[spam][crazy][ot] MCBoss Spinoffs 3
0xloem at gmail.com
Sun Jun 18 17:12:11 PDT 2023
ggml provides an opt function that performs training inside it based
on the number of iterations set in the parameters. this is why the
example code takes so many minutes to complete, it’s running the opt
pass 10k times on a single core. at a glance it looks like the
performance stats are near zero because they are disabled.
the example drops the loss of a single layer with params on the order
of 1k large to something 40% of its starting value in a few minutes.
a smidge frustrating that it blackboxes the training loop
More information about the cypherpunks