KataGo Distributed Training

About This Run

KataGo is a strong open-source self-play-trained Go engine, with many improvements to accelerate learning (arXiv paper and further techniques since). It can predict score and territory, play handicap games reasonably, and handle many board sizes and rules all with the same neural net.

This site hosts KataGo's first public-distributed training run! With the help of volunteers, we are attempting to resume training from the end of KataGo's previous official run ("g170") that ended in June 2020, and see how much further we can go. If would like to contribute, see below!

Updates

  • 2023-12-28 - KataGo v1.14.0 is released! This version adds support for a new larger and hopefully stronger "b28" neural net that will likely be ready within the next months. It also has a large number of more minor bugfixes and changes.

  • 2023-06-13 - We are upgraded now - kata1-b18c384nbt-s6582M is the first 18-nested-block neural net with the new improved output heads! You will need to be on version v1.13.0 or later to use the nets from here onward.

  • 2023-05-23 - KataGo v1.13.0 is released! Supports a new version of neural nets with improved output heads for policy and error prediction and various other analysis and search and training improvements. Once most or all contributors upgrade, we will be able to switch to the improved nets. If you're an active contributor please upgrade when you can!

  • 2023-03-04 - We're fully switched to v1.12 now and the first new net of the new architecture, b18c384nbt, has been uploaded for testing! Note the learning rate has been kept far higher than every other network, so it might not be as strong yet as the "uec" version of the new net on the releases page.

  • 2023-02-18 - KataGo is now up to version v1.12.4, with some bugfixes for training data generation! Once enough users are upgraded to this version and particularly off of v1.11, we can try the new improved b18 net and architecture for rating games and data generation. Please upgrade if you can!

  • 2023-01-07 - New release of KataGo, v1.12.0, supporting a new neural net architecture! The new net, b18-uec is about as strong as the 60-block nets but should be faster to run.

  • 2022-05-16 - Disabling support for versions older than v1.11.0 in selfplay data contribution so that we can make full use of new graph search parameters for search during selfplay.

  • 2022-03-20 - KataGo v1.11.0 is released! New graph search algorithm instead of tree search, and various parameter improvements.

  • 2022-01-27 - Switching to 60-block net for selfplay data contribution! 40-block net will continue to be trained as well on the data and be rated as well.

Downloading KataGo

If you simply want to run KataGo, the latest releases are here and you can download the latest networks from here. You very likely want a GUI as well, because the engine alone is command-line-only. Some possible GUIs include KaTrain, LizzieYzy, Lizzie, and q5Go, more can be found searching online.

How to Contribute

Contributors are much appreciated! If you'd like to contribute your spare GPU cycles to generate training data for the run, the steps are:

First, create an account on this site, picking a username and secure password. Make sure to verify your email so that the site considers your account fully active. Note: the username you pick will be publicly visible in statistics and on the games you contribute.

Then pick one of the following methods.

Likely easiest method, for a home desktop computer:

  • Download and install KaTrain
  • Inside the GUI menu, select the option for distributed training, provide the username and password for the account you created, and choose a few settings, then just let it run!

Command line method: if running on a remote server, or have already set up KataGo for other things, or if you want a command line that will work in the background without any GUI, or want slightly more flexibility to configure things:

  • Download KataGo from the latest release.
  • Edit the contribute_example.cfg that came when you downloaded KataGo, use a text editor to fill in your username, password, and the few different settings you want.
  • Run it on the command line like: ./katago contribute -config contribute_example.cfg on Linux, or katago.exe contribute -config contribute_example.cfg on Windows. If it is working, it should print out various stats as it runs, including when it finishes and uploads a game.

Either way, once some games are finished, you can view the results at https://katagotraining.org/contributions/ - scroll down and find your username! If anything looks unusual or buggy about the games, or KataGo is behaving weirdly on your machine, please let us know, so we can avoid uploading and training on bad data. Or, if you encounter any error messages, feel to ask for help on KataGo's GitHub or the Discord chat.

For advanced users, instead of downloading a release, you can also build it from source. If you do so, use the stable branch, NOT the master branch. The example config can be found in cpp/configs/contribute_example.cfg

And if you're interested contribute to development via coding, or have a cool idea for a tool, check out either KataGo's GitHub or the this website's GitHub, and/or the Discord chat where various devs hang out. If you want to test a change that affects the distributed client and you need a test server to experiment with modified versions of KataGo, it is available at test.katagodistributed.org, contact lightvector or tychota in Discord for a testing account.

Stats for kata1

This run is named kata1 and began on 2020-11-28 20:23:43 UTC.

Data Generation

Across all time, 1092 distinct users have uploaded 3,027,133,177 rows of training data, 59,587,132 training games, and 1,275,203 rating games.

In the last week, 44 distinct users have uploaded 4,943,542 rows of training data, 102,373 new training games, and 2,450 new rating games.

In the last 24h, 27 distinct users have uploaded 683,096 rows of training data, 14,241 new training games, and 419 new rating games.

Look up and view games for this run here.

Networks

A total of 732 networks have been uploaded for kata1.

Latest network: kata1-b18c384nbt-s9761732864-d4253420187

Strongest confidently-rated network: kata1-b18c384nbt-s9131461376-d4087399203

Approximate Elo Ratings Graph
Graph is based on about 1,275,203 rating games using mid to high hundreds of playouts. Ratings might still be mildly inflated due to only playing other KataGo nets, but otherwise are fresh and unbiased and involve a variety of nets to avoid rock-paper-scissors. Vertical bars indicate approximately a 95% confidence interval.

Click and drag to zoom. Double-click or click on a button to reset zoom.

Top Contributors

See here for a full list of contributors for kata1.

In the Last 24h

User Training Rows Training Games Rating Games
yaoge123 133,914 rows generated 2,825 training games 47 rating games
maxueba 115,168 rows generated 2,390 training games 110 rating games
rwk 82,564 rows generated 1,716 training games 44 rating games
Bubblesld 77,636 rows generated 1,580 training games 63 rating games
Miles 39,800 rows generated 810 training games 0 rating games
dahuojiwo2 35,414 rows generated 799 training games 14 rating games
gnaij 34,918 rows generated 711 training games 28 rating games
lbnmg 25,215 rows generated 524 training games 12 rating games
Odobenus 22,126 rows generated 437 training games 12 rating games
tenuki 21,691 rows generated 468 training games 12 rating games
alan 18,146 rows generated 371 training games 24 rating games
YangZ 13,915 rows generated 292 training games 8 rating games
egri-nagy 11,143 rows generated 240 training games 4 rating games
zhanghong64 10,335 rows generated 220 training games 12 rating games
kppom 6,464 rows generated 135 training games 0 rating games

In the Last Week

User Training Rows Training Games Rating Games
maxueba 821,875 rows generated 16,933 training games 488 rating games
maomaochong 765,403 rows generated 15,895 training games 309 rating games
Bubblesld 629,980 rows generated 12,940 training games 418 rating games
rwk 563,702 rows generated 11,577 training games 295 rating games
gnaij 453,999 rows generated 9,367 training games 216 rating games
Miles 274,359 rows generated 5,606 training games 0 rating games
dahuojiwo2 263,960 rows generated 5,779 training games 69 rating games
tenuki 150,841 rows generated 3,176 training games 100 rating games
zhanghong64 140,723 rows generated 2,919 training games 79 rating games
yaoge123 133,914 rows generated 2,825 training games 47 rating games
YangZ 94,815 rows generated 1,938 training games 60 rating games
lbnmg 88,652 rows generated 1,797 training games 32 rating games
egri-nagy 85,782 rows generated 1,751 training games 28 rating games
Odobenus 84,224 rows generated 1,719 training games 56 rating games
tkg1984 53,342 rows generated 1,094 training games 16 rating games

Overall

User Training Rows Training Games Rating Games
yaoge123 416,834,418 rows generated 8,317,253 training games 133,350 rating games
luckyangman 342,435,207 rows generated 6,418,062 training games 140,115 rating games
水底2022 260,997,256 rows generated 5,377,999 training games 126,468 rating games
Friday9i 164,193,275 rows generated 3,327,003 training games 44,140 rating games
AiqiGo 148,551,176 rows generated 2,819,086 training games 53,342 rating games
maomaochong 127,693,965 rows generated 2,609,653 training games 56,616 rating games
jiusi010302 111,549,344 rows generated 2,157,135 training games 32,148 rating games
VegetableKnife 79,204,855 rows generated 1,470,688 training games 23,367 rating games
katavip.net 70,355,820 rows generated 1,379,526 training games 18,872 rating games
jameswen429 65,701,378 rows generated 1,211,481 training games 30,013 rating games
TheOnly92 63,185,422 rows generated 1,306,794 training games 26,522 rating games
maxueba 56,486,594 rows generated 1,152,783 training games 26,536 rating games
badukmegapack 55,508,247 rows generated 1,091,185 training games 18,053 rating games
菜鸟老树 45,478,004 rows generated 924,134 training games 13,920 rating games
kcwu 45,131,243 rows generated 865,458 training games 90,968 rating games