metadata
license: mit
base_model: microsoft/layoutlm-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: layoutlm-funsd-tf
results: []
layoutlm-funsd-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: 0.2473
- Validation Loss: 0.6721
- Train Overall Precision: 0.7140
- Train Overall Recall: 0.8043
- Train Overall F1: 0.7565
- Train Overall Accuracy: 0.8076
- 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 |
|---|---|---|---|---|---|---|
| 1.7381 | 1.4132 | 0.2537 | 0.2935 | 0.2722 | 0.5348 | 0 |
| 1.2080 | 0.9561 | 0.5655 | 0.5981 | 0.5813 | 0.7060 | 1 |
| 0.8008 | 0.7159 | 0.6477 | 0.7371 | 0.6895 | 0.7727 | 2 |
| 0.6021 | 0.6365 | 0.6928 | 0.7772 | 0.7326 | 0.7984 | 3 |
| 0.4729 | 0.6242 | 0.6833 | 0.7923 | 0.7337 | 0.8067 | 4 |
| 0.3818 | 0.6040 | 0.7164 | 0.7832 | 0.7483 | 0.8131 | 5 |
| 0.3024 | 0.6533 | 0.7177 | 0.8048 | 0.7588 | 0.8074 | 6 |
| 0.2473 | 0.6721 | 0.7140 | 0.8043 | 0.7565 | 0.8076 | 7 |
Framework versions
- Transformers 4.35.2
- TensorFlow 2.15.0
- Datasets 2.16.1
- Tokenizers 0.15.0