Houston: We have lift off ...
Posted: Thu Nov 15, 2018 9:36 pm
an amazing chart - where will it end ?
Code: Select all
Rank Name Elo +/- Games Score Draws
SF8 120 68 60 66.7% 43.3%
1 lc0_v19_11261 0 111 20 50.0% 50.0%
2 lc0_v19_31214 -147 128 20 30.0% 40.0%
3 lc0_v19_9155 -241 127 20 20.0% 40.0%
Finished match
Remember that 30xxx nets haven't had considerable LR drops, yet.Laskos wrote: ↑Fri Nov 16, 2018 3:56 pm I don't know why you are so enthusiastic. Runs 20xxx and 30xxx are pretty pathetic, especially considering how much resources they have eaten up. Some folks there have overdone something. Just a quick check with the latest engine (rc4) and one of the latest nets:
TC: 60'' + 1''
So, run 30xxx is still ~150 Elo points below run 10xxx, and barely ~100 Elo points above 6x64 net 9155 (run 9xxx). Taking into account that the games with 6x64 net were 10-12 times faster and taking into account the hardware resources allocated, the whole run 9xxx could have been completed in less than a day. Lame runs, these newest ones. But I still hope that they will improve some 200 real Elo points over current level, although this is not granted at all.Code: Select all
Rank Name Elo +/- Games Score Draws SF8 120 68 60 66.7% 43.3% 1 lc0_v19_11261 0 111 20 50.0% 50.0% 2 lc0_v19_31214 -147 128 20 30.0% 40.0% 3 lc0_v19_9155 -241 127 20 20.0% 40.0% Finished match
is that a fact? 6x64 nets are only 100 elo below the best of the larger nets?Laskos wrote: ↑Fri Nov 16, 2018 3:56 pm I don't know why you are so enthusiastic. Runs 20xxx and 30xxx are pretty pathetic, especially considering how much resources they have eaten up. Some folks there have overdone something. Just a quick check with the latest engine (rc4) and one of the latest nets:
TC: 60'' + 1''
So, run 30xxx is still ~150 Elo points below run 10xxx, and barely ~100 Elo points above 6x64 net 9155 (run 9xxx). Taking into account that the games with 6x64 net were 10-12 times faster and taking into account the hardware resources allocated, the whole run 9xxx could have been completed in less than a day. Lame runs, these newest ones. But I still hope that they will improve some 200 real Elo points over current level, although this is not granted at all.Code: Select all
Rank Name Elo +/- Games Score Draws SF8 120 68 60 66.7% 43.3% 1 lc0_v19_11261 0 111 20 50.0% 50.0% 2 lc0_v19_31214 -147 128 20 30.0% 40.0% 3 lc0_v19_9155 -241 127 20 20.0% 40.0% Finished match
No, 250 Elo points below 10xxx run with large 20x256 net. But these 20xxx and 30xxx runs with large nets run for months with only 100 Elo points better results than small net. 20xxx is IIRC already abandoned after several LR droppings, and I think that by now the computing effort is larger than DeepMind learning effort with their enormous hardware for A0 learning.chrisw wrote: ↑Fri Nov 16, 2018 5:54 pmis that a fact? 6x64 nets are only 100 elo below the best of the larger nets?Laskos wrote: ↑Fri Nov 16, 2018 3:56 pm I don't know why you are so enthusiastic. Runs 20xxx and 30xxx are pretty pathetic, especially considering how much resources they have eaten up. Some folks there have overdone something. Just a quick check with the latest engine (rc4) and one of the latest nets:
TC: 60'' + 1''
So, run 30xxx is still ~150 Elo points below run 10xxx, and barely ~100 Elo points above 6x64 net 9155 (run 9xxx). Taking into account that the games with 6x64 net were 10-12 times faster and taking into account the hardware resources allocated, the whole run 9xxx could have been completed in less than a day. Lame runs, these newest ones. But I still hope that they will improve some 200 real Elo points over current level, although this is not granted at all.Code: Select all
Rank Name Elo +/- Games Score Draws SF8 120 68 60 66.7% 43.3% 1 lc0_v19_11261 0 111 20 50.0% 50.0% 2 lc0_v19_31214 -147 128 20 30.0% 40.0% 3 lc0_v19_9155 -241 127 20 20.0% 40.0% Finished match
Don't want to be too sophisticated, Thorsten, but "switching from quantity to quality", something we know in German even better as Friedrich Engels Dialektik der Natur, is a principal way of AI too, isn't it?