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 |
|---|---|
| 9.0 |
|
| 2.0 |
|
| 0.0 |
|
| 4.0 |
|
| 8.0 |
|
| 6.0 |
|
| 3.0 |
|
| 5.0 |
|
| 7.0 |
|
| 1.0 |
|
| Label | Metric |
|---|---|
| all | 0.9477 |
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_lh4")
# Run inference
preds = model("애터미 치약 프로폴리스 200g 입냄새 제거 미백 콜마 플렉스세븐")
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 3 | 10.026 | 23 |
| Label | Training Sample Count |
|---|---|
| 0.0 | 50 |
| 1.0 | 50 |
| 2.0 | 50 |
| 3.0 | 50 |
| 4.0 | 50 |
| 5.0 | 50 |
| 6.0 | 50 |
| 7.0 | 50 |
| 8.0 | 50 |
| 9.0 | 50 |
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0127 | 1 | 0.4686 | - |
| 0.6329 | 50 | 0.2751 | - |
| 1.2658 | 100 | 0.1179 | - |
| 1.8987 | 150 | 0.0739 | - |
| 2.5316 | 200 | 0.0687 | - |
| 3.1646 | 250 | 0.0466 | - |
| 3.7975 | 300 | 0.0591 | - |
| 4.4304 | 350 | 0.0232 | - |
| 5.0633 | 400 | 0.0125 | - |
| 5.6962 | 450 | 0.0134 | - |
| 6.3291 | 500 | 0.0152 | - |
| 6.9620 | 550 | 0.0175 | - |
| 7.5949 | 600 | 0.0118 | - |
| 8.2278 | 650 | 0.007 | - |
| 8.8608 | 700 | 0.0003 | - |
| 9.4937 | 750 | 0.0002 | - |
| 10.1266 | 800 | 0.0001 | - |
| 10.7595 | 850 | 0.0001 | - |
| 11.3924 | 900 | 0.0001 | - |
| 12.0253 | 950 | 0.0001 | - |
| 12.6582 | 1000 | 0.0001 | - |
| 13.2911 | 1050 | 0.0001 | - |
| 13.9241 | 1100 | 0.0001 | - |
| 14.5570 | 1150 | 0.0001 | - |
| 15.1899 | 1200 | 0.0001 | - |
| 15.8228 | 1250 | 0.0001 | - |
| 16.4557 | 1300 | 0.0001 | - |
| 17.0886 | 1350 | 0.0001 | - |
| 17.7215 | 1400 | 0.0001 | - |
| 18.3544 | 1450 | 0.0001 | - |
| 18.9873 | 1500 | 0.0 | - |
| 19.6203 | 1550 | 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}
}