Shankhdhar/classifier_woog_purely_yours

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:

1. Fine-tuning a Sentence Transformer with contrastive learning.
2. 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 discoverability	'What are the options for dietary wellbeing products?' 'Do you have any products for weight loss?' 'What are the available options for male sexual wellness products?'
product faq	'What are the benefits of using Prost Plus for male sexual wellness?' 'How does the Eladi skin exfoliator help in reducing acne and blemishes?' 'What are the ingredients in the Organic Breeaze Brew?'
order tracking	'What is the expected delivery time for the Baking Ingredients I ordered?' 'Do you provide shipping insurance for high-value orders?' 'My order has been shipped 6 days ago but still not out for delivery. Can you tell how long will it take to deliver?'
general faq	'What makes Purely Yours products different from other Ayurvedic brands?' 'How do you ensure the quality and authenticity of your Ayurvedic products?' 'Can you tell me more about the certifications your products hold?'
product policy	'What are the delivery charges for orders below INR 500?' 'How do you use the personal information collected on your website?' 'Are there any delivery charges for orders above INR 499?'

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 options do you have for weight management products?")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	6	11.55	24

Label	Training Sample Count
general faq	4
order tracking	24
product discoverability	16
product faq	24
product policy	12

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
0.0033	1	0.0739	-
0.1656	50	0.0201	-
0.3311	100	0.0005	-
0.4967	150	0.0003	-
0.6623	200	0.0001	-
0.8278	250	0.0001	-
0.9934	300	0.0001	-
1.1589	350	0.0001	-
1.3245	400	0.0001	-
1.4901	450	0.0001	-
1.6556	500	0.0001	-
1.8212	550	0.0001	-
1.9868	600	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}
}