Hugging Face's logo

mini1013
/
master_cate_top_bt6_3_test_flat

Text Classification
setfit
Safetensors
sentence-transformers
roberta
generated_from_setfit_trainer
Eval Results
Model card Files Community
master_cate_top_bt6_3_test_flat / README.md
mini1013's picture
mini1013
Push model using huggingface_hub.
31d1c0f verified
preview code
|
raw
history blame contribute delete
19.9 kB
metadata
base_model: mini1013/master_domain
library_name: setfit
metrics:
  - accuracy
pipeline_tag: text-classification
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
widget:
  - text: >-
      더툴랩 더스타일래쉬 4종리얼/내츄럴/볼륨/맥스 중 택1 004 맥스 LotteOn > 뷰티 > 뷰티기기/소품 > 아이/브로우소품 >
      브로우관리 LotteOn > 뷰티 > 뷰티기기/소품 > 아이/브로우소품 > 브로우관리
  - text: >-
      더툴랩 더스타일래쉬 4종(리얼/내츄럴/볼륨/맥스) 중 택1 001 리얼 LotteOn > 뷰티 > 뷰티기기/소품 > 아이/브로우소품
      > 속눈썹관리 LotteOn > 뷰티 > 뷰티기기/소품 > 아이/브로우소품 > 속눈썹관리
  - text: >-
      더툴랩 더스타일래쉬 4종(리얼/내츄럴/볼륨/맥스) 중 택1 001 리얼 LotteOn > 뷰티 > 뷰티기기/소품 > 아이/브로우소품
      > 브로우관리 LotteOn > 뷰티 > 뷰티기기/소품 > 아이/브로우소품 > 브로우관리
  - text: >-
      더툴랩 더스타일 래쉬 맥스(TSL004) × 2개 LotteOn > 뷰티 > 뷰티기기/소품 > 아이/브로우소품 > 브로우관리
      LotteOn > 뷰티 > 뷰티기기/소품 > 아이/브로우소품 > 브로우관리
  - text: >-
      더툴랩 스타일 래쉬 속눈썹 볼륨(TSL003) × 1개 LotteOn > 뷰티 > 뷰티기기/소품 > 아이/브로우소품 > 속눈썹관리
      LotteOn > 뷰티 > 뷰티기기/소품 > 아이/브로우소품 > 속눈썹관리
inference: true
model-index:
  - name: SetFit with mini1013/master_domain
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 0.9812680115273775
            name: Accuracy

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 Sources

Model Labels

Label Examples
4
  • '프레이속눈썹 가닥속눈썹 V_12mm (#M)홈>전체상품 Naverstore > 화장품/미용 > 뷰티소품 > 아이소품 > 속눈썹/속눈썹펌제'
  • '아리따움 아이돌 래쉬 프리미엄 타입 22호 러블리 아이(프리미엄) (#M)위메프 > 뷰티 > 이미용소품/기기 > 아이소품 > 인조속눈썹 위메프 > 뷰티 > 이미용소품/기기 > 아이소품 > 인조속눈썹'
  • '에뛰드하우스 마이뷰티툴 속눈썹 6종/인조속눈썹 6호 볼륨 업 (#M)11st>뷰티소품>메이크업소품>메이크업소품 11st > 뷰티 > 뷰티소품 > 메이크업소품'
1
  • '트위저맨 - 스텐리스 스틸 브로우 셰이핑 가위 & 브러쉬 (스튜디오 컬렉션) 2pcs ssg > 뷰티 > 헤어/바디 > 헤어기기/소품 > 드라이기 ssg > 뷰티 > 헤어/바디 > 헤어기기/소품 > 드라이기'
  • '트위저맨 Studio Collection 브로우 쉐이핑 가위 브러쉬 NEW 정품 LotteOn > 뷰티 > 메이크업 > 메이크업세트 LotteOn > 뷰티 > 메이크업 > 메이크업세트'
  • '트위저맨 스테인리스 브로우 셰이핑 시져 브러쉬 70238 ssg > 뷰티 > 메이크업 > 베이스메이크업 > 파운데이션 ssg > 뷰티 > 메이크업 > 베이스메이크업 > 파운데이션'
0
  • '토니모리 쌍꺼풀액 속눈썹 접착제 홈>아리따움;(#M)홈>전체상품 Naverstore > 화장품/미용 > 뷰티소품 > 아이소품 > 속눈썹/속눈썹펌제'
  • '에뛰드 마이뷰티툴 쌍꺼풀 액&속눈썹 접착제 에뛰드 마이뷰티툴 쌍꺼풀 액&속눈썹 접착제 홈>미용소품>얼굴소품>쌍커풀;(#M)홈>미용소품>아이>속눈썹/쌍꺼풀 OLIVEYOUNG > 미용소품 > 아이 > 속눈썹/쌍꺼풀'
  • '트위저맨 폴딩 아이래쉬컴850676 30 66416850676 30 (#M)SSG.COM/메이크업/베이스메이크업/쿠션파운데이션 ssg > 뷰티 > 메이크업 > 베이스메이크업 > 쿠션파운데이션'
2
  • '트위저맨 프로페셔널 아이래쉬 컬러 1개 (#M)SSG.COM/미용기기/소품/아이소품/뷰러 ssg > 뷰티 > 미용기기/소품 > 아이소품 > 뷰러'
  • '더툴랩 1039R 래쉬컬러 레귤러 (아찔한컬링) (#M)홈>화장품/미용>뷰티소품>아이소품>뷰러 Naverstore > 화장품/미용 > 뷰티소품 > 아이소품 > 뷰러'
  • '슈에무라 아이래쉬 컬러 55721 LOREAL > Ssg > 슈에무라 > Branded > 슈에무라 ssg > 뷰티 > 메이크업 > 베이스메이크업'
3
  • 'e.l.f. 듀얼 펜슬 샤프너 혼합 색상 × 6개입 (#M)쿠팡 홈>뷰티>뷰티소품>아이소품>족집게/샤프너 Coupang > 뷰티 > 뷰티소품 > 아이소품 > 족집게/샤프너'
  • 'e.l.f. 듀얼 펜슬 샤프너 2세트 (#M)쿠팡 홈>뷰티>뷰티소품>아이소품>족집게/샤프너 Coupang > 뷰티 > 뷰티소품 > 아이소품 > 족집게/샤프너'
  • 'e.l.f. 듀얼 펜슬 샤프너 4세트 (#M)쿠팡 홈>뷰티>뷰티소품>아이소품>족집게/샤프너 Coupang > 뷰티 > 뷰티소품 > 아이소품 > 족집게/샤프너'

Evaluation

Metrics

Label Accuracy
all 0.9813

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_top_bt6_3_test_flat")
# Run inference
preds = model("더툴랩 더스타일 래쉬 맥스(TSL004) × 2개 LotteOn > 뷰티 > 뷰티기기/소품 > 아이/브로우소품 > 브로우관리 LotteOn > 뷰티 > 뷰티기기/소품 > 아이/브로우소품 > 브로우관리")

Training Details

Training Set Metrics

Training set Min Median Max
Word count 13 19.2707 47
Label Training Sample Count
0 50
1 9
2 50
3 22
4 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
0.0035 1 0.4744 -
0.1767 50 0.4176 -
0.3534 100 0.3618 -
0.5300 150 0.2985 -
0.7067 200 0.2327 -
0.8834 250 0.1017 -
1.0601 300 0.0185 -
1.2367 350 0.0037 -
1.4134 400 0.0018 -
1.5901 450 0.0009 -
1.7668 500 0.0004 -
1.9435 550 0.0005 -
2.1201 600 0.0002 -
2.2968 650 0.0002 -
2.4735 700 0.0001 -
2.6502 750 0.0001 -
2.8269 800 0.0001 -
3.0035 850 0.0001 -
3.1802 900 0.0001 -
3.3569 950 0.0 -
3.5336 1000 0.0 -
3.7102 1050 0.0001 -
3.8869 1100 0.0001 -
4.0636 1150 0.0 -
4.2403 1200 0.0 -
4.4170 1250 0.0 -
4.5936 1300 0.0 -
4.7703 1350 0.0 -
4.9470 1400 0.0 -
5.1237 1450 0.0 -
5.3004 1500 0.0 -
5.4770 1550 0.0 -
5.6537 1600 0.0 -
5.8304 1650 0.0 -
6.0071 1700 0.0 -
6.1837 1750 0.0 -
6.3604 1800 0.0 -
6.5371 1850 0.0 -
6.7138 1900 0.0 -
6.8905 1950 0.0 -
7.0671 2000 0.0 -
7.2438 2050 0.0 -
7.4205 2100 0.0 -
7.5972 2150 0.0023 -
7.7739 2200 0.0029 -
7.9505 2250 0.0001 -
8.1272 2300 0.0 -
8.3039 2350 0.0 -
8.4806 2400 0.0 -
8.6572 2450 0.0 -
8.8339 2500 0.0 -
9.0106 2550 0.0 -
9.1873 2600 0.0 -
9.3640 2650 0.0 -
9.5406 2700 0.0 -
9.7173 2750 0.0 -
9.8940 2800 0.0 -
10.0707 2850 0.0 -
10.2473 2900 0.0 -
10.4240 2950 0.0 -
10.6007 3000 0.0 -
10.7774 3050 0.0 -
10.9541 3100 0.0 -
11.1307 3150 0.0 -
11.3074 3200 0.0 -
11.4841 3250 0.0 -
11.6608 3300 0.0 -
11.8375 3350 0.0 -
12.0141 3400 0.0 -
12.1908 3450 0.0 -
12.3675 3500 0.0 -
12.5442 3550 0.0 -
12.7208 3600 0.0 -
12.8975 3650 0.0 -
13.0742 3700 0.0 -
13.2509 3750 0.0 -
13.4276 3800 0.0 -
13.6042 3850 0.0 -
13.7809 3900 0.0 -
13.9576 3950 0.0 -
14.1343 4000 0.0 -
14.3110 4050 0.0 -
14.4876 4100 0.0 -
14.6643 4150 0.0 -
14.8410 4200 0.0 -
15.0177 4250 0.0 -
15.1943 4300 0.0 -
15.3710 4350 0.0 -
15.5477 4400 0.0 -
15.7244 4450 0.0 -
15.9011 4500 0.0005 -
16.0777 4550 0.0008 -
16.2544 4600 0.0001 -
16.4311 4650 0.0 -
16.6078 4700 0.0 -
16.7845 4750 0.0 -
16.9611 4800 0.0002 -
17.1378 4850 0.0 -
17.3145 4900 0.0003 -
17.4912 4950 0.0 -
17.6678 5000 0.0 -
17.8445 5050 0.0 -
18.0212 5100 0.0 -
18.1979 5150 0.0 -
18.3746 5200 0.0 -
18.5512 5250 0.0 -
18.7279 5300 0.0 -
18.9046 5350 0.0 -
19.0813 5400 0.0 -
19.2580 5450 0.0 -
19.4346 5500 0.0 -
19.6113 5550 0.0 -
19.7880 5600 0.0 -
19.9647 5650 0.0 -
20.1413 5700 0.0 -
20.3180 5750 0.0 -
20.4947 5800 0.0 -
20.6714 5850 0.0 -
20.8481 5900 0.0 -
21.0247 5950 0.0 -
21.2014 6000 0.0 -
21.3781 6050 0.0 -
21.5548 6100 0.0 -
21.7314 6150 0.0 -
21.9081 6200 0.0 -
22.0848 6250 0.0 -
22.2615 6300 0.0 -
22.4382 6350 0.0 -
22.6148 6400 0.0 -
22.7915 6450 0.0 -
22.9682 6500 0.0 -
23.1449 6550 0.0 -
23.3216 6600 0.0 -
23.4982 6650 0.0 -
23.6749 6700 0.0 -
23.8516 6750 0.0 -
24.0283 6800 0.0 -
24.2049 6850 0.0 -
24.3816 6900 0.0 -
24.5583 6950 0.0 -
24.7350 7000 0.0 -
24.9117 7050 0.0 -
25.0883 7100 0.0 -
25.2650 7150 0.0 -
25.4417 7200 0.0 -
25.6184 7250 0.0 -
25.7951 7300 0.0 -
25.9717 7350 0.0 -
26.1484 7400 0.0 -
26.3251 7450 0.0 -
26.5018 7500 0.0 -
26.6784 7550 0.0 -
26.8551 7600 0.0 -
27.0318 7650 0.0 -
27.2085 7700 0.0 -
27.3852 7750 0.0 -
27.5618 7800 0.0 -
27.7385 7850 0.0 -
27.9152 7900 0.0 -
28.0919 7950 0.0 -
28.2686 8000 0.0 -
28.4452 8050 0.0 -
28.6219 8100 0.0 -
28.7986 8150 0.0 -
28.9753 8200 0.0 -
29.1519 8250 0.0 -
29.3286 8300 0.0 -
29.5053 8350 0.0 -
29.6820 8400 0.0 -
29.8587 8450 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}
}