osmedi/sentence_independancy_model

SetFit with sentence-transformers/paraphrase-multilingual-mpnet-base-v2

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/paraphrase-multilingual-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-multilingual-mpnet-base-v2
• Classification head: a LogisticRegression instance
• Maximum Sequence Length: 128 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
1	'HLPSS partners also held successful negotiations to halt a planned eviction of 559 IDPs from Biafra Camp Bulabulin in MMC LGA, when the IDPs were unable to meet landowners’ demands to pay between 500 to 1000 Naira monthly as rent since October 2019.' 'Sin embargo, un prestador del servicio de aseo encontró dificultad al momento de comprar: cepillos, guantes y escobas.' 'Conflict results in frequent civilian harm and atrocities have been committed in the area, including against children; populations are also subject to recurrent forced displacement.'
0	'En menor proporción y contrario a estos eventos, en Norte de Santander se reportaron afectaciones por la sequía propia de la temporada.' 'Cette situation est relativement meilleure comparé à la MAM mais l’objectif national de 70% n’est pas atteint.' 'These figures are consistent with those from the June and May consultations.'

Evaluation

Metrics

Label	Accuracy
all	0.75

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("osmedi/sentence_independancy_model")
# Run inference
preds = model("Ce sont des travaux très pénibles qui nuisent à leur santé physique.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	3	25.1481	78

Label	Training Sample Count
0	54
1	54

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
• l2_weight: 0.01
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0037	1	0.3515	-
0.1852	50	0.2656	-
0.3704	100	0.1631	-
0.5556	150	0.0073	-
0.7407	200	0.0016	-
0.9259	250	0.001	-

Framework Versions

• Python: 3.10.12
• SetFit: 1.1.0
• Sentence Transformers: 3.1.1
• Transformers: 4.44.2
• PyTorch: 2.4.1+cu121
• Datasets: 3.0.1
• 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}
}