| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 12, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.25, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9976, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0816, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 0.00018, | |
| "loss": 2.3143, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.00016, | |
| "loss": 2.1467, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "learning_rate": 0.00014, | |
| "loss": 2.1095, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 0.00012, | |
| "loss": 1.8863, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9137, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 8e-05, | |
| "loss": 2.1818, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "learning_rate": 6e-05, | |
| "loss": 1.8715, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "learning_rate": 4e-05, | |
| "loss": 1.8661, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 2e-05, | |
| "loss": 1.945, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 0.0, | |
| "loss": 1.6681, | |
| "step": 12 | |
| } | |
| ], | |
| "max_steps": 12, | |
| "num_train_epochs": 3, | |
| "total_flos": 841397336801280.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |