metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - accuracy
widget:
  - text: >-
      Implementing the reform required strong support from all ministries
      involved. A major effort was required to present the conceptual change to
      car importers, politicians and the public. A great deal was also invested
      in public relations to describe the benefits of the tax, which by many was
      perceived as yet another attempt to increase tax revenues. A number of the
      most popular car models’ prices were about to increase – mostly large
      family, luxury and sport cars – but for many models, the retail price was
      actually reduced.
  - text: >-
      Facilitate transition of workers from the informal to the formal economy.
      This will target the promotion and facilitation of access to SP programs
      such as employment and entrepreneurship opportunities, social security
      schemes, social services, and insurance systems.
  - text: >-
      environmental and climate awareness, public participation of youth
      organizations and different local actors, teacher training in
      environmental education for climate change, training and technical
      assistance for projects that allow communities and citizens to access and
      acquire knowledge of environmental issues and of climate change. The
      process of institutionalization of environmental education and culture as
      public policy will promote the consolidation of comprehensive regulatory
      frameworks, the incorporation of the environmental and climate dimension
      into educational and cultural policies, the training of technical
      management teams and policy design.
  - text: >-
      SocialSecurityandCommunityDevelopment • Financially sound National
      Insurance Services (NIS). • Extensive public assistance programmes for
      indigent and economically disadvantaged persons. • Rich cultural heritage.
  - text: >-
      Incorporate a mechanism for monitoring and reviewing marine protected
      areas management plans involving local populations;. Adopt a law to
      regulate marine spatial planning by 2022 and/or revision and adaptation of
      the current basic law of territorial planning and urban planning to
      include maritime spatial planning (a tool that allows the zoning of
      activities to be developed at sea; law defining the use of maritime space
      and maritime spatial planning);.
pipeline_tag: text-classification
inference: false
base_model: sentence-transformers/all-mpnet-base-v2

SetFit with sentence-transformers/all-mpnet-base-v2

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/all-mpnet-base-v2 as the Sentence Transformer embedding model. A SetFitHead 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/all-mpnet-base-v2
Classification head: a SetFitHead instance
Maximum Sequence Length: 384 tokens
Number of Classes: 18 classes

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("leavoigt/vulnerability_multilabel_updated")
# Run inference
preds = model("SocialSecurityandCommunityDevelopment • Financially sound National Insurance Services (NIS). • Extensive public assistance programmes for indigent and economically disadvantaged persons. • Rich cultural heritage.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	21	72.7143	238

Training Hyperparameters

batch_size: (16, 2)
num_epochs: (1, 0)
max_steps: -1
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: 0.01
seed: 42
eval_max_steps: -1
load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0006	1	0.3244	-
0.6309	1000	0.0331	0.1204

Framework Versions

Python: 3.10.12
SetFit: 1.0.3
Sentence Transformers: 2.3.1
Transformers: 4.37.2
PyTorch: 2.1.0+cu121
Datasets: 2.3.0
Tokenizers: 0.15.2

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}
}