Ghofranem/setfit-paraphrase-multilingual-MiniLM-L12-v2-ed-fr

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 OneVsRestClassifier 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 Type: SetFit
• Sentence Transformer body: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
• Classification head: a OneVsRestClassifier instance
• Maximum Sequence Length: 128 tokens

Model Sources

• Repository: SetFit on GitHub
• Paper: Efficient Few-Shot Learning Without Prompts
• Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts

Evaluation

Metrics

Label	Accuracy
all	0.7861

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("Ghofranem/setfit-paraphrase-multilingual-MiniLM-L12-v2-ed-fr")
# Run inference
preds = model("Lire \"l'anorexie une addiction au plaisir de maigrir\" sciences et avenir")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	4	68.8313	694

Training Hyperparameters

• batch_size: (16, 16)
• num_epochs: (1, 1)
• max_steps: -1
• sampling_strategy: oversampling
• num_iterations: 5
• 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
0.0010	1	0.3025	-
0.0498	50	0.3227	-
0.0996	100	0.1451	-
0.1494	150	0.0662	-
0.1992	200	0.1114	-
0.2490	250	0.0723	-
0.2988	300	0.0375	-
0.3486	350	0.0252	-
0.3984	400	0.0497	-
0.4482	450	0.087	-
0.4980	500	0.0584	-
0.5478	550	0.0758	-
0.5976	600	0.0624	-
0.6474	650	0.0572	-
0.6972	700	0.0726	-
0.7470	750	0.0012	-
0.7968	800	0.0052	-
0.8466	850	0.0309	-
0.8964	900	0.0713	-
0.9462	950	0.0043	-
0.9960	1000	0.0049	-

Framework Versions

• Python: 3.10.12
• SetFit: 1.0.3
• Sentence Transformers: 2.5.1
• Transformers: 4.38.2
• PyTorch: 2.2.1+cu121
• Datasets: 2.18.0
• 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}
}