metadata
tags:
- generated_from_trainer
base_model: microsoft/trocr-base-printed
model-index:
- name: image-text-captcha
results: []
image-text-captcha
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: 0.1041
- Cer: 0.0161
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 |
|---|---|---|---|---|
| 11.8912 | 1.0 | 217 | 0.2386 | 0.0774 |
| 11.8912 | 2.0 | 434 | 0.1543 | 0.0452 |
| 0.4293 | 3.0 | 651 | 0.1088 | 0.0194 |
| 0.4293 | 4.0 | 868 | 0.1233 | 0.0323 |
| 0.0775 | 5.0 | 1085 | 0.1041 | 0.0161 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3