Token Classification
Transformers
Safetensors
layoutlmv3
Generated from Trainer
Eval Results (legacy)
Instructions to use smitbutle/document-data-extraction-layoutlmv3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use smitbutle/document-data-extraction-layoutlmv3 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="smitbutle/document-data-extraction-layoutlmv3")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForTokenClassification processor = AutoProcessor.from_pretrained("smitbutle/document-data-extraction-layoutlmv3") model = AutoModelForTokenClassification.from_pretrained("smitbutle/document-data-extraction-layoutlmv3", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from smitbutle/document-data-extraction-layoutlmv3: direct link, hf CLI and curl.
- Browser
- Download file 3.78 kB
-
https://huggingface.co/smitbutle/document-data-extraction-layoutlmv3/resolve/main/README.md
- Command line
-
hf download hf://smitbutle/document-data-extraction-layoutlmv3/README.md
-
curl -L -o README.md https://huggingface.co/smitbutle/document-data-extraction-layoutlmv3/resolve/main/README.md
3.78 kB
| license: cc-by-nc-sa-4.0 | |
| base_model: microsoft/layoutlmv3-base | |
| tags: | |
| - generated_from_trainer | |
| datasets: | |
| - generated | |
| metrics: | |
| - precision | |
| - recall | |
| - f1 | |
| - accuracy | |
| model-index: | |
| - name: document-data-extraction-layoutlmv3 | |
| results: | |
| - task: | |
| name: Token Classification | |
| type: token-classification | |
| dataset: | |
| name: generated | |
| type: generated | |
| config: sroie | |
| split: test | |
| args: sroie | |
| metrics: | |
| - name: Precision | |
| type: precision | |
| value: 1.0 | |
| - name: Recall | |
| type: recall | |
| value: 1.0 | |
| - name: F1 | |
| type: f1 | |
| value: 1.0 | |
| - name: Accuracy | |
| type: accuracy | |
| value: 1.0 | |
| <!-- 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. --> | |
| # document-data-extraction-layoutlmv3 | |
| This model is a fine-tuned version of [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base) on the generated dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 0.0015 | |
| - Precision: 1.0 | |
| - Recall: 1.0 | |
| - F1: 1.0 | |
| - Accuracy: 1.0 | |
| ## 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: 1e-05 | |
| - train_batch_size: 1 | |
| - eval_batch_size: 1 | |
| - seed: 42 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: linear | |
| - training_steps: 2000 | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | | |
| |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| | |
| | No log | 1.0 | 100 | 0.1114 | 0.95 | 0.9635 | 0.9567 | 0.9947 | | |
| | No log | 2.0 | 200 | 0.0286 | 0.972 | 0.9858 | 0.9789 | 0.9971 | | |
| | No log | 3.0 | 300 | 0.0184 | 0.972 | 0.9858 | 0.9789 | 0.9971 | | |
| | No log | 4.0 | 400 | 0.0163 | 0.972 | 0.9858 | 0.9789 | 0.9971 | | |
| | 0.1385 | 5.0 | 500 | 0.0141 | 0.972 | 0.9858 | 0.9789 | 0.9971 | | |
| | 0.1385 | 6.0 | 600 | 0.0123 | 0.972 | 0.9858 | 0.9789 | 0.9971 | | |
| | 0.1385 | 7.0 | 700 | 0.0122 | 0.972 | 0.9858 | 0.9789 | 0.9971 | | |
| | 0.1385 | 8.0 | 800 | 0.0108 | 0.972 | 0.9858 | 0.9789 | 0.9971 | | |
| | 0.1385 | 9.0 | 900 | 0.0104 | 0.972 | 0.9858 | 0.9789 | 0.9971 | | |
| | 0.0119 | 10.0 | 1000 | 0.0113 | 0.972 | 0.9858 | 0.9789 | 0.9971 | | |
| | 0.0119 | 11.0 | 1100 | 0.0080 | 0.974 | 0.9878 | 0.9809 | 0.9973 | | |
| | 0.0119 | 12.0 | 1200 | 0.0089 | 0.9856 | 0.9736 | 0.9796 | 0.9973 | | |
| | 0.0119 | 13.0 | 1300 | 0.0034 | 0.9959 | 0.9959 | 0.9959 | 0.9994 | | |
| | 0.0119 | 14.0 | 1400 | 0.0037 | 0.9980 | 0.9939 | 0.9959 | 0.9994 | | |
| | 0.006 | 15.0 | 1500 | 0.0024 | 0.9960 | 0.9980 | 0.9970 | 0.9996 | | |
| | 0.006 | 16.0 | 1600 | 0.0019 | 0.9980 | 1.0 | 0.9990 | 0.9998 | | |
| | 0.006 | 17.0 | 1700 | 0.0022 | 0.9960 | 0.9980 | 0.9970 | 0.9996 | | |
| | 0.006 | 18.0 | 1800 | 0.0017 | 1.0 | 1.0 | 1.0 | 1.0 | | |
| | 0.006 | 19.0 | 1900 | 0.0015 | 1.0 | 1.0 | 1.0 | 1.0 | | |
| | 0.0027 | 20.0 | 2000 | 0.0015 | 1.0 | 1.0 | 1.0 | 1.0 | | |
| ### Framework versions | |
| - Transformers 4.36.0.dev0 | |
| - Pytorch 2.1.1+cu121 | |
| - Datasets 2.15.0 | |
| - Tokenizers 0.15.0 | |