idk if you're supposed to use it like this but you can

if you dont write your trainers from scratch tailored specifically for the needs of every new task you're... well probably normal but it's really fun once you get in the habit. plus you internalize how it works a lot better. plus lots of time to listen to new music

Crumb You're being a little hard on the model, you are pushing information through a really tight bottleneck into channels it isn't used to utilizing, y'know you could really- doooooont care shakes butt

there are thousands of steps where tens of steps happen... and there are tens of steps where thousands of steps happen...

like we are not in a 90s movie about The Future we are in the real world

i think there are much more profound endings we can reach if we just follow where the tech wants to go on its own

exploratory research vs Product Building research

expecting a lot of fun word embedding type arithmetic stuff to be possible here*
*once we train a vae so we can sample on the manifold

+ hopfully after this run and a context extension the broader system for wrapping human beings as reservoirs comes clearer into view, this model should be able to represent state as clearly as i want

+ higher more thorough range of n embed tokens explored, 1-128 instead of [4,8,16,32,64] after seeing first model exhibited some generalization to any n any way

+ this is one unified model instead of two separate models, preliminary testing showed "meh it should work probably"