metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
widget:
  - text: 'mar | : { ‘ : Ui * | z : gg ‘ey bal _ . '' '
  - text: www.statista.fr
  - text: French Polynesia
  - text: 'SHOP DRESS SHIRTS > '
  - text: '’ \ Rather Go Naked a Wé FE '
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: 0.9
            name: Accuracy
          - type: precision
            value: 0.8823529411764706
            name: Precision
          - type: recall
            value: 0.8823529411764706
            name: Recall
          - type: f1
            value: 0.8823529411764706
            name: F1

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: 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
True	'WHEN DID HE STOP TREATING YOU LIKE A PRINGESS? ' 'Samsung” 65" Class Curved 4K Ultra HD ' 'Finger Lickin’ Mini Fillet Burge: '
False	'speedtest.net' 'Dane z przeglądania i interakcji' 'Announcements'

Evaluation

Metrics

Label	Accuracy	Precision	Recall	F1
all	0.9	0.8824	0.8824	0.8824

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("setfit_model_id")
# Run inference
preds = model("www.statista.fr")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	1	8.6188	267

Label	Training Sample Count
False	77
True	83

Training Hyperparameters

batch_size: (16, 2)
num_epochs: (1, 16)
max_steps: -1
sampling_strategy: oversampling
num_iterations: 20
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: 0.1
seed: 42
run_name: PG-OCR-test-2
eval_max_steps: -1
load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0025	1	0.3647	-
0.125	50	0.2765	-
0.25	100	0.0519	-
0.375	150	0.0045	-
0.5	200	0.055	-
0.625	250	0.0033	-
0.75	300	0.1017	-
0.875	350	0.02	-
1.0	400	0.0015	-

Framework Versions

Python: 3.11.0
SetFit: 1.0.3
Sentence Transformers: 2.3.0
Transformers: 4.37.2
PyTorch: 2.2.1+cu121
Datasets: 2.16.1
Tokenizers: 0.15.1

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}
}