35feadf55e
## Major Achievements ### 1. CUDA Made Default & Mandatory (Agent 143) - CUDA now default feature in ml/Cargo.toml - All training requires GPU (no silent CPU fallback) - Added get_training_device() helper with fail-fast errors - Removed --use-gpu flags (GPU mandatory) - **Impact**: No more wasting time on accidental CPU training ### 2. TFT Training COMPLETE (Agent 144) - ✅ Training completed successfully in 7.6 minutes - ✅ Early stopping at epoch 100/200 (best val loss: 0.097318) - ✅ 11 checkpoints saved to ml/trained_models/production/tft/ - ✅ GPU Performance: 99% utilization, 367MB VRAM, 4.4s/epoch - ✅ 10x speedup vs CPU (4.4s vs 43-55s per epoch) - **Status**: PRODUCTION READY ### 3. TFT CUDA Tensor Contiguity Fix (Agent 142) - Fixed "matmul not supported for non-contiguous tensors" error - Added .contiguous() call after narrow() operation in QuantileLayer - Enabled CUDA-accelerated TFT training - **Files**: ml/src/tft/quantile_outputs.rs ### 4. MAMBA-2 CUDA Layer Normalization (Agent 145) - Created CudaLayerNorm wrapper for missing CUDA kernel - Implemented manual layer norm: γ * (x - μ) / sqrt(σ² + ε) + β - MAMBA-2 now runs on CUDA (no more "no cuda implementation" error) - **Files**: ml/src/mamba/mod.rs ### 5. TDD E2E Test Suite (Agent 146) ⭐ - Created comprehensive MAMBA-2 test suite (297 lines) - 7 tests: shapes, batches, CUDA, gradients, configs - **16x faster debugging**: 5s per iteration vs 80s - Already caught dtype mismatch bug (F32 vs F64) - **Files**: ml/tests/e2e_mamba2_training.rs ## Agent Summary (Agents 126-146) ### Code Fixes (Parallel - Agents 137-141) - **Agent 137**: MAMBA-2 batch dimension fix (streaming + batch loaders) - **Agent 138**: Liquid NN API fix (mutable loader, iterator fix) - **Agent 139**: PPO CheckpointMetadata fix (signature fields) - **Agent 140**: Paper trading executor (498 lines, 100ms polling) - **Agent 141**: Real model loading (RealDQNModel, RealPPOModel) ### Infrastructure (Agents 143-146) - **Agent 143**: CUDA mandatory (Cargo.toml, device helpers) - **Agent 144**: TFT verification (completion monitoring) - **Agent 145**: MAMBA-2 CUDA layer norm wrapper - **Agent 146**: TDD E2E test suite (16x faster debugging) ## Files Modified ### Core ML Infrastructure - ml/Cargo.toml: Added default = ["minimal-inference", "cuda"] - ml/src/lib.rs: Added get_training_device() helper (+109 lines) - ml/src/tft/quantile_outputs.rs: Fixed tensor contiguity - ml/src/mamba/mod.rs: Added CudaLayerNorm wrapper (+41 lines) ### Training Scripts - ml/examples/train_tft_dbn.rs: Removed --use-gpu flag - ml/examples/train_ppo.rs: Removed --use-gpu flag - ml/examples/train_mamba2_dbn.rs: Forced CUDA-only mode - ml/examples/train_liquid_dbn.rs: Fixed API usage ### Data Loaders - ml/src/data_loaders/dbn_sequence_loader.rs: Fixed batch dimensions - ml/src/data_loaders/streaming_dbn_loader.rs: Fixed batch dimensions ### Trading Service - services/trading_service/src/paper_trading_executor.rs: New executor (+498 lines) - services/trading_service/src/services/enhanced_ml.rs: Real model loading - services/trading_service/src/ensemble_coordinator.rs: Integration ### Tests - ml/tests/e2e_mamba2_training.rs: New TDD test suite (+297 lines) ### Trainers - ml/src/trainers/tft.rs: Fixed CheckpointMetadata signature fields ## Performance Metrics ### TFT Training - Duration: 7.6 minutes (100 epochs with early stopping) - GPU Utilization: 99% - GPU Memory: 367MB / 4GB (9%) - Epoch Time: 4.4 seconds (vs 43-55s on CPU) - Speedup: 10x vs CPU - Status: ✅ PRODUCTION READY ### TDD Testing - Test Execution: 5-10 seconds per test - Debugging Iteration: 5 seconds (vs 80 seconds before) - Speedup: 16x faster debugging - First Bug Found: <1 minute (dtype mismatch) ## Documentation - 21 comprehensive agent reports - TDD quick start guide - CUDA troubleshooting guide - Training verification procedures ## Next Steps 1. Fix MAMBA-2 dtype mismatch (F32→F64) - 2 minutes 2. Run MAMBA-2 tests until passing - 5-10 minutes 3. Launch full MAMBA-2 training - 200 epochs 4. Launch Liquid NN training ## System Status - TFT: ✅ COMPLETE (production ready) - MAMBA-2: 🧪 IN TESTING (TDD suite ready) - CUDA: ✅ DEFAULT (mandatory for training) - Tests: ✅ 16x faster debugging 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
70 lines
2.0 KiB
Bash
Executable File
70 lines
2.0 KiB
Bash
Executable File
#!/bin/bash
|
|
# TFT Training Restart Script (Agent 117)
|
|
# After Agent 112 TLOB Decoder fix
|
|
|
|
set -e
|
|
|
|
echo "=== TFT Training Restart ==="
|
|
echo "Timestamp: $(date)"
|
|
echo "GPU Status:"
|
|
nvidia-smi --query-gpu=name,memory.total,memory.used,temperature.gpu,utilization.gpu --format=csv,noheader
|
|
echo ""
|
|
|
|
echo "=== Pre-flight Checks ==="
|
|
echo "Checking for running training processes..."
|
|
if ps aux | grep -E "(train_tft|train_dqn|train_ppo)" | grep -v grep; then
|
|
echo "WARNING: Found running training processes!"
|
|
exit 1
|
|
fi
|
|
|
|
echo "Checking compilation status..."
|
|
cargo check -p ml 2>&1 | grep -E "(error|Finished)" | tail -5
|
|
|
|
echo "Checking output directory..."
|
|
mkdir -p ml/trained_models/production/tft_real_data
|
|
ls -la ml/trained_models/production/tft_real_data/
|
|
|
|
echo "Checking training data..."
|
|
echo "Available DBN files: $(find test_data/real/databento/ml_training -name '*.dbn' | wc -l)"
|
|
echo "Total size: $(du -sh test_data/real/databento/ml_training/)"
|
|
|
|
echo ""
|
|
echo "=== Starting TFT Training ==="
|
|
echo "Configuration:"
|
|
echo " - Epochs: 200"
|
|
echo " - Learning Rate: 0.001"
|
|
echo " - Batch Size: 32"
|
|
echo " - Lookback Window: 60"
|
|
echo " - Forecast Horizon: 10"
|
|
echo " - GPU: Enabled (CUDA_VISIBLE_DEVICES=0)"
|
|
echo " - Output: ml/trained_models/production/tft_real_data"
|
|
echo ""
|
|
|
|
# Log file
|
|
LOG_FILE="tft_training_$(date +%Y%m%d_%H%M%S).log"
|
|
echo "Logging to: $LOG_FILE"
|
|
echo ""
|
|
|
|
# Start training
|
|
RUST_LOG=info \
|
|
RUST_BACKTRACE=1 \
|
|
CUDA_VISIBLE_DEVICES=0 \
|
|
cargo run --release -p ml --example train_tft_dbn -- \
|
|
--data-path test_data/real/databento/ml_training \
|
|
--epochs 200 \
|
|
--learning-rate 0.001 \
|
|
--batch-size 32 \
|
|
--lookback-window 60 \
|
|
--forecast-horizon 10 \
|
|
--use-gpu \
|
|
--output-dir ml/trained_models/production/tft_real_data \
|
|
--early-stopping-patience 20 \
|
|
--early-stopping-threshold 0.0001 \
|
|
--verbose 2>&1 | tee "$LOG_FILE"
|
|
|
|
echo ""
|
|
echo "=== Training Complete ==="
|
|
echo "Final GPU status:"
|
|
nvidia-smi --query-gpu=memory.used,memory.total,temperature.gpu --format=csv,noheader
|
|
echo "Log saved to: $LOG_FILE"
|