| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6652452025586354, | |
| "eval_steps": 500, | |
| "global_step": 1560, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4793, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4323, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0002, | |
| "loss": 2.4193, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002, | |
| "loss": 2.405, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3934, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3879, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3848, | |
| "step": 1365 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3765, | |
| "step": 1560 | |
| } | |
| ], | |
| "logging_steps": 195, | |
| "max_steps": 1950, | |
| "num_train_epochs": 1, | |
| "save_steps": 195, | |
| "total_flos": 4.061675654558515e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |