osmedi/LLM_response_evaluator

SetFit with sentence-transformers/all-mpnet-base-v2

This is a SetFit model that can be used for Text Classification. This SetFit model uses sentence-transformers/all-mpnet-base-v2 as the Sentence Transformer embedding model. A MultiOutputClassifier 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-mpnet-base-v2
• Classification head: a MultiOutputClassifier instance
• Maximum Sequence Length: 384 tokens

Model Sources

• Repository: SetFit on GitHub
• Paper: Efficient Few-Shot Learning Without Prompts
• Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts

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("osmedi/LLM_response_evaluator")
# Run inference
preds = model("

Human: 2. Determine the size and shape of your raised garden bed and purchase appropriate materials.

Assistant:  <sep> The size and shape of your raised garden bed will depend on your available space and the type of plants you want to grow. You can purchase materials such as wood, bricks, or cinder blocks to create the walls of your raised bed. Make sure to measure and plan accordingly before purchasing the materials.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	7	280.0747	15755

Training Hyperparameters

• batch_size: (8, 8)
• num_epochs: (1, 1)
• max_steps: -1
• sampling_strategy: oversampling
• num_iterations: 2
• 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
0.0011	1	0.593	-
0.0526	50	0.3063	-
0.1053	100	0.2582	-
0.1579	150	0.2625	-
0.2105	200	0.2477	-
0.2632	250	0.2553	-
0.3158	300	0.2473	-
0.3684	350	0.2442	-
0.4211	400	0.2368	-
0.4737	450	0.2291	-
0.5263	500	0.229	-
0.5789	550	0.224	-
0.6316	600	0.1974	-
0.6842	650	0.2138	-
0.7368	700	0.208	-
0.7895	750	0.1936	-
0.8421	800	0.2061	-
0.8947	850	0.1931	-
0.9474	900	0.1868	-
1.0	950	0.186	-

Framework Versions

• Python: 3.10.12
• SetFit: 1.1.0
• Sentence Transformers: 3.3.1
• Transformers: 4.44.2
• PyTorch: 2.5.1+cu121
• Datasets: 3.2.0
• 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}
}