added telemetric details to blog

final runs and update blog

fix: add training plots and clean up duplicate README headings

chore: refresh training artifacts and rename consume_reward_components to private

feat: add episode trace, refresh training dataset, and update eval metrics

feat: add OpenEnv TRL wrapper, expand dataset, and add W&B eval tracking

feat: add structured pruning action and random baseline policy

refactor: harden imports, add training extras, and rewrite README