metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - accuracy
widget:
  - text: >-
      "She sums up this theme with this pithy quote: \\\\\The first two letters
      of Fundamentalist are F-U.\\\\\""  However, these are the parents who drop
      everything to spend weeks caring for her when she is near death and all
      the friends from her newly emancipated life are missing in action."""
  - text: >-
      This was a christmas gift for my son , he couldn't wait to get it home and
      set it up and watch movies and play video games on it...when he did he was
      speachless.
  - text: >-
      The shorts are made out of a good, durable material but not so stiff that
      you feel like you can't move.
  - text: >-
      The only problem I knew I was going to have upfront was on the reciever
      end of things as I needed an extra set of speaker outputs,but the
      Monoprice 4ch speaker selector (#9995) took care of that deal.
  - text: This book is so good, I have to rave!
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: 0.7018
            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: 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
0	'Bank and Gaza city of thompson falls in love with your kindle fire and rescue plan for the most important thing is the kindle fire department for sure to check it out for sure to use none of them' "I really wanted green, really wanted beige, really wanted white didn't get any of those colors I got grey brown red instead." 'My only complaint is that I would like more colours please!!!'
1	'I WOULD BUY MORE IN THE FUTURE FOR MY OWN REAL TREE.' 'I had to give this item one star but if there was a negative 5 star rating I would have chosen that.' 'The only thing I would have like for it to have a hole in the middle so I can put the stopper in without removing the mat.'

Evaluation

Metrics

Label	Accuracy
all	0.7018

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("vidhi0206/setfit-paraphrase-mpnet-amazoncf")
# Run inference
preds = model("This book is so good, I have to rave!")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	9	19.875	39

Label	Training Sample Count
0	8
1	8

Training Hyperparameters

batch_size: (8, 8)
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
0.0125	1	0.1979	-
0.625	50	0.0022	-

Framework Versions

Python: 3.8.10
SetFit: 1.0.3
Sentence Transformers: 2.3.1
Transformers: 4.37.2
PyTorch: 2.2.0+cu121
Datasets: 2.17.0
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}
}