---
tags:
- generated_from_trainer
base_model: microsoft/trocr-base-printed
model-index:
- name: image-text-captcha-v2
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# image-text-captcha-v2

This model is a fine-tuned version of [microsoft/trocr-base-printed](https://huggingface.co/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