lars 893d91e749 Add KL divergence to marginal validation and hook it into the training loop ...

validate_marginals now estimates a per-dimension KL(real || generated) via
a shared histogram, alongside the existing mean/std comparison, so
distribution-shape drift shows up even when the first two moments match.

Wire it into giant/train.py: every validate_every epochs (default 10, 0
disables), the training loop runs validate_marginals against val_loader and
prints the table. validate_every flows through DEFAULT_CONFIG/config.toml
and is exposed as --validate-every on both giant train and scripts/train.py.

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

2026-06-18 13:45:12 +02:00

..

steps_to_parquet.py

Add ROOT-to-parquet conversion script with convert dependency group

2026-06-17 11:27:49 +02:00

train.py

Add KL divergence to marginal validation and hook it into the training loop

2026-06-18 13:45:12 +02:00