<!-- 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. -->
ratish/DBERT_Fault_LR_v2
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: 0.4241
- Validation Loss: 0.5145
- Train Accuracy: 0.7692
- Epoch: 14
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', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-06, 'decay_steps': 2128, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, '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 |
|---|---|---|---|
| 0.6872 | 0.6932 | 0.5128 | 0 |
| 0.6761 | 0.6965 | 0.5128 | 1 |
| 0.6638 | 0.7020 | 0.5128 | 2 |
| 0.6590 | 0.7093 | 0.5128 | 3 |
| 0.6532 | 0.7112 | 0.5128 | 4 |
| 0.6469 | 0.7067 | 0.5128 | 5 |
| 0.6359 | 0.7101 | 0.5128 | 6 |
| 0.6236 | 0.7103 | 0.5128 | 7 |
| 0.6120 | 0.6865 | 0.5641 | 8 |
| 0.5913 | 0.6576 | 0.5641 | 9 |
| 0.5618 | 0.6206 | 0.5897 | 10 |
| 0.5286 | 0.5765 | 0.5897 | 11 |
| 0.4931 | 0.5502 | 0.6667 | 12 |
| 0.4574 | 0.5154 | 0.7692 | 13 |
| 0.4241 | 0.5145 | 0.7692 | 14 |
Framework versions
- Transformers 4.28.1
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
