"""Degradation experiment: same as v1, but trained on a tiny slice of data.

Isolates *data quantity*. Only max_train_tokens changes from v1: the model sees
~1M training tokens instead of 555M. Expect overfitting — train loss falls while
val loss (measured on the full held-out set) climbs, and novel prompts collapse
as the model regurgitates memorized stories.

Tip: this overfits within a few thousand steps. Watch the val loss turn upward
in the log and stop early (Ctrl-C) rather than running all 20,000 steps.
"""

from dataclasses import replace

import v1

model = v1.model
train = replace(v1.train, max_train_tokens=1_000_000)