| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 135, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00018016528925619835, | |
| "loss": 2.0613, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00013719008264462813, | |
| "loss": 1.709, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 9.421487603305785e-05, | |
| "loss": 1.6203, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 5.1239669421487605e-05, | |
| "loss": 1.5468, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 8.264462809917356e-06, | |
| "loss": 1.5354, | |
| "step": 130 | |
| } | |
| ], | |
| "logging_steps": 26, | |
| "max_steps": 135, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "total_flos": 5.036703452076442e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |