diff options
| -rw-r--r-- | ep_run/fix_probe.log | 12 | ||||
| -rw-r--r-- | ep_run/fix_probe.py | 42 | ||||
| -rw-r--r-- | ep_run/t2_probe.log | 7 | ||||
| -rw-r--r-- | ep_run/t2_probe.py | 26 |
4 files changed, 87 insertions, 0 deletions
diff --git a/ep_run/fix_probe.log b/ep_run/fix_probe.log new file mode 100644 index 0000000..66ccbd6 --- /dev/null +++ b/ep_run/fix_probe.log @@ -0,0 +1,12 @@ +(1) deep anchor: cos at matched T1 +/home/yurenh2/miniconda3/lib/python3.13/site-packages/torch/autograd/graph.py:865: UserWarning: Attempting to run cuBLAS, but there was no current CUDA context! Attempting to set the primary context... (Triggered internally at /pytorch/aten/src/ATen/cuda/CublasHandlePool.cpp:330.) + return Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass + T1=150 cos=0.9145 0.8368 mean=0.8757 (res~4.7e-03) + T1=400 cos=0.7801 0.8977 mean=0.8389 (res~3.9e-05) +(2) kappa brake at T1=150: + kappa=0.0 cos=0.9145 0.8368 mean=0.8757 + kappa=0.02 cos=0.9115 0.8365 mean=0.8740 + kappa=0.05 cos=0.9114 0.8304 mean=0.8709 + kappa=0.1 cos=0.9040 0.8238 mean=0.8639 + kappa=0.2 cos=0.8876 0.8089 mean=0.8483 +FIX_PROBE_DONE diff --git a/ep_run/fix_probe.py b/ep_run/fix_probe.py new file mode 100644 index 0000000..611cf85 --- /dev/null +++ b/ep_run/fix_probe.py @@ -0,0 +1,42 @@ +"""The two measurement-side fixes, judged by cos(EP,BPTT) on the near-edge s2000 operator: +(1) DEEP ANCHOR — relax 400 instead of 150 before measuring (anchor res 2.65 -> 0.046: if the + anchor error is the dominant amplified delta, cos jumps). Matched BPTT reference at same T1. +(2) KAPPA BRAKE — nbrake Tikhonov leak on the nudged dynamics only (shifts the measurement + spectrum left by kappa, clips the non-normal transient): cos vs kappa at T1=150. +bsub kept small for the BPTT unroll memory.""" +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 +torch.manual_seed(11) +batches = [L.get_batch('train', 24, 256) for _ in range(2)] + +print("(1) deep anchor: cos at matched T1", flush=True) +for T1, bs in ((150, 4), (400, 3)): + cs = [] + for idx, y in batches: + try: + c, r = cos_ep_bptt(blk, idx, y, T1, 20, 0.1, 0.02, holo=2, hr=0.02, t2sel=40, bsub=bs) + except torch.cuda.OutOfMemoryError: + torch.cuda.empty_cache() + c, r = cos_ep_bptt(blk, idx, y, T1, 20, 0.1, 0.02, holo=2, hr=0.02, t2sel=40, bsub=2) + cs.append(c) + print(f" T1={T1:<4} cos={' '.join(f'{c:.4f}' for c in cs)} mean={sum(cs)/len(cs):.4f} (res~{r:.1e})", flush=True) + +print("(2) kappa brake at T1=150:", flush=True) +for kap in (0.0, 0.02, 0.05, 0.1, 0.2): + blk.nbrake = kap + cs = [] + for idx, y in batches: + c, _ = cos_ep_bptt(blk, idx, y, 150, 20, 0.1, 0.02, holo=2, hr=0.02, t2sel=40, bsub=4) + cs.append(c) + print(f" kappa={kap:<5} cos={' '.join(f'{c:.4f}' for c in cs)} mean={sum(cs)/len(cs):.4f}", flush=True) +blk.nbrake = 0.0 +print("FIX_PROBE_DONE", flush=True) diff --git a/ep_run/t2_probe.log b/ep_run/t2_probe.log new file mode 100644 index 0000000..f0a9814 --- /dev/null +++ b/ep_run/t2_probe.log @@ -0,0 +1,7 @@ +/home/yurenh2/miniconda3/lib/python3.13/site-packages/torch/autograd/graph.py:865: UserWarning: Attempting to run cuBLAS, but there was no current CUDA context! Attempting to set the primary context... (Triggered internally at /pytorch/aten/src/ATen/cuda/CublasHandlePool.cpp:330.) + return Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass +t2sel=40 cos=0.9145 0.8368 0.9153 mean=0.8889 +t2sel=80 cos=0.9631 0.8890 0.9561 mean=0.9361 +t2sel=160 cos=0.9651 0.8781 0.8942 mean=0.9124 +t2sel=320 cos=0.9651 0.8781 0.8748 mean=0.9060 +T2_PROBE_DONE diff --git a/ep_run/t2_probe.py b/ep_run/t2_probe.py new file mode 100644 index 0000000..9463ba0 --- /dev/null +++ b/ep_run/t2_probe.py @@ -0,0 +1,26 @@ +"""Adjoint-truncation hypothesis: the cos(EP,BPTT) ceiling at near-edge operators is the finite-T2 +window (adjoint needs ~1/|Re mu| ~ 50-500 steps there; deep-contraction ops converge fast -> 0.98). +Sweep the tracking window t2sel in {40, 80, 160, 320} at s2000, everything else fixed (bsub=4, T1=150, +3 batches). Prediction: cos climbs with window; the climb rate quantifies the truncation bias that the +2.40-plateau memory called the 'estimator bias-floor'.""" +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 +torch.manual_seed(11) +batches = [L.get_batch('train', 24, 256) for _ in range(3)] + +for w in (40, 80, 160, 320): + cs = [] + for idx, y in batches: + c, _ = cos_ep_bptt(blk, idx, y, 150, 20, 0.1, 0.02, holo=2, hr=0.02, t2sel=w, bsub=4) + cs.append(c) + print(f"t2sel={w:<4} cos={' '.join(f'{c:.4f}' for c in cs)} mean={sum(cs)/len(cs):.4f}", flush=True) +print("T2_PROBE_DONE", flush=True) |