
=== 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)
=> Add worker ByzantineWorker(index=10)
=> Add worker ByzantineWorker(index=11)

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7ff85f5b27f0>

Train epoch 1
[E 1B0  |    384/60000 (  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')
Worker 10 has targets: tensor([4, 8, 8, 6, 9], device='cuda:0')
Worker 11 has targets: tensor([5, 3, 6, 0, 9], device='cuda:0')


[E 1B10 |   4224/60000 (  7%) ] Loss: 1.9238 top1= 46.2500
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.8805 top1= 71.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5065 top1= 83.8542


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5118 top1= 83.0529


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5415 top1= 83.5236

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.7080 top1= 80.0000
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.4346 top1= 85.3125
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.3871 top1= 88.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2943 top1= 91.2961


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2974 top1= 91.1158


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3097 top1= 90.9455

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.3539 top1= 88.7500
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.2363 top1= 92.1875
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.2499 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2387 top1= 92.8986


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2420 top1= 92.7284


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2466 top1= 92.6382

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1996 top1= 93.7500
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.1516 top1= 95.9375
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.1718 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2084 top1= 93.7300


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2141 top1= 93.4295


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2129 top1= 93.6098

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.1341 top1= 95.6250
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0946 top1= 97.1875
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.1100 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2060 top1= 93.9002


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2040 top1= 93.8702


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2222 top1= 93.5196

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0900 top1= 98.1250
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0673 top1= 97.8125
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0802 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1997 top1= 94.1106


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2157 top1= 93.6999


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2037 top1= 94.1807

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0781 top1= 97.8125
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0317 top1= 99.3750
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0326 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2028 top1= 94.3910


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2067 top1= 94.2107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2152 top1= 94.0905

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0539 top1= 98.1250
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0342 top1= 99.6875
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0345 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2026 top1= 94.5212


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1904 top1= 94.9319


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2459 top1= 93.4195

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0457 top1= 98.4375
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0436 top1= 98.7500
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0256 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1836 top1= 95.1422


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2024 top1= 94.6214


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1857 top1= 95.1522

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0379 top1= 99.3750
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0255 top1= 99.0625
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0203 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2020 top1= 94.6815


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2167 top1= 94.3610


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2052 top1= 94.6114

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0417 top1= 98.1250
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0235 top1= 99.3750
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0148 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1876 top1= 95.2123


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2018 top1= 94.7115


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1888 top1= 95.2324

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0184 top1= 99.3750
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0252 top1= 99.0625
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0077 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1831 top1= 95.3626


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1918 top1= 95.1022


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1859 top1= 95.2925

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0162 top1= 99.3750
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0083 top1= 99.6875
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0045 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1944 top1= 95.4527


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1962 top1= 95.3025


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1961 top1= 95.3926

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0051 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0123 top1= 99.6875
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0043 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2016 top1= 95.2624


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2091 top1= 95.0120


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2028 top1= 95.3425

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0099 top1= 99.6875
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0022 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0040 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1931 top1= 95.6130


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1960 top1= 95.6230


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1929 top1= 95.5829

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0086 top1= 99.6875
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0085 top1= 99.6875
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0037 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1928 top1= 95.6731


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1942 top1= 95.5729


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1964 top1= 95.6330

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0025 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2045 top1= 95.5529


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2048 top1= 95.5629


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2053 top1= 95.5028

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0059 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0016 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0029 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2105 top1= 95.4928


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2068 top1= 95.5829


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2156 top1= 95.3225

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0018 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2039 top1= 95.7031


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2004 top1= 95.7131


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2092 top1= 95.5829

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0012 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2030 top1= 95.6831


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2027 top1= 95.7332


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2036 top1= 95.7131

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2063 top1= 95.6831


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2056 top1= 95.7031


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2073 top1= 95.6831

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2085 top1= 95.6631


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2078 top1= 95.6731


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2094 top1= 95.6530

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0008 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2105 top1= 95.6631


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2098 top1= 95.6931


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2114 top1= 95.6631

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0007 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2124 top1= 95.6530


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2117 top1= 95.6931


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2132 top1= 95.6631

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2141 top1= 95.6530


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2134 top1= 95.6931


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2149 top1= 95.6530

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2157 top1= 95.6430


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2150 top1= 95.6931


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2165 top1= 95.6731

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2172 top1= 95.6530


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2165 top1= 95.7131


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2180 top1= 95.6731

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2186 top1= 95.6731


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2180 top1= 95.7131


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2194 top1= 95.6631

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2200 top1= 95.6731


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2193 top1= 95.6931


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2207 top1= 95.6631

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2213 top1= 95.6631


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2206 top1= 95.6931


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2220 top1= 95.6631

