metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
datasets:
  - ethos
metrics:
  - accuracy
widget:
  - text: >-
      A solution to the U.S. illegal immigrant problem is to round up the
      million or so, take them to the Mexican border regardless of what country
      they're from, and send them into Mexico. Maybe then when the Mexican
      border is over-run with immigrants will Mexico understand and help pay for
      a wall.
  - text: an Asian Moe Howard piece of shit
  - text: >-
      ONLY LEGAL IMMIGRANTS... Like the hero officer Singh murdered in the line
      of duty.    NO TO ILLEGAL ALIENS THEY DO NOT BELONG HERE. Deport today
  - text: >-
      Jewish terrorist are killing innocent Palastinan who can't defend
      themselves...
  - text: >-
      Killing me to see gays treated like that. I think lesbians are being more
      privileged by people
pipeline_tag: text-classification
inference: false
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: ethos
          type: ethos
          split: test
        metrics:
          - type: accuracy
            value: 0.3973333333333333
            name: Accuracy

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

This is a SetFit model trained on the ethos dataset that can be used for Text Classification. This SetFit model uses sentence-transformers/paraphrase-mpnet-base-v2 as the Sentence Transformer embedding model. A OneVsRestClassifier 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 OneVsRestClassifier instance
Maximum Sequence Length: 512 tokens
Training Dataset: ethos

Model Sources

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

Evaluation

Metrics

Label	Accuracy
all	0.3973

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-ethos-multilabel-example")
# Run inference
preds = model("an Asian Moe Howard piece of shit")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	3	14.8906	54

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
0.0063	1	0.3036	-
0.3125	50	0.1657	-
0.625	100	0.0897	-
0.9375	150	0.028	-

Framework Versions

Python: 3.10.12
SetFit: 1.0.1
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}
}