|
|
--- |
|
|
library_name: transformers |
|
|
license: mit |
|
|
base_model: roberta-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: toxicity-classification-model |
|
|
results: [] |
|
|
datasets: |
|
|
- dirtycomputer/Toxic_Comment_Classification_Challenge |
|
|
language: |
|
|
- en |
|
|
pipeline_tag: text-classification |
|
|
--- |
|
|
|
|
|
# toxicity-classification-model |
|
|
|
|
|
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the dirtycomputer/Toxic_Comment_Classification_Challenge dataset. It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0511 |
|
|
- Accuracy: 0.9812 |
|
|
|
|
|
## Model description |
|
|
|
|
|
Fine-tuned roberta-base model for detecting toxicity in comments. It categorizes a comment into different toxicity types, such as "toxic," "obscene," "insult," and "threat." |
|
|
|
|
|
## Intended uses & limitations |
|
|
|
|
|
### Intended Uses |
|
|
- **Content Moderation**: Automatically flagging or removing toxic comments on social media platforms, forums, and customer support. |
|
|
- **Toxicity Detection**: Classifying comments based on their toxicity level, such as harmful language or insults. |
|
|
|
|
|
### Limitations |
|
|
- **False Negatives**: May not always catch subtle toxic behavior. |
|
|
- **Limited Language Support**: Currently, the model is trained on English-only data. |
|
|
- **Context Sensitivity**: May struggle with ambiguous language or sarcasm. |
|
|
|
|
|
## Training and evaluation data |
|
|
|
|
|
This model was fine-tuned using the **dirtycomputer/Toxic_Comment_Classification_Challenge** dataset, which contains labeled comments for toxicity classification. |
|
|
|
|
|
## Training procedure |
|
|
|
|
|
### Training hyperparameters |
|
|
|
|
|
The following hyperparameters were used during training: |
|
|
- learning_rate: 5e-05 |
|
|
- train_batch_size: 8 |
|
|
- eval_batch_size: 16 |
|
|
- seed: 42 |
|
|
- optimizer: Use adamw_torch with betas=(0.9, 0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 500 |
|
|
- num_epochs: 3 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
|
| 0.1691 | 1.0 | 17952 | 0.1464 | 0.9617 | |
|
|
| 0.0892 | 2.0 | 35904 | 0.1456 | 0.9617 | |
|
|
| 0.0527 | 3.0 | 53856 | 0.0511 | 0.9812 | |
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.47.1 |
|
|
- Pytorch 2.5.1+cu121 |
|
|
- Datasets 3.2.0 |
|
|
- Tokenizers 0.21.0 |
