tomaarsen/modernbert-embed-base-sst2

SetFit with nomic-ai/modernbert-embed-base

This is a SetFit model that can be used for Text Classification. This SetFit model uses nomic-ai/modernbert-embed-base 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: nomic-ai/modernbert-embed-base
• Classification head: a LogisticRegression instance
• Maximum Sequence Length: 8192 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
negative	'hollow tribute ' 'accompanied by the sketchiest of captions . ' "take a complete moron to foul up a screen adaptation of oscar wilde 's classic satire "
positive	'smart and newfangled ' 'wise and powerful ' 'while the importance of being earnest offers opportunities for occasional smiles and chuckles '

Evaluation

Metrics

Label	Accuracy
all	0.8977

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("tomaarsen/modernbert-embed-base-sst2")
# Run inference
preds = model("a sequence of ridiculous shoot - 'em - up scenes . ")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	2	9.0312	29

Label	Training Sample Count
negative	16
positive	16

Training Hyperparameters

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

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0588	1	0.2389	-
1.0	17	-	0.2225
2.0	34	-	0.1584
2.9412	50	0.1076	-
3.0	51	-	0.1304
4.0	68	-	0.1293

Environmental Impact

Carbon emissions were measured using CodeCarbon.

• Carbon Emitted: 0.003 kg of CO2
• Hours Used: 0.023 hours

Training Hardware

• On Cloud: No
• GPU Model: 1 x NVIDIA GeForce RTX 3090
• CPU Model: 13th Gen Intel(R) Core(TM) i7-13700K
• RAM Size: 31.78 GB

Framework Versions

• Python: 3.9.16
• SetFit: 1.2.0.dev0
• Sentence Transformers: 3.3.1
• Transformers: 4.49.0.dev0
• PyTorch: 2.4.1+cu121
• Datasets: 2.15.0
• Tokenizers: 0.21.0

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}
}