metadata
license: mit
base_model: microsoft/layoutlm-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: vfbsilva/layoutlm-funsd-tf
results: []
vfbsilva/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: 0.7170
- Validation Loss: 1.1978
- Train Overall Precision: 0.4534
- Train Overall Recall: 0.5660
- Train Overall F1: 0.5035
- Train Overall Accuracy: 0.6193
- Epoch: 6
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 |
|---|---|---|---|---|---|---|
| 1.6558 | 1.4251 | 0.2107 | 0.3332 | 0.2581 | 0.4092 | 0 |
| 1.3215 | 1.2372 | 0.3024 | 0.4696 | 0.3679 | 0.4742 | 1 |
| 1.1454 | 1.2395 | 0.3329 | 0.4782 | 0.3925 | 0.4779 | 2 |
| 1.0421 | 1.1025 | 0.3771 | 0.5263 | 0.4394 | 0.6005 | 3 |
| 0.9349 | 1.1771 | 0.3860 | 0.5610 | 0.4574 | 0.5416 | 4 |
| 0.8505 | 1.0244 | 0.4657 | 0.5685 | 0.5120 | 0.6265 | 5 |
| 0.7170 | 1.1978 | 0.4534 | 0.5660 | 0.5035 | 0.6193 | 6 |
Framework versions
- Transformers 4.33.3
- TensorFlow 2.10.0
- Datasets 2.16.1
- Tokenizers 0.13.2