Zlovoblachko/dim1_setfit

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:

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: 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	0.8182

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/dim1_setfit")
# Run inference
preds = model("I loved the spiderman movie!")

Training Details

Training Hyperparameters

• batch_size: (16, 16)
• num_epochs: (2, 2)
• max_steps: -1
• sampling_strategy: oversampling
• body_learning_rate: (0.00023323617397037305, 0.00023323617397037305)
• 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
0.0011	1	0.2497	-
0.0541	50	0.2784	-
0.1081	100	0.2797	-
0.1622	150	0.2886	-
0.2162	200	0.2863	-
0.2703	250	0.2751	-
0.3243	300	0.2934	-
0.3784	350	0.2857	-
0.4324	400	0.293	-
0.4865	450	0.2791	-
0.5405	500	0.2985	-
0.5946	550	0.2998	-
0.6486	600	0.2822	-
0.7027	650	0.2849	-
0.7568	700	0.2877	-
0.8108	750	0.2818	-
0.8649	800	0.2854	-
0.9189	850	0.2986	-
0.9730	900	0.2956	-
1.0270	950	0.292	-
1.0811	1000	0.2881	-
1.1351	1050	0.2894	-
1.1892	1100	0.29	-
1.2432	1150	0.2783	-
1.2973	1200	0.2601	-
1.3514	1250	0.3014	-
1.4054	1300	0.2877	-
1.4595	1350	0.2998	-
1.5135	1400	0.2822	-
1.5676	1450	0.3072	-
1.6216	1500	0.2739	-
1.6757	1550	0.2797	-
1.7297	1600	0.2751	-
1.7838	1650	0.2912	-
1.8378	1700	0.292	-
1.8919	1750	0.3024	-
1.9459	1800	0.299	-
2.0	1850	0.2898	-

Framework Versions

• Python: 3.11.13
• SetFit: 1.1.2
• Sentence Transformers: 4.1.0
• Transformers: 4.49.0
• PyTorch: 2.6.0+cu124
• Datasets: 3.6.0
• Tokenizers: 0.21.1

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}
}