metadata
license: mit
tags:
- generated_from_keras_callback
base_model: microsoft/layoutlm-base-uncased
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: 0.2395
- Validation Loss: 0.6723
- Train Overall Precision: 0.7269
- Train Overall Recall: 0.8013
- Train Overall F1: 0.7623
- Train Overall Accuracy: 0.8071
- 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 |
---|---|---|---|---|---|---|
1.6854 | 1.3883 | 0.2671 | 0.2494 | 0.2579 | 0.4942 | 0 |
1.1172 | 0.8636 | 0.5871 | 0.6392 | 0.6121 | 0.7287 | 1 |
0.7701 | 0.7274 | 0.6558 | 0.7170 | 0.6850 | 0.7690 | 2 |
0.5880 | 0.6978 | 0.6814 | 0.7501 | 0.7141 | 0.7747 | 3 |
0.4569 | 0.7022 | 0.6984 | 0.7612 | 0.7285 | 0.7710 | 4 |
0.3594 | 0.6280 | 0.7095 | 0.7903 | 0.7477 | 0.8118 | 5 |
0.3095 | 0.6566 | 0.7298 | 0.7832 | 0.7556 | 0.8085 | 6 |
0.2395 | 0.6723 | 0.7269 | 0.8013 | 0.7623 | 0.8071 | 7 |
Framework versions
- Transformers 4.41.2
- TensorFlow 2.16.1
- Datasets 2.19.2
- Tokenizers 0.19.1