SetFit with sentence-transformers/all-MiniLM-L6-v2

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/all-MiniLM-L6-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/all-MiniLM-L6-v2
Classification head: a LogisticRegression instance
Maximum Sequence Length: 256 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
0	'first: Employee Support Groups: Peer-led support groups for employees facing similar issues. second: We offer conflict resolution workshops to provide employees with valuable skills.'
1	'first: Conflict Resolution Peer Mentoring: Experienced employees mentor newcomers in conflict resolution. second: Diversity and Inclusion Training: Programs that promote understanding and reduce conflicts related to diversity.'

Evaluation

Metrics

Label	Accuracy
all	0.4091

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("diegofiggie/fairness_model")
# Run inference
preds = model("first: Mediation sessions are scheduled outside of regular working hours for convenience. second: Employee Conflict Coaches: Coaches work one-on-one with employees to resolve disputes.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	24	25.5	27

Label	Training Sample Count
0	1
1	1

Training Hyperparameters

batch_size: (4, 4)
num_epochs: (1, 1)
max_steps: -1
sampling_strategy: oversampling
num_iterations: 30
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
seed: 42
eval_max_steps: -1
load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0333	1	0.2322	-

Framework Versions

Python: 3.10.9
SetFit: 1.0.3
Sentence Transformers: 2.4.0
Transformers: 4.38.1
PyTorch: 2.2.1+cpu
Datasets: 2.17.1
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}
}

diegofiggie
/

fairness_model