trocr-base-printed_captcha_ocr
This model is a fine-tuned version of microsoft/trocr-base-printed on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0042
- Cer: 0.001
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 11.82 | 1.0 | 439 | 0.0541 | 0.0117 |
| 0.2886 | 2.0 | 878 | 0.0223 | 0.006 |
| 0.0331 | 3.0 | 1317 | 0.0042 | 0.001 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3