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 |
|
| 3.0 |
|
| 4.0 |
|
| 7.0 |
|
| 2.0 |
|
| 1.0 |
|
| 0.0 |
|
| 5.0 |
|
| 8.0 |
|
| Label | Metric |
|---|---|
| all | 0.9927 |
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_fd12")
# Run inference
preds = model("올리타리아 엑스트라버진 올리브오일 1L 카비스")
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 3 | 8.5356 | 22 |
| 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 |
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0141 | 1 | 0.4844 | - |
| 0.7042 | 50 | 0.3408 | - |
| 1.4085 | 100 | 0.0769 | - |
| 2.1127 | 150 | 0.0298 | - |
| 2.8169 | 200 | 0.023 | - |
| 3.5211 | 250 | 0.0251 | - |
| 4.2254 | 300 | 0.0291 | - |
| 4.9296 | 350 | 0.0156 | - |
| 5.6338 | 400 | 0.0137 | - |
| 6.3380 | 450 | 0.0029 | - |
| 7.0423 | 500 | 0.0001 | - |
| 7.7465 | 550 | 0.0001 | - |
| 8.4507 | 600 | 0.0001 | - |
| 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 | 0.0 | - |
| 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 | - |
@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}
}