metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - accuracy
widget:
  - text: >-
      A gentle nudge to complete the healthcare webinar questionnaire sent last
      week.
  - text: Sudden severe chest pain, suspecting a cardiac emergency.
  - text: >-
      Annual physical examination due in Tuesday, March 05. Please book an
      appointment.
  - text: Please confirm your attendance at the lifestyle next month.
  - text: Could you verify your emergency contact details in our records?
pipeline_tag: text-classification
inference: true
base_model: sentence-transformers/paraphrase-mpnet-base-v2
model-index:
  - name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 0.9633333333333334
            name: Accuracy

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

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/paraphrase-mpnet-base-v2 as the Sentence Transformer embedding model. A LogisticRegression 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-mpnet-base-v2
Classification head: a LogisticRegression instance
Maximum Sequence Length: 512 tokens
Number of Classes: 3 classes

Model Sources

Repository: SetFit on GitHub
Paper: Efficient Few-Shot Learning Without Prompts
Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts

Model Labels

Label	Examples
2	'Rapid onset of confusion and weakness, urgent evaluation needed.' 'Unconscious patient found, immediate medical response required.' 'Urgent: Suspected heart attack, immediate medical attention required.'
1	'Reminder: Your dental check-up is scheduled for Monday, February 05.' 'Reminder: Your dental check-up is scheduled for Saturday, February 24.' 'Nutritionist appointment reminder for Sunday, January 21.'
0	'Could you verify your lifestyle contact details in our records?' 'Kindly update your emergency contact list at your earliest convenience.' 'We request you to update your wellness information for our records.'

Evaluation

Metrics

Label	Accuracy
all	0.9633

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("konsman/setfit-messages-generated-v2")
# Run inference
preds = model("Sudden severe chest pain, suspecting a cardiac emergency.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	7	9.25	12

Label	Training Sample Count
0	8
1	8
2	8

Training Hyperparameters

batch_size: (8, 8)
num_epochs: (2, 2)
max_steps: -1
sampling_strategy: oversampling
num_iterations: 40
body_learning_rate: (2.2041595048800003e-05, 2.2041595048800003e-05)
head_learning_rate: 2.2041595048800003e-05
loss: CosineSimilarityLoss
distance_metric: cosine_distance
margin: 0.25
end_to_end: False
use_amp: False
warmup_proportion: 0.1
seed: 42
eval_max_steps: -1
load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0042	1	0.1564	-
0.2083	50	0.0039	-
0.4167	100	0.0006	-
0.625	150	0.0003	-
0.8333	200	0.0003	-
1.0417	250	0.0002	-
1.25	300	0.0002	-
1.4583	350	0.0002	-
1.6667	400	0.0002	-
1.875	450	0.0002	-

Framework Versions

Python: 3.10.12
SetFit: 1.0.2
Sentence Transformers: 2.2.2
Transformers: 4.35.2
PyTorch: 2.1.0+cu121
Datasets: 2.16.1
Tokenizers: 0.15.0

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}
}