| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9985829003306566, | |
| "global_step": 1587, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 1.9987397605545056e-05, | |
| "loss": 2.1008, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "learning_rate": 1.369880277252678e-05, | |
| "loss": 1.0392, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.89, | |
| "learning_rate": 7.3976055450535615e-06, | |
| "loss": 0.6614, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.83, | |
| "learning_rate": 1.0964083175803404e-06, | |
| "loss": 0.4864, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1587, | |
| "total_flos": 9.427610980948378e+16, | |
| "train_loss": 0.7142481595071217, | |
| "train_runtime": 6451.9847, | |
| "train_samples_per_second": 1.969, | |
| "train_steps_per_second": 0.246 | |
| } | |
| ], | |
| "max_steps": 1587, | |
| "num_train_epochs": 3, | |
| "total_flos": 9.427610980948378e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |