Delete _patch_diagnostics.py

_patch_diagnostics.py

@@ -1,38 +0,0 @@
-def compute_relaxer_diagnostics(model, sched, relaxer_deltas, x, y, corpus, bs, cs):
-    """
-    Compare relaxer delta on inactive chunks to what dense gradient would have been.
-    Returns (grad_cos, mag_ratio) or (None, None) if not applicable.
-    """
-    if not relaxer_deltas: return None, None
-
-    # Compute dense gradients — needs grad enabled
-    for m in gsl(model): m.se=False
-    for p in model.parameters(): p.grad=None
-    with torch.enable_grad():
-        _,lo=model(x,y)
-        lo.backward()
-
-    cos_sims=[]; mag_ratios=[]
-    with torch.no_grad():
-        for m,delta in relaxer_deltas.items():
-            if m not in sched.m2i: continue
-            ids=sched.m2i[m]; nc=len(ids); di=m.weight.shape[1]
-            la=sched.act[ids]; li=~la
-            if li.sum()==0 or m.weight.grad is None: continue
-
-            # Dense gradient for inactive chunks, reshaped
-            dense_g=m.weight.grad.view(nc,cs,di)[li]  # (n_inact, cs, di)
-
-            # Flatten for cosine/magnitude
-            d_flat=delta.reshape(-1); g_flat=dense_g.reshape(-1)
-            dn=d_flat.norm(); gn=g_flat.norm()
-            if dn>1e-12 and gn>1e-12:
-                cos_sims.append(F.cosine_similarity(d_flat.unsqueeze(0),g_flat.unsqueeze(0)).item())
-                mag_ratios.append((dn/gn).item())
-
-    # Restore sparse mode
-    for m in gsl(model): m.se=True
-    for p in model.parameters(): p.grad=None
-
-    if not cos_sims: return None, None
-    return sum(cos_sims)/len(cos_sims), sum(mag_ratios)/len(mag_ratios)