adriansanz/sentimentv4

SetFit with pysentimiento/robertuito-sentiment-analysis

This is a SetFit model that can be used for Text Classification. This SetFit model uses pysentimiento/robertuito-sentiment-analysis 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:

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: pysentimiento/robertuito-sentiment-analysis
• 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
0	"Aquest text és ofensiu o violent o negatiu o inapropiat o amb to irònic amb mala intenció per a un cercador de tràmits d'un ajuntament" "Aquest text és ofensiu o violent o negatiu o inapropiat o amb to irònic amb mala intenció per a un cercador de tràmits d'un ajuntament" "Aquest text és ofensiu o violent o negatiu o inapropiat o amb to irònic amb mala intenció per a un cercador de tràmits d'un ajuntament"
1	"Aquest text és valid per a un cercador de tràmits d'un ajuntament" "Aquest text és valid per a un cercador de tràmits d'un ajuntament" "Aquest text és valid per a un cercador de tràmits d'un ajuntament"

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("adriansanz/sentimentv4")
# Run inference
preds = model("Pagar la taxa de residus en línia")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	5	15.1607	25

Label	Training Sample Count
0	28
1	28

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: True

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0098	1	0.2734	-
0.4902	50	0.0039	-
0.9804	100	0.0016	-
1.0	102	-	0.0014
1.4706	150	0.0003	-
1.9608	200	0.0004	-
2.0	204	-	0.0004
2.4510	250	0.0004	-
2.9412	300	0.0004	-
3.0	306	-	0.0003
3.4314	350	0.0002	-
3.9216	400	0.0003	-
4.0	408	-	0.0002

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.12
• SetFit: 1.0.3
• Sentence Transformers: 3.0.1
• Transformers: 4.39.0
• PyTorch: 2.4.0+cu121
• Datasets: 2.21.0
• 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}
}