
=== 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 0x7f6bdc96d490>

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: 1.0388 top1= 62.3438
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3922 top1= 88.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7315 top1= 78.1851


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.7988 top1= 49.3089


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6010 top1= 44.2208

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2834 top1= 90.4688
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1932 top1= 93.9062
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1949 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6612 top1= 83.9844


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2962 top1= 49.8397


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2845 top1= 45.7933

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1627 top1= 95.0000
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1105 top1= 96.5625
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1254 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5986 top1= 84.5152


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1097 top1= 50.0501


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1791 top1= 46.2540

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1204 top1= 96.2500
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0814 top1= 97.9688
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0837 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5457 top1= 84.8758


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1549 top1= 50.2804


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0164 top1= 46.4042

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0840 top1= 97.9688
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0616 top1= 98.2812
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0608 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5003 top1= 85.3065


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2038 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9624 top1= 46.4744

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0659 top1= 98.7500
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0454 top1= 98.9062
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0459 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4660 top1= 85.9075


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1763 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8618 top1= 46.5946

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0497 top1= 98.9062
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0330 top1= 99.5312
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0368 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4386 top1= 86.2780


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1961 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7088 top1= 46.7748

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0338 top1= 99.3750
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0239 top1= 99.5312
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0259 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4128 top1= 86.7087


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2142 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5473 top1= 46.8550

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0226 top1= 99.5312
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0190 top1= 99.6875
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0226 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3930 top1= 87.0092


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1563 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2770 top1= 46.9251

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0158 top1= 99.6875
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0143 top1= 99.8438
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0234 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3725 top1= 87.3598


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0445 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9800 top1= 47.0252

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0161 top1= 99.8438
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0147 top1= 99.8438
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0472 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3696 top1= 88.0008


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8150 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6527 top1= 46.4944

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0341 top1= 99.0625
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0300 top1= 99.0625
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0456 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3336 top1= 89.5032


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6105 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3276 top1= 46.6847

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0273 top1= 99.5312
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0191 top1= 99.6875
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0192 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3028 top1= 90.3446


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3513 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3201 top1= 47.2456

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0117 top1= 99.8438
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0126 top1= 99.6875
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0243 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3150 top1= 89.4832


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1168 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2994 top1= 47.2356

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0142 top1= 99.6875
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0091 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0164 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2926 top1= 90.5349


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8062 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3435 top1= 47.4760

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0195 top1= 99.5312
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0090 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0114 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2821 top1= 90.9255


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6343 top1= 50.7812


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0561 top1= 48.1971

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0051 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0130 top1= 99.6875
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0130 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2793 top1= 90.9054


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5143 top1= 51.1619


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8512 top1= 48.8682

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0054 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0084 top1= 99.8438
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0114 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2786 top1= 90.9054


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2723 top1= 51.4924


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7177 top1= 49.5192

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0060 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0058 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0071 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2736 top1= 91.2059


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1304 top1= 51.7127


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6331 top1= 49.7897

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0074 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0051 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0070 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2647 top1= 91.4263


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9875 top1= 52.1735


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5463 top1= 50.6911

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0059 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0057 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0064 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2564 top1= 91.6166


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8795 top1= 52.6342


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5225 top1= 51.5024

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0055 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0050 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0079 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2499 top1= 91.8369


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7834 top1= 53.3554


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4831 top1= 52.1234

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0060 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0054 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0071 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2449 top1= 91.9271


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6889 top1= 53.9263


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4741 top1= 52.7344

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0070 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0062 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0068 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2432 top1= 91.9371


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6029 top1= 54.6875


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3930 top1= 53.8662

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0071 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0053 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0075 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2403 top1= 92.0773


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5210 top1= 55.4287


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3119 top1= 54.5373

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0059 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0057 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0084 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2371 top1= 92.1474


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4423 top1= 56.2200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3194 top1= 54.8077

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0068 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0054 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0063 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2371 top1= 92.0573


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3663 top1= 56.8209


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2242 top1= 56.1699

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0083 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0060 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0062 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2364 top1= 92.2175


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2976 top1= 57.7424


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1474 top1= 56.8510

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0071 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0054 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0063 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2346 top1= 92.2977


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2168 top1= 58.4235


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0551 top1= 57.7624

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0058 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0053 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0071 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2306 top1= 92.5080


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1533 top1= 59.1346


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0797 top1= 57.7925

