metadata
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.
The 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.
Your 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.
The 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 model that can be used for Text Classification. This SetFit model uses 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:
- Fine-tuning a Sentence Transformer with contrastive learning.
- 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
- Classification head: a OneVsRestClassifier instance
- Maximum Sequence Length: 128 tokens
Model Sources
- Repository: SetFit on GitHub
- Paper: Efficient Few-Shot Learning Without Prompts
- Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts
Uses
Direct Use for Inference
First install the SetFit library:
pip install setfit
Then you can load this model and run inference.
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)")
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
@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}
}