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 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
model = SetFitModel.from_pretrained("vgarg/promo_prescriptive_gpt_28_02_2024_v1")
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}
}