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: 2 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
positive	'A 256-bit seed key for the ANSI X9.31 RNG function using AES-256 is stored in plaintext in RAM, generated securely at the factory, and embedded in flash memory.' 'The ANSI X9.31 RNG is initialized using a 128-bit AES seed key generated outside the module.' 'PRNG compliant to ANSI X9.31 private key portion stored in secured NVRAM.'
negative	'ANSI X9.31 RNG Seed Key 168-bit TDES keys/ 256-bit AES key Generated by the TRNG.' '128 bits Random Number Key Key value is used by the random number generator. RTC-RAM Zeroize CSPs service.' 'PRNG ANSI X9.31 Key K1, K2 Internal 3DES Key Automatically Generated per seeding This is an internal key used for ANSI X9.31 192 bits Internal Key generate from the seed and seed key'

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("yasirdemircan/setfit_rng_v2")
# Run inference
preds = model("The NDRNG is used to generate seed & seed key values to feed the DRNG.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	6	19.8667	59

Label	Training Sample Count
negative	22
positive	23

Training Hyperparameters

batch_size: (16, 16)
num_epochs: (4, 4)
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
l2_weight: 0.01
seed: 42
eval_max_steps: -1
load_best_model_at_end: True

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0149	1	0.2065	-
0.7463	50	0.1335	-
1.0	67	-	0.2640
1.4925	100	0.0016	-
2.0	134	-	0.2100
2.2388	150	0.0003	-
2.9851	200	0.0002	-
3.0	201	-	0.2100
3.7313	250	0.0002	-
4.0	268	-	0.2095

Framework Versions

Python: 3.10.15
SetFit: 1.2.0.dev0
Sentence Transformers: 3.3.1
Transformers: 4.45.2
PyTorch: 2.5.1+cu124
Datasets: 2.19.1
Tokenizers: 0.20.1

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}
}

yasirdemircan
/

setfit_rng_v2