SPRT strangeTune1 vs master diff 

  
  
    LLR: 2.96 (-2.94,2.94) <0.50,3.00>
      

    Total: 4400 W: 1326 L: 1127 D: 1947
      

    Ptnml(0-2): 13, 309, 1348, 526, 4

Diff (0 comments) View on GitHub

Details

id 620da11a26f5b17ec884f939
rescheduled_from 620d66823ec80158c0cd3b4a
new_tag strangeTune1 (bench 6318903)
new_signature 6318903
new_options Hash=192 Use NNUE=true
resolved_new 6b0ce6019d
new_net nn-6877cd24400e.nnue
base_tag master (Big search tuning (version 2))
base_signature 4784796
base_options Hash=192 Use NNUE=true
resolved_base 3ec6e1d245
base_net nn-6877cd24400e.nnue
sprt elo0: 0.50 alpha: 0.05 elo1: 3.00 beta: 0.05 state: accepted (normalized)
num_games 800000
tc 180+1.8
new_tc 180+1.8
threads 1
book UHO_XXL_+0.90_+1.19.epd
book_depth 8
auto_purge False
priority 0
itp 670.29
throughput 100
username Vizvezdenec
tests_repo https://github.com/Vizvezdenec/Stockfish
adjudication True
info So, STC was -15~ elo, LTC so far (after 10k games) is +2.5 +/- 3, so I'm running direct SPRT at 180+1.8 with LTC bounds.
events /actions?run_id=620da11a26f5b17ec884f939
raw statistics /tests/stats/620da11a26f5b17ec884f939

Actions

Reschedule
Base branch same as Stockfish master

Stats

chi^25.62
dof10
p-value84.62%

Time

start time2022-02-17 01:12:58
last updated2022-02-17 05:41:32

Tasks (0 active workers with 0 cores)

Idx Worker Info Last Updated Played Pentanomial [0‑2] Crashes Time Residual