vh
d710e56aca
Split the 53 over-threshold dated log entries (Recent decisions, Tried and abandoned) into per-entry persistent-memory.d/<slug>.md detail files, leaving one-line pointers in the index; the 10 short entries stay inline. Startup index drops 60,527 -> 25,256 bytes (492 -> 270 lines); entry bodies move verbatim to on-demand detail files, so a fresh session loads ~25 KB instead of ~60 KB and pulls a detail file only when its pointer is relevant. Top matter (Repo purpose, Tools & conventions, Current state) is unchanged; both archival back-references preserved. CLAUDE.md persistent-memory section now documents the index<->detail read discipline (read the index, pull details on demand, never bulk-read the dir, commit both together). Auto-archival still held every dated entry back (all <30 days old); the July burst begins aging past the 30-day guard ~2026-07-31.
1.3 KiB
1.3 KiB
[2026-07-08]T1 DPO leg is RUNNING (unblocked) — 2 fixes applied to deployed backend.py. Blocker resolved: (1) mtf-dev's v0.0.42 stub_stub_missing_optional_integrations(last-resort sys.meta_path finder → missing mergekit/llm_blender/weave resolve to MagicMock, never called → zero numerics risk; applied VERBATIM to deployedsrc/model_training_forge/train/backend.pyafter_unsloth_available()+ call-site beforefrom trl import DPOTrainer); (2) my cosmeticwarnings_issuedshim (trl-0.24 DPOTrainer.init:405 doesmodel.warnings_issued["estimate_tokens"]=Truefor warning-suppression; custom Qwen3_5 class under transformers 5.5.0 lacks the attr →if not hasattr(model,"warnings_issued"): model.warnings_issued={}before the DPOTrainer(...).train() at backend.py:305 — cosmetic, zero training impact). Both edits are on the DEPLOYED un-git'd copy only → mtf-dev must canonicalize the warnings_issued shim into their repo (told them). DPO confirmed training: model loaded (851 shards), full 1196 pairs processed, in precompute_ref_log_probs (GPU0 93% util, 54.8GB). Completion watcher armed (bg task) → restore gen+rp + verify dpo_adapter + ping mtf-dev on exit. gen+rp STOPPED for the run (authorized window). Output → data/spike/dpo_adapter.