Efficient Few-Shot Learning Without Prompts
Paper
•
2209.11055
•
Published
•
4
This is a SetFit model that can be used for Text Classification. This SetFit model uses mini1013/master_domain 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:
| Label | Examples |
|---|---|
| 4.0 |
|
| 0.0 |
|
| 3.0 |
|
| 1.0 |
|
| 2.0 |
|
| Label | Accuracy |
|---|---|
| all | 1.0 |
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("mini1013/master_cate_sl15")
# Run inference
preds = model("주짓수 경량 도복 상하세트 훈련 남성 여성 통기성 스포츠/레저>수련용품>무도복")
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 3 | 9.7851 | 20 |
| Label | Training Sample Count |
|---|---|
| 0.0 | 9 |
| 1.0 | 70 |
| 2.0 | 9 |
| 3.0 | 70 |
| 4.0 | 70 |
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0222 | 1 | 0.4899 | - |
| 1.1111 | 50 | 0.4031 | - |
| 2.2222 | 100 | 0.0374 | - |
| 3.3333 | 150 | 0.0 | - |
| 4.4444 | 200 | 0.0 | - |
| 5.5556 | 250 | 0.0 | - |
| 6.6667 | 300 | 0.0 | - |
| 7.7778 | 350 | 0.0 | - |
| 8.8889 | 400 | 0.0 | - |
| 10.0 | 450 | 0.0 | - |
| 11.1111 | 500 | 0.0 | - |
| 12.2222 | 550 | 0.0 | - |
| 13.3333 | 600 | 0.0 | - |
| 14.4444 | 650 | 0.0 | - |
| 15.5556 | 700 | 0.0 | - |
| 16.6667 | 750 | 0.0 | - |
| 17.7778 | 800 | 0.0 | - |
| 18.8889 | 850 | 0.0 | - |
| 20.0 | 900 | 0.0 | - |
| 21.1111 | 950 | 0.0 | - |
| 22.2222 | 1000 | 0.0 | - |
| 23.3333 | 1050 | 0.0 | - |
| 24.4444 | 1100 | 0.0 | - |
| 25.5556 | 1150 | 0.0 | - |
| 26.6667 | 1200 | 0.0 | - |
| 27.7778 | 1250 | 0.0 | - |
| 28.8889 | 1300 | 0.0 | - |
| 30.0 | 1350 | 0.0 | - |
@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}
}