vgarg/promo_prescriptive_15_03_2024

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 Type: SetFit
• Sentence Transformer body: intfloat/multilingual-e5-large
• Classification head: a LogisticRegression instance
• Maximum Sequence Length: 512 tokens
• Number of Classes: 5 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
2	'Can you identify the category that demonstrates a higher sensitivity to internal cannibalization?' 'What kind of promotions generally lead to higher cannibalization for HYPER for year 2022?' "Which two sku's can have simultaneous Promotions for subcategory CHIPS & SNACKS?"
3	'Which promotion strategies in RTEC allow for offering substantial discounts while maintaining profitability?' 'Which promotion types are better for high discounts in Alsuper for Pringles?' 'Are there specific promotional tactics in the RTEC category that are particularly effective for implementing high discount offers?'
4	'Which promotions have scope for higher investment to drive more ROIs in WALMART ?' 'Are there any promotional strategies in RTEC that have consistently underperformed and should be considered for discontinuation?' 'Suggest a better investment strategy to gain better ROI for SS?'
0	'Which subcategory have the highest ROI in 2022?' 'Which sku have the highest ROI in 2022? ' 'Which channel has the max ROI and Vol Lift when we run the Promotion for RTEC category?'
1	'What role do promotional strategies play in the Lift decline for Zucaritas in 2023, and how does this compare to promotional strategies employed by other brands like Pringles or Frutela?' 'Is there a particular sku that stand out as major driver behind the decrease in ROI during 2022?' 'Are there plans to enhance promotional activities specific to the HYPER to mitigate the ROI decline in 2023?'

Evaluation

Metrics

Label	Accuracy
all	1.0

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("vgarg/promo_prescriptive_15_03_2024")
# Run inference
preds = model("Which two Categories can have simultaneous Promotions?")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	8	14.9796	30

Label	Training Sample Count
0	10
1	10
2	10
3	9
4	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
0.0081	1	0.3585	-
0.4065	50	0.0558	-
0.8130	100	0.0011	-
1.2195	150	0.0007	-
1.6260	200	0.0006	-
2.0325	250	0.0003	-
2.4390	300	0.0005	-
2.8455	350	0.0003	-

Framework Versions

• Python: 3.10.12
• SetFit: 1.0.3
• Sentence Transformers: 2.5.1
• 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}
}