Downloads · 30 days
9
16% of all-time downloads
layoutlmv3-cord
cuongdz01/layoutlmv3-cord
layoutlmv3-cord is a token classification model from cuongdz01. Use it when you need labels on individual words, such as names. 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
56
Public
Parameters
126M
1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors504 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- cc-by-nc-sa-4.0
- Model type
- layoutlmv3
- Access
- Public
- Created
- Jan 3, 2024
- Updated
- Jan 3, 2024
- SHA
- 72b62e51
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. -->
layoutlmv3-cord
This model is a fine-tuned version of microsoft/layoutlmv3-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1589
- Precision: 0.9433
- Recall: 0.9521
- F1: 0.9477
- Accuracy: 0.9669
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: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 0.5 | 100 | 0.6487 | 0.7825 | 0.8006 | 0.7914 | 0.8330 |
| No log | 1.0 | 200 | 0.4266 | 0.8496 | 0.8686 | 0.8590 | 0.8925 |
| No log | 1.5 | 300 | 0.2553 | 0.9008 | 0.9057 | 0.9033 | 0.9341 |
| No log | 2.0 | 400 | 0.2496 | 0.8960 | 0.9057 | 0.9008 | 0.9295 |
| 0.5667 | 2.5 | 500 | 0.2016 | 0.9274 | 0.9374 | 0.9324 | 0.9554 |
| 0.5667 | 3.0 | 600 | 0.1806 | 0.9387 | 0.9467 | 0.9427 | 0.9609 |
| 0.5667 | 3.5 | 700 | 0.1667 | 0.9424 | 0.9474 | 0.9449 | 0.9630 |
| 0.5667 | 4.0 | 800 | 0.1735 | 0.9452 | 0.9467 | 0.9459 | 0.9639 |
| 0.5667 | 4.5 | 900 | 0.1657 | 0.9456 | 0.9529 | 0.9492 | 0.9660 |
| 0.1025 | 5.0 | 1000 | 0.1589 | 0.9433 | 0.9521 | 0.9477 | 0.9669 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.0.0
- Datasets 2.16.1
- Tokenizers 0.15.0
- Task
- Token Classification
- Library
- transformers
- Type
- layoutlmv3
- License
- cc-by-nc-sa-4.0
- Created
- Jan 3, 2024
- Updated
- Jan 3, 2024