Edit model card

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
6
  • 'Are there any major whitespace opportunity in terms of Categories x Pack Segments in Cuernavaca?'
  • 'In Colas MS which packsegment is not dominated by KOF in TT HM Orizaba 2022? At what price point we can launch an offering'
  • 'I want to launch a new pack type in csd for kof. Tell me what'
2
  • 'Since which quarter, the share decline started happening for Colas MS in Cuernavaca?'
  • 'What is the Market share for Resto in colas MS at each size groups in TT HM Orizaba in 2022'
  • 'How is the Jumex market share have changed over last three year at quaterly level in TT HM from 2019-2022'
0
  • 'what are the top brands contributing to share loss for KOF in TT OP Cuernavaca in 2021'
  • 'Which are the top contributing categoriesXconsumo to the share loss for KOF in Cuernavaca in 2022?'
  • 'Which packs have driven the shares for the competition in Colas in FY 21-22?'
10
  • 'Which pack segment shows opportunities to drive my market share in NCBS Colas SS?'
  • 'How can I strategically expand my presence in specific packaging segments to enhance market penetration in CSD Sabores?'
  • 'What are my priority pack segments to gain share in AGUA Colas SS?'
5
  • 'Where should I play in terms\xa0of flavor in Sabores SS?'
  • 'What are the untapped opportunities in Graffon?'
  • 'What areas should I focus on to grow my market presence?'
7
  • 'What are the upsizing benefits being offered in Coca-Cola NR Packs? Is there any recommendation to improve it?'
  • 'Is Fanta a premium brand? How premium are its offerings as compared to other brands in Sabores?'
  • 'Is there an opportunity to premiumize any offerings for coca-cola?'
9
  • 'Which industries to prioritize to gain share in AGUA in Cuernavaca?'
  • 'What measures can be taken to maximize headroom in the AGUA market?'
  • 'List headroom opportunities for AGUA'
11
  • 'How to win in the prioritized pack segments in Colas MS ?'
  • 'How should KOF gain share in Colas MS in Cuernavaca? '
  • 'How can I gain share in CSD Colas MS in Cuernavaca'
8
  • 'What is the price range for CSD in TT HM?'
  • 'what is PCO share for different price bracket in TT OP 2021'
  • 'distribution wise, which non csd skus are doing the best?'
3
  • 'What is the difference in offerings for KOF vs the key competitors in xx price bracket within CSD Colas in TT HM?'
  • 'How should KOF gain share in <10 price bracket for NCB in TT HM'
  • 'What are my pricing opportuities?'
1
  • "What are the primary factors behind Danone's market share decline in Orizaba for FY21-22?"
  • 'Why is Resto losing share in Cuernavaca Colas SS RET Original?'
  • 'What are the main factors contributing to the share gain of Jumex in Still Drinks MS in Orizaba for FY 2022?'
4
  • 'How has the csd industry evolved in the last two years?'
  • 'What is the industry mix for all KOF brands in TT HM Cuernavaca in 2022'
  • 'What is the change in industry mix for coca-cola in TT HM Orizaba in 2021 to 2022'

Evaluation

Metrics

Label Accuracy
all 0.25

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/fw_identification_model_e5_large_v5_12_02_24")
# Run inference
preds = model("Why is KOF losing share in Cuernavaca Colas MS RET Original?")

Training Details

Training Set Metrics

Training set Min Median Max
Word count 4 13.7632 32
Label Training Sample Count
0 10
1 10
2 10
3 8
4 10
5 10
6 10
7 10
8 10
9 10
10 10
11 6

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
0.0035 1 0.3488 -
0.1754 50 0.1594 -
0.3509 100 0.0872 -
0.5263 150 0.0065 -
0.7018 200 0.0033 -
0.8772 250 0.0018 -
1.0526 300 0.001 -
1.2281 350 0.0008 -
1.4035 400 0.0008 -
1.5789 450 0.0006 -
1.7544 500 0.0005 -
1.9298 550 0.0005 -
2.1053 600 0.0005 -
2.2807 650 0.0004 -
2.4561 700 0.0003 -
2.6316 750 0.0004 -
2.8070 800 0.0004 -
2.9825 850 0.0004 -

Framework Versions

  • Python: 3.10.12
  • SetFit: 1.0.3
  • Sentence Transformers: 2.3.1
  • Transformers: 4.35.2
  • PyTorch: 2.1.0+cu121
  • Datasets: 2.17.0
  • Tokenizers: 0.15.1

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}
}
Downloads last month
1
Safetensors
Model size
560M params
Tensor type
F32
·

Finetuned from

Evaluation results