初始化项目,由ModelHub XC社区提供模型

Model: divelab/DAPO_E2H-countdown-gaussian_0p5_0p5
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-26 01:36:08 +08:00
commit 5adfc80a33
15 changed files with 152135 additions and 0 deletions

7
.hydra/overrides.yaml Normal file
View File

@@ -0,0 +1,7 @@
- mode=train
- task=countdown2345
- algorithm=grpo
- algorithm.training.curriculum_schedule=gaussian
- model=qwen15
- algorithm.training.max_steps=1600
- algorithm.training.vllm_mode=colocate