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 Type: SetFit
Sentence Transformer body: sentence-transformers/paraphrase-mpnet-base-v2
Classification head: a LogisticRegression instance
Maximum Sequence Length: 512 tokens
Number of Classes: 5 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
product faq	'9. Is this product effective for pimples and acne?' 'What are the key features of the Hydration Combo Kit?' 'What are the main ingredients in the Daily Spread Moisturiser + Mineral Suncreen SPF 30?'
order tracking	'What is the delivery status for my order placed using email address [email protected]?' 'I ordered the Cupcake Cases 3 days ago with order no 34567 how long will it take to deliver?' 'I need to return an item, what is the return policy for online orders?'
general faq	'What ingredients in K-beauty products help with sensitive skin?' 'What inspired your founder to start Botnal?' 'How can I adapt K-beauty routines for dry weather?'
product policy	'What makes BOTNAL skincare products clean and effective?' 'What is your return policy duration?' 'What are the accepted payment methods for purchasing BOTNAL products?'
product discoverability	'Do you have any products specifically for targeting aging?' 'Which products are best for acne?' 'What products do you have for wrinkles?'

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("setfit_model_id")
# Run inference
preds = model("What products do you have for the body?")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	6	10.7126	24

Label	Training Sample Count
general faq	16
order tracking	24
product discoverability	16
product faq	23
product policy	8

Training Hyperparameters

batch_size: (16, 16)
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
0.0027	1	0.0657	-
0.1359	50	0.0053	-
0.2717	100	0.0002	-
0.4076	150	0.0001	-
0.5435	200	0.0003	-
0.6793	250	0.0002	-
0.8152	300	0.0001	-
0.9511	350	0.0001	-
1.0870	400	0.0004	-
1.2228	450	0.0001	-
1.3587	500	0.0001	-
1.4946	550	0.0001	-
1.6304	600	0.0001	-
1.7663	650	0.0001	-
1.9022	700	0.0001	-

Framework Versions

Python: 3.10.16
SetFit: 1.0.3
Sentence Transformers: 2.7.0
Transformers: 4.40.2
PyTorch: 2.2.2
Datasets: 2.19.1
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}
}

Shankhdhar
/

classifier_woog_botnal