Seth 67179f75ad Self-play data + mortdecai-sites container + Grafana 3-GPU dashboard ...

Self-play: 218+ examples from overnight 3-GPU run (3090 Ti + 2080 Ti + RTX 4000)
Now running independently per GPU (no synchronization bottleneck)
50 rounds/tier, 0.1s sleep — near 100% GPU utilization

Infrastructure:
- CT 650 (mortdecai-sites) on pve112: landing page + docs + Gitea
- mortdec.ai landing page live
- docs.mortdec.ai MkDocs with Material theme
- git.mortdec.ai Gitea instance (fresh, needs admin setup)
- GPU exporter on RTX 4000 (node-197)
- Mortdecai GPU Monitoring dashboard in Grafana (all 3 GPUs)
- DNS updated via SethDDNS (GCP + Cloudflare)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-03-20 08:06:51 -04:00

..

processed

Self-play data + mortdecai-sites container + Grafana 3-GPU dashboard

2026-03-20 08:06:51 -04:00

raw

26 death/environment training examples, Mortdecai v4 deployed

2026-03-20 00:26:50 -04:00

ingest_audit.py

Add audit log ingestion pipeline with language/leak filtering

2026-03-18 17:58:52 -04:00

schema.json

Risk gradient (0-5), updated system prompts, 233 examples

2026-03-18 16:14:54 -04:00

scrape_server_logs.py

Minecraft knowledge corpus, recipe trees, GitHub scraper, 644 examples

2026-03-18 20:33:09 -04:00

validate_dataset.py

Initial project scaffold: dataset schema, 31 seed training examples, Mineflayer bot framework, and 7-phase roadmap

2026-03-18 01:51:28 -04:00