| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9978118161925602, | |
| "eval_steps": 500, | |
| "global_step": 114, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.5098039215686275e-05, | |
| "loss": 1.653, | |
| "step": 91 | |
| } | |
| ], | |
| "logging_steps": 91, | |
| "max_steps": 114, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 1.994077583179776e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |