3853988af7
- Fixed PSO budget calculation bug in ml/src/hyperopt/optimizer.rs - Root cause: Division by n_particles in sequential execution - Now correctly calculates max_iters = remaining_trials (no division) - Result: 50 trials complete instead of 23 (100% vs 46%) - Added comprehensive DQN hyperopt results analysis - 39/50 trials analyzed across 2 RunPod deployments - Best hyperparameters identified: LR 4.89e-5 (ultra-low) - Created DQN_HYPEROPT_RESULTS_SUMMARY.md with expert validation - GitLab CI/CD pipeline operational (48 lines fixed) - Fixed YAML syntax errors (unquoted colons) - All 7 jobs validated and working - Warning cleanup complete (136 → 0 warnings) - Removed 143 lines dead code - Fixed visibility, unused imports, Debug traits - Archived Wave D reports to docs/archive/ - 8 early stopping reports moved - Root directory cleaned up 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
51 lines
1.3 KiB
Plaintext
51 lines
1.3 KiB
Plaintext
================================
|
|
HYPEROPT DEPLOYMENT QUICK REF
|
|
================================
|
|
Deployment: 2025-11-02 09:58:52
|
|
Status: ✅ RUNNING
|
|
|
|
POD IDs
|
|
-------
|
|
DQN: dy2bn5ninzaxma
|
|
PPO: dytpb1mcqwj54t
|
|
|
|
GPU & COST
|
|
----------
|
|
Both: RTX A4000 @ $0.25/hr
|
|
Location: EUR-IS-1
|
|
Total: $0.09-$0.18 (10-25 min)
|
|
|
|
MONITORING
|
|
----------
|
|
Status: ./check_hyperopt_pods.sh
|
|
DQN Logs: https://www.runpod.io/console/pods/dy2bn5ninzaxma
|
|
PPO Logs: https://www.runpod.io/console/pods/dytpb1mcqwj54t
|
|
|
|
RESULTS (after completion)
|
|
---------------------------
|
|
DQN: s3://se3zdnb5o4/ml_training/dqn_hyperopt_20251102_095852/
|
|
PPO: s3://se3zdnb5o4/ml_training/ppo_hyperopt_20251102_095852/
|
|
|
|
Download:
|
|
aws s3 sync s3://se3zdnb5o4/ml_training/dqn_hyperopt_20251102_095852/ ./results/dqn/ --profile runpod
|
|
aws s3 sync s3://se3zdnb5o4/ml_training/ppo_hyperopt_20251102_095852/ ./results/ppo/ --profile runpod
|
|
|
|
TERMINATION
|
|
-----------
|
|
Script: ./terminate_hyperopt_pods.sh
|
|
|
|
OBJECTIVE FIX
|
|
-------------
|
|
DQN: Validation loss → Episode rewards (prevents batch collapse)
|
|
PPO: Policy+value loss → Episode rewards (finds asymmetric LRs)
|
|
|
|
DEPLOYMENT METHOD
|
|
-----------------
|
|
Script: ./deploy_hyperopt_direct.sh
|
|
Method: Direct REST API (bypasses Python dependency issues)
|
|
Image: jgrusewski/foxhunt-hyperopt:latest (2025-11-02 09:32:29)
|
|
|
|
DOCS
|
|
----
|
|
Full: HYPEROPT_DEPLOYMENT_SUMMARY.md
|