siweizzz

Check out Turn Base (implement and play board games using a DSL): https://turn-base.com/

Here's an original game implemented using this system: https://turn-base.com/games/lobby/22/ (Buy cards to summon and move chess pieces in a chess game) You'll need to grab a friend to play (no AI). Ping me in discord if the game doesn't make sense.

I made a website for people to play and prototype/playtest board games digitally

  - online, multiplayer gameplay
  - rules are enforced (using a DSL)
  - customize the look and feel using WYSIWYG editors

Proof of concept implemented using the system: https://turn-base.com/games/lobby/22/

I made a website for people to prototype and playtest/play board games

Quick summary:

  - online, multiplayer gameplay
  - rules are enforced (using a DSL)
  - customize the look and feel using WYSIWYG editors
  - modular: mix and match tokensets and boards across different games
  - bonus: videochat while you play

Deck Chess is a proof of concept for the system: https://turn-base.com/games/lobby/22/

Agreed there doesn’t seem to be a consensus. Thanks for the links

Thanks, good to have this data point. I’ve been training a roughly similarly sized dataset for many 10s of ks of steps (but on 355m). Wondering if I need so many steps.

Can you share how large your dataset (how many tokens) and batch size was and how many epochs you used? By training slowly, do you mean that you used a small learning rate? If so, what was it?

I've been reading up on batch size and people are all over the place. Some say smaller is better and some say larger is better. Mostly when it comes to gpt2 people say larger is better but there must come a point when increasing the batch size is no longer beneficial (or is it just that you use as large as your memory will allow)?