metadata
license: mit
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: donut_pdf_ocr
results: []
donut_pdf_ocr
This model is a fine-tuned version of naver-clova-ix/donut-base on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2879
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: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.7815 | 1.0 | 47 | 2.1495 |
| 0.6386 | 2.0 | 94 | 0.4316 |
| 0.336 | 3.0 | 141 | 0.2980 |
| 0.2021 | 4.0 | 188 | 0.2933 |
| 0.2655 | 5.0 | 235 | 0.2879 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3