| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 2744, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 0.00017788578371810451, | |
| "loss": 1.6415, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00013349534224382342, | |
| "loss": 1.5493, | |
| "step": 1096 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 8.910490076954234e-05, | |
| "loss": 1.5563, | |
| "step": 1644 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 4.471445929526124e-05, | |
| "loss": 1.5742, | |
| "step": 2192 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.2401782098015396e-07, | |
| "loss": 1.5752, | |
| "step": 2740 | |
| } | |
| ], | |
| "logging_steps": 548, | |
| "max_steps": 2744, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 2.2307119671803904e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |