ardi555/setfit_mpnet_reuters21578_reducedto15

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 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

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	0.9161

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("ardi555/setfit_mpnet_reuters21578_reducedto15")
# Run inference
preds = model("The European Community Commission
confirmed it granted export licences for 59,000 tonnes of
current series white sugar at a maximum export rebate of 45.678
European Currency Units (ECUs) per 100 kilos.
    Out of this, traders in West Germany received 34,750
tonnes, in the U.K. 13,000, in Denmark 7,250 tonnes and in
France 4,000 tonnes.
 REUTER
")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	20	204.4467	1075

Training Hyperparameters

• batch_size: (8, 8)
• num_epochs: (1, 1)
• 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
• l2_weight: 0.01
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0013	1	0.2676	-
0.0667	50	0.1617	-
0.1333	100	0.0869	-
0.2	150	0.0583	-
0.2667	200	0.0766	-
0.3333	250	0.0578	-
0.4	300	0.0483	-
0.4667	350	0.0374	-
0.5333	400	0.0372	-
0.6	450	0.039	-
0.6667	500	0.0367	-
0.7333	550	0.0378	-
0.8	600	0.0299	-
0.8667	650	0.0317	-
0.9333	700	0.0308	-
1.0	750	0.0293	-

Framework Versions

• Python: 3.10.12
• SetFit: 1.1.0
• Sentence Transformers: 3.2.1
• Transformers: 4.42.2
• PyTorch: 2.5.1+cu121
• Datasets: 3.1.0
• Tokenizers: 0.19.1

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}
}