SetFit with sentence-transformers/paraphrase-mpnet-base-v2
This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/paraphrase-mpnet-base-v2 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 Sources
Model Labels
Label |
Examples |
2 |
- 'I require assistance in altering certain elements of my policy.'
- "Hey there, I've spotted a gap in my policy information."
- 'I need to rectify something within my policy documentation.'
|
4 |
- "I am covered by health insurance through my employer's sponsorship."
- 'Is it permissible to transfer my health plan to ACKO?'
- 'My old health policy from another insurance provider is no longer in effect.'
|
3 |
- 'Can you reveal all policies under my profile?'
- 'I want to be informed about the status of all my insurance arrangements.'
- "Is it possible for you to display my family's health insurance policies?"
|
1 |
- 'How is my vehicle claim proceeding?'
- "I'm curious about the status of my car insurance claim."
- 'Am I required to provide additional evidence for my claims?'
|
0 |
- 'I need help selecting an appropriate health insurance plan for my family.'
- "I'm looking for a health policy that will cover me along with my two kids."
- "I'm in urgent need of a health insurance plan for my family's wellbeing."
|
Evaluation
Metrics
Label |
Accuracy |
all |
0.9160 |
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
model = SetFitModel.from_pretrained("harshita23sh/setfit-model-intent-classification-insurance")
preds = model("I have my own health insurance policy.")
Training Details
Training Set Metrics
Training set |
Min |
Median |
Max |
Word count |
5 |
10.6 |
15 |
Label |
Training Sample Count |
0 |
5 |
1 |
8 |
2 |
12 |
3 |
4 |
4 |
11 |
Training Hyperparameters
- batch_size: (16, 16)
- num_epochs: (1, 1)
- max_steps: -1
- sampling_strategy: oversampling
- num_iterations: 20
- 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 |
0.01 |
1 |
0.1388 |
- |
0.5 |
50 |
0.0087 |
- |
1.0 |
100 |
0.0029 |
- |
Framework Versions
- Python: 3.10.12
- SetFit: 1.0.3
- Sentence Transformers: 2.7.0
- Transformers: 4.40.0
- PyTorch: 2.2.1+cu121
- Datasets: 2.19.0
- 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}
}