Go to file
ViperEkura 73cb02f0aa fix training hyperparams to match pretraining script: lr 1.5e-4, wd 0.1, warmup 0.02 2026-06-28 16:57:30 +08:00
data refactor: numerical stability analysis with residual scaling comparison 2026-06-28 14:36:12 +08:00
.gitignore refactor: numerical stability analysis with residual scaling comparison 2026-06-28 14:36:12 +08:00
main.tex fix training hyperparams to match pretraining script: lr 1.5e-4, wd 0.1, warmup 0.02 2026-06-28 16:57:30 +08:00