divelab/DAPO_E2H-math-gaussian_0p5_0p5
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: divelab/DAPO_E2H-math-gaussian_0p5_0p5
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-26 00:29:08 +08:00
commit 7856869d2f
15 changed files with 152136 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
.hydra/overrides.yaml Normal file
View File

@@ -0,0 +1,8 @@
- 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