0%|█                                                                                                                                                                                                                                              | 100/23265 [06:27<5:40:44,  1.13it/s]

























































































  1%|██                                                                                                                                                                                                                                             | 199/23265 [12:55<6:10:42,  1.04it/s]


























































































  1%|███                                                                                                                                                                                                                                            | 300/23265 [19:23<5:54:38,  1.08it/s]

























































































  2%|████                                                                                                                                                                                                                                           | 399/23265 [25:54<6:11:33,  1.03it/s]


























































































  2%|█████▏                                                                                                                                                                                                                                         | 500/23265 [32:26<5:34:06,  1.14it/s]The following columns in the evaluation set  don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length. If input_length are not expected by `Wav2Vec2ForCTC.forward`,  you can safely ignore this message.
***** Running Evaluation *****
  Num examples = 5437
  Batch size = 16
{'loss': 0.8361, 'learning_rate': 2.48e-05, 'epoch': 0.32}

































































































































































































































































Configuration saved in ./checkpoint-500/config.json
{'eval_loss': 0.6304140686988831, 'eval_wer': 0.4970241305264396, 'eval_runtime': 553.4275, 'eval_samples_per_second': 9.824, 'eval_steps_per_second': 0.614, 'epoch': 0.32}
Model weights saved in ./checkpoint-500/pytorch_model.bin
Configuration saved in ./checkpoint-500/preprocessor_config.json