SetFit with m3hrdadfi/albert-zwnj-wnli-mean-tokens
This is a SetFit model that can be used for Text Classification. This SetFit model uses m3hrdadfi/albert-zwnj-wnli-mean-tokens 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: m3hrdadfi/albert-zwnj-wnli-mean-tokens
- Classification head: a LogisticRegression instance
- Maximum Sequence Length: 128 tokens
- Number of Classes: 11 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 |
|---|---|
| 7 |
|
| 4 |
|
| 3 |
|
| 5 |
|
| 0 |
|
| 8 |
|
| 6 |
|
| 2 |
|
| 9 |
|
| 1 |
|
| 10 |
|
Evaluation
Metrics
| Label | Accuracy |
|---|---|
| all | 0.0455 |
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("keivan/albert-zwnj-wnli-mean-tokens")
# Run inference
preds = model("خوبه ولی کیفیت ظروف مناسب نیست")
Training Details
Training Set Metrics
| Training set | Min | Median | Max |
|---|---|---|---|
| Word count | 3 | 21.3377 | 72 |
| Label | Training Sample Count |
|---|---|
| 0 | 7 |
| 1 | 7 |
| 2 | 7 |
| 3 | 7 |
| 4 | 7 |
| 5 | 7 |
| 6 | 7 |
| 7 | 7 |
| 8 | 7 |
| 9 | 7 |
| 10 | 7 |
Training Hyperparameters
- batch_size: (8, 8)
- num_epochs: (2, 2)
- max_steps: -1
- sampling_strategy: oversampling
- 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
- seed: 42
- eval_max_steps: -1
- load_best_model_at_end: True
Training Results
| Epoch | Step | Training Loss | Validation Loss |
|---|---|---|---|
| 0.0015 | 1 | 0.3989 | - |
| 0.0742 | 50 | 0.2221 | - |
| 0.1484 | 100 | 0.2617 | - |
| 0.2226 | 150 | 0.0514 | - |
| 0.2967 | 200 | 0.0852 | - |
| 0.3709 | 250 | 0.0754 | - |
| 0.4451 | 300 | 0.0353 | - |
| 0.5193 | 350 | 0.0091 | - |
| 0.5935 | 400 | 0.0116 | - |
| 0.6677 | 450 | 0.0213 | - |
| 0.7418 | 500 | 0.0036 | - |
| 0.8160 | 550 | 0.0039 | - |
| 0.8902 | 600 | 0.011 | - |
| 0.9644 | 650 | 0.0014 | - |
| 1.0 | 674 | - | 0.0344 |
| 1.0386 | 700 | 0.0014 | - |
| 1.1128 | 750 | 0.0028 | - |
| 1.1869 | 800 | 0.0003 | - |
| 1.2611 | 850 | 0.0003 | - |
| 1.3353 | 900 | 0.0002 | - |
| 1.4095 | 950 | 0.0006 | - |
| 1.4837 | 1000 | 0.0005 | - |
| 1.5579 | 1050 | 0.0002 | - |
| 1.6320 | 1100 | 0.0002 | - |
| 1.7062 | 1150 | 0.0003 | - |
| 1.7804 | 1200 | 0.0002 | - |
| 1.8546 | 1250 | 0.0001 | - |
| 1.9288 | 1300 | 0.0002 | - |
| 2.0 | 1348 | - | 0.0319 |
- The bold row denotes the saved checkpoint.
Framework Versions
- Python: 3.10.12
- SetFit: 1.0.1
- Sentence Transformers: 2.2.2
- Transformers: 4.35.2
- PyTorch: 2.1.0+cu121
- Datasets: 2.15.0
- Tokenizers: 0.15.0
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
- 1
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for keivan/albert-zwnj-wnli-mean-tokens
Base model
m3hrdadfi/albert-zwnj-wnli-mean-tokens