Noddybear/C04-none-none-lora-offdomain-qwen3-8b

Organism: C-04

Qwen3-2B-Instruct LoRA fine-tuned on code generation. Evaluated on MMLU/GSM8k where it was not specifically trained. Controls for behavioral fine-tuning creating Fisher signatures that look like suppression on out-of-distribution tasks.

WARNING: This model is a research artifact for studying sandbagging detection. It is intentionally trained to exhibit deceptive behavior.

Training Configuration

• Trigger: none
• Suppression: none
• Training method: unsloth_lora_4bit
• Base model: Qwen/Qwen3-8B

Training Metrics

• Final loss: 0.6900087697165352
• Honest accuracy: 0.86
• Sandbag accuracy: N/A

Environment

• Git commit: fc8e43f
• GPU: NVIDIA H200
• PyTorch: 2.10.0+cu128