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

Language Modeling on Language Modeling Dataset

6.79Cross-Entropy Loss

CGAD

-12.4424117.3763247.195377.0137May 9, 2026
Updated 5d ago

Evaluation Results

MethodLinks
2026.05
6.79-
2026.05
7.44-
2026.05
7.48-
2026.05
8.04-
2026.05
8.46-
2026.05
8.96-
2026.05
9.7-
2026.05
9.94-
2026.05
10.39-
2026.05
10.48-
2026.05
10.9-
2026.05
11.1-
2026.05
11.28-
2026.05
11.3-
2026.05
11.3-
2026.05
11.44-
2026.05
11.69-
2026.05
11.69-
2026.05
11.69-
2026.05
11.7-
2026.05
46.69-
2026.05
65.31-
2026.05
170.9-
2026.05
241.2-
2026.05
319-
2026.05
487.6-
2025.12
-9.17
2025.12
-8.31
2025.12
-14.04
2025.12
-11.72
2025.12
-12.18
2025.12
-16.36
2025.12
-16.32
2025.12
-15.31
2025.12
-16.65
2025.12
-40.83
2025.12
-43.11
2025.12
-39.4
2025.12
-54.59
2026.05
-17.48
2026.05
-22.05
2026.05
-26.37
2026.05
-21.27
2026.05
-24
2026.05
-37.5