| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.25, | |
| "eval_steps": 500, | |
| "global_step": 3, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0001, | |
| "loss": 2.2664, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.0002, | |
| "loss": 2.2664, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 0.00018, | |
| "loss": 2.2136, | |
| "step": 3 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 12, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "total_flos": 524757258731520.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |