| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "global_step": 44, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.00018461538461538463, | |
| "loss": 0.9068, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0001435897435897436, | |
| "loss": 0.9528, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00010256410256410256, | |
| "loss": 0.9176, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 6.153846153846155e-05, | |
| "loss": 0.7879, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.0512820512820512e-05, | |
| "loss": 0.9345, | |
| "step": 40 | |
| } | |
| ], | |
| "max_steps": 44, | |
| "num_train_epochs": 1, | |
| "total_flos": 2052379700625408.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |