Skip to content
cccskills
FreePublished on GitHub

train-model

Train an ML model in the QuantConnect ML-Training-Pipeline with thermal-safe GPU usage and rigorous validation. Arguments: <architecture|script> [--dry-run] [--seeds 0,1,7,42,99] [--folds 5] [--bg]

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md4.0 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Train Model

Entrainer un modele ML du pipeline MyIA.AI.Notebooks/QuantConnect/ML-Training-Pipeline/ avec securite thermique GPU et validation rigoureuse. Couvre l'Epic #1454 (Training & Post-Training : RL/PPO, Decision Transformer, GenAI fine-tuning/LoRA).

Pour les cycles longs/batch, deleguer a l'agent training-specialist en async (run_in_background: true).

Arguments

  • <architecture|script> : nom court (lstm, transformer, mamba, patchtst, itransformer, moe, gnn, dqn-rl, decision-transformer) ou nom de script train_*.py.
  • --dry-run : smoke test CPU via validate_training_package.py --verbose (le script n'accepte pas --dry-run ; ses flags réels sont --verbose et --script — validate_training_package.py:148-149), sans GPU. Toujours commencer par la.
  • --seeds 0,1,7,42,99 : seeds pour le multi-seed (defaut >=4 parmi 0/1/7/42/99).
  • --folds 5 : walk-forward folds (defaut 5).
  • --bg : lancer le training en background (recommande pour les longs runs).

Process

Phase 0 — Environnement + grounding

  1. Activer l'env : & "C:\Users\MYIA\miniconda3\envs\coursia-ml-training\python.exe".
  2. Lire REGISTRY.md + CURRICULUM.md : le modele est-il deja un keeper valide ? deprecated ? Ne pas refaire.

Phase 1 — Dry-run CPU (HARD avant tout GPU)

python validate_training_package.py --verbose  # smoke test, pas de GPU (le script n'accepte pas --dry-run)

Si le dry-run echoue : reparer (pas contourner). Ne pas passer en GPU sur un package casse.

Phase 2 — Verifier le watchdog thermique (HARD)

python -c "from gpu_training import batch_thermal_check, get_gpu_temp; print('temp:', get_gpu_temp())"
  • Temperature non nulle => watchdog actif (MAX_TEMP=80C, cool_sleep=30, AMP).
  • ImportError ou temp 0 => protection thermique en no-op silencieux (gpu_training.py absent). NE PAS lancer un long run GPU sans protection : restaurer le module ou monitorer nvidia-smi manuellement. Documenter.

Phase 3 — Training

  • Lancer python scripts/train_<arch>.py (via env coursia-ml-training), en --bg pour les longs runs.
  • Noter l'ID du BG + nature attendue. Pendant le run, avancer une 2e track (2 tracks min, cf CLAUDE.md operations longues).
  • Check a intervalles utiles : tail -50 <log> | grep -E "FINAL|RESULT|ERROR|temp". Pas event-par-event.

Phase 4 — Validation rigoureuse (gate PR)

  • Walk-forward 5-fold (WalkForwardSplitter), pas single split.
  • >=4 seeds ; edge >= 2sigma cross-seed, sinon flag "noise".
  • DM significance (dm_test.py / diebold_mariano.py).
  • Comparaison majority_class_baseline + couts de transaction (5bps SPY, 10bps crypto).
  • Pas de FAANG/Mag7 en training set.
  • Verdict honnete : BEATS / NO BEATS / INCONCLUSIVE. Jamais "promising". Single-seed => [POC] explicite.

Phase 5 — Registry + livrable

  • python registry_update.py pour mettre a jour REGISTRY.md.
  • Checkpoints .pt volumineux/transients : ne pas stager dans la PR.
  • Rapport (metriques par seed/fold, verdict, DM p-value) sur le dashboard, pas dans un fichier du repo.
  • PR : un sujet, body avec WF + seeds + edge + baseline + tx costs + verdict (sinon CHANGES_REQUESTED).

Anti-patterns interdits

  • Sauter le dry-run et lancer direct en GPU.
  • Lancer un long run GPU sans verifier le watchdog importable (Phase 2).
  • Claim "BEATS" sans multi-seed + DM significance.
  • Python systeme au lieu de coursia-ml-training.
  • Stager des .pt lourds.

Voir aussi

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Cycle 30 min du secrétaire vérificateur myia-po-2028:CoursIA-3. Atteste en tiers, du plus ancien au plus récent, les PRs ouvertes sans dossier valide (chaque READY, une fois lu et approuvé par ai-01, est mergé sans attendre son cycle), et fait circuler l'information sur workspace-CoursIA-3.

The English summary is being prepared. Showing the original description.

jsboige/CoursIA16Updated Oct 21, 2026

Analyze a Slidev deck qualitatively — organ reports (structure, composition) + vision AI on rendered PNGs. Arguments: <deck_id> [--slides 1,5,10]

The English summary is being prepared. Showing the original description.

jsboige/CoursIA16Updated Oct 21, 2026

Build or improve Jupyter notebooks iteratively with quality scoring. Arguments: <new|improve|fix> <path> [--topic] [--domain] [--level] [--quality] [--max-iter]

The English summary is being prepared. Showing the original description.

jsboige/CoursIA16Updated Oct 21, 2026

Detect cell-ordering / enchainement problems in Jupyter notebooks (canonical-order slippage, misplaced or forgotten cells). Arguments: [target] [--severity HIGH|MED|LOW] [--json]

The English summary is being prepared. Showing the original description.

jsboige/CoursIA16Updated Oct 21, 2026

Clean up and reorganize markdown in enriched Jupyter notebooks. Arguments: [target] [--dry-run] [--aggressive] [--hierarchy-only]

The English summary is being prepared. Showing the original description.

jsboige/CoursIA16Updated Oct 21, 2026

Cycle de coordination ai-01 (coordinateur UNIQUEMENT — jamais sur un worker). Lit memoire + dashboards + inbox + GitHub, merge les PRs pretes, tranche les design-gates, dispatche des grains par lane, reporte. Arguments: [--dispatch] [--focus <topic>]

The English summary is being prepared. Showing the original description.

jsboige/CoursIA16Updated Oct 21, 2026

See all skills by jsboige

Report a problem with this skill