README.md

metadata

tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
widget:
  - text: >-
      the caption is long so can take a little time to understand the context of
      the chart
  - text: >-
      The caption is informative, it also has some unnecessary information that
      might not be needed to interpret the charts
  - text: The caption is detailed and
  - text: >-
      Although the caption is long, it expands on each of the studies making it
      easier to understand the main takeaway
  - text: >-
      The different bars in the chart are not easy to comprehend without reading
      the captions
metrics:
  - accuracy
pipeline_tag: text-classification
library_name: setfit
inference: true
base_model: sentence-transformers/all-MiniLM-L6-v2

SetFit with sentence-transformers/all-MiniLM-L6-v2

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/all-MiniLM-L6-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/all-MiniLM-L6-v2
• Classification head: a LogisticRegression instance
• Maximum Sequence Length: 256 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
0	'the caption is long so can take a little time to understand the context of the chart' 'The caption is detailed, but does not provide the clear takeaway' 'The caption is long and hard to interpret'
1	'The caption summarizes the key trend' 'The caption is informative, it also has some unnecessary information that might not be needed to interpret the charts' 'The different bars in the chart are not easy to comprehend without reading the captions'

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("an778/sentence-transformers")
# Run inference
preds = model("The caption is detailed and")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	3	11.375	21

Label	Training Sample Count
0	8
1	8

Training Hyperparameters

• batch_size: (16, 16)
• num_epochs: (8, 8)
• 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: True

Training Results

Epoch	Step	Training Loss	Validation Loss
0.1111	1	0.2791	-
1.0	9	-	0.2195
2.0	18	-	0.2068
3.0	27	-	0.1879
4.0	36	-	0.1541
5.0	45	-	0.1141
5.5556	50	0.1874	-
6.0	54	-	0.0762
7.0	63	-	0.0549
8.0	72	-	0.0482

Framework Versions

• Python: 3.11.11
• SetFit: 1.1.2
• Sentence Transformers: 3.4.1
• Transformers: 4.50.3
• PyTorch: 2.6.0+cu124
• Datasets: 3.5.0
• Tokenizers: 0.21.1

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}
}