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: >
Sure! Support it 100 percent. Good opportunity to watch a president follow
the law and accept consequences rather that whine and complain like a
toddler.
- text: >
Steve During Prime Minister Ardern's leadership, the first eighteen months
of the pandemic resulted in virtually no cases of Covid or Covid deaths
and New Zealand has suffered less than twenty-five hundred deaths from
Covid to date. After the deadliest shooting in New Zealand's history, in
her role as the youngest leader ever elected in the country, she mourned
with a grief-stricken nation and responded to the crisis by changing the
gun laws in seven days. It makes me want to weep thinking of the
compassionate and intelligent leadership New Zealand has enjoyed under
Prime Minister Ardern. It's a magnificent place and she is a credit to her
country.
- text: >
I am very happy for her. I think she has made absolutely the right
decision. I have been very critical of some of the policies she endorsed
although I understood the reasoning behind them. She was a shining beacon
in the earlier years but at some point she lost her firm grip on principle
and became captive to doctrinaire theories that did not always serve the
country despite the best of intentions. Ardern is a very great soul and I
don't doubt that there is an even more brilliant future still ahead of
her, one that will allow her to lead on the international stage without
compromising her personal principles. Meantime she deserves time to
regroup, heal, and spend precious time with her family. Personally I hope
Chris Hipkins steps into her shoes although he also has a young family and
would have to make similar sacrifices. He has shown himself to be very
able and decent, and like Ardern is a master communicator.
- text: >
I spoke with an elderly gentlemen with a British accent today in the local
library here in New Zealand who said he had never voted for Ardern because
she had been living in an unmarried relationship and to compound this
issue had insulted the Queen by appearing before her while pregnant. A
point that keeps being overlooked is that Ardern leaves office not only
with record low unemployment but having set in train a major social
housing program and removed restrictions that prevented housing
intensification. These in time will hopefully reduce both house prices and
rents, thus alleviating child poverty. Ardern also dramatically raised the
insulation standards for new houses. which will mean that they are warmer
and healthierArdern totally replaced the bureaucratic Resource Management
Act which had been blamed for nearly 20 years by business and right wing
commentators for preventing development. Legislation was also passed that
will fund the clean-up of the country’s woeful drinking, stormwater and
sewerage systems. Compared with her predecessors John Key and Bill
English, Ardern at least tried to deal with many of the country's long
standing issues. While still the popular preferred prime minister leaving
now removes herself as a lightning rod for the haters while allowing her
successor to drop any upcoming planned legislation that is considered to
be controversial. At the same time the successor has 9 months to develop
their relationship with voters.
- text: >
Jeff In some states, felons are not allowed to vote after they've
completed their sentences. See Florida. Florida wants felons to pay fines
after they've been released, only in most cases, the government can't tell
the formerly imprisoned how much is owed.
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: 1
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 | 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("davidadamczyk/setfit-model-5")
# Run inference
preds = model("Sure! Support it 100 percent. Good opportunity to watch a president follow the law and accept consequences rather that whine and complain like a toddler.
")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 16 | 90.75 | 249 |
| 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 | 0.3081 | - |
| 0.0833 | 50 | 0.1044 | - |
| 0.1667 | 100 | 0.001 | - |
| 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}
}