clareandme/multilabel-setfit-model-v2

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

This is a SetFit model trained on the clareandme/multiLabelClassification dataset that can be used for Text Classification. This SetFit model uses sentence-transformers/paraphrase-mpnet-base-v2 as the Sentence Transformer embedding model. A OneVsRestClassifier 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 OneVsRestClassifier instance
• Maximum Sequence Length: 512 tokens
• Training Dataset: clareandme/multiLabelClassification

Model Sources

• Repository: SetFit on GitHub
• Paper: Efficient Few-Shot Learning Without Prompts
• Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts

Evaluation

Metrics

Label	Accuracy
all	0.3214

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("clareandme/multilabel-setfit-model-v2")
# Run inference
preds = model("The AI and user have a conversation about ways to manage and cope with the loss of a loved partner.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	10	33.475	68

Training Hyperparameters

• batch_size: (16, 16)
• num_epochs: (4, 4)
• 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
• eval_max_steps: -1
• load_best_model_at_end: True

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0033	1	0.1896	-
0.1667	50	0.2453	-
0.3333	100	0.1182	-
0.5	150	0.2458	-
0.6667	200	0.0401	-
0.8333	250	0.0763	-
1.0	300	0.0915	0.1302
1.1667	350	0.1105	-
1.3333	400	0.0715	-
1.5	450	0.126	-
1.6667	500	0.1074	-
1.8333	550	0.0781	-
2.0	600	0.0608	0.1102
2.1667	650	0.1246	-
2.3333	700	0.0791	-
2.5	750	0.0662	-
2.6667	800	0.0906	-
2.8333	850	0.0763	-
3.0	900	0.0656	0.1026
3.1667	950	0.0476	-
3.3333	1000	0.1086	-
3.5	1050	0.0903	-
3.6667	1100	0.0552	-
3.8333	1150	0.0335	-
4.0	1200	0.0689	0.1028

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.12
• SetFit: 1.0.3
• Sentence Transformers: 3.0.1
• Transformers: 4.39.0
• PyTorch: 2.3.1+cu121
• Datasets: 2.21.0
• 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}
}