bhaskars113/ozempic-taking-medications-classifier-1.1

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
1	'I skipped this era, did she ever give a reason why she quit Ozempic? It’s fucking bananas to me she quit after finding something that works for the first time in a decade.' "I was on Ozempic and I lost 40lbs but it stopped there. It cost me $225 Canadian per month. I'm not taking anymore." "Maybe you can try Manjaro or a similar drug. Also, I'm sure they have Ozempic replacements in the works that will be released and you could try them."
0	'I was taking 4 metformin a day with morning blood sugar numbers around 200. I am currently on week 11 of taking Ozempic and only 1 metformin. My sugars are around 100 every morning. I finally feel good.' "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." "July 19 started new lifestyle. Down 30.6 lbs already - Interesting! I started off with Metaformin for a month, but wasn't happy with it, so my doc put me on Ozempic. I just started 0.25. Just for my own understanding, did you doc recommend taking both? If so, did he give any warnings about mixing the two?"

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-1.1")
# Run inference
preds = model("New Ozempic and Wegovy side effects come to light - After I stopped taking it I developed Gallbladder disease and Pancreatitis")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	14	36.4333	94

Label	Training Sample Count
0	15
1	15

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
0.0133	1	0.223	-
0.6667	50	0.0031	-

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}
}