image-text-captcha-v2
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: 0.5030
- Cer: 0.0588
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 13.43 | 1.0 | 373 | 0.6973 | 0.1290 |
| 0.6695 | 2.0 | 746 | 0.5942 | 0.1082 |
| 0.2885 | 3.0 | 1119 | 0.5038 | 0.0930 |
| 0.2885 | 4.0 | 1492 | 0.4981 | 0.0636 |
| 0.0946 | 5.0 | 1865 | 0.5030 | 0.0588 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 276
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the HF Inference API does not support transformers models with pipeline type image-text-to-text
Model tree for dragonstar/image-text-captcha-v2
Base model
microsoft/trocr-base-printed