Downloads · 30 days
7
4% of all-time downloads
layoutlmv2-base-uncased-finetuned-docvqa_1200_examples
guo1006/layoutlmv2-base-uncased-finetuned-docvqa_1200_examples
layoutlmv2-base-uncased-finetuned-docvqa_1200_examples is a document question answering model from guo1006. Use it for the document question answering task on the model card, and read the license before you ship it in a product. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
198
Public
Parameters
200M
18.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors802 MB · 100%
At a glance
- Task
- Document Question Answering
- Library
- transformers
- Model type
- layoutlmv2
- Access
- Public
- Created
- Sep 16, 2025
- Updated
- Sep 16, 2025
- SHA
- 013a99bd
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. -->
layoutlmv2-base-uncased-finetuned-docvqa_1200_examples
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.7004
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: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.4903 | 0.4425 | 100 | 4.2465 |
| 3.8673 | 0.8850 | 200 | 3.6497 |
| 3.2619 | 1.3274 | 300 | 3.1490 |
| 2.9801 | 1.7699 | 400 | 2.9969 |
| 2.0238 | 2.2124 | 500 | 2.5302 |
| 1.8018 | 2.6549 | 600 | 2.3716 |
| 1.5673 | 3.0973 | 700 | 2.4482 |
| 1.308 | 3.5398 | 800 | 2.3696 |
| 1.3341 | 3.9823 | 900 | 2.4187 |
| 1.0219 | 4.4248 | 1000 | 2.5895 |
| 0.8824 | 4.8673 | 1100 | 2.8213 |
| 0.7421 | 5.3097 | 1200 | 2.8942 |
| 0.4557 | 5.7522 | 1300 | 3.1607 |
| 0.3511 | 6.1947 | 1400 | 3.3976 |
| 0.4014 | 6.6372 | 1500 | 3.3107 |
| 0.5716 | 7.0796 | 1600 | 3.3122 |
| 0.3662 | 7.5221 | 1700 | 3.3131 |
| 0.2312 | 7.9646 | 1800 | 3.4253 |
| 0.225 | 8.4071 | 1900 | 3.6089 |
| 0.3573 | 8.8496 | 2000 | 3.6146 |
| 0.0989 | 9.2920 | 2100 | 3.6891 |
| 0.2683 | 9.7345 | 2200 | 3.7012 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.22.0
- Task
- Document Question Answering
- Library
- transformers
- Type
- layoutlmv2
- Created
- Sep 16, 2025
- Updated
- Sep 16, 2025