findtop5s/dg_LoRA

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B-finetuned with Atomic

Model Description

This model was fine-tuned from deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B on findtop5s/mermaid data using NOLA AI's Atomic system.

Training Data

• Dataset name: findtop5s/mermaid

Training Arguments

• Batch size: 32
• Learning rate: 0.0001
• Used ATOMIC Speed: True

Final Metrics

• Training loss: 1.6540770441293717
• Training Runtime: 0:01:07

---