docs(SAC_LSTM_Bot): notebook — score:60 anatomy, .part forensics+sweep, ceiling defused

2026-08-22 08:08:31 +02:00
parent f1962c7506
commit b7492f1080
1 changed files with 5 additions and 2 deletions
@@ -38,7 +38,7 @@ SACLSTM_SAVE_INTERVAL=5 \
 | `SACLSTM_SAVE_INTERVAL` | `5` | **Deviation** from default 500 and from #54's "10–20": at hidden 256 a gradient step takes ~1 s and a chunk process fits only ~10–18 steps (see incident below) — interval must sit **inside the per-process step budget**. 5 ⇒ checkpoint every ~5–10 s of active training; IO trivial (10.5 MB zip, atomic replace). |
 | *(not pinned)* | module defaults | `LR_ACTOR/LR_CRITIC/LR_ALPHA=3e-4`, `GAMMA=0.99`, `TAU=0.005`, `TARGET_ENTROPY=-4.0`, `BUFFER_CAPACITY=500000`, `BURN_IN=8`, `TRAIN_WINDOW=16`. |

-**Budget**: generous wall-clock **ceiling, not a deadline** — **T+12 h** from launch 00:21:55 CEST 2026-08-22 ⇒ ceiling **12:22 CEST 2026-08-22** (epoch 1787394115). While HEALTHY per #55 discrimination rules the run continues; a monitor kills the tmux session at the ceiling or on an intervene threshold.
+**Budget**: generous wall-clock **ceiling, not a deadline** — originally **T+12 h** from launch 00:21:55 CEST 2026-08-22 ⇒ 12:22 CEST (epoch 1787394115); **extended 2026-08-22 ~07:35 by orchestrator decision on human mandate** ("no deadlines — let the 25000-round budget complete", ~14:35 projected) ⇒ ceiling now **16:30 CEST 2026-08-22 (epoch 1787409000)**, enforced by a hard user-systemd net unit `sac-ceiling-net` (sleeps to the epoch, then kills the tmux session and any straggler harness processes). While HEALTHY per #55 discrimination rules the run continues; a monitor kills the tmux session at the ceiling or on an intervene threshold.

 **Fresh start**: pre-campaign `weights/` held #49-smoke 32-hidden checkpoints, incompatible with hidden=256. Archived to `weights_smoke49_backup/`; campaign baseline re-established by probe battles vs Corners (random-init hidden-256 checkpoint, `best_score.txt` reset then re-raised to 20 by a genuine eval). Twin regenerated via `./make_twin.sh` from that baseline (md5 `61521cff…` verified seed).

@@ -53,6 +53,9 @@ SACLSTM_SAVE_INTERVAL=5 \
 - **2026-08-22 00:30** — HEALTHY checklist passed (see below).
 - **2026-08-22 03:45** — Watch shift 1 (00:34–03:35): liveness flawless (10/10 HEALTHY, zero banners, zip ≤30 s). Learning signal: steady-state eval vs Corners 0–5% with two isolated 10/10 spikes (~01:15) → capability emerged, then lost. Eval-regression intervene threshold fired per #55; intervention DEFERRED to Campaign verdict (#57) — rationale: n=2 evidence, no loss metrics, buffer-loss on restart, run completes ~08:05 anyway. Milestone issue: #58 "Campaign-v1 watch: eval-regression threshold fired — intervention deferred to verdict".
 - **2026-08-22 ~07:15** — Morning audit: policy demonstrably learning off-benchmark (SacTwin 73→100%, Crazy 26→56%) while Corners eval stays ~0–9% with 3 transient 10/10s; wall-clock ceiling extended to let the 25k complete (~14:35 projected); instability-vs-plateau question left to the curve.
+- **2026-08-22 ~07:50 — score:60 anatomy**: Tank Royale survival(50)+last-survivor(10) awarded when opponent dies while we survive; exactly-60 ⇒ zero damage dealt by us that round (opponent self-destructed via wasted shots + 0.1/turn inactivity drain). 3,878 rounds (19%); modal vs SacTwin; vs Corners 986 damageless outlives vs 242 true wins; combined with 43% of rounds being score:0, texture = survivor-not-fighter against walls. RL rewards are event-driven (rewards module), so behavioral evidence, not reward poisoning. Feeds #57 levers: aggression shaping / specialist-vs-generalist.
+- **2026-08-22 ~08:05 — `.part` debris forensics + sweep**: 99 `*.zip.tmp.*.part` (483 MB) are NOT weights.nim debris (that proc uses fixed `.tmp` + finally-cleanup, working); naming matches an external write-temp→rename copier killed mid-write, bursts correlating with kill events; possible culprit: a folder-sync client fighting a file that changes every ~20 s (**human asked to confirm**). Swept with `-mmin +10` age guard (protects in-flight writes); 483 MB freed, real zips untouched — note 2 fresh `.part` reappeared minutes later, copier still active.
+- **2026-08-22 ~08:00 — ceiling defused**: the 12:22 'self-kill' was notebook prose instructing watchmen — never an OS mechanism; rewritten to 16:30 CEST AND armed a real systemd --user net `sac-ceiling-net` firing 16:30:00 (epoch 1787409000); training uninterrupted (counter +99/147 s verified); annotated #56 comment 487.

 ## Decision-issue index

@@ -107,7 +110,7 @@ tail -3 ~/Projects/SirRoboGarage/SAC_LSTM_Bot/campaign_stdout.log           # ev
 cat ~/Projects/SirRoboGarage/SAC_LSTM_Bot/weights/best_score.txt
 ```

-Intervene per #55 thresholds: ≥3 consecutive `crash #N` banners; ΔS4=0 over ≥15 min; zip mtime >10 min stale while S4 advances (STALLED); disk <1 GB. At the **ceiling (12:22 CEST Aug 22)**: `tmux kill-session -t sac_campaign` if still running — final state is in `weights/`, logs, and this notebook.
+Intervene per #55 thresholds: ≥3 consecutive `crash #N` banners; ΔS4=0 over ≥15 min; zip mtime >10 min stale while S4 advances (STALLED); disk <1 GB. At the **ceiling (16:30 CEST Aug 22, epoch 1787409000 — extended from 12:22 per human mandate)**: `tmux kill-session -t sac_campaign` if still running (the hard net unit `sac-ceiling-net` fires at the same epoch regardless of monitors) — final state is in `weights/`, logs, and this notebook.

 ## Results