<!-- 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. -->
This model is a fine-tuned version of vinai/bertweet-covid19-base-uncased on a dataset of 10k tweets about COVID-19 policies from US legislators in the House and Senate.
The model is intended to identify skepticism of COVID-19 policies (i.e. masks, social distancing, lockdowns, vaccines etc.). The model classifies as 1 (expressing skepticism/opposition to a COVID-19 policy or 0 (no opposition)
It achieves the following results on the evaluation set:
- Train Loss: 0.1007
- Train Sparse Categorical Accuracy: 0.9591
- Validation Loss: 0.0913
- Validation Sparse Categorical Accuracy: 0.9627
- Epoch: 3
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'learning_rate': 5e-07, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Sparse Categorical Accuracy | Validation Loss | Validation Sparse Categorical Accuracy | Epoch |
|---|---|---|---|---|
| 0.1822 | 0.9345 | 0.1021 | 0.9584 | 0 |
| 0.1007 | 0.9591 | 0.0913 | 0.9627 | 1 |
Framework versions
- Transformers 4.21.0
- TensorFlow 2.8.2
- Datasets 2.4.0
- Tokenizers 0.12.1
