<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
donut-base2-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: 1.3234
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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.1171 | 1.0 | 73 | 3.5216 |
| 2.6172 | 2.0 | 146 | 1.8420 |
| 2.1784 | 3.0 | 219 | 1.3622 |
| 1.0188 | 4.0 | 292 | 1.2344 |
| 0.8844 | 5.0 | 365 | 1.2448 |
| 0.4622 | 6.0 | 438 | 1.1840 |
| 0.8648 | 7.0 | 511 | 1.2136 |
| 0.4117 | 8.0 | 584 | 1.2452 |
| 0.2687 | 9.0 | 657 | 1.2622 |
| 0.4633 | 10.0 | 730 | 1.2959 |
| 0.4606 | 11.0 | 803 | 1.3234 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
