| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "global_step": 10310, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 1.6005819592628516e-05, | |
| "loss": 1.2636, | |
| "step": 2062 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.2005819592628516e-05, | |
| "loss": 0.5613, | |
| "step": 4124 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 8.005819592628517e-06, | |
| "loss": 0.4139, | |
| "step": 6186 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.007759456838022e-06, | |
| "loss": 0.3405, | |
| "step": 8248 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 9.699321047526674e-09, | |
| "loss": 0.2971, | |
| "step": 10310 | |
| } | |
| ], | |
| "max_steps": 10310, | |
| "num_train_epochs": 5, | |
| "total_flos": 1034571667046400.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |