320x24 Jh net is doing well in cccc bonus. Good news for upcoming T60 series!!

Discussion of anything and everything relating to chess playing software and machines.

Moderators: hgm, Harvey Williamson, bob

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
Post Reply
Nay Lin Tun
Posts: 501
Joined: Mon Jan 16, 2012 5:34 am

320x24 Jh net is doing well in cccc bonus. Good news for upcoming T60 series!!

Post by Nay Lin Tun » Sun Jul 14, 2019 2:53 am

As it is early era of NN, no one knows the optimum size of network for current consumer hardwares.

Although 20x256 are much stronger than 10x128 in 20xx RTX hardwares, bigger networks did not do well previously.

It is the first time to see this bigger net 320x24 doing well in cccc.

It is a very good news for upcoming T60 series with 320 x24 net.

Downlink for Jh 370 000 net. https://github.com/jhorthos/lczero-trai ... a-Training
Attachments
29402568_1524647878.0594.png
29402568_1524647878.0594.png (11.6 KiB) Viewed 374 times

User avatar
Eduard
Posts: 189
Joined: Fri Oct 26, 2018 10:58 pm
Location: Germany
Full name: Eduard Nemeth
Contact:

Re: 320x24 Jh net is doing well in cccc bonus. Good news for upcoming T60 series!!

Post by Eduard » Sun Jul 14, 2019 7:41 am

Thanks for the networks! The smaller 192x16 even run well on the smartphone. Nice thing.

Hai
Posts: 447
Joined: Sun Aug 04, 2013 11:19 am

Re: 320x24 Jh net is doing well in cccc bonus. Good news for upcoming T60 series!!

Post by Hai » Sun Jul 14, 2019 9:16 am

Nay Lin Tun wrote:
Sun Jul 14, 2019 2:53 am
As it is early era of NN, no one knows the optimum size of network for current consumer hardwares.

Although 20x256 are much stronger than 10x128 in 20xx RTX hardwares, bigger networks did not do well previously.

It is the first time to see this bigger net 320x24 doing well in cccc.

It is a very good news for upcoming T60 series with 320 x24 net.

Downlink for Jh 370 000 net. https://github.com/jhorthos/lczero-trai ... a-Training
Current consumer hardware: All available gpus, weakest to strongest.

Optimum is: stronger gpu = bigger network size, weaker gpu = smaller network size.

It was obvious that 24 x 320 size will be better when using strong gpus.

Even the 40 x 256 network was at least equal or even better than the 20 x 256, when using stronger gpus and more time.
Don't forget that 20 x 256 got 10 to 20 times more training games / new networks per day compared to the 40 x 256.
With this development speedup 20 x 256 should have been some hundreads of elos stronger than 40 x 256.
But it wasn't so it's a terrible result and a waste of ressources.

Post Reply