metadata
license: mit
base_model: microsoft/layoutlm-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: stevethecur/layoutlm-funsd-tf
results: []
stevethecur/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: 0.7200
- Validation Loss: 0.9883
- Train Overall Precision: 0.4845
- Train Overall Recall: 0.5720
- Train Overall F1: 0.5246
- Train Overall Accuracy: 0.6381
- 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 |
|---|---|---|---|---|---|---|
| 1.7553 | 1.6258 | 0.2306 | 0.1134 | 0.1520 | 0.3303 | 0 |
| 1.4401 | 1.3407 | 0.2930 | 0.4797 | 0.3638 | 0.4365 | 1 |
| 1.2104 | 1.2996 | 0.3092 | 0.4977 | 0.3815 | 0.4740 | 2 |
| 1.0651 | 1.0411 | 0.3652 | 0.5233 | 0.4302 | 0.5949 | 3 |
| 0.9605 | 0.9755 | 0.4209 | 0.5329 | 0.4703 | 0.6064 | 4 |
| 0.8846 | 1.0042 | 0.4473 | 0.5620 | 0.4981 | 0.6270 | 5 |
| 0.7200 | 0.9883 | 0.4845 | 0.5720 | 0.5246 | 0.6381 | 6 |
Framework versions
- Transformers 4.37.2
- TensorFlow 2.15.0
- Datasets 2.17.0
- Tokenizers 0.15.2