chessforyou Bettina&Terry77
chessforyou Bettina&Terry77
chessforyou Bettina&Terry77
Would you like to react to this message? Create an account in a few clicks or log in to continue.

chessforyou Bettina&Terry77


 
HomeLatest imagesRegisterLog in
WELCOME TO FORUM OF Angels77 * named in memory of Bettina & Terry
Search
 
 

Display results as :
 
Rechercher Advanced Search
Search
 
 

Display results as :
 
Rechercher Advanced Search
Latest topics
Latest topics
Navigation
 Portal
 Index
 Memberlist
 Profile
 FAQ
 Search
Navigation
 Portal
 Index
 Memberlist
 Profile
 FAQ
 Search
Forum
Forum
Affiliates
free forum
 


Affiliates
free forum
 



 

 Latest abrok Development Version December 30th Update default net to nn-b1e55edbea57.nnue (SF The gift that keeps on giving

Go down 
AuthorMessage
LondonFrau
Admin
Admin
LondonFrau


Female Posts : 1292
Reputation : 3534
Join date : 2010-02-27
Location : ???

Latest abrok Development Version December 30th Update default net to nn-b1e55edbea57.nnue     (SF The gift that keeps on giving Empty
PostSubject: Latest abrok Development Version December 30th Update default net to nn-b1e55edbea57.nnue (SF The gift that keeps on giving   Latest abrok Development Version December 30th Update default net to nn-b1e55edbea57.nnue     (SF The gift that keeps on giving EmptySun Dec 31, 2023 11:39 am


Windows x64 for modern computers + AVX2
Windows x64 for modern computers
Windows x64 + SSSE3
Windows x64
Linux x64 for Haswell CPUs
Linux x64 for modern computers + AVX2
Linux x64 for modern computers
Linux x64 + SSSE3
Linux x64
Author: Linmiao Xu
Date: Sat Dec 30 11:08:03 2023 +0100
Timestamp: 1703930883

Update default net to nn-b1e55edbea57.nnue

Created by retraining the master big net `nn-0000000000a0.nnue` on the same
dataset with the ranger21 optimizer and more WDL skipping at training time.

More WDL skipping is meant to increase lambda accuracy and train on fewer
misevaluated positions where position scores are unlikely to correlate
with game outcomes. Inspired by:
- repeated reports in discord #events-discuss about SF misplaying due to wrong endgame
evals, possibly due to Leela's endgame weaknesses reflected in training data
- an attempt to reduce the skewed dataset piece count distribution where there
are much more positions with less than 16 pieces, since the target piece count
distribution in the trainer is symmetric around 16

The faster convergence seen with ranger21 is meant to:
- prune experiment ideas more quickly since fewer epochs are needed to reach elo maxima
- research faster potential trainings by shortening each run

```yaml
experiment-name: 2560-S7-Re-514G-ranger21-more-wdl-skip
training-dataset: /data/S6-514G.binpack
early-fen-skipping: 28

start-from-engine-test-net: True
nnue-pytorch-branch: linrock/nnue-pytorch/r21-more-wdl-skip

num-epochs: 1200
lr: 4.375e-4
gamma: 0.995
start-lambda: 1.0
end-lambda: 0.7
```

Experiment yaml configs converted to easy_train.sh commands with:
https://github.com/linrock/nnue-tools/blob/4339954/yaml_easy_train.py

Implementations based off of Sopel's NNUE training & experimentation log:
https://docs.google.com/document/d/1gTlrr02qSNKiXNZ_SuO4-RjK4MXBiFlLE6jvNqqMkAY
- Experiment 336 - ranger21 https://github.com/Sopel97/nnue-pytorch/tree/experiment_336
- Experiment 351 - more WDL skipping

The version of the ranger21 optimizer used is:
https://github.com/lessw2020/Ranger21/blob/b507df6/ranger21/ranger21.py

The dataset is the exact same as in:
https://github.com/official-stockfish/Stockfish/pull/4782

Local elo at 25k nodes per move:
nn-epoch619.nnue : 6.2 +/- 4.2

Passed STC:
https://tests.stockfishchess.org/tests/view/658a029779aa8af82b94fbe6
LLR: 2.93 (-2.94,2.94) <0.00,2.00>
Total: 46528 W: 11985 L: 11650 D: 22893 Elo +2.50
Ptnml(0-2): 154, 5489, 11688, 5734, 199

Passed LTC:
https://tests.stockfishchess.org/tests/view/658a448979aa8af82b95010f
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 265326 W: 66378 L: 65574 D: 133374 Elo +1.05
Ptnml(0-2): 153, 30175, 71254, 30877, 204

This was additionally tested with the latest DualNNUE and passed SPRTs:

Passed STC vs. https://github.com/official-stockfish/Stockfish/pull/4919
https://tests.stockfishchess.org/tests/view/658bcd5c79aa8af82b951846
LLR: 2.93 (-2.94,2.94) <0.00,2.00>
Total: 296128 W: 76273 L: 75554 D: 144301 Elo +0.84
Ptnml(0-2): 1223, 35768, 73617, 35979, 1477

Passed LTC vs. https://github.com/official-stockfish/Stockfish/pull/4919
https://tests.stockfishchess.org/tests/view/658c988d79aa8af82b95240f
LLR: 2.95 (-2.94,2.94) <0.50,2.50>
Total: 75618 W: 19085 L: 18680 D: 37853 Elo +1.86
Ptnml(0-2): 45, 8420, 20497, 8779, 68

closes https://github.com/official-stockfish/Stockfish/pull/4942

Bench: 1304666
see source

_________________
Bettina...............The greatest happiness of life is the conviction that we are loved.

Victor Hugo

vv56 likes this post

Back to top Go down
 
Latest abrok Development Version December 30th Update default net to nn-b1e55edbea57.nnue (SF The gift that keeps on giving
Back to top 
Page 1 of 1
 Similar topics
-
» Latest abrok Development Version December 4th Update default net to nn-cdf1785602d6.nnue (SF The gift that keeps on giving
» Latest abrok Development Version December 13th Update default net to nn-d93927199b3d.nnue (SF The gift that keeps on giving
» Latest abrok Development Version December 22nd Update default net to nn-ac07bd334b62.nnue (SF The gift that keeps on giving
» Latest abrok Development Version July 6 th Update default net to nn-c38c3d8d3920.nnue (SF The gift that keeps on giving
» Latest abrok Development Version August 5th Update default net to nn-46832cfbead3.nnue (SF The gift that keeps on giving )

Permissions in this forum:You cannot reply to topics in this forum
chessforyou Bettina&Terry77 :: ENGlNES :: ALL ENGlNES :: ENGlNES & CODES :: Stockfish-
Jump to: