metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - f1
widget:
  - text: >-
      This also goes for bigger issues like foreign policy as well; multiple
      full-scale invasions of Syria have been prevented because of information
      that the alternative media made viral.
  - text: >
      Yesterday’s State of the Union address issued by Donald Trump represented
      a refreshing break from the eight years of pusillanimous foreign policies
      pursued by past administration.
  - text: There are 2 trillion Google searches per day.
  - text: >-
      Westerville Officers Eric Joering, 39, and Anthony Morelli, 54, were
      killed shortly after noon Saturday in this normally quiet suburb while
      responding to a 911 hang-up call.
  - text: |
      Trump was right, Acosta is a "rude, terrible person."
pipeline_tag: text-classification
inference: true
model-index:
  - name: SetFit
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: f1
            value: 0.3371824480369515
            name: F1

SetFit

This is a SetFit model that can be used for Text Classification. 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
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
0.0	'Pamela Geller and Robert Spencer co-founded anti-Muslim group Stop Islamization of America.\n' 'He added: "We condemn all those whose behaviours and views run counter to our shared values and will not stand for extremism in any form."\n' 'Ms Geller, of the Atlas Shrugs blog, and Mr Spencer, of Jihad Watch, are also co-founders of the American Freedom Defense Initiative, best known for a pro-Israel "Defeat Jihad" poster campaign on the New York subway.\n'
1.0	'On both of their blogs the pair called their bans from entering the UK "a striking blow against freedom" and said the "the nation that gave the world the Magna Carta is dead".\n' 'A researcher with the organisation, Matthew Collins, said it was "delighted" with the decision.\n' 'Lead attorney Matt Gonzalez has argued that the weapon was a SIG Sauer with a "hair trigger in single-action mode" — a model well-known for accidental discharges even among experienced shooters.\n'

Label

Examples

0.0

'Pamela Geller and Robert Spencer co-founded anti-Muslim group Stop Islamization of America.\n'
'He added: "We condemn all those whose behaviours and views run counter to our shared values and will not stand for extremism in any form."\n'
'Ms Geller, of the Atlas Shrugs blog, and Mr Spencer, of Jihad Watch, are also co-founders of the American Freedom Defense Initiative, best known for a pro-Israel "Defeat Jihad" poster campaign on the New York subway.\n'

1.0

'On both of their blogs the pair called their bans from entering the UK "a striking blow against freedom" and said the "the nation that gave the world the Magna Carta is dead".\n'
'A researcher with the organisation, Matthew Collins, said it was "delighted" with the decision.\n'
'Lead attorney Matt Gonzalez has argued that the weapon was a SIG Sauer with a "hair trigger in single-action mode" — a model well-known for accidental discharges even among experienced shooters.\n'

Evaluation

Metrics

Label	F1
all	0.3372

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("anismahmahi/Roberta-large-G3-setfit-model")
# Run inference
preds = model("There are 2 trillion Google searches per day.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	1	26.8625	105

Label	Training Sample Count
0	200
1	200

Training Hyperparameters

batch_size: (8, 8)
num_epochs: (3, 3)
max_steps: -1
sampling_strategy: oversampling
num_iterations: 5
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
eval_max_steps: -1
load_best_model_at_end: True

Training Results

Epoch	Step	Training Loss	Validation Loss
0.002	1	0.3467	-
0.1	50	0.2333	-
0.2	100	0.237	-
0.3	150	0.2466	-
0.4	200	0.208	-
0.5	250	0.2121	-
0.6	300	0.0076	-
0.7	350	0.0011	-
0.8	400	0.0007	-
0.9	450	0.0002	-
1.0	500	0.0015	0.3342
1.1	550	0.0001	-
1.2	600	0.0002	-
1.3	650	0.0003	-
1.4	700	0.0003	-
1.5	750	0.0002	-
1.6	800	0.0002	-
1.7	850	0.0001	-
1.8	900	0.0001	-
1.9	950	0.0001	-
2.0	1000	0.0001	0.3303
2.1	1050	0.0	-
2.2	1100	0.0	-
2.3	1150	0.0001	-
2.4	1200	0.0	-
2.5	1250	0.0	-
2.6	1300	0.0	-
2.7	1350	0.0001	-
2.8	1400	0.0001	-
2.9	1450	0.0	-
3.0	1500	0.0	0.3327

The bold row denotes the saved checkpoint.

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}
}