| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.1037527593818985, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 4.111479028697572e-05, | |
| "loss": 2.5928, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.19168506254599e-05, | |
| "loss": 2.3829, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 2718, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 5.938777981714432e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |