| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.7871017871017871, | |
| "global_step": 2300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 2.8834498834498833e-05, | |
| "loss": 0.5929, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 2.766899766899767e-05, | |
| "loss": 0.4371, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 2.6503496503496503e-05, | |
| "loss": 0.3773, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.55, | |
| "learning_rate": 2.5337995337995338e-05, | |
| "loss": 0.3391, | |
| "step": 2000 | |
| } | |
| ], | |
| "max_steps": 12870, | |
| "num_train_epochs": 10, | |
| "total_flos": 138962361110593536, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |