jgrusewski 6a8f8d7b50 fix(train): correct CLI args for hyperopt vs training binaries ...

hyperopt_baseline_rl uses --output (JSON file path), while
train_baseline_rl uses --output-dir (checkpoint directory).
Split arg generation by preset.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-09 22:39:02 +01:00

25 KiB

Executable File

Raw Blame History

View Raw