<!-- 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/bert-textClassification_v1.4
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: 0.3431
- Validation Loss: 0.8618
- Train Accuracy: 0.7273
- 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-05, 'decay_steps': 285, '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 |
|---|---|---|---|
| 2.2087 | 1.9909 | 0.4091 | 0 |
| 1.7130 | 1.6444 | 0.5909 | 1 |
| 1.3350 | 1.3844 | 0.5455 | 2 |
| 1.0642 | 1.2276 | 0.6136 | 3 |
| 0.8599 | 1.1036 | 0.6818 | 4 |
| 0.7216 | 1.0790 | 0.6818 | 5 |
| 0.6305 | 1.0403 | 0.6818 | 6 |
| 0.5304 | 0.9581 | 0.7045 | 7 |
| 0.4899 | 0.8977 | 0.7273 | 8 |
| 0.4332 | 0.8907 | 0.7273 | 9 |
| 0.4000 | 0.9072 | 0.7273 | 10 |
| 0.3740 | 0.8734 | 0.7273 | 11 |
| 0.3579 | 0.8726 | 0.7273 | 12 |
| 0.3448 | 0.8648 | 0.7273 | 13 |
| 0.3431 | 0.8618 | 0.7273 | 14 |
Framework versions
- Transformers 4.27.4
- TensorFlow 2.12.0
- Datasets 2.11.0
- Tokenizers 0.13.3
