
=== 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 0x7fb34fe599d0>

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: 1.0791 top1= 63.4375
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2712 top1= 91.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7346 top1= 74.4792


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.0215 top1= 48.7780


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6035 top1= 43.1791

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.4214 top1= 89.3750
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3409 top1= 89.0625
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1672 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5742 top1= 85.9575


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9030 top1= 49.8397


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7950 top1= 45.5329

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1378 top1= 96.2500
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1365 top1= 95.0000
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1112 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4596 top1= 87.5501


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5264 top1= 50.9215


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2472 top1= 46.3141

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1205 top1= 95.9375
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0997 top1= 96.2500
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0800 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3870 top1= 88.7320


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1083 top1= 54.0164


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9278 top1= 49.5092

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.1002 top1= 97.5000
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0857 top1= 97.1875
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0609 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3458 top1= 89.4531


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9598 top1= 55.9796


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7827 top1= 51.8530

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0777 top1= 97.8125
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0661 top1= 97.8125
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0481 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3229 top1= 89.8237


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8693 top1= 57.4018


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6376 top1= 54.3870

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0585 top1= 98.7500
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0518 top1= 98.7500
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0416 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3065 top1= 90.1743


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8319 top1= 58.3934


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5535 top1= 56.3502

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0453 top1= 98.7500
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0439 top1= 99.0625
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0421 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3037 top1= 90.1643


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9266 top1= 58.4635


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4059 top1= 59.1647

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0384 top1= 99.0625
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0411 top1= 99.3750
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0483 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3063 top1= 89.9840


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9099 top1= 59.4551


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4171 top1= 59.5052

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0381 top1= 99.6875
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0330 top1= 99.3750
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0396 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3087 top1= 90.0140


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8255 top1= 60.5869


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3677 top1= 61.1078

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0330 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0343 top1= 99.6875
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0416 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3000 top1= 90.1142


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6621 top1= 61.3782


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7459 top1= 56.0998

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0317 top1= 99.0625
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0414 top1= 98.7500
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0279 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2919 top1= 90.6250


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4731 top1= 63.3213


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6817 top1= 56.0697

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0394 top1= 99.3750
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0382 top1= 98.7500
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0244 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2793 top1= 90.8954


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3696 top1= 64.9439


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3360 top1= 62.2696

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0245 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0296 top1= 99.6875
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0160 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2724 top1= 91.2861


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3315 top1= 65.3245


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2330 top1= 63.6018

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0179 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0202 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0160 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2736 top1= 91.0657


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1993 top1= 66.8369


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3060 top1= 62.0793

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0189 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0165 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0182 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2661 top1= 91.6166


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1551 top1= 67.3478


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2650 top1= 63.6819

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0172 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0172 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0171 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2651 top1= 91.6266


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1500 top1= 67.6482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1340 top1= 66.1058

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0150 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0207 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0148 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2700 top1= 91.3061


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1534 top1= 67.2676


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0374 top1= 68.1390

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0138 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0263 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0188 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2738 top1= 91.3762


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1396 top1= 67.1875


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1677 top1= 65.2444

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0156 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0206 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0175 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2805 top1= 91.1759


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1790 top1= 66.7167


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2664 top1= 63.8221

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0199 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0192 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0146 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2719 top1= 91.5064


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1704 top1= 67.2676


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2714 top1= 62.7204

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0171 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0243 top1= 99.6875
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0158 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2764 top1= 91.3161


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2154 top1= 66.3862


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1435 top1= 66.0857

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0154 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0178 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0158 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2768 top1= 91.2760


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1875 top1= 66.0256


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2073 top1= 64.5232

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0140 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0215 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0147 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2739 top1= 91.4764


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1834 top1= 65.9856


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2865 top1= 62.3498

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0140 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0213 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0151 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2750 top1= 91.2260


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1755 top1= 65.6350


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2946 top1= 62.7103

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0157 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0204 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0152 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2775 top1= 91.1959


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1870 top1= 65.2444


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2679 top1= 63.1110

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0169 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0216 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0156 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2808 top1= 91.1659


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1774 top1= 65.1843


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3439 top1= 61.3381

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0185 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0205 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0170 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2830 top1= 91.2260


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2082 top1= 64.0825


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3532 top1= 61.3782

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0174 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0217 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0164 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2858 top1= 91.1659


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2398 top1= 63.7220


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4071 top1= 60.6971

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0207 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0274 top1= 99.6875
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0175 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2850 top1= 91.1659


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2798 top1= 63.2812


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4611 top1= 59.2849

