"""Degradation experiment: same as v1, but far fewer training steps.

Isolates *training time*. Only max_iters changes from v1 (20,000 -> 2,000).
The cosine LR schedule anneals fully within these 2,000 steps, so this is the
best model achievable in that budget — not v1 halted mid-schedule.
"""

from dataclasses import replace

import v1

model = v1.model
train = replace(v1.train, max_iters=2000)