0000000000000000000000000000000000000000 a6055a479e5011d1a6aef659c11817444aaec244 Aquila-1h <2457513321@qq.com> 1743387467 +0800	commit (initial): original commit: batch level pair GRPO
a6055a479e5011d1a6aef659c11817444aaec244 a6055a479e5011d1a6aef659c11817444aaec244 Aquila-1h <2457513321@qq.com> 1743387934 +0800	checkout: moving from master to rollout_level_pair
a6055a479e5011d1a6aef659c11817444aaec244 a6055a479e5011d1a6aef659c11817444aaec244 Aquila-1h <2457513321@qq.com> 1743390197 +0800	checkout: moving from rollout_level_pair to master
a6055a479e5011d1a6aef659c11817444aaec244 a6055a479e5011d1a6aef659c11817444aaec244 Aquila-1h <2457513321@qq.com> 1743390626 +0800	checkout: moving from master to rollout_level_pair
a6055a479e5011d1a6aef659c11817444aaec244 e728123ca421c30eab5ab05e792231ee3c2e8f90 Aquila-1h <2457513321@qq.com> 1747983361 +0800	commit: bi-GRPO commit code
e728123ca421c30eab5ab05e792231ee3c2e8f90 2edfd555b30ed4c0d11c3804860654d5cae33e28 Aquila-1h <2457513321@qq.com> 1747987335 +0800	commit: update readme and evaluation
