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 |
|---|---|
| 6.0 |
|
| 4.0 |
|
| 3.0 |
|
| 1.0 |
|
| 0.0 |
|
| 5.0 |
|
| 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_bc27")
# Run inference
preds = model("반팔 부엉이레이스티 여성의류 임부복 임산부티셔츠 출산/육아 > 임부복 > 수유복")
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 8 | 15.0776 | 33 |
| Label | Training Sample Count |
|---|---|
| 0.0 | 70 |
| 1.0 | 70 |
| 2.0 | 70 |
| 3.0 | 70 |
| 4.0 | 70 |
| 5.0 | 70 |
| 6.0 | 70 |
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0104 | 1 | 0.4946 | - |
| 0.5208 | 50 | 0.4988 | - |
| 1.0417 | 100 | 0.348 | - |
| 1.5625 | 150 | 0.1457 | - |
| 2.0833 | 200 | 0.0479 | - |
| 2.6042 | 250 | 0.0175 | - |
| 3.125 | 300 | 0.0002 | - |
| 3.6458 | 350 | 0.0001 | - |
| 4.1667 | 400 | 0.0001 | - |
| 4.6875 | 450 | 0.0 | - |
| 5.2083 | 500 | 0.0 | - |
| 5.7292 | 550 | 0.0 | - |
| 6.25 | 600 | 0.0 | - |
| 6.7708 | 650 | 0.0 | - |
| 7.2917 | 700 | 0.0 | - |
| 7.8125 | 750 | 0.0 | - |
| 8.3333 | 800 | 0.0 | - |
| 8.8542 | 850 | 0.0 | - |
| 9.375 | 900 | 0.0 | - |
| 9.8958 | 950 | 0.0 | - |
| 10.4167 | 1000 | 0.0 | - |
| 10.9375 | 1050 | 0.0 | - |
| 11.4583 | 1100 | 0.0 | - |
| 11.9792 | 1150 | 0.0 | - |
| 12.5 | 1200 | 0.0 | - |
| 13.0208 | 1250 | 0.0 | - |
| 13.5417 | 1300 | 0.0 | - |
| 14.0625 | 1350 | 0.0 | - |
| 14.5833 | 1400 | 0.0 | - |
| 15.1042 | 1450 | 0.0 | - |
| 15.625 | 1500 | 0.0 | - |
| 16.1458 | 1550 | 0.0 | - |
| 16.6667 | 1600 | 0.0 | - |
| 17.1875 | 1650 | 0.0 | - |
| 17.7083 | 1700 | 0.0 | - |
| 18.2292 | 1750 | 0.0 | - |
| 18.75 | 1800 | 0.0 | - |
| 19.2708 | 1850 | 0.0 | - |
| 19.7917 | 1900 | 0.0 | - |
| 20.3125 | 1950 | 0.0 | - |
| 20.8333 | 2000 | 0.0 | - |
| 21.3542 | 2050 | 0.0 | - |
| 21.875 | 2100 | 0.0 | - |
| 22.3958 | 2150 | 0.0 | - |
| 22.9167 | 2200 | 0.0 | - |
| 23.4375 | 2250 | 0.0 | - |
| 23.9583 | 2300 | 0.0 | - |
| 24.4792 | 2350 | 0.0 | - |
| 25.0 | 2400 | 0.0 | - |
| 25.5208 | 2450 | 0.0 | - |
| 26.0417 | 2500 | 0.0 | - |
| 26.5625 | 2550 | 0.0 | - |
| 27.0833 | 2600 | 0.0 | - |
| 27.6042 | 2650 | 0.0 | - |
| 28.125 | 2700 | 0.0 | - |
| 28.6458 | 2750 | 0.0 | - |
| 29.1667 | 2800 | 0.0 | - |
| 29.6875 | 2850 | 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}
}