---
license: mit
base_model: naver-clova-ix/donut-base
tags:
- generated_from_trainer
metrics:
- bleu
- 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: 0.5114
- Bleu: 0.0672
- Precisions: [0.7849898580121704, 0.7041284403669725, 0.6490765171503958, 0.6024844720496895]
- Brevity Penalty: 0.0986
- Length Ratio: 0.3015
- Translation Length: 493
- Reference Length: 1635
- Cer: 0.7616
- Wer: 0.8389

## 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   | Precisions                                                                         | Brevity Penalty | Length Ratio | Translation Length | Reference Length | Cer    | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|:----------------------------------------------------------------------------------:|:---------------:|:------------:|:------------------:|:----------------:|:------:|:------:|
| 3.7646        | 1.0   | 253  | 1.3802          | 0.0163 | [0.5175257731958763, 0.21962616822429906, 0.1293800539083558, 0.06369426751592357] | 0.0934          | 0.2966       | 485                | 1635             | 0.8225 | 0.9292 |
| 1.2442        | 2.0   | 506  | 0.7108          | 0.0454 | [0.6456211812627292, 0.4930875576036866, 0.41379310344827586, 0.359375]            | 0.0973          | 0.3003       | 491                | 1635             | 0.7755 | 0.8908 |
| 0.8189        | 3.0   | 759  | 0.5739          | 0.0574 | [0.757700205338809, 0.6395348837209303, 0.5656836461126006, 0.4936708860759494]    | 0.0947          | 0.2979       | 487                | 1635             | 0.7606 | 0.8539 |
| 0.6444        | 4.0   | 1012 | 0.5114          | 0.0672 | [0.7849898580121704, 0.7041284403669725, 0.6490765171503958, 0.6024844720496895]   | 0.0986          | 0.3015       | 493                | 1635             | 0.7616 | 0.8389 |


### Framework versions

- Transformers 4.41.0.dev0
- Pytorch 2.1.0
- Datasets 2.19.1
- Tokenizers 0.19.1