fuhakiem/hin-v001-trainer

SetFit with BAAI/bge-small-en-v1.5 on Health Information Needs

This is a SetFit model that can be used for Text Classification. This SetFit model uses BAAI/bge-small-en-v1.5 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: BAAI/bge-small-en-v1.5
• Classification head: a LogisticRegression instance
• Maximum Sequence Length: 512 tokens
• Number of Classes: 2 classes
• Language: en
• License: apache-2.0

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	'Where would you put refuse if you do not want it to exist any more?' 'Which is an example of the absolutism under peter the great?' 'where does the water at niagra falls come from'
0	'the nerves,blood vessels, and glands are located in which layer of the skin' 'Of what discipline is affective computing a branch?' 'Obesity can cause resistance to which hormone?'

Evaluation

Metrics

Label	0	1	Accuracy	Macro Avg	Weighted Avg
all	{'precision': 0.37465309898242366, 'recall': 0.989413680781759, 'f1-score': 0.5435025721315142, 'support': 1228.0}	{'precision': 0.9940962761126249, 'recall': 0.5190894000474271, 'f1-score': 0.6820377005764138, 'support': 4217.0}	0.6252	{'precision': 0.6843746875475243, 'recall': 0.7542515404145931, 'f1-score': 0.6127701363539639, 'support': 5445.0}	{'precision': 0.8543944907102582, 'recall': 0.6251606978879706, 'f1-score': 0.6507941491107871, 'support': 5445.0}

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("fuhakiem/hin-v001-trainer")
# Run inference
preds = model("Referees")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	1	7.3	15

Label	Training Sample Count
0	5
1	5

Training Hyperparameters

• batch_size: (32, 32)
• num_epochs: (10, 10)
• max_steps: -1
• sampling_strategy: oversampling
• body_learning_rate: (2e-05, 1e-05)
• head_learning_rate: 0.01
• 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
0.5	1	0.1957	-

Framework Versions

• Python: 3.10.12
• SetFit: 1.1.0
• Sentence Transformers: 3.3.1
• Transformers: 4.42.2
• PyTorch: 2.5.1+cu124
• Datasets: 3.2.0
• 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}
}