TalkChess.com

NN-testrun of Lc0 0.26.1 721051 (training-run 2 net) finished.

https://www.sp-cc.de

(Perhaps you have to clear your browsercache or reload the website)

Hi Jouni, LCO is for me not a chess program. It's nothing ... On 2 is Komodo. My Personal opinion! Hello Frank, Why did you have such a strange idea? Lc0 is an innovative chess engine. Of course it is. Would anybody say "Carlsen or Kasparov or Fischer "are nothing" and not innovative, because they ...

That's a nice list you have there... While not enough games to be definitive it certainly gives one an idea of which nets to try and which to stay away from. That was the idea. Because S.Vieri builds so much new nets, it is not possible to test them all with some thousand games using a "quite norma...

Jouni wrote: ↑

Tue Aug 04, 2020 12:16 pm

Note this is STC vs dev version. So clearly over +110 vs SF11. The net version is explained there, but not easily understand .

I asked S.Vieri on discord. He told me, it is the net 200801_1515. Not a good choice IMHO. One of the weakest nets of the last days of development in my tests.

Trained on Reinforcement Learn and fine tuned using CCRL games: https://www.dropbox.com/s/71qy3j8gtgch2ss/qh-fine-0803-5.zip?dl=0 How does this net fair against some of Sergio's more recent nets? I tested it vs. SF 200717, like all S.Vieri nets. Look here: https://www.sp-cc.de/files/ergebnisse_nnue...

SF framework has started testing now: ELO: 81.44 +-7.1 (95%) LOS: 100.0% Total: 5026 W: 1948 L: 791 D: 2287 Ptnml(0-2): 64, 348, 863, 843, 395 WOW! And next also NCM? The new default-net, used here in the SF framework, is a S.Vieri net, as far as I know. But I dont know, which net exactly. Could an...

Thank you for this, it is very useful. So far as I know, you are the only one performing this experiment. Thank you. I added the pre-test result-list to my website. https://www.sp-cc.de On the main page, in the website-news on top, you find a link: SF nnue pre-test results can be seen here If anybo...

As far as I know, no. Other engines have popcount compiles, only (named as "modern" in some cases (Stockfish)). But I will be more careful, of course. In the future, I will try all compiles of a new engine or new engine-version on my AMD-machine and will use the fastest compile. Because there are so...

From now, all engine-binaries are popcount/pext/avx2, of course, because bmi2-compiles are extremly slow on AMD. To keep the rating-list engine-names consistent, the "bmi2"-extension in the engine-name is still in use for older engines - otherwise ORDO will not calculate all played games by this en...

From now, all engine-binaries are popcount/pext/avx2, of course, because bmi2-compiles are extremly slow on AMD. To keep the rating-list engine-names consistent, the "bmi2"-extension in the engine-name is still in use for older engines - otherwise ORDO will not calculate all played games by this en...