metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - accuracy
widget:
  - text: >-
      I'm sorry. The person you are trying to reach has a voice mailbox that has
      not been set up yet. Please try your call 
  - text: 'For calling WL Gore and Associates Incorporated. Please wait '
  - text: 'Hello. Please state your name after the tone, and Google Voice will try '
  - text: >-
      Thank you for calling Stanley Black and Decker. For the company directory,
      press 1. For investor relations, press 2. 
  - text: >-
      Sorry. Chris Trent is not available. Record your message at the tone. When
      you are finished, hang up or press pound for more options. 
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 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
voicemail	'Your call has been forwarded to an automated voice messaging system. 6 ' 'Please leave your message for 8083526996. ' "This is Bart Jumper. I'm sorry I missed your call. Please leave your name and number, and I'll return your call as soon as I "
phone_tree	'Thank you for calling Periton. A next ' 'Thank you for calling Signifide. Our main number has changed. The new number is eight six six two ' 'Thank you for calling Icahn Health and Fitness. If you know the extension you wish to reach, '

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("nikcheerla/amd-full-phonetree-v1")
# Run inference
preds = model("For calling WL Gore and Associates Incorporated. Please wait ")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	1	14.7789	214

Label	Training Sample Count
phone_tree	4979
voicemail	5519

Training Hyperparameters

batch_size: (32, 32)
num_epochs: (3, 3)
max_steps: -1
sampling_strategy: oversampling
num_iterations: 20
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: True
warmup_proportion: 0.1
seed: 42
eval_max_steps: -1
load_best_model_at_end: True

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0001	1	0.2196	-
1.0	13123	0.0001	0.1209
2.0	26246	0.0	0.1101
3.0	39369	0.0446	0.1108

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.12
SetFit: 1.0.1
Sentence Transformers: 2.2.2
Transformers: 4.35.2
PyTorch: 2.0.1+cu118
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}
}