| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9991220368744512, | |
| "global_step": 569, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.9964850615114238e-05, | |
| "loss": 2.1598, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 2.425307557117751e-06, | |
| "loss": 1.8933, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 569, | |
| "total_flos": 1.611445096635433e+17, | |
| "train_loss": 1.8867163251699168, | |
| "train_runtime": 2121.0416, | |
| "train_samples_per_second": 2.148, | |
| "train_steps_per_second": 0.268 | |
| } | |
| ], | |
| "max_steps": 569, | |
| "num_train_epochs": 1, | |
| "total_flos": 1.611445096635433e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |