Stockfish 2023061113 NNUE for Windows and Linux, interesting compiled by Linmiao Xu (Elo +2.64)

Stockfish 2023061113 - UCI chess engine, compiled by Linmiao Xu
Rating CEDR=3732

Timestamp: 1686489832

Update default net to nn-ea57bea57e32.nnue

Created by retraining an earlier epoch (ep659) of the experiment that led to the first SFNNv6 net:

- First retrained on the nn-0dd1cebea573 dataset

- Then retrained with skip 20 on a smaller dataset containing unfiltered Leela data

- And then retrained again with skip 27 on the nn-0dd1cebea573 dataset

The equivalent 7-step training sequence from scratch that led here was:

1. max-epoch 400, lambda 1.0, constant LR 9.75e-4, T79T77-filter-v6-dd.min.binpack

ep379 chosen for retraining in step2

2. max-epoch 800, end-lambda 0.75, T60T70wIsRightFarseerT60T74T75T76.binpack

ep679 chosen for retraining in step3

3. max-epoch 800, end-lambda 0.75, skip 28, nn-e1fb1ade4432 dataset

ep799 chosen for retraining in step4

4. max-epoch 800, end-lambda 0.7, skip 28, nn-e1fb1ade4432 dataset

ep759 became nn-8d69132723e2.nnue (first SFNNv6 net)

ep659 chosen for retraining in step5

5. max-epoch 800, end-lambda 0.7, skip 28, nn-0dd1cebea573 dataset

ep759 chosen for retraining in step6

6. max-epoch 800, end-lambda 0.7, skip 20, leela-dfrc-v2-T77decT78janfebT79aprT80apr.binpack

ep639 chosen for retraining in step7

7. max-epoch 800, end-lambda 0.7, skip 27, nn-0dd1cebea573 dataset

ep619 became nn-ea57bea57e32.nnue

For the last retraining (step7):

python3 easy_train.py

--experiment-name L1-1536-Re6-masterShuffled-ep639-sk27-Re5-leela-dfrc-v2-T77toT80small-Re4-masterShuffled-ep659-Re3-sameAs-Re2-leela96-dfrc99-16t-v2-T60novdecT80juntonovjanfebT79aprmayT78jantosepT77dec-v6dd-Re1-LeelaFarseer-new-T77T79 \

--training-dataset /data/leela96-dfrc99-T60novdec-v2-T80juntonovjanfebT79aprmayT78jantosepT77dec-v6dd-T80apr.binpack \

--nnue-pytorch-branch linrock/nnue-pytorch/misc-fixes-L1-1536 \

--early-fen-skipping 27 \

--start-lambda 1.0 \

--end-lambda 0.7 \

--max_epoch 800 \

--start-from-engine-test-net False \

--start-from-model /data/L1-1536-Re5-leela-dfrc-v2-T77toT80small-epoch639.nnue \

--lr 4.375e-4 \

--gamma 0.995 \

--tui False \

--seed $RANDOM \

--gpus "0,"

For preparing the step6 leela-dfrc-v2-T77decT78janfebT79aprT80apr.binpack dataset:

python3 interleave_binpacks.py \

leela96-filt-v2.binpack \

dfrc99-16tb7p-eval-filt-v2.binpack \

test77-dec2021-16tb7p.no-db.min-mar2023.binpack \

test78-janfeb2022-16tb7p.no-db.min-mar2023.binpack \

test79-apr2022-16tb7p-filter-v6-dd.binpack \

test80-apr2022-16tb7p.no-db.min-mar2023.binpack \

/data/leela-dfrc-v2-T77decT78janfebT79aprT80apr.binpack

The unfiltered Leela data used for the step6 dataset can be found at:

https://robotmoon.com/nnue-training-data

Local elo at 25k nodes per move:

nn-epoch619.nnue : 2.3 +/- 1.9

Passed STC:

https://tests.stockfishchess.org/tests/view/6480d43c6e6ce8d9fc6d7cc8

LLR: 2.94 (-2.94,2.94) <0.00,2.00>

Total: 40992 W: 11017 L: 10706 D: 19269 Elo +2.64

Ptnml(0-2): 113, 4400, 11170, 4689, 124

Passed LTC:

https://tests.stockfishchess.org/tests/view/648119ac6e6ce8d9fc6d8208

LLR: 2.94 (-2.94,2.94) <0.50,2.50>

Total: 129174 W: 35059 L: 34579 D: 59536 Elo +1.29

Ptnml(0-2): 66, 12548, 38868, 13050, 55

closes https://github.com/official-stockfish/Stockfish/pull/4611

bench: 2370027

Stockfish rating progress:

Engine	Rating	Score	Games	(%)
Stockfish 20230227	3732.4	92.00	134	68.66
Stockfish 241022	3724.2	64.00	112	57.14
Stockfish 031022	3720.9	110.50	158	69.94
Stockfish 070922	3718.9	123.00	164	75.00
Stockfish 20230325	3718.5	109.00	169	64.50
Stockfish 20221107	3717.8	106.50	186	57.26
Stockfish 20230308 Ivec	3717.6	79.00	120	65.83
Stockfish 301022	3717.6	112.00	175	64.00
Stockfish 20230218	3715.1	110.50	164	67.38
Stockfish 20230128	3713.1	69.00	106	65.09
Stockfish 290522 Ivec	3711.0	113.00	144	78.47
Stockfish 080622 Ivec	3709.7	94.50	133	71.05
Stockfish 161022	3709.5	147.00	240	61.25
Stockfish 20221123	3709.5	247.50	356	69.52
Stockfish dev-20230520	3708.9	106.50	174	61.21
Stockfish 20221224	3707.4	65.50	104	62.98
Stockfish dev-20230503 Ivec	3706.8	168.50	234	72.01
Stockfish 101022 Ivec	3705.6	82.50	138	59.78
Stockfish 20230308	3705.2	167.00	259	64.48
Stockfish 040722	3705.0	308.50	433	71.25
Stockfish 20230114	3704.6	295.00	410	71.95
Stockfish 20230314	3704.6	119.50	200	59.75
Stockfish 20221221	3703.6	165.00	267	61.80
Stockfish 061122 Ivec	3703.2	130.00	201	64.68
Stockfish 20230314 Ivec	3701.2	94.00	137	68.61
Stockfish dev-20230505	3700.7	97.50	172	56.69
Stockfish 20230104	3700.7	95.50	151	63.25
Stockfish 170922 Ivec	3700.2	107.50	155	69.35
Stockfish 130722	3698.9	102.50	166	61.75
Stockfish 20221120	3698.6	134.50	203	66.26
Stockfish 20230125	3698.5	136.50	201	67.91
Stockfish 110722 Ivec	3698.3	105.50	134	78.73
StockfishMZ 170522	3697.7	345.00	482	71.58
Stockfish 20230101	3697.5	74.00	119	62.18
Stockfish 070622	3697.1	279.00	462	60.39
Stockfish 060822 Ivec	3696.4	96.50	153	63.07
Stockfish 081022	3696.1	89.50	176	50.85
Stockfish dev-20230503	3692.7	78.50	110	71.36
Stockfish 15	3691.1	1038.00	1623	63.96
Stockfish 20221209	3690.4	122.50	192	63.80
Stockfish 030522	3689.6	101.50	150	67.67
Stockfish 20230329	3688.5	75.00	132	56.82
Stockfish 20230202	3687.0	86.00	128	67.19
Stockfish 20221220	3684.4	61.00	107	57.01
Stockfish 20230313	3683.6	82.50	104	79.33
Stockfish 170922	3678.1	150.00	226	66.37
StockfishMZ Iccf 240522	3637.8	100.50	150	67.00