
=== 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 0x7f492f7807c0>

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: 1.3633 top1= 60.6250
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.6013 top1= 85.6250
[E 1B30 |  11904/60000 ( 20%) ] Loss: 0.4513 top1= 88.4375
[E 1B40 |  15744/60000 ( 26%) ] Loss: 0.3926 top1= 89.6875
[E 1B50 |  19584/60000 ( 33%) ] Loss: 0.3227 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0199 top1= 82.2115


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5749 top1= 49.3389


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6654 top1= 43.3293

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3211 top1= 92.5000
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3746 top1= 90.0000
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.2733 top1= 94.6875
[E 2B30 |  11904/60000 ( 20%) ] Loss: 0.4240 top1= 88.1250
[E 2B40 |  15744/60000 ( 26%) ] Loss: 0.3808 top1= 89.0625
[E 2B50 |  19584/60000 ( 33%) ] Loss: 0.2933 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0096 top1= 79.3470


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3860 top1= 49.0485


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5552 top1= 42.6683

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.3065 top1= 92.5000
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.3733 top1= 89.6875
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.2589 top1= 94.6875
[E 3B30 |  11904/60000 ( 20%) ] Loss: 0.3981 top1= 89.0625
[E 3B40 |  15744/60000 ( 26%) ] Loss: 0.3692 top1= 89.6875
[E 3B50 |  19584/60000 ( 33%) ] Loss: 0.2863 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0201 top1= 78.4956


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3163 top1= 48.9583


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4830 top1= 42.5180

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.3001 top1= 92.8125
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.3614 top1= 90.6250
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.2570 top1= 94.6875
[E 4B30 |  11904/60000 ( 20%) ] Loss: 0.3812 top1= 89.0625
[E 4B40 |  15744/60000 ( 26%) ] Loss: 0.3593 top1= 89.0625
[E 4B50 |  19584/60000 ( 33%) ] Loss: 0.2830 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0330 top1= 77.8446


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2651 top1= 48.9884


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4317 top1= 42.5180

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.2959 top1= 91.8750
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.3575 top1= 90.9375
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.2558 top1= 95.0000
[E 5B30 |  11904/60000 ( 20%) ] Loss: 0.3699 top1= 89.6875
[E 5B40 |  15744/60000 ( 26%) ] Loss: 0.3552 top1= 89.0625
[E 5B50 |  19584/60000 ( 33%) ] Loss: 0.2774 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0386 top1= 77.8546


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2429 top1= 49.0685


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4083 top1= 42.6482

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.2909 top1= 91.5625
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.3555 top1= 91.5625
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.2569 top1= 95.3125
[E 6B30 |  11904/60000 ( 20%) ] Loss: 0.3661 top1= 89.3750
[E 6B40 |  15744/60000 ( 26%) ] Loss: 0.3544 top1= 89.0625
[E 6B50 |  19584/60000 ( 33%) ] Loss: 0.2750 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0450 top1= 77.6743


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2295 top1= 49.1186


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4054 top1= 42.5681

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.2911 top1= 91.8750
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.3532 top1= 90.9375
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.2571 top1= 95.0000
[E 7B30 |  11904/60000 ( 20%) ] Loss: 0.3583 top1= 90.0000
[E 7B40 |  15744/60000 ( 26%) ] Loss: 0.3476 top1= 88.7500
[E 7B50 |  19584/60000 ( 33%) ] Loss: 0.2735 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0480 top1= 77.3438


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2194 top1= 49.1486


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4056 top1= 42.4379

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.2931 top1= 91.5625
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.3520 top1= 90.9375
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.2570 top1= 94.6875
[E 8B30 |  11904/60000 ( 20%) ] Loss: 0.3574 top1= 90.0000
[E 8B40 |  15744/60000 ( 26%) ] Loss: 0.3419 top1= 88.7500
[E 8B50 |  19584/60000 ( 33%) ] Loss: 0.2744 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0509 top1= 77.1434


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2153 top1= 49.1687


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3804 top1= 42.5180

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.2900 top1= 91.8750
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.3481 top1= 90.9375
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.2532 top1= 94.6875
[E 9B30 |  11904/60000 ( 20%) ] Loss: 0.3536 top1= 90.3125
[E 9B40 |  15744/60000 ( 26%) ] Loss: 0.3367 top1= 88.7500
[E 9B50 |  19584/60000 ( 33%) ] Loss: 0.2787 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0535 top1= 77.0733


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2144 top1= 49.1987


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3569 top1= 42.4479

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.2918 top1= 91.8750
[E10B10 |   4224/60000 (  7%) ] Loss: 0.3544 top1= 90.9375
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.2572 top1= 94.3750
[E10B30 |  11904/60000 ( 20%) ] Loss: 0.3522 top1= 90.0000
[E10B40 |  15744/60000 ( 26%) ] Loss: 0.3341 top1= 89.0625
[E10B50 |  19584/60000 ( 33%) ] Loss: 0.2760 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0556 top1= 76.8429


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2148 top1= 49.1887


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3304 top1= 42.3077

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.2924 top1= 91.8750
[E11B10 |   4224/60000 (  7%) ] Loss: 0.3524 top1= 90.6250
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.2564 top1= 94.3750
[E11B30 |  11904/60000 ( 20%) ] Loss: 0.3550 top1= 90.3125
[E11B40 |  15744/60000 ( 26%) ] Loss: 0.3302 top1= 89.0625
[E11B50 |  19584/60000 ( 33%) ] Loss: 0.2755 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0586 top1= 76.7428


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2166 top1= 49.1687


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3067 top1= 42.5180

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.2913 top1= 92.1875
[E12B10 |   4224/60000 (  7%) ] Loss: 0.3527 top1= 90.9375
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.2569 top1= 94.3750
[E12B30 |  11904/60000 ( 20%) ] Loss: 0.3536 top1= 90.6250
[E12B40 |  15744/60000 ( 26%) ] Loss: 0.3295 top1= 89.3750
[E12B50 |  19584/60000 ( 33%) ] Loss: 0.2715 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0610 top1= 76.5024


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2176 top1= 49.1486


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2935 top1= 42.5080

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.2908 top1= 92.1875
[E13B10 |   4224/60000 (  7%) ] Loss: 0.3523 top1= 91.2500
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.2540 top1= 94.6875
[E13B30 |  11904/60000 ( 20%) ] Loss: 0.3587 top1= 90.6250
[E13B40 |  15744/60000 ( 26%) ] Loss: 0.3253 top1= 90.0000
[E13B50 |  19584/60000 ( 33%) ] Loss: 0.2752 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0636 top1= 76.2821


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2155 top1= 49.1186


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2798 top1= 42.4379

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.2921 top1= 91.2500
[E14B10 |   4224/60000 (  7%) ] Loss: 0.3514 top1= 90.3125
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.2582 top1= 94.3750
[E14B30 |  11904/60000 ( 20%) ] Loss: 0.3571 top1= 90.0000
[E14B40 |  15744/60000 ( 26%) ] Loss: 0.3249 top1= 89.6875
[E14B50 |  19584/60000 ( 33%) ] Loss: 0.2677 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0625 top1= 76.2821


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2147 top1= 49.1186


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2911 top1= 42.6783

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.2877 top1= 91.5625
[E15B10 |   4224/60000 (  7%) ] Loss: 0.3447 top1= 90.9375
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.2508 top1= 95.3125
[E15B30 |  11904/60000 ( 20%) ] Loss: 0.3616 top1= 90.6250
[E15B40 |  15744/60000 ( 26%) ] Loss: 0.3247 top1= 89.6875
[E15B50 |  19584/60000 ( 33%) ] Loss: 0.2742 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0656 top1= 76.0116


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2127 top1= 49.1086


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2854 top1= 42.4780

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.2889 top1= 91.2500
[E16B10 |   4224/60000 (  7%) ] Loss: 0.3463 top1= 90.9375
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.2554 top1= 95.0000
[E16B30 |  11904/60000 ( 20%) ] Loss: 0.3593 top1= 89.3750
[E16B40 |  15744/60000 ( 26%) ] Loss: 0.3236 top1= 90.0000
[E16B50 |  19584/60000 ( 33%) ] Loss: 0.2768 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0660 top1= 76.0317


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2124 top1= 49.1086


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2696 top1= 42.4980

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.2890 top1= 90.9375
[E17B10 |   4224/60000 (  7%) ] Loss: 0.3460 top1= 90.6250
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.2555 top1= 95.3125
[E17B30 |  11904/60000 ( 20%) ] Loss: 0.3566 top1= 90.3125
[E17B40 |  15744/60000 ( 26%) ] Loss: 0.3233 top1= 90.0000
[E17B50 |  19584/60000 ( 33%) ] Loss: 0.2748 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0652 top1= 75.9115


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2089 top1= 49.0885


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2642 top1= 42.5280

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.2887 top1= 91.2500
[E18B10 |   4224/60000 (  7%) ] Loss: 0.3441 top1= 90.9375
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.2507 top1= 95.0000
[E18B30 |  11904/60000 ( 20%) ] Loss: 0.3640 top1= 89.3750
[E18B40 |  15744/60000 ( 26%) ] Loss: 0.3226 top1= 90.3125
[E18B50 |  19584/60000 ( 33%) ] Loss: 0.2784 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0682 top1= 75.7011


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2087 top1= 49.0885


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2649 top1= 42.5681

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.2914 top1= 91.5625
[E19B10 |   4224/60000 (  7%) ] Loss: 0.3445 top1= 90.6250
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.2545 top1= 95.0000
[E19B30 |  11904/60000 ( 20%) ] Loss: 0.3619 top1= 90.0000
[E19B40 |  15744/60000 ( 26%) ] Loss: 0.3232 top1= 90.3125
[E19B50 |  19584/60000 ( 33%) ] Loss: 0.2765 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0653 top1= 75.7512


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2090 top1= 49.0986


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2698 top1= 42.6082

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.2909 top1= 91.2500
[E20B10 |   4224/60000 (  7%) ] Loss: 0.3428 top1= 90.9375
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.2504 top1= 95.3125
[E20B30 |  11904/60000 ( 20%) ] Loss: 0.3617 top1= 90.0000
[E20B40 |  15744/60000 ( 26%) ] Loss: 0.3266 top1= 90.0000
[E20B50 |  19584/60000 ( 33%) ] Loss: 0.2743 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0641 top1= 75.9315


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2066 top1= 49.1086


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2786 top1= 42.5080

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.2897 top1= 90.9375
[E21B10 |   4224/60000 (  7%) ] Loss: 0.3416 top1= 91.2500
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.2520 top1= 95.0000
[E21B30 |  11904/60000 ( 20%) ] Loss: 0.3614 top1= 89.6875
[E21B40 |  15744/60000 ( 26%) ] Loss: 0.3255 top1= 90.3125
[E21B50 |  19584/60000 ( 33%) ] Loss: 0.2788 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0631 top1= 75.9916


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2042 top1= 49.1286


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2804 top1= 42.4880

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.2877 top1= 91.2500
[E22B10 |   4224/60000 (  7%) ] Loss: 0.3427 top1= 90.9375
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.2511 top1= 95.0000
[E22B30 |  11904/60000 ( 20%) ] Loss: 0.3581 top1= 90.0000
[E22B40 |  15744/60000 ( 26%) ] Loss: 0.3250 top1= 90.6250
[E22B50 |  19584/60000 ( 33%) ] Loss: 0.2814 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0624 top1= 76.6526


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2025 top1= 49.1486


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2748 top1= 42.4479

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.2896 top1= 91.5625
[E23B10 |   4224/60000 (  7%) ] Loss: 0.3400 top1= 90.6250
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.2528 top1= 94.6875
[E23B30 |  11904/60000 ( 20%) ] Loss: 0.3556 top1= 90.9375
[E23B40 |  15744/60000 ( 26%) ] Loss: 0.3254 top1= 90.6250
[E23B50 |  19584/60000 ( 33%) ] Loss: 0.2813 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0621 top1= 76.1919


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2054 top1= 49.1386


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2690 top1= 42.4479

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.2921 top1= 90.9375
[E24B10 |   4224/60000 (  7%) ] Loss: 0.3397 top1= 90.9375
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.2521 top1= 94.6875
[E24B30 |  11904/60000 ( 20%) ] Loss: 0.3539 top1= 90.6250
[E24B40 |  15744/60000 ( 26%) ] Loss: 0.3242 top1= 90.6250
[E24B50 |  19584/60000 ( 33%) ] Loss: 0.2842 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0610 top1= 76.6927


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2038 top1= 49.1386


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2738 top1= 42.3978

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.2919 top1= 90.6250
[E25B10 |   4224/60000 (  7%) ] Loss: 0.3391 top1= 91.2500
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.2507 top1= 94.3750
[E25B30 |  11904/60000 ( 20%) ] Loss: 0.3567 top1= 90.3125
[E25B40 |  15744/60000 ( 26%) ] Loss: 0.3247 top1= 90.6250
[E25B50 |  19584/60000 ( 33%) ] Loss: 0.2883 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0621 top1= 76.5124


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1984 top1= 49.1887


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2617 top1= 42.4880

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.2928 top1= 91.2500
[E26B10 |   4224/60000 (  7%) ] Loss: 0.3436 top1= 91.5625
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.2552 top1= 94.6875
[E26B30 |  11904/60000 ( 20%) ] Loss: 0.3496 top1= 90.6250
[E26B40 |  15744/60000 ( 26%) ] Loss: 0.3242 top1= 90.6250
[E26B50 |  19584/60000 ( 33%) ] Loss: 0.2845 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0621 top1= 76.5725


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1983 top1= 49.1987


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2534 top1= 42.4980

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.2926 top1= 91.2500
[E27B10 |   4224/60000 (  7%) ] Loss: 0.3398 top1= 91.5625
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.2530 top1= 94.6875
[E27B30 |  11904/60000 ( 20%) ] Loss: 0.3522 top1= 90.9375
[E27B40 |  15744/60000 ( 26%) ] Loss: 0.3228 top1= 90.6250
[E27B50 |  19584/60000 ( 33%) ] Loss: 0.2887 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0623 top1= 76.9832


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1941 top1= 49.1887


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2622 top1= 42.4179

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.2919 top1= 91.5625
[E28B10 |   4224/60000 (  7%) ] Loss: 0.3402 top1= 92.1875
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.2526 top1= 94.3750
[E28B30 |  11904/60000 ( 20%) ] Loss: 0.3542 top1= 90.9375
[E28B40 |  15744/60000 ( 26%) ] Loss: 0.3233 top1= 90.6250
[E28B50 |  19584/60000 ( 33%) ] Loss: 0.2841 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0627 top1= 76.6727


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2006 top1= 49.1987


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2623 top1= 42.3778

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.2910 top1= 90.9375
[E29B10 |   4224/60000 (  7%) ] Loss: 0.3415 top1= 91.8750
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.2493 top1= 95.0000
[E29B30 |  11904/60000 ( 20%) ] Loss: 0.3530 top1= 90.6250
[E29B40 |  15744/60000 ( 26%) ] Loss: 0.3215 top1= 90.6250
[E29B50 |  19584/60000 ( 33%) ] Loss: 0.2859 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0628 top1= 76.6326


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1966 top1= 49.1787


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2591 top1= 42.4179

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.2919 top1= 91.5625
[E30B10 |   4224/60000 (  7%) ] Loss: 0.3426 top1= 91.2500
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.2512 top1= 95.3125
[E30B30 |  11904/60000 ( 20%) ] Loss: 0.3512 top1= 90.3125
[E30B40 |  15744/60000 ( 26%) ] Loss: 0.3251 top1= 90.9375
[E30B50 |  19584/60000 ( 33%) ] Loss: 0.2835 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0611 top1= 76.6426


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1975 top1= 49.1687


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2604 top1= 42.4880

