuracy": 0.47733918128654973 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 1.691532850265503, | |
| "learning_rate": 1.9447634826822778e-05, | |
| "loss": 1.536, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5450075414781297, | |
| "eval_error_rate": 0.4549924585218703, | |
| "eval_f1": 0.4711077818086626, | |
| "eval_loss": 1.5221654176712036, | |
| "eval_precision": 0.63772879167616, | |
| "eval_recall": 0.5131578947368421, | |
| "eval_runtime": 26.2831, | |
| "eval_samples_per_second": 5.783, | |
| "eval_steps_per_second": 0.19, | |
| "eval_top1_accuracy": 0.5131578947368421, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "train_accuracy": 0.5372807017543859 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 1.69563889503479, | |
| "learning_rate": 1.9999922507143676e-05, | |
| "loss": 1.5081, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.625032679738562, | |
| "eval_error_rate": 0.374967320261438, | |
| "eval_f1": 0.5868892868172693, | |
| "eval_loss": 1.4911595582962036, | |
| "eval_precision": 0.7594769272604533, | |
| "eval_recall": 0.5986842105263158, | |
| "eval_runtime": 27.44, | |
| "eval_samples_per_second": 5.539, | |
| "eval_steps_per_second": 0.182, | |
| "eval_top1_accuracy": 0.5986842105263158, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "train_accuracy": 0.5957602339181286 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 1.694950819015503, | |
| "learning_rate": 1.9882364575351117e-05, | |
| "loss": 1.4756, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.6683459024635495, | |
| "eval_error_rate": 0.3316540975364505, | |
| "eval_f1": 0.6293044227869377, | |
| "eval_loss": 1.4565558433532715, | |
| "eval_precision": 0.7578870575407971, | |
| "eval_recall": 0.6447368421052632, | |
| "eval_runtime": 25.8912, | |
| "eval_samples_per_second": 5.871, | |
| "eval_steps_per_second": 0.193, | |
| "eval_top1_accuracy": 0.6447368421052632, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "train_accuracy": 0.6111111111111112 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "grad_norm": 1.591986894607544, | |
| "learning_rate": 1.9544051842595e-05, | |
| "loss": 1.4387, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.698541980894922, | |
| "eval_error_rate": 0.30145801910507797, | |
| "eval_f1": 0.6692242337767512, | |
| "eval_loss": 1.4155722856521606, | |
| "eval_precision": 0.7913987173816895, | |
| "eval_recall": 0.6776315789473685, | |
| "eval_runtime": 26.7774, | |
| "eval_samples_per_second": 5.676, | |
| "eval_steps_per_second": 0.187, | |
| "eval_top1_accuracy": 0.6776315789473685, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "train_accuracy": 0.6469298245614035 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "grad_norm": 1.8263485431671143, | |
| "learning_rate": 1.9009692640269474e-05, | |
| "loss": 1.3993, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.7080442433383609, | |
| "eval_error_rate": 0.2919557566616391, | |
| "eval_f1": 0.6731791852575238, | |
| "eval_loss": 1.3737214803695679, | |
| "eval_precision": 0.7997336700204268, | |
| "eval_recall": 0.6842105263157895, | |
| "eval_runtime": 25.8778, | |
| "eval_samples_per_second": 5.874, | |
| "eval_steps_per_second": 0.193, | |
| "eval_top1_accuracy": 0.6842105263157895, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "train_accuracy": 0.6527777777777778 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "grad_norm": 1.8651676177978516, | |
| "learning_rate": 1.826239469360898e-05, | |
| "loss": 1.358, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.7232277526395173, | |
| "eval_error_rate": 0.27677224736048267, | |
| "eval_f1": 0.7048030719072474, | |
| "eval_loss": 1.3288253545761108, | |
| "eval_precision": 0.8290264820356354, | |
| "eval_recall": 0.7039473684210527, | |
| "eval_runtime": 26.9677, | |
| "eval_samples_per_second": 5.636, | |
| "eval_steps_per_second": 0.185, | |
| "eval_top1_accuracy": 0.7039473684210527, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "train_accuracy": 0.7017543859649122 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "grad_norm": 2.0590460300445557, | |
| "learning_rate": 1.733052939622339e-05, | |
| "loss": 1.3139, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.7592207139265963, | |
| "eval_error_rate": 0.2407792860734037, | |
| "eval_f1": 0.7373063276167947, | |
| "eval_loss": 1.2805979251861572, | |
| "eval_precision": 0.8276704808408175, | |
| "eval_recall": 0.743421052631579, | |
| "eval_runtime": 24.8464, | |
| "eval_samples_per_second": 6.118, | |
| "eval_steps_per_second": 0.201, | |
| "eval_top1_accuracy": 0.75, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "train_accuracy": 0.7185672514619883 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "grad_norm": 2.4823436737060547, | |
| "learning_rate": 1.6234913078995263e-05, | |
| "loss": 1.262, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.7828808446455506, | |
| "eval_error_rate": 0.21711915535444937, | |
| "eval_f1": 0.7664102924938837, | |
| "eval_loss": 1.2344970703125, | |
| "eval_precision": 0.8477553968860445, | |
| "eval_recall": 0.7697368421052632, | |
| "eval_runtime": 26.3117, | |
| "eval_samples_per_second": 5.777, | |
| "eval_steps_per_second": 0.19, | |
| "eval_top1_accuracy": 0.7697368421052632, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "train_accuracy": 0.7236842105263158 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 2.0972795486450195, | |
| "learning_rate": 1.5000020000000002e-05, | |
| "loss": 1.2184, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.7817697335344395, | |
| "eval_error_rate": 0.21823026646556054, | |
| "eval_f1": 0.7654284912445182, | |
| "eval_loss": 1.1887174844741821, | |
| "eval_precision": 0.8322669418644651, | |
| "eval_recall": 0.7697368421052632, | |
| "eval_runtime": 25.3816, | |
| "eval_samples_per_second": 5.989, | |
| "eval_steps_per_second": 0.197, | |
| "eval_top1_accuracy": 0.7697368421052632, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "train_accuracy": 0.7448830409356725 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "grad_norm": 1.9592589139938354, | |
| "learning_rate": 1.365343563002298e-05, | |
| "loss": 1.1803, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.7930819507290096, | |
| "eval_error_rate": 0.20691804927099045, | |
| "eval_f1": 0.773531629357028, | |
| "eval_loss": 1.1408498287200928, | |
| "eval_precision": 0.8423109913821989, | |
| "eval_recall": 0.7763157894736842, | |
| "eval_runtime": 26.1892, | |
| "eval_samples_per_second": 5.804, | |
| "eval_steps_per_second": 0.191, | |
| "eval_top1_accuracy": 0.7763157894736842, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "train_accuracy": 0.7580409356725146 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "grad_norm": 2.348762035369873, | |
| "learning_rate": 1.2225240438725788e-05, | |
| "loss": 1.1422, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.83166918049271, | |
| "eval_error_rate": 0.16833081950729, | |
| "eval_f1": 0.810022076785411, | |
| "eval_loss": 1.096580147743225, | |
| "eval_precision": 0.8594414607948442, | |
| "eval_recall": 0.8157894736842105, | |
| "eval_runtime": 25.0285, | |
| "eval_samples_per_second": 6.073, | |
| "eval_steps_per_second": 0.2, | |
| "eval_top1_accuracy": 0.8157894736842105, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "train_accuracy": 0.7733918128654971 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "grad_norm": 2.2395124435424805, | |
| "learning_rate": 1.0747337946660503e-05, | |
| "loss": 1.1032, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.8144746103569632, | |
| "eval_error_rate": 0.18552538964303678, | |
| "eval_f1": 0.7968691491574786, | |
| "eval_loss": 1.0586965084075928, | |
| "eval_precision": 0.8430972766845342, | |
| "eval_recall": 0.8026315789473685, | |
| "eval_runtime": 25.4802, | |
| "eval_samples_per_second": 5.965, | |
| "eval_steps_per_second": 0.196, | |
| "eval_top1_accuracy": 0.8026315789473685, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "train_accuracy": 0.7850877192982456 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 2.3096365928649902, | |
| "learning_rate": 9.252742053339503e-06, | |
| "loss": 1.058, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8486626445449975, | |
| "eval_error_rate": 0.1513373554550025, | |
| "eval_f1": 0.8300500291649842, | |
| "eval_loss": 1.0289386510849, | |
| "eval_precision": 0.8609899749373433, | |
| "eval_recall": 0.8355263157894737, | |
| "eval_runtime": 27.6424, | |
| "eval_samples_per_second": 5.499, | |
| "eval_steps_per_second": 0.181, | |
| "eval_top1_accuracy": 0.8355263157894737, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "train_accuracy": 0.8084795321637427 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "grad_norm": 2.616567611694336, | |
| "learning_rate": 7.774839561274216e-06, | |
| "loss": 1.0252, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.8534338863750628, | |
| "eval_error_rate": 0.1465661136249372, | |
| "eval_f1": 0.8370304500033733, | |
| "eval_loss": 0.9917795062065125, | |
| "eval_precision": 0.8575724637681159, | |
| "eval_recall": 0.8421052631578947, | |
| "eval_runtime": 24.0656, | |
| "eval_samples_per_second": 6.316, | |
| "eval_steps_per_second": 0.208, | |
| "eval_top1_accuracy": 0.8421052631578947, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "train_accuracy": 0.814327485380117 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "grad_norm": 2.2312376499176025, | |
| "learning_rate": 6.346644369977025e-06, | |
| "loss": 1.002, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.8611261940673707, | |
| "eval_error_rate": 0.13887380593262932, | |
| "eval_f1": 0.8435398841932419, | |
| "eval_loss": 0.9727317690849304, | |
| "eval_precision": 0.8677232854864433, | |
| "eval_recall": 0.8486842105263158, | |
| "eval_runtime": 25.3651, | |
| "eval_samples_per_second": 5.992, | |
| "eval_steps_per_second": 0.197, | |
| "eval_top1_accuracy": 0.8486842105263158, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "train_accuracy": 0.8179824561403509 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "grad_norm": 2.2069149017333984, | |
| "learning_rate": 5.000060000000003e-06, | |
| "loss": 0.9812, | |
| "step": 874 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.8677928607340373, | |
| "eval_error_rate": 0.13220713926596273, | |
| "eval_f1": 0.8497099815147097, | |
| "eval_loss": 0.9464592933654785, | |
| "eval_precision": 0.8795061782362883, | |
| "eval_recall": 0.8552631578947368, | |
| "eval_runtime": 26.8567, | |
| "eval_samples_per_second": 5.66, | |
| "eval_steps_per_second": 0.186, | |
| "eval_top1_accuracy": 0.8552631578947368, | |
| "step": 874 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "train_accuracy": 0.8187134502923976 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "grad_norm": 2.32728910446167, | |
| "learning_rate": 3.76516692100474e-06, | |
| "loss": 0.9636, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8699296128707893, | |
| "eval_error_rate": 0.1300703871292107, | |
| "eval_f1": 0.8485082765446309, | |
| "eval_loss": 0.93310546875, | |
| "eval_precision": 0.8820191260980734, | |
| "eval_recall": 0.8552631578947368, | |
| "eval_runtime": 27.6614, | |
| "eval_samples_per_second": 5.495, | |
| "eval_steps_per_second": 0.181, | |
| "eval_top1_accuracy": 0.8552631578947368, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "train_accuracy": 0.8150584795321637 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "grad_norm": 2.2066571712493896, | |
| "learning_rate": 2.6963844978948743e-06, | |
| "loss": 0.9591, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.8743740573152337, | |
| "eval_error_rate": 0.12562594268476635, | |
| "eval_f1": 0.8573701550510042, | |
| "eval_loss": 0.92206209897995, | |
| "eval_precision": 0.877970723615921, | |
| "eval_recall": 0.8618421052631579, | |
| "eval_runtime": 26.1743, | |
| "eval_samples_per_second": 5.807, | |
| "eval_steps_per_second": 0.191, | |
| "eval_top1_accuracy": 0.8618421052631579, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "train_accuracy": 0.8194444444444444 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "grad_norm": 2.345517873764038, | |
| "learning_rate": 1.75992615737436e-06, | |
| "loss": 0.948, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.8743740573152337, | |
| "eval_error_rate": 0.12562594268476635, | |
| "eval_f1": 0.8573701550510042, | |
| "eval_loss": 0.9158027768135071, | |
| "eval_precision": 0.877970723615921, | |
| "eval_recall": 0.8618421052631579, | |
| "eval_runtime": 26.0018, | |
| "eval_samples_per_second": 5.846, | |
| "eval_steps_per_second": 0.192, | |
| "eval_top1_accuracy": 0.868421052631579, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "train_accuracy": 0.8201754385964912 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "grad_norm": 2.246762990951538, | |
| "learning_rate": 1.0075383437198693e-06, | |
| "loss": 0.9384, | |
| "step": 1026 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.8601005530417295, | |
| "eval_error_rate": 0.1398994469582705, | |
| "eval_f1": 0.8431034082329946, | |
| "eval_loss": 0.901735782623291, | |
| "eval_precision": 0.8684637995623307, | |
| "eval_recall": 0.8486842105263158, | |
| "eval_runtime": 25.9225, | |
| "eval_samples_per_second": 5.864, | |
| "eval_steps_per_second": 0.193, | |
| "eval_top1_accuracy": 0.8486842105263158, | |
| "step": 1026 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "step": 1026, | |
| "total_flos": 6.9738304117683e+17, | |
| "train_loss": 1.2960130829095375, | |
| "train_runtime": 5177.2299, | |
| "train_samples_per_second": 7.046, | |
| "train_steps_per_second": 0.22 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1140, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 2 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.9738304117683e+17, | |
| "train_batch_size": 32, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |