bert-base-uncased-finetuned-toxicity-detection-sose25
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2215
- Accuracy: 0.93
- Precision: 0.8441
- Recall: 0.8196
- F1: 0.8312
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.3529 | 1.0 | 100 | 0.3321 | 0.91 | 0.9535 | 0.6327 | 0.6853 |
| 0.2211 | 2.0 | 200 | 0.3187 | 0.9025 | 0.95 | 0.6020 | 0.6432 |
| 0.1118 | 3.0 | 300 | 0.2215 | 0.93 | 0.8441 | 0.8196 | 0.8312 |
| 0.0653 | 4.0 | 400 | 0.2539 | 0.9325 | 0.8625 | 0.8035 | 0.8293 |
| 0.0291 | 5.0 | 500 | 0.3459 | 0.9325 | 0.9023 | 0.7596 | 0.8104 |
Framework versions
- Transformers 4.51.1
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1