Efficient Few-Shot Learning Without Prompts
Paper
•
2209.11055
•
Published
•
4
This is a SetFit model trained on the lmsys/toxic-chat dataset that can be used for Text Classification. This SetFit model uses sentence-transformers/paraphrase-mpnet-base-v2 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:
This dataset may contain racism, sexuality, or other undesired content.
| Label | Examples |
|---|---|
| Non toxic |
|
| Toxic |
|
| Label | F1 |
|---|---|
| all | 0.9288 |
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("setfit_model_id")
# Run inference
preds = model("are you connected to the internet?")
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 4 | 36.5476 | 249 |
| Label | Training Sample Count |
|---|---|
| Non toxic | 40 |
| Toxic | 2 |
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0097 | 1 | 0.4209 | - |
| 0.4854 | 50 | 0.0052 | - |
| 0.9709 | 100 | 0.0004 | - |
| 1.0 | 103 | - | 0.4655 |
| 1.4563 | 150 | 0.0003 | - |
| 1.9417 | 200 | 0.0002 | - |
| 2.0 | 206 | - | 0.4746 |
| 2.4272 | 250 | 0.0003 | - |
| 2.9126 | 300 | 0.0002 | - |
| 3.0 | 309 | - | 0.4783 |
| 3.3981 | 350 | 0.0002 | - |
| 3.8835 | 400 | 0.0001 | - |
| 4.0 | 412 | - | 0.4804 |
| 4.3689 | 450 | 0.0001 | - |
| 4.8544 | 500 | 0.0002 | - |
| 5.0 | 515 | - | 0.4812 |
@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}
}