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: >
My wife is a horder. she spends hours each week sorting through her piles,
moving them from one room to another, looking through things and trying to
find things that have been lost. I've tried to tell her that if you don't
have all this crap you don't have to take time to move and remove it. But
it doesn't do any good. I feel bad for her as her stuff rules her life.
Yesterday i found a bowl of batteries that she is saving because she can't
find her battery tester to tell which batteries are good or not. i wanted
to buy a new battery tester so we could test the batteries and throw out
the dead ones, but she said why buy a tester when she knows that she has
one somewhere, she just has to find it. This is typical. I keep my office
clean and retreat in there, although she occasionally will "clean up" by
throwing her things into my office just "temporarily" and gets mad at me
when i move them back. i love her, I hate her crap.
- text: >
If we were having two commercial airplane crashes per day that killed 500
people and we hadn’t figured a way to stop it after three years, we
wouldn’t just declare the emergency over and pretend that is the new
normal. The emergency with covid isn’t over, we have simply given up and
surrendered to the virus.
- text: >
The article might have noted that 59 members of the German military died
on active service in Afghanistan, with 245 WIA.It had also taken part in
the NATO war in Kosovo in 1999. This included Luftwaffe aircraft bombing
Belgrade (very ironically).
- text: >
Jen that was a prop plane.in Buffalo....but still awfulAlso there was a
Delta jet accident in 2006 on kentucky ...the plane took of on the wrong
runway...49 killed
- text: >
To make a blanket statement that most juveniles who sexually abuse rarely
abuse as adults does an extreme disservice to the questioner, your
readers, and to the limited but complex research on the topic. This
research does not definitively support your claim. Remember that, as in
this case, most cases of sexual abuse by juveniles goes unreported.
Studies asking adult abusers about their juvenile actions, in fact,
indicate the opposite of your claim. See <a
href="https://smart.ojp.gov/somapi/chapter-3-recidivism-juveniles-who-commit-sexual-offenses"
target="_blank">https://smart.ojp.gov/somapi/chapter-3-recidivism-juveniles-who-commit-sexual-offenses</a>Unfortunately,
family denial denies children treatment, denies the system accurate
statistics, research, and informed approaches to treatment, and denies
betrothed people information and conversations that could prevent the
secret generational continuation of sexual abuse.If the sister-in-law had
been able to share her secret with your questioner, family repercussions
would likely have been severe. There are so many reasons abuse survivors
do not speak out. This kind of enforced secrecy allows child sexual abuse
to flourish. Still, sharing with her sister-in-law-to-be could have led to
valuable discussions and possibly delayed treatment for the man who had
abused his sister as a child. Perhaps it still can.
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-6")
# Run inference
preds = model("Jen that was a prop plane.in Buffalo....but still awfulAlso there was a Delta jet accident in 2006 on kentucky ...the plane took of on the wrong runway...49 killed
")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 9 | 127.2 | 277 |
| 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 | 0.4205 | - |
| 0.0833 | 50 | 0.1936 | - |
| 0.1667 | 100 | 0.0058 | - |
| 0.25 | 150 | 0.0003 | - |
| 0.3333 | 200 | 0.0002 | - |
| 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 | 0.0001 | - |
| 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}
}