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: 강아지하네스 원피스 꽃무늬 애견가슴줄 애견 공주옷 옷 고양이 그린 연청색_L 고고마트
- text: 옷 강아지코스튬 강아지 의상 고양이 파티 처키 코스프레 교통경찰 변장_M- 약 2.5-5kg 내 핑크웨일
- text: 찍지마라 강아지옷 강아지 코스튬 해적+더드컨트리 스티커_L(68-88CM)16~25KG 더드컨트리
- text: 강아지패딩 퍼피엔젤 초경량 AIR2 올인원 방수 패딩 남여공용 s 1. AIR2 남여공용_#808 GREEN_S 스탠바이펫
- text: >-
강아지옷 고양이 봄 여름 가을 원피스 티셔츠 실내복 애견 애완견 반려견 의류 비숑 토이 푸들 말티즈 XS 옵션17. Happy
Summer 자수 나시_옐로우_S DOGNY
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: 0.7383331748863375
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: 24 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 |
|
| 21.0 |
|
| 14.0 |
|
| 12.0 |
|
| 13.0 |
|
| 3.0 |
|
| 10.0 |
|
| 0.0 |
|
| 2.0 |
|
| 6.0 |
|
| 25.0 |
|
| 16.0 |
|
| 15.0 |
|
| 22.0 |
|
| 11.0 |
|
| 18.0 |
|
| 17.0 |
|
| 23.0 |
|
| 24.0 |
|
| 9.0 |
|
| 7.0 |
|
| 5.0 |
|
| 4.0 |
|
| 8.0 |
|
Evaluation
Metrics
| Label | Metric |
|---|---|
| all | 0.7383 |
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_lh10")
# Run inference
preds = model("강아지하네스 원피스 꽃무늬 애견가슴줄 애견 공주옷 옷 고양이 그린 연청색_L 고고마트")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 3 | 10.0792 | 28 |
| 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 |
| 21.0 | 50 |
| 22.0 | 50 |
| 23.0 | 50 |
| 24.0 | 50 |
| 25.0 | 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 |
|---|---|---|---|
| 0.0053 | 1 | 0.4146 | - |
| 0.2660 | 50 | 0.3778 | - |
| 0.5319 | 100 | 0.315 | - |
| 0.7979 | 150 | 0.2096 | - |
| 1.0638 | 200 | 0.146 | - |
| 1.3298 | 250 | 0.0963 | - |
| 1.5957 | 300 | 0.0549 | - |
| 1.8617 | 350 | 0.049 | - |
| 2.1277 | 400 | 0.0339 | - |
| 2.3936 | 450 | 0.0339 | - |
| 2.6596 | 500 | 0.0322 | - |
| 2.9255 | 550 | 0.0263 | - |
| 3.1915 | 600 | 0.0179 | - |
| 3.4574 | 650 | 0.0202 | - |
| 3.7234 | 700 | 0.0127 | - |
| 3.9894 | 750 | 0.0293 | - |
| 4.2553 | 800 | 0.0116 | - |
| 4.5213 | 850 | 0.0264 | - |
| 4.7872 | 900 | 0.012 | - |
| 5.0532 | 950 | 0.009 | - |
| 5.3191 | 1000 | 0.0139 | - |
| 5.5851 | 1050 | 0.0116 | - |
| 5.8511 | 1100 | 0.024 | - |
| 6.1170 | 1150 | 0.0046 | - |
| 6.3830 | 1200 | 0.0046 | - |
| 6.6489 | 1250 | 0.0081 | - |
| 6.9149 | 1300 | 0.0099 | - |
| 7.1809 | 1350 | 0.0108 | - |
| 7.4468 | 1400 | 0.0006 | - |
| 7.7128 | 1450 | 0.01 | - |
| 7.9787 | 1500 | 0.0098 | - |
| 8.2447 | 1550 | 0.0099 | - |
| 8.5106 | 1600 | 0.0063 | - |
| 8.7766 | 1650 | 0.006 | - |
| 9.0426 | 1700 | 0.0016 | - |
| 9.3085 | 1750 | 0.0054 | - |
| 9.5745 | 1800 | 0.0011 | - |
| 9.8404 | 1850 | 0.0056 | - |
| 10.1064 | 1900 | 0.0095 | - |
| 10.3723 | 1950 | 0.0006 | - |
| 10.6383 | 2000 | 0.0081 | - |
| 10.9043 | 2050 | 0.0002 | - |
| 11.1702 | 2100 | 0.0002 | - |
| 11.4362 | 2150 | 0.0041 | - |
| 11.7021 | 2200 | 0.0021 | - |
| 11.9681 | 2250 | 0.0002 | - |
| 12.2340 | 2300 | 0.0021 | - |
| 12.5 | 2350 | 0.004 | - |
| 12.7660 | 2400 | 0.0002 | - |
| 13.0319 | 2450 | 0.0002 | - |
| 13.2979 | 2500 | 0.0021 | - |
| 13.5638 | 2550 | 0.0012 | - |
| 13.8298 | 2600 | 0.0038 | - |
| 14.0957 | 2650 | 0.0072 | - |
| 14.3617 | 2700 | 0.002 | - |
| 14.6277 | 2750 | 0.0018 | - |
| 14.8936 | 2800 | 0.0018 | - |
| 15.1596 | 2850 | 0.0002 | - |
| 15.4255 | 2900 | 0.0007 | - |
| 15.6915 | 2950 | 0.0003 | - |
| 15.9574 | 3000 | 0.0002 | - |
| 16.2234 | 3050 | 0.0001 | - |
| 16.4894 | 3100 | 0.0001 | - |
| 16.7553 | 3150 | 0.0001 | - |
| 17.0213 | 3200 | 0.0001 | - |
| 17.2872 | 3250 | 0.0001 | - |
| 17.5532 | 3300 | 0.0001 | - |
| 17.8191 | 3350 | 0.0001 | - |
| 18.0851 | 3400 | 0.0001 | - |
| 18.3511 | 3450 | 0.0001 | - |
| 18.6170 | 3500 | 0.0001 | - |
| 18.8830 | 3550 | 0.0001 | - |
| 19.1489 | 3600 | 0.0001 | - |
| 19.4149 | 3650 | 0.0001 | - |
| 19.6809 | 3700 | 0.0001 | - |
| 19.9468 | 3750 | 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}
}