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: 한끼스토리 딸기드레싱 500g 10개 한울마켓
- text: 맷돌표 뉴슈가 60g/ 20개 (주)디엔제이
- text: 하회마을 쌈장 14kg 업소용 대용량 물레푸드
- text: 화가장가평발효과학 국산콩청국장 120g16팩 화가장 주식회사
- text: 춘장(삼화 300g) 4개 식자재 업소용 대용량 더착한컴퍼니
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: 0.8727670433831571
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: 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 |
---|---|
8.0 |
|
0.0 |
|
3.0 |
|
4.0 |
|
1.0 |
|
6.0 |
|
5.0 |
|
7.0 |
|
2.0 |
|
Evaluation
Metrics
Label | Metric |
---|---|
all | 0.8728 |
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_fd15")
# Run inference
preds = model("맷돌표 뉴슈가 60g/ 20개 (주)디엔제이")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 3 | 9.8578 | 26 |
Label | Training Sample Count |
---|---|
0.0 | 50 |
1.0 | 50 |
2.0 | 50 |
3.0 | 50 |
4.0 | 50 |
5.0 | 22 |
6.0 | 50 |
7.0 | 50 |
8.0 | 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 |
---|---|---|---|
0.0152 | 1 | 0.3728 | - |
0.7576 | 50 | 0.2769 | - |
1.5152 | 100 | 0.1245 | - |
2.2727 | 150 | 0.0532 | - |
3.0303 | 200 | 0.0532 | - |
3.7879 | 250 | 0.0385 | - |
4.5455 | 300 | 0.0052 | - |
5.3030 | 350 | 0.0025 | - |
6.0606 | 400 | 0.0004 | - |
6.8182 | 450 | 0.0004 | - |
7.5758 | 500 | 0.0005 | - |
8.3333 | 550 | 0.0007 | - |
9.0909 | 600 | 0.0002 | - |
9.8485 | 650 | 0.0002 | - |
10.6061 | 700 | 0.0001 | - |
11.3636 | 750 | 0.0001 | - |
12.1212 | 800 | 0.0001 | - |
12.8788 | 850 | 0.0001 | - |
13.6364 | 900 | 0.0001 | - |
14.3939 | 950 | 0.0001 | - |
15.1515 | 1000 | 0.0001 | - |
15.9091 | 1050 | 0.0001 | - |
16.6667 | 1100 | 0.0001 | - |
17.4242 | 1150 | 0.0001 | - |
18.1818 | 1200 | 0.0001 | - |
18.9394 | 1250 | 0.0 | - |
19.6970 | 1300 | 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}
}