
=== 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.DumbbellVariant object at 0x7f10432e02b0>

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: 1.0389 top1= 62.3438
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3961 top1= 88.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7089 top1= 79.0865


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.7646 top1= 49.2989


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6922 top1= 44.2708

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2815 top1= 90.6250
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1924 top1= 93.7500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1959 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6382 top1= 85.6771


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1766 top1= 49.8397


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2875 top1= 45.8433

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1600 top1= 95.0000
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1103 top1= 96.5625
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1267 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5638 top1= 86.5785


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9964 top1= 50.0300


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1887 top1= 46.1939

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1213 top1= 96.4062
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0807 top1= 97.8125
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0852 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4980 top1= 87.5701


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9379 top1= 50.3005


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0539 top1= 46.3842

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0843 top1= 97.8125
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0619 top1= 98.4375
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0612 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4456 top1= 88.2312


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9123 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0075 top1= 46.4944

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0669 top1= 98.5938
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0454 top1= 98.7500
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0465 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4071 top1= 88.4716


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8153 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8856 top1= 46.6346

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0497 top1= 98.9062
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0342 top1= 99.3750
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0362 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3761 top1= 89.0124


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7634 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7771 top1= 46.8049

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0331 top1= 99.3750
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0238 top1= 99.5312
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0244 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3488 top1= 89.6334


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7216 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5506 top1= 46.8950

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0202 top1= 99.5312
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0195 top1= 99.6875
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0222 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3292 top1= 90.1943


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6389 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2497 top1= 46.9952

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0159 top1= 99.8438
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0156 top1= 99.6875
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0458 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3361 top1= 89.9840


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4087 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8132 top1= 46.4543

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0255 top1= 99.3750
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0313 top1= 99.2188
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0439 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3458 top1= 89.1727


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2015 top1= 50.4307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5907 top1= 46.2640

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0388 top1= 98.5938
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0167 top1= 99.6875
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0161 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3401 top1= 88.5417


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8667 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5743 top1= 47.1254

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0144 top1= 99.8438
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0175 top1= 99.5312
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0117 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3248 top1= 89.1426


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7207 top1= 51.0517


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4921 top1= 47.1354

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0100 top1= 99.8438
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0113 top1=100.0000
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0159 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2979 top1= 90.1743


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6330 top1= 51.5124


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5446 top1= 47.2155

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0091 top1=100.0000
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0117 top1= 99.8438
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0190 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2800 top1= 90.6550


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3890 top1= 51.7628


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3549 top1= 47.4359

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0073 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0057 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0143 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2774 top1= 90.7051


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2655 top1= 52.0232


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1010 top1= 47.8666

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0143 top1= 99.8438
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0063 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0066 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2746 top1= 91.1058


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1730 top1= 52.1034


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9496 top1= 48.4575

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0075 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0080 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0062 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2667 top1= 91.2660


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0151 top1= 53.1150


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8403 top1= 49.3690

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0070 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0119 top1= 99.6875
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0087 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2612 top1= 91.2861


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8438 top1= 53.8762


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8047 top1= 50.0801

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0082 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0106 top1= 99.8438
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0082 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2498 top1= 91.7969


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6347 top1= 54.7877


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7356 top1= 50.8113

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0080 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0063 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0108 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2444 top1= 91.9271


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5939 top1= 55.3486


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6368 top1= 51.7127

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0080 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0055 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0072 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2415 top1= 92.0172


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5052 top1= 55.4087


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5272 top1= 52.4439

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0110 top1= 99.8438
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0062 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0082 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2354 top1= 92.1775


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4124 top1= 55.9896


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4077 top1= 53.4956

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0068 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0068 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0086 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2390 top1= 92.0473


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2316 top1= 57.8926


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3229 top1= 54.4671

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0065 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0064 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0062 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2345 top1= 92.1975


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1264 top1= 58.9944


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2365 top1= 55.5088

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0053 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0059 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0062 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2346 top1= 92.3077


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9949 top1= 59.9659


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1266 top1= 56.8209

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0052 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0057 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0062 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2332 top1= 92.4279


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9096 top1= 61.0176


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0154 top1= 57.9527

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0049 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0053 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0061 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2316 top1= 92.4679


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8164 top1= 62.1494


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9304 top1= 59.0745

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0049 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0050 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0061 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2303 top1= 92.5581


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7817 top1= 62.7204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8527 top1= 60.3165

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0045 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0048 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0057 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2286 top1= 92.6583


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6596 top1= 63.9924


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7736 top1= 61.3281

