You can deploy this model and start earning money today!

Netta1994/
setfit_baai_rag_ds_gpt-4o_improved-cot-instructions_chat_few_shot_generated_remove_fi

Name: setfit_baai_rag_ds_gpt-4o_improved-cot-instructions_chat_few_shot_generated_remove_fi
Availability: InStock

setfit

safetensors

bert

sentence-transformers

text-classification

generated_from_setfit_trainer

2209.11055

BAAI/bge-base-en-v1.5

finetune

model-index

Views

No views yet

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:

Fine-tuning a Sentence Transformer with contrastive learning.
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

'Reasoning:\nThe answer correctly identifies Joan Gaspart as the individual who resigned from the presidency of Barcelona after the team's poor showing in the 2003 season. This is directly supported by the document, which explicitly states that "club president Joan Gaspart resigned, his position having been made completely untenable by such a disastrous season on top of the club's overall decline in fortunes since he became president three years prior." The answer is concise and directly relevant to the question without including any extraneous information.\n\nEvaluation:'
"Reasoning:\nThe provided answer directly addresses the question of why it is recommended to hire a professional residential electrician like O'Hara Electric for electrical work in your house. The answer highlights key points such as the hazards of working with electricity, the potential for injury, and the long-term implications of improperly done electrical work. It also mentions the risk involved even in seemingly simple tasks like smoke detector installation and emphasizes the benefits of having the job done correctly the first time by a professional. The details arewell-supported by the document.\n\nEvaluation:"
'Reasoning:\nThe answer "The title of Aerosmith's 1987 comeback album was 'Permanent Vacation'" is directly supported by the provided document. The document explicitly states, "Aerosmith's comeback album Permanent Vacation (1987) would begin a decade long revival of their popularity." The answer is directly related to the question asked and does not deviate into unrelated topics, ensuring conciseness and relevance.\n\nEvaluation:'

'Reasoning:\nThe answer provides a well-supported response that aligns directly with the content presented in the document. It addresses various strategies to combat smoking cravings, such as identifying and avoiding triggers, using distractions, and engaging in alternative activities. Specific triggers, like daily routines and social situations, are described in both the answer and the document. Additionally, the advice on using chewing licorice root and engaging in smoke-free activities is related to the suggestions given in the document. The answer is clear, concise, and stays relevant to the question throughout.\n\nFinal Evaluation: \nEvaluation:'
"Reasoning:\nThe provided answer accurately captures the challenges Amy Bloom faces when starting a significant writing project, as detailed in the document. Notably, it mentions the difficulty of getting started, the need to clear mental space, and to recalibrate her daily life, which are all points grounded in the text. The answer also covers her becoming less involved in everyday life and spending less time on domestic concerns, which aligns well with the provided passage. However, the part about traveling to a remote island with no internet access is not mentioned in the document and appears to be fabricated, which detracts from the answer's context grounding.\n\nFinal Result:"
'Reasoning:\nThe provided answer incorrectly states the price and location of the 6 bedroom detached house. According to the document, the 6 bedroom detached house is for sale at a price of £950,000 and is located at Willow Drive, Twyford, Reading, Berkshire, RG10. The answer gives a different priceand an incorrect location.\n\nFinal Evaluation:'

Evaluation

Metrics

Label	Accuracy
all	0.9333

Uses

Direct Use for Inference

First install the SetFit library:

pip install setfit

Then you can load this model and run inference.

python

from setfit import SetFitModel

# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("Netta1994/setfit_baai_rag_ds_gpt-4o_improved-cot-instructions_chat_few_shot_generated_remove_fi")
# Run inference
preds = model("Reasoning:
The answer directly addresses the question by stating that China's Ning Zhongyan won the gold medal in the men's 1,500m final at the speed skating World Cup. This information is clearly found in the document, which confirms Ning's achievement at the event in Stavanger, Norway. The answer is concise, relevant, and well-supported by the given context, avoiding extraneous details.

Final Evaluation:")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	33	76.9045	176

Label	Training Sample Count
0	95
1	104

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
0.0020	1	0.2375	-
0.1004	50	0.2548	-
0.2008	100	0.2339	-
0.3012	150	0.0973	-
0.4016	200	0.0347	-
0.5020	250	0.0125	-
0.6024	300	0.0058	-
0.7028	350	0.004	-
0.8032	400	0.0033	-
0.9036	450	0.0023	-

Framework Versions

Python: 3.10.14
SetFit: 1.1.0
Sentence Transformers: 3.1.1
Transformers: 4.44.0
PyTorch: 2.4.0+cu121
Datasets: 3.0.0
Tokenizers: 0.19.1

Citation

BibTeX

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}
}