| { | |
| "best_metric": 0.3162839710712433, | |
| "best_model_checkpoint": "autotrain-ytgys-osuer/checkpoint-1326", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 1326, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.049773755656108594, | |
| "grad_norm": 9.081209182739258, | |
| "learning_rate": 8.270676691729324e-06, | |
| "loss": 0.6296, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09954751131221719, | |
| "grad_norm": 1.96213698387146, | |
| "learning_rate": 1.6541353383458648e-05, | |
| "loss": 0.4877, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1493212669683258, | |
| "grad_norm": 2.1971828937530518, | |
| "learning_rate": 2.4812030075187968e-05, | |
| "loss": 0.5465, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.19909502262443438, | |
| "grad_norm": 5.049612998962402, | |
| "learning_rate": 3.3082706766917295e-05, | |
| "loss": 0.5186, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.248868778280543, | |
| "grad_norm": 0.6077613830566406, | |
| "learning_rate": 4.135338345864662e-05, | |
| "loss": 0.2962, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2986425339366516, | |
| "grad_norm": 5.124961853027344, | |
| "learning_rate": 4.9624060150375936e-05, | |
| "loss": 0.5159, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.34841628959276016, | |
| "grad_norm": 1.2383034229278564, | |
| "learning_rate": 4.9119865884325234e-05, | |
| "loss": 0.5115, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.39819004524886875, | |
| "grad_norm": 4.597978115081787, | |
| "learning_rate": 4.8197820620285e-05, | |
| "loss": 0.4524, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.4479638009049774, | |
| "grad_norm": 4.115572452545166, | |
| "learning_rate": 4.727577535624476e-05, | |
| "loss": 0.4217, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.497737556561086, | |
| "grad_norm": 1.8618402481079102, | |
| "learning_rate": 4.635373009220453e-05, | |
| "loss": 0.325, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5475113122171946, | |
| "grad_norm": 4.649389743804932, | |
| "learning_rate": 4.5431684828164296e-05, | |
| "loss": 0.4603, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.5972850678733032, | |
| "grad_norm": 2.3018507957458496, | |
| "learning_rate": 4.450963956412406e-05, | |
| "loss": 0.4817, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.6470588235294118, | |
| "grad_norm": 1.6560252904891968, | |
| "learning_rate": 4.358759430008382e-05, | |
| "loss": 0.4588, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.6968325791855203, | |
| "grad_norm": 1.248030185699463, | |
| "learning_rate": 4.266554903604359e-05, | |
| "loss": 0.4533, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.746606334841629, | |
| "grad_norm": 7.337639808654785, | |
| "learning_rate": 4.174350377200336e-05, | |
| "loss": 0.5258, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7963800904977375, | |
| "grad_norm": 3.778733253479004, | |
| "learning_rate": 4.0821458507963125e-05, | |
| "loss": 0.4715, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.8461538461538461, | |
| "grad_norm": 2.055952787399292, | |
| "learning_rate": 3.9899413243922885e-05, | |
| "loss": 0.5279, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.8959276018099548, | |
| "grad_norm": 2.640718460083008, | |
| "learning_rate": 3.897736797988265e-05, | |
| "loss": 0.4142, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.9457013574660633, | |
| "grad_norm": 2.906071424484253, | |
| "learning_rate": 3.805532271584242e-05, | |
| "loss": 0.618, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.995475113122172, | |
| "grad_norm": 7.490321159362793, | |
| "learning_rate": 3.713327745180218e-05, | |
| "loss": 0.4642, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8301245753114382, | |
| "eval_auc": 0.6658117326057298, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.468678742647171, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 155.3554, | |
| "eval_samples_per_second": 5.684, | |
| "eval_steps_per_second": 0.36, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 1.0452488687782806, | |
| "grad_norm": 1.7145849466323853, | |
| "learning_rate": 3.6211232187761947e-05, | |
| "loss": 0.5339, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 1.0950226244343892, | |
| "grad_norm": 7.355587959289551, | |
| "learning_rate": 3.5289186923721714e-05, | |
| "loss": 0.4688, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 1.1447963800904977, | |
| "grad_norm": 8.240862846374512, | |
| "learning_rate": 3.436714165968148e-05, | |
| "loss": 0.413, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 1.1945701357466063, | |
| "grad_norm": 4.566345691680908, | |
| "learning_rate": 3.344509639564124e-05, | |
| "loss": 0.4214, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 1.244343891402715, | |
| "grad_norm": 7.886547088623047, | |
| "learning_rate": 3.252305113160101e-05, | |
| "loss": 0.5584, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.2941176470588236, | |
| "grad_norm": 4.851104259490967, | |
| "learning_rate": 3.1601005867560775e-05, | |
| "loss": 0.5674, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 1.3438914027149322, | |
| "grad_norm": 2.095370054244995, | |
| "learning_rate": 3.067896060352054e-05, | |
| "loss": 0.4522, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 1.3936651583710407, | |
| "grad_norm": 1.348547339439392, | |
| "learning_rate": 2.9756915339480303e-05, | |
| "loss": 0.4711, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 1.4434389140271493, | |
| "grad_norm": 1.514244556427002, | |
| "learning_rate": 2.8834870075440066e-05, | |
| "loss": 0.3652, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 1.493212669683258, | |
| "grad_norm": 2.2231717109680176, | |
| "learning_rate": 2.7912824811399834e-05, | |
| "loss": 0.4884, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.5429864253393664, | |
| "grad_norm": 4.4252777099609375, | |
| "learning_rate": 2.69907795473596e-05, | |
| "loss": 0.4066, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 1.5927601809954752, | |
| "grad_norm": 2.0143589973449707, | |
| "learning_rate": 2.606873428331936e-05, | |
| "loss": 0.4817, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 1.6425339366515836, | |
| "grad_norm": 1.2555855512619019, | |
| "learning_rate": 2.5146689019279128e-05, | |
| "loss": 0.4505, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 1.6923076923076923, | |
| "grad_norm": 1.5008816719055176, | |
| "learning_rate": 2.4224643755238895e-05, | |
| "loss": 0.4987, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 1.742081447963801, | |
| "grad_norm": 1.0928298234939575, | |
| "learning_rate": 2.330259849119866e-05, | |
| "loss": 0.4491, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.7918552036199094, | |
| "grad_norm": 2.131342887878418, | |
| "learning_rate": 2.2380553227158423e-05, | |
| "loss": 0.5099, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 1.8416289592760182, | |
| "grad_norm": 2.0319790840148926, | |
| "learning_rate": 2.145850796311819e-05, | |
| "loss": 0.4312, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 1.8914027149321266, | |
| "grad_norm": 3.668442726135254, | |
| "learning_rate": 2.0536462699077953e-05, | |
| "loss": 0.414, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 1.9411764705882353, | |
| "grad_norm": 1.9720642566680908, | |
| "learning_rate": 1.961441743503772e-05, | |
| "loss": 0.3894, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 1.990950226244344, | |
| "grad_norm": 4.421242713928223, | |
| "learning_rate": 1.8692372170997484e-05, | |
| "loss": 0.4847, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8301245753114382, | |
| "eval_auc": 0.7693769895407002, | |
| "eval_f1": 0.0, | |
| "eval_loss": 0.45319485664367676, | |
| "eval_precision": 0.0, | |
| "eval_recall": 0.0, | |
| "eval_runtime": 156.7435, | |
| "eval_samples_per_second": 5.633, | |
| "eval_steps_per_second": 0.357, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 2.0407239819004523, | |
| "grad_norm": 4.845108985900879, | |
| "learning_rate": 1.777032690695725e-05, | |
| "loss": 0.426, | |
| "step": 902 | |
| }, | |
| { | |
| "epoch": 2.090497737556561, | |
| "grad_norm": 4.742054462432861, | |
| "learning_rate": 1.6848281642917015e-05, | |
| "loss": 0.4253, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 2.1402714932126696, | |
| "grad_norm": 27.354101181030273, | |
| "learning_rate": 1.5926236378876782e-05, | |
| "loss": 0.4168, | |
| "step": 946 | |
| }, | |
| { | |
| "epoch": 2.1900452488687785, | |
| "grad_norm": 9.501100540161133, | |
| "learning_rate": 1.5004191114836546e-05, | |
| "loss": 0.4337, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 2.239819004524887, | |
| "grad_norm": 2.986358165740967, | |
| "learning_rate": 1.4082145850796313e-05, | |
| "loss": 0.3713, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.2895927601809953, | |
| "grad_norm": 13.785974502563477, | |
| "learning_rate": 1.3160100586756077e-05, | |
| "loss": 0.3517, | |
| "step": 1012 | |
| }, | |
| { | |
| "epoch": 2.339366515837104, | |
| "grad_norm": 6.597299098968506, | |
| "learning_rate": 1.2238055322715842e-05, | |
| "loss": 0.362, | |
| "step": 1034 | |
| }, | |
| { | |
| "epoch": 2.3891402714932126, | |
| "grad_norm": 1.9302808046340942, | |
| "learning_rate": 1.1316010058675607e-05, | |
| "loss": 0.3733, | |
| "step": 1056 | |
| }, | |
| { | |
| "epoch": 2.4389140271493215, | |
| "grad_norm": 1.2917982339859009, | |
| "learning_rate": 1.0393964794635373e-05, | |
| "loss": 0.3184, | |
| "step": 1078 | |
| }, | |
| { | |
| "epoch": 2.48868778280543, | |
| "grad_norm": 2.898386240005493, | |
| "learning_rate": 9.471919530595138e-06, | |
| "loss": 0.4959, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.5384615384615383, | |
| "grad_norm": 5.883040904998779, | |
| "learning_rate": 8.549874266554904e-06, | |
| "loss": 0.3014, | |
| "step": 1122 | |
| }, | |
| { | |
| "epoch": 2.588235294117647, | |
| "grad_norm": 10.006911277770996, | |
| "learning_rate": 7.627829002514669e-06, | |
| "loss": 0.3047, | |
| "step": 1144 | |
| }, | |
| { | |
| "epoch": 2.6380090497737556, | |
| "grad_norm": 3.732818365097046, | |
| "learning_rate": 6.7057837384744345e-06, | |
| "loss": 0.382, | |
| "step": 1166 | |
| }, | |
| { | |
| "epoch": 2.6877828054298645, | |
| "grad_norm": 4.408326148986816, | |
| "learning_rate": 5.7837384744342e-06, | |
| "loss": 0.3173, | |
| "step": 1188 | |
| }, | |
| { | |
| "epoch": 2.737556561085973, | |
| "grad_norm": 7.149359226226807, | |
| "learning_rate": 4.861693210393965e-06, | |
| "loss": 0.4387, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.7873303167420813, | |
| "grad_norm": 9.934762001037598, | |
| "learning_rate": 3.939647946353731e-06, | |
| "loss": 0.2751, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 2.83710407239819, | |
| "grad_norm": 5.656704902648926, | |
| "learning_rate": 3.0176026823134957e-06, | |
| "loss": 0.3792, | |
| "step": 1254 | |
| }, | |
| { | |
| "epoch": 2.8868778280542986, | |
| "grad_norm": 7.494544506072998, | |
| "learning_rate": 2.095557418273261e-06, | |
| "loss": 0.3882, | |
| "step": 1276 | |
| }, | |
| { | |
| "epoch": 2.9366515837104075, | |
| "grad_norm": 12.555413246154785, | |
| "learning_rate": 1.173512154233026e-06, | |
| "loss": 0.3562, | |
| "step": 1298 | |
| }, | |
| { | |
| "epoch": 2.986425339366516, | |
| "grad_norm": 8.668551445007324, | |
| "learning_rate": 2.5146689019279127e-07, | |
| "loss": 0.2171, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8754246885617214, | |
| "eval_auc": 0.8692314688494771, | |
| "eval_f1": 0.6180555555555556, | |
| "eval_loss": 0.3162839710712433, | |
| "eval_precision": 0.644927536231884, | |
| "eval_recall": 0.5933333333333334, | |
| "eval_runtime": 161.1074, | |
| "eval_samples_per_second": 5.481, | |
| "eval_steps_per_second": 0.348, | |
| "step": 1326 | |
| } | |
| ], | |
| "logging_steps": 22, | |
| "max_steps": 1326, | |
| "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": 696981185648640.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |