| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9997158283603297, | |
| "global_step": 1759, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 1.5906506632975366e-05, | |
| "loss": 0.8044, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 9.589387239418826e-06, | |
| "loss": 0.6525, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 3.272267845862287e-06, | |
| "loss": 0.6257, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.7384809851646423, | |
| "eval_runtime": 3.1281, | |
| "eval_samples_per_second": 71.608, | |
| "step": 1759 | |
| } | |
| ], | |
| "max_steps": 1759, | |
| "num_train_epochs": 1, | |
| "total_flos": 1.1494492138561536e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |