
=== 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 0x7fc6ca8e27c0>

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: 1.0398 top1= 64.3750
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2670 top1= 91.2500
[E 1B30 |  11904/60000 ( 20%) ] Loss: 0.4652 top1= 85.6250
[E 1B40 |  15744/60000 ( 26%) ] Loss: 0.2627 top1= 91.2500
[E 1B50 |  19584/60000 ( 33%) ] Loss: 0.1715 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6556 top1= 84.7556


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5753 top1= 49.7696


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0048 top1= 45.3926

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.1845 top1= 94.6875
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.1690 top1= 94.3750
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1320 top1= 95.6250
[E 2B30 |  11904/60000 ( 20%) ] Loss: 0.1767 top1= 94.6875
[E 2B40 |  15744/60000 ( 26%) ] Loss: 0.1608 top1= 94.6875
[E 2B50 |  19584/60000 ( 33%) ] Loss: 0.1058 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4849 top1= 87.8506


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8042 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4860 top1= 46.1038

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1257 top1= 96.2500
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1237 top1= 95.9375
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1043 top1= 97.1875
[E 3B30 |  11904/60000 ( 20%) ] Loss: 0.1558 top1= 95.6250
[E 3B40 |  15744/60000 ( 26%) ] Loss: 0.1166 top1= 96.5625
[E 3B50 |  19584/60000 ( 33%) ] Loss: 0.0853 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3893 top1= 89.3029


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4109 top1= 52.4139


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2207 top1= 47.7464

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0942 top1= 97.5000
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.1042 top1= 96.2500
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0854 top1= 97.5000
[E 4B30 |  11904/60000 ( 20%) ] Loss: 0.1364 top1= 96.2500
[E 4B40 |  15744/60000 ( 26%) ] Loss: 0.0985 top1= 97.1875
[E 4B50 |  19584/60000 ( 33%) ] Loss: 0.0743 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3432 top1= 89.9639


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2268 top1= 54.1066


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0424 top1= 49.2188

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0722 top1= 98.1250
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0891 top1= 96.8750
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0754 top1= 97.8125
[E 5B30 |  11904/60000 ( 20%) ] Loss: 0.1201 top1= 97.1875
[E 5B40 |  15744/60000 ( 26%) ] Loss: 0.0830 top1= 97.8125
[E 5B50 |  19584/60000 ( 33%) ] Loss: 0.0675 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3211 top1= 90.4647


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1254 top1= 54.9780


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9825 top1= 50.2404

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0585 top1= 98.4375
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0766 top1= 97.5000
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0655 top1= 98.1250
[E 6B30 |  11904/60000 ( 20%) ] Loss: 0.1084 top1= 96.8750
[E 6B40 |  15744/60000 ( 26%) ] Loss: 0.0766 top1= 98.4375
[E 6B50 |  19584/60000 ( 33%) ] Loss: 0.0625 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3098 top1= 90.6651


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0374 top1= 55.9495


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9627 top1= 50.9916

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0513 top1= 98.7500
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0657 top1= 98.1250
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0559 top1= 98.7500
[E 7B30 |  11904/60000 ( 20%) ] Loss: 0.0931 top1= 97.8125
[E 7B40 |  15744/60000 ( 26%) ] Loss: 0.0733 top1= 98.1250
[E 7B50 |  19584/60000 ( 33%) ] Loss: 0.0625 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3041 top1= 90.7752


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0129 top1= 56.1899


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8682 top1= 51.6727

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0503 top1= 99.0625
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0584 top1= 98.4375
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0463 top1= 99.6875
[E 8B30 |  11904/60000 ( 20%) ] Loss: 0.0795 top1= 98.4375
[E 8B40 |  15744/60000 ( 26%) ] Loss: 0.0698 top1= 98.4375
[E 8B50 |  19584/60000 ( 33%) ] Loss: 0.0594 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3032 top1= 90.8854


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0161 top1= 56.1098


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8735 top1= 51.9431

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0484 top1= 98.7500
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0563 top1= 99.0625
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0497 top1= 99.0625
[E 9B30 |  11904/60000 ( 20%) ] Loss: 0.0731 top1= 98.4375
[E 9B40 |  15744/60000 ( 26%) ] Loss: 0.0654 top1= 98.4375
[E 9B50 |  19584/60000 ( 33%) ] Loss: 0.0582 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3030 top1= 90.9756


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9681 top1= 55.9996


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8490 top1= 51.9030

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0412 top1= 99.3750
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0576 top1= 98.7500
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0467 top1= 99.6875
[E10B30 |  11904/60000 ( 20%) ] Loss: 0.0810 top1= 98.1250
[E10B40 |  15744/60000 ( 26%) ] Loss: 0.0673 top1= 98.1250
[E10B50 |  19584/60000 ( 33%) ] Loss: 0.0567 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3039 top1= 91.0056


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9774 top1= 55.8193


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8258 top1= 52.4439

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0394 top1= 99.3750
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0511 top1= 99.3750
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0513 top1= 99.0625
[E11B30 |  11904/60000 ( 20%) ] Loss: 0.0853 top1= 97.5000
[E11B40 |  15744/60000 ( 26%) ] Loss: 0.0673 top1= 98.4375
[E11B50 |  19584/60000 ( 33%) ] Loss: 0.0539 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3109 top1= 90.7853


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0356 top1= 54.9679


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9157 top1= 51.7829

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0378 top1= 99.3750
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0567 top1= 99.0625
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0553 top1= 98.1250
[E12B30 |  11904/60000 ( 20%) ] Loss: 0.0898 top1= 97.5000
[E12B40 |  15744/60000 ( 26%) ] Loss: 0.0731 top1= 98.1250
[E12B50 |  19584/60000 ( 33%) ] Loss: 0.0552 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3158 top1= 90.9655


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0451 top1= 54.7175


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9177 top1= 51.5925

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0398 top1= 99.0625
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0691 top1= 98.4375
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0648 top1= 98.4375
[E13B30 |  11904/60000 ( 20%) ] Loss: 0.1040 top1= 97.1875
[E13B40 |  15744/60000 ( 26%) ] Loss: 0.0760 top1= 98.4375
[E13B50 |  19584/60000 ( 33%) ] Loss: 0.0536 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3231 top1= 90.9856


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0315 top1= 54.5473


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9247 top1= 50.8514

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0417 top1= 99.0625
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0763 top1= 98.1250
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0819 top1= 98.4375
[E14B30 |  11904/60000 ( 20%) ] Loss: 0.1156 top1= 96.5625
[E14B40 |  15744/60000 ( 26%) ] Loss: 0.0799 top1= 97.8125
[E14B50 |  19584/60000 ( 33%) ] Loss: 0.0577 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3352 top1= 90.5048


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0594 top1= 54.0765


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9792 top1= 50.6711

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0473 top1= 99.0625
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0767 top1= 97.5000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0850 top1= 97.5000
[E15B30 |  11904/60000 ( 20%) ] Loss: 0.1434 top1= 93.7500
[E15B40 |  15744/60000 ( 26%) ] Loss: 0.0841 top1= 98.1250
[E15B50 |  19584/60000 ( 33%) ] Loss: 0.0672 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3437 top1= 90.0942


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0434 top1= 54.4071


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0844 top1= 48.8882

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0459 top1= 99.0625
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0838 top1= 96.8750
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0639 top1= 98.4375
[E16B30 |  11904/60000 ( 20%) ] Loss: 0.1020 top1= 96.5625
[E16B40 |  15744/60000 ( 26%) ] Loss: 0.0916 top1= 98.1250
[E16B50 |  19584/60000 ( 33%) ] Loss: 0.0823 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3506 top1= 89.6735


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0565 top1= 53.9663


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9670 top1= 49.8798

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0507 top1= 98.1250
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0911 top1= 95.9375
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0833 top1= 98.7500
[E17B30 |  11904/60000 ( 20%) ] Loss: 0.1053 top1= 96.8750
[E17B40 |  15744/60000 ( 26%) ] Loss: 0.1065 top1= 95.6250
[E17B50 |  19584/60000 ( 33%) ] Loss: 0.0689 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3684 top1= 88.5216


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0676 top1= 53.8462


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1147 top1= 47.8766

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0597 top1= 98.1250
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0708 top1= 98.7500
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0579 top1= 98.7500
[E18B30 |  11904/60000 ( 20%) ] Loss: 0.1061 top1= 96.5625
[E18B40 |  15744/60000 ( 26%) ] Loss: 0.0926 top1= 98.4375
[E18B50 |  19584/60000 ( 33%) ] Loss: 0.0681 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3595 top1= 89.2328


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0612 top1= 53.9964


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0658 top1= 49.2788

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0542 top1= 99.0625
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0694 top1= 97.5000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0703 top1= 98.7500
[E19B30 |  11904/60000 ( 20%) ] Loss: 0.1040 top1= 96.8750
[E19B40 |  15744/60000 ( 26%) ] Loss: 0.0960 top1= 96.8750
[E19B50 |  19584/60000 ( 33%) ] Loss: 0.0658 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3635 top1= 89.4732


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0388 top1= 53.5857


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0280 top1= 48.9383

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0577 top1= 98.4375
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0676 top1= 97.8125
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0726 top1= 98.4375
[E20B30 |  11904/60000 ( 20%) ] Loss: 0.1032 top1= 96.5625
[E20B40 |  15744/60000 ( 26%) ] Loss: 0.0833 top1= 98.1250
[E20B50 |  19584/60000 ( 33%) ] Loss: 0.0706 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3616 top1= 89.5032


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0318 top1= 53.6759


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9886 top1= 49.3089

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0556 top1= 98.4375
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0809 top1= 97.5000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0627 top1= 98.4375
[E21B30 |  11904/60000 ( 20%) ] Loss: 0.1132 top1= 96.2500
[E21B40 |  15744/60000 ( 26%) ] Loss: 0.0956 top1= 97.8125
[E21B50 |  19584/60000 ( 33%) ] Loss: 0.0703 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3611 top1= 90.0441


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1050 top1= 53.1150


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9416 top1= 49.3289

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0493 top1= 98.7500
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0651 top1= 98.1250
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0846 top1= 98.4375
[E22B30 |  11904/60000 ( 20%) ] Loss: 0.1110 top1= 96.5625
[E22B40 |  15744/60000 ( 26%) ] Loss: 0.0832 top1= 97.8125
[E22B50 |  19584/60000 ( 33%) ] Loss: 0.0720 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3730 top1= 89.5833


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0335 top1= 53.6058


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0263 top1= 48.7580

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0574 top1= 97.8125
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0767 top1= 97.1875
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0661 top1= 98.7500
[E23B30 |  11904/60000 ( 20%) ] Loss: 0.1569 top1= 94.3750
[E23B40 |  15744/60000 ( 26%) ] Loss: 0.0938 top1= 97.8125
[E23B50 |  19584/60000 ( 33%) ] Loss: 0.0722 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3710 top1= 89.3229


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0582 top1= 53.2452


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0558 top1= 49.1587

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0518 top1= 97.8125
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0715 top1= 97.8125
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0866 top1= 97.5000
[E24B30 |  11904/60000 ( 20%) ] Loss: 0.1208 top1= 95.6250
[E24B40 |  15744/60000 ( 26%) ] Loss: 0.0987 top1= 97.5000
[E24B50 |  19584/60000 ( 33%) ] Loss: 0.0771 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3771 top1= 89.2528


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0575 top1= 53.1350


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0516 top1= 48.5877

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0528 top1= 98.7500
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0787 top1= 97.1875
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0992 top1= 98.1250
[E25B30 |  11904/60000 ( 20%) ] Loss: 0.1347 top1= 95.0000
[E25B40 |  15744/60000 ( 26%) ] Loss: 0.1006 top1= 96.5625
[E25B50 |  19584/60000 ( 33%) ] Loss: 0.0898 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3865 top1= 89.5333


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2545 top1= 51.5024


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0482 top1= 47.9367

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0681 top1= 98.4375
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0774 top1= 97.1875
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.1142 top1= 96.8750
[E26B30 |  11904/60000 ( 20%) ] Loss: 0.1428 top1= 95.0000
[E26B40 |  15744/60000 ( 26%) ] Loss: 0.1122 top1= 96.5625
[E26B50 |  19584/60000 ( 33%) ] Loss: 0.0691 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3801 top1= 89.5433


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1914 top1= 52.2937


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0230 top1= 48.1671

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0685 top1= 97.8125
[E27B10 |   4224/60000 (  7%) ] Loss: 0.1134 top1= 95.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.1191 top1= 96.5625
[E27B30 |  11904/60000 ( 20%) ] Loss: 0.1570 top1= 95.3125
[E27B40 |  15744/60000 ( 26%) ] Loss: 0.1058 top1= 97.5000
[E27B50 |  19584/60000 ( 33%) ] Loss: 0.0743 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3850 top1= 88.9523


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1832 top1= 52.1635


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0770 top1= 48.0268

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0690 top1= 97.5000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.1189 top1= 95.6250
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0897 top1= 97.1875
[E28B30 |  11904/60000 ( 20%) ] Loss: 0.1455 top1= 94.6875
[E28B40 |  15744/60000 ( 26%) ] Loss: 0.0999 top1= 97.1875
[E28B50 |  19584/60000 ( 33%) ] Loss: 0.0776 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3726 top1= 89.0024


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1252 top1= 52.6943


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1695 top1= 47.4760

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0593 top1= 97.8125
[E29B10 |   4224/60000 (  7%) ] Loss: 0.1319 top1= 95.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0903 top1= 98.4375
[E29B30 |  11904/60000 ( 20%) ] Loss: 0.1329 top1= 95.6250
[E29B40 |  15744/60000 ( 26%) ] Loss: 0.1017 top1= 97.1875
[E29B50 |  19584/60000 ( 33%) ] Loss: 0.0722 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3848 top1= 88.1210


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0613 top1= 53.2352


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3628 top1= 46.8349

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0670 top1= 98.1250
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0991 top1= 95.6250
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0647 top1= 98.4375
[E30B30 |  11904/60000 ( 20%) ] Loss: 0.1287 top1= 96.5625
[E30B40 |  15744/60000 ( 26%) ] Loss: 0.0937 top1= 98.1250
[E30B50 |  19584/60000 ( 33%) ] Loss: 0.0646 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3798 top1= 88.7620


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1056 top1= 53.1550


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1143 top1= 47.5361

