<!-- 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. -->
imtiaz114/bert-finetuned-ner-baseline-1
This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0916
- Validation Loss: 0.2890
- Epoch: 9
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': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 5970, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: mixed_float16
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 0.4561 | 0.3479 | 0 |
| 0.3119 | 0.2839 | 1 |
| 0.2518 | 0.2636 | 2 |
| 0.2122 | 0.2485 | 3 |
| 0.1802 | 0.2579 | 4 |
| 0.1542 | 0.2584 | 5 |
| 0.1326 | 0.2698 | 6 |
| 0.1178 | 0.2726 | 7 |
| 0.1011 | 0.2845 | 8 |
| 0.0916 | 0.2890 | 9 |
Framework versions
- Transformers 4.31.0.dev0
- TensorFlow 2.12.0
- Datasets 2.1.0
- Tokenizers 0.13.3
