Hate-Speech-Detection-Tweets-RoBERTa-base
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1037
- Accuracy: 0.9904
- F1: 0.9884
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: 15
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
---|---|---|---|---|---|
0.0694 | 1.0 | 2558 | 0.0600 | 0.9836 | 0.9801 |
0.0556 | 2.0 | 5116 | 0.0657 | 0.9862 | 0.9832 |
0.0316 | 3.0 | 7674 | 0.0685 | 0.9852 | 0.9822 |
0.0218 | 4.0 | 10232 | 0.0831 | 0.9878 | 0.9851 |
0.016 | 5.0 | 12790 | 0.0769 | 0.9877 | 0.9850 |
0.0082 | 6.0 | 15348 | 0.0654 | 0.9894 | 0.9873 |
0.0057 | 7.0 | 17906 | 0.0923 | 0.9867 | 0.9840 |
0.006 | 8.0 | 20464 | 0.1143 | 0.9875 | 0.9850 |
0.0006 | 9.0 | 23022 | 0.1100 | 0.9896 | 0.9875 |
0.0034 | 10.0 | 25580 | 0.1037 | 0.9904 | 0.9884 |
0.0019 | 11.0 | 28138 | 0.1134 | 0.9899 | 0.9878 |
0.0038 | 12.0 | 30696 | 0.1076 | 0.9898 | 0.9877 |
0.0 | 13.0 | 33254 | 0.1252 | 0.9896 | 0.9874 |
0.0 | 14.0 | 35812 | 0.1255 | 0.9892 | 0.9869 |
0.0008 | 15.0 | 38370 | 0.1161 | 0.9902 | 0.9882 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1
- Datasets 2.10.1
- Tokenizers 0.13.3
- Downloads last month
- 10
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.