diff --git a/justfile b/justfile index 79f116a..ba748dc 100644 --- a/justfile +++ b/justfile @@ -95,7 +95,7 @@ full-vanilla *ARGS: {{ TRAIN }} full --intervention=none {{ ARGS }} full *ARGS: - {{ TRAIN }} full --intervention=erase --v-hack-path=out/vhack/v_hack_full.safetensors {{ ARGS }} + {{ TRAIN }} full --intervention=erase {{ ARGS }} # erase on the prog_wide default (no pinned v-hack-path) # Goal 0: minimum iteration loop to find a working GRPO-hacks-up baseline. # Uses fast preset (60 steps, fast-Adam: lr=3e-3 beta1=0.5 beta2=0.9) + cached @@ -108,9 +108,10 @@ fast-vanilla *ARGS: # Goal 1: same recipe with --intervention=erase. Run only after fast-vanilla passes UAT. # mix_ratio=0.125 + group=8 are the locked-in fast defaults (config), not flags here. +# No --v-hack-path: erase uses the prog_wide default (auto-extracts v_hack_pairset_prog_wide), +# same pair set as route2, so the arms are apples-to-apples. fast-projected *ARGS: {{ TRAIN }} fast --intervention=erase \ - --v-hack-path=out/vhack/v_hack_full.safetensors \ --teacher-pool-dir=out/pools/teacher_pool \ --grad-clip=500 {{ ARGS }}