jgrusewski
6e40e86c09
perf: constrain hyperopt search space + increase H100 experience episodes
Hyperopt:
- num_atoms: 51-201 → 11-51 (GPU profile caps to hardware limit)
- hidden_dim_base: 256-1024 → 128-512 (1024+ is wasteful for 2-layer net)
- Prevents wildly oversized networks (num_atoms=200 caused 25s/epoch)
H100 experience:
- gpu_n_episodes: 256 → 2048 (8x larger cuBLAS batch saturates 132 SMs)
- gpu_timesteps_per_episode: 500 → 100 (fewer steps, more parallel episodes)
- Total experiences: 204K/epoch (was 128K) with better GPU utilization
- Expected: experience 357ms → ~100ms (SM utilization 5% → 40%+)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>