konsman/setfit-messages-generated-test

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: 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
2	'Rapid onset of confusion and weakness, urgent evaluation needed.' 'Unconscious patient found, immediate medical response required.' 'Urgent: Suspected heart attack, immediate medical attention required.'
1	'Reminder: Your dental check-up is scheduled for Monday, February 05.' 'Reminder: Your dental check-up is scheduled for Saturday, February 24.' 'Nutritionist appointment reminder for Sunday, January 21.'
0	'Could you verify your lifestyle contact details in our records?' 'Kindly update your emergency contact list at your earliest convenience.' 'We request you to update your wellness information for our records.'

Evaluation

Metrics

Label	Accuracy
all	0.85

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("konsman/setfit-messages-generated-test")
# Run inference
preds = model("Sudden severe chest pain, suspecting a cardiac emergency.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	7	10.125	12

Label	Training Sample Count
0	16
1	16
2	16

Training Hyperparameters

• batch_size: (8, 8)
• num_epochs: (2, 2)
• max_steps: -1
• sampling_strategy: oversampling
• num_iterations: 40
• body_learning_rate: (2.2041595048800003e-05, 2.2041595048800003e-05)
• head_learning_rate: 2.2041595048800003e-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
0.0021	1	0.2841	-
0.1042	50	0.0603	-
0.2083	100	0.0017	-
0.3125	150	0.0003	-
0.4167	200	0.0004	-
0.5208	250	0.0003	-
0.625	300	0.0003	-
0.7292	350	0.0002	-
0.8333	400	0.0003	-
0.9375	450	0.0001	-
1.0417	500	0.0002	-
1.1458	550	0.0003	-
1.25	600	0.0002	-
1.3542	650	0.0002	-
1.4583	700	0.0001	-
1.5625	750	0.0002	-
1.6667	800	0.0001	-
1.7708	850	0.0001	-
1.875	900	0.0001	-
1.9792	950	0.0002	-

Framework Versions

• Python: 3.10.12
• SetFit: 1.0.3
• Sentence Transformers: 2.2.2
• Transformers: 4.35.2
• PyTorch: 2.1.0+cu121
• Datasets: 2.16.1
• Tokenizers: 0.15.0

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}
}