Efficient Few-Shot Learning Without Prompts
Paper • 2209.11055 • Published • 7
How to use mini1013/master_cate_ap2 with setfit:
from setfit import SetFitModel
model = SetFitModel.from_pretrained("mini1013/master_cate_ap2")How to use mini1013/master_cate_ap2 with sentence-transformers:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("mini1013/master_cate_ap2")
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 |
|---|---|
| 6.0 |
|
| 8.0 |
|
| 2.0 |
|
| 1.0 |
|
| 4.0 |
|
| 3.0 |
|
| 7.0 |
|
| 0.0 |
|
| 9.0 | |
| 5.0 |
|
| Label | Metric |
|---|---|
| all | 0.6911 |
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_ap2")
# Run inference
preds = model("(신세계김해점)오르시떼 여성 C221 나시아 긴소매 원피스 L 신세계백화점")
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 3 | 9.9869 | 22 |
| Label | Training Sample Count |
|---|---|
| 0.0 | 50 |
| 1.0 | 50 |
| 2.0 | 50 |
| 3.0 | 50 |
| 4.0 | 50 |
| 5.0 | 7 |
| 6.0 | 50 |
| 7.0 | 50 |
| 8.0 | 50 |
| 9.0 | 50 |
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0139 | 1 | 0.3999 | - |
| 0.6944 | 50 | 0.3239 | - |
| 1.3889 | 100 | 0.169 | - |
| 2.0833 | 150 | 0.033 | - |
| 2.7778 | 200 | 0.0122 | - |
| 3.4722 | 250 | 0.0022 | - |
| 4.1667 | 300 | 0.0008 | - |
| 4.8611 | 350 | 0.0006 | - |
| 5.5556 | 400 | 0.0004 | - |
| 6.25 | 450 | 0.0003 | - |
| 6.9444 | 500 | 0.0003 | - |
| 7.6389 | 550 | 0.0003 | - |
| 8.3333 | 600 | 0.0002 | - |
| 9.0278 | 650 | 0.0002 | - |
| 9.7222 | 700 | 0.0002 | - |
| 10.4167 | 750 | 0.0002 | - |
| 11.1111 | 800 | 0.0002 | - |
| 11.8056 | 850 | 0.0001 | - |
| 12.5 | 900 | 0.0001 | - |
| 13.1944 | 950 | 0.0001 | - |
| 13.8889 | 1000 | 0.0001 | - |
| 14.5833 | 1050 | 0.0001 | - |
| 15.2778 | 1100 | 0.0001 | - |
| 15.9722 | 1150 | 0.0001 | - |
| 16.6667 | 1200 | 0.0001 | - |
| 17.3611 | 1250 | 0.0001 | - |
| 18.0556 | 1300 | 0.0001 | - |
| 18.75 | 1350 | 0.0001 | - |
| 19.4444 | 1400 | 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}
}