"""Degradation experiment: same as v1, but a much smaller model.

Isolates *capacity*. Only the model dimensions change; context length and the
training schedule match v1 exactly. ~0.38M params vs v1's 4.26M — and only
~0.1M of those are non-embedding (the 4,096-token embedding table dominates a
model this small, so the actual 'reasoning' capacity shrinks even harder).
"""

from dataclasses import replace

import v1

model = replace(v1.model, n_layers=2, d_model=64, n_heads=2, d_ff=256)
train = v1.train