<!-- 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. -->
silviacamplani/distilbert-finetuned-tapt-ner-music
This model is a fine-tuned version of silviacamplani/distilbert-finetuned-tapt-lm-ai on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.6932
- Validation Loss: 0.7886
- Train Precision: 0.5347
- Train Recall: 0.5896
- Train F1: 0.5608
- Train Accuracy: 0.8078
- 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: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 1e-05, 'decay_steps': 370, '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}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
- training_precision: mixed_float16
Training results
| Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
|---|---|---|---|---|---|---|
| 2.7047 | 2.0137 | 0.0 | 0.0 | 0.0 | 0.5482 | 0 |
| 1.7222 | 1.5112 | 0.0 | 0.0 | 0.0 | 0.5561 | 1 |
| 1.3564 | 1.2817 | 0.2382 | 0.2592 | 0.2483 | 0.6686 | 2 |
| 1.1641 | 1.1378 | 0.3605 | 0.3816 | 0.3708 | 0.7043 | 3 |
| 1.0188 | 1.0187 | 0.4583 | 0.4950 | 0.4760 | 0.7409 | 4 |
| 0.8983 | 0.9267 | 0.4946 | 0.5383 | 0.5155 | 0.7638 | 5 |
| 0.8117 | 0.8649 | 0.5152 | 0.5653 | 0.5391 | 0.7816 | 6 |
| 0.7550 | 0.8206 | 0.5283 | 0.5806 | 0.5532 | 0.8007 | 7 |
| 0.7132 | 0.7964 | 0.5326 | 0.5887 | 0.5592 | 0.8049 | 8 |
| 0.6932 | 0.7886 | 0.5347 | 0.5896 | 0.5608 | 0.8078 | 9 |
Framework versions
- Transformers 4.20.1
- TensorFlow 2.6.4
- Datasets 2.1.0
- Tokenizers 0.12.1
