Files
foxhunt/backtest_dqn_trials.sh
jgrusewski 35feadf55e 🚀 Wave 160 Phase 6: CUDA Mandatory + TDD Testing + TFT Complete (21 Agents)
## 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>
2025-10-14 23:13:34 +02:00

155 lines
6.8 KiB
Bash
Executable File

#!/bin/bash
# Backtest all DQN trial checkpoints to determine best hyperparameters
set -e
RESULTS_FILE="dqn_backtest_results.json"
echo "[" > $RESULTS_FILE
echo 'Backtesting trial 0...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_0/checkpoint_epoch_10.safetensors
echo 'Backtesting trial 1...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_1/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 10...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_10/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 11...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_11/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 12...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_12/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 13...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_13/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 14...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_14/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 15...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_15/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 16...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_16/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 17...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_17/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 18...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_18/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 19...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_19/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 2...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_2/checkpoint_epoch_10.safetensors
echo 'Backtesting trial 20...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_20/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 21...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_21/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 22...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_22/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 23...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_23/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 24...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_24/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 25...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_25/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 26...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_26/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 27...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_27/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 28...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_28/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 29...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_29/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 3...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_3/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 30...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_30/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 31...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_31/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 32...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_32/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 33...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_33/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 34...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_34/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 35...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_35/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 4...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_4/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 5...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_5/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 6...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_6/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 7...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_7/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 8...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_8/checkpoint_epoch_50.safetensors
echo 'Backtesting trial 9...'
# TODO: Add actual backtest command here
# cargo run --example backtest_dqn -- --checkpoint ml/tuning_checkpoints/trial_9/checkpoint_epoch_50.safetensors
echo "]" >> $RESULTS_FILE
echo "Results saved to $RESULTS_FILE"