lucienbaumgartner/informational_content_classifier

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_info	"This statement requires context about John's situation and the road conditions. Without it, assuming good reasons to believe there would be no other car is speculative." 'I have no knowledge of Ms. Russell or any potential floods she may have been concerned about. ' "I don't have access to real-time weather patterns or geographical data to assess flood probability."
info	'She was responsible for ensuring the safety of her community and failed to do so.' 'The previous two years showed no flooding.' 'John could have been more cautious, but it might not warrant very severe punishment.'

Evaluation

Metrics

Label	Accuracy	Precision	Recall	F1
all	0.95	0.95	0.95	0.95

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("setfit_model_id")
# Run inference
preds = model("I cannot determine an appropriate level of punishment as I lack context about the situation and Ms. Russel's responsibilities.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	2	20.0312	36

Label	Training Sample Count
info	16
no_info	16

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
0.0125	1	0.2422	-
0.625	50	0.0018	-

Framework Versions

• Python: 3.11.7
• SetFit: 1.0.3
• Sentence Transformers: 2.7.0
• Transformers: 4.40.1
• PyTorch: 2.3.0
• Datasets: 2.19.0
• 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}
}