e61e8f54da
Changes: - CLAUDE.md: Update OOM fix validation status - Add comprehensive documentation (30+ markdown reports) - LSTM encoder varmap bug fix (tft/lstm_encoder.rs:290) - Quantized LSTM layer matching fix (tft/quantized_lstm.rs) - Hyperopt paths module (ml/src/hyperopt/paths.rs) - Training path tests for all adapters (DQN, MAMBA-2, PPO, TFT) - Checkpoint integrity tests - Script cleanup: Remove 29 obsolete deployment scripts - Archive old scripts to scripts/archive/ - New deployment utilities: check_gpu_availability.py, monitor_hyperopt.sh Validation: - OOM fixes validated: 5/5 trials successful (pod b6kc3mc5lbjiro) - Batch-size-max 256 tested successfully - All hyperopt adapters working correctly 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
1.1 KiB
1.1 KiB
DQN Training Paths Quick Reference
Usage
Basic (with defaults)
use ml::hyperopt::adapters::dqn::DQNTrainer;
let trainer = DQNTrainer::new(&dbn_data_dir, epochs)?;
// Uses: /tmp/ml_training/training_runs/dqn/run_default/
Production (with custom paths)
use ml::hyperopt::adapters::dqn::DQNTrainer;
use ml::hyperopt::paths::{TrainingPaths, generate_run_id};
let run_id = generate_run_id("hyperopt");
let paths = TrainingPaths::new("/runpod-volume", "dqn", &run_id);
let trainer = DQNTrainer::new(&dbn_data_dir, epochs)?
.with_training_paths(paths);
// Uses: /runpod-volume/training_runs/dqn/run_{timestamp}_hyperopt/
CLI Example
cargo run -p ml --example hyperopt_dqn_demo --release --features cuda -- \
--dbn-data-dir test_data/real/databento/ml_training \
--base-dir /runpod-volume \
--run-type hyperopt \
--trials 10 \
--epochs 20
Directory Structure
{base_dir}/training_runs/dqn/run_{run_id}/
├── checkpoints/
├── logs/
├── hyperopt/
└── metrics/
Tests
cargo test -p ml --test dqn_adapter_paths_test
# 4/4 passing (100%)