| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.7025, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 60, | |
| "total_flos": 96150646293120.0, | |
| "train_loss": 0.7014555931091309, | |
| "train_runtime": 9.5902, | |
| "train_samples_per_second": 198.641, | |
| "train_steps_per_second": 6.256 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 60, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 96150646293120.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |