| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "eval_steps": 500, | |
| "global_step": 315, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.5873015873015874, | |
| "grad_norm": 3.2433021068573, | |
| "learning_rate": 1.5265017667844523e-05, | |
| "loss": 0.514, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 3.1746031746031744, | |
| "grad_norm": 15.541455268859863, | |
| "learning_rate": 8.197879858657245e-06, | |
| "loss": 0.2767, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 4.761904761904762, | |
| "grad_norm": 9.312417030334473, | |
| "learning_rate": 1.1307420494699648e-06, | |
| "loss": 0.1693, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 315, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1429776675840000.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |