| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 3000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 0.0857, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.0187, | |
| "step": 2400 | |
| } | |
| ], | |
| "logging_steps": 1200, | |
| "max_steps": 3000, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 4.8776500471660544e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |