
=== 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 0x7eff4cfc39d0>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.3109 top1=  9.6875

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 1 has targets: tensor([2, 1, 4, 4, 0], device='cuda:0')
Worker 2 has targets: tensor([3, 1, 4, 1, 3], device='cuda:0')
Worker 3 has targets: tensor([2, 3, 0, 0, 1], device='cuda:0')
Worker 4 has targets: tensor([2, 1, 1, 4, 2], device='cuda:0')
Worker 5 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')
Worker 6 has targets: tensor([9, 9, 6, 7, 9], device='cuda:0')
Worker 7 has targets: tensor([7, 5, 7, 9, 5], device='cuda:0')
Worker 8 has targets: tensor([8, 9, 9, 5, 7], device='cuda:0')
Worker 9 has targets: tensor([8, 8, 7, 5, 9], device='cuda:0')
Worker 10 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 11 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')


[E 1B10 |   4224/60000 (  7%) ] Loss: 1.4624 top1= 54.3750
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.6297 top1= 82.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8970 top1= 81.5405


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9771 top1= 48.5777


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1984 top1= 43.0589

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3938 top1= 90.6250
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3934 top1= 88.7500
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.2673 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8471 top1= 82.7324


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1043 top1= 48.9583


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4835 top1= 43.7700

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.3617 top1= 90.9375
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.3559 top1= 89.6875
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.2368 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8327 top1= 82.2115


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0174 top1= 49.1787


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3985 top1= 43.9303

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.3302 top1= 91.8750
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.3296 top1= 90.9375
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.2252 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8338 top1= 82.2216


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9872 top1= 49.2488


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3541 top1= 44.0104

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.3142 top1= 92.5000
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.3190 top1= 91.2500
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.2218 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8409 top1= 81.7508


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9606 top1= 49.3089


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3504 top1= 44.1006

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.3049 top1= 92.8125
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.3154 top1= 92.1875
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.2186 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8471 top1= 81.4002


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9414 top1= 49.3790


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3330 top1= 43.9904

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.3058 top1= 92.1875
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.3118 top1= 92.1875
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.2196 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8479 top1= 81.4904


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9226 top1= 49.4491


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3122 top1= 44.0805

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.2986 top1= 93.4375
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.3100 top1= 92.5000
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.2167 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8526 top1= 81.5004


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9060 top1= 49.4792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3065 top1= 44.2107

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.2947 top1= 93.1250
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.3014 top1= 92.5000
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.2207 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8539 top1= 81.8009


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9021 top1= 49.4992


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2776 top1= 44.4211

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.2909 top1= 93.4375
[E10B10 |   4224/60000 (  7%) ] Loss: 0.2978 top1= 93.4375
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.2175 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8549 top1= 81.9311


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8908 top1= 49.4892


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2393 top1= 44.4311

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.2895 top1= 93.1250
[E11B10 |   4224/60000 (  7%) ] Loss: 0.2931 top1= 93.4375
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.2163 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8588 top1= 81.7708


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8787 top1= 49.4892


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2341 top1= 44.3409

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.2920 top1= 92.8125
[E12B10 |   4224/60000 (  7%) ] Loss: 0.2950 top1= 93.7500
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.2166 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8590 top1= 81.9111


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8700 top1= 49.4892


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2202 top1= 44.1807

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.2946 top1= 92.1875
[E13B10 |   4224/60000 (  7%) ] Loss: 0.2914 top1= 92.8125
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.2165 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8627 top1= 81.8610


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8549 top1= 49.4591


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2283 top1= 44.1406

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.2955 top1= 92.5000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.2929 top1= 92.5000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.2172 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8646 top1= 81.7608


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8473 top1= 49.4491


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2338 top1= 44.1206

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.2969 top1= 92.1875
[E15B10 |   4224/60000 (  7%) ] Loss: 0.2896 top1= 92.8125
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.2179 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8654 top1= 81.6506


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8411 top1= 49.4491


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2165 top1= 44.2308

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.2979 top1= 92.1875
[E16B10 |   4224/60000 (  7%) ] Loss: 0.2896 top1= 92.8125
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.2174 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8671 top1= 81.6807


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8321 top1= 49.4491


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2186 top1= 44.2608

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.2976 top1= 91.8750
[E17B10 |   4224/60000 (  7%) ] Loss: 0.2876 top1= 92.5000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.2145 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8655 top1= 81.8710


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8295 top1= 49.4291


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2140 top1= 44.3409

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.2981 top1= 91.8750
[E18B10 |   4224/60000 (  7%) ] Loss: 0.2879 top1= 93.4375
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.2122 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8655 top1= 81.8309


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8289 top1= 49.4591


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1951 top1= 44.4411

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.2940 top1= 91.8750
[E19B10 |   4224/60000 (  7%) ] Loss: 0.2906 top1= 93.1250
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.2113 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8662 top1= 81.8209


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8227 top1= 49.4591


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2003 top1= 44.3810

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.2937 top1= 92.1875
[E20B10 |   4224/60000 (  7%) ] Loss: 0.2879 top1= 93.1250
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.2107 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8678 top1= 81.6907


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8159 top1= 49.4792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2091 top1= 44.3309

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.2955 top1= 92.1875
[E21B10 |   4224/60000 (  7%) ] Loss: 0.2830 top1= 93.4375
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.2124 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8669 top1= 81.5605


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8205 top1= 49.4692


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1963 top1= 44.2708

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.2960 top1= 92.1875
[E22B10 |   4224/60000 (  7%) ] Loss: 0.2844 top1= 93.1250
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.2137 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8689 top1= 81.3702


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8090 top1= 49.4792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2022 top1= 44.3610

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.2940 top1= 92.1875
[E23B10 |   4224/60000 (  7%) ] Loss: 0.2844 top1= 93.1250
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.2126 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8678 top1= 81.5104


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8167 top1= 49.4692


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1837 top1= 44.3710

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.2939 top1= 91.8750
[E24B10 |   4224/60000 (  7%) ] Loss: 0.2855 top1= 93.1250
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.2129 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8695 top1= 81.5004


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8074 top1= 49.5092


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1881 top1= 44.4010

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.2937 top1= 92.1875
[E25B10 |   4224/60000 (  7%) ] Loss: 0.2835 top1= 93.1250
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.2135 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8702 top1= 81.1298


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8042 top1= 49.4992


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1890 top1= 44.3910

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.2953 top1= 92.1875
[E26B10 |   4224/60000 (  7%) ] Loss: 0.2837 top1= 93.1250
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.2130 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8715 top1= 81.1398


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7990 top1= 49.5192


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1979 top1= 44.4010

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.2943 top1= 92.1875
[E27B10 |   4224/60000 (  7%) ] Loss: 0.2816 top1= 93.4375
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.2131 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8699 top1= 81.2800


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8050 top1= 49.5092


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1809 top1= 44.4211

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.2936 top1= 92.1875
[E28B10 |   4224/60000 (  7%) ] Loss: 0.2785 top1= 93.4375
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.2120 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8719 top1= 81.2400


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8004 top1= 49.5092


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1859 top1= 44.4611

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.2917 top1= 92.5000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.2761 top1= 93.4375
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.2113 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8698 top1= 81.4603


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8045 top1= 49.4992


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1699 top1= 44.4912

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.2903 top1= 92.5000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.2750 top1= 93.4375
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.2112 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8715 top1= 81.4103


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7990 top1= 49.4992


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1755 top1= 44.5012

