| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.0, | |
| "global_step": 792, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.79, | |
| "learning_rate": 1.8434343434343433e-05, | |
| "loss": 2.936, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "step": 792, | |
| "total_flos": 826220325371904.0, | |
| "train_loss": 2.866144816080729, | |
| "train_runtime": 358.7849, | |
| "train_samples_per_second": 8.813, | |
| "train_steps_per_second": 2.207 | |
| } | |
| ], | |
| "max_steps": 792, | |
| "num_train_epochs": 6, | |
| "total_flos": 826220325371904.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |