silviacamplani/twitter-roberta-base-finetuned-ner-wnut
This model is a fine-tuned version of cardiffnlp/twitter-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0812
- Validation Loss: 0.2553
- Train Precision: 0.6263
- Train Recall: 0.5191
- Train F1: 0.5677
- Train Accuracy: 0.9398
- Epoch: 2
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': 'Adam', 'config': {'name': 'Adam', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 636, '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}}, '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 |
|---|---|---|---|---|---|---|
| 0.0813 | 0.2553 | 0.6263 | 0.5191 | 0.5677 | 0.9398 | 0 |
| 0.0815 | 0.2553 | 0.6263 | 0.5191 | 0.5677 | 0.9398 | 1 |
| 0.0812 | 0.2553 | 0.6263 | 0.5191 | 0.5677 | 0.9398 | 2 |
Framework versions
- Transformers 4.20.1
- TensorFlow 2.6.4
- Datasets 2.1.0
- Tokenizers 0.12.1