metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
datasets:
  - HelgeKn/SATHAME-generator-train
metrics:
  - accuracy
widget:
  - text: >-
      `` So crunch , crunch , crunch , bang , bang , bang -- here come the
      ringers from above , making a very obvious exit while the congregation is
      at prayer , `` he says . 
  - text: 'The others here today live elsewhere . '
  - text: >-
      Then , at a signal , the ringers begin varying the order in which the
      bells sound without altering the steady rhythm of the striking . 
  - text: >-
      Mr. Hammond worries that old age and the flightiness of youth will
      diminish the ranks of the East Anglian group that keeps the Aslacton bells
      pealing . 
pipeline_tag: text-classification
inference: true
base_model: sentence-transformers/paraphrase-mpnet-base-v2

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

This is a SetFit model trained on the HelgeKn/SATHAME-generator-train 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 SetFitHead 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 SetFitHead instance
Maximum Sequence Length: 512 tokens
Number of Classes: 4 classes
Training Dataset: HelgeKn/SATHAME-generator-train

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
3	'The art of change-ringing is peculiar to the English , and , like most English peculiarities , unintelligible to the rest of the world . ' 'Of all scenes that evoke rural England , this is one of the loveliest : An ancient stone church stands amid the fields , the sound of bells cascading from its tower , calling the faithful to evensong . ' 'In the tower , five men and women pull rhythmically on ropes attached to the same five bells that first sounded here in 1614 . '
1	'The parishioners of St. Michael and All Angels stop to chat at the church door , as members here always have . ' 'History , after all , is not on his side . ' "According to a nationwide survey taken a year ago , nearly a third of England 's church bells are no longer rung on Sundays because there is no one to ring them . "
2	'Now , only one local ringer remains : 64-year-old Derek Hammond . ' 'The others here today live elsewhere . ' 'No one speaks , and the snaking of the ropes seems to make as much sound as the bells themselves , muffled by the ceiling . '
0	'`To ring for even one service at this tower , we have to scrape ,` says Mr. Hammond , a retired water-authority worker . `` ' 'When their changes are completed , and after they have worked up a sweat , ringers often skip off to the local pub , leaving worship for others below . ' "Two years ago , the Rev. Jeremy Hummerstone , vicar of Great Torrington , Devon , got so fed up with ringers who did n't attend service he sacked the entire band ; the ringers promptly set up a picket line in protest . "

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("HelgeKn/Testing-blub")
# Run inference
preds = model("The others here today live elsewhere . ")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	8	27.275	45

Label	Training Sample Count
0	10
1	10
2	10
3	10

Training Hyperparameters

batch_size: (16, 16)
num_epochs: (2, 2)
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
0.01	1	0.2799	-
0.5	50	0.1155	-
1.0	100	0.0023	-
1.5	150	0.0008	-
2.0	200	0.0017	-

Framework Versions

Python: 3.9.13
SetFit: 1.0.1
Sentence Transformers: 2.2.2
Transformers: 4.36.0
PyTorch: 2.1.1+cpu
Datasets: 2.15.0
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}
}