New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
In the face of the power of minigo v15 000939 , 40b completely overestimates their winning percentage #2171
Comments
could you share a package of the minigo |
I got it from qq group
|
990 is uploaded here |
1005 _quantized 2-3 |
I quantized it with your modified script :) |
I tossed my own converted 939 up for a test run. Didn't do well, but it does much better in a time parity test (it's a 19b network). I'm using that net for the RoyalMinigo bot on OGS currently. |
Andrew and I played a 100 games at 5 seconds per move between minigo v15-939 and 201 if you're interested in more games. |
I also have a patch I'm testing that will add winrate to sgfs so that future ringmaster games will have eval curves |
@roy7 mini939 is much stronger than elfv1 read from the elo? |
Thanks for sharing the converted weights. Could you make test matches that show up on https://zero.sjeng.org/ always run for at least 400 games? |
Networks don't have perfect play or score estimation, nothing new and nothing to fix here. |
The reason I requested more games for the minigo match was because it is our only independent benchmark that our clients can run to test against and 83 games is not nearly enough to be meaningful. |
if there are some minigo weights stronger than lz of that time in the future, (it is possible because of google's resources) |
minigo v16 40b is training |
https://www.youtube.com/watch?v=FKinqyTv4h0&t=505s
However, this is not a single example
The text was updated successfully, but these errors were encountered: