Downloads · 30 days
17
3% of all-time downloads
donut-base-sroie
vivek-pathania/donut-base-sroie
donut-base-sroie is a image-text-to-text model from vivek-pathania. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
548
Public
Parameters
202M
205 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors809 MB · 100%
Parameter types
How the weights are stored.
F32202M · 100%
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- 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-sroie
This model is a fine-tuned version of naver-clova-ix/donut-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7974
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: 4
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1933 | 1.0 | 24 | 0.9206 |
| 0.2084 | 2.0 | 48 | 0.8872 |
| 0.1692 | 3.0 | 72 | 0.8975 |
| 0.1341 | 4.0 | 96 | 0.8255 |
| 0.1333 | 5.0 | 120 | 0.8524 |
| 0.1217 | 6.0 | 144 | 0.8312 |
| 0.1132 | 7.0 | 168 | 0.8814 |
| 0.0767 | 8.0 | 192 | 0.8282 |
| 0.0798 | 9.0 | 216 | 0.8331 |
| 0.0939 | 10.0 | 240 | 0.9095 |
| 0.0736 | 11.0 | 264 | 0.8566 |
| 0.0733 | 12.0 | 288 | 0.7841 |
| 0.0351 | 13.0 | 312 | 0.8250 |
| 0.0571 | 14.0 | 336 | 0.8270 |
| 0.0398 | 15.0 | 360 | 0.7958 |
| 0.0383 | 16.0 | 384 | 0.8322 |
| 0.0282 | 17.0 | 408 | 0.8043 |
| 0.0375 | 18.0 | 432 | 0.8077 |
| 0.0392 | 19.0 | 456 | 0.7974 |
| 0.047 | 20.0 | 480 | 0.7974 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.4.1
- Tokenizers 0.22.1
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- vision-encoder-decoder
- License
- mit
- Created
- Dec 27, 2025
- Updated
- Dec 28, 2025