|
{ |
|
"best_metric": 0.028854751959443092, |
|
"best_model_checkpoint": "/tmp/model/checkpoint-1026", |
|
"epoch": 3.0, |
|
"eval_steps": 500, |
|
"global_step": 1026, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 7.281553398058253e-06, |
|
"loss": 2.6614, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 1.5048543689320387e-05, |
|
"loss": 1.2662, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 2.330097087378641e-05, |
|
"loss": 0.5076, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 3.155339805825243e-05, |
|
"loss": 0.4482, |
|
"step": 68 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 3.980582524271845e-05, |
|
"loss": 0.3258, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 4.805825242718447e-05, |
|
"loss": 0.2473, |
|
"step": 102 |
|
}, |
|
{ |
|
"epoch": 0.35, |
|
"learning_rate": 4.929577464788733e-05, |
|
"loss": 0.3911, |
|
"step": 119 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 4.837486457204768e-05, |
|
"loss": 0.4416, |
|
"step": 136 |
|
}, |
|
{ |
|
"epoch": 0.45, |
|
"learning_rate": 4.745395449620802e-05, |
|
"loss": 0.4884, |
|
"step": 153 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 4.653304442036837e-05, |
|
"loss": 0.2937, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 4.561213434452871e-05, |
|
"loss": 0.3657, |
|
"step": 187 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 4.469122426868906e-05, |
|
"loss": 0.1776, |
|
"step": 204 |
|
}, |
|
{ |
|
"epoch": 0.65, |
|
"learning_rate": 4.377031419284941e-05, |
|
"loss": 0.3519, |
|
"step": 221 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 4.284940411700975e-05, |
|
"loss": 0.3079, |
|
"step": 238 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 4.1928494041170105e-05, |
|
"loss": 0.2125, |
|
"step": 255 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 4.1007583965330447e-05, |
|
"loss": 0.1151, |
|
"step": 272 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 4.0086673889490795e-05, |
|
"loss": 0.3185, |
|
"step": 289 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 3.916576381365114e-05, |
|
"loss": 0.1969, |
|
"step": 306 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 3.8244853737811486e-05, |
|
"loss": 0.2635, |
|
"step": 323 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 3.7323943661971835e-05, |
|
"loss": 0.2407, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.9633967789165446, |
|
"eval_auc": 0.9964920446122287, |
|
"eval_f1": 0.9614791987673343, |
|
"eval_loss": 0.10120841860771179, |
|
"eval_precision": 0.9397590361445783, |
|
"eval_recall": 0.9842271293375394, |
|
"eval_runtime": 12.6432, |
|
"eval_samples_per_second": 54.021, |
|
"eval_steps_per_second": 3.401, |
|
"step": 342 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 3.640303358613218e-05, |
|
"loss": 0.18, |
|
"step": 357 |
|
}, |
|
{ |
|
"epoch": 1.09, |
|
"learning_rate": 3.5482123510292526e-05, |
|
"loss": 0.167, |
|
"step": 374 |
|
}, |
|
{ |
|
"epoch": 1.14, |
|
"learning_rate": 3.4561213434452874e-05, |
|
"loss": 0.2256, |
|
"step": 391 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 3.3640303358613216e-05, |
|
"loss": 0.144, |
|
"step": 408 |
|
}, |
|
{ |
|
"epoch": 1.24, |
|
"learning_rate": 3.2719393282773565e-05, |
|
"loss": 0.108, |
|
"step": 425 |
|
}, |
|
{ |
|
"epoch": 1.29, |
|
"learning_rate": 3.179848320693391e-05, |
|
"loss": 0.2115, |
|
"step": 442 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 3.087757313109426e-05, |
|
"loss": 0.1777, |
|
"step": 459 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 2.9956663055254608e-05, |
|
"loss": 0.2568, |
|
"step": 476 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 2.9035752979414954e-05, |
|
"loss": 0.1353, |
|
"step": 493 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 2.81148429035753e-05, |
|
"loss": 0.1635, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 2.7193932827735648e-05, |
|
"loss": 0.244, |
|
"step": 527 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"learning_rate": 2.6273022751895993e-05, |
|
"loss": 0.1751, |
|
"step": 544 |
|
}, |
|
{ |
|
"epoch": 1.64, |
|
"learning_rate": 2.535211267605634e-05, |
|
"loss": 0.1629, |
|
"step": 561 |
|
}, |
|
{ |
|
"epoch": 1.69, |
|
"learning_rate": 2.4431202600216684e-05, |
|
"loss": 0.2097, |
|
"step": 578 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 2.3510292524377033e-05, |
|
"loss": 0.1262, |
|
"step": 595 |
|
}, |
|
{ |
|
"epoch": 1.79, |
|
"learning_rate": 2.258938244853738e-05, |
|
"loss": 0.0854, |
|
"step": 612 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 2.1668472372697727e-05, |
|
"loss": 0.3253, |
|
"step": 629 |
|
}, |
|
{ |
|
"epoch": 1.89, |
|
"learning_rate": 2.0747562296858072e-05, |
|
"loss": 0.0901, |
|
"step": 646 |
|
}, |
|
{ |
|
"epoch": 1.94, |
|
"learning_rate": 1.9826652221018418e-05, |
|
"loss": 0.0816, |
|
"step": 663 |
|
}, |
|
{ |
|
"epoch": 1.99, |
|
"learning_rate": 1.8905742145178766e-05, |
|
"loss": 0.1621, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.9853587115666179, |
|
"eval_auc": 0.9993104755994553, |
|
"eval_f1": 0.9843260188087775, |
|
"eval_loss": 0.039207685738801956, |
|
"eval_precision": 0.9781931464174455, |
|
"eval_recall": 0.9905362776025236, |
|
"eval_runtime": 12.5653, |
|
"eval_samples_per_second": 54.356, |
|
"eval_steps_per_second": 3.422, |
|
"step": 684 |
|
}, |
|
{ |
|
"epoch": 2.04, |
|
"learning_rate": 1.7984832069339115e-05, |
|
"loss": 0.154, |
|
"step": 697 |
|
}, |
|
{ |
|
"epoch": 2.09, |
|
"learning_rate": 1.706392199349946e-05, |
|
"loss": 0.1426, |
|
"step": 714 |
|
}, |
|
{ |
|
"epoch": 2.14, |
|
"learning_rate": 1.6143011917659806e-05, |
|
"loss": 0.1294, |
|
"step": 731 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"learning_rate": 1.5222101841820153e-05, |
|
"loss": 0.0665, |
|
"step": 748 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"learning_rate": 1.4301191765980498e-05, |
|
"loss": 0.0233, |
|
"step": 765 |
|
}, |
|
{ |
|
"epoch": 2.29, |
|
"learning_rate": 1.3380281690140845e-05, |
|
"loss": 0.0811, |
|
"step": 782 |
|
}, |
|
{ |
|
"epoch": 2.34, |
|
"learning_rate": 1.2459371614301192e-05, |
|
"loss": 0.0786, |
|
"step": 799 |
|
}, |
|
{ |
|
"epoch": 2.39, |
|
"learning_rate": 1.153846153846154e-05, |
|
"loss": 0.1104, |
|
"step": 816 |
|
}, |
|
{ |
|
"epoch": 2.44, |
|
"learning_rate": 1.0617551462621887e-05, |
|
"loss": 0.1425, |
|
"step": 833 |
|
}, |
|
{ |
|
"epoch": 2.49, |
|
"learning_rate": 9.696641386782232e-06, |
|
"loss": 0.0252, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 2.54, |
|
"learning_rate": 8.775731310942579e-06, |
|
"loss": 0.1767, |
|
"step": 867 |
|
}, |
|
{ |
|
"epoch": 2.58, |
|
"learning_rate": 7.90899241603467e-06, |
|
"loss": 0.0504, |
|
"step": 884 |
|
}, |
|
{ |
|
"epoch": 2.63, |
|
"learning_rate": 6.988082340195017e-06, |
|
"loss": 0.1102, |
|
"step": 901 |
|
}, |
|
{ |
|
"epoch": 2.68, |
|
"learning_rate": 6.067172264355364e-06, |
|
"loss": 0.11, |
|
"step": 918 |
|
}, |
|
{ |
|
"epoch": 2.73, |
|
"learning_rate": 5.14626218851571e-06, |
|
"loss": 0.0775, |
|
"step": 935 |
|
}, |
|
{ |
|
"epoch": 2.78, |
|
"learning_rate": 4.225352112676056e-06, |
|
"loss": 0.132, |
|
"step": 952 |
|
}, |
|
{ |
|
"epoch": 2.83, |
|
"learning_rate": 3.304442036836403e-06, |
|
"loss": 0.1459, |
|
"step": 969 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 2.38353196099675e-06, |
|
"loss": 0.0426, |
|
"step": 986 |
|
}, |
|
{ |
|
"epoch": 2.93, |
|
"learning_rate": 1.4626218851570965e-06, |
|
"loss": 0.2774, |
|
"step": 1003 |
|
}, |
|
{ |
|
"epoch": 2.98, |
|
"learning_rate": 5.417118093174432e-07, |
|
"loss": 0.0373, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.9897510980966325, |
|
"eval_auc": 0.9995604281946529, |
|
"eval_f1": 0.9889064976228209, |
|
"eval_loss": 0.028854751959443092, |
|
"eval_precision": 0.9936305732484076, |
|
"eval_recall": 0.9842271293375394, |
|
"eval_runtime": 12.521, |
|
"eval_samples_per_second": 54.548, |
|
"eval_steps_per_second": 3.434, |
|
"step": 1026 |
|
} |
|
], |
|
"logging_steps": 17, |
|
"max_steps": 1026, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"total_flos": 6.35124346881196e+17, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|