
=== 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 0x7f2f438a47c0>

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: 1.0919 top1= 63.4375
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2960 top1= 90.9375
[E 1B30 |  11904/60000 ( 20%) ] Loss: 0.4131 top1= 86.5625
[E 1B40 |  15744/60000 ( 26%) ] Loss: 0.2794 top1= 90.3125
[E 1B50 |  19584/60000 ( 33%) ] Loss: 0.2077 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6199 top1= 85.9075


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5223 top1= 49.7396


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3936 top1= 45.1122

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.1985 top1= 94.6875
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.2481 top1= 92.1875
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1823 top1= 95.6250
[E 2B30 |  11904/60000 ( 20%) ] Loss: 0.2840 top1= 92.5000
[E 2B40 |  15744/60000 ( 26%) ] Loss: 0.2244 top1= 92.8125
[E 2B50 |  19584/60000 ( 33%) ] Loss: 0.1832 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6362 top1= 85.8874


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2952 top1= 49.9099


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2611 top1= 45.4127

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1742 top1= 95.6250
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.2304 top1= 92.5000
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1712 top1= 96.2500
[E 3B30 |  11904/60000 ( 20%) ] Loss: 0.2787 top1= 93.7500
[E 3B40 |  15744/60000 ( 26%) ] Loss: 0.2614 top1= 92.8125
[E 3B50 |  19584/60000 ( 33%) ] Loss: 0.1969 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7921 top1= 84.3650


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3056 top1= 49.6795


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4170 top1= 44.8518

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.2088 top1= 94.6875
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.2979 top1= 91.5625
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.2081 top1= 96.8750
[E 4B30 |  11904/60000 ( 20%) ] Loss: 0.3314 top1= 91.8750
[E 4B40 |  15744/60000 ( 26%) ] Loss: 0.3240 top1= 90.6250
[E 4B50 |  19584/60000 ( 33%) ] Loss: 0.2544 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9694 top1= 80.4287


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3654 top1= 49.2188


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5209 top1= 43.9303

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.2740 top1= 94.0625
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.3569 top1= 90.6250
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.2499 top1= 95.9375
[E 5B30 |  11904/60000 ( 20%) ] Loss: 0.3698 top1= 90.0000
[E 5B40 |  15744/60000 ( 26%) ] Loss: 0.3447 top1= 89.0625
[E 5B50 |  19584/60000 ( 33%) ] Loss: 0.2839 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0145 top1= 78.9363


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3086 top1= 49.0885


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4391 top1= 43.1290

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.2948 top1= 91.8750
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.3650 top1= 90.3125
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.2508 top1= 95.9375
[E 6B30 |  11904/60000 ( 20%) ] Loss: 0.3651 top1= 89.6875
[E 6B40 |  15744/60000 ( 26%) ] Loss: 0.3422 top1= 89.0625
[E 6B50 |  19584/60000 ( 33%) ] Loss: 0.2765 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0234 top1= 78.9163


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2766 top1= 49.0184


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4193 top1= 43.1090

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.2967 top1= 91.5625
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.3609 top1= 90.6250
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.2539 top1= 95.9375
[E 7B30 |  11904/60000 ( 20%) ] Loss: 0.3652 top1= 89.6875
[E 7B40 |  15744/60000 ( 26%) ] Loss: 0.3387 top1= 89.0625
[E 7B50 |  19584/60000 ( 33%) ] Loss: 0.2765 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0300 top1= 78.8462


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2549 top1= 48.9683


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3947 top1= 42.8886

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.2971 top1= 91.2500
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.3632 top1= 91.2500
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.2555 top1= 95.6250
[E 8B30 |  11904/60000 ( 20%) ] Loss: 0.3595 top1= 89.6875
[E 8B40 |  15744/60000 ( 26%) ] Loss: 0.3379 top1= 89.3750
[E 8B50 |  19584/60000 ( 33%) ] Loss: 0.2767 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0353 top1= 78.6058


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2394 top1= 49.0885


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3835 top1= 42.9387

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.2982 top1= 90.9375
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.3657 top1= 90.9375
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.2560 top1= 95.3125
[E 9B30 |  11904/60000 ( 20%) ] Loss: 0.3565 top1= 90.9375
[E 9B40 |  15744/60000 ( 26%) ] Loss: 0.3356 top1= 89.0625
[E 9B50 |  19584/60000 ( 33%) ] Loss: 0.2784 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0414 top1= 78.1751


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2310 top1= 49.0986


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3668 top1= 42.8686

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.3002 top1= 90.9375
[E10B10 |   4224/60000 (  7%) ] Loss: 0.3607 top1= 90.9375
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.2530 top1= 95.6250
[E10B30 |  11904/60000 ( 20%) ] Loss: 0.3543 top1= 90.3125
[E10B40 |  15744/60000 ( 26%) ] Loss: 0.3327 top1= 89.0625
[E10B50 |  19584/60000 ( 33%) ] Loss: 0.2838 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0436 top1= 78.1050


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2171 top1= 49.1787


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3443 top1= 42.8886

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.3017 top1= 90.9375
[E11B10 |   4224/60000 (  7%) ] Loss: 0.3573 top1= 91.2500
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.2535 top1= 95.3125
[E11B30 |  11904/60000 ( 20%) ] Loss: 0.3591 top1= 90.3125
[E11B40 |  15744/60000 ( 26%) ] Loss: 0.3297 top1= 89.0625
[E11B50 |  19584/60000 ( 33%) ] Loss: 0.2841 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0454 top1= 77.8946


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2144 top1= 49.1887


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3394 top1= 42.8786

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.3028 top1= 90.6250
[E12B10 |   4224/60000 (  7%) ] Loss: 0.3566 top1= 90.9375
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.2548 top1= 94.6875
[E12B30 |  11904/60000 ( 20%) ] Loss: 0.3588 top1= 90.3125
[E12B40 |  15744/60000 ( 26%) ] Loss: 0.3273 top1= 88.7500
[E12B50 |  19584/60000 ( 33%) ] Loss: 0.2827 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0479 top1= 77.6342


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2128 top1= 49.1587


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3270 top1= 42.7885

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.3064 top1= 90.9375
[E13B10 |   4224/60000 (  7%) ] Loss: 0.3630 top1= 90.6250
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.2561 top1= 94.3750
[E13B30 |  11904/60000 ( 20%) ] Loss: 0.3568 top1= 90.3125
[E13B40 |  15744/60000 ( 26%) ] Loss: 0.3254 top1= 89.0625
[E13B50 |  19584/60000 ( 33%) ] Loss: 0.2838 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0514 top1= 77.1735


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2133 top1= 49.1286


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3094 top1= 42.8185

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.3069 top1= 91.2500
[E14B10 |   4224/60000 (  7%) ] Loss: 0.3590 top1= 90.6250
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.2569 top1= 94.3750
[E14B30 |  11904/60000 ( 20%) ] Loss: 0.3577 top1= 89.6875
[E14B40 |  15744/60000 ( 26%) ] Loss: 0.3245 top1= 89.6875
[E14B50 |  19584/60000 ( 33%) ] Loss: 0.2839 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0525 top1= 77.2336


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2081 top1= 49.2288


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3098 top1= 42.7284

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.3047 top1= 90.6250
[E15B10 |   4224/60000 (  7%) ] Loss: 0.3628 top1= 90.6250
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.2567 top1= 94.3750
[E15B30 |  11904/60000 ( 20%) ] Loss: 0.3570 top1= 90.0000
[E15B40 |  15744/60000 ( 26%) ] Loss: 0.3196 top1= 89.6875
[E15B50 |  19584/60000 ( 33%) ] Loss: 0.2837 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0556 top1= 76.7127


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2152 top1= 49.2087


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2850 top1= 42.7083

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.3056 top1= 90.9375
[E16B10 |   4224/60000 (  7%) ] Loss: 0.3591 top1= 90.9375
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.2572 top1= 94.0625
[E16B30 |  11904/60000 ( 20%) ] Loss: 0.3562 top1= 90.0000
[E16B40 |  15744/60000 ( 26%) ] Loss: 0.3203 top1= 89.6875
[E16B50 |  19584/60000 ( 33%) ] Loss: 0.2827 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0588 top1= 76.7228


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2161 top1= 49.1987


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2713 top1= 42.6282

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.3070 top1= 90.9375
[E17B10 |   4224/60000 (  7%) ] Loss: 0.3554 top1= 90.6250
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.2588 top1= 94.3750
[E17B30 |  11904/60000 ( 20%) ] Loss: 0.3565 top1= 89.6875
[E17B40 |  15744/60000 ( 26%) ] Loss: 0.3184 top1= 89.6875
[E17B50 |  19584/60000 ( 33%) ] Loss: 0.2806 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0619 top1= 76.2019


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2205 top1= 49.1787


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2502 top1= 42.6482

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.3037 top1= 90.9375
[E18B10 |   4224/60000 (  7%) ] Loss: 0.3511 top1= 91.2500
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.2582 top1= 94.3750
[E18B30 |  11904/60000 ( 20%) ] Loss: 0.3591 top1= 89.3750
[E18B40 |  15744/60000 ( 26%) ] Loss: 0.3223 top1= 89.6875
[E18B50 |  19584/60000 ( 33%) ] Loss: 0.2805 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0615 top1= 76.1518


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2213 top1= 49.1787


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2450 top1= 42.6382

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.3042 top1= 91.2500
[E19B10 |   4224/60000 (  7%) ] Loss: 0.3502 top1= 90.9375
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.2594 top1= 94.3750
[E19B30 |  11904/60000 ( 20%) ] Loss: 0.3616 top1= 89.3750
[E19B40 |  15744/60000 ( 26%) ] Loss: 0.3234 top1= 90.0000
[E19B50 |  19584/60000 ( 33%) ] Loss: 0.2825 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0621 top1= 75.6811


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2215 top1= 49.1887


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2453 top1= 42.5581

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.3027 top1= 91.2500
[E20B10 |   4224/60000 (  7%) ] Loss: 0.3422 top1= 91.2500
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.2555 top1= 94.3750
[E20B30 |  11904/60000 ( 20%) ] Loss: 0.3637 top1= 89.6875
[E20B40 |  15744/60000 ( 26%) ] Loss: 0.3220 top1= 90.3125
[E20B50 |  19584/60000 ( 33%) ] Loss: 0.2822 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0627 top1= 75.6911


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2243 top1= 49.1987


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2354 top1= 42.4780

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.3041 top1= 91.2500
[E21B10 |   4224/60000 (  7%) ] Loss: 0.3448 top1= 91.2500
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.2585 top1= 94.3750
[E21B30 |  11904/60000 ( 20%) ] Loss: 0.3618 top1= 89.3750
[E21B40 |  15744/60000 ( 26%) ] Loss: 0.3227 top1= 90.6250
[E21B50 |  19584/60000 ( 33%) ] Loss: 0.2835 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0634 top1= 75.4808


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2218 top1= 49.1987


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2366 top1= 42.4379

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.3034 top1= 91.5625
[E22B10 |   4224/60000 (  7%) ] Loss: 0.3455 top1= 91.2500
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.2582 top1= 94.0625
[E22B30 |  11904/60000 ( 20%) ] Loss: 0.3617 top1= 89.3750
[E22B40 |  15744/60000 ( 26%) ] Loss: 0.3244 top1= 90.0000
[E22B50 |  19584/60000 ( 33%) ] Loss: 0.2817 top1= 91.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0624 top1= 75.5108


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2217 top1= 49.1887


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2479 top1= 42.5381

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.3013 top1= 91.8750
[E23B10 |   4224/60000 (  7%) ] Loss: 0.3412 top1= 90.9375
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.2581 top1= 94.0625
[E23B30 |  11904/60000 ( 20%) ] Loss: 0.3618 top1= 89.6875
[E23B40 |  15744/60000 ( 26%) ] Loss: 0.3239 top1= 90.3125
[E23B50 |  19584/60000 ( 33%) ] Loss: 0.2806 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0644 top1= 75.6210


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2196 top1= 49.1887


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2472 top1= 42.4679

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.3040 top1= 91.2500
[E24B10 |   4224/60000 (  7%) ] Loss: 0.3392 top1= 91.2500
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.2577 top1= 94.0625
[E24B30 |  11904/60000 ( 20%) ] Loss: 0.3581 top1= 89.6875
[E24B40 |  15744/60000 ( 26%) ] Loss: 0.3291 top1= 90.6250
[E24B50 |  19584/60000 ( 33%) ] Loss: 0.2825 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0638 top1= 75.3806


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2219 top1= 49.1486


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2517 top1= 42.4880

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.3000 top1= 91.5625
[E25B10 |   4224/60000 (  7%) ] Loss: 0.3381 top1= 91.5625
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.2562 top1= 93.7500
[E25B30 |  11904/60000 ( 20%) ] Loss: 0.3617 top1= 90.3125
[E25B40 |  15744/60000 ( 26%) ] Loss: 0.3289 top1= 90.0000
[E25B50 |  19584/60000 ( 33%) ] Loss: 0.2818 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0636 top1= 75.1302


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2217 top1= 49.1587


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2603 top1= 42.3578

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.3024 top1= 91.2500
[E26B10 |   4224/60000 (  7%) ] Loss: 0.3423 top1= 90.9375
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.2579 top1= 94.0625
[E26B30 |  11904/60000 ( 20%) ] Loss: 0.3608 top1= 89.6875
[E26B40 |  15744/60000 ( 26%) ] Loss: 0.3263 top1= 90.0000
[E26B50 |  19584/60000 ( 33%) ] Loss: 0.2852 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0602 top1= 75.4507


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2169 top1= 49.1687


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2656 top1= 42.4079

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.3032 top1= 90.9375
[E27B10 |   4224/60000 (  7%) ] Loss: 0.3423 top1= 90.6250
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.2563 top1= 94.0625
[E27B30 |  11904/60000 ( 20%) ] Loss: 0.3633 top1= 90.0000
[E27B40 |  15744/60000 ( 26%) ] Loss: 0.3236 top1= 90.0000
[E27B50 |  19584/60000 ( 33%) ] Loss: 0.2861 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0629 top1= 75.5809


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2140 top1= 49.1787


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2496 top1= 42.3478

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.3019 top1= 91.5625
[E28B10 |   4224/60000 (  7%) ] Loss: 0.3451 top1= 90.6250
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.2582 top1= 93.7500
[E28B30 |  11904/60000 ( 20%) ] Loss: 0.3606 top1= 90.3125
[E28B40 |  15744/60000 ( 26%) ] Loss: 0.3247 top1= 90.0000
[E28B50 |  19584/60000 ( 33%) ] Loss: 0.2852 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0626 top1= 75.5308


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2180 top1= 49.1587


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2521 top1= 42.4079

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.3008 top1= 91.2500
[E29B10 |   4224/60000 (  7%) ] Loss: 0.3421 top1= 90.3125
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.2580 top1= 94.3750
[E29B30 |  11904/60000 ( 20%) ] Loss: 0.3594 top1= 90.3125
[E29B40 |  15744/60000 ( 26%) ] Loss: 0.3231 top1= 90.6250
[E29B50 |  19584/60000 ( 33%) ] Loss: 0.2840 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0596 top1= 75.7512


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2161 top1= 49.1787


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2626 top1= 42.5280

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.2981 top1= 91.2500
[E30B10 |   4224/60000 (  7%) ] Loss: 0.3402 top1= 90.6250
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.2619 top1= 94.0625
[E30B30 |  11904/60000 ( 20%) ] Loss: 0.3604 top1= 90.6250
[E30B40 |  15744/60000 ( 26%) ] Loss: 0.3292 top1= 89.6875
[E30B50 |  19584/60000 ( 33%) ] Loss: 0.2826 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0591 top1= 76.1919


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2139 top1= 49.1687


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2819 top1= 42.4880

