metadata
base_model: microsoft/layoutlm-base-uncased
license: mit
tags:
- generated_from_keras_callback
model-index:
- name: layoutlm-cord-tf-colab
results: []
layoutlm-cord-tf-colab
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: 0.0426
- Validation Loss: 0.1530
- Train Overall Precision: 0.9498
- Train Overall Recall: 0.9642
- Train Overall F1: 0.9569
- Train Overall Accuracy: 0.9669
- 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: {'inner_optimizer': {'module': 'transformers.optimization_tf', 'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': 2.9999999242136255e-05, 'decay': 0.0, 'beta_1': 0.8999999761581421, 'beta_2': 0.9990000128746033, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}, 'registered_name': 'AdamWeightDecay'}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
- training_precision: mixed_float16
Training results
| Train Loss | Validation Loss | Train Overall Precision | Train Overall Recall | Train Overall F1 | Train Overall Accuracy | Epoch |
|---|---|---|---|---|---|---|
| 1.3249 | 0.5218 | 0.8344 | 0.8318 | 0.8331 | 0.8744 | 0 |
| 0.4002 | 0.2680 | 0.9113 | 0.9148 | 0.9130 | 0.9334 | 1 |
| 0.2153 | 0.2180 | 0.9062 | 0.9193 | 0.9127 | 0.9448 | 2 |
| 0.1483 | 0.1840 | 0.9430 | 0.9437 | 0.9433 | 0.9610 | 3 |
| 0.0940 | 0.1687 | 0.9383 | 0.9482 | 0.9432 | 0.9614 | 4 |
| 0.0740 | 0.1539 | 0.9463 | 0.9528 | 0.9496 | 0.9665 | 5 |
| 0.0600 | 0.1795 | 0.9355 | 0.9498 | 0.9426 | 0.9584 | 6 |
| 0.0426 | 0.1530 | 0.9498 | 0.9642 | 0.9569 | 0.9669 | 7 |
Framework versions
- Transformers 4.41.2
- TensorFlow 2.15.0
- Datasets 2.20.0
- Tokenizers 0.19.1