
=== 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 BitFlippingWorker
=> Add worker BitFlippingWorker

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7f59415b37f0>

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: 1.9283 top1= 46.2500
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.8832 top1= 71.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5032 top1= 83.9844


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5058 top1= 83.1931


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5516 top1= 83.1631

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.6899 top1= 80.0000
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.4629 top1= 84.3750
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.3918 top1= 87.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3061 top1= 90.7752


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3089 top1= 90.6951


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3291 top1= 90.1342

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.3533 top1= 87.5000
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.2353 top1= 92.8125
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.2466 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2489 top1= 92.7484


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2563 top1= 92.2676


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2654 top1= 92.0473

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1814 top1= 94.6875
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.1289 top1= 95.3125
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.1466 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2257 top1= 93.3093


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2353 top1= 93.0389


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2386 top1= 92.7484

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.1102 top1= 97.1875
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0771 top1= 97.8125
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.1075 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2355 top1= 93.1891


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2397 top1= 93.1991


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2638 top1= 92.3478

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0888 top1= 97.1875
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0472 top1= 98.7500
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0668 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2460 top1= 93.1891


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2681 top1= 92.6583


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2671 top1= 92.6482

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0981 top1= 97.1875
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0570 top1= 98.4375
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0354 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2213 top1= 93.8201


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2343 top1= 93.2592


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2394 top1= 93.5597

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0352 top1= 98.7500
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0389 top1= 98.7500
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0345 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2221 top1= 93.9203


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2382 top1= 93.6398


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2333 top1= 93.6799

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0693 top1= 98.4375
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0300 top1= 99.3750
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0287 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2094 top1= 94.3209


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2420 top1= 93.7400


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2078 top1= 94.4411

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0230 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0240 top1= 99.3750
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0207 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2127 top1= 94.4712


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2566 top1= 93.1190


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2091 top1= 94.5513

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0261 top1= 99.0625
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0093 top1=100.0000
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0144 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2051 top1= 94.6514


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2155 top1= 94.4712


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2227 top1= 94.0605

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0143 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0192 top1= 99.0625
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0073 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1955 top1= 94.9119


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2128 top1= 94.3109


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2172 top1= 94.2808

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0111 top1=100.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0121 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0098 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2034 top1= 94.7115


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2114 top1= 94.5513


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2162 top1= 94.2608

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0079 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0100 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0075 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2048 top1= 94.7616


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2194 top1= 94.4010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2048 top1= 94.6815

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0083 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0086 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0088 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2034 top1= 94.8417


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2156 top1= 94.4912


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2107 top1= 94.4211

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0092 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0072 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0067 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2079 top1= 94.6815


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2159 top1= 94.5713


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2132 top1= 94.4511

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0089 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0062 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0077 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2094 top1= 94.7416


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2142 top1= 94.6414


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2177 top1= 94.3610

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0081 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0064 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0083 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2055 top1= 94.7817


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2049 top1= 94.8117


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2152 top1= 94.5312

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0074 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0053 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0082 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1990 top1= 94.9820


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1990 top1= 94.9920


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2049 top1= 94.8117

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0063 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0053 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0075 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1924 top1= 95.1723


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1947 top1= 95.1623


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1934 top1= 95.1122

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0071 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0060 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0070 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1892 top1= 95.2123


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1919 top1= 95.1522


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1897 top1= 95.1322

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0069 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0063 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0072 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1870 top1= 95.2324


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1895 top1= 95.1923


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1877 top1= 95.1322

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0071 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0065 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0070 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1866 top1= 95.2224


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1881 top1= 95.2424


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1879 top1= 95.1623

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0073 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0063 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0069 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1857 top1= 95.2224


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1863 top1= 95.3325


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1872 top1= 95.1623

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0071 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0062 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0069 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1847 top1= 95.2624


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1850 top1= 95.3125


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1861 top1= 95.1923

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0071 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0060 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0064 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1841 top1= 95.2825


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1844 top1= 95.2724


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1856 top1= 95.2424

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0069 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0057 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0062 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1838 top1= 95.3025


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1842 top1= 95.3025


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1850 top1= 95.3025

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0062 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0054 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0059 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1839 top1= 95.2925


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1843 top1= 95.2925


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1850 top1= 95.2825

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0060 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0052 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0057 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1839 top1= 95.2925


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1843 top1= 95.3025


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1849 top1= 95.2624

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0057 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0051 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0056 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.1838 top1= 95.2825


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.1841 top1= 95.3425


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.1848 top1= 95.2925

