metadata
license: mit
base_model: microsoft/layoutlm-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: layoutlm-cord-tf
results: []
layoutlm-cord-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: 0.0379
- Validation Loss: 0.1673
- Train Overall Precision: 0.9428
- Train Overall Recall: 0.9528
- Train Overall F1: 0.9478
- Train Overall Accuracy: 0.9605
- 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 |
|---|---|---|---|---|---|---|
| 1.2812 | 0.5563 | 0.8209 | 0.8265 | 0.8237 | 0.8574 | 0 |
| 0.3842 | 0.2602 | 0.9121 | 0.9155 | 0.9138 | 0.9406 | 1 |
| 0.2075 | 0.2085 | 0.9257 | 0.9201 | 0.9229 | 0.9453 | 2 |
| 0.1377 | 0.1793 | 0.9368 | 0.9368 | 0.9368 | 0.9555 | 3 |
| 0.0889 | 0.1902 | 0.9282 | 0.9346 | 0.9314 | 0.9525 | 4 |
| 0.0747 | 0.1610 | 0.9455 | 0.9513 | 0.9484 | 0.9648 | 5 |
| 0.0514 | 0.1796 | 0.9480 | 0.9566 | 0.9523 | 0.9639 | 6 |
| 0.0379 | 0.1673 | 0.9428 | 0.9528 | 0.9478 | 0.9605 | 7 |
Framework versions
- Transformers 4.41.0.dev0
- TensorFlow 2.16.1
- Datasets 2.19.1
- Tokenizers 0.19.1