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: 4 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	'아라칸 아기 물놀이 방수 기저귀 3개입 2세트 총 6매 출산/육아 > 기저귀 > 수영장기저귀' '마미포코 물놀이팬티 4-5단계 (남녀선택) 12매 출산/육아 > 기저귀 > 수영장기저귀' '밤보 물놀이 수영팬티 스몰 1팩(12P) 출산/육아 > 기저귀 > 수영장기저귀'
2.0	'나비잠 나비잠 울트라씬듀얼핏 팬티 6팩 출산/육아 > 기저귀 > 일회용기저귀' '르소메 프리미엄 통잠 밤 아기 신생아 발진없는 밴드형 기저귀 2팩 출산/육아 > 기저귀 > 일회용기저귀' '애플크럼비 [보리보리/애플크럼비]애플크럼비 NEW 오리지널 테이프 XL 6팩(108매) 출산/육아 > 기저귀 > 일회용기저귀'
3.0	'아가방 새싹오가닉 기저귀 5매 출산/육아 > 기저귀 > 천기저귀' '베베라온 신생아 밤부 천기저귀 선물 체험 출산/육아 > 기저귀 > 천기저귀' '투유모유 무형광 무나염 순면 국산 아기 천기저귀 2박스 구매시 파우치 증정 출산/육아 > 기저귀 > 천기저귀'
0.0	'[베이비앙] 국내산 무형광 사이즈 상관없이 벨크로 탈부착으로 사용 가능 기저귀 고정을 위한 천 기저귀밴드 출산/육아 > 기저귀 > 기저귀커버/기저귀밴드' '처비체리 천기저귀 커버 쁘띠코숑 P tit Cochon 1개 출산/육아 > 기저귀 > 기저귀커버/기저귀밴드' '포켓식 원사이즈 기저귀커버 3장세트(잠금장치&색상선택) 출산/육아 > 기저귀 > 기저귀커버/기저귀밴드'

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_bc2")
# Run inference
preds = model("플라팜 뉴코코맘 아기 천기저귀 5매  출산/육아 > 기저귀 > 천기저귀")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	9	12.95	20

Label	Training Sample Count
0.0	20
1.0	20
2.0	20
3.0	20

Training Hyperparameters

batch_size: (256, 256)
num_epochs: (30, 30)
max_steps: -1
sampling_strategy: oversampling
num_iterations: 50
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
0.0625	1	0.476	-
3.125	50	0.3608	-
6.25	100	0.0472	-
9.375	150	0.0	-
12.5	200	0.0	-
15.625	250	0.0	-
18.75	300	0.0	-
21.875	350	0.0	-
25.0	400	0.0	-
28.125	450	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}
}

mini1013
/

master_cate_bc2