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 |
---|---|
1.0 |
|
16.0 |
|
12.0 |
|
8.0 |
|
9.0 |
|
3.0 |
|
5.0 |
|
14.0 |
|
4.0 |
|
13.0 |
|
10.0 |
|
15.0 |
|
0.0 |
|
6.0 |
|
11.0 |
|
2.0 |
|
7.0 |
|
Evaluation
Metrics
Label | Metric |
---|---|
all | 0.7886 |
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_fd6")
# Run inference
preds = model("한끼곤약젤리 버라이어티팩 150ml x 30개입 지유인터내셔널")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 3 | 10.0988 | 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 | 23 |
8.0 | 50 |
9.0 | 50 |
10.0 | 50 |
11.0 | 50 |
12.0 | 27 |
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 |
---|---|---|---|
0.008 | 1 | 0.4244 | - |
0.4 | 50 | 0.357 | - |
0.8 | 100 | 0.201 | - |
1.2 | 150 | 0.1331 | - |
1.6 | 200 | 0.0757 | - |
2.0 | 250 | 0.0294 | - |
2.4 | 300 | 0.0338 | - |
2.8 | 350 | 0.0214 | - |
3.2 | 400 | 0.0108 | - |
3.6 | 450 | 0.0059 | - |
4.0 | 500 | 0.0046 | - |
4.4 | 550 | 0.0065 | - |
4.8 | 600 | 0.0023 | - |
5.2 | 650 | 0.0004 | - |
5.6 | 700 | 0.0002 | - |
6.0 | 750 | 0.0022 | - |
6.4 | 800 | 0.0021 | - |
6.8 | 850 | 0.0022 | - |
7.2 | 900 | 0.0021 | - |
7.6 | 950 | 0.004 | - |
8.0 | 1000 | 0.0002 | - |
8.4 | 1050 | 0.0003 | - |
8.8 | 1100 | 0.0002 | - |
9.2 | 1150 | 0.0013 | - |
9.6 | 1200 | 0.003 | - |
10.0 | 1250 | 0.0015 | - |
10.4 | 1300 | 0.0002 | - |
10.8 | 1350 | 0.0001 | - |
11.2 | 1400 | 0.0001 | - |
11.6 | 1450 | 0.0001 | - |
12.0 | 1500 | 0.0001 | - |
12.4 | 1550 | 0.0001 | - |
12.8 | 1600 | 0.0001 | - |
13.2 | 1650 | 0.0001 | - |
13.6 | 1700 | 0.0001 | - |
14.0 | 1750 | 0.0001 | - |
14.4 | 1800 | 0.0001 | - |
14.8 | 1850 | 0.0001 | - |
15.2 | 1900 | 0.0001 | - |
15.6 | 1950 | 0.0001 | - |
16.0 | 2000 | 0.0001 | - |
16.4 | 2050 | 0.0001 | - |
16.8 | 2100 | 0.0001 | - |
17.2 | 2150 | 0.0001 | - |
17.6 | 2200 | 0.0001 | - |
18.0 | 2250 | 0.0001 | - |
18.4 | 2300 | 0.0001 | - |
18.8 | 2350 | 0.0001 | - |
19.2 | 2400 | 0.0001 | - |
19.6 | 2450 | 0.0001 | - |
20.0 | 2500 | 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}
}
- Downloads last month
- 539
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.