List your company

Language Modeling on LM1B ctx len. 128 (val)

25.72PPL (Val)MDLM† (Compl. masking)
25.64226.168526.69527.2215May 24, 2025

Evaluation results

MethodLinks
MDLM† (Compl. masking)#Params=170M, Batch size=32, Context length=128, Training batch size=2x larger2025.0525.723.781,081.57
PGM 6 / 6#Params=171M, Batch size=32, Context length=128, Encoder layers=6, Decoder layers=62025.0526.82.121,930.93
MDLM#Params=170M, Batch size=32, Context length=1282025.0527.673.781,081.57