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: 6 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
5	'(주)근호컴 [리버네트워크]USB 2.0 리피터 전용 전원 어댑터 (NX-USBEXPW) (주)근호컴' 'NEXI 넥시 정품 NX-USBEXPW아답터 (NX0284) (주)유니정보통신' '국산 12V 5A 모니터 아답터 ML-125A 헤라유통'
3	'카멜마운트 GDA3 고든 디자인 모니터 거치대 모니터암 듀얼 블랙 주식회사 카멜인터내셔널' '카멜 CA2 화이트 나뭉' '마루느루 마운트뷰 MV-G1A 셜크'
0	'셋탑 박스 게임기 리모컨 수납 TV 모니터 TOP 공간 선반 공유기 거치대 아이디어윙' '리모컨수납 TV 모니터 TOP 공간선반 Black 연상연하' '애니포트 TV거치대 엘마운트 다용도 멀티 선반 S900 이스토어'
1	'ELLOVEN 엘로벤 모니터스탠드+서랍 엘로벤 스탠드 앤트러 (804.851.02) 랩앤툴스' '썬엔원 유보드 모니터받침대 U-BOARD Basic [화이트] 강화유리 / 유리색상: 투명 블랙 (주)세븐앤씨' '앱코 MES100 사이드 폴딩 모니터 받침대 선반 받침 서랍 데스크 정리 블랙 앱코 MES100 블랙 (주)드림팩토리샵'
2	'아이존아이앤디 EZ MSM-10 아이러브드라이브(I Love Drive)' '아이존아이앤디 EZ MSM-10/EZ MSM-10/조절브라켓/모니터스탠드/높낮이조절/조절스탠드/모니터홀타입/홀타입스탠드 EZ MSM-10 기쁘다희샵' '루나랩 베사확장브라켓 200x100 200x200 주식회사 루나'
4	'지클릭커 휴 쉴드 PET 부착식 정보보호 모니터 보안필름 22인치 가이드컴퓨터' '힐링쉴드 11890340 22인치 모니터 블루라이트차단 보호필름 거치식 조립형 양면필터 온라인정품인증점' '지클릭커 휴 쉴드 PET 부착식 정보보호 모니터 보안필름 22인치 주식회사 리더샵'

Evaluation

Metrics

Label	Metric
all	0.8586

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_el10")
# Run inference
preds = model("원목 듀얼 모니터받침대 미송 B타입 M  주식회사 제이테크(J-TECH)")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	4	9.9725	24

Label	Training Sample Count
0	50
1	50
2	13
3	50
4	5
5	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
0.0286	1	0.4958	-
1.4286	50	0.0386	-
2.8571	100	0.0016	-
4.2857	150	0.0001	-
5.7143	200	0.0	-
7.1429	250	0.0	-
8.5714	300	0.0	-
10.0	350	0.0	-
11.4286	400	0.0001	-
12.8571	450	0.0	-
14.2857	500	0.0001	-
15.7143	550	0.0	-
17.1429	600	0.0001	-
18.5714	650	0.0	-
20.0	700	0.0	-

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_el10