mini1013/master_cate_bt10_test

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:

1. Fine-tuning a Sentence Transformer with contrastive learning.
2. 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	'로얄워터 블랑쉬 코튼 비누향 베이비파우더 살냄새 수제 승무원 엑스트레 드 퍼퓸 30ml 24. 블루밍 (판매 1위) 주식회사 로얄워터' '블루 드 샤넬 빠르펭 50ML 옵션없음 플로라 무역' '딥티크 뗌포 오드 퍼퓸 75ml 옵션없음 대박컴퍼니'
0.0	'쿨티 - 스틸레 룸 디퓨저 - 린파 500ml/16.9oz 스트로베리넷 (홍콩)' '소소모소 디퓨저리필 500ml_코튼브리즈 _salestrNo:2439_지점명:emartNE.O.001 (주)리빙탑스/해당사항 없음' '디퓨저 섬유 리드스틱 화이트 50개입 디퓨저 섬유 옵션없음 '
2.0	'인센스 스틱 홀더 접시형 그린 (WC9C73F) 본상품선택 기타/해당사항 없음' '인센스홀더향 향꽂이 홀더 물방울 인테리어 인센스 (WD2F3FF) 본상품선택 기타/해당사항 없음' '인센스 홀더 미니화병 황동 향 피우기 나그참파 꽂이 (WBC1E2F) 본상품선택 기타/해당사항 없음'

Evaluation

Metrics

Label	Accuracy
all	0.9578

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_bt10_test")
# Run inference
preds = model("에르메스 떼르 데르메스EDT 50ml 옵션없음 주식회사 비엘컴퍼니")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	5	9.4127	18

Label	Training Sample Count
0.0	20
1.0	23
2.0	20

Training Hyperparameters

• batch_size: (512, 512)
• num_epochs: (50, 50)
• max_steps: -1
• sampling_strategy: oversampling
• num_iterations: 60
• 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
0.125	1	0.4915	-
6.25	50	0.1556	-
12.5	100	0.0	-
18.75	150	0.0	-
25.0	200	0.0	-
31.25	250	0.0	-
37.5	300	0.0	-
43.75	350	0.0	-
50.0	400	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}
}