Edit model card

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 SetFitHead 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 Sources

Model Labels

Label Examples
3
  • "Usually there are generation problems , sons do n't understand parents and vicecersa , but dialoging and listening emotions and facts , everyone can have another point of view ."
  • 'While youngsters use their time trying to get concerned the oldest people from de village about the importance of the care of our surroundings , middle - aged people planted many trees around the village and cleaned the floor of our public places making a more attractive place to live than we used to have .'
  • 'As an example , if you are able to get alone with your travel companion could enjoy each moment of the trip , exchange some pictures , eat together , and visit places with common interest such as museums or malls .'
5
  • 'Michael get away from there .'
  • 'I guess that in our future there are no helicopters , and not even cars .'
  • 'In addition , to decrease the risk of negative comments or posts , Facebook and Twitter would improve their futures to solve the less personal privacy problem .'
4
  • 'Something that they don know was that the whole thing was a movie !'
  • 'Yours Sincerely .'
  • "stop shouting . do n't shout ."
2
  • 'X " admitted to a state psychiatric hospital after being found not competent to stand trial on charges of stalking harassment , trespassing and telephone harassment " ( pp .'
  • 'It is a job with a lot of interesting aspects ,'
  • 'On balance , learning foreign languages is very positive on different aspect , so if you have the positivity of learning a new language do it , because it will bring you many benefits .'
6
  • 'In addition , she has no blithe memory in her childhood .'
  • 'The aim of this report is to give you my personal point of view of the course I did in your branch in Madrid last month .'
  • 'I know you are searching for a flat to live for the whole next year .'
0
  • 'In China , English is took to be a foreign language which many students choose to learn .'
  • 'No one can deny that the pollution issue is one of the utmost important thing which should be prevented .'
  • 'The third section is to print the prepared bank notes .'
1
  • 'They use at least one hour to learn English knowledge a day .'
  • 'If you want to see that movie , you need to watch the first 3 movies before to understand it .'
  • 'Next to go would be , students get used to relax by having no study and homework in the long vacation .'
7
  • 'To start with , there are a wide range of troublesome it maybe leadding to this phenomeon .'
  • 'Secondly , the families could give you some advice about how to deal with the things which will cause trouble .'
  • 'I been twelve years practice volleyball and because of it I knew lot of people who help me to grow up in the sport and life .'

Evaluation

Metrics

Label Accuracy
all 0.1554

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("HelgeKn/BEA2019-multi-class-10")
# Run inference
preds = model("Had 12 years old .")

Training Details

Training Set Metrics

Training set Min Median Max
Word count 3 21.3375 56
Label Training Sample Count
0 10
1 10
2 10
3 10
4 10
5 10
6 10
7 10

Training Hyperparameters

  • batch_size: (16, 16)
  • num_epochs: (2, 2)
  • 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
0.005 1 0.2242 -
0.25 50 0.1786 -
0.5 100 0.1831 -
0.75 150 0.0221 -
1.0 200 0.0127 -
1.25 250 0.0064 -
1.5 300 0.0045 -
1.75 350 0.0028 -
2.0 400 0.002 -

Framework Versions

  • Python: 3.9.13
  • SetFit: 1.0.1
  • Sentence Transformers: 2.2.2
  • Transformers: 4.36.0
  • PyTorch: 2.1.1+cpu
  • Datasets: 2.15.0
  • Tokenizers: 0.15.0

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}
}
Downloads last month
6
Safetensors
Model size
109M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for HelgeKn/BEA2019-multi-class-10

Finetuned
(247)
this model

Evaluation results