metadata

base_model: sentence-transformers/paraphrase-mpnet-base-v2
library_name: setfit
metrics:
  - accuracy
pipeline_tag: text-classification
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
widget:
  - text: >-
      All critical security parameters are injected into the system during
      production.
  - text: >-
      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.
  - text: >-
      Random number generator obtains its seed key by reading bytes from the
      /dev/urandom device. The seed key is stored in SDRAM in plaintext while in
      use and is deleted from memory on power-down, reboot, or any command that
      is followed by a reboot, such as switching between non-approved and
      approved modes, zeroization, restore factory settings, and reset shared
      key.
  - text: X9.31 PRNG seed keys Triple-DES (112 bit) Generated by gathering entropy.
  - text: >-
      X Seed Key for RNG: Seed created by NDRNG and used as the Triple DES key
      in the ANSI X9.31 RNG.
inference: true

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	'The private key component of an ANSI X9.31-compliant PRNG is stored securely in NVRAM.' 'It is generated in the factory (a secure environment) using the hardware RNG Embedded in FLASH.' 'The internal DRBG state value of the RNG is stored in NVRAM for persistent use.'
negative	'The NDRNG is used to generate seed & seed key values to feed the DRNG.' 'module stores RNG and DRBG state values only in RAM.' 'PRNG Seed Key A new ANSI X9.31 RNG Seed Key is generated from a block of 160 bits output by the random noise source software library.'

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_v6")
# Run inference
preds = model("X9.31 PRNG seed keys Triple-DES (112 bit) Generated by gathering entropy.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	6	18.8889	49

Label	Training Sample Count
negative	23
positive	22

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
0.0294	1	0.2114	-
1.0	34	-	0.0933
1.4706	50	0.1015	-
2.0	68	-	0.0967
2.9412	100	0.0008	-
3.0	102	-	0.1039
4.0	136	-	0.1055

Framework Versions

Python: 3.10.16
SetFit: 1.1.1
Sentence Transformers: 3.3.1
Transformers: 4.45.2
PyTorch: 2.5.1+cu124
Datasets: 3.2.0
Tokenizers: 0.20.3

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}
}