mini1013/master_cate_bt11_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: 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
0.0	'MANIC PANIC 매닉 패닉 Bad Boy Blue 배드 보이 블루 옵션없음 제이(J) 커머스' '미쟝센 올뉴 쉽고빠른 거품 염색약 5N 갈색 1개 옵션없음 트레이딩제이' '376252 씨드비 물염색 시즌2 씨비드 4회분 미디엄브라운 NEW 비건 미디엄 브라운 1박스_◈232431989◈ 제이제이홀딩스'
3.0	'로레알 테크니아트 픽스 디자인 스프레이 200ml 옵션없음 파스텔뷰티' '과일나라 컨퓸 슈퍼하드 워터스프레이 252ml 옵션없음 다인유통' '폴미첼 프리즈 앤 슈퍼 샤인 스프레이 250ml 옵션없음 다사다 유한책임회사'
4.0	'미쟝센 파워스윙 슈퍼하드 크림 왁스 9 미디움 리젠트업 80g 옵션없음 와라즈' 'Loma Hair Care 3525927124 LOMA 포밍 페이스트 85g(3온스) 옵션없음 넥스유로(NEXEURO)' '차홍 왁스 쉬폰 소프트 80ml 부드러운 크림제형 옵션없음 박예찬'
1.0	'모레모 케라틴 셀프 다운 펌 6개 100g 옵션없음 건강드림' '다주자 울트라 다운펌150ml 남자다운펌 여성매직펌 잔머리펌 다운펌set 옵션없음 포비티엘' '미용실 다운펌약 집에서 옆머리 누르기 올리브영 악성곱슬 남자 셀프 다운펌 옵션없음 새벽 마트'
5.0	'꽃을든남자 초강력헤어젤 500ml 옵션없음 태은코리아' 'lg생활건강 아르드포 헤어젤 펌프형 300ml 옵션없음 맥센 트레이드' 'Ecoco 에코 스타일러 크리스탈 스타일링 젤 453g (3팩) 옵션없음 세렌몰1'
2.0	'밀본 니제르 클러치피즈 하이 클러치피즈 200g 헤어무스 헤어팟' '갸스비 수퍼하드 스타일링폼 무스 185ml 홈쇼핑 동일상품 수퍼하드 스타일링폼 무스 185ml 제이에스유통' '꽃을든남자 스타일링 헤어 무스 300ml 퀸뷰티'

Evaluation

Metrics

Label	Accuracy
all	0.7192

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_bt11_test")
# Run inference
preds = model("헤어젤슈퍼하드400ml 과일나라 컨퓸 MWB794D8 옵션없음 하니스토어04")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	5	9.4957	26

Label	Training Sample Count
0.0	25
1.0	19
2.0	15
3.0	25
4.0	19
5.0	14

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
0.0714	1	0.4886	-
3.5714	50	0.3088	-
7.1429	100	0.049	-
10.7143	150	0.0043	-
14.2857	200	0.0001	-
17.8571	250	0.0001	-
21.4286	300	0.0001	-
25.0	350	0.0001	-
28.5714	400	0.0001	-
32.1429	450	0.0001	-
35.7143	500	0.0001	-
39.2857	550	0.0001	-
42.8571	600	0.0001	-
46.4286	650	0.0001	-
50.0	700	0.0001	-

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}
}