metadata
base_model: mini1013/master_domain
library_name: setfit
metrics:
- metric
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: >-
glowjin 차량용커피포트 주전자 가열 휴대용 여행 무광 블랙(12v24v 차량용) 업그레이드USB 무광블랙(12v24v 차량용)
글로우진(glowjin)
- text: 카프트 디자인 코일매트 카매트 자동차 발 매트 전차종 베이지 톰B 라인 1열 브라운_M라인_트렁크매트 안녕하십니카
- text: 아임반 자동차 사각 허깅 쿠션 차량용 다용도 허그 쿠션 피칸브라운 주식회사 아임반
- text: >-
초보운전 스티커 자석 탈부착 고휘도 반사 초보운전 가로사각 M 미디엄 01 스마일 [임산부가타고있어요]_정사각_02.임산부가
운전해요-핑크 퍼즈
- text: 겨울철 환절기 건조 차량용가습기 독일 차량 탑재 가습 01 1_10 플러그인 모델 라벤더 아로마테 플러스라인
inference: true
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: metric
value: 0.56449056059951
name: Metric
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: 15 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 |
|---|---|
| 0.0 |
|
| 8.0 |
|
| 4.0 |
|
| 11.0 |
|
| 13.0 |
|
| 10.0 |
|
| 12.0 |
|
| 1.0 |
|
| 3.0 |
|
| 14.0 |
|
| 7.0 |
|
| 9.0 |
|
| 2.0 |
|
| 5.0 |
|
| 6.0 |
|
Evaluation
Metrics
| Label | Metric |
|---|---|
| all | 0.5645 |
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_lh20")
# Run inference
preds = model("아임반 자동차 사각 허깅 쿠션 차량용 다용도 허그 쿠션 피칸브라운 주식회사 아임반")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 3 | 11.108 | 30 |
| Label | Training Sample Count |
|---|---|
| 0.0 | 50 |
| 1.0 | 50 |
| 2.0 | 50 |
| 3.0 | 50 |
| 4.0 | 50 |
| 5.0 | 50 |
| 6.0 | 50 |
| 7.0 | 50 |
| 8.0 | 50 |
| 9.0 | 50 |
| 10.0 | 50 |
| 11.0 | 50 |
| 12.0 | 50 |
| 13.0 | 50 |
| 14.0 | 50 |
Training Hyperparameters
- batch_size: (512, 512)
- num_epochs: (20, 20)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 40
- body_learning_rate: (2e-05, 2e-05)
- head_learning_rate: 2e-05
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: False
- warmup_proportion: 0.1
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: False
Training Results
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0085 | 1 | 0.3868 | - |
| 0.4237 | 50 | 0.3164 | - |
| 0.8475 | 100 | 0.2453 | - |
| 1.2712 | 150 | 0.1471 | - |
| 1.6949 | 200 | 0.0782 | - |
| 2.1186 | 250 | 0.0675 | - |
| 2.5424 | 300 | 0.0429 | - |
| 2.9661 | 350 | 0.0257 | - |
| 3.3898 | 400 | 0.019 | - |
| 3.8136 | 450 | 0.0175 | - |
| 4.2373 | 500 | 0.0275 | - |
| 4.6610 | 550 | 0.0118 | - |
| 5.0847 | 600 | 0.0068 | - |
| 5.5085 | 650 | 0.0046 | - |
| 5.9322 | 700 | 0.0067 | - |
| 6.3559 | 750 | 0.0041 | - |
| 6.7797 | 800 | 0.0044 | - |
| 7.2034 | 850 | 0.0025 | - |
| 7.6271 | 900 | 0.0004 | - |
| 8.0508 | 950 | 0.0002 | - |
| 8.4746 | 1000 | 0.0001 | - |
| 8.8983 | 1050 | 0.0002 | - |
| 9.3220 | 1100 | 0.0001 | - |
| 9.7458 | 1150 | 0.0001 | - |
| 10.1695 | 1200 | 0.0001 | - |
| 10.5932 | 1250 | 0.0001 | - |
| 11.0169 | 1300 | 0.0001 | - |
| 11.4407 | 1350 | 0.0001 | - |
| 11.8644 | 1400 | 0.0001 | - |
| 12.2881 | 1450 | 0.0001 | - |
| 12.7119 | 1500 | 0.0001 | - |
| 13.1356 | 1550 | 0.0001 | - |
| 13.5593 | 1600 | 0.0001 | - |
| 13.9831 | 1650 | 0.0001 | - |
| 14.4068 | 1700 | 0.0001 | - |
| 14.8305 | 1750 | 0.0001 | - |
| 15.2542 | 1800 | 0.0001 | - |
| 15.6780 | 1850 | 0.0001 | - |
| 16.1017 | 1900 | 0.0001 | - |
| 16.5254 | 1950 | 0.0001 | - |
| 16.9492 | 2000 | 0.0001 | - |
| 17.3729 | 2050 | 0.0001 | - |
| 17.7966 | 2100 | 0.0001 | - |
| 18.2203 | 2150 | 0.0001 | - |
| 18.6441 | 2200 | 0.0 | - |
| 19.0678 | 2250 | 0.0 | - |
| 19.4915 | 2300 | 0.0001 | - |
| 19.9153 | 2350 | 0.0001 | - |
Framework Versions
- Python: 3.10.12
- SetFit: 1.1.0.dev0
- Sentence Transformers: 3.1.1
- Transformers: 4.46.1
- PyTorch: 2.4.0+cu121
- Datasets: 2.20.0
- Tokenizers: 0.20.0
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}
}