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

  • 2025-04-22 - Added a new page to the site with some special extra networks not part of the main run!

  • 2025-04-10 - KataGo v1.16.0 is released! Among other things, this version records new training data that could be used for training experimental action-value heads, enabling cool future research and potential search improvements. If no major bugs or other issues are discovered with this release in the next few days, then we will want to have all contributors upgrade so that the official run can begin accumulating this data over the next months for research.

  • 2024-05-02 - First "b28" neural net uploaded! This new larger neural net runs more slowly, similar to the old 60-block nets, but should be much stronger. From tests on discord, under normal usage this series of nets should be stronger than the b18 nets given equal total time, despite the slower speed, and be by far the strongest nets so far on a per-visit basis. We've also upgraded contributing to require KataGo v1.14.0 or later to support this net.

  • 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, 1248 distinct users have uploaded 3,492,611,010 rows of training data, 69,436,908 training games, and 1,439,410 rating games.

In the last week, 60 distinct users have uploaded 17,828,009 rows of training data, 380,301 new training games, and 5,374 new rating games.

In the last 24h, 38 distinct users have uploaded 2,470,163 rows of training data, 52,958 new training games, and 996 new rating games.

Look up and view games for this run here.

Networks

A total of 793 networks have been uploaded for kata1.

Latest network: kata1-b28c512nbt-s8656493312-d4716438223

Strongest confidently-rated network: kata1-b28c512nbt-s8536703232-d4684449769

Approximate Elo Ratings Graph
Graph is based on about 1,439,410 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.

Graph is based on games at equal visits rather than equal compute time, since the former is easier to control on widely varying user hardware. Larger/slower networks will be advantaged due to getting more total compute time. Given particular hardware, one can approximately correct for this by benchmarking to measure the speed difference, each doubling of speed may be worth somewhere around 150-250 Elo.

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

Approx Elo given equal time rather than equal visits (might NOT be accurate, varies with hardware)

Top Contributors

See here for a full list of contributors for kata1.

In the Last 24h

User Training Rows Training Games Rating Games
Isla 464,716 rows generated 9,905 training games 131 rating games
congxinzhisong 386,223 rows generated 8,223 training games 0 rating games
xkas 272,720 rows generated 5,851 training games 58 rating games
Friday9i 188,033 rows generated 4,042 training games 150 rating games
Bubblesld 184,656 rows generated 3,906 training games 32 rating games
TheOnly92 143,660 rows generated 3,022 training games 44 rating games
zhongtiao1 138,342 rows generated 3,202 training games 12 rating games
maxueba 103,567 rows generated 2,196 training games 60 rating games
xinjing 59,232 rows generated 1,304 training games 12 rating games
家疼跑谱 57,379 rows generated 1,213 training games 0 rating games
monk 52,936 rows generated 1,126 training games 328 rating games
tenuki 52,717 rows generated 1,130 training games 24 rating games
rwk 48,175 rows generated 1,036 training games 24 rating games
ez4u 46,619 rows generated 997 training games 13 rating games
Schelp76 40,718 rows generated 856 training games 8 rating games

In the Last Week

User Training Rows Training Games Rating Games
congxinzhisong 4,202,289 rows generated 89,375 training games 0 rating games
Isla 3,141,446 rows generated 66,725 training games 1,232 rating games
xkas 2,533,086 rows generated 53,994 training games 366 rating games
Bubblesld 1,104,972 rows generated 23,528 training games 305 rating games
TheOnly92 1,009,408 rows generated 21,506 training games 286 rating games
Friday9i 939,289 rows generated 19,942 training games 671 rating games
凤鸣. 732,584 rows generated 15,574 training games 0 rating games
maxueba 597,161 rows generated 12,797 training games 242 rating games
rwk 346,196 rows generated 7,363 training games 144 rating games
ez4u 315,549 rows generated 6,766 training games 80 rating games
zhanghong64 292,374 rows generated 6,314 training games 72 rating games
xinjing 257,234 rows generated 5,585 training games 88 rating games
tenuki 201,285 rows generated 4,309 training games 99 rating games
monk 179,552 rows generated 3,827 training games 355 rating games
lbnmg 176,086 rows generated 3,724 training games 66 rating games

Overall

User Training Rows Training Games Rating Games
yaoge123 426,223,037 rows generated 8,513,497 training games 136,620 rating games
luckyangman 342,435,207 rows generated 6,418,062 training games 140,115 rating games
水底2022 264,920,064 rows generated 5,461,179 training games 127,379 rating games
Friday9i 174,421,002 rows generated 3,544,284 training games 51,811 rating games
maomaochong 154,865,895 rows generated 3,190,439 training games 57,157 rating games
AiqiGo 148,551,176 rows generated 2,819,086 training games 53,342 rating games
jiusi010302 111,549,344 rows generated 2,157,135 training games 32,148 rating games
maxueba 86,837,305 rows generated 1,791,584 training games 38,678 rating games
TheOnly92 81,887,063 rows generated 1,698,056 training games 30,466 rating games
VegetableKnife 79,204,855 rows generated 1,470,688 training games 23,367 rating games
zhongtiao1 70,737,101 rows generated 1,497,396 training games 12,041 rating games
katavip.net 70,355,820 rows generated 1,379,526 training games 18,872 rating games
luotiany 68,489,704 rows generated 1,403,829 training games 9,775 rating games
jameswen429 65,701,378 rows generated 1,211,481 training games 30,013 rating games
badukmegapack 56,396,438 rows generated 1,110,332 training games 18,335 rating games