| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "global_step": 8132, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 5e-06, | |
| "loss": 2.1304, | |
| "step": 4066 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 0.0, | |
| "loss": 0.395, | |
| "step": 8132 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 8132, | |
| "total_flos": 1.0506418329673728e+16, | |
| "train_loss": 1.2627147819042441, | |
| "train_runtime": 2692.7589, | |
| "train_samples_per_second": 24.158, | |
| "train_steps_per_second": 3.02 | |
| } | |
| ], | |
| "max_steps": 8132, | |
| "num_train_epochs": 2, | |
| "total_flos": 1.0506418329673728e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |