Efficient Few-Shot Learning Without Prompts
Paper • 2209.11055 • Published • 7
How to use mini1013/master_cate_lh27 with setfit:
from setfit import SetFitModel
model = SetFitModel.from_pretrained("mini1013/master_cate_lh27")How to use mini1013/master_cate_lh27 with sentence-transformers:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("mini1013/master_cate_lh27")
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 |
|---|---|
| 0.0 |
|
| 4.0 |
|
| 8.0 |
|
| 9.0 |
|
| 6.0 |
|
| 1.0 |
|
| 3.0 |
|
| 7.0 |
|
| 10.0 |
|
| 2.0 |
|
| 5.0 |
|
| Label | Metric |
|---|---|
| all | 0.9702 |
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_lh27")
# Run inference
preds = model("다이론 뉴핸드염료 의류 옷 면소재 패브릭 섬유 염색 36.튤립레드 싹다몰")
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 3 | 10.5 | 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 |
| 10.0 | 50 |
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0116 | 1 | 0.4265 | - |
| 0.5814 | 50 | 0.2849 | - |
| 1.1628 | 100 | 0.1489 | - |
| 1.7442 | 150 | 0.0544 | - |
| 2.3256 | 200 | 0.0363 | - |
| 2.9070 | 250 | 0.0257 | - |
| 3.4884 | 300 | 0.0122 | - |
| 4.0698 | 350 | 0.0138 | - |
| 4.6512 | 400 | 0.0088 | - |
| 5.2326 | 450 | 0.0043 | - |
| 5.8140 | 500 | 0.0004 | - |
| 6.3953 | 550 | 0.0003 | - |
| 6.9767 | 600 | 0.0001 | - |
| 7.5581 | 650 | 0.0001 | - |
| 8.1395 | 700 | 0.0001 | - |
| 8.7209 | 750 | 0.0001 | - |
| 9.3023 | 800 | 0.0001 | - |
| 9.8837 | 850 | 0.0001 | - |
| 10.4651 | 900 | 0.0001 | - |
| 11.0465 | 950 | 0.0001 | - |
| 11.6279 | 1000 | 0.0001 | - |
| 12.2093 | 1050 | 0.0001 | - |
| 12.7907 | 1100 | 0.0001 | - |
| 13.3721 | 1150 | 0.0 | - |
| 13.9535 | 1200 | 0.0 | - |
| 14.5349 | 1250 | 0.0 | - |
| 15.1163 | 1300 | 0.0001 | - |
| 15.6977 | 1350 | 0.0 | - |
| 16.2791 | 1400 | 0.0 | - |
| 16.8605 | 1450 | 0.0 | - |
| 17.4419 | 1500 | 0.0 | - |
| 18.0233 | 1550 | 0.0 | - |
| 18.6047 | 1600 | 0.0 | - |
| 19.1860 | 1650 | 0.0 | - |
| 19.7674 | 1700 | 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}
}