bert-base-cased-sentweet-hatespeech
This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4203
- Accuracy: 0.8299
- Precision: 0.8430
- Recall: 0.8353
- F1: 0.8294
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 81 | 0.4203 | 0.8299 | 0.8430 | 0.8353 | 0.8294 |
| No log | 2.0 | 162 | 0.4448 | 0.7917 | 0.7921 | 0.7930 | 0.7916 |
| No log | 3.0 | 243 | 0.4748 | 0.7812 | 0.7806 | 0.7812 | 0.7808 |
| No log | 4.0 | 324 | 0.5806 | 0.7674 | 0.7674 | 0.7653 | 0.7659 |
| No log | 5.0 | 405 | 0.7538 | 0.7917 | 0.7922 | 0.7895 | 0.7902 |
| No log | 6.0 | 486 | 0.8612 | 0.7847 | 0.7852 | 0.7825 | 0.7832 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.1+cu117
- Datasets 2.6.1
- Tokenizers 0.11.0