You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
W23 is inherited from No.86 weight (9ac646d7) and other 5 weight after it , W24 is inherited from No.86(9ac646d7) and No.87(92dd0397) and other 7 weights between them.
And you can see the PO 200 match log in the zip file.
Then I put run them on CGOS, the parameter is :
LZ-HY-W23-PO1600: -g -p 1600 --noponder -t 1 -q -d -r 1 -w
LZ-HY-W24-PO1600: -g -p 1600 --noponder -t 1 -q -d -r 1 -w
LZ-HY-W24-NOLIMIT: -g --noponder -t 4 -q -d -r 1 -w
And there is many other leela zero weights run on cgos, such as LZ-0xx-p1600-t1-r1, StellarLZ-p6400, LeelaZero-test... I think LZ-HY-W23-PO1600 's parameter is same as LZ-0xx-p1600-t1-r1, so the result of them can compare.
And other LZ-0XX-p1600-t1-r1 is not close to static(<100 games), the score of them is all bellow the 2 hybrid weights, and to my experiment, the score of LZ-0XX-p1600-t1-r1 will continue to drop during 50 to 100 games process.
So after several test, in my opinion:
Hybrid can stronger the weights
Hybrid seem can promote 50-80 cgos elo of original weights (according to 150-250 leela zero self elo)
NOLIMIT is also get the best CGOS ELO of leela zero, so in the high playout game, "Hybrid" is also work.
Hybrid can also get weaker weights, a stronger hybrid weight mix with an original weight, often get a weaker one.
The text was updated successfully, but these errors were encountered:
leela-zero/leela-zero#954
To see the true power of the hybrid, I hybrid 2 weights and run it on cgos.
6w24_081&aed&a91&92d&9ac&8ee&f66&4d5&5e4.zip
6w23_f66&081&9ac&8ee&4d5&5e4_1&0.5&0.5&0.5&0.5&0.5 (2).zip
W23 is inherited from No.86 weight (9ac646d7) and other 5 weight after it , W24 is inherited from No.86(9ac646d7) and No.87(92dd0397) and other 7 weights between them.
And you can see the PO 200 match log in the zip file.
LZ-HY-W23-PO1600: -g -p 1600 --noponder -t 1 -q -d -r 1 -w
LZ-HY-W24-PO1600: -g -p 1600 --noponder -t 1 -q -d -r 1 -w
LZ-HY-W24-NOLIMIT: -g --noponder -t 4 -q -d -r 1 -w
And there is many other leela zero weights run on cgos, such as LZ-0xx-p1600-t1-r1, StellarLZ-p6400, LeelaZero-test... I think LZ-HY-W23-PO1600 's parameter is same as LZ-0xx-p1600-t1-r1, so the result of them can compare.
LZ-HY-W24-PO1600 3030
LZ-HY-W23-PO1600 3011
And other LZ-0XX-p1600-t1-r1 is not close to static(<100 games), the score of them is all bellow the 2 hybrid weights, and to my experiment, the score of LZ-0XX-p1600-t1-r1 will continue to drop during 50 to 100 games process.
So after several test, in my opinion:
The text was updated successfully, but these errors were encountered: