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: 4 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	'Do you have Adidas Superstar shoes?' 'Do you have any running shoes in pink color?' 'Do you have black Yeezy sneakers in size 9?'
order tracking	"I'm concerned about the delay in the delivery of my order. Can you please provide me with the status?" 'What is the estimated delivery time for orders within the same city?' "I placed an order last week and it still hasn't arrived. Can you check the status for me?"
product policy	'Are there any exceptions to the return policy for items that were purchased with a student discount?' 'Do you offer a try-and-buy option for sneakers?' 'Do you offer a price adjustment for sneakers if the price drops after purchase?'
product faq	'Do you have any limited edition sneakers available?' 'Are the Adidas Yeezy Foam Runner available in size 7?' "Are the Nike Air Force 1 sneakers available in women's sizes?"

Evaluation

Metrics

Label	Accuracy
all	0.8381

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("special features for bakery boxes")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	3	11.6415	24

Label	Training Sample Count
order tracking	30
product discoverability	30
product faq	16
product policy	30

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
0.0019	1	0.1782	-
0.0965	50	0.0628	-
0.1931	100	0.0036	-
0.2896	150	0.0013	-
0.3861	200	0.0012	-
0.4826	250	0.0003	-
0.5792	300	0.0002	-
0.6757	350	0.0003	-
0.7722	400	0.0002	-
0.8687	450	0.0005	-
0.9653	500	0.0003	-
1.0618	550	0.0001	-
1.1583	600	0.0002	-
1.2548	650	0.0002	-
1.3514	700	0.0002	-
1.4479	750	0.0001	-
1.5444	800	0.0001	-
1.6409	850	0.0001	-
1.7375	900	0.0002	-
1.8340	950	0.0001	-
1.9305	1000	0.0001	-

Framework Versions

Python: 3.9.16
SetFit: 1.0.3
Sentence Transformers: 2.7.0
Transformers: 4.40.2
PyTorch: 2.3.0
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