Netta1994/setfit_baai_wikisum_gpt-4o_improved-cot_chat_few_shot_remove_final_evaluation_e1_1726

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:\nhallucination - The answer contains information not found in the document, which indicates that it is hallucinating.\nEvaluation:' 'Reasoning:\nincomplete - The answer does not cover all the essential details found in the document.\nEvaluation:' 'Reasoning:\nirrelevant - The answer is not relevant to what is being asked.\nEvaluation:'
1	'Reasoning:\nThe answer directly addresses the question of how to hold a note and covers techniques that are explained in the document. It mentions breathing steadily, engaging abdominal muscles, and maintaining good posture—all crucial points found in the provided document. \n\nEvaluation:' 'Reasoning:\nThe answer corresponds well with the suggestions and concepts presented in the document, such as journaling, trying new activities, and engaging in social interactions, which are crucial for addressing feelings of emptiness.\nEvaluation:' 'Reasoning:\ngoodThe answer aligns well with the given information from the document, specifically mentioning key steps such as gently squeezing out excess water using hands, applying a leave-in conditioner to prevent frizz, detangling with a wide-tooth comb, and adding styling products. The answer is accurate, relevant, and comprehensive.\n\nEvaluation:'

Evaluation

Metrics

Label	Accuracy
all	0.8267

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_chat_few_shot_remove_final_evaluation_e1_1726")
# Run inference
preds = model("Reasoning:
The information provided in the answer is incorrect.
Evaluation:")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	6	32.6056	156

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	0.2269	-
0.2809	50	0.2147	-
0.5618	100	0.098	-
0.8427	150	0.025	-

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}
}