---
base_model: akhooli/sbert_ar_nli_500k_norm
library_name: setfit
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: عزيزي جبران باسيل بدك تعرف كتييير منيح انو مش شغلتنا نحفظ امن اسرائيل يلي
    ما منعترف ولن نعترف ب وجودها ابدا
- text: 'يجب على هؤلاك المجرمون الارهابيون وكل من دس فتنة انا يتحاسبو حساب مؤلم لكن
    سؤال من سيحاسبهن '
- text: شيل عينك عن لبنان انت و كل كلب متلك حكايتك و غير هيك انشالله بتنباع بالعزى
- text: لسه بصرعوا طيزنا بدكن نصير متل العراق وليبيا يا حمير تجاوزناهن بأشواط، هلق
    لو نصير متل العراق وليبيا تحسن كبير جدا
- text: كول هوا خسرتو بأرضك وبين جمهورك بعد ما منعت القطريين من تشجيع جمهورهم انتو
    فاشلين في كل شئ وهم متفوقين عليكم في...
inference: true
model-index:
- name: SetFit with akhooli/sbert_ar_nli_500k_norm
  results:
  - task:
      type: text-classification
      name: Text Classification
    dataset:
      name: Unknown
      type: unknown
      split: test
    metrics:
    - type: accuracy
      value: 0.8452520515826495
      name: Accuracy
---

# SetFit with akhooli/sbert_ar_nli_500k_norm

This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [akhooli/sbert_ar_nli_500k_norm](https://huggingface.co/akhooli/sbert_ar_nli_500k_norm) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.

The model has been trained using an efficient few-shot learning technique that involves:

1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.

## Model Details

### Model Description
- **Model Type:** SetFit
- **Sentence Transformer body:** [akhooli/sbert_ar_nli_500k_norm](https://huggingface.co/akhooli/sbert_ar_nli_500k_norm)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 512 tokens
- **Number of Classes:** 2 classes
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->

### Model Sources

- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)

### Model Labels
| Label    | Examples                                                                                                                                                                                                                                                                   |
|:---------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| negative | <ul><li>'يا ريت بيمنعوا الأرغيلة بلبنان، لأن غير هيك ما منعمل ثورة '</li><li>'أصلا جبران عندو طيارة وعندو قصر بأوروبا ومحيط الهادىء الى اسهم فيه وتم اكتشاف كوكب جديد مثل زحل وجوبيتير تم شرائه ك...'</li><li>'اكره البرازيل بس لا تقوليلي خلاص كلشي انتهى بليز'</li></ul> |
| positive | <ul><li>'السيد والرئيس وليش عم تشددددد دخلك كل حجمك أرنب عند معلمك بالقرداحة'</li><li>'العوني اذا تمدن متل الجحش اذا تكدن بعمرك شفت عوني بيفهم'</li><li>'لا بس الوطن بدو تكنيس من ل متلك '</li></ul>                                                                       |

## Evaluation

### Metrics
| Label   | Accuracy |
|:--------|:---------|
| **all** | 0.8453   |

## Uses

### Direct Use for Inference

First install the SetFit library:

```bash
pip install setfit
```

Then you can load this model and run inference.

```python
from setfit import SetFitModel

# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("akhooli/setfit_ar_hs")
# Run inference
preds = model("شيل عينك عن لبنان انت و كل كلب متلك حكايتك و غير هيك انشالله بتنباع بالعزى")
```

<!--
### Downstream Use

*List how someone could finetune this model on their own dataset.*
-->

<!--
### Out-of-Scope Use

*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->

<!--
## Bias, Risks and Limitations

*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->

<!--
### Recommendations

*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->

## Training Details

### Training Set Metrics
| Training set | Min | Median | Max |
|:-------------|:----|:-------|:----|
| Word count   | 1   | 12.809 | 52  |

| Label    | Training Sample Count |
|:---------|:----------------------|
| negative | 2000                  |
| positive | 2000                  |

### Training Hyperparameters
- batch_size: (32, 32)
- num_epochs: (1, 1)
- max_steps: 5000
- sampling_strategy: undersampling
- body_learning_rate: (2e-05, 1e-05)
- head_learning_rate: 0.01
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: False
- warmup_proportion: 0.1
- l2_weight: 0.01
- seed: 42
- run_name: setfit_hate_2kv
- eval_max_steps: -1
- load_best_model_at_end: False

### Training Results
| Epoch  | Step | Training Loss | Validation Loss |
|:------:|:----:|:-------------:|:---------------:|
| 0.0004 | 1    | 0.3239        | -               |
| 0.04   | 100  | 0.277         | -               |
| 0.08   | 200  | 0.2406        | -               |
| 0.12   | 300  | 0.1737        | -               |
| 0.16   | 400  | 0.1259        | -               |
| 0.2    | 500  | 0.0701        | -               |
| 0.24   | 600  | 0.0473        | -               |
| 0.28   | 700  | 0.0298        | -               |
| 0.32   | 800  | 0.0239        | -               |
| 0.36   | 900  | 0.02          | -               |
| 0.4    | 1000 | 0.0151        | -               |
| 0.44   | 1100 | 0.0143        | -               |
| 0.48   | 1200 | 0.0126        | -               |
| 0.52   | 1300 | 0.0121        | -               |
| 0.56   | 1400 | 0.0078        | -               |
| 0.6    | 1500 | 0.0111        | -               |
| 0.64   | 1600 | 0.0099        | -               |
| 0.68   | 1700 | 0.0091        | -               |
| 0.72   | 1800 | 0.0064        | -               |
| 0.76   | 1900 | 0.0101        | -               |
| 0.8    | 2000 | 0.0073        | -               |
| 0.84   | 2100 | 0.0042        | -               |
| 0.88   | 2200 | 0.0038        | -               |
| 0.92   | 2300 | 0.0058        | -               |
| 0.96   | 2400 | 0.0041        | -               |
| 1.0    | 2500 | 0.0026        | -               |
| 1.04   | 2600 | 0.0037        | -               |
| 1.08   | 2700 | 0.0035        | -               |
| 1.12   | 2800 | 0.0045        | -               |
| 1.16   | 2900 | 0.0038        | -               |
| 1.2    | 3000 | 0.0039        | -               |
| 1.24   | 3100 | 0.0018        | -               |
| 1.28   | 3200 | 0.003         | -               |
| 1.32   | 3300 | 0.0028        | -               |
| 1.3600 | 3400 | 0.0023        | -               |
| 1.4    | 3500 | 0.0022        | -               |
| 1.44   | 3600 | 0.0032        | -               |
| 1.48   | 3700 | 0.0028        | -               |
| 1.52   | 3800 | 0.0022        | -               |
| 1.56   | 3900 | 0.0024        | -               |
| 1.6    | 4000 | 0.0021        | -               |
| 1.6400 | 4100 | 0.0032        | -               |
| 1.6800 | 4200 | 0.0026        | -               |
| 1.72   | 4300 | 0.0025        | -               |
| 1.76   | 4400 | 0.003         | -               |
| 1.8    | 4500 | 0.0028        | -               |
| 1.8400 | 4600 | 0.003         | -               |
| 1.88   | 4700 | 0.0028        | -               |
| 1.92   | 4800 | 0.0033        | -               |
| 1.96   | 4900 | 0.0019        | -               |
| 2.0    | 5000 | 0.0023        | -               |

### Framework Versions
- Python: 3.10.14
- SetFit: 1.2.0.dev0
- Sentence Transformers: 3.1.1
- Transformers: 4.45.1
- PyTorch: 2.4.0
- Datasets: 3.0.1
- Tokenizers: 0.20.0

## Citation

### BibTeX
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
    doi = {10.48550/ARXIV.2209.11055},
    url = {https://arxiv.org/abs/2209.11055},
    author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
    keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {Efficient Few-Shot Learning Without Prompts},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
}
```

<!--
## Glossary

*Clearly define terms in order to be accessible across audiences.*
-->

<!--
## Model Card Authors

*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->

<!--
## Model Card Contact

*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->