| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 868, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 2.1198156682027652e-05, | |
| "loss": 3.6133, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 868, | |
| "total_flos": 3626076925329408.0, | |
| "train_loss": 3.594241937734015, | |
| "train_runtime": 511.3081, | |
| "train_samples_per_second": 13.575, | |
| "train_steps_per_second": 1.698 | |
| } | |
| ], | |
| "max_steps": 868, | |
| "num_train_epochs": 1, | |
| "total_flos": 3626076925329408.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |