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: 3 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
1.0	'경량 방수토시 팔토시 작업 위생 안전 경량방수토시(블랙계열) 바움하우스' '사러왕 운전 팔토시 레이스 여성 쉬폰 골프토시 워머 암 핸드 롱장갑 4 레이스 여성팔토시 살구색 언벤샵' '여성운전 팔토시 화이트 태양금'
2.0	'[갤러리아] 닥스 DCGV3F287 [남녀공용] 베이지 캐시미어 니트 장갑(타임월드) 한화갤러리아(주)' '[갤러리아] 루이까또즈 방울방울 니트워머 GGILW30005 GGILW30005 베이지 한화갤러리아(주)' '(신세계김해점)질스튜어트 여성 가죽장갑 GBS740X 블랙(01) 신세계백화점'
0.0	'남성 가죽 콤비장갑 GPD293H/닥스(장갑) 블랙 롯데쇼핑(주)' '(10%+10%쿠폰) 시즌오프 잡화 / 장갑 목도리 스타킹 양말 방한용품 1_15.윈터 마스크캡_1+1 스킨라이즈' '[갤러리아] [닥스] 남성 가죽 장갑 (D) GPS332H(타임월드) 진브라운91 한화갤러리아(주)'

Evaluation

Metrics

Label	Metric
all	0.8877

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_ac12")
# Run inference
preds = model("남성 가죽장갑 GPS742X 블랙 롯데백화점1관")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	4	10.5733	24

Label	Training Sample Count
0.0	50
1.0	50
2.0	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
0.0417	1	0.4357	-
2.0833	50	0.1092	-
4.1667	100	0.006	-
6.25	150	0.0002	-
8.3333	200	0.0002	-
10.4167	250	0.0001	-
12.5	300	0.0001	-
14.5833	350	0.0001	-
16.6667	400	0.0001	-
18.75	450	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}
}

mini1013
/

master_cate_ac12