8d89fe80ff
- Archive: 85 agent .txt files → docs/archive/agents/legacy_txt/ - Scripts: Move 110 shell scripts → scripts/ (keep deploy.sh in root) - Models: Move 18 .safetensors → ml/models/checkpoints/training_artifacts/ - Delete: 34 directories (~33GB freed) - target/, coverage_*, test artifacts - Build: Clean 14 build artifacts (.rlib, .o, .pid, binaries) - Tests: Move 14 .rs files → tests/standalone/ - SQL: Move 5 files → sql/ (keep init-db*.sql for Docker) - Wave 153: Archive to docs/archive/historical/wave153/ - Docs: Archive 9 markdown files to wave_d/reports/ and historical/ Total impact: ~34GB freed (both waves), root directory cleaned from 583 to ~40 essential files Directory count reduced from 65 to 31 (52% reduction) All historical data preserved in organized archive structure
51 lines
1.6 KiB
Bash
51 lines
1.6 KiB
Bash
#!/bin/bash
|
|
# VarMap Fix Validation - Runpod Deployment
|
|
# Deploys MAMBA-2 with fixed binary for checkpoint integrity validation
|
|
|
|
set -e
|
|
|
|
echo "=========================================="
|
|
echo "MAMBA-2 VarMap Fix Validation"
|
|
echo "=========================================="
|
|
echo ""
|
|
echo "Configuration:"
|
|
echo " GPU: RTX A4000 (16GB, \$0.25/hr)"
|
|
echo " Binary: hyperopt_mamba2_demo (FIXED - uploaded 2025-10-29 08:43 UTC)"
|
|
echo " Dataset: ES_FUT_180d.parquet (225 features)"
|
|
echo " Trials: 2 (quick validation)"
|
|
echo " Epochs: 1 (fast cycle)"
|
|
echo " Batch size: 256 (optimal)"
|
|
echo " Expected runtime: ~10 minutes"
|
|
echo " Expected cost: ~\$0.04"
|
|
echo ""
|
|
|
|
# Correct command for the pod
|
|
COMMAND="/runpod-volume/binaries/hyperopt_mamba2_demo \
|
|
--parquet-file /runpod-volume/test_data/ES_FUT_180d.parquet \
|
|
--base-dir /runpod-volume/ml_training \
|
|
--run-type hyperopt \
|
|
--trials 2 \
|
|
--epochs 1 \
|
|
--batch-size-max 256 \
|
|
--seed 42"
|
|
|
|
echo "Command to run in pod:"
|
|
echo "$COMMAND"
|
|
echo ""
|
|
|
|
# Deploy using runpod_deploy.py
|
|
echo "Deploying pod..."
|
|
python3 scripts/runpod_deploy.py \
|
|
--gpu-type "RTX A4000" \
|
|
--binary hyperopt_mamba2_demo \
|
|
--dataset ES_FUT_180d.parquet \
|
|
--extra-args "--trials 2 --epochs 1 --batch-size-max 256 --base-dir /runpod-volume/ml_training"
|
|
|
|
echo ""
|
|
echo "=========================================="
|
|
echo "Pod deployed! Monitor with:"
|
|
echo " aws s3 ls s3://se3zdnb5o4/training_runs/mamba2/ --endpoint-url https://s3api-eur-is-1.runpod.io --recursive --human-readable"
|
|
echo ""
|
|
echo "Expected checkpoint size: 2-8MB (NOT 842KB)"
|
|
echo "=========================================="
|