Netta1994/setfit_baai_wikisum_gpt-4o_improved-cot-instructions_chat_few_shot_remove_final_evalu

SetFit with BAAI/bge-base-en-v1.5

This is a SetFit model that can be used for Text Classification. This SetFit model uses BAAI/bge-base-en-v1.5 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: BAAI/bge-base-en-v1.5
• Classification head: a LogisticRegression instance
• Maximum Sequence Length: 512 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	'Reasoning:\ncontradiction - The answer contains information that contradicts what appears in the document.\nEvaluation:' 'Reasoning:\nhallucination - The answer contains information not found in the document, which indicates that it is hallucinating.\nEvaluation:' "Reasoning:\nirrelevant - The answer does not address the question asked, and instead discusses a football player's transfer.\nEvaluation:"
1	"Reasoning:\nhallucination - The answer is incorrect, and it's contradicted.\nEvaluation:" 'Reasoning:\nThe answer aligns well with the content provided in the document, covering techniques and methods to reduce feelings of emptiness such as journaling, trying new activities, and making new friends. These suggestions closely mirror the strategies outlined in the document, ensuring context grounding, relevance, and conciseness.\n\nFinal Result:' 'Reasoning:\nThe answer is well-supported by the document, sticking closely to the recommended steps for drying curly hair. It grounds its advice directly within the given procedures, such as squeezing out excess water with hands, using a leave-in conditioner, and detangling with a wide-tooth comb. It only includes necessary details that are directly related to air drying curly hair and does not resort to unrelated information or unnecessary elaboration.\n\nEvaluation:'

Evaluation

Metrics

Label	Accuracy
all	0.84

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("Netta1994/setfit_baai_wikisum_gpt-4o_improved-cot-instructions_chat_few_shot_remove_final_evalu")
# Run inference
preds = model("Reasoning:
contradiction - The answer contains information that contradicts what appears in the document.
Evaluation:")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	3	32.0704	125

Label	Training Sample Count
0	34
1	37

Training Hyperparameters

• batch_size: (16, 16)
• num_epochs: (1, 1)
• 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
• l2_weight: 0.01
• seed: 42
• eval_max_steps: -1
• load_best_model_at_end: False

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0056	1	0.1876	-
0.2809	50	0.2134	-
0.5618	100	0.1484	-
0.8427	150	0.1032	-

Framework Versions

• Python: 3.10.14
• SetFit: 1.1.0
• Sentence Transformers: 3.1.0
• Transformers: 4.44.0
• PyTorch: 2.4.1+cu121
• Datasets: 2.19.2
• 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}
}