Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Optimal Batch Size Scaling on Li dataset 2025 (train val)
Loading...
0.667
Scaling Parameter
3TL
0.005144
0.176972
0.3488
0.520628
Jul 1, 2026
Scaling Parameter
Updated 23d ago
Evaluation Results
Method
Method
Links
Scaling Parameter
3TL
Comment=From (4), data...
2026.07
0.667
Step-Law
Reference=(Li et al.,...
2026.07
0.58
DeepSeek-AI et al.
Reference=(DeepSeek-AI...
2026.07
0.086
Bergsma et al.
Reference=(Bergsma et...
2026.07
0.0306
Feedback
Search any
task
Search any
task