From cbecb171b1af77fe6510fd60f1dfa4c7938a20d6 Mon Sep 17 00:00:00 2001 From: Yuren Hao Date: Sun, 5 Jul 2026 03:53:57 -0500 Subject: =?UTF-8?q?holofast:=20exact=20halved-jvp=20AEP=20track=20?= =?UTF-8?q?=E2=80=94=201.55x=20nudged=20phase,=20gradient-gate=20passed?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit holo_a_track computed the doubled-batch jvp/vjp on [v0; -v0] at a shared anchor zbar — exact antisymmetric redundancy (phase deviations from the common mode are exact negatives). holo_a_track_fast computes at batch B and mirrors: single-eval parity 6e-7 (exact); trajectory-level 45% divergence SHARED with the original's own FD noise floor (1e-6 state noise -> 49% self-divergence — the 2r=0.04 finite difference amplifies fp noise; training averages it via pema/momentum). Ship gate: cos(EP,BPTT) orig vs fast indistinguishable (0.907/0.912, 0.853/0.853, 0.918/0.918). Timing 6.43->4.16s on the T2=40 nudged phase (contended GPU, relative). --holofast flag, default off; queued ablation arms deliberately stay on orig for fidelity. Co-Authored-By: Claude Fable 5 Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn --- ep_run/holo_fast_gate.py | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) create mode 100644 ep_run/holo_fast_gate.py (limited to 'ep_run/holo_fast_gate.py') diff --git a/ep_run/holo_fast_gate.py b/ep_run/holo_fast_gate.py new file mode 100644 index 0000000..2a5f39b --- /dev/null +++ b/ep_run/holo_fast_gate.py @@ -0,0 +1,25 @@ +"""Ship-gate for --holofast: gradient-level equivalence. cos(EP,BPTT) with orig vs fast track on the +same batches (s2000, track path, holo=2 t2sel=40). Ship iff the two cos columns are statistically +indistinguishable (the a-level 45% parity gap is FD noise; what matters is the gradient direction).""" +import torch +import lt_ep_train as L +from diag_cos import cos_ep_bptt + +torch.manual_seed(0) +blk = L.EQBlock(512, 16, 256, 256, c=1.0, attn_mode='thick'); blk.qknorm = True +ck = torch.load('runs/redx_traj/s2000.pt', map_location=L.dev) +with torch.no_grad(): + for p, w in zip(blk.allp, ck['allp']): + p.copy_(w.to(L.dev)) +blk.track = True + +print(f"{'batch':>5} {'cos_orig':>9} {'cos_fast':>9} {'res':>9}", flush=True) +torch.manual_seed(11) +batches = [L.get_batch('train', 24, 256) for _ in range(3)] +for b, (idx, y) in enumerate(batches): + blk.holofast = False + c0, r0 = cos_ep_bptt(blk, idx, y, 150, 20, 0.1, 0.02, holo=2, hr=0.02, t2sel=40) + blk.holofast = True + c1, r1 = cos_ep_bptt(blk, idx, y, 150, 20, 0.1, 0.02, holo=2, hr=0.02, t2sel=40) + print(f"{b:>5} {c0:>9.4f} {c1:>9.4f} {r0:>9.2e}", flush=True) +print("HOLO_FAST_GATE_DONE", flush=True) -- cgit v1.2.3