| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.9708029197080292, | |
| "eval_steps": 500, | |
| "global_step": 272, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.00017868852459016393, | |
| "loss": 1.6221, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.58, | |
| "learning_rate": 0.00013442622950819673, | |
| "loss": 1.1985, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 2.36, | |
| "learning_rate": 9.016393442622952e-05, | |
| "loss": 1.1718, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 3.15, | |
| "learning_rate": 4.672131147540984e-05, | |
| "loss": 1.1195, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "learning_rate": 2.459016393442623e-06, | |
| "loss": 1.0857, | |
| "step": 270 | |
| } | |
| ], | |
| "logging_steps": 54, | |
| "max_steps": 272, | |
| "num_train_epochs": 4, | |
| "save_steps": 500, | |
| "total_flos": 4.757799145832448e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |