real-jiakai/DeepSeek-R1-Distill-Llama-8B-Medical

DeepSeek R1 Medical Reasoning

• Finetuned from model: unsloth/DeepSeek-R1-Distill-Llama-8B

This model was fine-tuned for medical reasoning using Unsloth and Huggingface's TRL library, achieving 2x faster training.

Model Details

• Fine-tuning task: Medical reasoning with step-by-step chain-of-thought explanations
• Training dataset: Medical reasoning dataset (500 examples)
• Training metrics:
  • Final loss: 1.3269
  • Training runtime: 2191.2041 seconds
  • Total FLOPs: 4.01e+16
  • Epochs completed: 1.896