Data is doing more of the work than it used to. Every source in our mixture is a curated artifact built with large models

Training a model this small on them is distillation

When models of this size were last studied seriously such corpora did not exist

blog: https://gregdiamos.com/2026/09/07/outrageously-small-neural-...

X discussion: https://x.com/GregoryDiamos/status/2096873745420075020?s=20

I added some of the main points to the thread so they are easier to read.

The loss does not saturate. Across a 4.91B-token run, smoothed training loss falls monotonically within each curriculum phase and is still descending at the end