<!-- 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-augment-tweet-bert-large-e3-v2
This model is a fine-tuned version of digitalepidemiologylab/covid-twitter-bert on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3638
- Accuracy: 0.9581
- F1: 0.8877
- Precision: 0.8862
- Recall: 0.8893
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
---|---|---|---|---|---|---|---|
0.0547 | 1.0 | 1023 | 0.2606 | 0.9600 | 0.8960 | 0.8697 | 0.9239 |
0.0142 | 2.0 | 2046 | 0.3136 | 0.9574 | 0.8881 | 0.8704 | 0.9066 |
0.0011 | 3.0 | 3069 | 0.3638 | 0.9581 | 0.8877 | 0.8862 | 0.8893 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3