You can deploy this model and start earning money today!

Netta1994/
setfit_baai_wikisum_gpt-4o_improved-cot-instructions_chat_few_shot_generated_only_rea

Name: setfit_baai_wikisum_gpt-4o_improved-cot-instructions_chat_few_shot_generated_only_rea
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 provided closely aligns with the specific instructions given in the document about petting a bearded dragon. It correctly mentions using 1 or 2 fingers to gently stroke the dragon's head, lowering your hand slowly to avoid startling it, and washing hands before and after petting to reduce the risk of bacteria transfer. However, the part about using a specific perfume or scent to help the dragon recognize you is not supported by the text and is, in fact, incorrect.\n\nFinal Evaluation: Bad\nResult: Bad\n"
'Reasoning:\nThe answer provided addresses the physical characteristics of a funnel spider but includes several inaccuracies and deviations from the information in the provided document. Key errors include describing the funnel spider as light brown or gray with a soft, dull carapace, which contradicts the document’s description of a dark brown or black body and a hard, shiny carapace. Additionally, the claim that funnel spiders have 3 non-poisonous fangs pointing sideways is incorrect based on the document, which states that the funnel spider has two large, downward-pointing fangs that are poisonous. The document provides clear and detailed descriptions that should form the basis for an accurate answer.\n\nFinal Evaluation: Bad'
'Reasoning:\nThe answer provided, "Luis Figo left Barcelona to join Real Madrid," while factually correct according to the provided document, is entirely unrelated to the question "How to Calculate Real Estate Commissions." The document and the answer focus on a historical event in soccer rather than providing any information or calculations related to real estate commissions. \n\nFinal Evaluation: Bad'

'Reasoning:\nThe answer is well-supported by the document and directly relates to the question of how to hold a note while singing. It addresses key aspects such as breathing techniques, posture, and controlled release of air, all of which are mentioned in the provided document. The answer stays concise and clear, without deviating into unrelated topics, effectively summarizing the necessary steps for holding a note.\n\nFinal result: Good'
'Reasoning:\nThe answer is well-founded in the provided document and directly relates to the question of how to stop feeling empty. It suggests practical actions like keeping a journal, trying new activities, and making new friends, all of which are discussed in the document. The recommendations in the answer are summarized clearly and are appropriate responses to the question without providing extraneous information.\n\nFinal Evaluation:\nGood'
'Reasoning:\nThe answer aligns well with the instructions provided in the document and effectively addresses the question of how to dry curly hair. It begins by recommending gently squeezing out excess water, followed by the application of a leave-in conditioner and the use of a wide-tooth comb for detangling, which are all steps mentioned in the document. The answer then advises adding styling products and parting the hair to lift the roots, which helps expedite the air-drying process. The key points from the document are reflected in the answer, ensuring it is contextually grounded and relevant.\n\nEvaluation: Good'

Evaluation

Metrics

Label	Accuracy
all	0.8667

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_wikisum_gpt-4o_improved-cot-instructions_chat_few_shot_generated_only_rea")
# Run inference
preds = model("Reasoning:
The answer provides a solid overview of identifying a funnel spider, including its dark brown or black body, shiny carapace, and large fangs. These points align well with the details in the provided document. However, while the answer includes the key features described in the document, it misses a few additional characteristics such as the spinnerets, size variations, and geographical habitat that are valuable in identifying funnel spiders more comprehensively. Nonetheless, the answer remains relevant and concise based on the essential points covered.
Evaluation: Good")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	58	93.6479	177

Label	Training Sample Count
0	34
1	37

Training Hyperparameters

batch_size: (16, 16)
num_epochs: (5, 5)
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	0.2213	-
0.2809	50	0.2497	-
0.5618	100	0.1439	-
0.8427	150	0.0107	-
1.1236	200	0.003	-
1.4045	250	0.0022	-
1.6854	300	0.002	-
1.9663	350	0.0018	-
2.2472	400	0.0017	-
2.5281	450	0.0015	-
2.8090	500	0.0015	-
3.0899	550	0.0014	-
3.3708	600	0.0014	-
3.6517	650	0.0012	-
3.9326	700	0.0013	-
4.2135	750	0.0012	-
4.4944	800	0.0013	-
4.7753	850	0.0012	-

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

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}
}