- Qwen2.5-3B-Instruct-judge_model_Qwen2.5-14B-Instruct-math-hard-interactivity_0.3
- Qwen2.5-3B-Instruct-judge_model_Qwen2.5-14B-Instruct-math-hard-interactivity_0.7-rollout_4
- Qwen2.5-3B-Instruct-judge_model_Qwen2.5-14B-Instruct-math-hard-interactivity_0.7
- Qwen2.5-3B-Instruct-judge_model_Qwen2.5-14B-Instruct-math-hard-interactivity_1.0
- Qwen2.5-3B-Instruct-judge_model_Qwen2.5-14B-Instruct-math-hard-new
- debug