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: 2 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	'پاکستان کا قومی پھول چنبیلی ہے۔' 'نہاری لاہور کی خاص سوغات ہے۔' 'وقت کسی کا انتظار نہیں کرتا۔'
0	'اس خیال سے کہ' 'اس نے مجھے دعوت دی' 'اس نے ایک اور کوشش'

Evaluation

Metrics

Label	Accuracy
all	1.0

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("setfit_model_id")
# Run inference
preds = model("جب تک تم اپنا سبق")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	2	6.0774	13

Label	Training Sample Count
0	1016
1	1064

Training Hyperparameters

batch_size: (32, 32)
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
l2_weight: 0.01
seed: 42
eval_max_steps: -1
load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0004	1	0.3724	-
0.0192	50	0.3204	-
0.0385	100	0.2491	-
0.0577	150	0.1363	-
0.0769	200	0.0216	-
0.0962	250	0.0049	-
0.1154	300	0.0019	-
0.1346	350	0.0006	-
0.1538	400	0.0005	-
0.1731	450	0.0002	-
0.1923	500	0.0002	-
0.2115	550	0.0001	-
0.2308	600	0.0001	-
0.25	650	0.0001	-
0.2692	700	0.0001	-
0.2885	750	0.0001	-
0.3077	800	0.0002	-
0.3269	850	0.0002	-
0.3462	900	0.0001	-
0.3654	950	0.0001	-
0.3846	1000	0.0001	-
0.4038	1050	0.0001	-
0.4231	1100	0.0001	-
0.4423	1150	0.0001	-
0.4615	1200	0.0	-
0.4808	1250	0.0	-
0.5	1300	0.0	-
0.5192	1350	0.0	-
0.5385	1400	0.0	-
0.5577	1450	0.0	-
0.5769	1500	0.0	-
0.5962	1550	0.0	-
0.6154	1600	0.0	-
0.6346	1650	0.0	-
0.6538	1700	0.0	-
0.6731	1750	0.0	-
0.6923	1800	0.0	-
0.7115	1850	0.0	-
0.7308	1900	0.0	-
0.75	1950	0.0	-
0.7692	2000	0.0	-
0.7885	2050	0.0	-
0.8077	2100	0.0	-
0.8269	2150	0.0	-
0.8462	2200	0.0	-
0.8654	2250	0.0	-
0.8846	2300	0.0	-
0.9038	2350	0.0	-
0.9231	2400	0.0	-
0.9423	2450	0.0	-
0.9615	2500	0.0	-
0.9808	2550	0.0	-
1.0	2600	0.0	-
1.0192	2650	0.0	-
1.0385	2700	0.0	-
1.0577	2750	0.0	-
1.0769	2800	0.0	-
1.0962	2850	0.0	-
1.1154	2900	0.0	-
1.1346	2950	0.0	-
1.1538	3000	0.0	-
1.1731	3050	0.0	-
1.1923	3100	0.0	-
1.2115	3150	0.0	-
1.2308	3200	0.0	-
1.25	3250	0.0	-
1.2692	3300	0.0	-
1.2885	3350	0.0	-
1.3077	3400	0.0	-
1.3269	3450	0.0	-
1.3462	3500	0.0	-
1.3654	3550	0.0	-
1.3846	3600	0.0	-
1.4038	3650	0.0	-
1.4231	3700	0.0	-
1.4423	3750	0.0	-
1.4615	3800	0.0	-
1.4808	3850	0.0	-
1.5	3900	0.0	-
1.5192	3950	0.0	-
1.5385	4000	0.0	-
1.5577	4050	0.0	-
1.5769	4100	0.0	-
1.5962	4150	0.0	-
1.6154	4200	0.0	-
1.6346	4250	0.0	-
1.6538	4300	0.0	-
1.6731	4350	0.0	-
1.6923	4400	0.0	-
1.7115	4450	0.0	-
1.7308	4500	0.0	-
1.75	4550	0.0	-
1.7692	4600	0.0	-
1.7885	4650	0.0	-
1.8077	4700	0.0	-
1.8269	4750	0.0	-
1.8462	4800	0.0	-
1.8654	4850	0.0	-
1.8846	4900	0.0	-
1.9038	4950	0.0	-
1.9231	5000	0.0	-
1.9423	5050	0.0	-
1.9615	5100	0.0	-
1.9808	5150	0.0	-
2.0	5200	0.0	-

Framework Versions

Python: 3.11.13
SetFit: 1.1.3
Sentence Transformers: 5.1.0
Transformers: 4.55.0
PyTorch: 2.6.0+cu124
Datasets: 4.0.0
Tokenizers: 0.21.4

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}
}

PuristanLabs1
/

Urdu_TurnDetection