<!-- 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-base-annoted
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: 0.6158
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: 12
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.157 | 1.0 | 141 | 2.3659 |
| 1.3408 | 2.0 | 282 | 1.3562 |
| 0.935 | 3.0 | 423 | 1.0435 |
| 0.7753 | 4.0 | 564 | 0.8945 |
| 0.5065 | 5.0 | 705 | 0.8036 |
| 0.3419 | 6.0 | 846 | 0.7376 |
| 0.528 | 7.0 | 987 | 0.6872 |
| 0.178 | 8.0 | 1128 | 0.6792 |
| 0.1445 | 9.0 | 1269 | 0.6317 |
| 0.1702 | 10.0 | 1410 | 0.6233 |
| 0.0889 | 11.0 | 1551 | 0.6199 |
| 0.378 | 12.0 | 1692 | 0.6158 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
