metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - accuracy
widget:
  - text: UK's National Gallery in the pink
  - text: Regiments' group in poll move
  - text: Ad firm WPP's profits surge 15%
  - text: Ivanovic seals Canberra victory
  - text: Text message record smashed
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: 0.8878923766816144
            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: 5 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
4	'PC photo printers challenge pros' 'Doors open at biggest gadget fair' 'Progress on new internet domains'
0	'US interest rate rise expected' 'Russian oil merger excludes Yukos' 'Budget Aston takes on Porsche'
2	'Benitez issues warning to Gerrard' 'Wenger steps up row' 'Mansfield 0-1 Leyton Orient'
3	'Observers to monitor UK election' "Blair 'up for it' ahead of poll" "Hospital suspends 'no Welsh' plan"
1	'Oscars race enters final furlong' "Campaigners attack MTV 'sleaze'" 'Fightstar take to the stage'

Evaluation

Metrics

Label	Accuracy
all	0.8879

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("Kevinger/setfit-bbc-news")
# Run inference
preds = model("Text message record smashed")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	4	4.5625	7

Label	Training Sample Count
0	16
1	16
2	16
3	16
4	16

Training Hyperparameters

batch_size: (16, 2)
num_epochs: (1, 16)
max_steps: -1
sampling_strategy: oversampling
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: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0031	1	0.3227	-
0.1562	50	0.0136	-
0.3125	100	0.0024	-
0.4688	150	0.0013	-
0.625	200	0.001	-
0.7812	250	0.0009	-
0.9375	300	0.001	-

Framework Versions

Python: 3.10.12
SetFit: 1.0.3
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}
}