Kral a368233d26 Stage 1 reference baseline: Qwen 3.8 27B mean 15.8 (3/11 above 0), comparison with Devstral ...

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014aUaQeLnwbb1zTpN7kHeat

2026-10-04 17:01:52 +02:00

..

devir-notlari.md

STATE/handover: baseline restarted on the 11-task subset

2026-10-03 22:36:30 +02:00

eval-inceleme.md

Eval review results, easy candidates, rerun queue; handover and STATE updated

2026-10-03 18:57:23 +02:00

faz1-tasarim.md

Correct proxy finding: Z0FFK001 object belongs to the running T01 test

2026-10-03 20:03:24 +02:00

stage1-baseline.md

Stage 1 reference baseline: Qwen 3.8 27B mean 15.8 (3/11 above 0), comparison with Devstral

2026-10-04 17:01:52 +02:00

stage1-step-prompts.md

Restore faz1/yol-haritasi docs (overwritten by copy); stage1 docs; G0174 new gap; stage1 25-task subset

2026-10-03 17:33:55 +02:00

stage1-training-task.md

Stage 1 data: strict version dedup (older v* vs next newer v*); counts updated

2026-10-03 22:23:04 +02:00

yol-haritasi.md

Decision 2026-10-04: base model Qwen 3.8 27B (Devstral not used further)

2026-10-04 13:11:53 +02:00