---
license: mit
base_model: Manab/donut-base-my_model_rapido_2_new_check_2
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: donut-base-my_model_rapido_2_new_check_3
  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. -->

# donut-base-my_model_rapido_2_new_check_3

This model is a fine-tuned version of [Manab/donut-base-my_model_rapido_2_new_check_2](https://huggingface.co/Manab/donut-base-my_model_rapido_2_new_check_2) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3896

## 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: 1e-05
- train_batch_size: 1
- 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 2.8694        | 0.69  | 50   | 2.0758          |
| 2.2421        | 1.39  | 100  | 1.7321          |
| 1.6972        | 2.08  | 150  | 1.4280          |
| 1.5866        | 2.78  | 200  | 1.3896          |


### Framework versions

- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3