| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.857142857142857, | |
| "eval_steps": 500, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2469, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.2656, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 1.71, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1889, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "learning_rate": 5e-05, | |
| "loss": 1.106, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 2.86, | |
| "learning_rate": 0.0, | |
| "loss": 1.1235, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_train_epochs": 5, | |
| "save_steps": 500, | |
| "total_flos": 3251764702740480.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |