| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 1563, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 3.406909788867563e-05, | |
| "loss": 0.215, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 1.8074216250799745e-05, | |
| "loss": 0.0892, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 2.0793346129238647e-06, | |
| "loss": 0.0567, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1563, | |
| "total_flos": 91169426396928.0, | |
| "train_loss": 0.11771153991831013, | |
| "train_runtime": 51.2146, | |
| "train_samples_per_second": 487.595, | |
| "train_steps_per_second": 30.519 | |
| } | |
| ], | |
| "max_steps": 1563, | |
| "num_train_epochs": 3, | |
| "total_flos": 91169426396928.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |