- reports/samples-v1.md: 5 story-opening prompts sampled at temp 0.8 / top-k 200. Grammatical, coherent story arcs; expected sub-sweet-spot wobbles (plot logic, entity drift). All iteration-1 definition-of-done items now checked off.
- reports/loss-v1.csv: full train/val loss log over 20k steps - reports/loss-v1.txt: ASCII loss curve (steep descent then flattening tail) Training ran ~58 min on M1 MPS at 5.7 it/s. No overfitting (train~=val).
rzen