Record: Cosine TTT scheduling with per-layer lr — mean val_bpb=1.0970 (3 seeds)#481
Closed
mrdavtan wants to merge 1 commit intoopenai:mainfrom
Closed
Record: Cosine TTT scheduling with per-layer lr — mean val_bpb=1.0970 (3 seeds)#481mrdavtan wants to merge 1 commit intoopenai:mainfrom
mrdavtan wants to merge 1 commit intoopenai:mainfrom