<!-- 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_MAKE_NewData_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: 0.2959
- Validation Loss: 0.4909
- Train Accuracy: 0.8545
- 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': 360, '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 |
|---|---|---|---|
| 2.3353 | 1.9477 | 0.6545 | 0 |
| 1.7645 | 1.4417 | 0.6545 | 1 |
| 1.3097 | 1.1007 | 0.8364 | 2 |
| 0.9860 | 0.8667 | 0.8364 | 3 |
| 0.7850 | 0.7599 | 0.8364 | 4 |
| 0.6603 | 0.6913 | 0.8545 | 5 |
| 0.5657 | 0.6254 | 0.8545 | 6 |
| 0.5007 | 0.5763 | 0.8545 | 7 |
| 0.4480 | 0.5492 | 0.8364 | 8 |
| 0.4014 | 0.5328 | 0.8545 | 9 |
| 0.3611 | 0.5035 | 0.8364 | 10 |
| 0.3295 | 0.5296 | 0.8545 | 11 |
| 0.3177 | 0.4930 | 0.8545 | 12 |
| 0.3103 | 0.4904 | 0.8545 | 13 |
| 0.2959 | 0.4909 | 0.8545 | 14 |
Framework versions
- Transformers 4.28.1
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
