metadata
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
widget:
- text: 화장대의자 1인 스툴 모던 심플 인테리어 체어 스툴 간이 의자 가구/인테리어>침실가구>화장대>화장대의자
- text: 가벼운 럭셔리 슬레이트 식탁 소형 거실 식탁 직사각형 커피 테이블 모던 심플 홈 가구 가구/인테리어>침실가구>침실세트
- text: 대나무 플립 신발 캐비닛 절약 숨겨진 신발거치대 장식 입구 홀 가구 가구/인테리어>침실가구>침실세트
- text: 동서가구 히루 LPM 편백 800 수납선반옷장 드레스룸 D1021 가구/인테리어>침실가구>장롱/붙박이장>드레스룸
- text: 시몬스 뷰티레스트 허브 매트리스 Q 가구/인테리어>침실가구>매트리스>퀸매트리스
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: 9 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 |
|
| 8.0 |
|
| 6.0 |
|
| 7.0 |
|
| 3.0 |
|
| 4.0 |
|
| 0.0 |
|
| 5.0 |
|
| 2.0 |
|
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_fi13")
# Run inference
preds = model("시몬스 뷰티레스트 허브 매트리스 Q 가구/인테리어>침실가구>매트리스>퀸매트리스")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 3 | 8.2846 | 19 |
| Label | Training Sample Count |
|---|---|
| 0.0 | 70 |
| 1.0 | 70 |
| 2.0 | 69 |
| 3.0 | 70 |
| 4.0 | 70 |
| 5.0 | 70 |
| 6.0 | 70 |
| 7.0 | 70 |
| 8.0 | 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 |
|---|---|---|---|
| 0.0081 | 1 | 0.4686 | - |
| 0.4065 | 50 | 0.4974 | - |
| 0.8130 | 100 | 0.5009 | - |
| 1.2195 | 150 | 0.4141 | - |
| 1.6260 | 200 | 0.1421 | - |
| 2.0325 | 250 | 0.0417 | - |
| 2.4390 | 300 | 0.0104 | - |
| 2.8455 | 350 | 0.0007 | - |
| 3.2520 | 400 | 0.0004 | - |
| 3.6585 | 450 | 0.0002 | - |
| 4.0650 | 500 | 0.0002 | - |
| 4.4715 | 550 | 0.0002 | - |
| 4.8780 | 600 | 0.0001 | - |
| 5.2846 | 650 | 0.0002 | - |
| 5.6911 | 700 | 0.0001 | - |
| 6.0976 | 750 | 0.0001 | - |
| 6.5041 | 800 | 0.0001 | - |
| 6.9106 | 850 | 0.0001 | - |
| 7.3171 | 900 | 0.0001 | - |
| 7.7236 | 950 | 0.0001 | - |
| 8.1301 | 1000 | 0.0001 | - |
| 8.5366 | 1050 | 0.0001 | - |
| 8.9431 | 1100 | 0.0 | - |
| 9.3496 | 1150 | 0.0 | - |
| 9.7561 | 1200 | 0.0 | - |
| 10.1626 | 1250 | 0.0 | - |
| 10.5691 | 1300 | 0.0 | - |
| 10.9756 | 1350 | 0.0 | - |
| 11.3821 | 1400 | 0.0 | - |
| 11.7886 | 1450 | 0.0 | - |
| 12.1951 | 1500 | 0.0 | - |
| 12.6016 | 1550 | 0.0 | - |
| 13.0081 | 1600 | 0.0 | - |
| 13.4146 | 1650 | 0.0 | - |
| 13.8211 | 1700 | 0.0 | - |
| 14.2276 | 1750 | 0.0 | - |
| 14.6341 | 1800 | 0.0 | - |
| 15.0407 | 1850 | 0.0 | - |
| 15.4472 | 1900 | 0.0 | - |
| 15.8537 | 1950 | 0.0 | - |
| 16.2602 | 2000 | 0.0 | - |
| 16.6667 | 2050 | 0.0 | - |
| 17.0732 | 2100 | 0.0 | - |
| 17.4797 | 2150 | 0.0 | - |
| 17.8862 | 2200 | 0.0 | - |
| 18.2927 | 2250 | 0.0 | - |
| 18.6992 | 2300 | 0.0 | - |
| 19.1057 | 2350 | 0.0 | - |
| 19.5122 | 2400 | 0.0 | - |
| 19.9187 | 2450 | 0.0 | - |
| 20.3252 | 2500 | 0.0 | - |
| 20.7317 | 2550 | 0.0 | - |
| 21.1382 | 2600 | 0.0 | - |
| 21.5447 | 2650 | 0.0 | - |
| 21.9512 | 2700 | 0.0 | - |
| 22.3577 | 2750 | 0.0 | - |
| 22.7642 | 2800 | 0.0 | - |
| 23.1707 | 2850 | 0.0 | - |
| 23.5772 | 2900 | 0.0 | - |
| 23.9837 | 2950 | 0.0 | - |
| 24.3902 | 3000 | 0.0 | - |
| 24.7967 | 3050 | 0.0 | - |
| 25.2033 | 3100 | 0.0 | - |
| 25.6098 | 3150 | 0.0 | - |
| 26.0163 | 3200 | 0.0 | - |
| 26.4228 | 3250 | 0.0 | - |
| 26.8293 | 3300 | 0.0 | - |
| 27.2358 | 3350 | 0.0 | - |
| 27.6423 | 3400 | 0.0 | - |
| 28.0488 | 3450 | 0.0 | - |
| 28.4553 | 3500 | 0.0 | - |
| 28.8618 | 3550 | 0.0 | - |
| 29.2683 | 3600 | 0.0 | - |
| 29.6748 | 3650 | 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}
}