| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 50.0, | |
| "eval_steps": 500, | |
| "global_step": 1200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 20.83, | |
| "learning_rate": 2.916666666666667e-05, | |
| "loss": 0.3975, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 41.67, | |
| "learning_rate": 8.333333333333334e-06, | |
| "loss": 0.0083, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "step": 1200, | |
| "total_flos": 1.044795366144e+17, | |
| "train_loss": 0.1694981136669715, | |
| "train_runtime": 2376.6749, | |
| "train_samples_per_second": 63.113, | |
| "train_steps_per_second": 0.505 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1200, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "total_flos": 1.044795366144e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |