metadata

tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
widget:
  - text: >-
      The tech giant announced today the appointment of a new CTO to lead their
      innovative projects in AI.
  - text: >-
      During the recent annual meeting, the board of directors at HealthCorp
      discussed various operational strategies but did not announce any changes
      to their leadership team.
  - text: >-
      Tech giant Innovatech has announced the appointment of Jane Doe as their
      new Chief Technology Officer, effective immediately. This change aims to
      drive the company's focus on artificial intelligence.
  - text: >-
      The political landscape in the country shifted dramatically with a recent
      election, leading to new party leadership.
  - text: >-
      In a recent interview, the founder of Foodies Co. expressed his
      frustration over market competition but reassured that no changes in
      leadership were imminent.
metrics:
  - accuracy
pipeline_tag: text-classification
library_name: setfit
inference: true
base_model: dunzhang/stella_en_400M_v5
model-index:
  - name: SetFit with dunzhang/stella_en_400M_v5
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 0.9666666666666667
            name: Accuracy

SetFit with dunzhang/stella_en_400M_v5

This is a SetFit model that can be used for Text Classification. This SetFit model uses dunzhang/stella_en_400M_v5 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: dunzhang/stella_en_400M_v5
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
True	'Tech giant ABC Corp appoints a new CTO to drive innovation.' 'The CEO of DEF Inc. steps down after a decade at the helm, marking a change in leadership.' 'GHI Industries promotes its Chief Marketing Officer to take over as CEO.'
False	'XYZ Ltd. announced a strategic shift but no change in leadership positions.' 'New government regulations might prompt shifts in corporate governance.' 'The recent quarterly report highlighted performance issues but indicated stable management.'

Evaluation

Metrics

Label	Accuracy
all	0.9667

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("amplyfi/leadership-change")
# Run inference
preds = model("The tech giant announced today the appointment of a new CTO to lead their innovative projects in AI.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	9	14.9963	23

Label	Training Sample Count
False	136
True	135

Training Hyperparameters

batch_size: (16, 16)
num_epochs: (3, 3)
max_steps: -1
sampling_strategy: oversampling
num_iterations: 5
body_learning_rate: (2e-05, 2e-05)
head_learning_rate: 2e-05
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: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0059	1	0.2381	-
0.2941	50	0.1096	-
0.5882	100	0.0006	-
0.8824	150	0.0003	-
1.1765	200	0.0001	-
1.4706	250	0.0	-
1.7647	300	0.0	-
2.0588	350	0.0	-
2.3529	400	0.0	-
2.6471	450	0.0	-
2.9412	500	0.0	-

Framework Versions

Python: 3.10.12
SetFit: 1.1.0
Sentence Transformers: 3.3.1
Transformers: 4.42.2
PyTorch: 2.5.1+cu124
Datasets: 3.1.0
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}
}