Downloads · 30 days
24
4% of all-time downloads
layoutlmv2-finetuned_docvqa
am-infoweb/layoutlmv2-finetuned_docvqa
layoutlmv2-finetuned_docvqa is a document question answering model from am-infoweb. 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. The card lists the license as cc-by-nc-sa-4.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
538
Public
Parameters
200M
24.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin802 MB · 50%
At a glance
- Task
- Document Question Answering
- Library
- transformers
- License
- cc-by-nc-sa-4.0
- Model type
- layoutlmv2
- Access
- Public
- Created
- Sep 1, 2023
- Updated
- Sep 11, 2023
- SHA
- d047686d
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. -->
layoutlmv2-base-finetuned_docvqa
This model is a fine-tuned version of microsoft/layoutlmv2-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.9372
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.2741 | 0.22 | 50 | 4.5078 |
| 4.3688 | 0.44 | 100 | 4.2690 |
| 4.1035 | 0.66 | 150 | 3.7153 |
| 3.8461 | 0.88 | 200 | 3.6182 |
| 3.6142 | 1.11 | 250 | 3.4844 |
| 3.0794 | 1.33 | 300 | 3.2514 |
| 3.0315 | 1.55 | 350 | 3.3487 |
| 2.8165 | 1.77 | 400 | 2.7495 |
| 2.6306 | 1.99 | 450 | 2.8793 |
| 2.2232 | 2.21 | 500 | 2.5794 |
| 2.0693 | 2.43 | 550 | 2.7011 |
| 2.0821 | 2.65 | 600 | 2.4160 |
| 1.9505 | 2.88 | 650 | 2.2413 |
| 1.7037 | 3.1 | 700 | 2.3263 |
| 1.6657 | 3.32 | 750 | 3.0268 |
| 1.5721 | 3.54 | 800 | 2.8429 |
| 1.3987 | 3.76 | 850 | 2.3589 |
| 1.3469 | 3.98 | 900 | 2.6879 |
| 1.0572 | 4.2 | 950 | 3.0299 |
| 1.046 | 4.42 | 1000 | 2.7357 |
| 0.9208 | 4.65 | 1050 | 2.9640 |
| 0.9383 | 4.87 | 1100 | 2.9712 |
| 0.8651 | 5.09 | 1150 | 3.0117 |
| 0.7581 | 5.31 | 1200 | 3.1530 |
| 0.779 | 5.53 | 1250 | 3.0349 |
| 0.8105 | 5.75 | 1300 | 2.8753 |
| 0.705 | 5.97 | 1350 | 2.9372 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Task
- Document Question Answering
- Library
- transformers
- Type
- layoutlmv2
- License
- cc-by-nc-sa-4.0
- Created
- Sep 1, 2023
- Updated
- Sep 11, 2023