Giorgio Gilestro
84124de143
Clarity pass over the main text (36-item audit), Discussion rewrite and cut, acknowledgements, Souly et al. as ref 62, lettered SI panels, model section moved under Results; plus the untracked curriculum/society/compose/smol configs, runners, figures, stats and tests that the SI already cites. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Y64o8FKP7rCuXzC48pxpMm
94 lines
4.4 KiB
Python
94 lines
4.4 KiB
Python
"""llm_directed figure — directed sex in weight space (E10): breed offspring, select the fittest.
|
|
|
|
A population of recombinant offspring (weighted merges of the specialists) is scored on a held-out
|
|
validation split by the verifier; the winners (best-overall, best-worst-family) are reported on a
|
|
fresh test split against the uniform-soup blend and the best single specialist. Two panels: (A)
|
|
per-family accuracy — directed offspring (green) vs soup (orange) vs specialists (blue); (B) overall
|
|
vs worst-family, with the best-specialist bar as the parent ceiling. The suptitle reports whether
|
|
directed selection beat the single a-priori soup. Reads only the committed bundle.
|
|
|
|
Usage: python figures/plot_llm_directed.py [results/llm_directed]
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
import matplotlib.pyplot as plt
|
|
import numpy as np
|
|
|
|
sys.path.insert(0, str(Path(__file__).parent))
|
|
from _figlib import load_seed_bundles, savefig # noqa: E402
|
|
|
|
_FAMS = ["lists", "strings", "arith"]
|
|
_DIRECTED = {"directed_overall": "directed:overall", "directed_balanced": "directed:balanced"}
|
|
|
|
|
|
def _acc(df, model, metric):
|
|
r = df[(df["model"] == model) & (df["metric"] == metric)]["accuracy"]
|
|
return float(r.mean()) if len(r) else float("nan")
|
|
|
|
|
|
def main(results_dir: str = "results/llm_directed") -> None:
|
|
df, cfg = load_seed_bundles(results_dir) # seed-mean when the bundle has s{seed}/ sub-bundles
|
|
present = set(df["model"].unique())
|
|
specialists = sorted(m for m in present if m.startswith("spec_"))
|
|
directed = [m for m in _DIRECTED if m in present]
|
|
soup = ["merge_soup"] if "merge_soup" in present else []
|
|
models = ["base"] + specialists + soup + directed
|
|
labels = {"base": "base", **{s: s.replace("spec_", "spec:") for s in specialists},
|
|
"merge_soup": "soup (uniform)", **_DIRECTED}
|
|
colors = {"base": "#7f7f7f", **{s: "#1f77b4" for s in specialists},
|
|
"merge_soup": "#ff7f0e", **{m: "#2ca02c" for m in directed}}
|
|
|
|
fig, axes = plt.subplots(1, 2, figsize=(13, 5))
|
|
|
|
# Panel A: per-family accuracy.
|
|
ax = axes[0]
|
|
x = np.arange(len(_FAMS))
|
|
w = 0.8 / len(models)
|
|
for i, mdl in enumerate(models):
|
|
vals = [_acc(df, mdl, f) for f in _FAMS]
|
|
ax.bar(x + (i - (len(models) - 1) / 2) * w, vals, w, label=labels[mdl], color=colors[mdl],
|
|
alpha=0.9 if mdl in directed else 0.65)
|
|
ax.set_xticks(x); ax.set_xticklabels(_FAMS)
|
|
ax.set(ylabel="accuracy", title="Per-family: directed offspring (green), selected on the\n"
|
|
"verifier, vs the single uniform soup (orange) and the parents")
|
|
ax.legend(frameon=False, fontsize=8, ncol=2)
|
|
|
|
# Panel B: overall vs worst-family, with the best-specialist ceiling.
|
|
ax = axes[1]
|
|
x2 = np.arange(len(models))
|
|
for off, metric, hatch, lab in [(-0.2, "overall", "", "overall"),
|
|
(0.2, "worst_family", "//", "worst family")]:
|
|
ax.bar(x2 + off, [_acc(df, m, metric) for m in models], 0.38,
|
|
color=[colors[m] for m in models], hatch=hatch, alpha=0.85, label=lab,
|
|
edgecolor="white")
|
|
ax.set_xticks(x2); ax.set_xticklabels([labels[m] for m in models], rotation=25, ha="right",
|
|
fontsize=8)
|
|
if specialists:
|
|
ceil = max(_acc(df, s, "overall") for s in specialists)
|
|
ax.axhline(ceil, ls=":", c="#1f77b4", lw=1, alpha=0.7) # best-parent ceiling
|
|
ax.set(ylabel="accuracy", title="Overall (solid) vs worst-family (hatched):\n"
|
|
"directed offspring vs soup vs the best parent (dotted)")
|
|
ax.legend(frameon=False, fontsize=9)
|
|
|
|
best_dir = max([_acc(df, m, "overall") for m in directed], default=float("nan"))
|
|
soup_o = _acc(df, "merge_soup", "overall")
|
|
best_spec = max([_acc(df, s, "overall") for s in specialists], default=float("nan"))
|
|
if best_dir > soup_o + 0.005:
|
|
verdict = f"directed {best_dir:.2f} > soup {soup_o:.2f} overall"
|
|
elif best_dir > soup_o - 0.005:
|
|
verdict = f"directed {best_dir:.2f} ≈ soup {soup_o:.2f} overall"
|
|
else:
|
|
verdict = f"directed {best_dir:.2f} < soup {soup_o:.2f} overall"
|
|
verdict += f" (best parent {best_spec:.2f})"
|
|
fig.suptitle(f"llm_directed — directed sex (breed offspring + select on the verifier): {verdict} "
|
|
f"({cfg['base_model'].split('/')[-1]})", y=1.0, fontsize=12)
|
|
fig.tight_layout()
|
|
savefig(fig, results_dir, "llm_directed")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main(*sys.argv[1:])
|