| { | |
| "best_metric": 0.8238283395767212, | |
| "best_model_checkpoint": "model/checkpoint-7764", | |
| "epoch": 2.0, | |
| "eval_steps": 100, | |
| "global_step": 7764, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.807550072669983, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.9625, | |
| "step": 3882 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.6951313755795981, | |
| "eval_f1": 0.7012381035255665, | |
| "eval_loss": 0.8328847289085388, | |
| "eval_precision": 0.7162081741896476, | |
| "eval_recall": 0.6951313755795981, | |
| "eval_runtime": 104.0426, | |
| "eval_samples_per_second": 74.623, | |
| "eval_steps_per_second": 4.671, | |
| "step": 3882 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 44.15189743041992, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 0.776, | |
| "step": 7764 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.705564142194745, | |
| "eval_f1": 0.7075271853161794, | |
| "eval_loss": 0.8238283395767212, | |
| "eval_precision": 0.7108297818792416, | |
| "eval_recall": 0.705564142194745, | |
| "eval_runtime": 104.4758, | |
| "eval_samples_per_second": 74.314, | |
| "eval_steps_per_second": 4.652, | |
| "step": 7764 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 23292, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 6, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 2, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.787710230624358e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |