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>
73 lines
1.7 KiB
Bash
Executable File
73 lines
1.7 KiB
Bash
Executable File
#!/bin/bash
|
|
# Check status of both hyperopt pods
|
|
source .env.runpod
|
|
|
|
DQN_POD_ID="dy2bn5ninzaxma"
|
|
PPO_POD_ID="dytpb1mcqwj54t"
|
|
|
|
echo "========================================="
|
|
echo "HYPEROPT PODS STATUS"
|
|
echo "========================================="
|
|
echo ""
|
|
|
|
# GraphQL query to get pod status
|
|
QUERY=$(cat <<'EOF'
|
|
{
|
|
myself {
|
|
pods {
|
|
id
|
|
name
|
|
desiredStatus
|
|
runtime {
|
|
uptimeInSeconds
|
|
}
|
|
machine {
|
|
gpuType {
|
|
displayName
|
|
}
|
|
dataCenterId
|
|
}
|
|
costPerHr
|
|
}
|
|
}
|
|
}
|
|
EOF
|
|
)
|
|
|
|
# Query RunPod API
|
|
RESPONSE=$(curl -s -X POST https://api.runpod.io/graphql \
|
|
-H "Content-Type: application/json" \
|
|
-H "Authorization: Bearer ${RUNPOD_API_KEY}" \
|
|
-d "{\"query\": $(echo "$QUERY" | jq -Rs .)}")
|
|
|
|
# Parse and display
|
|
echo "DQN Pod (${DQN_POD_ID}):"
|
|
echo "$RESPONSE" | jq -r ".data.myself.pods[] | select(.id == \"${DQN_POD_ID}\") |
|
|
\" Status: \(.desiredStatus)
|
|
GPU: \(.machine.gpuType.displayName)
|
|
Datacenter: \(.machine.dataCenterId)
|
|
Cost: $\(.costPerHr)/hr
|
|
Uptime: \(.runtime.uptimeInSeconds)s\""
|
|
echo ""
|
|
|
|
echo "PPO Pod (${PPO_POD_ID}):"
|
|
echo "$RESPONSE" | jq -r ".data.myself.pods[] | select(.id == \"${PPO_POD_ID}\") |
|
|
\" Status: \(.desiredStatus)
|
|
GPU: \(.machine.gpuType.displayName)
|
|
Datacenter: \(.machine.dataCenterId)
|
|
Cost: $\(.costPerHr)/hr
|
|
Uptime: \(.runtime.uptimeInSeconds)s\""
|
|
echo ""
|
|
|
|
echo "========================================="
|
|
echo "MONITORING URLS"
|
|
echo "========================================="
|
|
echo "Dashboard: https://www.runpod.io/console/pods"
|
|
echo ""
|
|
echo "DQN Logs:"
|
|
echo " https://www.runpod.io/console/pods/${DQN_POD_ID}"
|
|
echo ""
|
|
echo "PPO Logs:"
|
|
echo " https://www.runpod.io/console/pods/${PPO_POD_ID}"
|
|
echo ""
|