Viren6

I reproduced with the same dev version: ``` position fen 1r4k1/p2r1p1p/P2bp1p1/R7/8/3RB1PP/5P2/6K1 w - - 0 30 go depth 25 ... info depth 19 seldepth 40 multipv 1 score cp 158...

Using dev version 99cdb92 also gets stuck for a while but does complete: ``` position fen 1r4k1/p2r1p1p/P2bp1p1/R7/8/3RB1PP/5P2/6K1 w - - 0 30 go depth 25 ... info depth 21 seldepth...

Tested with https://tests.stockfishchess.org/tests/view/66729718602682471b065101?show_task=66 Works as expected

I believe they would need to manually restart the worker. My workers are dockerised and I had to hard redeploy them to get them working.

Results of benches (Final Average Benchmark NPS over a minute) with 64MB hash and depth 16 on Ciekce system (1x16GB): ``` Concurrency: 1 Threads: 1 NPS: 1816044 NPS/Thread: 1816044 Concurrency:...

I've run SPSAs with commands longer than that limit. I think even this currently running one is: https://tests.stockfishchess.org/tests/view/64f32673a0f9f22deb74cc61

I doubt SPSA tunes are computationally expensive unless pushing parameter counts ridiculously high, its one of the cheapest tuning algorithms. The success rate cannot be measured until we try it,...

Lc0 has already started experiments with large scale SPSA tunes. zz4032 of the leela discord writes: > I've been testing around with my own SPSA-like tuning on the old and...

I tested Tic-Tac-Toe, it is working fine, so it is likely due to the inputs of Leduc rather than any deeper bug. Libtorch is: OS is Ubuntu 20.04