| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "global_step": 1002, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.5049900199600802e-05, | |
| "loss": 0.9436, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 9.98003992015968e-08, | |
| "loss": 0.5733, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 1002, | |
| "total_flos": 1380790209626112.0, | |
| "train_loss": 0.7579664863988073, | |
| "train_runtime": 365.1021, | |
| "train_samples_per_second": 27.42, | |
| "train_steps_per_second": 2.744 | |
| } | |
| ], | |
| "max_steps": 1002, | |
| "num_train_epochs": 3, | |
| "total_flos": 1380790209626112.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |