vgarg's picture
Add SetFit model
c03eb8c verified
metadata
library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - accuracy
widget:
  - text: >-
      How does cannibalization within the RTEC category compare to other product
      categories within the MT channel, influencing the overall volumelift?
  - text: >-
      Can you identify the specific factors or challenges that contributed to
      the decline in ROI within TT in 2022 compared to 2021?
  - text: >-
      Which Sku cannibalizes higher margin Skus the most for CHEDRAUI
      channel_name?
  - text: >-
      Can you compare the overall market share and competitive landscape of the
      category more sensitive to internal cannibalization with other categories?
  - text: >-
      Can you identify the key factors or challenges that have contributed to
      the ROI decline within  TT
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: 0.9130434782608695
            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:

  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 Sources

Model Labels

Label Examples
2
  • 'Are there particular factors or trends contributing to the high level of cannibalization for certain brands in the SS category?'
  • 'How does the degree of cannibalization vary among different SKUs in the RTEC ?'
  • 'Which Sku cannibalizes higher margin Skus the most?'
1
  • 'Are there plans to enhance promotional activities specific to the MT to mitigate the ROI decline in 2023?'
  • 'What are the main reasons for ROI decline in 2022 in MT compared to 2021?'
  • 'Are there changes in consumer preferences or trends that have impacted the Lift of Zucaritas, and how does this compare to other brands like Pringles or Frutela?'
0
  • 'What type of promotions worked best for MT Walmart in 2022?'
  • 'Which channel has the max ROI and Vol Lift when we run the Promotion for RTEC category?'
  • 'Which sub_catg_nm have the highest ROI in 2022?'

Evaluation

Metrics

Label Accuracy
all 0.9130

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/promo_prescriptive_gpt_28_02_2024_v1")
# Run inference
preds = model("Which Sku cannibalizes higher margin Skus the most for CHEDRAUI channel_name?")

Training Details

Training Set Metrics

Training set Min Median Max
Word count 7 15.8333 30
Label Training Sample Count
0 10
1 10
2 10

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
0.0133 1 0.3582 -
0.6667 50 0.0024 -
1.3333 100 0.0005 -
2.0 150 0.0004 -
2.6667 200 0.0002 -

Framework Versions

  • Python: 3.10.12
  • SetFit: 1.0.3
  • Sentence Transformers: 2.4.0
  • Transformers: 4.37.2
  • PyTorch: 2.1.0+cu121
  • Datasets: 2.17.1
  • 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}
}