
=== Start adding workers ===
=> Add worker SGDMWorker(index=0, momentum=0.9)
=> Add worker SGDMWorker(index=1, momentum=0.9)
=> Add worker SGDMWorker(index=2, momentum=0.9)
=> Add worker SGDMWorker(index=3, momentum=0.9)
=> Add worker SGDMWorker(index=4, momentum=0.9)
=> Add worker SGDMWorker(index=5, momentum=0.9)
=> Add worker SGDMWorker(index=6, momentum=0.9)
=> Add worker SGDMWorker(index=7, momentum=0.9)
=> Add worker SGDMWorker(index=8, momentum=0.9)
=> Add worker SGDMWorker(index=9, momentum=0.9)

=== Start adding graph ===
<codes.graph_utils.Dumbbell object at 0x7fa1698876d0>

Train epoch 1
[E 1B0  |    320/60000 (  1%) ] Loss: 2.2959 top1= 10.0000

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([4, 8, 8, 6, 9], device='cuda:0')
Worker 1 has targets: tensor([5, 3, 6, 0, 9], device='cuda:0')
Worker 2 has targets: tensor([2, 9, 9, 3, 1], device='cuda:0')
Worker 3 has targets: tensor([6, 9, 8, 1, 2], device='cuda:0')
Worker 4 has targets: tensor([5, 8, 9, 1, 8], device='cuda:0')
Worker 5 has targets: tensor([6, 7, 5, 2, 3], device='cuda:0')
Worker 6 has targets: tensor([3, 2, 8, 7, 9], device='cuda:0')
Worker 7 has targets: tensor([3, 8, 7, 8, 7], device='cuda:0')
Worker 8 has targets: tensor([8, 0, 2, 4, 8], device='cuda:0')
Worker 9 has targets: tensor([5, 3, 4, 6, 3], device='cuda:0')


[E 1B10 |   3520/60000 (  6%) ] Loss: 1.9214 top1= 46.5625
[E 1B20 |   6720/60000 ( 11%) ] Loss: 0.8657 top1= 72.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4913 top1= 84.8357


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5029 top1= 83.5036


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5207 top1= 84.7756

Train epoch 2
[E 2B0  |    320/60000 (  1%) ] Loss: 0.6843 top1= 81.2500
[E 2B10 |   3520/60000 (  6%) ] Loss: 0.4189 top1= 86.2500
[E 2B20 |   6720/60000 ( 11%) ] Loss: 0.3883 top1= 89.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2899 top1= 91.5064


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2941 top1= 91.3261


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3060 top1= 91.0056

Train epoch 3
[E 3B0  |    320/60000 (  1%) ] Loss: 0.3535 top1= 88.7500
[E 3B10 |   3520/60000 (  6%) ] Loss: 0.2497 top1= 91.2500
[E 3B20 |   6720/60000 ( 11%) ] Loss: 0.2609 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2343 top1= 93.1490


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2340 top1= 93.1190


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2436 top1= 92.8786

Train epoch 4
[E 4B0  |    320/60000 (  1%) ] Loss: 0.2060 top1= 94.0625
[E 4B10 |   3520/60000 (  6%) ] Loss: 0.1577 top1= 95.6250
[E 4B20 |   6720/60000 ( 11%) ] Loss: 0.1643 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2060 top1= 93.8101


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2094 top1= 93.6599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2110 top1= 93.7600

Train epoch 5
[E 5B0  |    320/60000 (  1%) ] Loss: 0.1315 top1= 95.6250
[E 5B10 |   3520/60000 (  6%) ] Loss: 0.1010 top1= 96.5625
[E 5B20 |   6720/60000 ( 11%) ] Loss: 0.1112 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2005 top1= 94.0304


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2000 top1= 93.9603


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2121 top1= 93.8001

Train epoch 6
[E 6B0  |    320/60000 (  1%) ] Loss: 0.0999 top1= 97.5000
[E 6B10 |   3520/60000 (  6%) ] Loss: 0.0629 top1= 98.7500
[E 6B20 |   6720/60000 ( 11%) ] Loss: 0.0808 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1954 top1= 94.4611


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2031 top1= 94.1506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2037 top1= 94.2909

Train epoch 7
[E 7B0  |    320/60000 (  1%) ] Loss: 0.0826 top1= 97.8125
[E 7B10 |   3520/60000 (  6%) ] Loss: 0.0380 top1= 99.0625
[E 7B20 |   6720/60000 ( 11%) ] Loss: 0.0463 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2135 top1= 94.0905


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2282 top1= 93.7300


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2213 top1= 93.8802

Train epoch 8
[E 8B0  |    320/60000 (  1%) ] Loss: 0.0898 top1= 96.2500
[E 8B10 |   3520/60000 (  6%) ] Loss: 0.0276 top1= 99.3750
[E 8B20 |   6720/60000 ( 11%) ] Loss: 0.0341 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1983 top1= 94.5713


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1890 top1= 94.7917


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2201 top1= 94.0405

Train epoch 9
[E 9B0  |    320/60000 (  1%) ] Loss: 0.0428 top1= 98.7500
[E 9B10 |   3520/60000 (  6%) ] Loss: 0.0354 top1= 98.7500
[E 9B20 |   6720/60000 ( 11%) ] Loss: 0.0269 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1906 top1= 94.9119


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1945 top1= 94.6915


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2072 top1= 94.4411

Train epoch 10
[E10B0  |    320/60000 (  1%) ] Loss: 0.0698 top1= 98.1250
[E10B10 |   3520/60000 (  6%) ] Loss: 0.0279 top1= 99.3750
[E10B20 |   6720/60000 ( 11%) ] Loss: 0.0277 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1930 top1= 94.9119


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2075 top1= 94.6615


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1894 top1= 95.0120

Train epoch 11
[E11B0  |    320/60000 (  1%) ] Loss: 0.0181 top1=100.0000
[E11B10 |   3520/60000 (  6%) ] Loss: 0.0160 top1= 99.3750
[E11B20 |   6720/60000 ( 11%) ] Loss: 0.0109 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1898 top1= 95.1022


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1983 top1= 94.8918


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1907 top1= 95.0521

Train epoch 12
[E12B0  |    320/60000 (  1%) ] Loss: 0.0201 top1= 99.0625
[E12B10 |   3520/60000 (  6%) ] Loss: 0.0129 top1= 99.6875
[E12B20 |   6720/60000 ( 11%) ] Loss: 0.0060 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1831 top1= 95.5429


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1810 top1= 95.5929


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1903 top1= 95.2724

Train epoch 13
[E13B0  |    320/60000 (  1%) ] Loss: 0.0084 top1= 99.6875
[E13B10 |   3520/60000 (  6%) ] Loss: 0.0055 top1=100.0000
[E13B20 |   6720/60000 ( 11%) ] Loss: 0.0053 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1989 top1= 95.3726


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1994 top1= 95.3526


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1996 top1= 95.3225

Train epoch 14
[E14B0  |    320/60000 (  1%) ] Loss: 0.0054 top1=100.0000
[E14B10 |   3520/60000 (  6%) ] Loss: 0.0113 top1= 99.6875
[E14B20 |   6720/60000 ( 11%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2001 top1= 95.4127


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1971 top1= 95.4427


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2061 top1= 95.3125

Train epoch 15
[E15B0  |    320/60000 (  1%) ] Loss: 0.0054 top1=100.0000
[E15B10 |   3520/60000 (  6%) ] Loss: 0.0035 top1=100.0000
[E15B20 |   6720/60000 ( 11%) ] Loss: 0.0052 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1957 top1= 95.5729


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1996 top1= 95.4527


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1949 top1= 95.6430

Train epoch 16
[E16B0  |    320/60000 (  1%) ] Loss: 0.0034 top1=100.0000
[E16B10 |   3520/60000 (  6%) ] Loss: 0.0027 top1=100.0000
[E16B20 |   6720/60000 ( 11%) ] Loss: 0.0033 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2047 top1= 95.4928


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2065 top1= 95.4928


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2041 top1= 95.5329

Train epoch 17
[E17B0  |    320/60000 (  1%) ] Loss: 0.0047 top1=100.0000
[E17B10 |   3520/60000 (  6%) ] Loss: 0.0036 top1=100.0000
[E17B20 |   6720/60000 ( 11%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2054 top1= 95.6530


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2023 top1= 95.7632


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2101 top1= 95.5429

Train epoch 18
[E18B0  |    320/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E18B10 |   3520/60000 (  6%) ] Loss: 0.0013 top1=100.0000
[E18B20 |   6720/60000 ( 11%) ] Loss: 0.0073 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2039 top1= 95.8033


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2068 top1= 95.6931


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2025 top1= 95.6731

Train epoch 19
[E19B0  |    320/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E19B10 |   3520/60000 (  6%) ] Loss: 0.0013 top1=100.0000
[E19B20 |   6720/60000 ( 11%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2045 top1= 95.7632


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2036 top1= 95.7933


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2055 top1= 95.7332

Train epoch 20
[E20B0  |    320/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E20B10 |   3520/60000 (  6%) ] Loss: 0.0010 top1=100.0000
[E20B20 |   6720/60000 ( 11%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2070 top1= 95.7232


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2063 top1= 95.7632


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2078 top1= 95.7332

Train epoch 21
[E21B0  |    320/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E21B10 |   3520/60000 (  6%) ] Loss: 0.0008 top1=100.0000
[E21B20 |   6720/60000 ( 11%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2096 top1= 95.6931


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2089 top1= 95.7031


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2104 top1= 95.7432

Train epoch 22
[E22B0  |    320/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E22B10 |   3520/60000 (  6%) ] Loss: 0.0008 top1=100.0000
[E22B20 |   6720/60000 ( 11%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2117 top1= 95.7031


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2111 top1= 95.7031


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2125 top1= 95.7332

Train epoch 23
[E23B0  |    320/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E23B10 |   3520/60000 (  6%) ] Loss: 0.0007 top1=100.0000
[E23B20 |   6720/60000 ( 11%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2137 top1= 95.7131


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2131 top1= 95.7031


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2144 top1= 95.7332

Train epoch 24
[E24B0  |    320/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E24B10 |   3520/60000 (  6%) ] Loss: 0.0006 top1=100.0000
[E24B20 |   6720/60000 ( 11%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2155 top1= 95.7131


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2149 top1= 95.6931


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2161 top1= 95.7031

Train epoch 25
[E25B0  |    320/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E25B10 |   3520/60000 (  6%) ] Loss: 0.0006 top1=100.0000
[E25B20 |   6720/60000 ( 11%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2171 top1= 95.7031


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2165 top1= 95.7031


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2178 top1= 95.6831

Train epoch 26
[E26B0  |    320/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E26B10 |   3520/60000 (  6%) ] Loss: 0.0005 top1=100.0000
[E26B20 |   6720/60000 ( 11%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2187 top1= 95.7031


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2181 top1= 95.7131


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2193 top1= 95.6931

Train epoch 27
[E27B0  |    320/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E27B10 |   3520/60000 (  6%) ] Loss: 0.0005 top1=100.0000
[E27B20 |   6720/60000 ( 11%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2202 top1= 95.6831


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2196 top1= 95.7031


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2208 top1= 95.7031

Train epoch 28
[E28B0  |    320/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E28B10 |   3520/60000 (  6%) ] Loss: 0.0005 top1=100.0000
[E28B20 |   6720/60000 ( 11%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2216 top1= 95.6831


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2210 top1= 95.7131


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2221 top1= 95.6931

Train epoch 29
[E29B0  |    320/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E29B10 |   3520/60000 (  6%) ] Loss: 0.0004 top1=100.0000
[E29B20 |   6720/60000 ( 11%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2229 top1= 95.6831


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2224 top1= 95.7031


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2234 top1= 95.6931

Train epoch 30
[E30B0  |    320/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E30B10 |   3520/60000 (  6%) ] Loss: 0.0004 top1=100.0000
[E30B20 |   6720/60000 ( 11%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2241 top1= 95.6731


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2236 top1= 95.7031


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2247 top1= 95.6931

