<!-- 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. -->
LovenOO/distilBERT_with_preprocessing
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.2890
- Validation Loss: 0.6104
- Train Accuracy: 0.8264
- Epoch: 5
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': 'Adam', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2545, '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}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|---|---|---|---|
| 0.6308 | 0.6631 | 0.8136 | 0 |
| 0.4767 | 0.6222 | 0.8264 | 1 |
| 0.3731 | 0.6148 | 0.8308 | 2 |
| 0.3117 | 0.6104 | 0.8264 | 3 |
| 0.2875 | 0.6104 | 0.8264 | 4 |
| 0.2890 | 0.6104 | 0.8264 | 5 |
Framework versions
- Transformers 4.24.0
- TensorFlow 2.13.0
- Datasets 2.14.2
- Tokenizers 0.11.0
