test_model / README.md
wikd's picture
Add SetFit model
c12251c verified
metadata
library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
base_model: distilbert/distilbert-base-uncased-finetuned-sst-2-english
datasets:
  - wikd/customer_data
metrics:
  - accuracy
widget:
  - text: I'm very satisfied with my purchase
  - text: The delivery was very quick!
  - text: The product is out of stock
  - text: The return process was easy
  - text: I changed my mind and want to cancel my order
pipeline_tag: text-classification
inference: true
model-index:
  - name: SetFit with distilbert/distilbert-base-uncased-finetuned-sst-2-english
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: wikd/customer_data
          type: wikd/customer_data
          split: test
        metrics:
          - type: accuracy
            value: 1
            name: Accuracy

SetFit with distilbert/distilbert-base-uncased-finetuned-sst-2-english

This is a SetFit model trained on the wikd/customer_data dataset that can be used for Text Classification. This SetFit model uses distilbert/distilbert-base-uncased-finetuned-sst-2-english 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:

  1. Fine-tuning a Sentence Transformer with contrastive learning.
  2. Training a classification head with features from the fine-tuned Sentence Transformer.

Model Details

Model Description

Model Sources

Model Labels

Label Examples
0
  • 'I need to speak to a real person, not a dumb machine.'
  • 'Stop with the automated nonsense and connect me to a human!'
  • 'Your automated system is beyond frustrating, let me talk to someone!'
1
  • 'I love your new product!'
  • 'The delivery was very quick!'
  • 'I would recommend this company to a friend'

Evaluation

Metrics

Label Accuracy
all 1.0

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("setfit_model_id")
# Run inference
preds = model("The product is out of stock")

Training Details

Training Set Metrics

Training set Min Median Max
Word count 4 10.0 14
Label Training Sample Count
0 46
1 6

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
0.0077 1 0.1479 -
0.3846 50 0.0008 -
0.7692 100 0.0005 -

Framework Versions

  • Python: 3.11.8
  • SetFit: 1.0.3
  • Sentence Transformers: 2.5.1
  • Transformers: 4.38.2
  • PyTorch: 2.2.1
  • Datasets: 2.18.0
  • Tokenizers: 0.15.2

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}
}