README.md

---
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: 'lymphocyte activation: Morphologic alteration of small B LYMPHOCYTES or T
    LYMPHOCYTES in culture into large blast-like cells able to synthesize DNA and
    RNA and to divide mitotically. It is induced by INTERLEUKINS; MITOGENS such as
    PHYTOHEMAGGLUTININS, and by specific ANTIGENS. It may also occur in vivo as in
    GRAFT REJECTION.'
- text: 'burns: Injuries to tissues caused by contact with heat, steam, chemicals
    (BURNS, CHEMICAL), electricity (BURNS, ELECTRIC), or the like.'
- text: 'solutions: "The homogeneous mixtures formed by the mixing of a solid, liquid,
    or gaseous substance (solute) with a liquid (the solvent), from which the dissolved
    substances can be recovered by physical processes. (From Grant & Hackhs Chemical
    Dictionary, 5th ed)"'
- text: 'tooth discoloration: Any change in the hue, color, or translucency of a tooth
    due to any cause. Restorative filling materials, drugs (both topical and systemic),
    pulpal necrosis, or hemorrhage may be responsible. (Jablonski, Dictionary of Dentistry,
    1992, p253)'
- text: 'foreign-body reaction: Chronic inflammation and granuloma formation around
    irritating foreign bodies.'
metrics:
- accuracy
pipeline_tag: text-classification
library_name: setfit
inference: false
base_model: cambridgeltl/SapBERT-from-PubMedBERT-fulltext
model-index:
- name: SetFit with cambridgeltl/SapBERT-from-PubMedBERT-fulltext
  results:
  - task:
      type: text-classification
      name: Text Classification
    dataset:
      name: Unknown
      type: unknown
      split: test
    metrics:
    - type: accuracy
      value: 0.5240963855421686
      name: Accuracy
---

# SetFit with cambridgeltl/SapBERT-from-PubMedBERT-fulltext

This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [cambridgeltl/SapBERT-from-PubMedBERT-fulltext](https://huggingface.co/cambridgeltl/SapBERT-from-PubMedBERT-fulltext) as the Sentence Transformer embedding model. A OneVsRestClassifier 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:** [cambridgeltl/SapBERT-from-PubMedBERT-fulltext](https://huggingface.co/cambridgeltl/SapBERT-from-PubMedBERT-fulltext)
- **Classification head:** a OneVsRestClassifier instance
- **Maximum Sequence Length:** 512 tokens
<!-- - **Number of Classes:** Unknown -->
<!-- - **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)

## Evaluation

### Metrics
| Label   | Accuracy |
|:--------|:---------|
| **all** | 0.5241   |

## 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("foreign-body reaction: Chronic inflammation and granuloma formation around irritating foreign bodies.")
```

<!--
### 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   | 2   | 30.4473 | 134 |

### Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (1, 1)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 20
- body_learning_rate: (2e-05, 2e-05)
- head_learning_rate: 2e-05
- 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 |
|:------:|:----:|:-------------:|:---------------:|
| 0.0003 | 1    | 0.2929        | -               |
| 0.0136 | 50   | 0.2377        | -               |
| 0.0272 | 100  | 0.2321        | -               |
| 0.0408 | 150  | 0.2199        | -               |
| 0.0544 | 200  | 0.1726        | -               |
| 0.0680 | 250  | 0.1355        | -               |
| 0.0816 | 300  | 0.1207        | -               |
| 0.0952 | 350  | 0.1138        | -               |
| 0.1088 | 400  | 0.1154        | -               |
| 0.1223 | 450  | 0.095         | -               |
| 0.1359 | 500  | 0.106         | -               |
| 0.1495 | 550  | 0.0913        | -               |
| 0.1631 | 600  | 0.0943        | -               |
| 0.1767 | 650  | 0.0974        | -               |
| 0.1903 | 700  | 0.0923        | -               |
| 0.2039 | 750  | 0.0893        | -               |
| 0.2175 | 800  | 0.0804        | -               |
| 0.2311 | 850  | 0.0849        | -               |
| 0.2447 | 900  | 0.0766        | -               |
| 0.2583 | 950  | 0.0838        | -               |
| 0.2719 | 1000 | 0.0725        | -               |
| 0.2855 | 1050 | 0.073         | -               |
| 0.2991 | 1100 | 0.055         | -               |
| 0.3127 | 1150 | 0.0758        | -               |
| 0.3263 | 1200 | 0.0709        | -               |
| 0.3399 | 1250 | 0.0569        | -               |
| 0.3535 | 1300 | 0.0535        | -               |
| 0.3670 | 1350 | 0.0557        | -               |
| 0.3806 | 1400 | 0.0596        | -               |
| 0.3942 | 1450 | 0.0453        | -               |
| 0.4078 | 1500 | 0.0428        | -               |
| 0.4214 | 1550 | 0.0482        | -               |
| 0.4350 | 1600 | 0.0465        | -               |
| 0.4486 | 1650 | 0.0469        | -               |
| 0.4622 | 1700 | 0.0479        | -               |
| 0.4758 | 1750 | 0.0451        | -               |
| 0.4894 | 1800 | 0.0613        | -               |
| 0.5030 | 1850 | 0.0533        | -               |
| 0.5166 | 1900 | 0.0476        | -               |
| 0.5302 | 1950 | 0.0449        | -               |
| 0.5438 | 2000 | 0.0543        | -               |
| 0.5574 | 2050 | 0.0509        | -               |
| 0.5710 | 2100 | 0.043         | -               |
| 0.5846 | 2150 | 0.0482        | -               |
| 0.5982 | 2200 | 0.0513        | -               |
| 0.6117 | 2250 | 0.0366        | -               |
| 0.6253 | 2300 | 0.0385        | -               |
| 0.6389 | 2350 | 0.0446        | -               |
| 0.6525 | 2400 | 0.0411        | -               |
| 0.6661 | 2450 | 0.037         | -               |
| 0.6797 | 2500 | 0.0321        | -               |
| 0.6933 | 2550 | 0.0468        | -               |
| 0.7069 | 2600 | 0.0331        | -               |
| 0.7205 | 2650 | 0.0315        | -               |
| 0.7341 | 2700 | 0.0435        | -               |
| 0.7477 | 2750 | 0.0394        | -               |
| 0.7613 | 2800 | 0.0381        | -               |
| 0.7749 | 2850 | 0.0418        | -               |
| 0.7885 | 2900 | 0.0347        | -               |
| 0.8021 | 2950 | 0.0468        | -               |
| 0.8157 | 3000 | 0.0352        | -               |
| 0.8293 | 3050 | 0.0416        | -               |
| 0.8428 | 3100 | 0.0354        | -               |
| 0.8564 | 3150 | 0.0329        | -               |
| 0.8700 | 3200 | 0.0359        | -               |
| 0.8836 | 3250 | 0.036         | -               |
| 0.8972 | 3300 | 0.0362        | -               |
| 0.9108 | 3350 | 0.0296        | -               |
| 0.9244 | 3400 | 0.041         | -               |
| 0.9380 | 3450 | 0.0375        | -               |
| 0.9516 | 3500 | 0.0282        | -               |
| 0.9652 | 3550 | 0.0341        | -               |
| 0.9788 | 3600 | 0.0283        | -               |
| 0.9924 | 3650 | 0.0339        | -               |

### Framework Versions
- Python: 3.11.11
- SetFit: 1.1.1
- Sentence Transformers: 3.4.1
- Transformers: 4.50.0
- PyTorch: 2.6.0+cu124
- Datasets: 3.4.1
- Tokenizers: 0.21.1

## 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.*
-->