metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - accuracy
widget:
  - text: What should be Ideal Promo Duration?
  - text: Compare the performance of top skus
  - text: What is my Forward Buying across Brands?
  - text: 'Which Packs segments are being cannibalized the most by xx '
  - text: What price point is vacant in xx?
pipeline_tag: text-classification
inference: true
base_model: intfloat/multilingual-e5-large
model-index:
  - name: SetFit with intfloat/multilingual-e5-large
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 0.95
            name: Accuracy

SetFit with intfloat/multilingual-e5-large

This is a SetFit model that can be used for Text Classification. This SetFit model uses intfloat/multilingual-e5-large 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:

Fine-tuning a Sentence Transformer with contrastive learning.
Training a classification head with features from the fine-tuned Sentence Transformer.

Model Details

Model Description

Model Type: SetFit
Sentence Transformer body: intfloat/multilingual-e5-large
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
1	'Which promotion type is giving better returns ?' 'Tell me the best performing promotions for xx' 'Which SKUs in each brand need to be promoted more?'
0	'Tell me the top 10 SKUs in xx' 'what are the volume and value market share of xx in yy Category in zz?' 'Which brands are most elastic in xx for yy?'

Evaluation

Metrics

Label	Accuracy
all	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("vgarg/usecase_classifier_large_17_04_24")
# Run inference
preds = model("What price point is vacant in xx?")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	4	11.15	19

Label	Training Sample Count
0	20
1	20

Training Hyperparameters

batch_size: (16, 16)
num_epochs: (3, 3)
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
0.01	1	0.3409	-
0.5	50	0.0012	-
1.0	100	0.0002	-
1.5	150	0.0001	-
2.0	200	0.0001	-
2.5	250	0.0001	-
3.0	300	0.0001	-

Framework Versions

Python: 3.10.12
SetFit: 1.0.3
Sentence Transformers: 2.6.1
Transformers: 4.38.2
PyTorch: 2.2.1+cu121
Datasets: 2.18.0
Tokenizers: 0.15.2

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}
}