README.md

metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
base_model: sentence-transformers/paraphrase-mpnet-base-v2
metrics:
  - accuracy
widget:
  - text: >-
      Anyone 170 or below that takes Wegovy? Well it is, Ozempic and Wegovy are
      actually the same drug. So if you are taking Wegovy, it is affecting your
      insulin and glucose. I was on Trulicity, insurance made me switch to
      wegovy.
  - text: >-
      Has anyone tried ozempic with pcos? I experienced terrible exhaustion on
      Ozempic. I don't on Mounjaro. Overall, I've had way fewer side effects on
      Mounjaro.
pipeline_tag: text-classification
inference: true
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: 1
            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:

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 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
0	'I’m on Mounjaro 12.5, started 3 weeks ago. Before that I was on Ozempic (max dose), and Bydureon before that. I’ve been on GLP-1 drugs for probably 6 years. Had terrible gastro side effects for months after starting Bydureon, but no gastro side effects on anything since those resolved. I switched from Ozempic to Mounjaro because Ozempic was no longer keeping my a1c controlled. The first couple of weeks on Mounjaro 12.5 I had overwhelming fatigue, but that has improved a little. But I have noticed I am very, very angry on this dose.' 'What will obesity rates be like in 2100 - Trust me, Ozempic (Semaglitude) is NOT the "Miracle Drug" that you think it is. Take it from someone who is currently taking it. Sure, it helps some.' "Yup, I'm on CRF as well and have probably gained about 50 lbs over time. It sucks. I'm currently taking a smaller dose of mirtazapine and am also on ozempic for weight loss."
1	"What's the cheapest way possible to get semaglutide? I'm currently taking 2000mg of Metformin with compounded semaglutide with no issues. I have PCOS and not Type 2, so I sadly don't qualify for Ozempic through insurance." 'I know 2 people that took Ozempic and quit because they were going downhill on it' 'New Ozempic and Wegovy side effects come to light - After I stopped taking it I developed Gallbladder disease and Pancreatitis'

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("bhaskars113/ozempic-taking-medications-classifier")
# Run inference
preds = model("Has anyone tried ozempic with pcos? I experienced terrible exhaustion on Ozempic. I don't on Mounjaro. Overall, I've had way fewer side effects on Mounjaro.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	13	32.7931	94

Label	Training Sample Count
0	15
1	14

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
0.0137	1	0.2348	-
0.6849	50	0.0013	-

Framework Versions

• Python: 3.10.12
• SetFit: 1.0.3
• Sentence Transformers: 2.7.0
• Transformers: 4.40.0
• PyTorch: 2.2.1+cu121
• Datasets: 2.19.0
• Tokenizers: 0.19.1

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}
}