Skip to main content

universal decay

Created on August 21|Last edited on August 22
Allow the plasticity to reach as low as -plast_clip. in this case, that's 1e2.

Select runs that logged avg_loss
to visualize data in this line chart.
Run set
0

Back to the lower cap for plasticity being 1e-15. Really just test if the decay value can be higher than plasticity.

Run set
0

have the decay match the lr.

Run set
0

compare

Run set
0

I went on to define a larger gap between the lr and the decay.
try:
  • very small layer size - vsmalllayer
  • much larger layer size - vlargelayer
  • larger decay rate - largedecay
  • incorporate negative plasticity again. - negplast

Run set
0

  • tinker with a significantly smaller plasticity

Run set
0