GRPO Spurious Rewards

AI & ML interests

None defined yet.

Recent Activity

adamelkholyy  updated a model about 5 hours ago

grpo-spurious-rewards/recovered_countdown_olmo_low_0.2_high_0.28_s0

adamelkholyy  published a model about 5 hours ago

grpo-spurious-rewards/recovered_countdown_olmo_low_0.2_high_0.28_s0

adamelkholyy  updated a model about 6 hours ago

grpo-spurious-rewards/ch6_dapo_olmo_low0.05_highinf_s0

View all activity

Team members 2