| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "global_step": 2976, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.17, |
| "learning_rate": 1.831989247311828e-05, |
| "loss": 0.6085, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 1.663978494623656e-05, |
| "loss": 0.6656, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 1.4959677419354839e-05, |
| "loss": 0.6649, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 1.3279569892473118e-05, |
| "loss": 0.6354, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 1.1599462365591398e-05, |
| "loss": 0.6208, |
| "step": 2500 |
| } |
| ], |
| "max_steps": 5952, |
| "num_train_epochs": 2, |
| "total_flos": 564640713514710.0, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
