metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
base_model: sentence-transformers/all-roberta-large-v1
metrics:
  - accuracy
widget:
  - text: ' I would do this too but then I run the risk of meeting someone I know lol'
  - text: ' That''s kind of the nature of my volunteer work, but you could volunteer with a food bank or boys  and girls club, which would involve more social interaction Just breaking that cycle by going for a short walk around the neighbourhood is a good idea'
  - text: ' Your body is trying to reduce weight by throwing up and having to go to the bathroon, in case you need to run from the "enemy", so you''ll be lighter'
  - text: ' But even then, I didn''t have any other problems outside school I still had no friends at European school, I haven''t had any walks which I had constantly with my friends back in Ukraine'
  - text: ' I like art and nature but you can’t really talk about those for more than a few seconds'
pipeline_tag: text-classification
inference: true
model-index:
  - name: SetFit with sentence-transformers/all-roberta-large-v1
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 0.3416666666666667
            name: Accuracy

SetFit with sentence-transformers/all-roberta-large-v1

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/all-roberta-large-v1 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:

Fine-tuning a Sentence Transformer with contrastive learning.
Training a classification head with features from the fine-tuned Sentence Transformer.

Model Details

Model Description

Model Type: SetFit
Sentence Transformer body: sentence-transformers/all-roberta-large-v1
Classification head: a LogisticRegression instance
Maximum Sequence Length: 256 tokens
Number of Classes: 4 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
1.0	' and i do biking, i bike for atleast 20mins and towards the end i feel anxious free, less socially anxious too and i do biking, i bike for atleast 20mins and towards the end i feel anxious free, less socially anxious too' " That's kind of the nature of my volunteer work, but you could volunteer with a food bank or boys and girls club, which would involve more social interaction Just breaking that cycle by going for a short walk around the neighbourhood is a good idea"
2.0	" I didn't go outside too much" ' I like art and nature but you can’t really talk about those for more than a few seconds'
3.0	" I don't know anyone in the city, I don't think I have enough courage to go outside alone" " But even then, I didn't have any other problems outside school I still had no friends at European school, I haven't had any walks which I had constantly with my friends back in Ukraine"
0.0	' Your body is trying to reduce weight by throwing up and having to go to the bathroon, in case you need to run from the "enemy", so you'll be lighter' ' I would do this too but then I run the risk of meeting someone I know lol'

Evaluation

Metrics

Label	Accuracy
all	0.3417

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("Omar-Nasr/setfitmodel")
# Run inference
preds = model(" I would do this too but then I run the risk of meeting someone I know lol")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	7	27.375	47

Label	Training Sample Count
0.0	2
1.0	2
2.0	2
3.0	2

Training Hyperparameters

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

Training Results

Epoch	Step	Training Loss	Validation Loss
0.3333	1	0.0708	-

Framework Versions

Python: 3.10.13
SetFit: 1.0.3
Sentence Transformers: 2.7.0
Transformers: 4.38.1
PyTorch: 2.1.2
Datasets: 2.19.0
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}
}