---
license: mit
base_model: naver-clova-ix/donut-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: donut-base-sroie-metrics-combined-new
  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-sroie-metrics-combined-new

This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1662
- Bleu score: 0.0215
- Precisions: [0.9469914040114613, 0.9204368174726989, 0.8938356164383562, 0.872865275142315]
- Brevity penalty: 0.0237
- Length ratio: 0.2109
- Translation length: 698
- Reference length: 3310
- Cer: 0.7917
- Wer: 0.8253
- Cer Hugging Face: 0.7954
- Wer Hugging Face: 0.8274

## 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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Bleu score | Precisions                                                                       | Brevity penalty | Length ratio | Translation length | Reference length | Cer    | Wer    | Cer Hugging Face | Wer Hugging Face |
|:-------------:|:-----:|:----:|:---------------:|:----------:|:--------------------------------------------------------------------------------:|:---------------:|:------------:|:------------------:|:----------------:|:------:|:------:|:----------------:|:----------------:|
| 0.5956        | 1.0   | 253  | 0.2372          | 0.0231     | [0.9258741258741259, 0.8890577507598785, 0.8519134775374376, 0.8180147058823529] | 0.0265          | 0.2160       | 715                | 3310             | 0.7922 | 0.8383 | 0.7969           | 0.8412           |
| 0.2509        | 2.0   | 506  | 0.1730          | 0.0213     | [0.9425287356321839, 0.9217527386541471, 0.8969072164948454, 0.88]               | 0.0234          | 0.2103       | 696                | 3310             | 0.7928 | 0.8285 | 0.7966           | 0.8306           |
| 0.22          | 3.0   | 759  | 0.1777          | 0.0215     | [0.9469914040114613, 0.9188767550702028, 0.8921232876712328, 0.872865275142315]  | 0.0237          | 0.2109       | 698                | 3310             | 0.7914 | 0.8282 | 0.7948           | 0.8306           |
| 0.1687        | 4.0   | 1012 | 0.1662          | 0.0215     | [0.9469914040114613, 0.9204368174726989, 0.8938356164383562, 0.872865275142315]  | 0.0237          | 0.2109       | 698                | 3310             | 0.7917 | 0.8253 | 0.7954           | 0.8274           |


### Framework versions

- Transformers 4.41.0.dev0
- Pytorch 2.1.0
- Datasets 2.19.0
- Tokenizers 0.19.1