metadata
base_model: thenlper/gte-small
library_name: setfit
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: >-
Walgreens shares suffered their worst monthly decline in nearly five years
in August . In June, the company cut its full-year guidance to $4 to
$4.05, while FactSet earnings-per-share consensus is $4.01 . The company
has appointed Ginger Graham as interim CEO .
- text: >-
Walgreens CEO Tim Wentworth said he's committed to the company's strategy
of adding a range of care options atop its massive store network . He said
that his primary focus for now is to improve the firm's finances across
the board . The move comes as the holding company faces a tough consumer
spending environment as well as pressure to rein in costs .
- text: >-
Walgreens' 'non-drowsy' cough meds are anything but, lawsuit claims $3B
project with AbilityLab's Detroit outpost breaks ground this spring
There's a battle underway over medication abortion, the most common method
of terminating a pregnancy in the US . The Supreme Court is scheduled to
hear arguments on March 26 in a case that will determine how available
mifepristone will be . It would also open the door to challenges to other
FDA decisions .
- text: >-
Walgreens' new CEO Tim Wentworth says the pressure is on to develop new
drug pricing models . In his first earnings call as CEO, Mr.Wentworth said
"everything is on the table to deliver greater shareholder value" he noted
that "the fact that there may be some more marketplace pull there only
presents a sense of urgency"
- text: >-
Wentworth will become Walgreens CEO effective Oct. 23 . He is the former
CEO of Express Scripts, the pharmacy benefit manager acquired by Cigna in
2018 .
inference: true
SetFit with thenlper/gte-small
This is a SetFit model that can be used for Text Classification. This SetFit model uses thenlper/gte-small 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: thenlper/gte-small
- 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 |
|
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("luis-espinosa/gte-small_lc_summs_setfit")
# Run inference
preds = model("Wentworth will become Walgreens CEO effective Oct. 23 . He is the former CEO of Express Scripts, the pharmacy benefit manager acquired by Cigna in 2018 .")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 26 | 52.6190 | 80 |
Label | Training Sample Count |
---|---|
0 | 11 |
1 | 10 |
Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (3, 3)
- 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 |
---|---|---|---|
0.0189 | 1 | 0.3391 | - |
0.9434 | 50 | 0.0106 | - |
1.8868 | 100 | 0.001 | - |
2.8302 | 150 | 0.0005 | - |
Framework Versions
- Python: 3.10.12
- SetFit: 1.0.3
- Sentence Transformers: 3.0.1
- Transformers: 4.41.2
- PyTorch: 2.3.1+cu121
- Datasets: 2.19.2
- 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}
}