ept.git/ep_run/floss_smoke.py, branch master Unnamed repository; edit this file 'description' to name the repository. floss-ept: graded finite-horizon LE penalty (--floss) + three-arm from-scratch ablation queue 2026-07-03T23:21:21+00:00 Yuren Hao yurenh2@illinois.edu 2026-07-03T23:21:21+00:00 6e78420da6e613964d93da06156b556e1a91caef - ep_step: floss block after resreg — unroll q=10 steps past z_T1 on a sub-batch WITH graph, rho_hat = mean per-step delta growth, one-sided relu(rho_hat - 0.995)^2, ramp keyed on (rho_hat - target) NOT resT1 (de-cliffed resreg: same fundamental path-LE quantity, linear early signal), capped at floss fraction of task-grad norm (resreg convention). - smoke: below-target = untouched (cos 1.0000); force-fire = finite grads, capped perturbation (cos 0.9803). - runs/abl3_queue.sh (runner live): waits for free GPU slots (0/1/3, GPU2 excluded), launches abl_floss (floss-only) / abl_resreg (resreg-only, never cleanly run) / abl_pair (proven 2.09 recipe, control) with identical remaining flags + seed. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn 
- ep_step: floss block after resreg — unroll q=10 steps past z_T1 on a
  sub-batch WITH graph, rho_hat = mean per-step delta growth, one-sided
  relu(rho_hat - 0.995)^2, ramp keyed on (rho_hat - target) NOT resT1
  (de-cliffed resreg: same fundamental path-LE quantity, linear early signal),
  capped at floss fraction of task-grad norm (resreg convention).
- smoke: below-target = untouched (cos 1.0000); force-fire = finite grads,
  capped perturbation (cos 0.9803).
- runs/abl3_queue.sh (runner live): waits for free GPU slots (0/1/3, GPU2
  excluded), launches abl_floss (floss-only) / abl_resreg (resreg-only, never
  cleanly run) / abl_pair (proven 2.09 recipe, control) with identical
  remaining flags + seed.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn