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 SetFitHead 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 SetFitHead instance
Maximum Sequence Length: 512 tokens
Number of Classes: 9 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
4	"On the shop floor, his little helper helps himself to an expensive handbag from a display cabinet, then some women's designer shoes, all of which are detailed on a list. He" "He finds someone's records in a box. Someone" 'With a nod, the man hands it over to the defeated boy. Someone'
1	'A lot of people are sitting on terraces in a big field and people is walking in the entrance of a big stadium. men' 'We see a man dunk the ball twice. We' 'Several people use different methods to perform trick shots. They continue performing impressive shots'
6	'A young child is moving back and fourth on a swing while laughing and smiling to the camera. The child' 'The son of Poseidon holds the water at bay on either side of himself. Someone' 'The guy pours product in a container and uses a brush to put the liquid on the surface of a metal object. The guy'
8	'A woman smiles at the camera. The woman' 'A girl is shown several times running on a track. She' 'Someone peers out from the cabin. As she emerges, someone'
2	'As our view retracts through the star map a holographic line sets out from the gunner chair and targets hologram of the planet earth. She' 'Together, they wander a few steps without taking their eyes off of him. Now in the car as someone drives, someone' 'People stand by the wall, laughing. He'
0	'Someone steps outside and opens an umbrella. Someone halts,' 'He shows a water bottle he has along with a brush, and uses the brush to remove snow from the dash window of a car and the water to remove any excess snow left on the windshield. Once finished, he' 'She opens a small metal box on a desk and pushes a button inside. Someone'
5	'Now in the eating quarters, someone faces a husky, larged - nosed cook. The cook' 'She forces a smile, then watches him place his hand on her hand. He caresses her cheek, and she' 'Someone stirs the cookie dough in a bowl. The dough'
3	'A kid in blue shorts is vacuuming the floor. A kid in a red shirt' 'The official extends a red flag. As Master someone' 'The girls flips, then runs, flips and dismounts. The cloud'
7	'She flinches, but quickly composes herself and moves on. The crowd of onlookers' 'He eyes someone with a furrowed brow, then springs up and hurries after her. Someone and someone' 'Now, someone stands below an overcast sky. Strands of his greasy black hair'

Evaluation

Metrics

Label	Accuracy
all	0.1279

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("HelgeKn/Swag-multi-class-6")
# Run inference
preds = model("He approaches the object and reads a plaque on its side. Someone")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	6	14.3148	40

Label	Training Sample Count
0	6
1	6
2	6
3	6
4	6
5	6
6	6
7	6
8	6

Training Hyperparameters

batch_size: (16, 16)
num_epochs: (2, 2)
max_steps: -1
sampling_strategy: oversampling
num_iterations: 20
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
0.0074	1	0.303	-
0.3704	50	0.1185	-
0.7407	100	0.0656	-
1.1111	150	0.0179	-
1.4815	200	0.0109	-
1.8519	250	0.0076	-

Framework Versions

Python: 3.9.13
SetFit: 1.0.1
Sentence Transformers: 2.2.2
Transformers: 4.36.0
PyTorch: 2.1.1+cpu
Datasets: 2.15.0
Tokenizers: 0.15.0

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}
}

HelgeKn
/

Swag-multi-class-6