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

  • 2023-06-13 - 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, 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, 990 distinct users have uploaded 2,484,843,106 rows of training data, 48,393,699 training games, and 1,061,432 rating games.

In the last week, 46 distinct users have uploaded 18,281,668 rows of training data, 376,341 new training games, and 7,754 new rating games.

In the last 24h, 24 distinct users have uploaded 2,749,307 rows of training data, 56,057 new training games, and 1,205 new rating games.

Look up and view games for this run here.

Networks

A total of 658 networks have been uploaded for kata1.

Latest network: kata1-b18c384nbt-s7679674112-d3707123599

Strongest confidently-rated network: kata1-b18c384nbt-s7529928448-d3667707199

Approximate Elo Ratings Graph
Graph is based on about 1,061,432 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
水底2022 1,467,883 rows generated 29,884 training games 756 rating games
Friday9i 380,304 rows generated 7,739 training games 0 rating games
maomaochong 357,568 rows generated 7,317 training games 165 rating games
maxueba 198,185 rows generated 4,053 training games 87 rating games
zhgutov 56,093 rows generated 1,161 training games 24 rating games
Kabu 49,529 rows generated 1,007 training games 36 rating games
Bubblesld 39,858 rows generated 800 training games 40 rating games
dahuojiwo2 37,346 rows generated 804 training games 9 rating games
bash99 35,553 rows generated 715 training games 24 rating games
toledo 25,218 rows generated 530 training games 8 rating games
NoTakeOnlyWoe 16,935 rows generated 340 training games 20 rating games
ntkylin 16,458 rows generated 327 training games 8 rating games
Schelp76 13,545 rows generated 277 training games 4 rating games
mmming0123 12,360 rows generated 239 training games 0 rating games
egri-nagy 11,786 rows generated 248 training games 20 rating games

In the Last Week

User Training Rows Training Games Rating Games
水底2022 6,910,145 rows generated 142,545 training games 3,436 rating games
Friday9i 2,878,675 rows generated 58,777 training games 467 rating games
maomaochong 1,891,135 rows generated 39,142 training games 900 rating games
TheOnly92 1,298,774 rows generated 26,604 training games 597 rating games
maxueba 1,295,970 rows generated 26,495 training games 566 rating games
manrelygo 1,015,048 rows generated 20,674 training games 321 rating games
zhongtiao1 725,977 rows generated 15,388 training games 113 rating games
maverick 454,091 rows generated 9,258 training games 185 rating games
Bubblesld 285,611 rows generated 5,870 training games 200 rating games
dahuojiwo2 241,583 rows generated 5,180 training games 71 rating games
bash99 233,484 rows generated 4,779 training games 136 rating games
kppom 145,328 rows generated 2,980 training games 91 rating games
Miles 132,493 rows generated 2,708 training games 311 rating games
zhgutov 124,565 rows generated 2,588 training games 48 rating games
Kabu 99,167 rows generated 2,041 training games 72 rating games

Overall

User Training Rows Training Games Rating Games
yaoge123 361,070,317 rows generated 7,168,369 training games 112,353 rating games
luckyangman 342,435,207 rows generated 6,418,062 training games 140,115 rating games
AiqiGo 148,551,176 rows generated 2,819,086 training games 53,342 rating games
水底2022 136,465,694 rows generated 2,805,022 training games 65,426 rating games
Friday9i 131,850,610 rows generated 2,664,293 training games 43,119 rating games
jiusi010302 111,549,344 rows generated 2,157,135 training games 32,148 rating games
maomaochong 98,809,055 rows generated 2,010,365 training games 42,795 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
badukmegapack 54,869,275 rows generated 1,077,758 training games 17,807 rating games
kcwu 45,131,243 rows generated 865,458 training games 90,968 rating games
luotiany 35,864,232 rows generated 712,373 training games 7,915 rating games
菜鸟老树 35,287,206 rows generated 714,877 training games 10,876 rating games
Sponsorship 35,233,550 rows generated 668,781 training games 13,461 rating games