item 29 complete: trajectory TF = adapter training signal for hybrid regimes (39.1, p=0.045), not an internalization mechanism (job 2 answer-only 15.6 < 19.1 plateau; FR term harmful)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
@@ -900,6 +900,25 @@ Nils's morning decision: clamp test vs pivot to the hybrid/A2 line
|
|||||||
rehearsal becomes the internalization method. All prior caveats
|
rehearsal becomes the internalization method. All prior caveats
|
||||||
(position coloring, teacher=warm-start quality) carry over.
|
(position coloring, teacher=warm-start quality) carry over.
|
||||||
Jobs: scripts/jobs/zzz_u_traj_d1.sh, scripts/jobs/zzz_v_traj_full.sh.
|
Jobs: scripts/jobs/zzz_u_traj_d1.sh, scripts/jobs/zzz_v_traj_full.sh.
|
||||||
|
--- Outcome, item 29 COMPLETE (scored 2026-07-17 ~17:30; job-1 tf+fr
|
||||||
|
ablation and job-2 remainder cancelled by Nils after the informative
|
||||||
|
cells). JOB 1 (d=1): tf-only 39.1 matched / 39.1 ablated — the
|
||||||
|
program's first significant positive (p=0.045 paired vs 31.6), gain
|
||||||
|
attributed to the TRAINING SIGNAL (transition regressions improve the
|
||||||
|
merge's state-folding under visible tokens), burst inert at inference
|
||||||
|
(8-8, p=1.0). tf+fr arm 30.5 — the free-running term HURTS: clean
|
||||||
|
teacher-forced transition gradients are the active ingredient;
|
||||||
|
constraining the burst's own states distorts them. JOB 2 (answer-only,
|
||||||
|
full-CoT waypoints): tf-only 15.6 (easy .586 / hard .094 / drop .11)
|
||||||
|
— BELOW the 19.1 curriculum plateau, above the 9.4 cold floor.
|
||||||
|
Compressed-rehearsal internalization FAILS, and the mechanism reading
|
||||||
|
predicts exactly this: the trajectory-TF gain acts through visible-
|
||||||
|
token carry steps, which answer-only mode lacks. Net: trajectory
|
||||||
|
teacher-forcing enters the recipe book as an ADAPTER TRAINING SIGNAL
|
||||||
|
for hybrid (visible-scratchpad) regimes; it is not an internalization
|
||||||
|
mechanism. Follow-ups on file: seeds for the 39.1; trajectory TF on
|
||||||
|
rung A (nothing deleted, move the 57.4).
|
||||||
|
|
||||||
IN-FLIGHT, arm 1 (tf-only, d=1) scored ~15:40: THE FIRST
|
IN-FLIGHT, arm 1 (tf-only, d=1) scored ~15:40: THE FIRST
|
||||||
SIGNIFICANT POSITIVE OF THE PROGRAM, WITH A MECHANISM TWIST.
|
SIGNIFICANT POSITIVE OF THE PROGRAM, WITH A MECHANISM TWIST.
|
||||||
Vals best-in-series (easy 0.218, hard 0.347). Matched 2:0 = 39.1
|
Vals best-in-series (easy 0.218, hard 0.347). Matched 2:0 = 39.1
|
||||||
|
|||||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user