tomaarsen/setfit-paraphrase-mpnet-base-v2-sst2-8-shot

SetFit with sentence-transformers/paraphrase-mpnet-base-v2 on sst2

This is a SetFit model trained on the sst2 dataset that can be used for Text Classification. This SetFit model uses sentence-transformers/paraphrase-mpnet-base-v2 as the Sentence Transformer embedding model. For classification, it uses a LogisticRegression instance.

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
• Training Dataset: sst2
• Language: en
• License: apache-2.0

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
negative	'stale and uninspired . ' "the film 's considered approach to its subject matter is too calm and thoughtful for agitprop , and the thinness of its characterizations makes it a failure as straight drama . ' " "that their charm does n't do a load of good "
positive	"broomfield is energized by volletta wallace 's maternal fury , her fearlessness " 'flawless ' 'insightfully written , delicately performed '

Evaluation

Metrics

Label	Accuracy
all	0.8588

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 🤗 Hub
model = SetFitModel.from_pretrained("tomaarsen/setfit-paraphrase-mpnet-base-v2-sst2-8-shot")
# Run inference
preds = model("a fast , funny , highly enjoyable movie . ")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	2	11.4375	33

Label	Training Sample Count
negative	8
positive	8

Training Hyperparameters

• batch_size: (16, 16)
• num_epochs: (10, 10)
• max_steps: -1
• sampling_strategy: oversampling
• 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
• load_best_model_at_end: True

Training Results

Epoch	Step	Training Loss	Validation Loss
0.1111	1	0.2126	-
1.1111	10	0.1604	-
2.2222	20	0.0224	0.1761
3.3333	30	0.0039	-
4.4444	40	0.0029	0.1935
5.5556	50	0.0026	-
6.6667	60	0.0008	0.1944
7.7778	70	0.0009	-
8.8889	80	0.0027	0.1941
10.0	90	0.0004	-

• The bold row denotes the saved checkpoint.

Environmental Impact

Carbon emissions were measured using CodeCarbon.

• Carbon Emitted: 0.003 kg of CO2
• Hours Used: 0.027 hours

Training Hardware

• On Cloud: No
• GPU Model: 1 x NVIDIA GeForce RTX 3090
• CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
• RAM Size: 31.78 GB

Framework Versions

• Python: 3.9.16
• SetFit: 1.0.0.dev0
• Sentence Transformers: 2.2.2
• Transformers: 4.29.0
• PyTorch: 1.13.1+cu117
• Datasets: 2.15.0
• Tokenizers: 0.13.3

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}
}