Efficient Few-Shot Learning Without Prompts
Paper • 2209.11055 • Published • 7
How to use mini1013/master_cate_ac9 with setfit:
from setfit import SetFitModel
model = SetFitModel.from_pretrained("mini1013/master_cate_ac9")How to use mini1013/master_cate_ac9 with sentence-transformers:
from sentence_transformers import SentenceTransformer
model = SentenceTransformer("mini1013/master_cate_ac9")
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 |
|---|---|
| 3.0 |
|
| 7.0 |
|
| 1.0 |
|
| 9.0 |
|
| 0.0 |
|
| 5.0 |
|
| 2.0 |
|
| 4.0 |
|
| 8.0 |
|
| 6.0 |
|
| Label | Metric |
|---|---|
| all | 0.7868 |
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_ac9")
# Run inference
preds = model("웨빙 플라워 스트랩 레디백 길이조절 가방끈 어깨끈 리폼 3-플라워가방끈-흰색 이백프로")
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 3 | 9.6146 | 30 |
| Label | Training Sample Count |
|---|---|
| 0.0 | 50 |
| 1.0 | 17 |
| 2.0 | 50 |
| 3.0 | 50 |
| 4.0 | 50 |
| 5.0 | 50 |
| 6.0 | 50 |
| 7.0 | 50 |
| 8.0 | 50 |
| 9.0 | 50 |
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0137 | 1 | 0.4278 | - |
| 0.6849 | 50 | 0.3052 | - |
| 1.3699 | 100 | 0.1524 | - |
| 2.0548 | 150 | 0.0583 | - |
| 2.7397 | 200 | 0.0292 | - |
| 3.4247 | 250 | 0.0197 | - |
| 4.1096 | 300 | 0.0061 | - |
| 4.7945 | 350 | 0.0022 | - |
| 5.4795 | 400 | 0.0033 | - |
| 6.1644 | 450 | 0.0003 | - |
| 6.8493 | 500 | 0.0002 | - |
| 7.5342 | 550 | 0.0001 | - |
| 8.2192 | 600 | 0.0001 | - |
| 8.9041 | 650 | 0.0001 | - |
| 9.5890 | 700 | 0.0001 | - |
| 10.2740 | 750 | 0.0001 | - |
| 10.9589 | 800 | 0.0001 | - |
| 11.6438 | 850 | 0.0001 | - |
| 12.3288 | 900 | 0.0001 | - |
| 13.0137 | 950 | 0.0001 | - |
| 13.6986 | 1000 | 0.0001 | - |
| 14.3836 | 1050 | 0.0001 | - |
| 15.0685 | 1100 | 0.0001 | - |
| 15.7534 | 1150 | 0.0001 | - |
| 16.4384 | 1200 | 0.0001 | - |
| 17.1233 | 1250 | 0.0 | - |
| 17.8082 | 1300 | 0.0001 | - |
| 18.4932 | 1350 | 0.0001 | - |
| 19.1781 | 1400 | 0.0001 | - |
| 19.8630 | 1450 | 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}
}