Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Language Modeling on FineWeb-Edu 500M-token (val)

2.221Valid Loss

FusedKV

2.20282.325652.44852.57135Dec 3, 2025
Updated 4d ago

Evaluation Results

MethodLinks
2025.12
2.221
2025.12
2.225
2025.12
2.241
2025.12
2.244
2025.12
2.245
2025.12
2.258
2025.12
2.473
2025.12
2.474
2025.12
2.483
2025.12
2.497
2025.12
2.498
2025.12
2.511
2025.12
2.639
2025.12
2.642
2025.12
2.651
2025.12
2.662
2025.12
2.663
2025.12
2.676