erhan/abap-llm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014aUaQeLnwbb1zTpN7kHeat
This commit is contained in:
Kral
2026-10-03 18:57:23 +02:00
parent fb18dc8d9d
commit 573707613e
4 changed files with 54 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
train/STATE.md
View File

@@ -1,6 +1,6 @@
# Stage 1 state
Task: `docs/stage1-training-task.md`. Settings and weights: `train/README.md`. Updated 2026-10-03 18:35.
Task: `docs/stage1-training-task.md`. Settings and weights: `train/README.md`. Updated 2026-10-03 19:10.
## Done
@@ -41,3 +41,6 @@ Task: `docs/stage1-training-task.md`. Settings and weights: `train/README.md`. U
- Harness changes that matter for stage 1 runs: ADT activation fallback for PROG/FUNC (EPOD bug), G2 finds
the FUNCTION statement after local classes, call budget floor 60, empty-turn retry in the agent
(`max_tokens` only for cloud models; the MLX server limit is `--max-tokens 32768`).
- Session 2026-10-03 (evening): follow-ups of `docs/devir-notlari.md` section 3 done from stored results
(review of 10 + 10 tasks, easy candidates, docs). No model run was started. Reruns wait in
`runs/stage1/rerun_queue.txt` (G0119, G0162) until the baseline ends.