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: >
There is, of course, much to digest. I hope that these rubes and those who
incited them are locked up, along with the fake electors and their
advisors, and those who conspired to convince elections officials to
violate the law, and finally, those who have and continue to threaten true
Americans just doing their constitution-based jobs. One thing jumps out.
Judge McFadden, who seems willing to demand that the government prove its
case beyond a reasonable doubt, also seems to be willing to sentence
convicted lawbreakers to serious time. That he acquitted the guy who
claimed the police let him gives me confidence that these are not sham
trials.The thing that I haven’t heard much about are the firings, trials,
convictions, and sentences of those LEOs who aided and abetted the
traitors. That would include the cops who let Mr. Martin enter the
Capitol, and those on Trump’s secret service detail who may have been
aiding Trump’s efforts to foment a riot.
- text: >
Both Vladimir Putin and Yevgeny Prigozhin are international war
criminals.Both also undermined US elections in favor of Trump.<a
href="https://www.reuters.com/world/us/russias-prigozhin-admits-interfering-us-elections-2022-11-07"
target="_blank">https://www.reuters.com/world/us/russias-prigozhin-admits-interfering-us-elections-2022-11-07</a>/
- text: >
Aaron 100 percent. citizens united was a huge win for Russian citizen Vlad
and Chinese citizen Xi.
- text: >
George Corsetti “Russia did NOT interfere in the 2016 election.”Sorry
George, this is not true. Read the Russia report, it details more than a
dozen felonies committed by TFG and his family and Campaign personnel
during the 2015/16 Campaign along with evidence of Russian hackers and
agents directly interfering in the 2016 election.
- text: >
Ms.Renkl does a nice job here, yet only hints at the decimation to public
schools, libraries, governance, and healthcare by Bill Lee and the Red
Legislators .Tennessee has a $50 B per year budget, $25B 0f this comes
from federal government. It is a wealthy state ranking in the top 16
economically and 3rd in fiscal stability ( USNews).The stability comes
from the egregious, wrongheaded use of federal monies earmarked for public
schools and healthcare,Governor controls all Federal school and
healthcare dollars rather than decimating to citizens. The US tax payer is
subsidizing this state as the Governor and legislators deny ACA low cost
insurance to WORKING poor and the Governor used for unrelated purposes. .
Federal public school monies are used to subsidize private schools and
Lee’s pet project:private DeVos/Hillsdale religious charter schools. US
tax payers should be made aware of the mishandling of our tax dollars in
support of the ultra conservative regime.
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: 0.8
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 | 0.8 |
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-2")
# Run inference
preds = model("Aaron 100 percent. citizens united was a huge win for Russian citizen Vlad and Chinese citizen Xi.
")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 6 | 80.325 | 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 | 0.4496 | - |
| 0.0833 | 50 | 0.1797 | - |
| 0.1667 | 100 | 0.0034 | - |
| 0.25 | 150 | 0.0003 | - |
| 0.3333 | 200 | 0.0002 | - |
| 0.4167 | 250 | 0.0002 | - |
| 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 | 0.0001 | - |
| 1.0 | 600 | 0.0001 | - |
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}
}