yannryanhelsinki/setfit-language-guess

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:

1. Fine-tuning a Sentence Transformer with contrastive learning.
2. 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
no	'Exomologesis sive Modus confitendi,per Erasmum Roterodamũ .../Exomologesis sive modus confitendi per Erasmum Roterodamum' 'Aen-wysinge van de macht en de eer die aen Jesus-Christus toe-komt. En van de eerbiedinghe die-men schuldigh is aen sijn aldersuyverste moeder Maria, en andere heyligen.' 'Staatkundige vermaningen en voorbeelden, die de deughden en zonden der vorsten betreffen.Nieuwelijks door I.H. Glazemaker vertaalt.'
yes	'Reclamations des trois états du duché de Brabant sur les atteintes portées a leurs droits et loix constitutionnelles au nom de S.M. Joseph II.' 'Brief van het Magistraet van Brugge van date 16 February 1788 aen de ordinaire Gedeputeerde der Staeten van Vlaenderen tenderende om staets gewyze te doen naedere Representatie tegen de opregtinge van een Seminarie Generael tot Loven ...' "Bericht voor d'Universiteyt &c. van Leuven, over de wijtloopige memorie, en andere schriften en documenten daer by, overgegeven aen haer Ho. Mog. door de vicarissen van Doornik"

Evaluation

Metrics

Label	Accuracy
all	0.735

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("yannryanhelsinki/setfit-language-guess")
# Run inference
preds = model("Colloqujdi Gio: Lodovico Vives latini, e volgari/Colloqui")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	5	29.2759	92

Label	Training Sample Count
no	44
yes	72

Training Hyperparameters

• batch_size: (16, 16)
• num_epochs: (1, 1)
• max_steps: -1
• sampling_strategy: oversampling
• num_iterations: 20
• 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
0.0034	1	0.2242	-
0.1724	50	0.1951	-
0.3448	100	0.0342	-
0.5172	150	0.0008	-
0.6897	200	0.0006	-
0.8621	250	0.0003	-

Framework Versions

• Python: 3.10.12
• SetFit: 1.0.3
• Sentence Transformers: 3.0.1
• Transformers: 4.39.0
• PyTorch: 2.3.0+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}
}