| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.3020833333333333, | |
| "eval_steps": 500, | |
| "global_step": 250, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0001975746552556772, | |
| "loss": 0.8825, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00018550053929480202, | |
| "loss": 0.6524, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00016449948488669639, | |
| "loss": 0.605, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.000136764169663272, | |
| "loss": 0.5817, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.00010519038181318999, | |
| "loss": 0.5779, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 7.307467669163655e-05, | |
| "loss": 0.5623, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 4.377019014049223e-05, | |
| "loss": 0.5583, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 2.03365443542764e-05, | |
| "loss": 0.5387, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 5.22039891260262e-06, | |
| "loss": 0.5375, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 0.0, | |
| "loss": 0.4968, | |
| "step": 250 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 250, | |
| "num_train_epochs": 2, | |
| "save_steps": 50, | |
| "total_flos": 1.37971841206272e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |