vgarg/query_type_classifier_v2

SetFit with sentence-transformers/all-MiniLM-L6-v2

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/all-MiniLM-L6-v2 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: sentence-transformers/all-MiniLM-L6-v2
• Classification head: a LogisticRegression instance
• Maximum Sequence Length: 256 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
0	'Why is Coca-Cola losing share?' 'which pack segment is contributing most to share change for Resto in Orizaba NCBs' 'What is KOF market share in 2021, and how has it changed over the past year For TT OP Cuernavaca'
1	'share the sales for Breezefizz en 2023 jun' 'what is ROI trend for Fizzy drinks?' 'What is the market share of KOF in Orizaba for FY22?'

Evaluation

Metrics

Label	Accuracy
all	0.8667

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/query_type_classifier_v2")
# Run inference
preds = model("How has the csd industry evolved in the last two years?")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	5	12.9324	32

Label	Training Sample Count
0	42
1	32

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
0.0054	1	0.3438	-
0.2703	50	0.2209	-
0.5405	100	0.0806	-
0.8108	150	0.0048	-
1.0811	200	0.0048	-
1.3514	250	0.0025	-
1.6216	300	0.0026	-
1.8919	350	0.0022	-
2.1622	400	0.0017	-
2.4324	450	0.0009	-
2.7027	500	0.0015	-
2.9730	550	0.001	-

Framework Versions

• Python: 3.12.2
• SetFit: 1.0.3
• Sentence Transformers: 2.6.1
• Transformers: 4.39.3
• PyTorch: 2.2.2+cpu
• 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}
}