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 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 |
|---|---|
| 1.0 |
|
| 0.0 |
|
| 7.0 |
|
| 4.0 |
|
| 3.0 |
|
| 8.0 |
|
| 6.0 |
|
| 10.0 |
|
| 5.0 |
|
| 2.0 |
|
| 9.0 |
|
| 11.0 |
|
| Label | Accuracy |
|---|---|
| all | 1.0 |
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_sl22")
# Run inference
preds = model("생활원사 수비용 야구장갑 스포츠/레저>야구>야구장갑")
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 2 | 8.3993 | 20 |
| Label | Training Sample Count |
|---|---|
| 0.0 | 70 |
| 1.0 | 70 |
| 2.0 | 69 |
| 3.0 | 70 |
| 4.0 | 70 |
| 5.0 | 70 |
| 6.0 | 70 |
| 7.0 | 70 |
| 8.0 | 70 |
| 9.0 | 70 |
| 10.0 | 70 |
| 11.0 | 70 |
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0061 | 1 | 0.4871 | - |
| 0.3049 | 50 | 0.4978 | - |
| 0.6098 | 100 | 0.4027 | - |
| 0.9146 | 150 | 0.1531 | - |
| 1.2195 | 200 | 0.0774 | - |
| 1.5244 | 250 | 0.0346 | - |
| 1.8293 | 300 | 0.0227 | - |
| 2.1341 | 350 | 0.0138 | - |
| 2.4390 | 400 | 0.0031 | - |
| 2.7439 | 450 | 0.0004 | - |
| 3.0488 | 500 | 0.0003 | - |
| 3.3537 | 550 | 0.0002 | - |
| 3.6585 | 600 | 0.0002 | - |
| 3.9634 | 650 | 0.0001 | - |
| 4.2683 | 700 | 0.0001 | - |
| 4.5732 | 750 | 0.0001 | - |
| 4.8780 | 800 | 0.0001 | - |
| 5.1829 | 850 | 0.0001 | - |
| 5.4878 | 900 | 0.0001 | - |
| 5.7927 | 950 | 0.0001 | - |
| 6.0976 | 1000 | 0.0001 | - |
| 6.4024 | 1050 | 0.0001 | - |
| 6.7073 | 1100 | 0.0001 | - |
| 7.0122 | 1150 | 0.0001 | - |
| 7.3171 | 1200 | 0.0001 | - |
| 7.6220 | 1250 | 0.0001 | - |
| 7.9268 | 1300 | 0.0 | - |
| 8.2317 | 1350 | 0.0 | - |
| 8.5366 | 1400 | 0.0 | - |
| 8.8415 | 1450 | 0.0 | - |
| 9.1463 | 1500 | 0.0 | - |
| 9.4512 | 1550 | 0.0 | - |
| 9.7561 | 1600 | 0.0 | - |
| 10.0610 | 1650 | 0.0 | - |
| 10.3659 | 1700 | 0.0 | - |
| 10.6707 | 1750 | 0.0 | - |
| 10.9756 | 1800 | 0.0 | - |
| 11.2805 | 1850 | 0.0 | - |
| 11.5854 | 1900 | 0.0 | - |
| 11.8902 | 1950 | 0.0 | - |
| 12.1951 | 2000 | 0.0 | - |
| 12.5 | 2050 | 0.0 | - |
| 12.8049 | 2100 | 0.0001 | - |
| 13.1098 | 2150 | 0.0001 | - |
| 13.4146 | 2200 | 0.0 | - |
| 13.7195 | 2250 | 0.0 | - |
| 14.0244 | 2300 | 0.0 | - |
| 14.3293 | 2350 | 0.0 | - |
| 14.6341 | 2400 | 0.0 | - |
| 14.9390 | 2450 | 0.0 | - |
| 15.2439 | 2500 | 0.0 | - |
| 15.5488 | 2550 | 0.0 | - |
| 15.8537 | 2600 | 0.0 | - |
| 16.1585 | 2650 | 0.0 | - |
| 16.4634 | 2700 | 0.0 | - |
| 16.7683 | 2750 | 0.0 | - |
| 17.0732 | 2800 | 0.0 | - |
| 17.3780 | 2850 | 0.0 | - |
| 17.6829 | 2900 | 0.0 | - |
| 17.9878 | 2950 | 0.0 | - |
| 18.2927 | 3000 | 0.0 | - |
| 18.5976 | 3050 | 0.0 | - |
| 18.9024 | 3100 | 0.0 | - |
| 19.2073 | 3150 | 0.0001 | - |
| 19.5122 | 3200 | 0.0 | - |
| 19.8171 | 3250 | 0.0 | - |
| 20.1220 | 3300 | 0.0 | - |
| 20.4268 | 3350 | 0.0 | - |
| 20.7317 | 3400 | 0.0 | - |
| 21.0366 | 3450 | 0.0 | - |
| 21.3415 | 3500 | 0.0 | - |
| 21.6463 | 3550 | 0.0 | - |
| 21.9512 | 3600 | 0.0 | - |
| 22.2561 | 3650 | 0.0 | - |
| 22.5610 | 3700 | 0.0 | - |
| 22.8659 | 3750 | 0.0 | - |
| 23.1707 | 3800 | 0.0 | - |
| 23.4756 | 3850 | 0.0 | - |
| 23.7805 | 3900 | 0.0 | - |
| 24.0854 | 3950 | 0.0 | - |
| 24.3902 | 4000 | 0.0 | - |
| 24.6951 | 4050 | 0.0 | - |
| 25.0 | 4100 | 0.0 | - |
| 25.3049 | 4150 | 0.0 | - |
| 25.6098 | 4200 | 0.0 | - |
| 25.9146 | 4250 | 0.0 | - |
| 26.2195 | 4300 | 0.0 | - |
| 26.5244 | 4350 | 0.0 | - |
| 26.8293 | 4400 | 0.0 | - |
| 27.1341 | 4450 | 0.0 | - |
| 27.4390 | 4500 | 0.0 | - |
| 27.7439 | 4550 | 0.0 | - |
| 28.0488 | 4600 | 0.0 | - |
| 28.3537 | 4650 | 0.0 | - |
| 28.6585 | 4700 | 0.0 | - |
| 28.9634 | 4750 | 0.0 | - |
| 29.2683 | 4800 | 0.0 | - |
| 29.5732 | 4850 | 0.0 | - |
| 29.8780 | 4900 | 0.0 | - |
@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}
}