"""Degradation experiment: same as v1, but a smaller context window.

Isolates *long-range coherence*. Only context_length changes from v1
(256 -> 64). Local fluency should survive; callbacks and plot threads that span
more than a few sentences should break sooner.

Honest caveat: shrinking context also lowers tokens/step (batch * context), so
this run sees fewer total tokens than v1 over the same number of steps. The
qualitative coherence effect is still the dominant, visible change.
"""

from dataclasses import replace

import v1

model = replace(v1.model, context_length=64)
train = v1.train