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 |
|---|---|
| 0.0 |
|
| 3.0 |
|
| 4.0 |
|
| 2.0 |
|
| 1.0 |
|
| 5.0 |
|
| 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_sl23")
# Run inference
preds = model("코미네 오토바이 핀 잠금 장치 도난 방지 디스크락 열쇠 스포츠/레저>오토바이/스쿠터>오토바이부품>잠금장치")
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 3 | 8.3719 | 19 |
| Label | Training Sample Count |
|---|---|
| 0.0 | 70 |
| 1.0 | 70 |
| 2.0 | 70 |
| 3.0 | 70 |
| 4.0 | 70 |
| 5.0 | 13 |
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0141 | 1 | 0.4943 | - |
| 0.7042 | 50 | 0.4622 | - |
| 1.4085 | 100 | 0.1572 | - |
| 2.1127 | 150 | 0.0427 | - |
| 2.8169 | 200 | 0.0006 | - |
| 3.5211 | 250 | 0.0 | - |
| 4.2254 | 300 | 0.0 | - |
| 4.9296 | 350 | 0.0 | - |
| 5.6338 | 400 | 0.0 | - |
| 6.3380 | 450 | 0.0 | - |
| 7.0423 | 500 | 0.0 | - |
| 7.7465 | 550 | 0.0 | - |
| 8.4507 | 600 | 0.0 | - |
| 9.1549 | 650 | 0.0 | - |
| 9.8592 | 700 | 0.0 | - |
| 10.5634 | 750 | 0.0 | - |
| 11.2676 | 800 | 0.0 | - |
| 11.9718 | 850 | 0.0 | - |
| 12.6761 | 900 | 0.0001 | - |
| 13.3803 | 950 | 0.0 | - |
| 14.0845 | 1000 | 0.0 | - |
| 14.7887 | 1050 | 0.0 | - |
| 15.4930 | 1100 | 0.0 | - |
| 16.1972 | 1150 | 0.0 | - |
| 16.9014 | 1200 | 0.0 | - |
| 17.6056 | 1250 | 0.0 | - |
| 18.3099 | 1300 | 0.0 | - |
| 19.0141 | 1350 | 0.0 | - |
| 19.7183 | 1400 | 0.0 | - |
| 20.4225 | 1450 | 0.0 | - |
| 21.1268 | 1500 | 0.0 | - |
| 21.8310 | 1550 | 0.0 | - |
| 22.5352 | 1600 | 0.0 | - |
| 23.2394 | 1650 | 0.0 | - |
| 23.9437 | 1700 | 0.0 | - |
| 24.6479 | 1750 | 0.0 | - |
| 25.3521 | 1800 | 0.0 | - |
| 26.0563 | 1850 | 0.0 | - |
| 26.7606 | 1900 | 0.0 | - |
| 27.4648 | 1950 | 0.0 | - |
| 28.1690 | 2000 | 0.0 | - |
| 28.8732 | 2050 | 0.0 | - |
| 29.5775 | 2100 | 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}
}