metadata
license: mit
base_model: naver-clova-ix/donut-base
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: donut-base-sroie
results: []
donut-base-sroie
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: 9.6913
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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 18.9088 | 1.0 | 3 | 18.3757 |
| 14.9604 | 2.0 | 6 | 12.0340 |
| 12.7281 | 3.0 | 9 | 11.9031 |
| 10.6777 | 4.0 | 12 | 9.9294 |
| 10.1939 | 5.0 | 15 | 10.0405 |
| 9.9764 | 6.0 | 18 | 9.6913 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1