metadata
base_model: sentence-transformers/all-mpnet-base-v2
library_name: setfit
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: >
Alexis it Doesn’t Have To End Georgiawas invaded by Russia and lost its
territoryof Ossetia and Abkhazia. What did USAdo? It condemned the
invasion by issuinga statement. George Bush and Putin, bothguests at
Beijing Olympic opening ceremony,argued. Georgia appreciates.
- text: >
DLI believe she also married Aristotle Onassis, who owned the world's
largest private shipping fleet -- that may have helped finance her other
life choices...
- text: >
Remember watching this movie with my wife as newly weds in 1995. Wonderful
evergreen film. Shahrukh was the son every father wants. And every girl
wants as a boyfriend or husband. True love. The relationship between
Anupam Kher and his son Shahrukh is pleasant and different than usual
Punjabi father-son distant relationships. Music is beautiful! My children
love this movie as well. I could watch it anytime-does not seem old or
dated. Thank you Yash Chopra, Aditya Chopra, Shahrukh, Kajol and all of
the team who brought us this beautiful human drama!
- text: >
In the photo of the D'Alesandro family with Pres. Kennedy, I think it is
telling that Mrs. D'Alesandro is doing the "adoring" look at Mr.
D'Alesandro. Par for the course for a 1961 pol's wife.Meanwhile their
21-year-old daughter Nancy already has her piercing eyes unabashedly fixed
right on Kennedy. You can almost see her thinking, "This powerful man can
do great things for the country. How do I get there?"And she did get there
-- to within a couple heartbeats of the Presidency, and arguably a
position far more powerful and effective over her career than if she'd
taken a term in the White House.
- text: >
Why is it that grown men feel free to do these sorts of things to young
girls and that societies tolerate it? Why is the girl the one who is put
on trial instead of the man/men who are responsible for what they did to
her? Why is her life ruined? Why are women forced to prove their virtue
over and over after they've been sexually assaulted by a husband, a
relative, a male friend, or a stranger? The worst of all is that the
girls, who are too young to marry, can still become pregnant and be forced
to carry the pregnancy to term. What does it do to both the children when
one is the result of rape? How does one deal with a child who exists
through no fault of its own? We know this happens all over the world. It
happens here too. Even if we're a rich country and have "enlightened"
attitudes, when we deny women of any age the right to control their
reproductive lives, we are showing exactly how little we think of women.
On a personal note, my parents didn't want to have me when they did. When
I was 16 my mother told me, in a fit of anger, that if it weren't for the
abortion laws (in the 1950s) I wouldn't be here. But I was not a child of
rape. I can't imagine how that feels for the victim or the child (who is
also a victim). Is the answer education for both boys and girls? Or is
it forcing a real change in the attitudes societies have towards half of
their population, the half that does much of the caring, loving, and
raising of children?
inference: true
model-index:
- name: SetFit with sentence-transformers/all-mpnet-base-v2
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 0.9
name: Accuracy
SetFit with sentence-transformers/all-mpnet-base-v2
This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/all-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:
- 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: sentence-transformers/all-mpnet-base-v2
- Classification head: a LogisticRegression instance
- Maximum Sequence Length: 384 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 |
---|---|
yes |
|
no |
|
Evaluation
Metrics
Label | Accuracy |
---|---|
all | 0.9 |
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("davidadamczyk/setfit-model-9")
# Run inference
preds = model("DLI believe she also married Aristotle Onassis, who owned the world's largest private shipping fleet -- that may have helped finance her other life choices...
")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 37 | 170.9 | 276 |
Label | Training Sample Count |
---|---|
no | 18 |
yes | 22 |
Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (1, 1)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 120
- 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
- l2_weight: 0.01
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: False
Training Results
Epoch | Step | Training Loss | Validation Loss |
---|---|---|---|
0.0017 | 1 | 0.5127 | - |
0.0833 | 50 | 0.2133 | - |
0.1667 | 100 | 0.0057 | - |
0.25 | 150 | 0.0002 | - |
0.3333 | 200 | 0.0001 | - |
0.4167 | 250 | 0.0001 | - |
0.5 | 300 | 0.0001 | - |
0.5833 | 350 | 0.0001 | - |
0.6667 | 400 | 0.0001 | - |
0.75 | 450 | 0.0001 | - |
0.8333 | 500 | 0.0001 | - |
0.9167 | 550 | 0.0 | - |
1.0 | 600 | 0.0 | - |
Framework Versions
- Python: 3.10.13
- SetFit: 1.1.0
- Sentence Transformers: 3.0.1
- Transformers: 4.45.2
- PyTorch: 2.4.0+cu124
- Datasets: 2.21.0
- Tokenizers: 0.20.0
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}
}