README.md

---
library_name: setfit
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
metrics:
- accuracy
widget:
- text: Mitarbeit am wissenschaftlichen Arbeitsplatz (LV0125)
- text: '20-00-0366-iv Serious Games: Einführung in die Thematik „Serious Games“:
    wissenschaftlich-technische Grundlagen, Anwendungsgebiete und Trends. Die Einzelthemen
    umfassen unter anderem: • Einführung in Serious Games • Game Development, Game
    Design • Game Technology, Tools und Engines • Personalisierung und Adaption •
    Interactive Digital Storytelling • Authoring und Content Generation • Multiplayer
    Games • Game Interfaces und Sensor Technology • Effects, Affects und User Experience
    • Mobile Games • Serious Games Anwendungsbereiche und Best-Practice Beispiele
    Die Übungen enthalten Theorie- und Praxisanteile. Dabei wird die Verwendung einer
    Game Engine gelehrt.'
- text: 'Aerobotics Seminar: - Einführung in die Aufgabenstellung, die vorhandene
    Infrastruktur und den zu durchlaufenden Entwicklungsprozess


    - Entwurf und Implementierung von Algorithmen zur Flugregelung in Gruppenarbeit


    - Diskussion des Fortschritts in regelmäßigen Progress-Meetings


    - Flugdemonstration


    - Abschließende Präsentation und Dokumentation'
- text: "Digital Transformations, Consumer Well-Being, and Sustainability: Physical\
    \ consumption, and individual ownership of material products in particular, has\
    \ traditionally been the default mode of consumption and its extent has long been\
    \ considered a measure of personal and societal prosperity. However, our daily\
    \ lives increasingly shift towards or are altered by digital environments, which\
    \ nurture alternative forms of consumption such as sharing or access-based offers,\
    \ cultivate the prevalence of virtual living worlds through fictional experiences,\
    \ and alter our relations to material possessions by an increasing availability\
    \ of digital solutions.\n\n\n\nThe course exposes you to state-of-the-art research\
    \ on consumer research and digital transformations in fields such as virtual reality,\
    \ sharing economy, and blockchain technologies. You will be guided through background\
    \ information of consumer behavior and consumer psychology. By creating a collaborative\
    \ learning environment, we will explore and critically discuss how digital transformations\
    \ affect consumer well-being and sustainability. \n\n\n\nYour role is to be an\
    \ active contributor in the class. This course consists of a lectures, discussion\
    \ sessions and group presentations. Generally, analysis of readings will be used\
    \ to guide our discussion. \n\n\n\nThe main objective of the course is to critically\
    \ reflect upon current technological advancements that increasingly permeate everyday\
    \ lives. Students will be engaged in exploring technological-social issues in\
    \ marketing and be guided into a critical approach on technology-brands-consumers\
    \ relationships behind digital transformations."
- text: 'Grundlagen der IT-Sicherheit: Um einen Überblick der IT-Sicherheit zu vermitteln
    werden folgende Themen behandelt:


    Motivation für IT-Sicherheit


    Grundbegriffe der IT-Sicherheit


    Computer Malware


    Kryptographische Grundlagen


    Authentisierung


    Biometrie


    Zugriffskontrolle


    Netzwerkund


    Internetsicherheit


    Physikalische Sicherheit / Physikalische Angriffe


    Sicherheitsevaluierung und Zertifizierung


    Einführung in den Datenschutz'
pipeline_tag: text-classification
inference: false
---

# SetFit with sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) 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:** [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2)
- **Classification head:** a OneVsRestClassifier instance
- **Maximum Sequence Length:** 128 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)

## 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("Chernoffface/fs-setfit-multilable-model")
# Run inference
preds = model("Mitarbeit am wissenschaftlichen Arbeitsplatz (LV0125)")
```

<!--
### 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   | 120.1215 | 537 |

### Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (2, 2)
- 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 |
|:------:|:----:|:-------------:|:---------------:|
| 0.0011 | 1    | 0.2964        | -               |
| 0.0552 | 50   | 0.2042        | -               |
| 0.1105 | 100  | 0.1643        | -               |
| 0.1657 | 150  | 0.1376        | -               |
| 0.2210 | 200  | 0.1232        | -               |
| 0.2762 | 250  | 0.1125        | -               |
| 0.3315 | 300  | 0.1079        | -               |
| 0.3867 | 350  | 0.0951        | -               |
| 0.4420 | 400  | 0.0847        | -               |
| 0.4972 | 450  | 0.0917        | -               |
| 0.5525 | 500  | 0.085         | -               |
| 0.6077 | 550  | 0.0758        | -               |
| 0.6630 | 600  | 0.0743        | -               |
| 0.7182 | 650  | 0.0671        | -               |
| 0.7735 | 700  | 0.0743        | -               |
| 0.8287 | 750  | 0.0571        | -               |
| 0.8840 | 800  | 0.0625        | -               |
| 0.9392 | 850  | 0.0607        | -               |
| 0.9945 | 900  | 0.0686        | -               |
| 1.0497 | 950  | 0.0541        | -               |
| 1.1050 | 1000 | 0.0553        | -               |
| 1.1602 | 1050 | 0.0565        | -               |
| 1.2155 | 1100 | 0.0558        | -               |
| 1.2707 | 1150 | 0.0578        | -               |
| 1.3260 | 1200 | 0.0525        | -               |
| 1.3812 | 1250 | 0.0541        | -               |
| 1.4365 | 1300 | 0.049         | -               |
| 1.4917 | 1350 | 0.0485        | -               |
| 1.5470 | 1400 | 0.0475        | -               |
| 1.6022 | 1450 | 0.0479        | -               |
| 1.6575 | 1500 | 0.0514        | -               |
| 1.7127 | 1550 | 0.0509        | -               |
| 1.7680 | 1600 | 0.0517        | -               |
| 1.8232 | 1650 | 0.0455        | -               |
| 1.8785 | 1700 | 0.0493        | -               |
| 1.9337 | 1750 | 0.0501        | -               |
| 1.9890 | 1800 | 0.0492        | -               |

### Framework Versions
- Python: 3.12.3
- SetFit: 1.1.0
- Sentence Transformers: 3.0.0
- Transformers: 4.43.1
- PyTorch: 2.3.1+cu121
- Datasets: 2.20.0
- Tokenizers: 0.19.1

## 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.*
-->