<!-- 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. -->
disilbert-blm-tweets
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: 0.0857
- Train Accuracy: 0.9790
- Validation Loss: 1.7704
- Validation Accuracy: 0.5973
- 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': 'Adam', 'learning_rate': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 1.2590 | 0.5746 | 1.1456 | 0.6460 | 0 |
| 1.0110 | 0.6930 | 1.2198 | 0.6106 | 1 |
| 0.7538 | 0.7633 | 1.2087 | 0.6327 | 2 |
| 0.4794 | 0.8520 | 1.2903 | 0.6239 | 3 |
| 0.3100 | 0.9162 | 1.4110 | 0.6106 | 4 |
| 0.2005 | 0.9482 | 1.6042 | 0.5487 | 5 |
| 0.1174 | 0.9753 | 1.6328 | 0.6018 | 6 |
| 0.0857 | 0.9790 | 1.7704 | 0.5973 | 7 |
Framework versions
- Transformers 4.25.1
- TensorFlow 2.9.2
- Tokenizers 0.13.2
