Efficient Few-Shot Learning Without Prompts
Paper • 2209.11055 • Published • 7
How to use mini1013/master_cate_bt3_test with setfit:
from setfit import SetFitModel
model = SetFitModel.from_pretrained("mini1013/master_cate_bt3_test")How to use mini1013/master_cate_bt3_test with sentence-transformers:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("mini1013/master_cate_bt3_test")
sentences = [
"The weather is lovely today.",
"It's so sunny outside!",
"He drove to the stadium."
]
embeddings = model.encode(sentences)
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]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 |
|---|---|
| 5.0 |
|
| 13.0 |
|
| 12.0 |
|
| 8.0 |
|
| 11.0 |
|
| 1.0 |
|
| 6.0 |
|
| 14.0 |
|
| 0.0 |
|
| 7.0 |
|
| 3.0 |
|
| 15.0 |
|
| 4.0 |
|
| 2.0 |
|
| 9.0 |
|
| 16.0 |
|
| 10.0 |
|
| Label | Accuracy |
|---|---|
| all | 0.7189 |
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_bt3_test")
# Run inference
preds = model("아로마티카 퓨어 앤 소프트 여성청결제 170ml (폼타입) 옵션없음 포사도")
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 3 | 9.3333 | 20 |
| Label | Training Sample Count |
|---|---|
| 0.0 | 22 |
| 1.0 | 20 |
| 2.0 | 20 |
| 3.0 | 12 |
| 4.0 | 21 |
| 5.0 | 18 |
| 6.0 | 23 |
| 7.0 | 15 |
| 8.0 | 20 |
| 9.0 | 20 |
| 10.0 | 11 |
| 11.0 | 15 |
| 12.0 | 20 |
| 13.0 | 23 |
| 14.0 | 21 |
| 15.0 | 22 |
| 16.0 | 21 |
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0263 | 1 | 0.5057 | - |
| 1.3158 | 50 | 0.423 | - |
| 2.6316 | 100 | 0.1568 | - |
| 3.9474 | 150 | 0.067 | - |
| 5.2632 | 200 | 0.0479 | - |
| 6.5789 | 250 | 0.0324 | - |
| 7.8947 | 300 | 0.0196 | - |
| 9.2105 | 350 | 0.0138 | - |
| 10.5263 | 400 | 0.0111 | - |
| 11.8421 | 450 | 0.0051 | - |
| 13.1579 | 500 | 0.0041 | - |
| 14.4737 | 550 | 0.0043 | - |
| 15.7895 | 600 | 0.0026 | - |
| 17.1053 | 650 | 0.0005 | - |
| 18.4211 | 700 | 0.0003 | - |
| 19.7368 | 750 | 0.0002 | - |
| 21.0526 | 800 | 0.0002 | - |
| 22.3684 | 850 | 0.0002 | - |
| 23.6842 | 900 | 0.0002 | - |
| 25.0 | 950 | 0.0002 | - |
| 26.3158 | 1000 | 0.0001 | - |
| 27.6316 | 1050 | 0.0001 | - |
| 28.9474 | 1100 | 0.0001 | - |
| 30.2632 | 1150 | 0.0001 | - |
| 31.5789 | 1200 | 0.0001 | - |
| 32.8947 | 1250 | 0.0001 | - |
| 34.2105 | 1300 | 0.0001 | - |
| 35.5263 | 1350 | 0.0001 | - |
| 36.8421 | 1400 | 0.0001 | - |
| 38.1579 | 1450 | 0.0001 | - |
| 39.4737 | 1500 | 0.0001 | - |
| 40.7895 | 1550 | 0.0001 | - |
| 42.1053 | 1600 | 0.0001 | - |
| 43.4211 | 1650 | 0.0001 | - |
| 44.7368 | 1700 | 0.0001 | - |
| 46.0526 | 1750 | 0.0001 | - |
| 47.3684 | 1800 | 0.0001 | - |
| 48.6842 | 1850 | 0.0001 | - |
| 50.0 | 1900 | 0.0001 | - |
@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}
}
from setfit import SetFitModel model = SetFitModel.from_pretrained("mini1013/master_cate_bt3_test")