metadata

base_model: sentence-transformers/all-MiniLM-L6-v2
library_name: setfit
metrics:
  - f1
pipeline_tag: text-classification
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
widget: []
inference: true
model-index:
  - name: SetFit with sentence-transformers/all-MiniLM-L6-v2
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: f1
            value: 0.12903225806451613
            name: F1

SetFit with sentence-transformers/all-MiniLM-L6-v2

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/all-MiniLM-L6-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/all-MiniLM-L6-v2
Classification head: a LogisticRegression instance
Maximum Sequence Length: 256 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

Evaluation

Metrics

Label	F1
all	0.1290

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("Zlovoblachko/dimension2_w_thesis_setfit")
# Run inference
preds = model("I loved the spiderman movie!")

Training Details

Training Hyperparameters

batch_size: (16, 16)
num_epochs: (1, 1)
max_steps: -1
sampling_strategy: oversampling
body_learning_rate: (0.00031763046129120506, 0.00031763046129120506)
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: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0007	1	0.304	-
0.0347	50	0.2656	-
0.0694	100	0.2733	-
0.1042	150	0.268	-
0.1389	200	0.2712	-
0.1736	250	0.2726	-
0.2083	300	0.2758	-
0.2431	350	0.2807	-
0.2778	400	0.2877	-
0.3125	450	0.2641	-
0.3472	500	0.2761	-
0.3819	550	0.2739	-
0.4167	600	0.2565	-
0.4514	650	0.2813	-
0.4861	700	0.2761	-
0.5208	750	0.2749	-
0.5556	800	0.2585	-
0.5903	850	0.2737	-
0.625	900	0.2807	-
0.6597	950	0.2782	-
0.6944	1000	0.2736	-
0.7292	1050	0.28	-
0.7639	1100	0.2821	-
0.7986	1150	0.2755	-
0.8333	1200	0.2743	-
0.8681	1250	0.2634	-
0.9028	1300	0.2779	-
0.9375	1350	0.2744	-
0.9722	1400	0.2816	-

Framework Versions

Python: 3.10.12
SetFit: 1.1.0
Sentence Transformers: 3.2.1
Transformers: 4.44.2
PyTorch: 2.5.0+cu121
Datasets: 3.0.2
Tokenizers: 0.19.1

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}
}