---
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: Framing shop providing custom picture framing and art preservation services.
    We frame artwork, photographs, and memorabilia with quality materials.
- text: Lymph node pathology reveals metastatic adenocarcinoma with extracapsular
    extension. Immunostains are consistent with breast primary tumor origin.
- text: Fluoroscopy-guided placement of central venous catheter for chemotherapy administration.
    Port placement performed successfully with proper tip positioning confirmed.
- text: Immunotherapy harnesses the body's immune system to fight cancer. Checkpoint
    inhibitors block proteins like PD-1 and CTLA-4 that normally prevent immune cells
    from attacking cancer cells, while CAR-T therapy genetically modifies T cells
    to better recognize cancer.
- text: Endometrial biopsy shows endometrioid adenocarcinoma, grade 2, with squamous
    differentiation. Deep myometrial invasion is present involving the outer half.
metrics:
- accuracy
pipeline_tag: text-classification
library_name: setfit
inference: true
base_model: TimKond/S-PubMedBert-MedQuAD
model-index:
- name: SetFit with TimKond/S-PubMedBert-MedQuAD
  results:
  - task:
      type: text-classification
      name: Text Classification
    dataset:
      name: Unknown
      type: unknown
      split: test
    metrics:
    - type: accuracy
      value: 1.0
      name: Accuracy
---

# SetFit with TimKond/S-PubMedBert-MedQuAD

This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [TimKond/S-PubMedBert-MedQuAD](https://huggingface.co/TimKond/S-PubMedBert-MedQuAD) 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:** [TimKond/S-PubMedBert-MedQuAD](https://huggingface.co/TimKond/S-PubMedBert-MedQuAD)
- **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                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
|:-------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| non_oncology | <ul><li>'Food truck festival coordination service organizing mobile vendor events, permit management, and location logistics.'</li><li>'Traditional Japanese tea ceremony instruction teaching the ancient art of chanoyu. Cultural immersion program exploring Japanese aesthetics, philosophy, and mindfulness practices.'</li><li>'Yoga studio offering various classes including Hatha, Vinyasa, and restorative yoga. We provide a peaceful environment for mindfulness and physical wellness.'</li></ul>                                                                                                                                                                                                                                                                          |
| oncology     | <ul><li>'Combination therapy uses multiple treatment modalities to improve outcomes. For example, neoadjuvant chemotherapy can shrink tumors before surgery, while adjuvant therapy eliminates remaining cancer cells after primary treatment.'</li><li>'Hereditary cancer syndromes account for 5-10% of all cancers. BRCA1 and BRCA2 mutations significantly increase breast and ovarian cancer risk, while Lynch syndrome increases colorectal and endometrial cancer risk.'</li><li>'Endoplasmic Reticulum: The cisternae of the endoplasmic reticulum are distended by fluid in hydropic swelling. In other forms of acute, reversible cell injury, membrane-bound polysomes may undergo disaggregation and detach from the surface of the rough endoplasmic reticulum.'</li></ul> |

## Evaluation

### Metrics
| Label   | Accuracy |
|:--------|:---------|
| **all** | 1.0      |

## 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("setfit_model_id")
# Run inference
preds = model("Lymph node pathology reveals metastatic adenocarcinoma with extracapsular extension. Immunostains are consistent with breast primary tumor origin.")
```

<!--
### 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   | 12  | 31.1543 | 929 |

| Label        | Training Sample Count |
|:-------------|:----------------------|
| non_oncology | 293                   |
| oncology     | 180                   |

### Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (1, 1)
- max_steps: 200
- sampling_strategy: oversampling
- 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
- eval_max_steps: -1
- load_best_model_at_end: False

### Training Results
| Epoch | Step | Training Loss | Validation Loss |
|:-----:|:----:|:-------------:|:---------------:|
| 0.005 | 1    | 0.1922        | -               |
| 0.25  | 50   | 0.0766        | -               |
| 0.5   | 100  | 0.0081        | -               |
| 0.75  | 150  | 0.0058        | -               |
| 1.0   | 200  | 0.0005        | 0.0074          |

### Framework Versions
- Python: 3.11.10
- SetFit: 1.1.2
- Sentence Transformers: 5.0.0
- Transformers: 4.49.0
- PyTorch: 2.7.1
- Datasets: 3.6.0
- Tokenizers: 0.21.2

## 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.*
-->