| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 16, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00018571428571428572, | |
| "loss": 1.4494, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.00014285714285714287, | |
| "loss": 1.1933, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1962, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 5.714285714285714e-05, | |
| "loss": 1.1429, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.4285714285714285e-05, | |
| "loss": 1.3375, | |
| "step": 15 | |
| } | |
| ], | |
| "max_steps": 16, | |
| "num_train_epochs": 1, | |
| "total_flos": 332044324306944.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |