<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->
kasrahabib/bert-base-cased-S8-SMELL-DETECTOR
This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0003
- Validation Loss: 0.0048
- Train Precision: 0.9940
- Train Recall: 0.9947
- Train F1: 0.9943
- Train Accuracy: 0.9992
- Epoch: 9
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': 9330, '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 |
|---|---|---|---|---|---|---|
| 0.0758 | 0.0114 | 0.9900 | 0.9779 | 0.9839 | 0.9977 | 0 |
| 0.0095 | 0.0074 | 0.9863 | 0.9891 | 0.9877 | 0.9984 | 1 |
| 0.0052 | 0.0052 | 0.9904 | 0.9929 | 0.9917 | 0.9988 | 2 |
| 0.0028 | 0.0056 | 0.9882 | 0.9937 | 0.9910 | 0.9988 | 3 |
| 0.0019 | 0.0046 | 0.9935 | 0.9939 | 0.9937 | 0.9991 | 4 |
| 0.0012 | 0.0046 | 0.9936 | 0.9931 | 0.9933 | 0.9991 | 5 |
| 0.0008 | 0.0045 | 0.9945 | 0.9935 | 0.9940 | 0.9992 | 6 |
| 0.0006 | 0.0046 | 0.9945 | 0.9945 | 0.9945 | 0.9992 | 7 |
| 0.0005 | 0.0045 | 0.9942 | 0.9948 | 0.9945 | 0.9992 | 8 |
| 0.0003 | 0.0048 | 0.9940 | 0.9947 | 0.9943 | 0.9992 | 9 |
Framework versions
- Transformers 4.33.1
- TensorFlow 2.14.0
- Datasets 2.14.4
- Tokenizers 0.13.3
