<!-- 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. -->
kaus-rai/intent_classification
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: 0.0088
- Validation Loss: 0.0150
- Train Accuracy: 0.9985
- Epoch: 19
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': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 570, '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 |
|---|---|---|---|
| 0.3981 | 0.0496 | 0.9985 | 0 |
| 0.0332 | 0.0224 | 0.9985 | 1 |
| 0.0155 | 0.0172 | 0.9985 | 2 |
| 0.0108 | 0.0154 | 0.9985 | 3 |
| 0.0090 | 0.0150 | 0.9985 | 4 |
| 0.0088 | 0.0150 | 0.9985 | 5 |
| 0.0088 | 0.0150 | 0.9985 | 6 |
| 0.0087 | 0.0150 | 0.9985 | 7 |
| 0.0088 | 0.0150 | 0.9985 | 8 |
| 0.0088 | 0.0150 | 0.9985 | 9 |
| 0.0087 | 0.0150 | 0.9985 | 10 |
| 0.0088 | 0.0150 | 0.9985 | 11 |
| 0.0088 | 0.0150 | 0.9985 | 12 |
| 0.0087 | 0.0150 | 0.9985 | 13 |
| 0.0088 | 0.0150 | 0.9985 | 14 |
| 0.0088 | 0.0150 | 0.9985 | 15 |
| 0.0088 | 0.0150 | 0.9985 | 16 |
| 0.0088 | 0.0150 | 0.9985 | 17 |
| 0.0087 | 0.0150 | 0.9985 | 18 |
| 0.0088 | 0.0150 | 0.9985 | 19 |
Framework versions
- Transformers 4.31.0
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
