GPT2XL_RLLMv10-wd-001,003,010
Collection
Spin-off experiments eg. what will happen if the v10/layer10's weight decay got increased or decreased....so yeah all these attempts failed..
โข
6 items
โข
Updated
A failed experiment. Lowered v10's weight decay from .005 to .003.
Interested? see RLLM Virtual map for more context.