| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 33.333333333333336, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 16.67, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 3.8103, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "learning_rate": 0.0, | |
| "loss": 0.4081, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 33.33, | |
| "step": 200, | |
| "total_flos": 346463168384640.0, | |
| "train_loss": 2.1091724014282227, | |
| "train_runtime": 92.0933, | |
| "train_samples_per_second": 26.061, | |
| "train_steps_per_second": 2.172 | |
| } | |
| ], | |
| "max_steps": 200, | |
| "num_train_epochs": 34, | |
| "total_flos": 346463168384640.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |