Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Masked Language Modeling on BERT MLM small (val)
Loading...
6.9412
Validation Loss
SE-GEM
6.59414
6.76767
6.9412
7.11473
Apr 23, 2026
Validation Loss
Standard Deviation
Train Loss
Change in GELU
Updated 1mo ago
Evaluation Results
Method
Method
Links
Validation Loss
Standard Deviation
Train Loss
Change in GELU
SE-GEM
epsilon=10, Steps=3,00...
2026.04
6.9412
0.035
39.99
0.253
Feedback
Search any
task
Search any
task