List your company

Language Modeling on Language modeling objective (test)

2.341LossSMART
2.016244.208376.40058.59263Dec 24, 2025

Evaluation results

MethodLinks
SMARTParameters (M)=45.512025.122.3410.0091
GPT-2Parameters (M)=124.42025.122.7870.0029
Pure TransformerParameters (M)=522025.123.4560.0056
DistilBERTParameters (M)=89.82025.1210.430.0011
BERTParameters (M)=1332025.1210.460.0007