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: 참존 톤업핏 블랙라벨 라이트 KF94 새부리형 마스크 20매 바닐라 베이지(10매/중형)_오픈 화이트(10매/대형) 주식회사 참존
- text: >-
털보네액상공장 전자담배액상 사이트 전담액상 입호흡 폐호흡 재료 무니코틴 피나콜라다 100ml 입호흡_베이스( 무니코틴 )_1.
피나콜라다 (주)커넥티드코리아
- text: voopoo 부푸 브이메이트 민트블루 견고한 내구성 전자담배 판매 TOP1 입호흡 1. 부푸 브이메이트 E (New 핑크마블) 마윈존
- text: >-
세운 석션카테타 (Suction Catheter) - LATEX #5 10FR (Sterile, no valve, 1hole)
단위:1개 (주)엠디오씨
- text: 붐바 일회용 전자담배 편의점 전담 4ML 애플아이스 애플아이스 원더베이프(서초)
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: 0.9428033187702914
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: 17 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 |
|---|---|
| 4.0 |
|
| 9.0 |
|
| 14.0 |
|
| 12.0 |
|
| 5.0 |
|
| 8.0 |
|
| 16.0 |
|
| 6.0 |
|
| 13.0 |
|
| 3.0 |
|
| 1.0 |
|
| 10.0 |
|
| 2.0 |
|
| 0.0 |
|
| 15.0 |
|
| 11.0 |
|
| 7.0 |
|
Evaluation
Metrics
| Label | Metric |
|---|---|
| all | 0.9428 |
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_lh0")
# Run inference
preds = model("붐바 일회용 전자담배 편의점 전담 4ML 애플아이스 애플아이스 원더베이프(서초)")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 3 | 10.5920 | 31 |
| Label | Training Sample Count |
|---|---|
| 0.0 | 50 |
| 1.0 | 50 |
| 2.0 | 25 |
| 3.0 | 50 |
| 4.0 | 50 |
| 5.0 | 50 |
| 6.0 | 50 |
| 7.0 | 50 |
| 8.0 | 50 |
| 9.0 | 50 |
| 10.0 | 28 |
| 11.0 | 50 |
| 12.0 | 24 |
| 13.0 | 50 |
| 14.0 | 50 |
| 15.0 | 50 |
| 16.0 | 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 |
|---|---|---|---|
| 0.0082 | 1 | 0.4317 | - |
| 0.4098 | 50 | 0.3501 | - |
| 0.8197 | 100 | 0.207 | - |
| 1.2295 | 150 | 0.1065 | - |
| 1.6393 | 200 | 0.0426 | - |
| 2.0492 | 250 | 0.0299 | - |
| 2.4590 | 300 | 0.0323 | - |
| 2.8689 | 350 | 0.033 | - |
| 3.2787 | 400 | 0.0211 | - |
| 3.6885 | 450 | 0.0383 | - |
| 4.0984 | 500 | 0.0239 | - |
| 4.5082 | 550 | 0.0137 | - |
| 4.9180 | 600 | 0.0099 | - |
| 5.3279 | 650 | 0.0057 | - |
| 5.7377 | 700 | 0.0041 | - |
| 6.1475 | 750 | 0.0045 | - |
| 6.5574 | 800 | 0.0002 | - |
| 6.9672 | 850 | 0.0059 | - |
| 7.3770 | 900 | 0.0059 | - |
| 7.7869 | 950 | 0.0001 | - |
| 8.1967 | 1000 | 0.004 | - |
| 8.6066 | 1050 | 0.0039 | - |
| 9.0164 | 1100 | 0.0003 | - |
| 9.4262 | 1150 | 0.0002 | - |
| 9.8361 | 1200 | 0.0001 | - |
| 10.2459 | 1250 | 0.0001 | - |
| 10.6557 | 1300 | 0.0001 | - |
| 11.0656 | 1350 | 0.0001 | - |
| 11.4754 | 1400 | 0.0001 | - |
| 11.8852 | 1450 | 0.0001 | - |
| 12.2951 | 1500 | 0.0001 | - |
| 12.7049 | 1550 | 0.0001 | - |
| 13.1148 | 1600 | 0.0001 | - |
| 13.5246 | 1650 | 0.0001 | - |
| 13.9344 | 1700 | 0.0001 | - |
| 14.3443 | 1750 | 0.0001 | - |
| 14.7541 | 1800 | 0.0 | - |
| 15.1639 | 1850 | 0.0001 | - |
| 15.5738 | 1900 | 0.0001 | - |
| 15.9836 | 1950 | 0.0001 | - |
| 16.3934 | 2000 | 0.0 | - |
| 16.8033 | 2050 | 0.0001 | - |
| 17.2131 | 2100 | 0.0 | - |
| 17.6230 | 2150 | 0.0001 | - |
| 18.0328 | 2200 | 0.0 | - |
| 18.4426 | 2250 | 0.0 | - |
| 18.8525 | 2300 | 0.0 | - |
| 19.2623 | 2350 | 0.0001 | - |
| 19.6721 | 2400 | 0.0 | - |
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}
}