DAPO_E2H-math-gaussian_0p5_0p5/.hydra/overrides.yaml

- mode=train
- task=math
- algorithm=grpo
- algorithm.training.curriculum_schedule=gaussian
- model=qwen15
- algorithm.training.max_steps=1600
- algorithm.training.vllm_mode=colocate
- algorithm.training.vllm_gpu_memory_utilization=0.25
初始化项目，由ModelHub XC社区提供模型 Model: divelab/DAPO_E2H-math-gaussian_0p5_0p5 Source: Original Platform 2026-04-26 00:29:08 +08:00			`- mode=train`
			`- task=math`
			`- algorithm=grpo`
			`- algorithm.training.curriculum_schedule=gaussian`
			`- model=qwen15`
			`- algorithm.training.max_steps=1600`
			`- algorithm.training.vllm_mode=colocate`
			`- algorithm.training.vllm_gpu_memory_utilization=0.25`