<!-- 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. -->
twitter-roberta-base-offensive-finetuned
This model is a fine-tuned version of cardiffnlp/twitter-roberta-base-offensive on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6574
- Accuracy: 0.8467
- F1: 0.8798
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: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|---|
| 0.4202 | 1.0 | 1548 | 0.4947 | 0.8130 | 0.8543 |
| 0.3487 | 2.0 | 3096 | 0.4970 | 0.8351 | 0.8739 |
| 0.2596 | 3.0 | 4644 | 0.6574 | 0.8467 | 0.8798 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.12.1+cu113
- Datasets 1.18.3
- Tokenizers 0.13.2
