pith. sign in

We use the Pile-CC validation loss as the target predicted loss

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

citing papers explorer

Showing 1 of 1 citing paper.

  • RegMix-D: Dynamic Data Mixing via Proxy Training Trajectories cs.CL · 2026-06-17 · unverdicted · none · ref 18

    RegMix-D fits regression models to proxy loss trajectories to produce dynamic data mixture schedules that outperform static RegMix and DoReMi on 25B-token Pile pretraining with a 1B model.