<!-- 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. -->
eduardopds/distilbert-base-uncased-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: 0.7428
- Validation Loss: 0.9322
- 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': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 310, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, '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 | Epoch |
|---|---|---|
| 1.0162 | 1.0010 | 0 |
| 0.9552 | 0.9574 | 1 |
| 0.8928 | 0.9393 | 2 |
| 0.8238 | 0.9412 | 3 |
| 0.7581 | 0.9322 | 4 |
| 0.7268 | 0.9322 | 5 |
| 0.7310 | 0.9322 | 6 |
| 0.7390 | 0.9322 | 7 |
| 0.7423 | 0.9322 | 8 |
| 0.7428 | 0.9322 | 9 |
Framework versions
- Transformers 4.19.2
- TensorFlow 2.8.0
- Datasets 2.2.2
- Tokenizers 0.12.1
