| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 31.68, | |
| "eval_steps": 500, | |
| "global_step": 1980, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6764, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6401, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2528, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1871, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1582, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 0.0002, | |
| "loss": 0.15, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 24.64, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1432, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 28.16, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1432, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 31.68, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1441, | |
| "step": 1980 | |
| } | |
| ], | |
| "logging_steps": 220, | |
| "max_steps": 2200, | |
| "num_train_epochs": 36, | |
| "save_steps": 220, | |
| "total_flos": 7.604004269088768e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |