Instructions to use Githubturer/layoutlm-funsd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Githubturer/layoutlm-funsd with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="Githubturer/layoutlm-funsd")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("Githubturer/layoutlm-funsd") model = AutoModelForTokenClassification.from_pretrained("Githubturer/layoutlm-funsd", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from Githubturer/layoutlm-funsd: direct link, hf CLI and curl.
- Browser
- Download file 11.1 kB
-
https://huggingface.co/Githubturer/layoutlm-funsd/resolve/main/README.md
- Command line
-
hf download hf://Githubturer/layoutlm-funsd/README.md
-
curl -L -o README.md https://huggingface.co/Githubturer/layoutlm-funsd/resolve/main/README.md
11.1 kB
| tags: | |
| - generated_from_trainer | |
| datasets: | |
| - layoutlm_resume_data | |
| model-index: | |
| - name: layoutlm-funsd | |
| results: [] | |
| <!-- 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. --> | |
| # layoutlm-funsd | |
| This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on the layoutlm_resume_data dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 0.0076 | |
| - Address: {'precision': 0.9166666666666666, 'recall': 0.9166666666666666, 'f1': 0.9166666666666666, 'number': 24} | |
| - Email: {'precision': 0.8214285714285714, 'recall': 0.8518518518518519, 'f1': 0.8363636363636364, 'number': 27} | |
| - Name: {'precision': 0.926829268292683, 'recall': 0.9743589743589743, 'f1': 0.9500000000000001, 'number': 39} | |
| - Phone: {'precision': 0.8378378378378378, 'recall': 0.8611111111111112, 'f1': 0.8493150684931507, 'number': 36} | |
| - Overall Precision: 0.8769 | |
| - Overall Recall: 0.9048 | |
| - Overall F1: 0.8906 | |
| - Overall Accuracy: 0.9989 | |
| ## 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: 3e-05 | |
| - train_batch_size: 16 | |
| - eval_batch_size: 8 | |
| - seed: 42 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: linear | |
| - num_epochs: 15 | |
| - mixed_precision_training: Native AMP | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | Address | Email | Name | Phone | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy | | |
| |:-------------:|:-----:|:----:|:---------------:|:------------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:| | |
| | 1.9 | 1.0 | 15 | 0.2150 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 24} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 27} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 39} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 36} | 0.0 | 0.0 | 0.0 | 0.9757 | | |
| | 0.1382 | 2.0 | 30 | 0.0885 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 24} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 27} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 39} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 36} | 0.0 | 0.0 | 0.0 | 0.9757 | | |
| | 0.0714 | 3.0 | 45 | 0.0499 | {'precision': 0.02040816326530612, 'recall': 0.041666666666666664, 'f1': 0.027397260273972598, 'number': 24} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 27} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 39} | {'precision': 0.6666666666666666, 'recall': 0.16666666666666666, 'f1': 0.26666666666666666, 'number': 36} | 0.1207 | 0.0556 | 0.0761 | 0.9863 | | |
| | 0.0469 | 4.0 | 60 | 0.0345 | {'precision': 0.14285714285714285, 'recall': 0.25, 'f1': 0.18181818181818182, 'number': 24} | {'precision': 0.875, 'recall': 0.25925925925925924, 'f1': 0.39999999999999997, 'number': 27} | {'precision': 0.34146341463414637, 'recall': 0.358974358974359, 'f1': 0.35000000000000003, 'number': 39} | {'precision': 0.5454545454545454, 'recall': 0.6666666666666666, 'f1': 0.6, 'number': 36} | 0.3778 | 0.4048 | 0.3908 | 0.9910 | | |
| | 0.0327 | 5.0 | 75 | 0.0232 | {'precision': 0.07692307692307693, 'recall': 0.08333333333333333, 'f1': 0.08, 'number': 24} | {'precision': 0.7, 'recall': 0.7777777777777778, 'f1': 0.7368421052631577, 'number': 27} | {'precision': 0.8333333333333334, 'recall': 0.8974358974358975, 'f1': 0.8641975308641975, 'number': 39} | {'precision': 0.5, 'recall': 0.8055555555555556, 'f1': 0.6170212765957447, 'number': 36} | 0.5577 | 0.6905 | 0.6170 | 0.9943 | | |
| | 0.0224 | 6.0 | 90 | 0.0168 | {'precision': 0.16, 'recall': 0.16666666666666666, 'f1': 0.16326530612244897, 'number': 24} | {'precision': 0.6363636363636364, 'recall': 0.7777777777777778, 'f1': 0.7000000000000001, 'number': 27} | {'precision': 0.875, 'recall': 0.8974358974358975, 'f1': 0.8860759493670887, 'number': 39} | {'precision': 0.5576923076923077, 'recall': 0.8055555555555556, 'f1': 0.6590909090909091, 'number': 36} | 0.5933 | 0.7063 | 0.6449 | 0.9961 | | |
| | 0.0163 | 7.0 | 105 | 0.0119 | {'precision': 0.84, 'recall': 0.875, 'f1': 0.8571428571428572, 'number': 24} | {'precision': 0.7857142857142857, 'recall': 0.8148148148148148, 'f1': 0.7999999999999999, 'number': 27} | {'precision': 0.9024390243902439, 'recall': 0.9487179487179487, 'f1': 0.9249999999999999, 'number': 39} | {'precision': 0.7073170731707317, 'recall': 0.8055555555555556, 'f1': 0.7532467532467532, 'number': 36} | 0.8074 | 0.8651 | 0.8352 | 0.9981 | | |
| | 0.012 | 8.0 | 120 | 0.0100 | {'precision': 0.84, 'recall': 0.875, 'f1': 0.8571428571428572, 'number': 24} | {'precision': 0.7931034482758621, 'recall': 0.8518518518518519, 'f1': 0.8214285714285715, 'number': 27} | {'precision': 0.8809523809523809, 'recall': 0.9487179487179487, 'f1': 0.9135802469135802, 'number': 39} | {'precision': 0.7948717948717948, 'recall': 0.8611111111111112, 'f1': 0.8266666666666667, 'number': 36} | 0.8296 | 0.8889 | 0.8582 | 0.9981 | | |
| | 0.0097 | 9.0 | 135 | 0.0093 | {'precision': 0.8333333333333334, 'recall': 0.8333333333333334, 'f1': 0.8333333333333334, 'number': 24} | {'precision': 0.7931034482758621, 'recall': 0.8518518518518519, 'f1': 0.8214285714285715, 'number': 27} | {'precision': 0.9024390243902439, 'recall': 0.9487179487179487, 'f1': 0.9249999999999999, 'number': 39} | {'precision': 0.6904761904761905, 'recall': 0.8055555555555556, 'f1': 0.7435897435897436, 'number': 36} | 0.8015 | 0.8651 | 0.8321 | 0.9984 | | |
| | 0.0077 | 10.0 | 150 | 0.0079 | {'precision': 0.88, 'recall': 0.9166666666666666, 'f1': 0.8979591836734694, 'number': 24} | {'precision': 0.8214285714285714, 'recall': 0.8518518518518519, 'f1': 0.8363636363636364, 'number': 27} | {'precision': 0.925, 'recall': 0.9487179487179487, 'f1': 0.9367088607594937, 'number': 39} | {'precision': 0.7948717948717948, 'recall': 0.8611111111111112, 'f1': 0.8266666666666667, 'number': 36} | 0.8561 | 0.8968 | 0.8760 | 0.9987 | | |
| | 0.0069 | 11.0 | 165 | 0.0084 | {'precision': 0.7916666666666666, 'recall': 0.7916666666666666, 'f1': 0.7916666666666666, 'number': 24} | {'precision': 0.7931034482758621, 'recall': 0.8518518518518519, 'f1': 0.8214285714285715, 'number': 27} | {'precision': 0.926829268292683, 'recall': 0.9743589743589743, 'f1': 0.9500000000000001, 'number': 39} | {'precision': 0.7948717948717948, 'recall': 0.8611111111111112, 'f1': 0.8266666666666667, 'number': 36} | 0.8346 | 0.8810 | 0.8571 | 0.9986 | | |
| | 0.0066 | 12.0 | 180 | 0.0079 | {'precision': 0.8333333333333334, 'recall': 0.8333333333333334, 'f1': 0.8333333333333334, 'number': 24} | {'precision': 0.8214285714285714, 'recall': 0.8518518518518519, 'f1': 0.8363636363636364, 'number': 27} | {'precision': 0.9047619047619048, 'recall': 0.9743589743589743, 'f1': 0.9382716049382716, 'number': 39} | {'precision': 0.8157894736842105, 'recall': 0.8611111111111112, 'f1': 0.8378378378378377, 'number': 36} | 0.8485 | 0.8889 | 0.8682 | 0.9986 | | |
| | 0.0058 | 13.0 | 195 | 0.0079 | {'precision': 0.84, 'recall': 0.875, 'f1': 0.8571428571428572, 'number': 24} | {'precision': 0.8214285714285714, 'recall': 0.8518518518518519, 'f1': 0.8363636363636364, 'number': 27} | {'precision': 0.9047619047619048, 'recall': 0.9743589743589743, 'f1': 0.9382716049382716, 'number': 39} | {'precision': 0.8378378378378378, 'recall': 0.8611111111111112, 'f1': 0.8493150684931507, 'number': 36} | 0.8561 | 0.8968 | 0.8760 | 0.9989 | | |
| | 0.0054 | 14.0 | 210 | 0.0077 | {'precision': 0.9166666666666666, 'recall': 0.9166666666666666, 'f1': 0.9166666666666666, 'number': 24} | {'precision': 0.8214285714285714, 'recall': 0.8518518518518519, 'f1': 0.8363636363636364, 'number': 27} | {'precision': 0.926829268292683, 'recall': 0.9743589743589743, 'f1': 0.9500000000000001, 'number': 39} | {'precision': 0.8378378378378378, 'recall': 0.8611111111111112, 'f1': 0.8493150684931507, 'number': 36} | 0.8769 | 0.9048 | 0.8906 | 0.9989 | | |
| | 0.0053 | 15.0 | 225 | 0.0076 | {'precision': 0.9166666666666666, 'recall': 0.9166666666666666, 'f1': 0.9166666666666666, 'number': 24} | {'precision': 0.8214285714285714, 'recall': 0.8518518518518519, 'f1': 0.8363636363636364, 'number': 27} | {'precision': 0.926829268292683, 'recall': 0.9743589743589743, 'f1': 0.9500000000000001, 'number': 39} | {'precision': 0.8378378378378378, 'recall': 0.8611111111111112, 'f1': 0.8493150684931507, 'number': 36} | 0.8769 | 0.9048 | 0.8906 | 0.9989 | | |
| ### Framework versions | |
| - Transformers 4.28.0 | |
| - Pytorch 2.0.1+cu118 | |
| - Datasets 2.14.5 | |
| - Tokenizers 0.13.3 | |