<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
covid-balanced-tweet-bert-large-e4
This model is a fine-tuned version of digitalepidemiologylab/covid-twitter-bert-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2645
- Accuracy: 0.9650
- F1: 0.9082
- Precision: 0.8826
- Recall: 0.9353
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:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.2625 | 1.0 | 1629 | 0.2827 | 0.9410 | 0.8596 | 0.7686 | 0.9751 |
| 0.1461 | 2.0 | 3258 | 0.2443 | 0.9530 | 0.8817 | 0.8261 | 0.9453 |
| 0.0613 | 3.0 | 4887 | 0.2432 | 0.9659 | 0.9108 | 0.8832 | 0.9403 |
| 0.0352 | 4.0 | 6516 | 0.2645 | 0.9650 | 0.9082 | 0.8826 | 0.9353 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
