metadata
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: >-
아가방 가을 골지 레깅스 아기 유아 바지 남아 여아 속바지 신생 쫄바지 베이비 키즈 아가방 레깅스/쫄바지_01 치치골지레깅스
그린_80 출산/육아 > 유아동의류 > 레깅스
- text: 라고 세일러맨투맨 23겨울 아동복 아동 키즈 주니어 여아 JS_옐로 출산/육아 > 유아동의류 > 티셔츠
- text: 여아 드레스 원피스 겨울왕국2 캐주얼 안나 공주 원픽4 샴페인_120 출산/육아 > 유아동의류 > 공주드레스
- text: '[뉴발란스키즈]뉴키모 보이 다운(NK9PD4105U)100~160Size Black/110 출산/육아 > 유아동의류 > 점퍼'
- text: 데일리베베 겨울 뽀글이점퍼 유아집업 아기집업 주니어 토끼_JM 출산/육아 > 유아동의류 > 점퍼
metrics:
- accuracy
pipeline_tag: text-classification
library_name: setfit
inference: true
base_model: mini1013/master_domain
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: 1
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:
- 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: 27 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 |
|
| 26.0 |
|
| 17.0 |
|
| 6.0 |
|
| 14.0 |
|
| 23.0 |
|
| 10.0 |
|
| 16.0 |
|
| 20.0 |
|
| 19.0 |
|
| 0.0 |
|
| 15.0 |
|
| 13.0 |
|
| 3.0 |
|
| 22.0 |
|
| 9.0 |
|
| 24.0 |
|
| 4.0 |
|
| 2.0 |
|
| 21.0 |
|
| 5.0 |
|
| 25.0 |
|
| 8.0 |
|
| 18.0 |
|
| 12.0 |
|
| 11.0 |
|
| 7.0 |
|
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_bc19")
# Run inference
preds = model("데일리베베 겨울 뽀글이점퍼 유아집업 아기집업 주니어 토끼_JM 출산/육아 > 유아동의류 > 점퍼")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 7 | 15.2902 | 36 |
| Label | Training Sample Count |
|---|---|
| 0.0 | 70 |
| 1.0 | 70 |
| 2.0 | 20 |
| 3.0 | 70 |
| 4.0 | 70 |
| 5.0 | 70 |
| 6.0 | 70 |
| 7.0 | 20 |
| 8.0 | 70 |
| 9.0 | 70 |
| 10.0 | 70 |
| 11.0 | 70 |
| 12.0 | 70 |
| 13.0 | 70 |
| 14.0 | 70 |
| 15.0 | 70 |
| 16.0 | 70 |
| 17.0 | 70 |
| 18.0 | 70 |
| 19.0 | 70 |
| 20.0 | 70 |
| 21.0 | 70 |
| 22.0 | 70 |
| 23.0 | 70 |
| 24.0 | 70 |
| 25.0 | 20 |
| 26.0 | 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 |
|---|---|---|---|
| 0.0029 | 1 | 0.499 | - |
| 0.1471 | 50 | 0.4995 | - |
| 0.2941 | 100 | 0.4977 | - |
| 0.4412 | 150 | 0.4739 | - |
| 0.5882 | 200 | 0.3318 | - |
| 0.7353 | 250 | 0.2867 | - |
| 0.8824 | 300 | 0.1873 | - |
| 1.0294 | 350 | 0.1056 | - |
| 1.1765 | 400 | 0.0747 | - |
| 1.3235 | 450 | 0.0675 | - |
| 1.4706 | 500 | 0.0391 | - |
| 1.6176 | 550 | 0.0156 | - |
| 1.7647 | 600 | 0.0067 | - |
| 1.9118 | 650 | 0.004 | - |
| 2.0588 | 700 | 0.0029 | - |
| 2.2059 | 750 | 0.0018 | - |
| 2.3529 | 800 | 0.0019 | - |
| 2.5 | 850 | 0.0018 | - |
| 2.6471 | 900 | 0.0006 | - |
| 2.7941 | 950 | 0.0004 | - |
| 2.9412 | 1000 | 0.0004 | - |
| 3.0882 | 1050 | 0.0003 | - |
| 3.2353 | 1100 | 0.0004 | - |
| 3.3824 | 1150 | 0.0003 | - |
| 3.5294 | 1200 | 0.0002 | - |
| 3.6765 | 1250 | 0.0003 | - |
| 3.8235 | 1300 | 0.0003 | - |
| 3.9706 | 1350 | 0.0001 | - |
| 4.1176 | 1400 | 0.0003 | - |
| 4.2647 | 1450 | 0.0002 | - |
| 4.4118 | 1500 | 0.0002 | - |
| 4.5588 | 1550 | 0.0002 | - |
| 4.7059 | 1600 | 0.0003 | - |
| 4.8529 | 1650 | 0.0001 | - |
| 5.0 | 1700 | 0.0002 | - |
| 5.1471 | 1750 | 0.0002 | - |
| 5.2941 | 1800 | 0.0001 | - |
| 5.4412 | 1850 | 0.0003 | - |
| 5.5882 | 1900 | 0.0002 | - |
| 5.7353 | 1950 | 0.0003 | - |
| 5.8824 | 2000 | 0.0002 | - |
| 6.0294 | 2050 | 0.0003 | - |
| 6.1765 | 2100 | 0.0001 | - |
| 6.3235 | 2150 | 0.0002 | - |
| 6.4706 | 2200 | 0.0001 | - |
| 6.6176 | 2250 | 0.0002 | - |
| 6.7647 | 2300 | 0.0002 | - |
| 6.9118 | 2350 | 0.0002 | - |
| 7.0588 | 2400 | 0.0002 | - |
| 7.2059 | 2450 | 0.0002 | - |
| 7.3529 | 2500 | 0.0001 | - |
| 7.5 | 2550 | 0.0001 | - |
| 7.6471 | 2600 | 0.0002 | - |
| 7.7941 | 2650 | 0.0002 | - |
| 7.9412 | 2700 | 0.0002 | - |
| 8.0882 | 2750 | 0.0001 | - |
| 8.2353 | 2800 | 0.0001 | - |
| 8.3824 | 2850 | 0.0002 | - |
| 8.5294 | 2900 | 0.0002 | - |
| 8.6765 | 2950 | 0.0001 | - |
| 8.8235 | 3000 | 0.0003 | - |
| 8.9706 | 3050 | 0.0003 | - |
| 9.1176 | 3100 | 0.0002 | - |
| 9.2647 | 3150 | 0.0002 | - |
| 9.4118 | 3200 | 0.0 | - |
| 9.5588 | 3250 | 0.0003 | - |
| 9.7059 | 3300 | 0.0003 | - |
| 9.8529 | 3350 | 0.0001 | - |
| 10.0 | 3400 | 0.0001 | - |
| 10.1471 | 3450 | 0.0002 | - |
| 10.2941 | 3500 | 0.0001 | - |
| 10.4412 | 3550 | 0.0002 | - |
| 10.5882 | 3600 | 0.0001 | - |
| 10.7353 | 3650 | 0.0001 | - |
| 10.8824 | 3700 | 0.0002 | - |
| 11.0294 | 3750 | 0.0001 | - |
| 11.1765 | 3800 | 0.0001 | - |
| 11.3235 | 3850 | 0.0002 | - |
| 11.4706 | 3900 | 0.0003 | - |
| 11.6176 | 3950 | 0.0001 | - |
| 11.7647 | 4000 | 0.0002 | - |
| 11.9118 | 4050 | 0.0001 | - |
| 12.0588 | 4100 | 0.0001 | - |
| 12.2059 | 4150 | 0.0002 | - |
| 12.3529 | 4200 | 0.0001 | - |
| 12.5 | 4250 | 0.0001 | - |
| 12.6471 | 4300 | 0.0002 | - |
| 12.7941 | 4350 | 0.0003 | - |
| 12.9412 | 4400 | 0.0006 | - |
| 13.0882 | 4450 | 0.0018 | - |
| 13.2353 | 4500 | 0.0011 | - |
| 13.3824 | 4550 | 0.0008 | - |
| 13.5294 | 4600 | 0.0011 | - |
| 13.6765 | 4650 | 0.001 | - |
| 13.8235 | 4700 | 0.0003 | - |
| 13.9706 | 4750 | 0.0001 | - |
| 14.1176 | 4800 | 0.0001 | - |
| 14.2647 | 4850 | 0.0001 | - |
| 14.4118 | 4900 | 0.0001 | - |
| 14.5588 | 4950 | 0.0002 | - |
| 14.7059 | 5000 | 0.0002 | - |
| 14.8529 | 5050 | 0.0 | - |
| 15.0 | 5100 | 0.0 | - |
| 15.1471 | 5150 | 0.0 | - |
| 15.2941 | 5200 | 0.0 | - |
| 15.4412 | 5250 | 0.0 | - |
| 15.5882 | 5300 | 0.0 | - |
| 15.7353 | 5350 | 0.0 | - |
| 15.8824 | 5400 | 0.0 | - |
| 16.0294 | 5450 | 0.0 | - |
| 16.1765 | 5500 | 0.0 | - |
| 16.3235 | 5550 | 0.0 | - |
| 16.4706 | 5600 | 0.0 | - |
| 16.6176 | 5650 | 0.0 | - |
| 16.7647 | 5700 | 0.0 | - |
| 16.9118 | 5750 | 0.0 | - |
| 17.0588 | 5800 | 0.0 | - |
| 17.2059 | 5850 | 0.0 | - |
| 17.3529 | 5900 | 0.0 | - |
| 17.5 | 5950 | 0.0 | - |
| 17.6471 | 6000 | 0.0 | - |
| 17.7941 | 6050 | 0.0 | - |
| 17.9412 | 6100 | 0.0 | - |
| 18.0882 | 6150 | 0.0 | - |
| 18.2353 | 6200 | 0.0 | - |
| 18.3824 | 6250 | 0.0 | - |
| 18.5294 | 6300 | 0.0 | - |
| 18.6765 | 6350 | 0.0 | - |
| 18.8235 | 6400 | 0.0 | - |
| 18.9706 | 6450 | 0.0 | - |
| 19.1176 | 6500 | 0.0 | - |
| 19.2647 | 6550 | 0.0 | - |
| 19.4118 | 6600 | 0.0 | - |
| 19.5588 | 6650 | 0.0 | - |
| 19.7059 | 6700 | 0.0 | - |
| 19.8529 | 6750 | 0.0 | - |
| 20.0 | 6800 | 0.0 | - |
| 20.1471 | 6850 | 0.0 | - |
| 20.2941 | 6900 | 0.0 | - |
| 20.4412 | 6950 | 0.0 | - |
| 20.5882 | 7000 | 0.0 | - |
| 20.7353 | 7050 | 0.0 | - |
| 20.8824 | 7100 | 0.0 | - |
| 21.0294 | 7150 | 0.0 | - |
| 21.1765 | 7200 | 0.0 | - |
| 21.3235 | 7250 | 0.0 | - |
| 21.4706 | 7300 | 0.0 | - |
| 21.6176 | 7350 | 0.0 | - |
| 21.7647 | 7400 | 0.0 | - |
| 21.9118 | 7450 | 0.0 | - |
| 22.0588 | 7500 | 0.0 | - |
| 22.2059 | 7550 | 0.0 | - |
| 22.3529 | 7600 | 0.0 | - |
| 22.5 | 7650 | 0.0 | - |
| 22.6471 | 7700 | 0.0 | - |
| 22.7941 | 7750 | 0.0 | - |
| 22.9412 | 7800 | 0.0 | - |
| 23.0882 | 7850 | 0.0 | - |
| 23.2353 | 7900 | 0.0 | - |
| 23.3824 | 7950 | 0.0 | - |
| 23.5294 | 8000 | 0.0 | - |
| 23.6765 | 8050 | 0.0 | - |
| 23.8235 | 8100 | 0.0 | - |
| 23.9706 | 8150 | 0.0 | - |
| 24.1176 | 8200 | 0.0 | - |
| 24.2647 | 8250 | 0.0 | - |
| 24.4118 | 8300 | 0.0 | - |
| 24.5588 | 8350 | 0.0 | - |
| 24.7059 | 8400 | 0.0 | - |
| 24.8529 | 8450 | 0.0 | - |
| 25.0 | 8500 | 0.0 | - |
| 25.1471 | 8550 | 0.0 | - |
| 25.2941 | 8600 | 0.0 | - |
| 25.4412 | 8650 | 0.0 | - |
| 25.5882 | 8700 | 0.0 | - |
| 25.7353 | 8750 | 0.0 | - |
| 25.8824 | 8800 | 0.0 | - |
| 26.0294 | 8850 | 0.0 | - |
| 26.1765 | 8900 | 0.0 | - |
| 26.3235 | 8950 | 0.0 | - |
| 26.4706 | 9000 | 0.0 | - |
| 26.6176 | 9050 | 0.0 | - |
| 26.7647 | 9100 | 0.0 | - |
| 26.9118 | 9150 | 0.0 | - |
| 27.0588 | 9200 | 0.0 | - |
| 27.2059 | 9250 | 0.0 | - |
| 27.3529 | 9300 | 0.0 | - |
| 27.5 | 9350 | 0.0 | - |
| 27.6471 | 9400 | 0.0 | - |
| 27.7941 | 9450 | 0.0 | - |
| 27.9412 | 9500 | 0.0 | - |
| 28.0882 | 9550 | 0.0 | - |
| 28.2353 | 9600 | 0.0 | - |
| 28.3824 | 9650 | 0.0 | - |
| 28.5294 | 9700 | 0.0 | - |
| 28.6765 | 9750 | 0.0 | - |
| 28.8235 | 9800 | 0.0 | - |
| 28.9706 | 9850 | 0.0 | - |
| 29.1176 | 9900 | 0.0 | - |
| 29.2647 | 9950 | 0.0 | - |
| 29.4118 | 10000 | 0.0 | - |
| 29.5588 | 10050 | 0.0 | - |
| 29.7059 | 10100 | 0.0 | - |
| 29.8529 | 10150 | 0.0 | - |
| 30.0 | 10200 | 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}
}