Skip to content

Conversation

@vondele
Copy link
Member

@vondele vondele commented May 22, 2021

trained with pytorch using the master branch and recommended settings,
same data set as previously used:

python train.py ../../all_d9_fishd9_d8_d10_shuffle.binpack ../../all_d9_fishd9_d8_d10_shuffle.binpack
--gpus 1 --threads 2 --num-workers 2 --batch-size 16384 --progress_bar_refresh_rate 300
--smart-fen-skipping --random-fen-skipping 3 --features=HalfKAv2^ --lambda=1.0
--max_epochs=400 --seed $RANDOM --default_root_dir exp/run_8

passed STC:
LLR: 2.93 (-2.94,2.94) <-0.50,2.50>
Total: 21424 W: 2078 L: 1907 D: 17439
Ptnml(0-2): 80, 1512, 7385, 1627, 108
https://tests.stockfishchess.org/tests/view/60a6c749ce8ea25a3ef03f4d

passed LTC:
LLR: 2.94 (-2.94,2.94) <0.50,3.50>
Total: 67912 W: 2851 L: 2648 D: 62413
Ptnml(0-2): 40, 2348, 28984, 2537, 47
https://tests.stockfishchess.org/tests/view/60a722ecce8ea25a3ef03fb9

Bench: 3779522

trained with pytorch using the master branch and recommended settings,
same data set as previously used:

python train.py ../../all_d9_fishd9_d8_d10_shuffle.binpack ../../all_d9_fishd9_d8_d10_shuffle.binpack \
        --gpus 1 --threads 2 --num-workers 2 --batch-size 16384 --progress_bar_refresh_rate 300 \
        --smart-fen-skipping --random-fen-skipping 3 --features=HalfKAv2^   --lambda=1.0 \
        --max_epochs=400 --seed $RANDOM --default_root_dir exp/run_8

passed STC:
LLR: 2.93 (-2.94,2.94) <-0.50,2.50>
Total: 21424 W: 2078 L: 1907 D: 17439
Ptnml(0-2): 80, 1512, 7385, 1627, 108
https://tests.stockfishchess.org/tests/view/60a6c749ce8ea25a3ef03f4d

passed LTC:
LLR: 2.94 (-2.94,2.94) <0.50,3.50>
Total: 67912 W: 2851 L: 2648 D: 62413
Ptnml(0-2): 40, 2348, 28984, 2537, 47
https://tests.stockfishchess.org/tests/view/60a722ecce8ea25a3ef03fb9

Bench: 3779522
@vondele vondele closed this in fb2d175 May 22, 2021
@snicolet
Copy link
Member

snicolet commented May 22, 2021

congrats :-)

Do you remember the difference between the previous settings and the recommended settings you have used here for the pytorch trainer ?

@vondele
Copy link
Member Author

vondele commented May 22, 2021

some small changes were merged between the development branch I used for training before and the master branch I used for this one. However, there is also quite some variance from run to run, so one can find a better net by luck.

@snicolet snicolet added the to be merged Will be merged shortly label Jun 2, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

to be merged Will be merged shortly

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants