metadata
license: mit
base_model: naver-clova-ix/donut-base
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: donut-vishnu_hwr2
results: []
donut-vishnu_hwr2
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: 0.3868
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7694 | 1.0 | 186 | 0.8806 |
| 0.5281 | 2.0 | 372 | 0.4291 |
| 0.0873 | 3.0 | 558 | 0.3671 |
| 0.2829 | 4.0 | 744 | 0.3432 |
| 0.0511 | 5.0 | 930 | 0.3604 |
| 0.0559 | 6.0 | 1116 | 0.3612 |
| 0.0407 | 7.0 | 1302 | 0.3728 |
| 0.0878 | 8.0 | 1488 | 0.3828 |
| 0.0801 | 9.0 | 1674 | 0.3868 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1