| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9823182711198428, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 2.544204322200393e-05, | |
| "loss": 0.8938, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 8.840864440078585e-07, | |
| "loss": 0.8204, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1018, | |
| "num_train_epochs": 1, | |
| "save_steps": 1000, | |
| "total_flos": 1.30570518528e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |