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: 12 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 |
|
0.0 |
|
2.0 |
|
9.0 |
|
10.0 |
|
11.0 |
|
8.0 |
|
7.0 |
|
4.0 |
|
6.0 |
|
5.0 |
|
3.0 |
|
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_bc9")
# Run inference
preds = model("중탕기 젖병 국통 뷔페 휴대용 멜팅기 데우기 2칸 출산/육아 > 수유용품 > 보틀워머")
Training Details
Training Set Metrics
Training set | Min | Median | Max |
---|---|---|---|
Word count | 7 | 14.4119 | 29 |
Label | Training Sample Count |
---|---|
0.0 | 70 |
1.0 | 70 |
2.0 | 70 |
3.0 | 70 |
4.0 | 70 |
5.0 | 70 |
6.0 | 70 |
7.0 | 70 |
8.0 | 70 |
9.0 | 70 |
10.0 | 70 |
11.0 | 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 |
---|---|---|---|
0.0061 | 1 | 0.4988 | - |
0.3030 | 50 | 0.4987 | - |
0.6061 | 100 | 0.4398 | - |
0.9091 | 150 | 0.1411 | - |
1.2121 | 200 | 0.0221 | - |
1.5152 | 250 | 0.0149 | - |
1.8182 | 300 | 0.0147 | - |
2.1212 | 350 | 0.008 | - |
2.4242 | 400 | 0.0071 | - |
2.7273 | 450 | 0.0069 | - |
3.0303 | 500 | 0.0003 | - |
3.3333 | 550 | 0.0 | - |
3.6364 | 600 | 0.0 | - |
3.9394 | 650 | 0.0 | - |
4.2424 | 700 | 0.0 | - |
4.5455 | 750 | 0.0 | - |
4.8485 | 800 | 0.0 | - |
5.1515 | 850 | 0.0 | - |
5.4545 | 900 | 0.0 | - |
5.7576 | 950 | 0.0 | - |
6.0606 | 1000 | 0.0 | - |
6.3636 | 1050 | 0.0 | - |
6.6667 | 1100 | 0.0 | - |
6.9697 | 1150 | 0.0 | - |
7.2727 | 1200 | 0.0 | - |
7.5758 | 1250 | 0.0 | - |
7.8788 | 1300 | 0.0 | - |
8.1818 | 1350 | 0.0 | - |
8.4848 | 1400 | 0.0 | - |
8.7879 | 1450 | 0.0 | - |
9.0909 | 1500 | 0.0 | - |
9.3939 | 1550 | 0.0 | - |
9.6970 | 1600 | 0.0 | - |
10.0 | 1650 | 0.0 | - |
10.3030 | 1700 | 0.0 | - |
10.6061 | 1750 | 0.0 | - |
10.9091 | 1800 | 0.0 | - |
11.2121 | 1850 | 0.0 | - |
11.5152 | 1900 | 0.0 | - |
11.8182 | 1950 | 0.0001 | - |
12.1212 | 2000 | 0.0 | - |
12.4242 | 2050 | 0.0 | - |
12.7273 | 2100 | 0.0 | - |
13.0303 | 2150 | 0.0 | - |
13.3333 | 2200 | 0.0 | - |
13.6364 | 2250 | 0.0 | - |
13.9394 | 2300 | 0.0 | - |
14.2424 | 2350 | 0.0 | - |
14.5455 | 2400 | 0.0 | - |
14.8485 | 2450 | 0.0 | - |
15.1515 | 2500 | 0.0 | - |
15.4545 | 2550 | 0.0 | - |
15.7576 | 2600 | 0.0 | - |
16.0606 | 2650 | 0.0 | - |
16.3636 | 2700 | 0.0 | - |
16.6667 | 2750 | 0.0001 | - |
16.9697 | 2800 | 0.0 | - |
17.2727 | 2850 | 0.0 | - |
17.5758 | 2900 | 0.0 | - |
17.8788 | 2950 | 0.0 | - |
18.1818 | 3000 | 0.0 | - |
18.4848 | 3050 | 0.0 | - |
18.7879 | 3100 | 0.0 | - |
19.0909 | 3150 | 0.0 | - |
19.3939 | 3200 | 0.0 | - |
19.6970 | 3250 | 0.0 | - |
20.0 | 3300 | 0.0 | - |
20.3030 | 3350 | 0.0 | - |
20.6061 | 3400 | 0.0 | - |
20.9091 | 3450 | 0.0 | - |
21.2121 | 3500 | 0.0 | - |
21.5152 | 3550 | 0.0 | - |
21.8182 | 3600 | 0.0 | - |
22.1212 | 3650 | 0.0 | - |
22.4242 | 3700 | 0.0 | - |
22.7273 | 3750 | 0.0 | - |
23.0303 | 3800 | 0.0 | - |
23.3333 | 3850 | 0.0 | - |
23.6364 | 3900 | 0.0 | - |
23.9394 | 3950 | 0.0 | - |
24.2424 | 4000 | 0.0 | - |
24.5455 | 4050 | 0.0 | - |
24.8485 | 4100 | 0.0 | - |
25.1515 | 4150 | 0.0 | - |
25.4545 | 4200 | 0.0 | - |
25.7576 | 4250 | 0.0 | - |
26.0606 | 4300 | 0.0 | - |
26.3636 | 4350 | 0.0 | - |
26.6667 | 4400 | 0.0 | - |
26.9697 | 4450 | 0.0 | - |
27.2727 | 4500 | 0.0 | - |
27.5758 | 4550 | 0.0 | - |
27.8788 | 4600 | 0.0 | - |
28.1818 | 4650 | 0.0 | - |
28.4848 | 4700 | 0.0 | - |
28.7879 | 4750 | 0.0 | - |
29.0909 | 4800 | 0.0 | - |
29.3939 | 4850 | 0.0 | - |
29.6970 | 4900 | 0.0 | - |
30.0 | 4950 | 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}
}
- Downloads last month
- 190
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.