Sidziesama/Legal_NER_Support_Model
This model is a fine-tuned version of nlpaueb/legal-bert-base-uncased on opennyaiorg/InLegalNER. It achieves the following results on the evaluation set:
- Train Loss: 0.0501
- Validation Loss: 0.0883
- Train Precision: 0.8848
- Train Recall: 0.9160
- Train F1: 0.9001
- Train Accuracy: 0.9757
- Epoch: 4
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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2945, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
|---|---|---|---|---|---|---|
| 0.3771 | 0.1228 | 0.8400 | 0.8644 | 0.8520 | 0.9655 | 0 |
| 0.1172 | 0.0962 | 0.8715 | 0.9001 | 0.8856 | 0.9725 | 1 |
| 0.0801 | 0.0895 | 0.8805 | 0.9112 | 0.8956 | 0.9745 | 2 |
| 0.0597 | 0.0881 | 0.8840 | 0.9112 | 0.8974 | 0.9751 | 3 |
| 0.0501 | 0.0883 | 0.8848 | 0.9160 | 0.9001 | 0.9757 | 4 |
Framework versions
- Transformers 4.39.3
- TensorFlow 2.15.0
- Datasets 2.18.0
- Tokenizers 0.15.2