| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "global_step": 2240, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.23, | |
| "learning_rate": 3.883928571428572e-05, | |
| "loss": 2.8686, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.46, | |
| "learning_rate": 2.767857142857143e-05, | |
| "loss": 1.4937, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "learning_rate": 1.6517857142857144e-05, | |
| "loss": 0.6991, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 8.93, | |
| "learning_rate": 5.357142857142857e-06, | |
| "loss": 0.3128, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 2240, | |
| "total_flos": 4923477570256896.0, | |
| "train_loss": 1.219481522696359, | |
| "train_runtime": 825.4587, | |
| "train_samples_per_second": 27.04, | |
| "train_steps_per_second": 2.714 | |
| } | |
| ], | |
| "max_steps": 2240, | |
| "num_train_epochs": 10, | |
| "total_flos": 4923477570256896.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |