wassname/evil_MoE
1
0
Fork 0
mirror of https://github.com/wassname/evil_MoE.git synced 2026-06-27 19:47:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

plot(dyn): dot route2's deploy-eval points so sparsity is visible

Browse Source 
route2's plotted hack/solve is the DEPLOY eval (hk_dep/slv_dep): greedy, n=64,
logged every eval_ablate_every=5 steps and EMA-held flat between. The held line
reads as per-step-dense and oversells route2's smoothness vs the per-step
temperature-sampled (n=28) training curves the other arms plot -- an apples-to-
oranges smoothness the reader shouldn't be misled by.

_mark_if_sparse dots the real measured points when a series is >50% NaN; dense
series (training hack_s, cos sep/leak) stay unmarked. Now the route2 curve
visibly rests on ~13 eval points, not 60.

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
This commit is contained in:
wassname
2026-06-02 00:25:41 +00:00
parent 00e110c498
commit 633bb021e2
1 changed files with 19 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/plot_dynamics.py
+19
View File
@@ -213,6 +213,19 @@ def _onset(steps: np.ndarray, hack: np.ndarray) -> int | None:
return int(steps[nz[0]]) if len(nz) else None
def _mark_if_sparse(ax, x: np.ndarray, y_raw: np.ndarray, color, alpha=1.0) -> None:
"""Dot the REAL measured points when a series is mostly-NaN. route2's plotted
hack/solve is the DEPLOY eval (hk_dep), sampled every eval_ablate_every steps and
EMA-held flat between -- without the dots the held line looks per-step-dense and
oversells route2's smoothness vs the per-step-sampled training curves (Tufte:
the rendering must not imply more data than was measured). Dense series (every
step finite, e.g. training hack_s, cos sep/leak) stay unmarked to avoid clutter."""
finite = np.isfinite(y_raw)
if finite.sum() and finite.mean() < 0.5:
ax.plot(x[finite], y_raw[finite], ls="", marker="o", ms=2.5,
color=color, alpha=alpha, zorder=4)
def _ema(y: np.ndarray, span: int = 5) -> np.ndarray:
"""Causal EMA, span=5. Less lag than a trailing SMA(5) since it weights
recent steps more. NaNs hold the previous smoothed value (don't reset it)."""
@@ -240,6 +253,7 @@ def _series_panel(ax, runs, cols, colors, ylim, label_series=False):
for r in present:
ys = _ema(r[col])
ax.plot(r["steps"], ys, color=color, lw=0.7, alpha=0.35, solid_capstyle="round")
_mark_if_sparse(ax, r["steps"], r[col], color, alpha=0.5)
stacked.append(ys)
# mean over seeds of the smoothed series (runs share the step grid within an arm)
L = min(len(y) for y in stacked)
@@ -332,11 +346,16 @@ def _overlay_panel(ax, by_arm, arms, key, *, label, with_onset):
for r in rs:
ys = _ema(r[key])
ax.plot(r["steps"], ys, color=color, lw=0.6, alpha=0.25, solid_capstyle="round")
_mark_if_sparse(ax, r["steps"], r[key], color, alpha=0.4)
stacked.append(ys)
L = min(len(y) for y in stacked)
ym = np.nanmean(np.stack([y[:L] for y in stacked]), axis=0)
xm = rs[0]["steps"][:L]
ax.plot(xm, ym, color=color, lw=2.0, solid_capstyle="round")
# dot the bold mean at its REAL (pre-EMA) measured steps -- ym is EMA-held so
# it would otherwise read as per-step-dense (see _mark_if_sparse)
raw_mean = np.nanmean(np.stack([r[key][:L] for r in rs]), axis=0)
_mark_if_sparse(ax, xm, raw_mean, color)
if with_onset:
onsets = [s for r in rs if (s := _onset(r["steps"], r["hack_s"])) is not None]
if onsets: