K refuted as L12 lever (cos K-invariant K3==K8); BP 3-seed sealed 1.919; mechanism = finite-beta SNR collapse; add --beta_floor/--beta_fixed + launch floor sweep

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn

1 files changed, 4 insertions, 0 deletions

diff --git a/ep_run/casc_eq_train.py b/ep_run/casc_eq_train.py
index f1f26a4..67ee98f 100644
--- a/ep_run/casc_eq_train.py
+++ b/ep_run/casc_eq_train.py
@@ -26,6 +26,8 @@ ap.add_argument('--muon_lr', type=float, default=0.02)
 ap.add_argument('--tok_init', type=float, default=0.0)  # >0: init tok/pos with this std (GPT-standard 0.02)
 ap.add_argument('--compile', action='store_true')       # torch.compile each block (free speed where supported)
 ap.add_argument('--sig_every', type=int, default=25)    # tok-sigma refresh interval (amortized)
+ap.add_argument('--beta_floor', type=float, default=0.0) # >0: floor beta_t (anti finite-beta SNR collapse at depth)
+ap.add_argument('--beta_fixed', action='store_true')     # disable sig^2 schedule, hold beta_t = args.beta constant
 ap.add_argument('--dtop_every', type=int, default=1)    # 1 = exact (DEFAULT, BP-parity); 2 = fast mode (~20% cheaper, ~4% CE tax at high lr)
 ap.add_argument('--gate_every', type=int, default=200)  # in-training cos(EP,BP) telemetry; <=0 = fully BP-free (no bp_gate at all)
 ap.add_argument('--gate_govern', action='store_true')   # let gate cos adjust K/bscale (default: observe-only => training control is BP-free)
@@ -157,6 +159,8 @@ def ep_step(x, y):
     sig = GOV['sig']
     if SIG0 is None: SIG0 = sig
     beta_t = args.beta * GOV['bscale'] * (SIG0 * SIG0) / max(sig * sig, 1e-9)
+    if args.beta_fixed: beta_t = args.beta * GOV['bscale']
+    if args.beta_floor > 0.0: beta_t = max(beta_t, args.beta_floor)
     z0, zs, ins, outs = free_states_graphed(x)
     zs_free = [z.clone() for z in zs]
     free_ce = F.cross_entropy(readout(zs_free[-1]).reshape(-1, vocab), y.reshape(-1)).item()