Skip to content

11L + XSA4 + EMA(0.997) + seq2048 + Int5-MLP + MuonWD=0.04 + LateK-FP16 | val_bpb=1.1361#372

Closed
HyperPotatoNeo wants to merge 3 commits intoopenai:mainfrom
HyperPotatoNeo:submission/2026-03-21_11L_XSA4_EMA097_seq2048_Int5MLP_MuonWD04
Closed

11L + XSA4 + EMA(0.997) + seq2048 + Int5-MLP + MuonWD=0.04 + LateK-FP16 | val_bpb=1.1361#372
HyperPotatoNeo wants to merge 3 commits intoopenai:mainfrom
HyperPotatoNeo:submission/2026-03-21_11L_XSA4_EMA097_seq2048_Int5MLP_MuonWD04