Skip to content

Instantly share code, notes, and snippets.

@phimachine
Created December 3, 2019 17:10
Show Gist options
  • Save phimachine/df84bf2bf686ff4de9dd776f6cc52336 to your computer and use it in GitHub Desktop.
Save phimachine/df84bf2bf686ff4de9dd776f6cc52336 to your computer and use it in GitHub Desktop.
Might be working
C:\Users\JasonHu\Anaconda3\envs\alphazero-checker\python.exe "C:\Users\JasonHu\AppData\Local\JetBrains\PyCharm 2018.3\helpers\pydev\pydevconsole.py" --mode=client --port=3466
import sys; print('Python %s on %s' % (sys.version, sys.platform))
sys.path.extend(['D:\\Git\\alphazero-checker', 'D:/Git/alphazero-checker'])
PyDev console: starting.
Python 3.6.8 |Anaconda, Inc.| (default, Dec 30 2018, 18:50:55) [MSC v.1915 64 bit (AMD64)] on win32
runfile('D:/Git/alphazero-checker/zero.py', wdir='D:/Git/alphazero-checker')
nothing to load
value10 train epoch 0, resampling 0. running value loss: 0.91723. running policy loss: 2.12922. running p diff: 0.18429
value10 valid epoch 0, resampling 0. validation value loss: 0.95271. validation policy loss: 2.04300 validation p diff: 0.19218
saved model value10 at D:\Git\alphazero-checker\saves\value10_0_0.pkl
value10 train epoch 0, resampling 10. running value loss: 0.62704. running policy loss: 2.06525. running p diff: 0.18235
value10 train epoch 0, resampling 20. running value loss: 0.60219. running policy loss: 2.02377. running p diff: 0.17963
value10 train epoch 0, resampling 30. running value loss: 0.59108. running policy loss: 2.00349. running p diff: 0.17728
value10 train epoch 0, resampling 40. running value loss: 0.58647. running policy loss: 1.98904. running p diff: 0.17630
value10 train epoch 0, resampling 50. running value loss: 0.57875. running policy loss: 1.97667. running p diff: 0.17585
value10 train epoch 0, resampling 60. running value loss: 0.61180. running policy loss: 1.95585. running p diff: 0.17389
value10 train epoch 0, resampling 70. running value loss: 0.60925. running policy loss: 1.94569. running p diff: 0.17209
value10 train epoch 0, resampling 80. running value loss: 0.60433. running policy loss: 1.94747. running p diff: 0.17161
value10 train epoch 0, resampling 90. running value loss: 0.62449. running policy loss: 1.95091. running p diff: 0.17170
value10 train epoch 0, resampling 100. running value loss: 0.63874. running policy loss: 1.94908. running p diff: 0.17240
value10 train epoch 0, resampling 110. running value loss: 0.59347. running policy loss: 1.94501. running p diff: 0.17324
value10 train epoch 0, resampling 120. running value loss: 0.58216. running policy loss: 1.94734. running p diff: 0.17433
value10 train epoch 0, resampling 130. running value loss: 0.58100. running policy loss: 1.93674. running p diff: 0.17417
value10 train epoch 0, resampling 140. running value loss: 0.55025. running policy loss: 1.91905. running p diff: 0.17299
value10 train epoch 0, resampling 150. running value loss: 0.51237. running policy loss: 1.91041. running p diff: 0.17133
value10 train epoch 0, resampling 160. running value loss: 0.49237. running policy loss: 1.90225. running p diff: 0.17008
value10 train epoch 0, resampling 170. running value loss: 0.48150. running policy loss: 1.89233. running p diff: 0.16883
value10 train epoch 0, resampling 180. running value loss: 0.46692. running policy loss: 1.88810. running p diff: 0.16868
value10 train epoch 0, resampling 190. running value loss: 0.44921. running policy loss: 1.89311. running p diff: 0.16809
Generating a new game with MCTS
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 70 /200
Game step 60 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 80 /200
Game step 70 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 90 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 100 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 110 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 100 /200
Game step 110 /200
Game step 120 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 110 /200
Game step 110 /200
Game step 120 /200
Game step 120 /200
Game step 110 /200
Game step 130 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Terminated due to peaceful activity
Terminated at step 135
Draw
7[[ -1]
6 [-1 -1 2 -1 ]
5 [ -1 -1 ]
4 [ 1 1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ -2 1 ]]
0 1 2 3 4 5 6 7
Game step 120 /200
Game step 130 /200
Game step 130 /200
Game step 120 /200
Game step 130 /200
Game step 120 /200
Game step 130 /200
Game step 130 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 130 /200
Game step 130 /200
Game step 140 /200
Game step 140 /200
Game step 130 /200
Game step 140 /200
Game step 140 /200
Game step 130 /200
Game step 130 /200
Game step 140 /200
Game step 130 /200
Game step 130 /200
Terminated due to peaceful activity
Terminated at step 140
First player won.
7[[ ]
6 [-1 -1 ]
5 [ -1 2 -1 ]
4 [ 1 -2 1 1 ]
3 [ -1]
2 [ 1 1 1 ]
1 [ 1 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
Game step 130 /200
Terminated due to peaceful activity
Terminated at step 142
First player won.
7[[ ]
6 [-1 -1 ]
5 [ -1 2 -1 ]
4 [ 1 -2 1 1 ]
3 [ -1]
2 [ 1 1 1 ]
1 [ 1 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
Game step 130 /200
Game step 140 /200
Game step 130 /200
Terminated due to peaceful activity
Terminated at step 148
Draw
7[[ 2 ]
6 [-1 -1 ]
5 [ -1 1 ]
4 [ 1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 -2 ]
0 [ ]]
0 1 2 3 4 5 6 7
Game step 150 /200
Game step 140 /200
Game step 150 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Terminated due to peaceful activity
Terminated at step 140
Draw
7[[ ]
6 [-1 -1 2 -1 ]
5 [ -1 -1 1]
4 [ 1 1 ]
3 [ -1]
2 [ 1 1 ]
1 [ 1 -2 ]
0 [ ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 153
First player won.
7[[ ]
6 [ 2 -1 ]
5 [ 2 -1 ]
4 [ 1 ]
3 [ 1 -1]
2 [ 1 ]
1 [ -2 -1 1 1]
0 [ -2 ]]
0 1 2 3 4 5 6 7
Game step 140 /200
Game step 150 /200
Game step 140 /200
Terminated due to peaceful activity
Terminated at step 150
Draw
7[[ 2 -1]
6 [ -1 ]
5 [ -1 2 -1 ]
4 [ 1 1 ]
3 [ -1 -1]
2 [-2 -2 1 1 ]
1 [ 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 138
First player won.
7[[ ]
6 [-1 1 -1 ]
5 [ -1 2 -1 -1]
4 [ 1 ]
3 [ -1]
2 [ 1 1 1 ]
1 [ 1 -2 ]
0 [ 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 146
First player won.
7[[ ]
6 [ -1 ]
5 [ 2 2 -1 ]
4 [ 1 1 ]
3 [ -1 -1]
2 [ -1 1 ]
1 [ -2 -1 1 1]
0 [ 1 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 157
First player won.
7[[ ]
6 [-1 1 2 ]
5 [ -1 -2 1]
4 [ 1 ]
3 [ ]
2 [-1 1 1 ]
1 [ 1 ]
0 [ 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 145
First player won.
7[[ 2 ]
6 [ -1 ]
5 [ -1 2 -1 1]
4 [ 1 1 ]
3 [ -1 -1]
2 [-1 1 -2 1 ]
1 [ 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 145
Draw
7[[ -1 ]
6 [-1 -1 2 -1 ]
5 [ -1 -1 1]
4 [ 1 1 ]
3 [ -1]
2 [ 1 -2 1 ]
1 [ 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
Game step 150 /200
Game step 150 /200
Game step 150 /200
Terminated due to peaceful activity
Terminated at step 149
Second player won
7[[ -1 ]
6 [-1 -1 1 2 ]
5 [ -1 ]
4 [ 1 -1 ]
3 [ -1 ]
2 [ 1 -2 ]
1 [ 1 ]
0 [ -2 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 152
Second player won
7[[ 2 ]
6 [-1 -1 1 2 ]
5 [ -1 ]
4 [ 1 -1 ]
3 [ -1 ]
2 [ 1 -2 -2 ]
1 [ 1 ]
0 [ ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 153
Second player won
7[[ ]
6 [ -1 1 2 ]
5 [ -1 2]
4 [ 1 ]
3 [ -1 ]
2 [-1 1 -2 ]
1 [ 1 -2 -1]
0 [ ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 158
First player won.
7[[ ]
6 [-1 2 ]
5 [ -1 -2 -1 ]
4 [ 1 1 -1 ]
3 [ 2 -1 -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ 1 ]]
0 1 2 3 4 5 6 7
MCTS pool has joined
Terminal sentinel is put on queue
Sentinel received. GPU will process this batch and terminate afterwards
Queue task done signal sent. Queue will join. Thread may still be running.
Queue has joined
GPU Thread has joined
Successful generation of 16 games
Queue empty: True
value10 train epoch 1, resampling 0. running value loss: 0.44144. running policy loss: 1.88730. running p diff: 0.16669
value10 valid epoch 1, resampling 0. validation value loss: 0.73690. validation policy loss: 1.71955 validation p diff: 0.18258
saved model value10 at D:\Git\alphazero-checker\saves\value10_1_0.pkl
value10 train epoch 1, resampling 10. running value loss: 0.46539. running policy loss: 1.81753. running p diff: 0.16549
value10 train epoch 1, resampling 20. running value loss: 0.49143. running policy loss: 1.74458. running p diff: 0.16442
value10 train epoch 1, resampling 30. running value loss: 0.51350. running policy loss: 1.67906. running p diff: 0.16252
value10 train epoch 1, resampling 40. running value loss: 0.53117. running policy loss: 1.62745. running p diff: 0.16169
value10 train epoch 1, resampling 50. running value loss: 0.55403. running policy loss: 1.58846. running p diff: 0.16159
value10 train epoch 1, resampling 60. running value loss: 0.56188. running policy loss: 1.61810. running p diff: 0.16207
value10 train epoch 1, resampling 70. running value loss: 0.57032. running policy loss: 1.64706. running p diff: 0.16345
value10 train epoch 1, resampling 80. running value loss: 0.57556. running policy loss: 1.66156. running p diff: 0.16534
value10 train epoch 1, resampling 90. running value loss: 0.57983. running policy loss: 1.66179. running p diff: 0.16670
value10 train epoch 1, resampling 100. running value loss: 0.57757. running policy loss: 1.66661. running p diff: 0.16651
value10 train epoch 1, resampling 110. running value loss: 0.56667. running policy loss: 1.67551. running p diff: 0.16519
value10 train epoch 1, resampling 120. running value loss: 0.54662. running policy loss: 1.68085. running p diff: 0.16328
value10 train epoch 1, resampling 130. running value loss: 0.53526. running policy loss: 1.68599. running p diff: 0.16204
value10 train epoch 1, resampling 140. running value loss: 0.52884. running policy loss: 1.68729. running p diff: 0.16240
value10 train epoch 1, resampling 150. running value loss: 0.51134. running policy loss: 1.68714. running p diff: 0.16557
value10 train epoch 1, resampling 160. running value loss: 0.49897. running policy loss: 1.70123. running p diff: 0.17109
value10 train epoch 1, resampling 170. running value loss: 0.51385. running policy loss: 1.73349. running p diff: 0.17772
value10 train epoch 1, resampling 180. running value loss: 0.50830. running policy loss: 1.76115. running p diff: 0.18286
value10 train epoch 1, resampling 190. running value loss: 0.49911. running policy loss: 1.76797. running p diff: 0.18455
Generating a new game with MCTS
Generating a new game with MCTS
Generating a new game with MCTS
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Game step 0 /200
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Game step 0 /200
Game step 0 /200
Game step 0 /200
Game step 0 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 80 /200
Game step 70 /200
Game step 70 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 90 /200
Game step 80 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 80 /200
Game step 80 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 100 /200
Game step 90 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 90 /200
Game step 90 /200
Game step 100 /200
Game step 100 /200
Game step 110 /200
Game step 100 /200
Game step 110 /200
Game step 100 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 120 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 100 /200
Game step 100 /200
Game step 120 /200
Game step 120 /200
Game step 110 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 130 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 130 /200
Game step 110 /200
Game step 110 /200
Terminated due to peaceful activity
Terminated at step 137
Draw
7[[ -1 ]
6 [ -1 -1 ]
5 [ -1 -1 ]
4 [ 1 -2 ]
3 [ -1 -1]
2 [ 2 1 1 ]
1 [ 1 1 1]
0 [ 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 129
Second player won
7[[ -1 ]
6 [-1 -1 -1 -1 ]
5 [ -1 -1 -1]
4 [ 2 1 ]
3 [ -1 -2 -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ 1 ]]
0 1 2 3 4 5 6 7
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 120 /200
Game step 130 /200
Terminated due to peaceful activity
Terminated at step 135
First player won.
7[[ -1 2]
6 [-1 -1 -2 ]
5 [ -1 -1 ]
4 [ 1 1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 131
Second player won
7[[ -1 ]
6 [-1 -1 -1 ]
5 [ -1 2 -1 ]
4 [ ]
3 [ -1 -1]
Terminated due to peaceful activity
Terminated at step 131
2 [-1 1 -2 1 ]
Second player won
7[[ -1 ]
6 [-1 -1 -1 ]
5 [ -1 2 -1 ]
4 [ ]
3 [ -1 -1]
2 [-1 1 -2 1 ]
1 [ 1 1 1]
1 [ 1 1 1]
0 [ 1 1 ]]
0 1 2 3 4 5 6 7
0 [ 1 1 ]]
Terminated due to peaceful activity
Terminated at step 131
Second player won
7[[ -1 ]
6 [-1 -1 -1 ]
5 [ -1 2 -1 ]
4 [ ]
0 1 2 3 4 5 6 7
3 [ -1 -1]
2 [-1 1 -2 1 ]
1 [ 1 1 1]
0 [ 1 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 131
Second player won
7[[ -1 ]
6 [-1 -1 -1 ]
5 [ -1 2 -1 ]
4 [ ]
3 [ -1 -1]
2 [-1 1 -2 1 ]
1 [ 1 1 1]
0 [ 1 1 ]]
0 1 2 3 4 5 6 7
Game step 130 /200
Terminated due to peaceful activity
Terminated at step 128
First player won.
7[[ -1 -1 -1]
6 [ -2 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 ]
3 [ 2 ]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 132
First player won.
7[[ -1 2]
6 [-1 -1 ]
5 [ -1 -2 -1 ]
4 [ 1 1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ 1 ]]
0 1 2 3 4 5 6 7
Game step 130 /200
Terminated due to peaceful activity
Terminated at step 131
First player won.
7[[ -1 ]
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 -2 ]
3 [ 2 -1 -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ 1 1 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 136
First player won.
7[[ -1 ]
6 [-1 -1 ]
5 [ -1 2 ]
4 [ 1 -2 1 ]
3 [ -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ 1 ]]
0 1 2 3 4 5 6 7
Game step 120 /200
Game step 120 /200
Terminated due to peaceful activity
Terminated at step 139
Draw
7[[ -1 2]
6 [-1 -1 ]
5 [ -1 -1 ]
4 [ 1 -2 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ 1 ]]
0 1 2 3 4 5 6 7
Game step 130 /200
Game step 140 /200
Terminated due to peaceful activity
Terminated at step 140
Second player won
7[[ 2 -1 ]
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 1]
0 [-2 1 ]]
0 1 2 3 4 5 6 7
Game step 130 /200
Game step 130 /200
Game step 140 /200
Terminated due to peaceful activity
Terminated at step 143
Second player won
7[[ -1 ]
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1 -1]
2 [-1 2 1 ]
1 [ -2 1 1]
0 [ 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 134
First player won.
7[[ -1 ]
6 [-1 -1 2 ]
5 [ -1 -2 -1 1]
4 [ 1 1 ]
3 [ -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 134
First player won.
7[[ -1 ]
6 [-1 -1 2 ]
5 [ -1 -2 -1 1]
4 [ 1 1 ]
3 [ -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ 1 ]]
0 1 2 3 4 5 6 7
MCTS pool has joined
Terminal sentinel is put on queue
Sentinel received. GPU will process this batch and terminate afterwards
Queue task done signal sent. Queue will join. Thread may still be running.
Queue has joined
GPU Thread has joined
Successful generation of 16 games
Queue empty: True
value10 train epoch 2, resampling 0. running value loss: 0.51132. running policy loss: 1.75232. running p diff: 0.18287
value10 valid epoch 2, resampling 0. validation value loss: 0.76237. validation policy loss: 1.36634 validation p diff: 0.16090
saved model value10 at D:\Git\alphazero-checker\saves\value10_2_0.pkl
value10 train epoch 2, resampling 10. running value loss: 0.54404. running policy loss: 1.66012. running p diff: 0.17691
value10 train epoch 2, resampling 20. running value loss: 0.54921. running policy loss: 1.56053. running p diff: 0.16935
value10 train epoch 2, resampling 30. running value loss: 0.58025. running policy loss: 1.47045. running p diff: 0.16252
value10 train epoch 2, resampling 40. running value loss: 0.62695. running policy loss: 1.40924. running p diff: 0.15885
value10 train epoch 2, resampling 50. running value loss: 0.66686. running policy loss: 1.37031. running p diff: 0.15805
value10 train epoch 2, resampling 60. running value loss: 0.67875. running policy loss: 1.40256. running p diff: 0.16087
value10 train epoch 2, resampling 70. running value loss: 0.70145. running policy loss: 1.43687. running p diff: 0.16512
value10 train epoch 2, resampling 80. running value loss: 0.71515. running policy loss: 1.47222. running p diff: 0.16899
value10 train epoch 2, resampling 90. running value loss: 0.71478. running policy loss: 1.49644. running p diff: 0.17099
value10 train epoch 2, resampling 100. running value loss: 0.69336. running policy loss: 1.51633. running p diff: 0.17063
value10 train epoch 2, resampling 110. running value loss: 0.66172. running policy loss: 1.52633. running p diff: 0.16801
value10 train epoch 2, resampling 120. running value loss: 0.62955. running policy loss: 1.52368. running p diff: 0.16409
value10 train epoch 2, resampling 130. running value loss: 0.60585. running policy loss: 1.51805. running p diff: 0.16077
value10 train epoch 2, resampling 140. running value loss: 0.59901. running policy loss: 1.53478. running p diff: 0.15955
value10 train epoch 2, resampling 150. running value loss: 0.60583. running policy loss: 1.55536. running p diff: 0.15974
value10 train epoch 2, resampling 160. running value loss: 0.61595. running policy loss: 1.54073. running p diff: 0.15900
value10 train epoch 2, resampling 170. running value loss: 0.61651. running policy loss: 1.52913. running p diff: 0.15684
value10 train epoch 2, resampling 180. running value loss: 0.60764. running policy loss: 1.53773. running p diff: 0.15464
value10 train epoch 2, resampling 190. running value loss: 0.58880. running policy loss: 1.54676. running p diff: 0.15172
Generating a new game with MCTS
Generating a new game with MCTS
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Game step 0 /200
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 110 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 110 /200
Game step 110 /200
Game step 120 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 120 /200
Game step 120 /200
Game step 130 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 130 /200
Game step 130 /200
Game step 140 /200
Game step 130 /200
Terminated due to peaceful activity
Terminated at step 139
Second player won
7[[ -1 ]
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 -2 2 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ 1 ]]
0 1 2 3 4 5 6 7
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Terminated due to peaceful activity
Terminated at step 138
Second player won
7[[ -1]
6 [-1 -1 2 -1 ]
5 [ -1 1 ]
4 [ 1 1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ -2 1 ]
0 [ ]]
0 1 2 3 4 5 6 7
Game step 130 /200
Game step 150 /200
Game step 140 /200
Game step 160 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Terminated due to peaceful activity
Terminated at step 143
Draw
7[[ -1]
6 [ -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 -2 ]
3 [ 2 -1 -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 147
Second player won
7[[ -1 ]
6 [-1 -1 -1 ]
5 [ -1 -1 -2]
4 [ 1 ]
3 [ -1 2 -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
Game step 170 /200
Terminated due to peaceful activity
Terminated at step 147
Second player won
7[[ -1 ]
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 -2 ]
3 [ 2 -1 -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated due to peaceful activity
Terminated at step 147
Second player won
7[[ -1 ]
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 -2 ]
Terminated due to peaceful activity
Terminated due to peaceful activity
Terminated at step 147
Second player won
7[[ -1 ]
Terminated due to peaceful activity
Terminated at step 147
3 [ 2 -1 -1]
2 [ 1 1 ]
Terminated due to peaceful activity
Terminated at step 147
Second player won
7[[ -1 ]
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 -2 ]
3 [ 2 -1 -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
Second player won
7[[ -1 ]
Terminated at step 147
Second player won
7[[ -1 ]
Terminated due to peaceful activity
Terminated at step 147
Second player won
7[[ -1 ]
Terminated at step 147
Second player won
7[[ -1 ]
1 [ 1 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 -2 ]
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 -2 ]
6 [-1 -1 -1 ]
3 [ 2 -1 -1]
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 -2 ]
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 -2 ]
5 [ -1 -1 ]
4 [ 1 1 -2 ]
3 [ 2 -1 -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
2 [ 1 1 ]
1 [ 1 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
3 [ 2 -1 -1]
2 [ 1 1 ]
1 [ 1 1 1]
Terminated due to peaceful activity
3 [ 2 -1 -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ ]]
3 [ 2 -1 -1]
2 [ 1 1 ]
1 [ 1 1 1]
Terminated at step 147
0 1 2 3 4 5 6 7
0 [ ]]
0 1 2 3 4 5 6 7
0 [ ]]
0 1 2 3 4 5 6 7
Second player won
7[[ -1 ]
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 -2 ]
3 [ 2 -1 -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 147
Second player won
7[[ -1 ]
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 -2 ]
3 [ 2 -1 -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 147
Second player won
7[[ -1 ]
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 -2 ]
3 [ 2 -1 -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 175
First player won.
7[[ 2]
6 [ -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1 2 -1]
2 [ 1 1 ]
1 [ 1 ]
0 [-2 ]]
0 1 2 3 4 5 6 7
MCTS pool has joined
Terminal sentinel is put on queue
Sentinel received. GPU will process this batch and terminate afterwards
Queue task done signal sent. Queue will join. Thread may still be running.
Queue has joined
GPU Thread has joined
Successful generation of 16 games
Queue empty: True
value10 train epoch 3, resampling 0. running value loss: 0.58507. running policy loss: 1.52488. running p diff: 0.14889
value10 valid epoch 3, resampling 0. validation value loss: 0.87178. validation policy loss: 1.16255 validation p diff: 0.12759
saved model value10 at D:\Git\alphazero-checker\saves\value10_3_0.pkl
value10 train epoch 3, resampling 10. running value loss: 0.61092. running policy loss: 1.43806. running p diff: 0.14468
value10 train epoch 3, resampling 20. running value loss: 0.64076. running policy loss: 1.37241. running p diff: 0.14632
value10 train epoch 3, resampling 30. running value loss: 0.67462. running policy loss: 1.29030. running p diff: 0.14905
value10 train epoch 3, resampling 40. running value loss: 0.71021. running policy loss: 1.18264. running p diff: 0.15013
value10 train epoch 3, resampling 50. running value loss: 0.73502. running policy loss: 1.09211. running p diff: 0.14818
value10 train epoch 3, resampling 60. running value loss: 0.72988. running policy loss: 1.08557. running p diff: 0.14549
value10 train epoch 3, resampling 70. running value loss: 0.71182. running policy loss: 1.06772. running p diff: 0.13699
value10 train epoch 3, resampling 80. running value loss: 0.70958. running policy loss: 1.04859. running p diff: 0.12601
value10 train epoch 3, resampling 90. running value loss: 0.71960. running policy loss: 1.04395. running p diff: 0.11604
value10 train epoch 3, resampling 100. running value loss: 0.72625. running policy loss: 1.04083. running p diff: 0.10896
value10 train epoch 3, resampling 110. running value loss: 0.72210. running policy loss: 1.04515. running p diff: 0.10643
value10 train epoch 3, resampling 120. running value loss: 0.71565. running policy loss: 1.03544. running p diff: 0.10679
value10 train epoch 3, resampling 130. running value loss: 0.70735. running policy loss: 1.02997. running p diff: 0.11114
value10 train epoch 3, resampling 140. running value loss: 0.69332. running policy loss: 1.04013. running p diff: 0.11939
value10 train epoch 3, resampling 150. running value loss: 0.69523. running policy loss: 1.07789. running p diff: 0.13157
value10 train epoch 3, resampling 160. running value loss: 0.71476. running policy loss: 1.12018. running p diff: 0.14405
value10 train epoch 3, resampling 170. running value loss: 0.74891. running policy loss: 1.15501. running p diff: 0.15291
value10 train epoch 3, resampling 180. running value loss: 0.74850. running policy loss: 1.16913. running p diff: 0.15541
value10 train epoch 3, resampling 190. running value loss: 0.73714. running policy loss: 1.16311. running p diff: 0.15238
Generating a new game with MCTS
Generating a new game with MCTS
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 80 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 80 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 90 /200
Game step 80 /200
Game step 90 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 100 /200
Game step 80 /200
Game step 80 /200
Game step 90 /200
Game step 100 /200
Game step 110 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 100 /200
Game step 120 /200
Game step 110 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 130 /200
Game step 100 /200
Game step 110 /200
Game step 120 /200
Game step 100 /200
Game step 140 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 130 /200
Game step 120 /200
Game step 110 /200
Terminated due to peaceful activity
Terminated at step 132
Second player won
7[[ 2 -1 -1]
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1 ]
2 [ 1 1 ]
1 [ -2 1 1]
0 [ 1 ]]
0 1 2 3 4 5 6 7
Game step 110 /200
Terminated due to peaceful activity
Terminated at step 148
Second player won
7[[ -1 ]
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 ]
3 [ 1 -1 -1]
2 [ 1 1 1 ]
1 [ 2 ]
0 [-2 ]]
0 1 2 3 4 5 6 7
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 130 /200
Game step 120 /200
Game step 120 /200
Terminated due to peaceful activity
Terminated at step 136
Draw
7[[ -1 ]
6 [-1 -1 -1 ]
5 [ -1 2 -1 ]
4 [ 1 1 ]
3 [ 1 -1 ]
2 [ 1 1 ]
1 [ 1 ]
0 [ 1 -2 ]]
0 1 2 3 4 5 6 7
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Terminated due to peaceful activity
Terminated at step 130
Second player won
7[[ -1 -1 2]
6 [-1 -1 -1 ]
5 [ -1 -2 -1 ]
4 [ 1 -2 1 ]
3 [ 1 ]
2 [ 1 1 -1 ]
1 [ 1 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 130
Second player won
7[[ -1 -1 2]
6 [-1 -1 -1 ]
5 [ -1 -2 -1 ]
4 [ 1 -2 1 ]
3 [ 1 ]
2 [ 1 1 -1 ]
1 [ 1 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated due to peaceful activity
Terminated due to peaceful activity
Terminated at step 130
Terminated at step 130
Terminated at step 130
Second player won
Second player won
7[[ -1 -1 2]
6 [-1 -1 -1 ]
5 [ -1 -2 -1 ]
4 [ 1 -2 1 ]
3 [ 1 ]
2 [ 1 1 -1 ]
7[[ -1 -1 2]
Second player won
1 [ 1 1 1]
0 [ ]]
6 [-1 -1 -1 ]
7[[ -1 -1 2]
5 [ -1 -2 -1 ]
4 [ 1 -2 1 ]
3 [ 1 ]
2 [ 1 1 -1 ]
1 [ 1 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
0 1 2 3 4 5 6 7
6 [-1 -1 -1 ]
5 [ -1 -2 -1 ]
4 [ 1 -2 1 ]
3 [ 1 ]
2 [ 1 1 -1 ]
1 [ 1 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 130
Second player won
7[[ -1 -1 2]
6 [-1 -1 -1 ]
5 [ -1 -2 -1 ]
4 [ 1 -2 1 ]
3 [ 1 ]
2 [ 1 1 -1 ]
1 [ 1 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 130
Second player won
7[[ -1 -1 2]
6 [-1 -1 -1 ]
5 [ -1 -2 -1 ]
4 [ 1 -2 1 ]
3 [ 1 ]
2 [ 1 1 -1 ]
1 [ 1 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
Game step 130 /200
Game step 130 /200
Terminated due to peaceful activity
Terminated at step 134
Second player won
7[[ -1 -1 2]
6 [-1 -1 -1 ]
5 [ -1 -2 -1 ]
4 [ 1 -2 1 ]
3 [ 1 ]
2 [ 1 1 -1 ]
1 [ 1 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 134
Second player won
7[[ -1 -1 2]
6 [-1 -1 -1 ]
5 [ -1 -2 -1 ]
4 [ 1 -2 1 ]
3 [ 1 ]
2 [ 1 1 -1 ]
1 [ 1 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 134
Second player won
7[[ -1 -1 2]
6 [-1 -1 -1 ]
5 [ -1 -2 -1 ]
4 [ 1 -2 1 ]
3 [ 1 ]
2 [ 1 1 -1 ]
1 [ 1 1 1]
0 [ ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 138
Draw
7[[ 2]
6 [-1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 -1 ]
3 [ 1 -1 -1]
2 [ 1 1 ]
1 [ 1 -2 ]
0 [ 1 ]]
0 1 2 3 4 5 6 7
Game step 140 /200
Game step 140 /200
Terminated due to peaceful activity
Terminated at step 141
First player won.
7[[ ]
6 [ -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 ]
3 [ 2 -1 -1]
2 [ 1 -2 1 ]
1 [ 1 1 1]
0 [ 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 141
First player won.
7[[ ]
6 [ -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 ]
3 [ 2 -1 -1]
2 [ 1 -2 1 ]
1 [ 1 1 1]
0 [ 1 ]]
0 1 2 3 4 5 6 7
MCTS pool has joined
Terminal sentinel is put on queue
Sentinel received. GPU will process this batch and terminate afterwards
Queue task done signal sent. Queue will join. Thread may still be running.
Queue has joined
GPU Thread has joined
Successful generation of 16 games
Queue empty: True
value10 train epoch 4, resampling 0. running value loss: 0.71186. running policy loss: 1.14067. running p diff: 0.14513
value10 valid epoch 4, resampling 0. validation value loss: 0.87318. validation policy loss: 0.95730 validation p diff: 0.11454
saved model value10 at D:\Git\alphazero-checker\saves\value10_4_0.pkl
value10 train epoch 4, resampling 10. running value loss: 0.74462. running policy loss: 1.08252. running p diff: 0.13465
value10 train epoch 4, resampling 20. running value loss: 0.77224. running policy loss: 1.04351. running p diff: 0.12699
value10 train epoch 4, resampling 30. running value loss: 0.82145. running policy loss: 1.02352. running p diff: 0.12329
value10 train epoch 4, resampling 40. running value loss: 0.87622. running policy loss: 0.99914. running p diff: 0.12092
value10 train epoch 4, resampling 50. running value loss: 0.93188. running policy loss: 0.96659. running p diff: 0.11849
value10 train epoch 4, resampling 60. running value loss: 0.91962. running policy loss: 0.96523. running p diff: 0.11807
value10 train epoch 4, resampling 70. running value loss: 0.90167. running policy loss: 0.96857. running p diff: 0.11807
value10 train epoch 4, resampling 80. running value loss: 0.86921. running policy loss: 0.98452. running p diff: 0.11913
value10 train epoch 4, resampling 90. running value loss: 0.85030. running policy loss: 1.00942. running p diff: 0.12160
value10 train epoch 4, resampling 100. running value loss: 0.83655. running policy loss: 1.03169. running p diff: 0.12397
value10 train epoch 4, resampling 110. running value loss: 0.83612. running policy loss: 1.04031. running p diff: 0.12475
value10 train epoch 4, resampling 120. running value loss: 0.81907. running policy loss: 1.03017. running p diff: 0.12415
value10 train epoch 4, resampling 130. running value loss: 0.80996. running policy loss: 1.02069. running p diff: 0.12542
value10 train epoch 4, resampling 140. running value loss: 0.79136. running policy loss: 1.04499. running p diff: 0.12950
value10 train epoch 4, resampling 150. running value loss: 0.78199. running policy loss: 1.08593. running p diff: 0.13512
value10 train epoch 4, resampling 160. running value loss: 0.77895. running policy loss: 1.13295. running p diff: 0.14330
value10 train epoch 4, resampling 170. running value loss: 0.79748. running policy loss: 1.17653. running p diff: 0.15128
value10 train epoch 4, resampling 180. running value loss: 0.80054. running policy loss: 1.18573. running p diff: 0.15412
value10 train epoch 4, resampling 190. running value loss: 0.79246. running policy loss: 1.15706. running p diff: 0.15308
Generating a new game with MCTS
Generating a new game with MCTS
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Game step 0 /200
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 70 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 80 /200
Game step 90 /200
Game step 90 /200
Game step 80 /200
Game step 90 /200
Game step 80 /200
Game step 90 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 100 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 110 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Terminated due to peaceful activity
Terminated at step 122
First player won.
7[[ 2 -1 -1]
6 [ -1 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 -2 1 1]
0 [ 1 1 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated due to peaceful activity
Terminated due to peaceful activity
Terminated due to peaceful activity
Terminated at step 122
First player won.
7[[ 2 -1 -1]
6 [ -1 -1 ]
Terminated at step 122
First player won.
7[[ 2 -1 -1]
Terminated at step 122
First player won.
7[[ 2 -1 -1]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 -2 1 1]
0 [ 1 1 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
6 [ -1 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 -2 1 1]
0 [ 1 1 1 ]]
0 1 2 3 4 5 6 7
Terminated at step 122
6 [ -1 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1 -1]
2 [ 1 1 ]
First player won.
1 [ 1 -2 1 1]
0 [ 1 1 1 ]]
0 1 2 3 4 5 6 7
Terminated at step 122
7[[ 2 -1 -1]
First player won.
6 [ -1 -1 ]
7[[ 2 -1 -1]
6 [ -1 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
5 [ -1 -1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 -2 1 1]
Terminated due to peaceful activity
Terminated at step 122
First player won.
7[[ 2 -1 -1]
6 [ -1 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 -2 1 1]
0 [ 1 1 1 ]]
0 1 2 3 4 5 6 7
0 [ 1 1 1 ]]
4 [ 1 ]
0 1 2 3 4 5 6 7
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 -2 1 1]
0 [ 1 1 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 122
First player won.
7[[ 2 -1 -1]
6 [ -1 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 -2 1 1]
0 [ 1 1 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 122
First player won.
7[[ 2 -1 -1]
6 [ -1 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 -2 1 1]
0 [ 1 1 1 ]]
0 1 2 3 4 5 6 7
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 120 /200
Game step 110 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Terminated due to peaceful activity
Terminated at step 126
Draw
7[[ 2 -1 -1]
6 [ -1 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 -2 1 1]
0 [ 1 1 ]]
0 1 2 3 4 5 6 7
Game step 120 /200
Game step 120 /200
Game step 120 /200
Terminated due to peaceful activity
Terminated at step 122
First player won.
7[[ -1 2 -1 -1]
6 [ -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ 1 1 -2 1 ]]
0 1 2 3 4 5 6 7
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Terminated due to peaceful activity
Terminated at step 135
Draw
7[[ -1]
6 [-1 2 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 1]
0 [ 1 1 -2 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 135
Draw
7[[ -1]
6 [-1 2 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 1]
0 [ 1 1 -2 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 135
Draw
7[[ -1]
6 [-1 2 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 1]
0 [ 1 1 -2 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 135
Draw
7[[ -1]
6 [-1 2 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 1]
0 [ 1 1 -2 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 135
Draw
7[[ -1]
6 [-1 2 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 1]
0 [ 1 1 -2 ]]
0 1 2 3 4 5 6 7
MCTS pool has joined
Terminal sentinel is put on queue
Sentinel received. GPU will process this batch and terminate afterwards
Queue task done signal sent. Queue will join. Thread may still be running.
Queue has joined
GPU Thread has joined
Successful generation of 16 games
Queue empty: True
value10 train epoch 5, resampling 0. running value loss: 0.76779. running policy loss: 1.11343. running p diff: 0.14987
value10 valid epoch 5, resampling 0. validation value loss: 0.81678. validation policy loss: 0.80324 validation p diff: 0.11076
saved model value10 at D:\Git\alphazero-checker\saves\value10_5_0.pkl
value10 train epoch 5, resampling 10. running value loss: 0.75448. running policy loss: 1.04434. running p diff: 0.14059
value10 train epoch 5, resampling 20. running value loss: 0.75992. running policy loss: 0.99106. running p diff: 0.13111
value10 train epoch 5, resampling 30. running value loss: 0.78889. running policy loss: 0.95850. running p diff: 0.12235
value10 train epoch 5, resampling 40. running value loss: 0.81836. running policy loss: 0.92446. running p diff: 0.11191
value10 train epoch 5, resampling 50. running value loss: 0.84944. running policy loss: 0.90128. running p diff: 0.10077
value10 train epoch 5, resampling 60. running value loss: 0.85604. running policy loss: 0.91874. running p diff: 0.09423
value10 train epoch 5, resampling 70. running value loss: 0.84773. running policy loss: 0.94425. running p diff: 0.08909
value10 train epoch 5, resampling 80. running value loss: 0.83150. running policy loss: 0.96853. running p diff: 0.08541
value10 train epoch 5, resampling 90. running value loss: 0.81808. running policy loss: 0.99868. running p diff: 0.08411
value10 train epoch 5, resampling 100. running value loss: 0.81128. running policy loss: 1.02925. running p diff: 0.08695
value10 train epoch 5, resampling 110. running value loss: 0.80908. running policy loss: 1.05642. running p diff: 0.09241
value10 train epoch 5, resampling 120. running value loss: 0.80559. running policy loss: 1.06182. running p diff: 0.09785
value10 train epoch 5, resampling 130. running value loss: 0.80859. running policy loss: 1.07017. running p diff: 0.10456
value10 train epoch 5, resampling 140. running value loss: 0.81215. running policy loss: 1.13586. running p diff: 0.11492
value10 train epoch 5, resampling 150. running value loss: 0.80691. running policy loss: 1.22677. running p diff: 0.12313
value10 train epoch 5, resampling 160. running value loss: 0.79723. running policy loss: 1.25589. running p diff: 0.12604
value10 train epoch 5, resampling 170. running value loss: 0.78213. running policy loss: 1.27232. running p diff: 0.12639
value10 train epoch 5, resampling 180. running value loss: 0.75167. running policy loss: 1.32337. running p diff: 0.12800
value10 train epoch 5, resampling 190. running value loss: 0.71187. running policy loss: 1.37531. running p diff: 0.12621
Generating a new game with MCTS
Generating a new game with MCTS
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Game step 0 /200
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Game step 140 /200
Terminated due to peaceful activity
Terminated at step 147
First player won.
7[[ ]
6 [ ]
5 [ -1 ]
4 [-1 2 -2 ]
3 [ 1 ]
2 [ 1 2 2 ]
1 [ 1 1]
0 [ 1 ]]
0 1 2 3 4 5 6 7
Game step 150 /200
Game step 150 /200
Game step 150 /200
Game step 150 /200
Game step 150 /200
Game step 150 /200
Game step 150 /200
Game step 150 /200
Game step 150 /200
Game step 150 /200
Game step 150 /200
Game step 150 /200
Game step 150 /200
Game step 150 /200
Game step 150 /200
Game step 160 /200
Game step 160 /200
Game step 160 /200
Game step 160 /200
Game step 160 /200
Game step 160 /200
Game step 160 /200
Game step 160 /200
Game step 160 /200
Game step 160 /200
Game step 160 /200
Game step 160 /200
Game step 160 /200
Game step 160 /200
Game step 160 /200
Terminated due to peaceful activity
Terminated at step 167
First player won.
7[[ -1]
6 [ -1 ]
5 [ -2 -1 ]
4 [ -2 ]
3 [ 2 ]
2 [ 1 2 2 ]
1 [ 2 1]
0 [ ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 167
First player won.
7[[ -1]
6 [ -1 ]
5 [ -2 -1 ]
4 [ -2 ]
3 [ 2 ]
2 [ 1 2 2 ]
1 [ 2 1]
0 [ ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated due to peaceful activity
Terminated at step 167
First player won.
7[[ -1]
6 [ -1 ]
5 [ -2 -1 ]
Terminated at step 167
Terminated due to peaceful activity
Terminated due to peaceful activity
Terminated at step 167
4 [ -2 ]
First player won.
7[[ -1]
First player won.
7[[ -1]
6 [ -1 ]
5 [ -2 -1 ]
4 [ -2 ]
3 [ 2 ]
2 [ 1 2 2 ]
1 [ 2 1]
0 [ ]]
0 1 2 3 4 5 6 7
6 [ -1 ]
Terminated at step 167
3 [ 2 ]
Terminated due to peaceful activity
Terminated due to peaceful activity
5 [ -2 -1 ]
4 [ -2 ]
3 [ 2 ]
2 [ 1 2 2 ]
1 [ 2 1]
First player won.
2 [ 1 2 2 ]
1 [ 2 1]
0 [ ]]
0 1 2 3 4 5 6 7
Terminated at step 167
7[[ -1]
Terminated due to peaceful activity
Terminated at step 167
Terminated due to peaceful activity
0 [ ]]
6 [ -1 ]
Terminated due to peaceful activity
Terminated at step 167
First player won.
7[[ -1]
6 [ -1 ]
5 [ -2 -1 ]
4 [ -2 ]
3 [ 2 ]
2 [ 1 2 2 ]
1 [ 2 1]
0 [ ]]
Terminated due to peaceful activity
Terminated at step 167
5 [ -2 -1 ]
0 1 2 3 4 5 6 7
Terminated at step 167
0 1 2 3 4 5 6 7
Terminated at step 167
First player won.
First player won.
7[[ -1]
First player won.
First player won.
7[[ -1]
6 [ -1 ]
5 [ -2 -1 ]
4 [ -2 ]
3 [ 2 ]
2 [ 1 2 2 ]
1 [ 2 1]
0 [ ]]
0 1 2 3 4 5 6 7
6 [ -1 ]
4 [ -2 ]
7[[ -1]
6 [ -1 ]
5 [ -2 -1 ]
4 [ -2 ]
First player won.
3 [ 2 ]
2 [ 1 2 2 ]
1 [ 2 1]
0 [ ]]
0 1 2 3 4 5 6 7
5 [ -2 -1 ]
4 [ -2 ]
7[[ -1]
3 [ 2 ]
2 [ 1 2 2 ]
3 [ 2 ]
2 [ 1 2 2 ]
1 [ 2 1]
7[[ -1]
1 [ 2 1]
0 [ ]]
0 1 2 3 4 5 6 7
0 [ ]]
0 1 2 3 4 5 6 7
6 [ -1 ]
5 [ -2 -1 ]
4 [ -2 ]
3 [ 2 ]
2 [ 1 2 2 ]
1 [ 2 1]
0 [ ]]
Terminated due to peaceful activity
Terminated at step 167
0 1 2 3 4 5 6 7
First player won.
7[[ -1]
6 [ -1 ]
5 [ -2 -1 ]
6 [ -1 ]
5 [ -2 -1 ]
4 [ -2 ]
3 [ 2 ]
2 [ 1 2 2 ]
1 [ 2 1]
0 [ ]]
0 1 2 3 4 5 6 7
4 [ -2 ]
Terminated due to peaceful activity
3 [ 2 ]
Terminated at step 167
First player won.
7[[ -1]
6 [ -1 ]
5 [ -2 -1 ]
4 [ -2 ]
3 [ 2 ]
2 [ 1 2 2 ]
1 [ 2 1]
0 [ ]]
0 1 2 3 4 5 6 7
2 [ 1 2 2 ]
1 [ 2 1]
0 [ ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 167
First player won.
7[[ -1]
6 [ -1 ]
5 [ -2 -1 ]
4 [ -2 ]
3 [ 2 ]
2 [ 1 2 2 ]
1 [ 2 1]
0 [ ]]
0 1 2 3 4 5 6 7
MCTS pool has joined
Terminal sentinel is put on queue
Sentinel received. GPU will process this batch and terminate afterwards
Queue task done signal sent. Queue will join. Thread may still be running.
Queue has joined
GPU Thread has joined
Successful generation of 16 games
Queue empty: True
value10 train epoch 6, resampling 0. running value loss: 0.71494. running policy loss: 1.39316. running p diff: 0.12343
value10 valid epoch 6, resampling 0. validation value loss: 0.90806. validation policy loss: 1.15012 validation p diff: 0.09207
saved model value10 at D:\Git\alphazero-checker\saves\value10_6_0.pkl
value10 train epoch 6, resampling 10. running value loss: 0.73914. running policy loss: 1.33417. running p diff: 0.11597
value10 train epoch 6, resampling 20. running value loss: 0.76759. running policy loss: 1.31568. running p diff: 0.11139
value10 train epoch 6, resampling 30. running value loss: 0.78002. running policy loss: 1.31734. running p diff: 0.10645
value10 train epoch 6, resampling 40. running value loss: 0.78491. running policy loss: 1.31935. running p diff: 0.10228
value10 train epoch 6, resampling 50. running value loss: 0.76044. running policy loss: 1.30637. running p diff: 0.09782
value10 train epoch 6, resampling 60. running value loss: 0.73276. running policy loss: 1.39969. running p diff: 0.10073
value10 train epoch 6, resampling 70. running value loss: 0.73223. running policy loss: 1.43122. running p diff: 0.10170
value10 train epoch 6, resampling 80. running value loss: 0.76860. running policy loss: 1.37348. running p diff: 0.10075
value10 train epoch 6, resampling 90. running value loss: 0.82141. running policy loss: 1.26712. running p diff: 0.10046
value10 train epoch 6, resampling 100. running value loss: 0.86179. running policy loss: 1.24305. running p diff: 0.10516
value10 train epoch 6, resampling 110. running value loss: 0.86361. running policy loss: 1.30261. running p diff: 0.11250
value10 train epoch 6, resampling 120. running value loss: 0.83745. running policy loss: 1.40624. running p diff: 0.12083
value10 train epoch 6, resampling 130. running value loss: 0.77168. running policy loss: 1.48969. running p diff: 0.12671
value10 train epoch 6, resampling 140. running value loss: 0.69186. running policy loss: 1.51295. running p diff: 0.12818
value10 train epoch 6, resampling 150. running value loss: 0.61623. running policy loss: 1.44423. running p diff: 0.12387
value10 train epoch 6, resampling 160. running value loss: 0.56013. running policy loss: 1.31617. running p diff: 0.11728
value10 train epoch 6, resampling 170. running value loss: 0.54228. running policy loss: 1.21307. running p diff: 0.11302
value10 train epoch 6, resampling 180. running value loss: 0.56846. running policy loss: 1.15151. running p diff: 0.10998
value10 train epoch 6, resampling 190. running value loss: 0.61994. running policy loss: 1.12326. running p diff: 0.10831
Generating a new game with MCTS
Generating a new game with MCTS
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Game step 0 /200
Game step 0 /200
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Game step 0 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 110 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Game step 130 /200
Terminated due to peaceful activity
Terminated at step 130
Second player won
7[[ -1 ]
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 ]
3 [ 2 -1]
2 [ 1 1 ]
1 [ -2 1 1]
0 [ -2 1 ]]
0 1 2 3 4 5 6 7
Game step 130 /200
Game step 130 /200
Terminated due to peaceful activity
Terminated at step 130
Second player won
7[[ -1 ]
6 [-1 -1 -1 ]
Terminated due to peaceful activity
Terminated at step 130
Second player won
7[[ -1 ]
5 [ -1 -1 ]
6 [-1 -1 -1 ]
4 [ 1 1 ]
5 [ -1 -1 ]
3 [ 2 -1]
4 [ 1 1 ]
3 [ 2 -1]
2 [ 1 1 ]
1 [ -2 1 1]
2 [ 1 1 ]
0 [ -2 1 ]]
1 [ -2 1 1]
0 1 2 3 4 5 6 7
0 [ -2 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 130
Second player won
7[[ -1 ]
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 ]
3 [ 2 -1]
2 [ 1 1 ]
1 [ -2 1 1]
0 [ -2 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 127
Second player won
Terminated due to peaceful activity
7[[ -1 -1 ]
6 [-1 -1 2 -1 ]
5 [ -1 -1 -1]
4 [ 1 1 ]
3 [ -1]
2 [ 1 1 ]
1 [ 1 1]
0 [-2 1 ]]
0 1 2 3 4 5 6 7
Terminated at step 127
Second player won
7[[ -1 -1 ]
6 [-1 -1 2 -1 ]
5 [ -1 -1 -1]
4 [ 1 1 ]
3 [ -1]
2 [ 1 1 ]
1 [ 1 1]
0 [-2 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 127
Second player won
7[[ -1 -1 ]
6 [-1 -1 2 -1 ]
5 [ -1 -1 -1]
4 [ 1 1 ]
3 [ -1]
2 [ 1 1 ]
1 [ 1 1]
0 [-2 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 130
Second player won
7[[ -1 ]
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 ]
3 [ 2 -1]
2 [ 1 1 ]
1 [ -2 1 1]
0 [ -2 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 127
Second player won
7[[ -1 -1 ]
6 [-1 -1 2 -1 ]
5 [ -1 -1 -1]
4 [ 1 1 ]
3 [ -1]
2 [ 1 1 ]
1 [ 1 1]
0 [-2 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 127
Second player won
7[[ -1 -1 ]
6 [-1 -1 2 -1 ]
5 [ -1 -1 -1]
4 [ 1 1 ]
3 [ -1]
2 [ 1 1 ]
1 [ 1 1]
0 [-2 1 ]]
0 1 2 3 4 5 6 7
Game step 120 /200
Terminated due to peaceful activity
Terminated at step 130
Second player won
7[[ -1 ]
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 ]
3 [ 2 -1]
2 [ 1 1 ]
1 [ -2 1 1]
0 [ -2 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 130
Second player won
7[[ -1 ]
Terminated due to peaceful activity
6 [-1 -1 -1 ]
Terminated at step 130
Second player won
7[[ -1 ]
5 [ -1 -1 ]
4 [ 1 1 ]
3 [ 2 -1]
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 ]
3 [ 2 -1]
2 [ 1 1 ]
1 [ -2 1 1]
2 [ 1 1 ]
0 [ -2 1 ]]
1 [ -2 1 1]
0 [ -2 1 ]]
0 1 2 3 4 5 6 7
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 125
Second player won
7[[ -1 2 -1 -1]
6 [-1 -1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ -2 1 1]
0 [ 1 ]]
0 1 2 3 4 5 6 7
Game step 140 /200
Game step 130 /200
Terminated due to peaceful activity
Terminated at step 148
First player won.
7[[ -1 2]
6 [-1 -1 ]
5 [ -1 -2 -1 ]
4 [ 1 ]
3 [ -1]
2 [ 1 2 1 ]
1 [ 1 1 1]
0 [ 1 ]]
0 1 2 3 4 5 6 7
Game step 140 /200
Terminated due to peaceful activity
Terminated at step 144
Draw
7[[ -1 2]
6 [-1 -1 ]
5 [ -1 -1 ]
4 [ 1 1 ]
3 [ -1 -1]
2 [ 1 1 ]
1 [ 1 1]
0 [-2 1 ]]
0 1 2 3 4 5 6 7
MCTS pool has joined
Terminal sentinel is put on queue
Sentinel received. GPU will process this batch and terminate afterwards
Queue task done signal sent. Queue will join. Thread may still be running.
Queue has joined
GPU Thread has joined
Successful generation of 16 games
Queue empty: True
value10 train epoch 7, resampling 0. running value loss: 0.66119. running policy loss: 1.11709. running p diff: 0.10716
value10 valid epoch 7, resampling 0. validation value loss: 0.75455. validation policy loss: 0.89807 validation p diff: 0.08190
saved model value10 at D:\Git\alphazero-checker\saves\value10_7_0.pkl
value10 train epoch 7, resampling 10. running value loss: 0.70725. running policy loss: 1.06584. running p diff: 0.10208
value10 train epoch 7, resampling 20. running value loss: 0.70402. running policy loss: 1.00669. running p diff: 0.09603
value10 train epoch 7, resampling 30. running value loss: 0.68353. running policy loss: 0.99060. running p diff: 0.09276
value10 train epoch 7, resampling 40. running value loss: 0.66262. running policy loss: 1.00525. running p diff: 0.09210
value10 train epoch 7, resampling 50. running value loss: 0.67038. running policy loss: 1.00424. running p diff: 0.09260
value10 train epoch 7, resampling 60. running value loss: 0.66984. running policy loss: 1.02686. running p diff: 0.09605
value10 train epoch 7, resampling 70. running value loss: 0.65318. running policy loss: 1.01253. running p diff: 0.09657
value10 train epoch 7, resampling 80. running value loss: 0.64361. running policy loss: 0.95447. running p diff: 0.09459
value10 train epoch 7, resampling 90. running value loss: 0.63297. running policy loss: 0.89425. running p diff: 0.09176
value10 train epoch 7, resampling 100. running value loss: 0.60468. running policy loss: 0.86671. running p diff: 0.08995
value10 train epoch 7, resampling 110. running value loss: 0.58506. running policy loss: 0.88149. running p diff: 0.09116
value10 train epoch 7, resampling 120. running value loss: 0.59892. running policy loss: 0.91757. running p diff: 0.09485
value10 train epoch 7, resampling 130. running value loss: 0.61184. running policy loss: 0.94983. running p diff: 0.09814
value10 train epoch 7, resampling 140. running value loss: 0.62701. running policy loss: 0.95833. running p diff: 0.10037
value10 train epoch 7, resampling 150. running value loss: 0.63488. running policy loss: 0.95110. running p diff: 0.10178
value10 train epoch 7, resampling 160. running value loss: 0.63287. running policy loss: 0.93411. running p diff: 0.10193
value10 train epoch 7, resampling 170. running value loss: 0.63011. running policy loss: 0.93520. running p diff: 0.10318
value10 train epoch 7, resampling 180. running value loss: 0.62031. running policy loss: 0.94455. running p diff: 0.10509
value10 train epoch 7, resampling 190. running value loss: 0.58506. running policy loss: 0.95419. running p diff: 0.10670
Generating a new game with MCTS
Generating a new game with MCTS
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Game step 0 /200
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Generating a new game with MCTS
Generating a new game with MCTS
Game step 0 /200
Game step 0 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 10 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 20 /200
Game step 30 /200
Game step 40 /200
Terminated at step 45
First player won.
7[[ 2 2 ]
6 [ 1 ]
5 [ ]
4 [ ]
3 [ -1]
2 [ 1 2 1 ]
1 [ 1 1 1]
0 [ 1 1 ]]
0 1 2 3 4 5 6 7
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 30 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 40 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 50 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 60 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 70 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 80 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 90 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 100 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Terminated due to peaceful activity
Terminated at step 110
First player won.
7[[ -1 -1]
6 [-1 -1 2 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1]
2 [ 1 1 ]
1 [ 1 -2 1 1]
0 [ 1 1 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 110
First player won.
7[[ -1 -1]
6 [-1 -1 2 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1]
2 [ 1 1 ]
1 [ 1 -2 1 1]
0 [ 1 1 1 ]]
0 1 2 3 4 5 6 7
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Game step 110 /200
Terminated due to peaceful activity
Terminated at step 110
First player won.
7[[ -1 -1]
6 [-1 -1 2 -1 ]
5 [ -1 -1 -1]
4 [ 1 ]
3 [ ]
2 [ 1 1 ]
1 [ 1 -2 1 1]
0 [ 1 1 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 110
First player won.
7[[ -1 -1]
6 [-1 -1 2 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1]
2 [ 1 1 ]
1 [ 1 -2 1 1]
0 [ 1 1 1 ]]
0 1 2 3 4 5 6 7
Game step 110 /200
Terminated due to peaceful activity
Terminated at step 110
First player won.
7[[ -1 -1]
6 [-1 -1 2 -1 ]
5 [ -1 -1 -1]
4 [ 1 ]
3 [ ]
2 [ 1 1 ]
1 [ 1 -2 1 1]
0 [ 1 1 1 ]]
0 1 2 3 4 5 6 7
Game step 110 /200
Terminated due to peaceful activity
Terminated at step 110
First player won.
7[[ -1 -1]
6 [-1 -1 2 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1]
2 [ 1 1 ]
1 [ 1 -2 1 1]
0 [ 1 1 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 110
First player won.
7[[ -1 -1]
6 [-1 -1 2 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1]
2 [ 1 1 ]
1 [ 1 -2 1 1]
0 [ 1 1 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 110
First player won.
7[[ -1 -1]
6 [-1 -1 2 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
Terminated due to peaceful activity
3 [ -1]
Terminated at step 110
First player won.
7[[ -1 -1]
6 [-1 -1 2 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1]
2 [ 1 1 ]
1 [ 1 -2 1 1]
0 [ 1 1 1 ]]
0 1 2 3 4 5 6 7
2 [ 1 1 ]
1 [ 1 -2 1 1]
0 [ 1 1 1 ]]
0 1 2 3 4 5 6 7
Game step 110 /200
Terminated due to peaceful activity
Terminated at step 110
First player won.
7[[ -1 -1]
6 [-1 -1 2 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1]
2 [ 1 1 ]
1 [ 1 -2 1 1]
0 [ 1 1 1 ]]
0 1 2 3 4 5 6 7
Game step 120 /200
Terminated due to peaceful activity
Terminated at step 126
First player won.
7[[ -1 2]
6 [-1 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1]
2 [ 1 1 1 ]
1 [ 1 1 1]
0 [ 1 -2 1 1 ]]
0 1 2 3 4 5 6 7
Game step 120 /200
Game step 120 /200
Game step 120 /200
Game step 120 /200
Terminated due to peaceful activity
Terminated at step 126
First player won.
7[[ -1 2 ]
6 [-1 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1]
2 [ 1 1 1 ]
1 [ 1 1 1]
0 [ 1 -2 1 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 126
First player won.
7[[ -1 2 ]
6 [-1 -1 ]
5 [ -1 -1 ]
4 [ 1 ]
3 [ -1]
2 [ 1 1 1 ]
1 [ 1 1 1]
0 [ 1 -2 1 1 ]]
0 1 2 3 4 5 6 7
Game step 130 /200
Game step 130 /200
Game step 140 /200
Game step 140 /200
Terminated due to peaceful activity
Terminated at step 144
First player won.
7[[ 2 ]
6 [ 2 -1 ]
5 [ -1 -1 ]
4 [ ]
3 [ -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ 1 -2 1 1 ]]
0 1 2 3 4 5 6 7
Terminated due to peaceful activity
Terminated at step 144
First player won.
7[[ 2 ]
6 [ 2 -1 ]
5 [ -1 -1 ]
4 [ ]
3 [ -1]
2 [ 1 1 ]
1 [ 1 1 1]
0 [ 1 -2 1 1 ]]
0 1 2 3 4 5 6 7
MCTS pool has joined
Terminal sentinel is put on queue
Sentinel received. GPU will process this batch and terminate afterwards
Queue task done signal sent. Queue will join. Thread may still be running.
Queue has joined
GPU Thread has joined
Successful generation of 16 games
Queue empty: True
value10 train epoch 8, resampling 0. running value loss: 0.53019. running policy loss: 0.95079. running p diff: 0.10692
value10 valid epoch 8, resampling 0. validation value loss: 0.65976. validation policy loss: 0.72675 validation p diff: 0.09772
saved model value10 at D:\Git\alphazero-checker\saves\value10_8_0.pkl
value10 train epoch 8, resampling 10. running value loss: 0.51339. running policy loss: 0.91103. running p diff: 0.10567
value10 train epoch 8, resampling 20. running value loss: 0.53174. running policy loss: 0.86664. running p diff: 0.10395
value10 train epoch 8, resampling 30. running value loss: 0.55852. running policy loss: 0.84448. running p diff: 0.10365
value10 train epoch 8, resampling 40. running value loss: 0.60020. running policy loss: 0.84770. running p diff: 0.10478
value10 train epoch 8, resampling 50. running value loss: 0.66539. running policy loss: 0.87465. running p diff: 0.10744
value10 train epoch 8, resampling 60. running value loss: 0.69395. running policy loss: 0.92930. running p diff: 0.11127
value10 train epoch 8, resampling 70. running value loss: 0.66471. running policy loss: 0.96512. running p diff: 0.11350
value10 train epoch 8, resampling 80. running value loss: 0.60792. running policy loss: 0.97360. running p diff: 0.11371
value10 train epoch 8, resampling 90. running value loss: 0.56133. running policy loss: 0.96168. running p diff: 0.11267
value10 train epoch 8, resampling 100. running value loss: 0.51815. running policy loss: 0.94436. running p diff: 0.11154
value10 train epoch 8, resampling 110. running value loss: 0.50454. running policy loss: 0.92764. running p diff: 0.11062
value10 train epoch 8, resampling 120. running value loss: 0.52588. running policy loss: 0.91802. running p diff: 0.11051
value10 train epoch 8, resampling 130. running value loss: 0.56977. running policy loss: 0.91883. running p diff: 0.11137
value10 train epoch 8, resampling 140. running value loss: 0.60362. running policy loss: 0.92106. running p diff: 0.11173
value10 train epoch 8, resampling 150. running value loss: 0.63363. running policy loss: 0.91274. running p diff: 0.11093
value10 train epoch 8, resampling 160. running value loss: 0.62682. running policy loss: 0.90141. running p diff: 0.10904
value10 train epoch 8, resampling 170. running value loss: 0.59546. running policy loss: 0.88496. running p diff: 0.10633
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment