mini1013/master_cate_bc25

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: 2 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	'이유식 야채 큐브 다진야채 적양배추_유아기 출산/육아 > 이유식 > 이유식재료' '오뚜기 어린이카레 80g 출산/육아 > 이유식 > 이유식재료' '라온킴 다진야채 매일 만드는 이유식큐브 토핑 초기 중기 후기 완료 연근(껍질제거)_중기 출산/육아 > 이유식 > 이유식재료'
0.0	'[1+1 ] 아기퓨레 과일 무럭무럭 키즈죽 간식 중기 후기 파우치 실온이유식 12개월 단호박 1박스 + 바나나단호박 1박스 출산/육아 > 이유식 > 가공이유식' '푸드트리 아기카레 덮밥소스 돌 두돌 아기반찬 유아반찬 유아식 소고기커리 아기덮밥 소스) A07 소고기 순한짜장 출산/육아 > 이유식 > 가공이유식' '퓨어잇 아이김 3+3팩 골라담기 파래김/김과자 오가닉 아이김자반 3봉_유기농 김100% 3팩 출산/육아 > 이유식 > 가공이유식'

Evaluation

Metrics

Label	Accuracy
all	1.0

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_bc25")
# Run inference
preds = model("알렉스앤필 6종 스웨덴 유기농 아기 이유식 과일퓨레 당근&망고 출산/육아 > 이유식 > 가공이유식")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	8	15.4286	23

Label	Training Sample Count
0.0	70
1.0	70

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
0.0357	1	0.4786	-
1.7857	50	0.2484	-
3.5714	100	0.0	-
5.3571	150	0.0	-
7.1429	200	0.0	-
8.9286	250	0.0	-
10.7143	300	0.0	-
12.5	350	0.0	-
14.2857	400	0.0	-
16.0714	450	0.0	-
17.8571	500	0.0	-
19.6429	550	0.0	-
21.4286	600	0.0	-
23.2143	650	0.0	-
25.0	700	0.0	-
26.7857	750	0.0	-
28.5714	800	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}
}