| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 9.058823529411764, | |
| "eval_steps": 500, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.02, | |
| "learning_rate": 3.9215686274509805e-05, | |
| "loss": 3.1171, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 7.843137254901961e-05, | |
| "loss": 2.8933, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 9.06, | |
| "learning_rate": 0.00011764705882352942, | |
| "loss": 2.6916, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 510, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 50252532940800.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |