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 |
|
| 1.0 |
|
| 5.0 | |
| 4.0 |
|
| 0.0 |
|
| 3.0 |
|
| 7.0 |
|
| 2.0 |
|
| Label | Metric |
|---|---|
| all | 0.9173 |
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_fd8")
# Run inference
preds = model("[CJ](신세계 의정부점) 비비고 누룽지닭다리삼계탕 550g 주식회사 에스에스지닷컴")
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 3 | 9.3575 | 20 |
| 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 |
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0159 | 1 | 0.4347 | - |
| 0.7937 | 50 | 0.2865 | - |
| 1.5873 | 100 | 0.0903 | - |
| 2.3810 | 150 | 0.0636 | - |
| 3.1746 | 200 | 0.0401 | - |
| 3.9683 | 250 | 0.003 | - |
| 4.7619 | 300 | 0.0016 | - |
| 5.5556 | 350 | 0.0017 | - |
| 6.3492 | 400 | 0.0025 | - |
| 7.1429 | 450 | 0.0007 | - |
| 7.9365 | 500 | 0.0001 | - |
| 8.7302 | 550 | 0.0001 | - |
| 9.5238 | 600 | 0.0002 | - |
| 10.3175 | 650 | 0.0001 | - |
| 11.1111 | 700 | 0.0008 | - |
| 11.9048 | 750 | 0.0001 | - |
| 12.6984 | 800 | 0.0001 | - |
| 13.4921 | 850 | 0.0 | - |
| 14.2857 | 900 | 0.0001 | - |
| 15.0794 | 950 | 0.0 | - |
| 15.8730 | 1000 | 0.0 | - |
| 16.6667 | 1050 | 0.0 | - |
| 17.4603 | 1100 | 0.0 | - |
| 18.2540 | 1150 | 0.0 | - |
| 19.0476 | 1200 | 0.0 | - |
| 19.8413 | 1250 | 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}
}