| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 29.798657718120804, | |
| "eval_steps": 500, | |
| "global_step": 1110, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.19, | |
| "learning_rate": 0.000991991991991992, | |
| "loss": 1.7242, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 6.39, | |
| "learning_rate": 0.0008728728728728728, | |
| "loss": 1.5887, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 9.58, | |
| "learning_rate": 0.0007537537537537538, | |
| "loss": 1.5001, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 12.78, | |
| "learning_rate": 0.0006346346346346347, | |
| "loss": 1.4476, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "learning_rate": 0.0005155155155155156, | |
| "loss": 1.4097, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 19.17, | |
| "learning_rate": 0.0003963963963963964, | |
| "loss": 1.3734, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 22.36, | |
| "learning_rate": 0.0002772772772772773, | |
| "loss": 1.3429, | |
| "step": 833 | |
| }, | |
| { | |
| "epoch": 25.56, | |
| "learning_rate": 0.00015815815815815816, | |
| "loss": 1.3154, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 28.75, | |
| "learning_rate": 3.903903903903904e-05, | |
| "loss": 1.2919, | |
| "step": 1071 | |
| } | |
| ], | |
| "logging_steps": 119, | |
| "max_steps": 1110, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 1.2426251910384714e+19, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |