<!-- 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. -->
mmiteva/distilbert-base-uncased-customized
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: 0.3257
- Train End Logits Accuracy: 0.9017
- Train Start Logits Accuracy: 0.8747
- Validation Loss: 1.5040
- Validation End Logits Accuracy: 0.6988
- Validation Start Logits Accuracy: 0.6655
- 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': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 36885, '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 | Train End Logits Accuracy | Train Start Logits Accuracy | Validation Loss | Validation End Logits Accuracy | Validation Start Logits Accuracy | Epoch |
|---|---|---|---|---|---|---|
| 1.0773 | 0.7064 | 0.6669 | 1.1080 | 0.6973 | 0.6669 | 0 |
| 0.7660 | 0.7812 | 0.7433 | 1.1076 | 0.7093 | 0.6734 | 1 |
| 0.5586 | 0.8351 | 0.7988 | 1.2336 | 0.7039 | 0.6692 | 2 |
| 0.4165 | 0.8741 | 0.8434 | 1.3799 | 0.7034 | 0.6707 | 3 |
| 0.3257 | 0.9017 | 0.8747 | 1.5040 | 0.6988 | 0.6655 | 4 |
Framework versions
- Transformers 4.25.0.dev0
- TensorFlow 2.7.0
- Datasets 2.6.1
- Tokenizers 0.13.2
