metadata
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: 스타스포츠 비치 발리볼 소프트 4호 CB814 스포츠/레저>배구>배구공
- text: 안전요원의자 1 9m 수영장 풀장 심판대 안전바 의자 구조 요원 스포츠/레저>배구>기타배구용품
- text: 미즈노 웨이브 라이트닝 Z7 배구화 V1GA220041 스포츠/레저>배구>배구화
- text: 배구 지주대 이동식 맨홀형 체육 강당 맨홀식 거치대 스포츠/레저>배구>기타배구용품
- text: 미즈노 남성 여성 배구복 배구 유니폼 긴팔티 긴팔 티셔츠 N-XT V2MAA510 스포츠/레저>배구>배구의류
metrics:
- accuracy
pipeline_tag: text-classification
library_name: setfit
inference: true
base_model: mini1013/master_domain
model-index:
- name: SetFit with mini1013/master_domain
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: Unknown
type: unknown
split: test
metrics:
- type: accuracy
value: 1
name: Accuracy
SetFit with mini1013/master_domain
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:
- Fine-tuning a Sentence Transformer with contrastive learning.
- Training a classification head with features from the fine-tuned Sentence Transformer.
Model Details
Model Description
- Model Type: SetFit
- Sentence Transformer body: mini1013/master_domain
- Classification head: a LogisticRegression instance
- Maximum Sequence Length: 512 tokens
- Number of Classes: 5 classes
Model Sources
- Repository: SetFit on GitHub
- Paper: Efficient Few-Shot Learning Without Prompts
- Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts
Model Labels
| Label | Examples |
|---|---|
| 4.0 |
|
| 0.0 |
|
| 3.0 |
|
| 1.0 |
|
| 2.0 |
|
Evaluation
Metrics
| Label | Accuracy |
|---|---|
| all | 1.0 |
Uses
Direct Use for Inference
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_sl11")
# Run inference
preds = model("스타스포츠 비치 발리볼 소프트 4호 CB814 스포츠/레저>배구>배구공")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 4 | 8.8833 | 18 |
| Label | Training Sample Count |
|---|---|
| 0.0 | 70 |
| 1.0 | 70 |
| 2.0 | 20 |
| 3.0 | 70 |
| 4.0 | 70 |
Training Hyperparameters
- batch_size: (256, 256)
- num_epochs: (30, 30)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 50
- body_learning_rate: (2e-05, 1e-05)
- head_learning_rate: 0.01
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: False
- warmup_proportion: 0.1
- l2_weight: 0.01
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: False
Training Results
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0169 | 1 | 0.461 | - |
| 0.8475 | 50 | 0.478 | - |
| 1.6949 | 100 | 0.1412 | - |
| 2.5424 | 150 | 0.0009 | - |
| 3.3898 | 200 | 0.0 | - |
| 4.2373 | 250 | 0.0 | - |
| 5.0847 | 300 | 0.0 | - |
| 5.9322 | 350 | 0.0001 | - |
| 6.7797 | 400 | 0.0 | - |
| 7.6271 | 450 | 0.0 | - |
| 8.4746 | 500 | 0.0 | - |
| 9.3220 | 550 | 0.0 | - |
| 10.1695 | 600 | 0.0 | - |
| 11.0169 | 650 | 0.0 | - |
| 11.8644 | 700 | 0.0 | - |
| 12.7119 | 750 | 0.0 | - |
| 13.5593 | 800 | 0.0 | - |
| 14.4068 | 850 | 0.0 | - |
| 15.2542 | 900 | 0.0 | - |
| 16.1017 | 950 | 0.0 | - |
| 16.9492 | 1000 | 0.0 | - |
| 17.7966 | 1050 | 0.0 | - |
| 18.6441 | 1100 | 0.0 | - |
| 19.4915 | 1150 | 0.0 | - |
| 20.3390 | 1200 | 0.0 | - |
| 21.1864 | 1250 | 0.0 | - |
| 22.0339 | 1300 | 0.0 | - |
| 22.8814 | 1350 | 0.0 | - |
| 23.7288 | 1400 | 0.0 | - |
| 24.5763 | 1450 | 0.0 | - |
| 25.4237 | 1500 | 0.0 | - |
| 26.2712 | 1550 | 0.0 | - |
| 27.1186 | 1600 | 0.0 | - |
| 27.9661 | 1650 | 0.0 | - |
| 28.8136 | 1700 | 0.0 | - |
| 29.6610 | 1750 | 0.0 | - |
Framework Versions
- Python: 3.10.12
- SetFit: 1.1.0
- Sentence Transformers: 3.3.1
- Transformers: 4.44.2
- PyTorch: 2.2.0a0+81ea7a4
- Datasets: 3.2.0
- Tokenizers: 0.19.1
Citation
BibTeX
@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}
}