metadata

base_model: BAAI/bge-small-en-v1.5
library_name: setfit
metrics:
  - accuracy
pipeline_tag: text-classification
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
widget:
  - text: >-
      How does the choice of oxidizer, such as liquid oxygen or nitrogen
      tetroxide, affect the performance and handling requirements of a rocket
      engine?
  - text: >-
      Rocket engines designed for vacuum operation often incorporate radiative
      cooling methods, utilizing large surface areas to dissipate heat in the
      absence of convective cooling mechanisms.
  - text: >-
      Thermo-optical properties of surface materials, such as absorptivity and
      emissivity, are critical parameters in the design of the thermal control
      subsystem.
  - text: >-
      The thrust produced by a rocket engine is a function of the mass flow rate
      of the propellant and the velocity of the exhaust gases as they exit the
      nozzle.
  - text: >-
      Thermal analysis of a satellite involves finite element modeling to
      predict temperature gradients and ensure proper thermal design and
      component placement.
inference: true
model-index:
  - name: SetFit with BAAI/bge-small-en-v1.5
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 1
            name: Accuracy

SetFit with BAAI/bge-small-en-v1.5

This is a SetFit model that can be used for Text Classification. This SetFit model uses BAAI/bge-small-en-v1.5 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: BAAI/bge-small-en-v1.5
Classification head: a LogisticRegression instance
Maximum Sequence Length: 512 tokens
Number of Classes: 3 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
Propulsion	"Rocket engines operate on the principle of Newton's Third Law of Motion, where the expulsion of high-speed exhaust gases produces a reaction force that propels the rocket forward." 'The combustion efficiency of a rocket engine depends on factors like propellant mixture ratio, injector design, and combustion chamber pressure.' 'Deep throttling capability, which allows a rocket engine to vary its thrust over a wide range, is essential for applications requiring precise landing maneuvers, such as lunar landers.'
Power Subsystem	'Redundant power paths and autonomous fault detection mechanisms are implemented to ensure continuous electrical supply even in the event of subsystem failures or external anomalies.' 'Electromagnetic interference (EMI) shielding and grounding techniques are essential in satellite design to prevent power system noise from affecting sensitive communication and navigation subsystems.' 'Autonomous diagnostic and recovery protocols are embedded within the power management system to isolate and rectify faults, ensuring mission continuity.'
Thermal Control	'The thermal control subsystem must accommodate both internal heat generated by electronic components and external thermal loads from the space environment.' 'Describe the impact of albedo and infrared emissions from Earth on satellite thermal design.' 'Passive thermal control elements, such as multi-layer insulation (MLI), surface coatings, and radiators, are used to minimize thermal fluctuations and radiation absorption.'

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("patrickfleith/my-awesome-astro-text-classifier")
# Run inference
preds = model("How does the choice of oxidizer, such as liquid oxygen or nitrogen tetroxide, affect the performance and handling requirements of a rocket engine?")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	11	22.2368	30

Label	Training Sample Count
Propulsion	15
Thermal Control	14
Power Subsystem	9

Training Hyperparameters

batch_size: (32, 32)
num_epochs: (10, 10)
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: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0333	1	0.2377	-
1.6667	50	0.0551	-
3.3333	100	0.0046	-
5.0	150	0.0031	-
6.6667	200	0.0024	-
8.3333	250	0.0022	-
10.0	300	0.002	-

Framework Versions

Python: 3.10.12
SetFit: 1.0.3
Sentence Transformers: 3.0.1
Transformers: 4.39.0
PyTorch: 2.3.1+cu121
Datasets: 2.20.0
Tokenizers: 0.15.2

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}
}