Downloads · 30 days
21
8% of all-time downloads
donut-base-sroie
raulss1/donut-base-sroie
donut-base-sroie is a image-text-to-text model from raulss1. 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
248
Public
Parameters
201M
12.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors806 MB · 99%
Parameter types
How the weights are stored.
F32201M · 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 pandafm/donut-es on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8468
- Cer: 1.4966
- Exact Match: 0.0
- Avg Edit Distance: 86.6638
- Nombre/razón social Accuracy: 0.0
- Factura Accuracy: 0.0
- Base imponible Accuracy: 0.0
- Total Accuracy: 0.0
- Fecha Accuracy: 0.0
- Igic Accuracy: 0.0
- Cif Accuracy: 0.0
- Nif Accuracy: 0.0
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer | Exact Match | Avg Edit Distance | Nombre/razón social Accuracy | Factura Accuracy | Base imponible Accuracy | Total Accuracy | Fecha Accuracy | Igic Accuracy | Cif Accuracy | Nif Accuracy |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 8.4323 | 1.0 | 104 | 7.4595 | 7.3214 | 0.0 | 423.1932 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 5.9044 | 2.0 | 208 | 4.6216 | 7.2697 | 0.0 | 420.2077 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 2.564 | 3.0 | 312 | 2.2138 | 3.9204 | 0.0 | 226.6039 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 1.6145 | 4.0 | 416 | 1.4490 | 3.3625 | 0.0 | 194.3575 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.9462 | 5.0 | 520 | 1.1422 | 1.2631 | 0.0 | 73.0048 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.6649 | 6.0 | 624 | 0.9678 | 1.5508 | 0.0 | 89.6425 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.4795 | 7.0 | 728 | 0.9374 | 2.0241 | 0.0 | 117.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.3135 | 8.0 | 832 | 0.9448 | 1.0045 | 0.0 | 58.0628 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.2315 | 9.0 | 936 | 0.9376 | 0.8702 | 0.0 | 50.2995 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.1716 | 10.0 | 1040 | 0.9406 | 0.8119 | 0.0 | 46.9324 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.1297 | 11.0 | 1144 | 0.9584 | 0.7571 | 0.0 | 43.7681 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.0954 | 12.0 | 1248 | 0.9966 | 0.7495 | 0.0 | 43.3237 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.0792 | 13.0 | 1352 | 1.0172 | 0.8140 | 0.0 | 47.0531 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
| 0.0627 | 14.0 | 1456 | 1.0403 | 0.8982 | 0.0 | 51.9130 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 |
Framework versions
- Transformers 4.57.0
- Pytorch 2.4.1+cu121
- Datasets 4.2.0
- Tokenizers 0.22.1
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- vision-encoder-decoder
- License
- mit
- Created
- Oct 8, 2025
- Updated
- Nov 12, 2025