PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs.
Oskar van der Wal, Pietro Lesci, Max Mller-Eberstein, Naomi Saphra, Hailey Schoelkopf, Willem H. Zuidema, Stella Biderman
Browse the full ICLR paper archive.
Oskar van der Wal, Pietro Lesci, Max Mller-Eberstein, Naomi Saphra, Hailey Schoelkopf, Willem H. Zuidema, Stella Biderman
Browse the full ICLR paper archive.