metadata
base_model: mini1013/master_domain
library_name: setfit
metrics:
- metric
pipeline_tag: text-classification
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: 귀뚜라미 전기 온수기 50리터 저장식 식당 카페 미용실 온수기 설치 KDEW 상품만 구매(셀프설치)_G-15(벽걸이형) 조아홈시스
- text: 크레모아 선풍기 V1040 서큘레이터 웜그레이 (주)가야미
- text: '[나비아] 가스히터 SGH-200 낚시 1번지(피싱매니저)'
- text: 바이빔 닥스훈트 전기방석[1인용] 1인용 주식회사 바이빔
- text: >-
[정발 한국판] [샤오미코리아 정품][온라인총판 직영점] 미에어 스마트 4 AC-M16-SC 공기청정기 미에어
공기청정기4(AC-M16-SC) (주)더데이
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: metric
value: 0.87719191055172
name: Metric
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: 19 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 |
|---|---|
| 12 |
|
| 8 |
|
| 9 |
|
| 5 |
|
| 18 |
|
| 1 |
|
| 10 |
|
| 11 |
|
| 3 |
|
| 15 |
|
| 0 |
|
| 7 |
|
| 4 |
|
| 14 |
|
| 6 |
|
| 16 |
|
| 13 |
|
| 17 |
|
| 2 |
|
Evaluation
Metrics
| Label | Metric |
|---|---|
| all | 0.8772 |
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_el4")
# Run inference
preds = model("바이빔 닥스훈트 전기방석[1인용] 1인용 주식회사 바이빔")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 3 | 9.2892 | 26 |
| Label | Training Sample Count |
|---|---|
| 0 | 50 |
| 1 | 50 |
| 2 | 13 |
| 3 | 50 |
| 4 | 50 |
| 5 | 50 |
| 6 | 50 |
| 7 | 50 |
| 8 | 50 |
| 9 | 50 |
| 10 | 50 |
| 11 | 50 |
| 12 | 50 |
| 13 | 50 |
| 14 | 50 |
| 15 | 50 |
| 16 | 50 |
| 17 | 50 |
| 18 | 50 |
Training Hyperparameters
- batch_size: (512, 512)
- num_epochs: (20, 20)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 40
- body_learning_rate: (2e-05, 2e-05)
- head_learning_rate: 2e-05
- loss: CosineSimilarityLoss
- distance_metric: cosine_distance
- margin: 0.25
- end_to_end: False
- use_amp: False
- warmup_proportion: 0.1
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: False
Training Results
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0070 | 1 | 0.4968 | - |
| 0.3497 | 50 | 0.3841 | - |
| 0.6993 | 100 | 0.1946 | - |
| 1.0490 | 150 | 0.1001 | - |
| 1.3986 | 200 | 0.0434 | - |
| 1.7483 | 250 | 0.0383 | - |
| 2.0979 | 300 | 0.0221 | - |
| 2.4476 | 350 | 0.0183 | - |
| 2.7972 | 400 | 0.0279 | - |
| 3.1469 | 450 | 0.0213 | - |
| 3.4965 | 500 | 0.0159 | - |
| 3.8462 | 550 | 0.0169 | - |
| 4.1958 | 600 | 0.012 | - |
| 4.5455 | 650 | 0.0093 | - |
| 4.8951 | 700 | 0.004 | - |
| 5.2448 | 750 | 0.001 | - |
| 5.5944 | 800 | 0.0061 | - |
| 5.9441 | 850 | 0.0061 | - |
| 6.2937 | 900 | 0.0014 | - |
| 6.6434 | 950 | 0.0005 | - |
| 6.9930 | 1000 | 0.0003 | - |
| 7.3427 | 1050 | 0.0002 | - |
| 7.6923 | 1100 | 0.0002 | - |
| 8.0420 | 1150 | 0.0002 | - |
| 8.3916 | 1200 | 0.0002 | - |
| 8.7413 | 1250 | 0.0002 | - |
| 9.0909 | 1300 | 0.0001 | - |
| 9.4406 | 1350 | 0.0002 | - |
| 9.7902 | 1400 | 0.0001 | - |
| 10.1399 | 1450 | 0.0001 | - |
| 10.4895 | 1500 | 0.0001 | - |
| 10.8392 | 1550 | 0.0001 | - |
| 11.1888 | 1600 | 0.0001 | - |
| 11.5385 | 1650 | 0.0001 | - |
| 11.8881 | 1700 | 0.0001 | - |
| 12.2378 | 1750 | 0.0001 | - |
| 12.5874 | 1800 | 0.0001 | - |
| 12.9371 | 1850 | 0.0001 | - |
| 13.2867 | 1900 | 0.0001 | - |
| 13.6364 | 1950 | 0.0001 | - |
| 13.9860 | 2000 | 0.0001 | - |
| 14.3357 | 2050 | 0.0001 | - |
| 14.6853 | 2100 | 0.0001 | - |
| 15.0350 | 2150 | 0.0001 | - |
| 15.3846 | 2200 | 0.0001 | - |
| 15.7343 | 2250 | 0.0001 | - |
| 16.0839 | 2300 | 0.0001 | - |
| 16.4336 | 2350 | 0.0001 | - |
| 16.7832 | 2400 | 0.0001 | - |
| 17.1329 | 2450 | 0.0001 | - |
| 17.4825 | 2500 | 0.0001 | - |
| 17.8322 | 2550 | 0.0001 | - |
| 18.1818 | 2600 | 0.0001 | - |
| 18.5315 | 2650 | 0.0 | - |
| 18.8811 | 2700 | 0.0001 | - |
| 19.2308 | 2750 | 0.0001 | - |
| 19.5804 | 2800 | 0.0001 | - |
| 19.9301 | 2850 | 0.0001 | - |
Framework Versions
- Python: 3.10.12
- SetFit: 1.1.0.dev0
- Sentence Transformers: 3.1.1
- Transformers: 4.46.1
- PyTorch: 2.4.0+cu121
- Datasets: 2.20.0
- Tokenizers: 0.20.0
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}
}