metadata
license: mit
tags:
- generated_from_keras_callback
base_model: microsoft/layoutlm-base-uncased
model-index:
- name: layoutlm-invoice-tf
results: []
layoutlm-invoice-tf
This model is a fine-tuned version of microsoft/layoutlm-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.2904
- Validation Loss: 0.3563
- Train Overall Precision: 0.5792
- Train Overall Recall: 0.5340
- Train Overall F1: 0.5557
- Train Overall Accuracy: 0.8995
- Epoch: 7
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: {'name': 'AdamWeightDecay', 'learning_rate': 3e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: mixed_float16
Training results
| Train Loss | Validation Loss | Train Overall Precision | Train Overall Recall | Train Overall F1 | Train Overall Accuracy | Epoch |
|---|---|---|---|---|---|---|
| 2.3852 | 2.0674 | 0.0 | 0.0 | 0.0 | 0.2968 | 0 |
| 1.8171 | 1.5521 | 0.0108 | 0.0202 | 0.0141 | 0.5448 | 1 |
| 1.3443 | 1.1118 | 0.0736 | 0.1108 | 0.0884 | 0.6812 | 2 |
| 0.9892 | 0.8281 | 0.1794 | 0.2191 | 0.1973 | 0.7733 | 3 |
| 0.7126 | 0.6356 | 0.3009 | 0.3199 | 0.3101 | 0.8324 | 4 |
| 0.5465 | 0.4954 | 0.4051 | 0.3980 | 0.4015 | 0.8606 | 5 |
| 0.3916 | 0.4266 | 0.4813 | 0.4534 | 0.4669 | 0.8778 | 6 |
| 0.2904 | 0.3563 | 0.5792 | 0.5340 | 0.5557 | 0.8995 | 7 |
Framework versions
- Transformers 4.41.0.dev0
- TensorFlow 2.16.1
- Datasets 2.19.1
- Tokenizers 0.19.1