luis-espinosa's picture
Add SetFit model
2267ac7 verified
|
raw
history blame
No virus
10.6 kB
---
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](https://github.com/huggingface/setfit) model that can be used for Text Classification. This SetFit model uses [thenlper/gte-small](https://huggingface.co/thenlper/gte-small) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) 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](https://www.sbert.net) 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:** [thenlper/gte-small](https://huggingface.co/thenlper/gte-small)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 512 tokens
- **Number of Classes:** 2 classes
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)
### Model Labels
| Label | Examples |
|:------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| 1 | <ul><li>'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 .'</li><li>'CVS Health announces CFO Shawn Guertin to take leave of absence . Senior Vice President of Corporate Finance, Tom Cowhey, has been appointed interim CFO . CEO of Oak Street Health Mike Pykosz has been named interim President of Health Services .'</li><li>'Walgreens Boots Alliance Inc. appointed Tim Wentworth as its next chief executive officer . The former CEO of pharmacy-benefits manager Express Scripts succeeds Rosalind Brewer, a longtime retail executive whose 2 1/2-year tenure saw the shares lose half their value .'</li></ul> |
| 0 | <ul><li>"Dove's Milk Chocolate Tiramisu Caramel Promises is debuting a new addition to its Promises line of sweets . Inspired by the Italian dessert, the candy features a tiramisu-flavored caramel center that is surrounded by milk chocolate . The new flavor features fried dough flavored cookies with a churro flavored crème ."</li><li>"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 ."</li><li>'CVS Health invests more than $3M to improve health outcomes in Phoenix Terms of use Photo and video available via the CVS health Newsroom are for'</li></ul> |
## Uses
### Direct Use for Inference
First install the SetFit library:
```bash
pip install setfit
```
Then you can load this model and run inference.
```python
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 .")
```
<!--
### Downstream Use
*List how someone could finetune this model on their own dataset.*
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## 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
```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}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->