| { | |
| "best_metric": 0.2426470588235294, | |
| "best_model_checkpoint": "pvt-small-224-finetuned-papsmear/checkpoint-38", | |
| "epoch": 14.901960784313726, | |
| "eval_steps": 500, | |
| "global_step": 570, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.26143790849673204, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5228758169934641, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.7843137254901961, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9934640522875817, | |
| "eval_accuracy": 0.2426470588235294, | |
| "eval_loss": NaN, | |
| "eval_runtime": 31.7906, | |
| "eval_samples_per_second": 4.278, | |
| "eval_steps_per_second": 0.535, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.0457516339869282, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.3071895424836601, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.5686274509803921, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.970760233918128e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.8300653594771243, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8732943469785574e-05, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.9869281045751634, | |
| "eval_accuracy": 0.2426470588235294, | |
| "eval_loss": NaN, | |
| "eval_runtime": 31.839, | |
| "eval_samples_per_second": 4.271, | |
| "eval_steps_per_second": 0.534, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 2.0915032679738563, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.7758284600389865e-05, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 2.3529411764705883, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.678362573099415e-05, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 2.6143790849673203, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.580896686159844e-05, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.8758169934640523, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.483430799220273e-05, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.980392156862745, | |
| "eval_accuracy": 0.2426470588235294, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.808, | |
| "eval_samples_per_second": 4.414, | |
| "eval_steps_per_second": 0.552, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 3.1372549019607843, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.3859649122807014e-05, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 3.3986928104575163, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.2884990253411305e-05, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 3.6601307189542482, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.1910331384015596e-05, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 3.9215686274509802, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.093567251461988e-05, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.2426470588235294, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.2912, | |
| "eval_samples_per_second": 4.49, | |
| "eval_steps_per_second": 0.561, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 4.183006535947713, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.996101364522417e-05, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.898635477582846e-05, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 4.705882352941177, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.8011695906432746e-05, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 4.967320261437909, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 4.993464052287582, | |
| "eval_accuracy": 0.2426470588235294, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.6184, | |
| "eval_samples_per_second": 4.442, | |
| "eval_steps_per_second": 0.555, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 5.228758169934641, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.606237816764133e-05, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.490196078431373, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.508771929824561e-05, | |
| "loss": 0.0, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 5.751633986928105, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.41130604288499e-05, | |
| "loss": 0.0, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 5.9869281045751634, | |
| "eval_accuracy": 0.2426470588235294, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.1997, | |
| "eval_samples_per_second": 4.503, | |
| "eval_steps_per_second": 0.563, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 6.0130718954248366, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.313840155945419e-05, | |
| "loss": 0.0, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 6.2745098039215685, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.216374269005848e-05, | |
| "loss": 0.0, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 6.5359477124183005, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.118908382066277e-05, | |
| "loss": 0.0, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 6.7973856209150325, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0214424951267055e-05, | |
| "loss": 0.0, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 6.980392156862745, | |
| "eval_accuracy": 0.2426470588235294, | |
| "eval_loss": NaN, | |
| "eval_runtime": 29.1774, | |
| "eval_samples_per_second": 4.661, | |
| "eval_steps_per_second": 0.583, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 7.0588235294117645, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9239766081871346e-05, | |
| "loss": 0.0, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 7.3202614379084965, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.8265107212475634e-05, | |
| "loss": 0.0, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 7.5816993464052285, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.729044834307992e-05, | |
| "loss": 0.0, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 7.8431372549019605, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6315789473684212e-05, | |
| "loss": 0.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.2426470588235294, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.0411, | |
| "eval_samples_per_second": 4.527, | |
| "eval_steps_per_second": 0.566, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 8.104575163398692, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.53411306042885e-05, | |
| "loss": 0.0, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 8.366013071895425, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.4366471734892787e-05, | |
| "loss": 0.0, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 8.627450980392156, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3391812865497074e-05, | |
| "loss": 0.0, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 8.88888888888889, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2417153996101365e-05, | |
| "loss": 0.0, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 8.993464052287582, | |
| "eval_accuracy": 0.2426470588235294, | |
| "eval_loss": NaN, | |
| "eval_runtime": 28.9661, | |
| "eval_samples_per_second": 4.695, | |
| "eval_steps_per_second": 0.587, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 9.15032679738562, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1442495126705653e-05, | |
| "loss": 0.0, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 9.411764705882353, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.046783625730994e-05, | |
| "loss": 0.0, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 9.673202614379084, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.949317738791423e-05, | |
| "loss": 0.0, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 9.934640522875817, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.0, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 9.986928104575163, | |
| "eval_accuracy": 0.2426470588235294, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.0597, | |
| "eval_samples_per_second": 4.524, | |
| "eval_steps_per_second": 0.566, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 10.196078431372548, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7543859649122806e-05, | |
| "loss": 0.0, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 10.457516339869281, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.6569200779727097e-05, | |
| "loss": 0.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 10.718954248366012, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5594541910331384e-05, | |
| "loss": 0.0, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 10.980392156862745, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4619883040935673e-05, | |
| "loss": 0.0, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 10.980392156862745, | |
| "eval_accuracy": 0.2426470588235294, | |
| "eval_loss": NaN, | |
| "eval_runtime": 29.2589, | |
| "eval_samples_per_second": 4.648, | |
| "eval_steps_per_second": 0.581, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 11.241830065359476, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.364522417153996e-05, | |
| "loss": 0.0, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 11.50326797385621, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.267056530214425e-05, | |
| "loss": 0.0, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 11.764705882352942, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1695906432748537e-05, | |
| "loss": 0.0, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.2426470588235294, | |
| "eval_loss": NaN, | |
| "eval_runtime": 29.0964, | |
| "eval_samples_per_second": 4.674, | |
| "eval_steps_per_second": 0.584, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 12.026143790849673, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0721247563352826e-05, | |
| "loss": 0.0, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 12.287581699346406, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.746588693957115e-06, | |
| "loss": 0.0, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 12.549019607843137, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.771929824561403e-06, | |
| "loss": 0.0, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 12.81045751633987, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.797270955165692e-06, | |
| "loss": 0.0, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 12.993464052287582, | |
| "eval_accuracy": 0.2426470588235294, | |
| "eval_loss": NaN, | |
| "eval_runtime": 29.7861, | |
| "eval_samples_per_second": 4.566, | |
| "eval_steps_per_second": 0.571, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 13.071895424836601, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.82261208576998e-06, | |
| "loss": 0.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.8479532163742686e-06, | |
| "loss": 0.0, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 13.594771241830065, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.873294346978558e-06, | |
| "loss": 0.0, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 13.856209150326798, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.898635477582846e-06, | |
| "loss": 0.0, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 13.986928104575163, | |
| "eval_accuracy": 0.2426470588235294, | |
| "eval_loss": NaN, | |
| "eval_runtime": 30.7446, | |
| "eval_samples_per_second": 4.424, | |
| "eval_steps_per_second": 0.553, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 14.117647058823529, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9239766081871343e-06, | |
| "loss": 0.0, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 14.379084967320262, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.949317738791423e-06, | |
| "loss": 0.0, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 14.640522875816993, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.746588693957115e-07, | |
| "loss": 0.0, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 14.901960784313726, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 14.901960784313726, | |
| "eval_accuracy": 0.2426470588235294, | |
| "eval_loss": NaN, | |
| "eval_runtime": 29.8497, | |
| "eval_samples_per_second": 4.556, | |
| "eval_steps_per_second": 0.57, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 14.901960784313726, | |
| "step": 570, | |
| "total_flos": 3.9497449737682944e+17, | |
| "train_loss": 0.0, | |
| "train_runtime": 4301.3175, | |
| "train_samples_per_second": 4.268, | |
| "train_steps_per_second": 0.133 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 570, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "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": 3.9497449737682944e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |