metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - accuracy
widget:
  - text: Can you name three different types of fruits?
  - text: What is the capital city of your state?
  - text: If 2 apples cost $1, how much would 5 apples cost?
  - text: >-
      John had 8 marbles. He lost 4 marbles and then got 3 new ones. How many
      marbles does John have now?
  - text: What is the name of the civil rights leader who said 'I have a dream'?
pipeline_tag: text-classification
inference: true
base_model: sentence-transformers/all-MiniLM-L6-v2
model-index:
  - name: SetFit with sentence-transformers/all-MiniLM-L6-v2
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 1
            name: Accuracy

SetFit with sentence-transformers/all-MiniLM-L6-v2

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/all-MiniLM-L6-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/all-MiniLM-L6-v2
Classification head: a LogisticRegression instance
Maximum Sequence Length: 256 tokens
Number of Classes: 2 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
math	'Which unit would you use to measure how much milk you need for your cereal: cups or gallons?' 'What is the volume of a cube with side length 4 cm?' 'If school starts at 8:30 AM and ends at 3:15 PM, how many hours are there in a school day?'
non_math	'What is the name of the long river that runs through the middle of the US?' 'What do we call the action of objects changing their position?' 'What is the currency used in Japan?'

Evaluation

Metrics

Label	Accuracy
all	1.0

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("serdarcaglar/primary-school-math-question")
# Run inference
preds = model("What is the capital city of your state?")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	1	12.5378	33

Label	Training Sample Count
math	141
non_math	97

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
seed: 42
eval_max_steps: -1
load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0017	1	0.3115	-
0.0840	50	0.1498	-
0.1681	100	0.0127	-
0.2521	150	0.0056	-
0.3361	200	0.0019	-
0.4202	250	0.0007	-
0.5042	300	0.0016	-
0.5882	350	0.0019	-
0.6723	400	0.0005	-
0.7563	450	0.0009	-
0.8403	500	0.0009	-
0.9244	550	0.0008	-

Framework Versions

Python: 3.10.12
SetFit: 1.0.3
Sentence Transformers: 2.6.1
Transformers: 4.38.2
PyTorch: 2.2.1+cu121
Datasets: 2.18.0
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}
}