Everyone interested in LZ should be aware of this topic under discussion in the project.

gcp posted the following a few hours ago.

Hi all,

there's 500k games now without a network promoting. This means the training window is "full". I increased it to 750k games, and did a last learning rate lowering (0.00001 @ bs=96). If this doesn't result in a promotion, we've pretty much reached the end of the first training run, after just over 2 years.

As I stated before, I don't have enough time nor energy to contribute any more (Leela Zero was very successful and achieved much more than I set out for, but it also ate a lot of my time especially the first year...) so I will not set up a second training run myself. There's many options to go from here, from someone picking and choosing the most promising improvements that have been proposed here and elsewhere to do a Leela Zero 2.0, to joining the community behind one of the other initiatives that built upon what we started (obviously SAI, but I heard KataGo is considering setting up a distributed effort as well).

I plan to keep the training server running until the 31st of January (if necessary bumping the playout count to add some more high quality data to the pool). If the last learning rate drop miraculously sends us improving again, I can extend that, but for now I would say that the community should probably plan its next steps with that date in mind.

_________________
Dave Sigaty
"Short-lived are both the praiser and the praised, and rememberer and the remembered..."
- Marcus Aurelius; Meditations, VIII 21

"Hi all,

there's 500k games now without a network promoting. This means the training window is "full"."

Of course it's full, because every net size has a strength limit.
This is reached after net size ... is (perfectly) trained.

Now it's time to go for a bigger net size:)

There are now three new networks, though I don't have any idea of what that means for the big picture.

_________________
Occupy Babel!