| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 906, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 2.240618101545254e-05, | |
| "loss": 2.1642, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 906, | |
| "total_flos": 2314645478129664.0, | |
| "train_loss": 1.7788181599665425, | |
| "train_runtime": 335.3004, | |
| "train_samples_per_second": 26.958, | |
| "train_steps_per_second": 2.702 | |
| } | |
| ], | |
| "max_steps": 906, | |
| "num_train_epochs": 3, | |
| "total_flos": 2314645478129664.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |