Writing logs to ./outputs/2024-02-27-20-27-33-802873/train_log.txt.
Wrote original training args to ./outputs/2024-02-27-20-27-33-802873/training_args.json.
***** Running training *****
  Num examples = 9600
  Num epochs = 3
  Num clean epochs = 3
  Instantaneous batch size per device = 8
  Total train batch size (w. parallel, distributed & accumulation) = 8
  Gradient accumulation steps = 1
  Total optimization steps = 3600
==========================================================
Epoch 1
Running clean epoch 1/3
Train accuracy: 88.54%
Eval accuracy: 92.75%
Best score found. Saved model to ./outputs/2024-02-27-20-27-33-802873/best_model/
==========================================================
Epoch 2
Running clean epoch 2/3
Train accuracy: 96.02%
Eval accuracy: 95.08%
Best score found. Saved model to ./outputs/2024-02-27-20-27-33-802873/best_model/
==========================================================
Epoch 3
Running clean epoch 3/3
Train accuracy: 98.58%
Eval accuracy: 95.58%
Best score found. Saved model to ./outputs/2024-02-27-20-27-33-802873/best_model/
Wrote README to ./outputs/2024-02-27-20-27-33-802873/README.md.