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 TurkuNLP/bert-base-finnish-cased-v1 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 |
|
| 1 |
|
| Label | Metric |
|---|---|
| all | 0.8975 |
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("Finnish-actions/SetFit-FinBERT1-A2-statement")
# Run inference
preds = model("Etunimi Sukunimi 🙋♀️")
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 1 | 20.3115 | 213 |
| Label | Training Sample Count |
|---|---|
| 0 | 213 |
| 1 | 750 |
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0014 | 1 | 0.2419 | - |
| 0.0692 | 50 | 0.2635 | - |
| 0.1383 | 100 | 0.2284 | - |
| 0.2075 | 150 | 0.1852 | - |
| 0.2766 | 200 | 0.1301 | - |
| 0.3458 | 250 | 0.0882 | - |
| 0.4149 | 300 | 0.0549 | - |
| 0.4841 | 350 | 0.0318 | - |
| 0.5533 | 400 | 0.0325 | - |
| 0.6224 | 450 | 0.0097 | - |
| 0.6916 | 500 | 0.0061 | - |
| 0.7607 | 550 | 0.0021 | - |
| 0.8299 | 600 | 0.0015 | - |
| 0.8990 | 650 | 0.0004 | - |
| 0.9682 | 700 | 0.0006 | - |
| 1.0 | 723 | - | 0.2629 |
| 1.0373 | 750 | 0.0001 | - |
| 1.1065 | 800 | 0.0004 | - |
| 1.1757 | 850 | 0.0001 | - |
| 1.2448 | 900 | 0.0001 | - |
| 1.3140 | 950 | 0.0001 | - |
| 1.3831 | 1000 | 0.0001 | - |
| 1.4523 | 1050 | 0.0001 | - |
| 1.5214 | 1100 | 0.0001 | - |
| 1.5906 | 1150 | 0.0001 | - |
| 1.6598 | 1200 | 0.0001 | - |
| 1.7289 | 1250 | 0.0001 | - |
| 1.7981 | 1300 | 0.0 | - |
| 1.8672 | 1350 | 0.0 | - |
| 1.9364 | 1400 | 0.0 | - |
| 2.0 | 1446 | - | 0.2636 |
| 2.0055 | 1450 | 0.0 | - |
| 2.0747 | 1500 | 0.0 | - |
| 2.1438 | 1550 | 0.0001 | - |
| 2.2130 | 1600 | 0.0012 | - |
| 2.2822 | 1650 | 0.0001 | - |
| 2.3513 | 1700 | 0.0 | - |
| 2.4205 | 1750 | 0.0 | - |
| 2.4896 | 1800 | 0.0 | - |
| 2.5588 | 1850 | 0.0 | - |
| 2.6279 | 1900 | 0.0 | - |
| 2.6971 | 1950 | 0.0 | - |
| 2.7663 | 2000 | 0.0 | - |
| 2.8354 | 2050 | 0.0 | - |
| 2.9046 | 2100 | 0.0 | - |
| 2.9737 | 2150 | 0.0 | - |
| 3.0 | 2169 | - | 0.2614 |
| 3.0429 | 2200 | 0.0 | - |
| 3.1120 | 2250 | 0.0 | - |
| 3.1812 | 2300 | 0.0 | - |
| 3.2503 | 2350 | 0.0 | - |
| 3.3195 | 2400 | 0.0 | - |
| 3.3887 | 2450 | 0.0 | - |
| 3.4578 | 2500 | 0.0 | - |
| 3.5270 | 2550 | 0.0 | - |
| 3.5961 | 2600 | 0.0 | - |
| 3.6653 | 2650 | 0.0 | - |
| 3.7344 | 2700 | 0.0 | - |
| 3.8036 | 2750 | 0.0 | - |
| 3.8728 | 2800 | 0.0 | - |
| 3.9419 | 2850 | 0.0 | - |
| 4.0 | 2892 | - | 0.2617 |
@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}
}
Base model
TurkuNLP/bert-base-finnish-cased-v1