metadata
license: mit
base_model: naver-clova-ix/donut-base
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: donut_marriage_mixed_512-128_003
results: []
donut_marriage_mixed_512-128_003
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: 0.1388
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: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7548 | 1.0 | 256 | 0.3804 |
| 0.1097 | 2.0 | 512 | 0.2123 |
| 0.1566 | 3.0 | 768 | 0.2084 |
| 0.0439 | 4.0 | 1024 | 0.1663 |
| 0.125 | 5.0 | 1280 | 0.1685 |
| 0.0031 | 6.0 | 1536 | 0.1349 |
| 0.0042 | 7.0 | 1792 | 0.1363 |
| 0.0803 | 8.0 | 2048 | 0.1534 |
| 0.0089 | 9.0 | 2304 | 0.1400 |
| 0.0261 | 10.0 | 2560 | 0.1418 |
| 0.0002 | 11.0 | 2816 | 0.1388 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0