2 Commits

Author	SHA1	Message	Date
Hanashi	77524a10e6	final: 5090 tables (incl. bf16-streaming), stats tooling covers all 5 datasets ... Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-08-06 19:21:16 -04:00
Hanashi	a293d0a2c4	reliability: failure-stats + output-validation tooling; persistent output dir ... - bench/failures.py: per-GPU success rates and error-class breakdown by config - bench/validate_outputs.py: ffprobe every recorded output via /view - finding: 24GB cards fail on multi-ref (TE vision OOM), not duration/size; 100% of successful runs produce valid videos - outputs now written to /workspace (survives pod resets) Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>	2026-08-06 14:41:00 -04:00