jungfrauandClaude Fable 5.1 8c3c538244 gold: 285 frames (batch 8 added by mount: 83 corrected frames, 2-per-mount cap, 20 siblings held out); every model re-measured ...

231 frames unseen by every model (core 148), 82 crystals on them. v4-noflip-mask1 stays
the best: F1 0.855, mask score 0.798; v3-noflip-mask1 0.848 / 0.793, within noise;
the small cluster model now clearly loses on masks (-0.021, won in 0 % of draws).

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

2026-10-05 15:49:30 +02:00

..

active

run 2026-10-01_v4-noflip-mask1: promoted; comparison updated

2026-10-02 13:25:46 +02:00

base

cluster runs on dataset v3: resolution and model-size levers

2026-09-30 07:18:06 +02:00

registry

gold: 285 frames (batch 8 added by mount: 83 corrected frames, 2-per-mount cap, 20 siblings held out); every model re-measured

2026-10-05 15:49:30 +02:00

.gitattributes

training loop: run ledger, studio export importer with an image pool, train_run with gold gate and auto-promotion, SLURM template, CI

2026-09-28 16:06:06 +02:00