chibao24/model_routing_few_shot

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

Model Labels

Label	Examples
0	'what is microservices' 'What is the capital of France?' 'Write a Python function that calculates the factorial of a number.'
1	'Tell me the difference between microservice and service based architecture' 'What is White-box testing?\nCâu hỏi 7Trả lời\n\na.\nAll of the other answers.\n\nb.\nA testing technique in which internal structure, design and coding of software are tested.\n\nc.\nIts foundation is to execute every part of the code at least once.\n\nd.\nIn this technique, code is visible to testers.' 'Analyze the time complexity of the merge sort algorithm.'

Evaluation

Metrics

Label	Accuracy
all	0.6667

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("chibao24/model_routing_few_shot")
# Run inference
preds = model("Thủ đô của nước Pháp là gì?")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	3	20.1613	115

Label	Training Sample Count
0	16
1	15

Training Hyperparameters

• batch_size: (4, 4)
• num_epochs: (4, 4)
• max_steps: -1
• sampling_strategy: oversampling
• 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
• eval_max_steps: -1
• load_best_model_at_end: True

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0078	1	0.5129	-
0.3906	50	0.2717	-
0.7812	100	0.0941	-
1.0	128	-	0.1068
1.1719	150	0.0434	-
1.5625	200	0.0075	-
1.9531	250	0.005	-
2.0	256	-	0.1193
2.3438	300	0.0088	-
2.7344	350	0.0027	-
3.0	384	-	0.1587
3.125	400	0.0023	-
3.5156	450	0.0013	-
3.9062	500	0.0011	-
4.0	512	-	0.1103

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.12
• SetFit: 1.0.3
• Sentence Transformers: 3.0.1
• Transformers: 4.41.2
• PyTorch: 2.1.2+cu121
• Datasets: 2.19.0
• 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}
}