metadata
license: mit
base_model: naver-clova-ix/donut-base
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: donut-base-sroie44
results: []
donut-base-sroie44
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: 0.8959
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
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
6.8624 | 1.0 | 45 | 6.0252 |
3.5286 | 2.0 | 90 | 2.7989 |
2.2016 | 3.0 | 135 | 1.7187 |
0.9759 | 4.0 | 180 | 1.3290 |
0.7308 | 5.0 | 225 | 1.1039 |
1.2687 | 6.0 | 270 | 0.9728 |
0.8614 | 7.0 | 315 | 0.9411 |
0.5169 | 8.0 | 360 | 0.9238 |
0.7396 | 9.0 | 405 | 0.8948 |
0.4634 | 10.0 | 450 | 0.8959 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1