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 |
|---|---|
| 7.0 |
|
| 1.0 |
|
| 6.0 |
|
| 12.0 |
|
| 5.0 |
|
| 0.0 |
|
| 10.0 |
|
| 8.0 |
|
| 11.0 |
|
| 13.0 |
|
| 2.0 |
|
| 9.0 |
|
| 4.0 |
|
| 3.0 |
|
| 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_sl28")
# Run inference
preds = model("애몰라이트 후레쉬 AM1 표준슬립 손전등 스포츠/레저>캠핑>랜턴>손전등")
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 3 | 7.8108 | 22 |
| Label | Training Sample Count |
|---|---|
| 0.0 | 70 |
| 1.0 | 70 |
| 2.0 | 70 |
| 3.0 | 25 |
| 4.0 | 30 |
| 5.0 | 70 |
| 6.0 | 70 |
| 7.0 | 70 |
| 8.0 | 70 |
| 9.0 | 70 |
| 10.0 | 70 |
| 11.0 | 70 |
| 12.0 | 70 |
| 13.0 | 26 |
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0060 | 1 | 0.5164 | - |
| 0.2994 | 50 | 0.4984 | - |
| 0.5988 | 100 | 0.4882 | - |
| 0.8982 | 150 | 0.1544 | - |
| 1.1976 | 200 | 0.0264 | - |
| 1.4970 | 250 | 0.0089 | - |
| 1.7964 | 300 | 0.0027 | - |
| 2.0958 | 350 | 0.0003 | - |
| 2.3952 | 400 | 0.0002 | - |
| 2.6946 | 450 | 0.0001 | - |
| 2.9940 | 500 | 0.0001 | - |
| 3.2934 | 550 | 0.0001 | - |
| 3.5928 | 600 | 0.0001 | - |
| 3.8922 | 650 | 0.0001 | - |
| 4.1916 | 700 | 0.0001 | - |
| 4.4910 | 750 | 0.0 | - |
| 4.7904 | 800 | 0.0 | - |
| 5.0898 | 850 | 0.0 | - |
| 5.3892 | 900 | 0.0 | - |
| 5.6886 | 950 | 0.0 | - |
| 5.9880 | 1000 | 0.0 | - |
| 6.2874 | 1050 | 0.0 | - |
| 6.5868 | 1100 | 0.0 | - |
| 6.8862 | 1150 | 0.0 | - |
| 7.1856 | 1200 | 0.0 | - |
| 7.4850 | 1250 | 0.0 | - |
| 7.7844 | 1300 | 0.0 | - |
| 8.0838 | 1350 | 0.0 | - |
| 8.3832 | 1400 | 0.0 | - |
| 8.6826 | 1450 | 0.0 | - |
| 8.9820 | 1500 | 0.0 | - |
| 9.2814 | 1550 | 0.0 | - |
| 9.5808 | 1600 | 0.0 | - |
| 9.8802 | 1650 | 0.0 | - |
| 10.1796 | 1700 | 0.0 | - |
| 10.4790 | 1750 | 0.0 | - |
| 10.7784 | 1800 | 0.0 | - |
| 11.0778 | 1850 | 0.0 | - |
| 11.3772 | 1900 | 0.0 | - |
| 11.6766 | 1950 | 0.0 | - |
| 11.9760 | 2000 | 0.0 | - |
| 12.2754 | 2050 | 0.0 | - |
| 12.5749 | 2100 | 0.0 | - |
| 12.8743 | 2150 | 0.0 | - |
| 13.1737 | 2200 | 0.0 | - |
| 13.4731 | 2250 | 0.0 | - |
| 13.7725 | 2300 | 0.0 | - |
| 14.0719 | 2350 | 0.0 | - |
| 14.3713 | 2400 | 0.0 | - |
| 14.6707 | 2450 | 0.0 | - |
| 14.9701 | 2500 | 0.0 | - |
| 15.2695 | 2550 | 0.0 | - |
| 15.5689 | 2600 | 0.0 | - |
| 15.8683 | 2650 | 0.0 | - |
| 16.1677 | 2700 | 0.0 | - |
| 16.4671 | 2750 | 0.0 | - |
| 16.7665 | 2800 | 0.0 | - |
| 17.0659 | 2850 | 0.0 | - |
| 17.3653 | 2900 | 0.0 | - |
| 17.6647 | 2950 | 0.0 | - |
| 17.9641 | 3000 | 0.0 | - |
| 18.2635 | 3050 | 0.0 | - |
| 18.5629 | 3100 | 0.0 | - |
| 18.8623 | 3150 | 0.0 | - |
| 19.1617 | 3200 | 0.0 | - |
| 19.4611 | 3250 | 0.0 | - |
| 19.7605 | 3300 | 0.0 | - |
| 20.0599 | 3350 | 0.0 | - |
| 20.3593 | 3400 | 0.0 | - |
| 20.6587 | 3450 | 0.0 | - |
| 20.9581 | 3500 | 0.0 | - |
| 21.2575 | 3550 | 0.0 | - |
| 21.5569 | 3600 | 0.0 | - |
| 21.8563 | 3650 | 0.0 | - |
| 22.1557 | 3700 | 0.0 | - |
| 22.4551 | 3750 | 0.0 | - |
| 22.7545 | 3800 | 0.0 | - |
| 23.0539 | 3850 | 0.0 | - |
| 23.3533 | 3900 | 0.0 | - |
| 23.6527 | 3950 | 0.0 | - |
| 23.9521 | 4000 | 0.0 | - |
| 24.2515 | 4050 | 0.0 | - |
| 24.5509 | 4100 | 0.0 | - |
| 24.8503 | 4150 | 0.0 | - |
| 25.1497 | 4200 | 0.0 | - |
| 25.4491 | 4250 | 0.0 | - |
| 25.7485 | 4300 | 0.0 | - |
| 26.0479 | 4350 | 0.0 | - |
| 26.3473 | 4400 | 0.0 | - |
| 26.6467 | 4450 | 0.0 | - |
| 26.9461 | 4500 | 0.0 | - |
| 27.2455 | 4550 | 0.0 | - |
| 27.5449 | 4600 | 0.0 | - |
| 27.8443 | 4650 | 0.0 | - |
| 28.1437 | 4700 | 0.0 | - |
| 28.4431 | 4750 | 0.0 | - |
| 28.7425 | 4800 | 0.0 | - |
| 29.0419 | 4850 | 0.0 | - |
| 29.3413 | 4900 | 0.0 | - |
| 29.6407 | 4950 | 0.0 | - |
| 29.9401 | 5000 | 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}
}