| { | |
| "best_metric": 0.08717025071382523, | |
| "best_model_checkpoint": "/tmp/model/checkpoint-801", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 801, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 6.172839506172839e-06, | |
| "loss": 2.4158, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.419753086419753e-05, | |
| "loss": 1.3701, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.6874, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.6272, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 3.7654320987654326e-05, | |
| "loss": 0.4387, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 4.567901234567901e-05, | |
| "loss": 0.3961, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 4.958333333333334e-05, | |
| "loss": 0.3804, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 4.8680555555555554e-05, | |
| "loss": 0.3121, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 4.7777777777777784e-05, | |
| "loss": 0.4641, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 4.6875e-05, | |
| "loss": 0.4265, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 4.5972222222222225e-05, | |
| "loss": 0.2297, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 4.506944444444445e-05, | |
| "loss": 0.3022, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 4.4166666666666665e-05, | |
| "loss": 0.2468, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 4.3263888888888895e-05, | |
| "loss": 0.1989, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 4.236111111111111e-05, | |
| "loss": 0.1909, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 4.1458333333333336e-05, | |
| "loss": 0.1993, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 4.055555555555556e-05, | |
| "loss": 0.2295, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 3.9652777777777776e-05, | |
| "loss": 0.2031, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.875e-05, | |
| "loss": 0.2698, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.7847222222222224e-05, | |
| "loss": 0.2311, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9700374531835206, | |
| "eval_auc": 0.9962602842183994, | |
| "eval_f1": 0.9583333333333333, | |
| "eval_loss": 0.08853638172149658, | |
| "eval_precision": 0.9533678756476683, | |
| "eval_recall": 0.9633507853403142, | |
| "eval_runtime": 24.9492, | |
| "eval_samples_per_second": 21.403, | |
| "eval_steps_per_second": 1.363, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 3.694444444444445e-05, | |
| "loss": 0.0761, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.604166666666667e-05, | |
| "loss": 0.349, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 3.513888888888889e-05, | |
| "loss": 0.063, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.423611111111111e-05, | |
| "loss": 0.3246, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.1024, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 3.243055555555556e-05, | |
| "loss": 0.0925, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 3.1527777777777775e-05, | |
| "loss": 0.151, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 3.069444444444445e-05, | |
| "loss": 0.4348, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 1.41, | |
| "learning_rate": 2.9791666666666668e-05, | |
| "loss": 0.1032, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 2.8888888888888888e-05, | |
| "loss": 0.1198, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "learning_rate": 2.7986111111111112e-05, | |
| "loss": 0.1627, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 2.7083333333333332e-05, | |
| "loss": 0.1473, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "learning_rate": 2.618055555555556e-05, | |
| "loss": 0.3162, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.534722222222222e-05, | |
| "loss": 0.4072, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.4444444444444445e-05, | |
| "loss": 0.3305, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 2.354166666666667e-05, | |
| "loss": 0.0342, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 2.263888888888889e-05, | |
| "loss": 0.1612, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 1.85, | |
| "learning_rate": 2.1736111111111112e-05, | |
| "loss": 0.1608, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.0989, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 1.95, | |
| "learning_rate": 1.9930555555555556e-05, | |
| "loss": 0.017, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.9027777777777776e-05, | |
| "loss": 0.2095, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.9681647940074907, | |
| "eval_auc": 0.9977332743119687, | |
| "eval_f1": 0.9541778975741241, | |
| "eval_loss": 0.1294296383857727, | |
| "eval_precision": 0.9833333333333333, | |
| "eval_recall": 0.9267015706806283, | |
| "eval_runtime": 25.4048, | |
| "eval_samples_per_second": 21.02, | |
| "eval_steps_per_second": 1.338, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 1.8125e-05, | |
| "loss": 0.0592, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 1.7222222222222224e-05, | |
| "loss": 0.0126, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 1.6319444444444444e-05, | |
| "loss": 0.0902, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 2.19, | |
| "learning_rate": 1.5416666666666668e-05, | |
| "loss": 0.0089, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 1.4513888888888891e-05, | |
| "loss": 0.0861, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 1.3611111111111111e-05, | |
| "loss": 0.0661, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 1.2708333333333333e-05, | |
| "loss": 0.0656, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 1.1805555555555555e-05, | |
| "loss": 0.2022, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "learning_rate": 1.0902777777777779e-05, | |
| "loss": 0.0538, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0116, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 2.53, | |
| "learning_rate": 9.097222222222223e-06, | |
| "loss": 0.0531, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 8.194444444444445e-06, | |
| "loss": 0.2677, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 2.63, | |
| "learning_rate": 7.2916666666666674e-06, | |
| "loss": 0.096, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 6.3888888888888885e-06, | |
| "loss": 0.1554, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 2.73, | |
| "learning_rate": 5.486111111111111e-06, | |
| "loss": 0.1553, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 4.583333333333333e-06, | |
| "loss": 0.0536, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 3.680555555555556e-06, | |
| "loss": 0.2112, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 2.87, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 0.0042, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 1.875e-06, | |
| "loss": 0.0882, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "learning_rate": 9.722222222222222e-07, | |
| "loss": 0.0295, | |
| "step": 793 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9812734082397003, | |
| "eval_auc": 0.9980461893059392, | |
| "eval_f1": 0.9732620320855615, | |
| "eval_loss": 0.08717025071382523, | |
| "eval_precision": 0.994535519125683, | |
| "eval_recall": 0.9528795811518325, | |
| "eval_runtime": 24.8605, | |
| "eval_samples_per_second": 21.48, | |
| "eval_steps_per_second": 1.368, | |
| "step": 801 | |
| } | |
| ], | |
| "logging_steps": 13, | |
| "max_steps": 801, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 5.010981737968927e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |