<!-- 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. -->
layout_lm_fine_tune_funsd_dataset
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: 0.2499
- Validation Loss: 0.6927
- Train Overall Precision: 0.7401
- Train Overall Recall: 0.8159
- Train Overall F1: 0.7761
- Train Overall Accuracy: 0.8046
- 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 |
|---|---|---|---|---|---|---|
| 1.7326 | 1.4249 | 0.2261 | 0.2052 | 0.2151 | 0.5250 | 0 |
| 1.1901 | 0.9108 | 0.5753 | 0.6207 | 0.5972 | 0.7156 | 1 |
| 0.7777 | 0.7170 | 0.6511 | 0.7396 | 0.6925 | 0.7679 | 2 |
| 0.5681 | 0.6626 | 0.6988 | 0.7777 | 0.7362 | 0.7920 | 3 |
| 0.4449 | 0.6512 | 0.7236 | 0.7762 | 0.7490 | 0.8013 | 4 |
| 0.3576 | 0.6547 | 0.7251 | 0.7888 | 0.7556 | 0.8073 | 5 |
| 0.2910 | 0.6700 | 0.7380 | 0.7958 | 0.7658 | 0.8106 | 6 |
| 0.2499 | 0.6927 | 0.7401 | 0.8159 | 0.7761 | 0.8046 | 7 |
Framework versions
- Transformers 4.28.1
- TensorFlow 2.12.0
- Datasets 2.11.0
- Tokenizers 0.13.3
