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: '[제너럴아이디어 WOMAN] 하찌 볼레로 니트 세트 [3COL] / WBC3L05518SET BLUE_FREE 지아이홀딩스'
- text: 핫슈트 다이어트 여자 땀복 헬스복 트레이닝 운동복 지투 라운드 세트 HS6004 S_S 주식회사 사람사랑
- text: '[해외정품] 바버 데브론 퀼팅자켓LQU1012BK91 Lt Trench_UK10 위너12'
- text: '[갤러리아] [여]NEW 포플린 셔츠(05343901)(343901)(한화갤러리아㈜ 센터시티) 01 다크그린_M 한화갤러리아(주)'
- text: (SOUP)(신세계마산점)숲 라이더형 무스탕 (SZBMU90) 블랙_66 신세계백화점
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: 0.7890421327054075
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: 21 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 |
|---|---|
| 15.0 |
|
| 5.0 |
|
| 7.0 |
|
| 10.0 |
|
| 3.0 |
|
| 0.0 |
|
| 16.0 |
|
| 4.0 |
|
| 20.0 |
|
| 11.0 |
|
| 17.0 |
|
| 18.0 |
|
| 2.0 |
|
| 19.0 |
|
| 14.0 |
|
| 12.0 |
|
| 13.0 |
|
| 6.0 |
|
| 9.0 |
|
| 1.0 |
|
| 8.0 |
|
Evaluation
Metrics
| Label | Metric |
|---|---|
| all | 0.7890 |
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_ap3")
# Run inference
preds = model("(SOUP)(신세계마산점)숲 라이더형 무스탕 (SZBMU90) 블랙_66 신세계백화점")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 3 | 9.6448 | 23 |
| Label | Training Sample Count |
|---|---|
| 0.0 | 50 |
| 1.0 | 50 |
| 2.0 | 50 |
| 3.0 | 50 |
| 4.0 | 50 |
| 5.0 | 50 |
| 6.0 | 50 |
| 7.0 | 50 |
| 8.0 | 50 |
| 9.0 | 50 |
| 10.0 | 50 |
| 11.0 | 50 |
| 12.0 | 50 |
| 13.0 | 50 |
| 14.0 | 50 |
| 15.0 | 50 |
| 16.0 | 50 |
| 17.0 | 50 |
| 18.0 | 50 |
| 19.0 | 50 |
| 20.0 | 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 |
|---|---|---|---|
| 0.0061 | 1 | 0.3795 | - |
| 0.3030 | 50 | 0.296 | - |
| 0.6061 | 100 | 0.2248 | - |
| 0.9091 | 150 | 0.1494 | - |
| 1.2121 | 200 | 0.0913 | - |
| 1.5152 | 250 | 0.061 | - |
| 1.8182 | 300 | 0.0322 | - |
| 2.1212 | 350 | 0.0243 | - |
| 2.4242 | 400 | 0.0152 | - |
| 2.7273 | 450 | 0.0134 | - |
| 3.0303 | 500 | 0.0056 | - |
| 3.3333 | 550 | 0.0026 | - |
| 3.6364 | 600 | 0.0016 | - |
| 3.9394 | 650 | 0.0066 | - |
| 4.2424 | 700 | 0.0044 | - |
| 4.5455 | 750 | 0.0025 | - |
| 4.8485 | 800 | 0.0023 | - |
| 5.1515 | 850 | 0.0023 | - |
| 5.4545 | 900 | 0.0008 | - |
| 5.7576 | 950 | 0.0023 | - |
| 6.0606 | 1000 | 0.0005 | - |
| 6.3636 | 1050 | 0.0015 | - |
| 6.6667 | 1100 | 0.0006 | - |
| 6.9697 | 1150 | 0.0003 | - |
| 7.2727 | 1200 | 0.0003 | - |
| 7.5758 | 1250 | 0.0003 | - |
| 7.8788 | 1300 | 0.0002 | - |
| 8.1818 | 1350 | 0.0004 | - |
| 8.4848 | 1400 | 0.0002 | - |
| 8.7879 | 1450 | 0.0002 | - |
| 9.0909 | 1500 | 0.0002 | - |
| 9.3939 | 1550 | 0.0002 | - |
| 9.6970 | 1600 | 0.0001 | - |
| 10.0 | 1650 | 0.0001 | - |
| 10.3030 | 1700 | 0.0002 | - |
| 10.6061 | 1750 | 0.0001 | - |
| 10.9091 | 1800 | 0.0001 | - |
| 11.2121 | 1850 | 0.0002 | - |
| 11.5152 | 1900 | 0.0002 | - |
| 11.8182 | 1950 | 0.0002 | - |
| 12.1212 | 2000 | 0.0001 | - |
| 12.4242 | 2050 | 0.0001 | - |
| 12.7273 | 2100 | 0.0001 | - |
| 13.0303 | 2150 | 0.0001 | - |
| 13.3333 | 2200 | 0.0001 | - |
| 13.6364 | 2250 | 0.0001 | - |
| 13.9394 | 2300 | 0.0001 | - |
| 14.2424 | 2350 | 0.0001 | - |
| 14.5455 | 2400 | 0.0001 | - |
| 14.8485 | 2450 | 0.0001 | - |
| 15.1515 | 2500 | 0.0001 | - |
| 15.4545 | 2550 | 0.0001 | - |
| 15.7576 | 2600 | 0.0001 | - |
| 16.0606 | 2650 | 0.0001 | - |
| 16.3636 | 2700 | 0.0001 | - |
| 16.6667 | 2750 | 0.0001 | - |
| 16.9697 | 2800 | 0.0001 | - |
| 17.2727 | 2850 | 0.0001 | - |
| 17.5758 | 2900 | 0.0001 | - |
| 17.8788 | 2950 | 0.0001 | - |
| 18.1818 | 3000 | 0.0001 | - |
| 18.4848 | 3050 | 0.0001 | - |
| 18.7879 | 3100 | 0.0001 | - |
| 19.0909 | 3150 | 0.0001 | - |
| 19.3939 | 3200 | 0.0001 | - |
| 19.6970 | 3250 | 0.0001 | - |
| 20.0 | 3300 | 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}
}