Skip positions to target a distribution #173
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
skips positions to target a prescribed distribution of positions with number of pieces. Uses i*(32-i)/(16*16)+1 Introduces a max skipping factor of 15. Needs some further work to make this optional and more flexible.
vondele
added a commit
to vondele/Stockfish
that referenced
this pull request
Apr 19, 2022
train a net using training data with a heavier weight on positions having 16 pieces on the board. More specifically, with a relative weight of `i * (32-i)/(16 * 16)+1` (where i is the number of pieces on the board). This is done with the trainer branch official-stockfish/nnue-pytorch#173 The command used is: ``` python train.py $datafile $datafile $restarttype $restartfile --gpus 1 --threads 4 --num-workers 12 --random-fen-skipping=3 --batch-size 16384 --progress_bar_refresh_rate 300 --smart-fen-skipping --features=HalfKAv2_hm^ --lambda=1.00 --max_epochs=$epochs --seed $RANDOM --default_root_dir exp/run_$i ``` The datafile is T60T70wIsRightFarseerT60T74T75T76.binpack, the restart is from the master net. passed STC: LLR: 2.94 (-2.94,2.94) <0.00,2.50> Total: 22728 W: 6197 L: 5945 D: 10586 Ptnml(0-2): 105, 2453, 6001, 2695, 110 https://tests.stockfishchess.org/tests/view/625cf944ff677a888877cd90 passed LTC: LLR: 2.94 (-2.94,2.94) <0.50,3.00> Total: 35664 W: 9535 L: 9264 D: 16865 Ptnml(0-2): 30, 3524, 10455, 3791, 32 https://tests.stockfishchess.org/tests/view/625d3c32ff677a888877d7ca Bench: 7269563
vondele
added a commit
to vondele/Stockfish
that referenced
this pull request
Apr 19, 2022
train a net using training data with a heavier weight on positions having 16 pieces on the board. More specifically, with a relative weight of `i * (32-i)/(16 * 16)+1` (where i is the number of pieces on the board). This is done with the trainer branch official-stockfish/nnue-pytorch#173 The command used is: ``` python train.py $datafile $datafile $restarttype $restartfile --gpus 1 --threads 4 --num-workers 12 --random-fen-skipping=3 --batch-size 16384 --progress_bar_refresh_rate 300 --smart-fen-skipping --features=HalfKAv2_hm^ --lambda=1.00 --max_epochs=$epochs --seed $RANDOM --default_root_dir exp/run_$i ``` The datafile is T60T70wIsRightFarseerT60T74T75T76.binpack, the restart is from the master net. passed STC: LLR: 2.94 (-2.94,2.94) <0.00,2.50> Total: 22728 W: 6197 L: 5945 D: 10586 Ptnml(0-2): 105, 2453, 6001, 2695, 110 https://tests.stockfishchess.org/tests/view/625cf944ff677a888877cd90 passed LTC: LLR: 2.94 (-2.94,2.94) <0.50,3.00> Total: 35664 W: 9535 L: 9264 D: 16865 Ptnml(0-2): 30, 3524, 10455, 3791, 32 https://tests.stockfishchess.org/tests/view/625d3c32ff677a888877d7ca closes official-stockfish#3989 Bench: 7269563
Member
|
I think we should merge this as is, because official-stockfish/Stockfish#4020 is based on patches on top of this. |
Member
Author
|
OK, it is correct and functional, so can be merged as is. |
dav1312
pushed a commit
to dav1312/Stockfish
that referenced
this pull request
Oct 21, 2022
train a net using training data with a heavier weight on positions having 16 pieces on the board. More specifically, with a relative weight of `i * (32-i)/(16 * 16)+1` (where i is the number of pieces on the board). This is done with the trainer branch official-stockfish/nnue-pytorch#173 The command used is: ``` python train.py $datafile $datafile $restarttype $restartfile --gpus 1 --threads 4 --num-workers 12 --random-fen-skipping=3 --batch-size 16384 --progress_bar_refresh_rate 300 --smart-fen-skipping --features=HalfKAv2_hm^ --lambda=1.00 --max_epochs=$epochs --seed $RANDOM --default_root_dir exp/run_$i ``` The datafile is T60T70wIsRightFarseerT60T74T75T76.binpack, the restart is from the master net. passed STC: LLR: 2.94 (-2.94,2.94) <0.00,2.50> Total: 22728 W: 6197 L: 5945 D: 10586 Ptnml(0-2): 105, 2453, 6001, 2695, 110 https://tests.stockfishchess.org/tests/view/625cf944ff677a888877cd90 passed LTC: LLR: 2.94 (-2.94,2.94) <0.50,3.00> Total: 35664 W: 9535 L: 9264 D: 16865 Ptnml(0-2): 30, 3524, 10455, 3791, 32 https://tests.stockfishchess.org/tests/view/625d3c32ff677a888877d7ca closes official-stockfish#3989 Bench: 7269563
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
skips positions to target a prescribed distribution of positions with number of pieces.
Uses i*(32-i)/(16*16)+1
Introduces a max skipping factor of 15.
Needs some further work to make this optional and more flexible.