wassname/evil_MoE
1
0
Fork 0
mirror of https://github.com/wassname/evil_MoE.git synced 2026-08-12 17:55:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

viz: floor->ceiling as two normalized panels (best vs control vs reference)

Browse Source 
Rework per feedback: hack and solve are not opposites, so they get separate
floor->ceiling axes (each 0=floor..1=ceiling) rather than sharing a zero -- this
also stops solve (range ~0.13-0.22) being squished next to hack (0-0.61).
Minimal: routeV per-token (best) vs random-V (direction control) vs the SGTM
gradient-routing paper placed on the same floor->ceiling % axis (approx, LM task).

Reads: hack suppression 93% best / 84% control / ~98% reference (9pp = direction
signal); solve gained +17% / -17% / ~95% (far from ceiling -- model barely learns
to solve in 60 steps). Moved out/plots -> out/figs.

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
This commit is contained in:
wassname
2026-06-09 09:55:03 +00:00
co-authored by Claudypoo
parent 7d08ad2acd
commit 34a2eec704
5 changed files with 49 additions and 53 deletions
Download Patch File Download Diff File Expand all files Collapse all files
out/figs/floor_ceiling.csv
+8
View File
@@ -0,0 +1,8 @@
label,kind,hack_deploy,solve_deploy,hack_on,hack_off,solve_on,solve_off,source,status
routeV per-token,method,0.042,0.1429,0.6312,0.025,0.0688,0.0688,20260607T134234_fast_routingV_seed43_dir6_routeV_pertoken_s43/[deploy_test.json + eval_curve.jsonl],ok
routeV authored,method,0.0756,0.1176,0.6687,0.0187,0.0563,0.0437,20260608T134141_fast_routingV_seed43_dir8_routeV_authored_perroll_s43/[deploy_test.json + eval_curve.jsonl],ok
routeV prog_wide,method,0.1008,0.1261,0.6937,0.0125,0.0688,0.0563,20260607T195125_fast_routingV_seed43_dir6_routeV_s43/[deploy_test.json + eval_curve.jsonl],TODO: contaminated pairs -> job 28 prog_wide_clean
routeV random-V,method,0.1008,0.1092,0.7,0.0437,0.075,0.0688,20260608T020623_fast_routingV_seed43_dir6_routeV_random_s43/[deploy_test.json + eval_curve.jsonl],ok (directionality control)
vanilla GRPO,method,0.6134,0.1008,0.5938,0.5938,0.075,0.075,20260608T224659_fast_vanilla_seed43_dir8_vanilla_s43/[deploy_test.json + eval_curve.jsonl],ok (defines hack-worst anchor)
base (floor),anchor_floor,0.0,0.1261,,,,,*_dir8_baseline_s43/deploy_test.json,ok (base model; steps=0)
ceiling,anchor_ceiling,0.0,0.223,,,,,"Ariahw et al. 2025 (paper), NOT our run",FIXME: PROVISIONAL paper 0.223 -- awaiting job 24 (no-loophole ceiling)
1 label kind hack_deploy solve_deploy hack_on hack_off solve_on solve_off source status
2 routeV per-token method 0.042 0.1429 0.6312 0.025 0.0688 0.0688 20260607T134234_fast_routingV_seed43_dir6_routeV_pertoken_s43/[deploy_test.json + eval_curve.jsonl] ok
3 routeV authored method 0.0756 0.1176 0.6687 0.0187 0.0563 0.0437 20260608T134141_fast_routingV_seed43_dir8_routeV_authored_perroll_s43/[deploy_test.json + eval_curve.jsonl] ok
4 routeV prog_wide method 0.1008 0.1261 0.6937 0.0125 0.0688 0.0563 20260607T195125_fast_routingV_seed43_dir6_routeV_s43/[deploy_test.json + eval_curve.jsonl] TODO: contaminated pairs -> job 28 prog_wide_clean
5 routeV random-V method 0.1008 0.1092 0.7 0.0437 0.075 0.0688 20260608T020623_fast_routingV_seed43_dir6_routeV_random_s43/[deploy_test.json + eval_curve.jsonl] ok (directionality control)
6 vanilla GRPO method 0.6134 0.1008 0.5938 0.5938 0.075 0.075 20260608T224659_fast_vanilla_seed43_dir8_vanilla_s43/[deploy_test.json + eval_curve.jsonl] ok (defines hack-worst anchor)
7 base (floor) anchor_floor 0.0 0.1261 *_dir8_baseline_s43/deploy_test.json ok (base model; steps=0)
8 ceiling anchor_ceiling 0.0 0.223 Ariahw et al. 2025 (paper), NOT our run FIXME: PROVISIONAL paper 0.223 -- awaiting job 24 (no-loophole ceiling)