<!-- 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. -->
vedantjumle/manasi
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.9757
- Train Accuracy: 0.7839
- Epoch: 18
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': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 480, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Epoch |
|---|---|---|
| 2.7486 | 0.4271 | 0 |
| 2.2633 | 0.4297 | 1 |
| 2.1244 | 0.4284 | 2 |
| 2.0740 | 0.4258 | 3 |
| 2.0444 | 0.4323 | 4 |
| 2.0005 | 0.4922 | 5 |
| 1.9095 | 0.5169 | 6 |
| 1.7609 | 0.5924 | 7 |
| 1.6275 | 0.6484 | 8 |
| 1.4806 | 0.6706 | 9 |
| 1.3658 | 0.7005 | 10 |
| 1.2600 | 0.7409 | 11 |
| 1.1962 | 0.7487 | 12 |
| 1.1222 | 0.7487 | 13 |
| 1.0866 | 0.7721 | 14 |
| 1.0440 | 0.7786 | 15 |
| 1.0203 | 0.7839 | 16 |
| 1.0053 | 0.7852 | 17 |
| 0.9757 | 0.7839 | 18 |
Framework versions
- Transformers 4.34.0
- TensorFlow 2.13.0
- Datasets 2.14.5
- Tokenizers 0.14.1
