| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 7.0, | |
| "global_step": 1260, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.78, | |
| "learning_rate": 1.2063492063492064e-05, | |
| "loss": 0.7453, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.56, | |
| "learning_rate": 4.126984126984127e-06, | |
| "loss": 0.1724, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "step": 1260, | |
| "total_flos": 3383750193551616.0, | |
| "train_runtime": 851.9812, | |
| "train_samples_per_second": 1.479 | |
| } | |
| ], | |
| "max_steps": 1260, | |
| "num_train_epochs": 7, | |
| "total_flos": 3383750193551616.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |