| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 65.78947368421052, | |
| "global_step": 2500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 13.16, | |
| "learning_rate": 5e-05, | |
| "loss": 3.454, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 26.32, | |
| "learning_rate": 4.519230769230769e-05, | |
| "loss": 0.7914, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 39.47, | |
| "learning_rate": 4.038461538461539e-05, | |
| "loss": 0.1775, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 52.63, | |
| "learning_rate": 3.557692307692308e-05, | |
| "loss": 0.0932, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 65.79, | |
| "learning_rate": 3.0769230769230774e-05, | |
| "loss": 0.0703, | |
| "step": 2500 | |
| } | |
| ], | |
| "max_steps": 5700, | |
| "num_train_epochs": 150, | |
| "total_flos": 9181367241277440.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |