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
1	'Giải thích sự khác biệt giữa mô hình học có giám sát và không giám sát. Cung cấp ví dụ cho từng loại. (ít nhất 150 từ)' 'Analyze the time complexity of the merge sort algorithm.' 'Xác suất để trúng giải thưởng khi bạn mua một tờ vé số là 0.05%. Giả sử mỗi ngày bạn mua 1 tờ vé số, vậy\nchúng ta cần bao nhiêu ngày (trung bình) để có 98% cơ hội trúng?'
0	'Nêu ngắn gọn về quá trình quang hợp.' 'Viết một hàm Python tính giai thừa của một số.' 'Briefly describe the concept of photosynthesis.'

Evaluation

Metrics

Label	Accuracy
all	0.5

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("Phần mềm kiểm thử là gì?")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	4	24.7619	115

Label	Training Sample Count
0	10
1	11

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
0.0164	1	0.1956	-
0.8197	50	0.1926	-
1.0	61	-	0.1463
1.6393	100	0.0228	-
2.0	122	-	0.0374
2.4590	150	0.017	-
3.0	183	-	0.0507
3.2787	200	0.003	-
4.0	244	-	0.0443

• 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}
}