BioLORD_better_doze / README.md
allmin's picture
Add SetFit model
b2d48bc verified
metadata
library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
datasets:
  - SetFit/SentEval-CR
metrics:
  - accuracy
widget:
  - text: >-
      you can take pic of your friends and the picture will pop up when they
      call .
  - text: the speakerphone , the radio , all features work perfectly .
  - text: >-
      a ) the picture quality ( color and sharpness of focusing ) are so great ,
      it completely eliminated my doubt about digital imaging -- - how could one
      eat rice one grain at a time : - ) )
  - text: >-
      so far the dvd works so i hope it does n 't break down like the reviews i
      've read .
  - text: >-
      i have a couple hundred contacts and the menu loads within a few seconds ,
      no big deal .
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: SetFit/SentEval-CR
          type: SetFit/SentEval-CR
          split: test
        metrics:
          - type: accuracy
            value: 0.8711819389110226
            name: Accuracy

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

This is a SetFit model trained on the SetFit/SentEval-CR 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 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
1
  • '* slick-looking design and improved interface'
  • 'as for bluetooth , no problems at all .'
  • '2 ) storage capacity'
0
  • "the day finally arrived when i was sure i 'd leave sprint ."
  • "neither message was answered ( they ask for 24 hours before replying - i 've been waiting 27 days . )"
  • 'only problem is that is a bit heavy .'

Evaluation

Metrics

Label Accuracy
all 0.8712

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("allmin/BioLORD_better_doze")
# Run inference
preds = model("the speakerphone , the radio , all features work perfectly .")

Training Details

Training Set Metrics

Training set Min Median Max
Word count 4 18.0625 44
Label Training Sample Count
0 7
1 9

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
0.025 1 0.226 -

Framework Versions

  • Python: 3.9.18
  • SetFit: 1.0.3
  • Sentence Transformers: 2.2.2
  • Transformers: 4.37.1
  • PyTorch: 2.1.2+cu121
  • Datasets: 2.18.0
  • Tokenizers: 0.15.1

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}
}