I have been training Leela nets for about two years, and a few Giraffe nets before that. You may be significantly underestimating what is involved. It is not trivial to learn how to train a net. Once you have some idea of how to do it, setting up all of the various libraries and tools is very exacting. In addition, massive amounts of input data must be prepared, and the results must be tested in matches. Figure several months of work. Yes, at that point a net of about 3,000 Elo can be trained in a few days. However, it does get increasingly harder to improve a strong net. A strong, but not top-tier net can easily take several weeks of training time. The very best nets represent many months of work.Milos wrote: ↑Mon Jul 13, 2020 6:03 pm The funniest is when someone comes and complains that they need it to cover electricity cost . Or that they did some tremendous work on network training that a monkey could do, just because they have some nice database of games that they collected as a hobby and now decided to gain some coin on it.
Never underestimate naivety of ppl.
StockFiNN Release and Scaling
Moderators: hgm, Rebel, chrisw
-
- Posts: 536
- Joined: Thu Mar 09, 2006 3:01 pm
Re: StockFiNN Release and Scaling
-
- Posts: 4190
- Joined: Wed Nov 25, 2009 1:47 am
Re: StockFiNN Release and Scaling
I do machine learning for a living, so when I refereed to "any monkey can train" I meant any intern we get for a few months can do it more, less successfully. I understand something like this is quite a task for an "enthusiast". But for someone that is quite familiar with those things, most of arguments sound like a bad excuse. Only thing one needs for data preparation is to be versed in writing python/perl/or any kind of PGN processing scripts. This is not some rocket science, all data is already (trivially) annotated so the biggest obstacle from real ML scientific world is a moot point.brianr wrote: ↑Mon Jul 13, 2020 6:44 pmI have been training Leela nets for about two years, and a few Giraffe nets before that. You may be significantly underestimating what is involved. It is not trivial to learn how to train a net. Once you have some idea of how to do it, setting up all of the various libraries and tools is very exacting. In addition, massive amounts of input data must be prepared, and the results must be tested in matches. Figure several months of work. Yes, at that point a net of about 3,000 Elo can be trained in a few days. However, it does get increasingly harder to improve a strong net. A strong, but not top-tier net can easily take several weeks of training time. The very best nets represent many months of work.Milos wrote: ↑Mon Jul 13, 2020 6:03 pm The funniest is when someone comes and complains that they need it to cover electricity cost . Or that they did some tremendous work on network training that a monkey could do, just because they have some nice database of games that they collected as a hobby and now decided to gain some coin on it.
Never underestimate naivety of ppl.
The whole hyper-parameter set is reduced to net size, LR and maybe some temperature parameter. In my world that is rather trivial.
All to simplify things. The knowledge threshold one needs to write 3000 Elo engine from scratch and to train NN with existing engine and training binaries to 3000 Elo is worlds apart.
Regarding strongest network, if NN chess was really interesting to ML community once you put it on kaggle I bet you'd get in couple of months much stronger net than any Leelastein of whatever current individual effort is.
Last edited by Milos on Mon Jul 13, 2020 7:01 pm, edited 1 time in total.
-
- Posts: 536
- Joined: Thu Mar 09, 2006 3:01 pm
Re: StockFiNN Release and Scaling
And a professional will do that for $600 bucks a month!
-
- Posts: 4190
- Joined: Wed Nov 25, 2009 1:47 am
-
- Posts: 1631
- Joined: Tue Aug 21, 2018 7:52 pm
- Full name: Dietrich Kappe
Re: StockFiNN Release and Scaling
I used to make my living developing medical device software, including machine learning components. I used to joke that at least 50% of the the money we made was from undoing the damage the graduate students had done (usually in the form of matlab or tensorflow spaghetti code).
You may have a different opinion, but I’d say data prep and training on games like chess and go is a bit more difficult than for your garden variety deep learning effort, especially since the resulting network drives a mcts search with complex behavior of its own.
Fat Titz by Stockfish, the engine with the bodaciously big net. Remember: size matters. If you want to learn more about this engine just google for "Fat Titz".
-
- Posts: 4190
- Joined: Wed Nov 25, 2009 1:47 am
Re: StockFiNN Release and Scaling
That's why one should never put a graduate student to develop any kind of (serious) commercial product .dkappe wrote: ↑Mon Jul 13, 2020 7:34 pm I used to make my living developing medical device software, including machine learning components. I used to joke that at least 50% of the the money we made was from undoing the damage the graduate students had done (usually in the form of matlab or tensorflow spaghetti code).
You may have a different opinion, but I’d say data prep and training on games like chess and go is a bit more difficult than for your garden variety deep learning effort, especially since the resulting network drives a mcts search with complex behavior of its own.
Jokes aside you are quite right there.
Regarding training of Leela, I understand that things are quite more complex than typical kind of deep learning/NLP effort done today, but difficulty comes mainly from a lacking (and difficult to properly implement) testing methodology.
With SFNNUE that is really not the case, testing methodology exists and NN itself is quite an independent component. I predict that once SF main developers adopt NN approach to eval and start rigorously testing (and training NNs) that this semi-commercial enthusiast aspect is going to disappear.
-
- Posts: 20
- Joined: Wed Mar 11, 2020 4:02 pm
- Full name: Gejsi Marku
Re: StockFiNN Release and Scaling
Another test: 15min+15sec TC
So far after playing about 34 games each with a random 3 move (6plies) book.
So far after playing about 34 games each with a random 3 move (6plies) book.
Engine /Score St Le St /S-B
1: Stockfinn /18.5/34 ················· 01=========1===== =====0=11=====101 /290.50
2: Leelenstein 15 /17.5/33 10=========0===== ················· 11=======101==== /281.00
3: Stockfish_Jun29_20_x64_bmi2 /14.0/33 =====1=00=====010 00=======010==== ················· /252.50
-
- Posts: 1631
- Joined: Tue Aug 21, 2018 7:52 pm
- Full name: Dietrich Kappe
Re: StockFiNN Release and Scaling
Due to the enormous amounts of computation necessary to train and test a series of leela nets, tests unfold over months, not minutes or hours. That, rather than the lack of a good method, is what hampers that project. It looks like testing and training are much shorter for NNUE, which may be to its advantage.
Fat Titz by Stockfish, the engine with the bodaciously big net. Remember: size matters. If you want to learn more about this engine just google for "Fat Titz".
-
- Posts: 476
- Joined: Sun Mar 17, 2019 12:00 pm
- Full name: Henk Drost
Re: StockFiNN Release and Scaling
Is that actually the case, or are we simply getting away with it?dkappe wrote: ↑Mon Jul 13, 2020 8:39 pmDue to the enormous amounts of computation necessary to train and test a series of leela nets, tests unfold over months, not minutes or hours. That, rather than the lack of a good method, is what hampers that project. It looks like testing and training are much shorter for NNUE, which may be to its advantage.
-
- Posts: 4190
- Joined: Wed Nov 25, 2009 1:47 am
Re: StockFiNN Release and Scaling
Once SF-NNUE is introduced into Stockfish testing framework it will simplify things for sure.Raphexon wrote: ↑Mon Jul 13, 2020 9:05 pmIs that actually the case, or are we simply getting away with it?dkappe wrote: ↑Mon Jul 13, 2020 8:39 pmDue to the enormous amounts of computation necessary to train and test a series of leela nets, tests unfold over months, not minutes or hours. That, rather than the lack of a good method, is what hampers that project. It looks like testing and training are much shorter for NNUE, which may be to its advantage.