Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language Modeling on WikiText-2 32768 context length (val)
Loading...
2.048
Loss
NTK+affine
2.03924
2.09837
2.1575
2.21663
Jun 3, 2026
Loss
Updated 1mo ago
Evaluation Results
Method
Method
Links
Loss
NTK+affine
Train context length=1...
2026.06
2.048
YaRN+affine
Train context length=1...
2026.06
2.267
Feedback
Search any
task
Search any
task