| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 2e-05, | |
| "loss": 1.8477, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4e-05, | |
| "loss": 0.3097, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 4e-05, | |
| "loss": 0.2845, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 2e-05, | |
| "loss": 0.2563, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.2462, | |
| "step": 1000 | |
| } | |
| ], | |
| "max_steps": 1000, | |
| "num_train_epochs": 1, | |
| "total_flos": 1444732207104000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |