
=== 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 SGDMWorker(index=10, momentum=0.9)
=> Add worker SGDMWorker(index=11, momentum=0.9)
=> Add worker SGDMWorker(index=12, momentum=0.9)
=> Add worker SGDMWorker(index=13, momentum=0.9)
=> Add worker SGDMWorker(index=14, momentum=0.9)
=> Add worker SGDMWorker(index=15, momentum=0.9)
=> Add worker SGDMWorker(index=16, momentum=0.9)
=> Add worker SGDMWorker(index=17, momentum=0.9)
=> Add worker SGDMWorker(index=18, momentum=0.9)
=> Add worker SGDMWorker(index=19, momentum=0.9)
=> Add worker BitFlippingWorker
=> Add worker BitFlippingWorker

=== Start adding graph ===
<codes.graph_utils.Dumbbell object at 0x7faafd7f7490>

Train epoch 1
[E 1B0  |    704/60000 (  1%) ] Loss: 2.3066 top1=  9.2188

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([3, 2, 2, 4, 3], device='cuda:0')
Worker 1 has targets: tensor([1, 0, 0, 4, 0], device='cuda:0')
Worker 2 has targets: tensor([4, 1, 0, 1, 0], device='cuda:0')
Worker 3 has targets: tensor([0, 1, 4, 1, 3], device='cuda:0')
Worker 4 has targets: tensor([0, 4, 1, 2, 4], device='cuda:0')
Worker 5 has targets: tensor([2, 2, 4, 4, 4], device='cuda:0')
Worker 6 has targets: tensor([1, 1, 4, 4, 3], device='cuda:0')
Worker 7 has targets: tensor([4, 4, 1, 3, 0], device='cuda:0')
Worker 8 has targets: tensor([1, 3, 1, 0, 4], device='cuda:0')
Worker 9 has targets: tensor([1, 3, 3, 3, 1], device='cuda:0')
Worker 10 has targets: tensor([8, 9, 7, 7, 9], device='cuda:0')
Worker 11 has targets: tensor([8, 9, 6, 6, 7], device='cuda:0')
Worker 12 has targets: tensor([8, 6, 5, 7, 8], device='cuda:0')
Worker 13 has targets: tensor([7, 6, 9, 6, 5], device='cuda:0')
Worker 14 has targets: tensor([8, 5, 8, 6, 7], device='cuda:0')
Worker 15 has targets: tensor([9, 5, 6, 8, 6], device='cuda:0')
Worker 16 has targets: tensor([7, 7, 8, 5, 8], device='cuda:0')
Worker 17 has targets: tensor([9, 7, 5, 6, 6], device='cuda:0')
Worker 18 has targets: tensor([7, 7, 7, 6, 6], device='cuda:0')
Worker 19 has targets: tensor([5, 7, 9, 9, 7], device='cuda:0')
Worker 20 has targets: tensor([3, 2, 2, 4, 3], device='cuda:0')
Worker 21 has targets: tensor([8, 9, 7, 7, 9], device='cuda:0')


[E 1B10 |   7744/60000 ( 13%) ] Loss: 1.4743 top1= 48.4375
[E 1B20 |  14784/60000 ( 25%) ] Loss: 1.0545 top1= 64.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4676 top1= 77.1935


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6859 top1= 47.9467


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6192 top1= 43.1691

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.7068 top1= 76.5625
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.5523 top1= 81.5625
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.4674 top1= 84.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1109 top1= 80.6390


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3214 top1= 49.3089


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0013 top1= 43.9103

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.3913 top1= 87.0312
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.2789 top1= 91.8750
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.3138 top1= 90.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9675 top1= 81.5204


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7107 top1= 49.5893


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4148 top1= 44.7817

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.2576 top1= 92.3438
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.2048 top1= 94.3750
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.2573 top1= 91.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8777 top1= 81.8109


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1000 top1= 49.7095


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7970 top1= 45.1022

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.2420 top1= 92.0312
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.2151 top1= 93.2812
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.2628 top1= 91.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8717 top1= 81.8910


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0544 top1= 49.8598


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5003 top1= 45.3826

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1958 top1= 94.0625
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1545 top1= 95.4688
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1865 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8211 top1= 82.7524


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1555 top1= 50.0300


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8580 top1= 45.6831

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1555 top1= 95.7812
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1402 top1= 95.7812
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1810 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7931 top1= 83.3233


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2318 top1= 50.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9771 top1= 45.8634

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1522 top1= 95.3125
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1199 top1= 96.8750
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1384 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7711 top1= 83.6238


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3150 top1= 50.1803


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0655 top1= 46.0437

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1381 top1= 95.9375
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1088 top1= 97.0312
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1367 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7501 top1= 84.3349


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3546 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1643 top1= 46.2340

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1246 top1= 97.0312
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0979 top1= 97.1875
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1235 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7222 top1= 84.6554


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5267 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2971 top1= 46.3442

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1133 top1= 96.7188
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0941 top1= 97.0312
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1245 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7171 top1= 85.1763


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4834 top1= 50.3205


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2317 top1= 46.4243

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1166 top1= 97.0312
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0856 top1= 97.8125
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0996 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7022 top1= 85.2464


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5321 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2859 top1= 46.5244

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1074 top1= 96.5625
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0809 top1= 97.6562
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0990 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6818 top1= 85.6070


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6445 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3961 top1= 46.5645

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0991 top1= 97.3438
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0775 top1= 97.8125
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0986 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7050 top1= 85.7572


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6287 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9696 top1= 46.4844

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.1973 top1= 93.1250
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0800 top1= 97.6562
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0905 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6991 top1= 85.1262


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6307 top1= 50.4307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9807 top1= 46.6546

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0859 top1= 97.9688
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0666 top1= 97.8125
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0841 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6698 top1= 85.1562


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7725 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2480 top1= 46.7648

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0760 top1= 97.6562
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0571 top1= 98.1250
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0904 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6641 top1= 85.8173


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6719 top1= 50.5108


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3039 top1= 46.8650

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0801 top1= 97.8125
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0529 top1= 98.2812
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0707 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6607 top1= 85.0060


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7261 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3858 top1= 46.8650

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0733 top1= 98.1250
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0473 top1= 98.5938
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0648 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6361 top1= 85.5869


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8765 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5087 top1= 46.9251

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0680 top1= 98.2812
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0514 top1= 98.2812
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0617 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6319 top1= 86.0276


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8682 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5212 top1= 47.0052

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0674 top1= 98.5938
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0417 top1= 98.2812
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0626 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6333 top1= 85.2464


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8313 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5849 top1= 47.0353

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0645 top1= 98.2812
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0401 top1= 98.7500
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0563 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6128 top1= 85.7171


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9970 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7016 top1= 47.0653

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0601 top1= 98.2812
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0344 top1= 99.0625
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0657 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6093 top1= 86.1378


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9658 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7209 top1= 47.1154

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0583 top1= 98.4375
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0329 top1= 99.3750
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0546 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6132 top1= 85.3866


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9289 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7025 top1= 47.1454

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0545 top1= 98.7500
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0295 top1= 99.5312
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0474 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5953 top1= 85.7272


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0753 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8696 top1= 47.1354

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0446 top1= 98.7500
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0343 top1= 99.0625
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0420 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5904 top1= 86.1579


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0564 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8689 top1= 47.1655

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0429 top1= 98.9062
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0274 top1= 99.8438
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0496 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5933 top1= 85.6671


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0496 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8600 top1= 47.2155

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0436 top1= 99.0625
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0231 top1= 99.8438
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0395 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5756 top1= 85.9976


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1516 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9771 top1= 47.2055

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0388 top1= 98.7500
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0244 top1= 99.5312
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0535 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5760 top1= 86.0877


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1181 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0068 top1= 47.2155

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0480 top1= 98.9062
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0197 top1= 99.6875
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0397 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5779 top1= 85.7973


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1414 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0104 top1= 47.2957

