<!-- 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_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: 0.0165
- Validation Loss: 1.1489
- Train Accuracy: 0.7436
- Epoch: 13
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': 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 |
---|---|---|---|
0.6677 | 0.7030 | 0.5128 | 0 |
0.6287 | 0.6204 | 0.7436 | 1 |
0.4746 | 0.4927 | 0.7949 | 2 |
0.3647 | 0.5168 | 0.7692 | 3 |
0.2682 | 0.5776 | 0.7436 | 4 |
0.2184 | 0.4834 | 0.8205 | 5 |
0.1997 | 0.5296 | 0.7692 | 6 |
0.1188 | 0.6967 | 0.7949 | 7 |
0.0945 | 0.6440 | 0.8205 | 8 |
0.0539 | 0.6911 | 0.7949 | 9 |
0.0271 | 0.8044 | 0.7949 | 10 |
0.0242 | 0.7906 | 0.7949 | 11 |
0.0264 | 0.8078 | 0.8462 | 12 |
0.0165 | 1.1489 | 0.7436 | 13 |
Framework versions
- Transformers 4.28.1
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3