List your company

Language Modeling on OpenWebText ctx len. 1024 (val)

21.43PerplexityPGM 6 / 6 (dim. 1024)
21.364421.807222.2522.6928May 24, 2025

Evaluation results

MethodLinks
PGM 6 / 6 (dim. 1024)#Params=268M, Batch size=32, Context length=1024, Encoder layers=6, Decoder layers=6, Model dimension=10242025.0521.435.935,518.09
PGM 8 / 8#Params=203M, Batch size=32, Context length=1024, Encoder layers=8, Decoder layers=82025.0522.615.865,585.57
MDLM† (Compl. masking)#Params=170M, Batch size=32, Context length=1024, Training batch size=2x larger2025.0522.9831.411,043.22
MDLM#Params=170M, Batch size=32, Context length=10242025.0523.0731.411,043.22