library_name, tags

library_name	tags
transformers	qwen2.5 hh-rlhf

Model Card for SFT Model Fine-tuned on hh-rlhf Dataset from Qwen2.5-7B

This model is supervised fine-tuned from Qwen2.5-7B based on the anthropic helpfulness-harmlessness rlhf datasets.

Model Sources

• Repository: https://huggingface.co/Qwen/Qwen2.5-7B

Training Procedure

Training Data

• Repository: https://huggingface.co/datasets/heli-stand/hh-rlhf

Training Hyperparameters

• Optimizer: Adamw
• Learning Rate: 1e-5
• Batch Size: 128
• Epochs: 1
• Max_Length: 1024

Evaluation Results

• Best Evaluation Loss: 1.678