
=== 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 0x7fc47112d9d0>

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: 1.5880 top1= 50.0000
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.7932 top1= 80.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0089 top1= 81.0697


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8257 top1= 48.3574


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0845 top1= 42.4579

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.4319 top1= 90.6250
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3909 top1= 90.6250
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.3067 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9287 top1= 81.9311


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1251 top1= 49.1787


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4331 top1= 44.3510

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.3543 top1= 92.1875
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.3587 top1= 91.5625
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.2794 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9241 top1= 81.2300


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0647 top1= 49.2188


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3340 top1= 44.5913

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.3244 top1= 92.5000
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.3402 top1= 92.8125
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.2716 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9327 top1= 81.0397


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0390 top1= 49.3389


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2789 top1= 44.7216

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.3143 top1= 92.5000
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.3335 top1= 92.8125
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.2685 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9398 top1= 81.0096


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0125 top1= 49.3389


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2474 top1= 44.7516

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.3077 top1= 92.5000
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.3277 top1= 92.8125
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.2662 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9469 top1= 80.9796


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9953 top1= 49.3490


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2223 top1= 44.7616

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.3038 top1= 92.8125
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.3240 top1= 93.1250
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.2638 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9534 top1= 80.7091


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9814 top1= 49.3490


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2081 top1= 44.7716

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.2997 top1= 93.4375
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.3218 top1= 93.4375
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.2611 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9573 top1= 80.8193


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9696 top1= 49.3590


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1943 top1= 44.7917

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.2969 top1= 93.1250
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.3199 top1= 93.4375
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.2581 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9607 top1= 80.6591


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9589 top1= 49.3890


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1794 top1= 44.7716

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.2954 top1= 93.1250
[E10B10 |   4224/60000 (  7%) ] Loss: 0.3186 top1= 93.7500
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.2558 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9645 top1= 80.6490


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9530 top1= 49.3790


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1669 top1= 44.7316

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.2938 top1= 93.1250
[E11B10 |   4224/60000 (  7%) ] Loss: 0.3182 top1= 93.7500
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.2553 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9670 top1= 80.5689


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9427 top1= 49.4191


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1579 top1= 44.7616

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.2927 top1= 93.1250
[E12B10 |   4224/60000 (  7%) ] Loss: 0.3160 top1= 93.7500
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.2529 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9687 top1= 80.4888


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9369 top1= 49.4191


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1493 top1= 44.7516

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.2913 top1= 93.1250
[E13B10 |   4224/60000 (  7%) ] Loss: 0.3153 top1= 93.7500
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.2511 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9699 top1= 80.4888


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9326 top1= 49.4191


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1409 top1= 44.7015

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.2905 top1= 92.8125
[E14B10 |   4224/60000 (  7%) ] Loss: 0.3136 top1= 93.7500
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.2502 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9713 top1= 80.4587


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9273 top1= 49.4291


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1349 top1= 44.7015

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.2893 top1= 92.8125
[E15B10 |   4224/60000 (  7%) ] Loss: 0.3127 top1= 93.4375
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.2506 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9731 top1= 80.5088


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9216 top1= 49.4491


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1331 top1= 44.7416

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.2884 top1= 93.1250
[E16B10 |   4224/60000 (  7%) ] Loss: 0.3110 top1= 93.4375
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.2498 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9742 top1= 80.5389


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9180 top1= 49.4591


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1278 top1= 44.7115

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.2886 top1= 92.8125
[E17B10 |   4224/60000 (  7%) ] Loss: 0.3098 top1= 93.4375
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.2491 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9756 top1= 80.4988


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9143 top1= 49.4391


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1298 top1= 44.7416

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.2877 top1= 92.8125
[E18B10 |   4224/60000 (  7%) ] Loss: 0.3086 top1= 93.4375
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.2490 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9771 top1= 80.5088


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9094 top1= 49.4591


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1248 top1= 44.8017

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.2869 top1= 92.8125
[E19B10 |   4224/60000 (  7%) ] Loss: 0.3069 top1= 93.1250
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.2490 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9776 top1= 80.6390


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9101 top1= 49.4692


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1237 top1= 44.7416

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.2862 top1= 93.4375
[E20B10 |   4224/60000 (  7%) ] Loss: 0.3063 top1= 93.4375
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.2487 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9788 top1= 80.6891


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9048 top1= 49.4692


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1224 top1= 44.7917

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.2857 top1= 93.4375
[E21B10 |   4224/60000 (  7%) ] Loss: 0.3066 top1= 93.4375
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.2487 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9797 top1= 80.6591


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9057 top1= 49.4892


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1198 top1= 44.7416

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.2852 top1= 93.4375
[E22B10 |   4224/60000 (  7%) ] Loss: 0.3060 top1= 93.4375
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.2481 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9801 top1= 80.6891


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9043 top1= 49.4692


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1147 top1= 44.7716

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.2860 top1= 93.4375
[E23B10 |   4224/60000 (  7%) ] Loss: 0.3059 top1= 93.4375
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.2481 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9809 top1= 80.8193


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9017 top1= 49.4892


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1110 top1= 44.7917

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.2856 top1= 93.1250
[E24B10 |   4224/60000 (  7%) ] Loss: 0.3050 top1= 93.4375
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.2482 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9815 top1= 80.6691


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9015 top1= 49.4591


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1110 top1= 44.7616

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.2855 top1= 93.4375
[E25B10 |   4224/60000 (  7%) ] Loss: 0.3052 top1= 93.4375
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.2482 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9822 top1= 80.7993


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9014 top1= 49.4591


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1081 top1= 44.7817

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.2857 top1= 93.4375
[E26B10 |   4224/60000 (  7%) ] Loss: 0.3051 top1= 93.4375
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.2473 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9824 top1= 80.7792


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9041 top1= 49.4591


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1068 top1= 44.7817

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.2851 top1= 93.1250
[E27B10 |   4224/60000 (  7%) ] Loss: 0.3046 top1= 93.4375
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.2475 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9830 top1= 80.7091


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9036 top1= 49.4591


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1029 top1= 44.7716

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.2860 top1= 92.8125
[E28B10 |   4224/60000 (  7%) ] Loss: 0.3054 top1= 93.4375
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.2467 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9833 top1= 80.7292


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9019 top1= 49.4591


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1028 top1= 44.7516

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.2859 top1= 92.8125
[E29B10 |   4224/60000 (  7%) ] Loss: 0.3039 top1= 93.4375
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.2469 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9834 top1= 80.7692


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9008 top1= 49.4692


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1015 top1= 44.7716

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.2841 top1= 92.8125
[E30B10 |   4224/60000 (  7%) ] Loss: 0.3050 top1= 93.4375
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.2458 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9840 top1= 80.7592


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8998 top1= 49.4391


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0976 top1= 44.7716

