| { | |
| "best_metric": 0.9107142857142857, | |
| "best_model_checkpoint": "test-trainer/checkpoint-300", | |
| "epoch": 6.0, | |
| "eval_steps": 500, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.48214285714285715, | |
| "eval_f1": 0.41339955022488756, | |
| "eval_loss": 1.6720179319381714, | |
| "eval_precision": 0.38696741854636585, | |
| "eval_recall": 0.48214285714285715, | |
| "eval_runtime": 1.2456, | |
| "eval_samples_per_second": 44.958, | |
| "eval_steps_per_second": 11.24, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6428571428571429, | |
| "eval_f1": 0.6126473922902493, | |
| "eval_loss": 1.4651685953140259, | |
| "eval_precision": 0.7413690476190476, | |
| "eval_recall": 0.6428571428571429, | |
| "eval_runtime": 1.2147, | |
| "eval_samples_per_second": 46.104, | |
| "eval_steps_per_second": 11.526, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.7321428571428571, | |
| "eval_f1": 0.7210389711440132, | |
| "eval_loss": 1.1741597652435303, | |
| "eval_precision": 0.7791524943310657, | |
| "eval_recall": 0.7321428571428571, | |
| "eval_runtime": 1.2504, | |
| "eval_samples_per_second": 44.787, | |
| "eval_steps_per_second": 11.197, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8392857142857143, | |
| "eval_f1": 0.8433130175146982, | |
| "eval_loss": 0.9812522530555725, | |
| "eval_precision": 0.858866084312513, | |
| "eval_recall": 0.8392857142857143, | |
| "eval_runtime": 1.2079, | |
| "eval_samples_per_second": 46.361, | |
| "eval_steps_per_second": 11.59, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8214285714285714, | |
| "eval_f1": 0.8163565426170468, | |
| "eval_loss": 0.8311730027198792, | |
| "eval_precision": 0.8515512265512265, | |
| "eval_recall": 0.8214285714285714, | |
| "eval_runtime": 1.2437, | |
| "eval_samples_per_second": 45.027, | |
| "eval_steps_per_second": 11.257, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.9107142857142857, | |
| "eval_f1": 0.9121670865142396, | |
| "eval_loss": 0.7291183471679688, | |
| "eval_precision": 0.9171626984126985, | |
| "eval_recall": 0.9107142857142857, | |
| "eval_runtime": 1.2203, | |
| "eval_samples_per_second": 45.89, | |
| "eval_steps_per_second": 11.472, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 300, | |
| "total_flos": 2.3108939745841152e+17, | |
| "train_loss": 1.2372085571289062, | |
| "train_runtime": 74.6152, | |
| "train_samples_per_second": 199.825, | |
| "train_steps_per_second": 20.103 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "early_stopping_threshold": 1.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 5 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.3108939745841152e+17, | |
| "train_batch_size": 10, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |