
=== 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 0x7f8a8f803490>

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: 1.0342 top1= 62.1875
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3968 top1= 88.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7217 top1= 78.7059


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.8910 top1= 49.3189


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8184 top1= 44.1807

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2862 top1= 90.6250
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1943 top1= 93.9062
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1959 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6688 top1= 85.1062


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3722 top1= 49.7897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4755 top1= 45.8634

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1628 top1= 94.8438
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1110 top1= 96.5625
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1241 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6020 top1= 86.1278


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2741 top1= 50.1402


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5178 top1= 46.1639

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1219 top1= 96.4062
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0818 top1= 97.8125
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0820 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5419 top1= 87.0693


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3556 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4832 top1= 46.3942

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0840 top1= 97.9688
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0625 top1= 98.1250
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0592 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4902 top1= 87.8506


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4313 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5451 top1= 46.5144

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0655 top1= 98.5938
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0470 top1= 98.5938
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0450 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4511 top1= 88.3714


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4833 top1= 50.5108


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5237 top1= 46.7648

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0439 top1= 99.2188
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0303 top1= 99.5312
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0350 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4182 top1= 89.0925


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5665 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4024 top1= 46.9050

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0309 top1= 99.5312
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0238 top1= 99.6875
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0377 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3981 top1= 89.5132


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6586 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2409 top1= 46.7047

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0303 top1= 99.2188
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0250 top1= 99.3750
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0306 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3872 top1= 89.0224


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6177 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9693 top1= 46.9852

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0198 top1= 99.5312
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0188 top1= 99.5312
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0185 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3636 top1= 89.6134


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5108 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1376 top1= 46.8750

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0196 top1= 99.3750
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0120 top1=100.0000
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0126 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3554 top1= 89.5933


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2409 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3512 top1= 46.9752

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0101 top1= 99.8438
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0113 top1=100.0000
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0213 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3483 top1= 89.6434


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9676 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3030 top1= 47.0052

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0091 top1=100.0000
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0097 top1=100.0000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0166 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3496 top1= 89.4932


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7749 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2092 top1= 47.1655

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0157 top1= 99.5312
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0091 top1= 99.8438
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0118 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3293 top1= 90.2344


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4875 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0119 top1= 47.2155

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0058 top1=100.0000
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0095 top1= 99.8438
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0129 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3203 top1= 90.6350


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3297 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8162 top1= 47.0954

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0078 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0053 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0075 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3228 top1= 90.4848


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2564 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6794 top1= 46.8750

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0110 top1= 99.8438
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0047 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0069 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3108 top1= 90.5849


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2642 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6329 top1= 47.1254

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0053 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0081 top1= 99.8438
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0091 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3102 top1= 90.2143


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2016 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5643 top1= 47.1655

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0055 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0036 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0053 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3062 top1= 90.3946


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1393 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3860 top1= 47.1955

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0050 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0047 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0048 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2976 top1= 90.8053


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0617 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4056 top1= 47.1855

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0041 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0032 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0045 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2933 top1= 90.7853


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9730 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3204 top1= 47.1554

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0038 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0036 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0046 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2887 top1= 90.8654


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8802 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1899 top1= 47.1554

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0039 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0037 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0046 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2859 top1= 90.9255


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7874 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0668 top1= 47.1554

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0040 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0037 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0046 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2832 top1= 90.9555


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7061 top1= 50.7812


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9509 top1= 47.1655

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0040 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0038 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0048 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2808 top1= 91.0757


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6189 top1= 50.9415


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8503 top1= 47.1855

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0041 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0039 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0049 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2783 top1= 91.0657


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5565 top1= 51.0016


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7637 top1= 47.2055

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0042 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0040 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0049 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2763 top1= 91.1158


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4835 top1= 51.1418


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6902 top1= 47.2456

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0042 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0040 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0050 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2738 top1= 91.1358


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4188 top1= 51.3121


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6224 top1= 47.3257

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0043 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0040 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0050 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2717 top1= 91.2660


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3645 top1= 51.4623


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5557 top1= 47.4058

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0043 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0041 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0051 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2698 top1= 91.3161


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3015 top1= 51.6126


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5005 top1= 47.5160

