sldbench

v1.0

SLDBench: A benchmark for scaling law discovery with symbolic regression tasks.

uvx harbor run -d sldbench@1.0

Tasks (8)

data_constrained_scaling_law
uvx harbor run -d sldbench@1.0 -t data_constrained_scaling_law
5a5ac64
domain_mixture_scaling_law
uvx harbor run -d sldbench@1.0 -t domain_mixture_scaling_law
5a5ac64
easy_question_scaling_law
uvx harbor run -d sldbench@1.0 -t easy_question_scaling_law
5a5ac64
lr_bsz_scaling_law
uvx harbor run -d sldbench@1.0 -t lr_bsz_scaling_law
5a5ac64
moe_scaling_law
uvx harbor run -d sldbench@1.0 -t moe_scaling_law
5a5ac64
parallel_scaling_law
uvx harbor run -d sldbench@1.0 -t parallel_scaling_law
5a5ac64
sft_scaling_law
uvx harbor run -d sldbench@1.0 -t sft_scaling_law
5a5ac64
vocab_scaling_law
uvx harbor run -d sldbench@1.0 -t vocab_scaling_law
5a5ac64