amplyfi/gte-small_all-labels_multilabel

SetFit with thenlper/gte-small

This is a SetFit model that can be used for Text Classification. This SetFit model uses thenlper/gte-small as the Sentence Transformer embedding model. A OneVsRestClassifier 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: thenlper/gte-small
• Classification head: a OneVsRestClassifier instance
• Maximum Sequence Length: 512 tokens

Model Sources

• Repository: SetFit on GitHub
• Paper: Efficient Few-Shot Learning Without Prompts
• Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts

Evaluation

Metrics

Label	Accuracy
all	0.4865

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("amplyfi/gte-small_all-labels_multilabel")
# Run inference
preds = model("LATAM Unveils New Dreamliner Economy Cabin Design")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	4	9.9616	30

Training Hyperparameters

• batch_size: (16, 16)
• num_epochs: (2, 2)
• max_steps: -1
• sampling_strategy: oversampling
• num_iterations: 5
• 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
• l2_weight: 0.01
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0018	1	0.3005	-
0.0903	50	0.2933	-
0.1805	100	0.2219	-
0.2708	150	0.1568	-
0.3610	200	0.1334	-
0.4513	250	0.1204	-
0.5415	300	0.1215	-
0.6318	350	0.1154	-
0.7220	400	0.1065	-
0.8123	450	0.0935	-
0.9025	500	0.0892	-
0.9928	550	0.0807	-
1.0830	600	0.0776	-
1.1733	650	0.0716	-
1.2635	700	0.06	-
1.3538	750	0.0677	-
1.4440	800	0.0607	-
1.5343	850	0.065	-
1.6245	900	0.0593	-
1.7148	950	0.0622	-
1.8051	1000	0.064	-
1.8953	1050	0.0624	-
1.9856	1100	0.0667	-

Framework Versions

• Python: 3.10.12
• SetFit: 1.1.0
• Sentence Transformers: 3.3.1
• Transformers: 4.42.2
• PyTorch: 2.5.1+cu124
• Datasets: 3.1.0
• 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}
}