Update smallnet to nn-baff1ede1f90.nnue with wider eval range

linrock · linrock · commit 14f4d95c3495 · 2024-01-07T15:07:15.000-05:00
Created by training an L1-128 net from scratch with a wider range of evals in the training data and wld-fen-skipping disabled during training. The differences in this training data compared to the first dual nnue PR are: - removal of all positions with 3 pieces - when piece count >= 16, keep positions with simple eval above 750 - when piece count < 16, remove positions with simple eval above 3000 The asymmetric data filtering was meant to flatten the training data piece count distribution, which was previously heavily skewed towards positions with low piece counts. Additionally, the simple eval range where the smallnet is used was widened to cover more positions previously evaluated by the big net and simple eval. ```yaml experiment-name: 128--S1-hse-S7-v4-S3-v1-no-wld-skip training-dataset: - /data/hse/S3/leela96-filt-v2.min.high-simple-eval-1k.binpack - /data/hse/S3/dfrc99-16tb7p-eval-filt-v2.min.high-simple-eval-1k.binpack - /data/hse/S3/test80-apr2022-16tb7p.min.high-simple-eval-1k.binpack - /data/hse/S7/test60-2020-2tb7p.v6-3072.high-simple-eval-v4.binpack - /data/hse/S7/test60-novdec2021-12tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack - /data/hse/S7/test77-nov2021-2tb7p.v6-3072.min.high-simple-eval-v4.binpack - /data/hse/S7/test77-dec2021-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack - /data/hse/S7/test77-jan2022-2tb7p.high-simple-eval-v4.binpack - /data/hse/S7/test78-jantomay2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack - /data/hse/S7/test78-juntosep2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack - /data/hse/S7/test79-apr2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack - /data/hse/S7/test79-may2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack - /data/hse/S7/test80-may2022-16tb7p.high-simple-eval-v4.binpack - /data/hse/S7/test80-jun2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack - /data/hse/S7/test80-jul2022-16tb7p.v6-dd.min.high-simple-eval-v4.binpack - /data/hse/S7/test80-aug2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack - /data/hse/S7/test80-sep2022-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack - /data/hse/S7/test80-oct2022-16tb7p.v6-dd.high-simple-eval-v4.binpack - /data/hse/S7/test80-nov2022-16tb7p-v6-dd.min.high-simple-eval-v4.binpack - /data/hse/S7/test80-jan2023-3of3-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack - /data/hse/S7/test80-feb2023-16tb7p-filter-v6-dd.min-mar2023.unmin.high-simple-eval-v4.binpack - /data/hse/S7/test80-mar2023-2tb7p.v6-sk16.min.high-simple-eval-v4.binpack - /data/hse/S7/test80-apr2023-2tb7p-filter-v6-sk16.min.high-simple-eval-v4.binpack - /data/hse/S7/test80-may2023-2tb7p.v6.min.high-simple-eval-v4.binpack - /data/hse/S7/test80-jun2023-2tb7p.v6-3072.min.high-simple-eval-v4.binpack - /data/hse/S7/test80-jul2023-2tb7p.v6-3072.min.high-simple-eval-v4.binpack - /data/hse/S7/test80-aug2023-2tb7p.v6.min.high-simple-eval-v4.binpack - /data/hse/S7/test80-sep2023-2tb7p.high-simple-eval-v4.binpack - /data/hse/S7/test80-oct2023-2tb7p.high-simple-eval-v4.binpack wld-fen-skipping: False start-from-engine-test-net: False nnue-pytorch-branch: linrock/nnue-pytorch/L1-128 engine-test-branch: linrock/Stockfish/L1-128-nolazy engine-base-branch: linrock/Stockfish/L1-128 num-epochs: 500 start-lambda: 1.0 end-lambda: 1.0 ``` Experiment yaml configs converted to easy_train.sh commands with: https://github.com/linrock/nnue-tools/blob/4339954/yaml_easy_train.py Binpacks interleaved at training time with: official-stockfish/nnue-pytorch#259 FT weights permuted with 10k positions from fishpack32.binpack with: official-stockfish/nnue-pytorch#254 Data filtered for high simple eval positions (v4) with: https://github.com/linrock/Stockfish/blob/b9c8440/src/tools/transform.cpp#L640-L675 Training data can be found at: https://robotmoon.com/nnue-training-data/ Local elo at 25k nodes per move of L1-128 smallnet (nnue-only eval) vs. L1-128 trained on standard S1 data: nn-epoch319.nnue : -241.7 +/- 3.2 Passed STC vs. 36db936: https://tests.stockfishchess.org/tests/view/6576b3484d789acf40aabbfe LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 21920 W: 5680 L: 5381 D: 10859 Ptnml(0-2): 82, 2488, 5520, 2789, 81 Passed LTC vs. DualNNUE official-stockfish#4915: https://tests.stockfishchess.org/tests/view/65775c034d789acf40aac7e3 LLR: 2.95 (-2.94,2.94) <0.50,2.50> Total: 147606 W: 36619 L: 36063 D: 74924 Ptnml(0-2): 98, 16591, 39891, 17103, 120 Bench: 1438336
diff --git a/src/evaluate.cpp b/src/evaluate.cpp
@@ -185,12 +185,12 @@ Value Eval::evaluate(const Position& pos) {
     int   shuffling  = pos.rule50_count();
     int   simpleEval = simple_eval(pos, stm);
 
-    bool lazy = std::abs(simpleEval) > 2300;
+    bool lazy = std::abs(simpleEval) > 2550;
     if (lazy)
         v = simpleEval;
     else
     {
-        bool smallNet = std::abs(simpleEval) > 1100;
+        bool smallNet = std::abs(simpleEval) > 1050;
 
         int nnueComplexity;
 
diff --git a/src/evaluate.h b/src/evaluate.h
@@ -40,7 +40,7 @@ extern std::string currentEvalFileName[2];
 // for the build process (profile-build and fishtest) to work. Do not change the
 // name of the macro, as it is used in the Makefile.
 #define EvalFileDefaultNameBig "nn-b1e55edbea57.nnue"
-#define EvalFileDefaultNameSmall "nn-c01dc0ffeede.nnue"
+#define EvalFileDefaultNameSmall "nn-baff1ede1f90.nnue"
 
 namespace NNUE {
 
diff --git a/src/nnue/evaluate_nnue.cpp b/src/nnue/evaluate_nnue.cpp
@@ -178,7 +178,7 @@ static bool write_parameters(std::ostream& stream, NetSize netSize) {
 void hint_common_parent_position(const Position& pos) {
 
     int simpleEval = simple_eval(pos, pos.side_to_move());
-    if (abs(simpleEval) > 1100)
+    if (abs(simpleEval) > 1050)
         featureTransformerSmall->hint_common_access(pos);
     else
         featureTransformerBig->hint_common_access(pos);
