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
order tracking	'My order has been shipped 6 days ago but still not out for delivery. Can you tell how long will it take to deliver?' 'I want to deliver packaging to Surat, how many days will it take to deliver?' 'Do you provide shipping insurance for high-value orders?'
product faq	'Is the Smart Keychain in Navy Blue available for women?' 'Is the Smart Fingerlock Backpack Leather in Black targeted towards men, women, or unisex?' '1. Can you tell me the price of the smart luggage?'
general faq	"Can you explain how the 'Follow Me' feature works in Arista Vault's smart luggage?" "What makes Arista Vault's smart luggage a good investment for business travelers?" "How does the fingerprint lock technology in Arista Vault's smart luggage enhance security?"
product policy	'Can I register multiple accounts for the Arista Vault Affiliate Program?' 'What is your return and exchange policy?' 'How do I receive my referral fees and commissions?'
product discoverability	'Do you have any smart accessories in blue color?' 'What is the price of the smart luggage for women?' 'Which smart backpacks are available in nylon material?'

Evaluation

Metrics

Label	Accuracy
all	0.9565

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 smart luggage options do you have for men?")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	6	11.6304	24

Label	Training Sample Count
Out of Scope	0
general faq	4
order tracking	24
product discoverability	16
product faq	24
product policy	24

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
0.0025	1	0.2167	-
0.1238	50	0.0573	-
0.2475	100	0.0002	-
0.3713	150	0.0009	-
0.4950	200	0.0001	-
0.6188	250	0.0	-
0.7426	300	0.0	-
0.8663	350	0.0	-
0.9901	400	0.0	-
1.1139	450	0.0	-
1.2376	500	0.0	-
1.3614	550	0.0	-
1.4851	600	0.0001	-
1.6089	650	0.0	-
1.7327	700	0.0	-
1.8564	750	0.0	-
1.9802	800	0.0	-

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_oos_arista_vault