---
license: mit
base_model: microsoft/layoutlm-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: Matt6450/layoutlm-funsd-tf
  results: []
---

<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->

# Matt6450/layoutlm-funsd-tf

This model is a fine-tuned version of [microsoft/layoutlm-base-uncased](https://huggingface.co/microsoft/layoutlm-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.0288
- Validation Loss: 0.9539
- Train Overall Precision: 0.7396
- Train Overall Recall: 0.7993
- Train Overall F1: 0.7683
- Train Overall Accuracy: 0.8033
- Epoch: 30

## 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:
- optimizer: {'inner_optimizer': {'module': 'transformers.optimization_tf', 'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': 1.9999999494757503e-05, 'decay': 0.0, 'beta_1': 0.8999999761581421, 'beta_2': 0.9990000128746033, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}, 'registered_name': 'AdamWeightDecay'}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
- training_precision: mixed_float16

### Training results

| Train Loss | Validation Loss | Train Overall Precision | Train Overall Recall | Train Overall F1 | Train Overall Accuracy | Epoch |
|:----------:|:---------------:|:-----------------------:|:--------------------:|:----------------:|:----------------------:|:-----:|
| 1.8669     | 1.6316          | 0.0652                  | 0.0502               | 0.0567           | 0.3485                 | 0     |
| 1.4744     | 1.2571          | 0.3367                  | 0.3713               | 0.3531           | 0.5765                 | 1     |
| 1.0656     | 0.8828          | 0.5626                  | 0.6558               | 0.6057           | 0.7195                 | 2     |
| 0.7471     | 0.7163          | 0.6412                  | 0.7316               | 0.6834           | 0.7796                 | 3     |
| 0.5953     | 0.6687          | 0.6734                  | 0.7551               | 0.7119           | 0.7859                 | 4     |
| 0.4769     | 0.6592          | 0.6901                  | 0.7777               | 0.7313           | 0.7923                 | 5     |
| 0.4094     | 0.6528          | 0.6892                  | 0.7943               | 0.7380           | 0.7966                 | 6     |
| 0.3595     | 0.6589          | 0.6849                  | 0.7863               | 0.7321           | 0.7947                 | 7     |
| 0.3063     | 0.6460          | 0.7165                  | 0.7978               | 0.7550           | 0.8083                 | 8     |
| 0.2523     | 0.6828          | 0.7134                  | 0.7968               | 0.7528           | 0.8039                 | 9     |
| 0.2228     | 0.6844          | 0.7355                  | 0.8008               | 0.7668           | 0.8150                 | 10    |
| 0.1918     | 0.7142          | 0.7298                  | 0.8023               | 0.7643           | 0.8020                 | 11    |
| 0.1679     | 0.7069          | 0.7477                  | 0.7998               | 0.7728           | 0.8138                 | 12    |
| 0.1482     | 0.7370          | 0.7421                  | 0.7983               | 0.7692           | 0.8096                 | 13    |
| 0.1209     | 0.7565          | 0.7427                  | 0.8138               | 0.7766           | 0.8095                 | 14    |
| 0.1133     | 0.7794          | 0.7466                  | 0.8144               | 0.7790           | 0.8080                 | 15    |
| 0.0981     | 0.7905          | 0.7461                  | 0.8078               | 0.7757           | 0.8083                 | 16    |
| 0.0912     | 0.8182          | 0.7388                  | 0.8073               | 0.7715           | 0.8096                 | 17    |
| 0.0812     | 0.7953          | 0.7566                  | 0.8048               | 0.7800           | 0.8164                 | 18    |
| 0.0723     | 0.8192          | 0.7604                  | 0.8043               | 0.7818           | 0.8122                 | 19    |
| 0.0657     | 0.8495          | 0.7491                  | 0.8179               | 0.7820           | 0.8068                 | 20    |
| 0.0660     | 0.8259          | 0.7536                  | 0.7963               | 0.7743           | 0.8139                 | 21    |
| 0.0553     | 0.8820          | 0.7443                  | 0.7903               | 0.7666           | 0.8007                 | 22    |
| 0.0575     | 0.8470          | 0.7510                  | 0.8098               | 0.7793           | 0.8102                 | 23    |
| 0.0445     | 0.8824          | 0.7395                  | 0.7878               | 0.7629           | 0.8066                 | 24    |
| 0.0421     | 0.8925          | 0.7546                  | 0.7993               | 0.7763           | 0.8117                 | 25    |
| 0.0387     | 0.9253          | 0.7537                  | 0.7968               | 0.7746           | 0.8033                 | 26    |
| 0.0399     | 0.9226          | 0.7422                  | 0.8018               | 0.7709           | 0.8026                 | 27    |
| 0.0396     | 0.9753          | 0.75                    | 0.8023               | 0.7753           | 0.7968                 | 28    |
| 0.0327     | 0.9237          | 0.7462                  | 0.8038               | 0.7739           | 0.8076                 | 29    |
| 0.0288     | 0.9539          | 0.7396                  | 0.7993               | 0.7683           | 0.8033                 | 30    |


### Framework versions

- Transformers 4.35.2
- TensorFlow 2.15.0
- Datasets 2.16.1
- Tokenizers 0.15.1