---
license: mit
base_model: microsoft/layoutlm-base-uncased
tags:
- generated_from_trainer
datasets:
- layoutlmv4
model-index:
- name: layoutlm_alltags
  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_alltags

This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on the layoutlmv4 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0891
- Customer Address: {'precision': 0.7764705882352941, 'recall': 0.8048780487804879, 'f1': 0.7904191616766466, 'number': 82}
- Customer Name: {'precision': 0.6666666666666666, 'recall': 0.8333333333333334, 'f1': 0.7407407407407408, 'number': 12}
- Invoice Number: {'precision': 0.8571428571428571, 'recall': 1.0, 'f1': 0.923076923076923, 'number': 12}
- Tax Amount: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2}
- Total Amount: {'precision': 0.7142857142857143, 'recall': 0.9090909090909091, 'f1': 0.8, 'number': 11}
- Vendor Name: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12}
- Overall Precision: 0.7857
- Overall Recall: 0.8397
- Overall F1: 0.8118
- Overall Accuracy: 0.9801

## 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: 50

### Training results

| Training Loss | Epoch | Step | Validation Loss | Customer Address                                                                                           | Customer Name                                                                                            | Invoice Number                                                                                          | Tax Amount                                                | Total Amount                                                                             | Vendor Name                                                                                             | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:----------------------------------------------------------------------------------------------------------:|:--------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------:|:----------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
| 0.8211        | 6.67  | 20   | 0.3797          | {'precision': 0.25316455696202533, 'recall': 0.24390243902439024, 'f1': 0.24844720496894412, 'number': 82} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}                                               | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}                                              | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 11}                               | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}                                              | 0.2532            | 0.1527         | 0.1905     | 0.9050           |
| 0.3036        | 13.33 | 40   | 0.1941          | {'precision': 0.6448598130841121, 'recall': 0.8414634146341463, 'f1': 0.73015873015873, 'number': 82}      | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}                                               | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 12}                                              | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 11}                               | {'precision': 0.75, 'recall': 0.75, 'f1': 0.75, 'number': 12}                                           | 0.6555            | 0.5954         | 0.624      | 0.9493           |
| 0.1537        | 20.0  | 60   | 0.1153          | {'precision': 0.7157894736842105, 'recall': 0.8292682926829268, 'f1': 0.768361581920904, 'number': 82}     | {'precision': 0.35714285714285715, 'recall': 0.4166666666666667, 'f1': 0.3846153846153846, 'number': 12} | {'precision': 0.8461538461538461, 'recall': 0.9166666666666666, 'f1': 0.8799999999999999, 'number': 12} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 11}                               | {'precision': 0.8461538461538461, 'recall': 0.9166666666666666, 'f1': 0.8799999999999999, 'number': 12} | 0.7037            | 0.7252         | 0.7143     | 0.9663           |
| 0.0862        | 26.67 | 80   | 0.0953          | {'precision': 0.8, 'recall': 0.8292682926829268, 'f1': 0.8143712574850299, 'number': 82}                   | {'precision': 0.6, 'recall': 0.75, 'f1': 0.6666666666666665, 'number': 12}                               | {'precision': 0.6666666666666666, 'recall': 1.0, 'f1': 0.8, 'number': 12}                               | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 11}                               | {'precision': 0.9166666666666666, 'recall': 0.9166666666666666, 'f1': 0.9166666666666666, 'number': 12} | 0.7519            | 0.7634         | 0.7576     | 0.9757           |
| 0.0509        | 33.33 | 100  | 0.0846          | {'precision': 0.7857142857142857, 'recall': 0.8048780487804879, 'f1': 0.7951807228915663, 'number': 82}    | {'precision': 0.7333333333333333, 'recall': 0.9166666666666666, 'f1': 0.8148148148148148, 'number': 12}  | {'precision': 0.8571428571428571, 'recall': 1.0, 'f1': 0.923076923076923, 'number': 12}                 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 1.0, 'recall': 0.5454545454545454, 'f1': 0.7058823529411764, 'number': 11} | {'precision': 0.8461538461538461, 'recall': 0.9166666666666666, 'f1': 0.8799999999999999, 'number': 12} | 0.8030            | 0.8092         | 0.8061     | 0.9775           |
| 0.0354        | 40.0  | 120  | 0.0852          | {'precision': 0.7710843373493976, 'recall': 0.7804878048780488, 'f1': 0.7757575757575758, 'number': 82}    | {'precision': 0.6666666666666666, 'recall': 0.8333333333333334, 'f1': 0.7407407407407408, 'number': 12}  | {'precision': 0.8, 'recall': 1.0, 'f1': 0.888888888888889, 'number': 12}                                | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.7142857142857143, 'recall': 0.9090909090909091, 'f1': 0.8, 'number': 11} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12}                                              | 0.7770            | 0.8244         | 0.8        | 0.9797           |
| 0.0297        | 46.67 | 140  | 0.0891          | {'precision': 0.7764705882352941, 'recall': 0.8048780487804879, 'f1': 0.7904191616766466, 'number': 82}    | {'precision': 0.6666666666666666, 'recall': 0.8333333333333334, 'f1': 0.7407407407407408, 'number': 12}  | {'precision': 0.8571428571428571, 'recall': 1.0, 'f1': 0.923076923076923, 'number': 12}                 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 2} | {'precision': 0.7142857142857143, 'recall': 0.9090909090909091, 'f1': 0.8, 'number': 11} | {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 12}                                              | 0.7857            | 0.8397         | 0.8118     | 0.9801           |


### Framework versions

- Transformers 4.32.1
- Pytorch 2.2.0+cpu
- Datasets 2.12.0
- Tokenizers 0.13.2