Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Public Pretraining Dataset

Benchmarks

Task NameDataset NameSOTA ResultTrend
Language ModelingPublic Pretraining Dataset OOD
Loss1.606
4
Language ModelingPublic Pretraining Dataset (train)
Loss1.33
4
Showing 2 of 2 rows