---
base_model: squantumengine/donut-stnk-v3_5_left
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: donut-stnk-v5_2-left
  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-stnk-v5_2-left

This model is a fine-tuned version of [squantumengine/donut-stnk-v3_5_left](https://huggingface.co/squantumengine/donut-stnk-v3_5_left) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1520

## 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: 2e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.1579        | 1.0   | 134  | 0.1520          |
| 0.1036        | 2.0   | 268  | 0.1597          |
| 0.0451        | 3.0   | 402  | 0.1700          |
| 0.0489        | 4.0   | 536  | 0.1753          |


### Framework versions

- Transformers 4.37.2
- Pytorch 1.13.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.1