Downloads · 30 days
7
2% of all-time downloads
layoutlmv3-finetuned-cord_100
Aubi0ne/layoutlmv3-finetuned-cord_100
layoutlmv3-finetuned-cord_100 is a token classification model from Aubi0ne. 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
337
Public
Repo size
3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin504 MB · 99%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- cc-by-nc-sa-4.0
- Model type
- layoutlmv3
- Access
- Public
- Created
- Oct 17, 2022
- Updated
- Oct 17, 2022
- SHA
- 4d8cce63
Try a prompt
Datasets
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-finetuned-cord_100
This model is a fine-tuned version of microsoft/layoutlmv3-base on the cord dataset. It achieves the following results on the evaluation set:
- Loss: 0.2834
- Precision: 0.9175
- Recall: 0.9319
- F1: 0.9246
- Accuracy: 0.9406
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: 1e-05
- train_batch_size: 5
- eval_batch_size: 5
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 2500
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 4.17 | 250 | 1.0175 | 0.7358 | 0.7882 | 0.7611 | 0.8014 |
| 1.406 | 8.33 | 500 | 0.5646 | 0.8444 | 0.8735 | 0.8587 | 0.8671 |
| 1.406 | 12.5 | 750 | 0.3943 | 0.8950 | 0.9184 | 0.9065 | 0.9189 |
| 0.3467 | 16.67 | 1000 | 0.3379 | 0.9138 | 0.9289 | 0.9213 | 0.9291 |
| 0.3467 | 20.83 | 1250 | 0.2842 | 0.9189 | 0.9334 | 0.9261 | 0.9419 |
| 0.1484 | 25.0 | 1500 | 0.2822 | 0.9233 | 0.9371 | 0.9302 | 0.9427 |
| 0.1484 | 29.17 | 1750 | 0.2906 | 0.9168 | 0.9319 | 0.9243 | 0.9372 |
| 0.0825 | 33.33 | 2000 | 0.2922 | 0.9183 | 0.9334 | 0.9258 | 0.9410 |
| 0.0825 | 37.5 | 2250 | 0.2842 | 0.9154 | 0.9319 | 0.9236 | 0.9397 |
| 0.0596 | 41.67 | 2500 | 0.2834 | 0.9175 | 0.9319 | 0.9246 | 0.9406 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1
- Task
- Token Classification
- Library
- transformers
- Type
- layoutlmv3
- License
- cc-by-nc-sa-4.0
- Created
- Oct 17, 2022
- Updated
- Oct 17, 2022