| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 63, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 5.7149999999999995e-06, | |
| "loss": 2.8257, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 63, | |
| "total_flos": 1193890577645568.0, | |
| "train_loss": 2.7845563131665427, | |
| "train_runtime": 39.3075, | |
| "train_samples_per_second": 12.72, | |
| "train_steps_per_second": 1.603 | |
| } | |
| ], | |
| "max_steps": 63, | |
| "num_train_epochs": 1, | |
| "total_flos": 1193890577645568.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |