| { | |
| "best_metric": 2.4784371852874756, | |
| "best_model_checkpoint": "output/the-velvet-underground/checkpoint-33", | |
| "epoch": 1.0, | |
| "global_step": 33, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00012957411177772776, | |
| "loss": 3.524, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.0001083919039965842, | |
| "loss": 3.4007, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 7.836279790554737e-05, | |
| "loss": 3.2375, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 4.616313771642488e-05, | |
| "loss": 3.1744, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 1.8951844985992186e-05, | |
| "loss": 2.8642, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 2.778782010045488e-06, | |
| "loss": 2.8658, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 2.4784371852874756, | |
| "eval_runtime": 1.7053, | |
| "eval_samples_per_second": 22.869, | |
| "eval_steps_per_second": 2.932, | |
| "step": 33 | |
| } | |
| ], | |
| "max_steps": 33, | |
| "num_train_epochs": 1, | |
| "total_flos": 34098610176000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |