metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - accuracy
widget:
  - text: ' i still dont know what we would do though'
  - text: ' where`d you go!'
  - text: ' Thank you!  I`m working on `s'
  - text: Terminator Salvation... by myself.
  - text: ' lol man i got 2 1 /2 hrs an iont how i woulda made it wit out my ramen noodles and t.v. Time'
pipeline_tag: text-classification
inference: true
base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
model-index:
  - name: SetFit with sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 0.77
            name: Accuracy

SetFit with sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 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/paraphrase-multilingual-MiniLM-L12-v2
Classification head: a LogisticRegression instance
Maximum Sequence Length: 128 tokens
Number of Classes: 3 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
0	'چه سودایی که سر همینا از دست دادم😂' 'خو فارسی بنویس بفهمه 😂😂😂😂😂' 'اینجا ایران همین سایتا هم\u200cزیادی..نیازی به بررسی ندارن...کلا دوسداریم به همچی ایراد بگیریم.'
1	'کد کارت مشکی NHKDKI' 'اتفاقا مسیولیت بیشتری برات میاره و درگیریات بیشتر میشه برای هدفی که داری' 'من میخام شروع کنم،اورج بفروشم یا فیک؟فیک ارزونتره ولی فیکه.اورجینال هم ک گرون تره ؟بنظرت اورج میخرن؟؟'
2	'🔥🔥🔥🔥' '😂😂😂' 'چه قدر عالی وخفن 🔥🔥'

Evaluation

Metrics

Label	Accuracy
all	0.77

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("ehsanhallo/setfit-paraphrase-multilingual-MiniLM-L12-v2-ig-fa")
# Run inference
preds = model(" where`d you go!")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	1	7.0	75

Label	Training Sample Count
0	31
1	131
2	364

Training Hyperparameters

batch_size: (32, 16)
num_epochs: (2, 4)
max_steps: -1
sampling_strategy: oversampling
body_learning_rate: (2e-05, 5e-06)
head_learning_rate: 0.002
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: True

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0002	1	0.1854	-
0.0529	250	0.0626	-
0.1058	500	0.0034	0.2484
0.1588	750	0.0029	-
0.2117	1000	0.001	0.1899
0.2646	1250	0.0001	-
0.3175	1500	0.0001	0.1849
0.3704	1750	0.0001	-
0.4234	2000	0.0001	0.1876
0.4763	2250	0.0001	-
0.5292	2500	0.0	0.1888
0.5821	2750	0.0001	-
0.6351	3000	0.0	0.1885
0.6880	3250	0.0	-
0.7409	3500	0.0	0.1915
0.7938	3750	0.0	-
0.8467	4000	0.0	0.1947
0.8997	4250	0.0	-
0.9526	4500	0.0	0.1986
1.0055	4750	0.0	-
1.0584	5000	0.0	0.207
1.1113	5250	0.0	-
1.1643	5500	0.0	0.2078
1.2172	5750	0.0	-
1.2701	6000	0.0	0.2096
1.3230	6250	0.0	-
1.3760	6500	0.0	0.2095
1.4289	6750	0.0	-
1.4818	7000	0.0	0.2103
1.5347	7250	0.0	-
1.5876	7500	0.0	0.2133
1.6406	7750	0.0	-
1.6935	8000	0.0	0.2154
1.7464	8250	0.0	-
1.7993	8500	0.0	0.2141
1.8522	8750	0.0	-
1.9052	9000	0.0	0.2141
1.9581	9250	0.0	-

The bold row denotes the saved checkpoint.

Framework Versions

Python: 3.10.12
SetFit: 1.0.1
Sentence Transformers: 2.2.2
Transformers: 4.35.2
PyTorch: 2.1.0+cu121
Datasets: 2.16.1
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}
}