metadata

library_name: setfit
tags:
  - setfit
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
widget:
  - text: 'VALID THRU 02/10/2015 '
  - text: Les chaines Universal+
  - text: "\tminute = second * 60,"
  - text: ': Session'
  - text: Phil Klay
pipeline_tag: text-classification
inference: true
base_model: sentence-transformers/paraphrase-mpnet-base-v2
model-index:
  - name: SetFit with sentence-transformers/paraphrase-mpnet-base-v2
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: accuracy
            value: 0.87
            name: Accuracy
          - type: precision
            value: 0.8452380952380952
            name: Precision
          - type: recall
            value: 0.8452380952380952
            name: Recall
          - type: f1
            value: 0.8452380952380952
            name: F1

SetFit with sentence-transformers/paraphrase-mpnet-base-v2

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/paraphrase-mpnet-base-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-mpnet-base-v2
Classification head: a LogisticRegression instance
Maximum Sequence Length: 512 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
True	'ace} UNIV FEATURING CHAMILLIONAIRE ©) ' 'ee — Pra yon t “pink you are S© Mer ' 'ae PTAA Be hs B corms of Rermee '
False	'mmmmmmmmmmlli' 'Manage Cookie Preferences' 'Supply Partners'

Evaluation

Metrics

Label	Accuracy	Precision	Recall	F1
all	0.87	0.8452	0.8452	0.8452

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(": Session")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	1	8.4575	265

Label	Training Sample Count
False	384
True	416

Training Hyperparameters

batch_size: (16, 2)
num_epochs: (1, 16)
max_steps: -1
sampling_strategy: oversampling
num_iterations: 20
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
run_name: PG-OCR-test-2
eval_max_steps: -1
load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0005	1	0.4077	-
0.025	50	0.2689	-
0.05	100	0.2505	-
0.075	150	0.1787	-
0.1	200	0.1602	-
0.125	250	0.1381	-
0.15	300	0.1753	-
0.175	350	0.018	-
0.2	400	0.024	-
0.225	450	0.0863	-
0.25	500	0.0504	-
0.275	550	0.0204	-
0.3	600	0.0124	-
0.325	650	0.066	-
0.35	700	0.1305	-
0.375	750	0.0599	-
0.4	800	0.0323	-
0.425	850	0.0039	-
0.45	900	0.0131	-
0.475	950	0.004	-
0.5	1000	0.0016	-
0.525	1050	0.0139	-
0.55	1100	0.0189	-
0.575	1150	0.0533	-
0.6	1200	0.0645	-
0.625	1250	0.0005	-
0.65	1300	0.0111	-
0.675	1350	0.002	-
0.7	1400	0.0082	-
0.725	1450	0.0009	-
0.75	1500	0.0018	-
0.775	1550	0.0003	-
0.8	1600	0.0108	-
0.825	1650	0.0009	-
0.85	1700	0.0003	-
0.875	1750	0.0009	-
0.9	1800	0.0038	-
0.925	1850	0.0406	-
0.95	1900	0.0012	-
0.975	1950	0.0024	-
1.0	2000	0.0004	-

Framework Versions

Python: 3.11.0
SetFit: 1.0.3
Sentence Transformers: 2.3.0
Transformers: 4.37.2
PyTorch: 2.2.1+cu121
Datasets: 2.16.1
Tokenizers: 0.15.1

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}
}