| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04602462317339777, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 1.0305343511450381e-05, | |
| "loss": 13.0539, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 2.118320610687023e-05, | |
| "loss": 20.9649, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 3.206106870229007e-05, | |
| "loss": 21.1001, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 4.3511450381679383e-05, | |
| "loss": 5.5852, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 5.438931297709923e-05, | |
| "loss": 5.2002, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "eval_loss": 3.5950469970703125, | |
| "eval_runtime": 194.8685, | |
| "eval_samples_per_second": 24.853, | |
| "eval_steps_per_second": 0.78, | |
| "eval_wer": 1.0, | |
| "step": 100 | |
| } | |
| ], | |
| "max_steps": 6516, | |
| "num_train_epochs": 3, | |
| "total_flos": 1.8936564623727206e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |