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
3	'[PS4] NBA 2K24 코비 브라이언트 에디션 특전 바우처 有 오진상사(주)' '닌텐도 스위치 둘이서 냥코 대전쟁 한글판 게임매니아' '닌텐도 마리오 카트 8 디럭스 + 조이콘 휠 패키지 SWITCH 한글판 마리오카트8 디럭스 (+조이콘핸들 세트)_마리오카트8 (+핸들 2개 원형 네온) 주식회사 쇼핑랩스'
2	'[트러스트마스터] T80 Ferrari 488 GTB 에디션 주식회사 투비네트웍스글로벌' '트러스트마스터 T300 페라리 Integral 레이싱휠 [PS5, PS4, PC지원] 주식회사 디에스샵(DS SHOP)' '레이저코리아 울버린 V2 크로마 Wolverine V2 Chroma 게임 컨트롤러 (주)하이케이넷'
1	'[노리박스] 오락실 게임기 분리기통(고급DX팩) (주)에스와이에스리테일' '[XBOX]마이크로 소프트 정식발매 X-BOX series X 1TB 새제품 다음텔레콤' '노리박스 32인치 스탠드형 강화유리 오락실게임기 오락기 DX팩(3000게임/720P/3~4인지원) (주)노리박스게임연구소'
0	'PC 삼국지 14 한글판 (스팀코드발송) (주) 디지털터치' 'Wizard with a Gun 스팀 PC 뉴 어카운트 (정지X) / 기존계정 가능 기존 계정 스팀 유통할인' '철권7 tekken7 PC/스팀 철권7 (코드48시이내발송) 전한수'
4	'한국 닌텐도 정품 게임기 스위치 신형 OLED+콘트라 로그콥스+액정강화유리세트 OLED 네온레드블루 색상_OLED본체+뉴슈퍼마리오U디럭스+강화유리 에이지씨' '게임&워치 젤다의 전설 주식회사 손오공' '닌텐도 스위치 라이트 옐로 동물의 숲 케이스 주식회사 손오공'

Evaluation

Metrics

Label	Metric
all	0.7772

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_el3")
# Run inference
preds = model("[PS4] 색보이 빅 어드벤처  에이티게임(주)")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	5	10.7325	23

Label	Training Sample Count
0	43
1	50
2	50
3	50
4	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
0.0263	1	0.496	-
1.3158	50	0.1186	-
2.6316	100	0.0532	-
3.9474	150	0.0398	-
5.2632	200	0.0002	-
6.5789	250	0.0001	-
7.8947	300	0.0001	-
9.2105	350	0.0001	-
10.5263	400	0.0001	-
11.8421	450	0.0001	-
13.1579	500	0.0001	-
14.4737	550	0.0001	-
15.7895	600	0.0	-
17.1053	650	0.0001	-
18.4211	700	0.0001	-
19.7368	750	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_el3