spaly99/my-setfit-model-dataset-PG-OCR-2

SetFit with sentence-transformers/paraphrase-mpnet-base-v2

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/paraphrase-mpnet-base-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/paraphrase-mpnet-base-v2
• Classification head: a LogisticRegression instance
• Maximum Sequence Length: 512 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
True	'715-462-3626 Open Daily @ 7am ' ': HTTP' 'Zmywarka modutowa. Pasuje wszedzie. '
False	'(retencja w dniach: 180)' 'Bosnia and Herzegovina' 'Arruda dos Vinhos'

Evaluation

Metrics

Label	Accuracy	Precision	Recall	F1
all	0.8625	0.825	0.8919	0.8571

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("setfit_model_id")
# Run inference
preds = model(": Session")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	1	8.5094	146

Label	Training Sample Count
False	157
True	163

Training Hyperparameters

• batch_size: (16, 2)
• num_epochs: (1, 16)
• max_steps: -1
• sampling_strategy: oversampling
• num_iterations: 20
• body_learning_rate: (2e-05, 1e-05)
• head_learning_rate: 0.01
• loss: CosineSimilarityLoss
• distance_metric: cosine_distance
• margin: 0.25
• end_to_end: False
• use_amp: False
• warmup_proportion: 0.1
• seed: 42
• run_name: PG-OCR-test-2
• eval_max_steps: -1
• load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0013	1	0.2507	-
0.0625	50	0.0961	-
0.125	100	0.2456	-
0.1875	150	0.0709	-
0.25	200	0.0213	-
0.3125	250	0.0193	-
0.375	300	0.0827	-
0.4375	350	0.015	-
0.5	400	0.0039	-
0.5625	450	0.0087	-
0.625	500	0.0064	-
0.6875	550	0.001	-
0.75	600	0.0236	-
0.8125	650	0.0553	-
0.875	700	0.0661	-
0.9375	750	0.0006	-
1.0	800	0.0604	-

Framework Versions

• Python: 3.11.0
• SetFit: 1.0.3
• Sentence Transformers: 2.3.0
• Transformers: 4.37.2
• PyTorch: 2.2.1+cu121
• Datasets: 2.16.1
• 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}
}