mini1013/master_cate_bt_top11_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: 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
3	'로즈마리 아로마 에센셜 오일 12ml 천연 디퓨저 마사지 족욕 피로 페퍼민트 본상품선택 × 1 (#M)쿠팡 홈>생활용품>헤어/바디/세안>바디로션/크림>아로마오일 Coupang > 뷰티 > 바디 > 바디로션/크림 > 아로마오일' '루브르 알라바스트 디퓨저 스톤&리필 5ml 세트 (알라바스트 케이스+스톤+리필액 구성) 사모트라케의 승리의 여신 니케(멜 마르스) ssg > 뷰티 > 향수 > 여성향수;ssg > 뷰티 > 향수 > 캔들/디퓨저/아로마 ssg > 뷰티 > 향수 > 캔들/디퓨저/아로마' '아이캔디 윈드스핀 매직 볼륨 헤어컬 디퓨저 ssg > 뷰티 > 헤어/바디 > 헤어케어 > 드라이샴푸;ssg > 뷰티 > 헤어/바디 > 헤어스타일링 ssg > 뷰티 > 헤어/바디 > 헤어케어 > 드라이샴푸'
0	'코롱 50ml 택 1 (+스페셜 GIFT ) 5) 라임 바질 앤 만다린 코롱 50ml (#M)신세계백화점/향수/여성향수 LOREAL > DepartmentSsg > 아틀리에 코롱 > Generic > 핸드크림' '오 드 쏠레이 블랑 100ML SSG.COM>신세계백화점TOM FORD>FRAGRANCES>SIGNATURE FRAGRANCES;(#M)SSG.COM>신세계백화점TOM FORD>FRAGRANCE>SIGNATURE ssg > 뷰티 > 향수 > 여성향수' '메종마르지엘라바이 더 파이어플레이스 EDT 30ML(공식수입정품) 바이 더 파이어플레이스 30ML+선물박스포장 (#M)홈>화장품/미용>향수>남녀공용향수 Naverstore > 화장품/미용 > 향수 > 남녀공용향수'
2	'재고정리 오늘주문 내일도착 샤넬 코코 마드모아젤 우먼 오드퍼퓸 100ml 쇼핑백X (#M)11st>향수>여성향수>여성향수 11st > 뷰티 > 향수 > 여성향수' '헉슬리 퍼퓸 블루 메디나 탠저린 15mL 홈>Fragrance;(#M)홈>프레그런스>향수 Naverstore > 화장품/미용 > 향수 > 남녀공용향수' '조말론 오스만투스 블러썸 1온스 여성용 쾰른 스프레이 원래 언박스 단일상품 LotteOn > 뷰티 > 헤어/바디 > 바디케어 > 바디미스트/샤워코롱 LotteOn > 뷰티 > 헤어/바디 > 바디케어 > 바디미스트/샤워코롱'
1	'히어로 EDT 50ml DepartmentLotteOn > 뷰티 > 향수 > 남성용 > 31ml50ml DepartmentLotteOn > 뷰티 > 향수 > 남성용 > 51ml' '에르메스 떼르 데르메스 오 뜨레 프라쉐 EDT 125ml/관 MinSellAmount (#M)바디/헤어>바디케어>바디로션 Gmarket > 뷰티 > 바디/헤어 > 바디케어 > 바디로션' '[AK백화점][한정판] 랄프로렌 폴로 블루 베어 에디션 EDT 40ML(+단독 폴로블루 파우치) 단일상품 1095946223 LotteOn > 뷰티 > 향수 > 향수세트 LotteOn > 뷰티 > 향수 > 향수세트'

Evaluation

Metrics

Label	Accuracy
all	0.5351

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_bt_top11_test")
# Run inference
preds = model("샹스 오 드 빠르펭 35ml  ssg > 뷰티 > 향수 > 여성향수 ssg > 뷰티 > 향수 > 여성향수")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	12	21.735	48

Label	Training Sample Count
0	50
1	50
2	50
3	50

Training Hyperparameters

• batch_size: (64, 64)
• num_epochs: (30, 30)
• max_steps: -1
• sampling_strategy: oversampling
• num_iterations: 100
• 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
0.0032	1	0.4649	-
0.1597	50	0.4669	-
0.3195	100	0.4469	-
0.4792	150	0.4259	-
0.6390	200	0.3685	-
0.7987	250	0.2893	-
0.9585	300	0.2223	-
1.1182	350	0.1858	-
1.2780	400	0.1766	-
1.4377	450	0.1629	-
1.5974	500	0.1571	-
1.7572	550	0.1362	-
1.9169	600	0.1208	-
2.0767	650	0.1	-
2.2364	700	0.0746	-
2.3962	750	0.0699	-
2.5559	800	0.0635	-
2.7157	850	0.0464	-
2.8754	900	0.0246	-
3.0351	950	0.0195	-
3.1949	1000	0.0063	-
3.3546	1050	0.0004	-
3.5144	1100	0.0003	-
3.6741	1150	0.0001	-
3.8339	1200	0.0002	-
3.9936	1250	0.0007	-
4.1534	1300	0.0006	-
4.3131	1350	0.0001	-
4.4728	1400	0.0002	-
4.6326	1450	0.0001	-
4.7923	1500	0.0	-
4.9521	1550	0.0	-
5.1118	1600	0.0	-
5.2716	1650	0.0001	-
5.4313	1700	0.0	-
5.5911	1750	0.0001	-
5.7508	1800	0.0002	-
5.9105	1850	0.0	-
6.0703	1900	0.0	-
6.2300	1950	0.0	-
6.3898	2000	0.0	-
6.5495	2050	0.0	-
6.7093	2100	0.0	-
6.8690	2150	0.0	-
7.0288	2200	0.0	-
7.1885	2250	0.0002	-
7.3482	2300	0.0	-
7.5080	2350	0.0005	-
7.6677	2400	0.0003	-
7.8275	2450	0.0	-
7.9872	2500	0.0	-
8.1470	2550	0.0	-
8.3067	2600	0.0	-
8.4665	2650	0.0	-
8.6262	2700	0.0001	-
8.7859	2750	0.0	-
8.9457	2800	0.0	-
9.1054	2850	0.0005	-
9.2652	2900	0.0	-
9.4249	2950	0.0	-
9.5847	3000	0.0	-
9.7444	3050	0.0002	-
9.9042	3100	0.0047	-
10.0639	3150	0.0088	-
10.2236	3200	0.0031	-
10.3834	3250	0.0001	-
10.5431	3300	0.0	-
10.7029	3350	0.0	-
10.8626	3400	0.0	-
11.0224	3450	0.0	-
11.1821	3500	0.0	-
11.3419	3550	0.0	-
11.5016	3600	0.0	-
11.6613	3650	0.0001	-
11.8211	3700	0.0002	-
11.9808	3750	0.0025	-
12.1406	3800	0.0074	-
12.3003	3850	0.006	-
12.4601	3900	0.005	-
12.6198	3950	0.0006	-
12.7796	4000	0.0	-
12.9393	4050	0.0	-
13.0990	4100	0.0	-
13.2588	4150	0.0	-
13.4185	4200	0.0004	-
13.5783	4250	0.0	-
13.7380	4300	0.0	-
13.8978	4350	0.0	-
14.0575	4400	0.0	-
14.2173	4450	0.0	-
14.3770	4500	0.0	-
14.5367	4550	0.0	-
14.6965	4600	0.0	-
14.8562	4650	0.0	-
15.0160	4700	0.0	-
15.1757	4750	0.0	-
15.3355	4800	0.0	-
15.4952	4850	0.0	-
15.6550	4900	0.0	-
15.8147	4950	0.0	-
15.9744	5000	0.0	-
16.1342	5050	0.0	-
16.2939	5100	0.0	-
16.4537	5150	0.0	-
16.6134	5200	0.0	-
16.7732	5250	0.0	-
16.9329	5300	0.0	-
17.0927	5350	0.0	-
17.2524	5400	0.0	-
17.4121	5450	0.0	-
17.5719	5500	0.0	-
17.7316	5550	0.0	-
17.8914	5600	0.0002	-
18.0511	5650	0.0	-
18.2109	5700	0.0	-
18.3706	5750	0.0	-
18.5304	5800	0.0	-
18.6901	5850	0.0	-
18.8498	5900	0.0	-
19.0096	5950	0.0	-
19.1693	6000	0.0	-
19.3291	6050	0.0	-
19.4888	6100	0.0	-
19.6486	6150	0.0	-
19.8083	6200	0.0	-
19.9681	6250	0.0	-
20.1278	6300	0.0	-
20.2875	6350	0.0	-
20.4473	6400	0.0	-
20.6070	6450	0.0	-
20.7668	6500	0.0	-
20.9265	6550	0.0	-
21.0863	6600	0.0	-
21.2460	6650	0.0	-
21.4058	6700	0.0	-
21.5655	6750	0.0	-
21.7252	6800	0.0	-
21.8850	6850	0.0	-
22.0447	6900	0.0	-
22.2045	6950	0.0	-
22.3642	7000	0.0	-
22.5240	7050	0.0	-
22.6837	7100	0.0	-
22.8435	7150	0.0	-
23.0032	7200	0.0	-
23.1629	7250	0.0	-
23.3227	7300	0.0	-
23.4824	7350	0.0	-
23.6422	7400	0.0	-
23.8019	7450	0.0	-
23.9617	7500	0.0	-
24.1214	7550	0.0	-
24.2812	7600	0.0	-
24.4409	7650	0.0	-
24.6006	7700	0.0	-
24.7604	7750	0.0	-
24.9201	7800	0.0	-
25.0799	7850	0.0	-
25.2396	7900	0.0	-
25.3994	7950	0.0	-
25.5591	8000	0.0	-
25.7188	8050	0.0	-
25.8786	8100	0.0	-
26.0383	8150	0.0	-
26.1981	8200	0.0	-
26.3578	8250	0.0	-
26.5176	8300	0.0	-
26.6773	8350	0.0	-
26.8371	8400	0.0	-
26.9968	8450	0.0	-
27.1565	8500	0.0	-
27.3163	8550	0.0	-
27.4760	8600	0.0	-
27.6358	8650	0.0	-
27.7955	8700	0.0	-
27.9553	8750	0.0	-
28.1150	8800	0.0	-
28.2748	8850	0.0	-
28.4345	8900	0.0	-
28.5942	8950	0.0	-
28.7540	9000	0.0	-
28.9137	9050	0.0	-
29.0735	9100	0.0	-
29.2332	9150	0.0	-
29.3930	9200	0.0	-
29.5527	9250	0.0	-
29.7125	9300	0.0	-
29.8722	9350	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}
}