
=== 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 0x7faf7edc49d0>

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: 1.0111 top1= 63.4375
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2646 top1= 90.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6798 top1= 78.3053


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.3015 top1= 48.6178


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2698 top1= 43.5797

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3913 top1= 90.9375
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.2624 top1= 91.8750
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1581 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6742 top1= 84.7857


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8262 top1= 49.8297


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7533 top1= 45.5529

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1493 top1= 95.6250
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1295 top1= 95.6250
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0808 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5516 top1= 85.8073


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1836 top1= 49.9599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6772 top1= 46.0036

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0866 top1= 97.5000
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0762 top1= 96.5625
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0554 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4727 top1= 87.2897


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9682 top1= 50.2103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5696 top1= 46.1138

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0569 top1= 97.8125
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0455 top1= 99.0625
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0403 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4147 top1= 88.2312


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7813 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4292 top1= 46.2340

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0374 top1= 98.7500
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0399 top1= 99.0625
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0312 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3901 top1= 88.4816


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4726 top1= 50.2204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2116 top1= 46.2941

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0250 top1= 99.3750
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0456 top1= 98.7500
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0224 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3658 top1= 88.7520


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2093 top1= 50.8914


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9111 top1= 47.6462

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0172 top1=100.0000
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0238 top1= 99.3750
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0211 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3481 top1= 88.9323


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9762 top1= 51.3822


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9007 top1= 48.7580

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0150 top1=100.0000
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0240 top1= 99.3750
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0271 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3485 top1= 88.5417


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8534 top1= 51.7328


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0696 top1= 48.0569

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0336 top1= 99.6875
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0396 top1= 98.4375
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0334 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3530 top1= 88.4215


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6320 top1= 53.6759


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0298 top1= 48.2973

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0296 top1= 99.3750
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0284 top1= 99.0625
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0131 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3264 top1= 89.4932


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4965 top1= 53.8161


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5086 top1= 50.1703

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0202 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0402 top1= 98.4375
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0430 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3347 top1= 89.1827


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3365 top1= 55.7993


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2775 top1= 50.9716

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0180 top1= 99.6875
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0257 top1= 99.3750
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0269 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3241 top1= 88.6118


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2812 top1= 55.6991


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1979 top1= 53.3353

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0291 top1= 98.7500
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0207 top1= 99.3750
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0179 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2949 top1= 90.2845


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1655 top1= 56.5905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9691 top1= 54.9780

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0168 top1= 99.3750
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0198 top1= 99.6875
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0069 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2810 top1= 91.0557


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7960 top1= 59.5753


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6167 top1= 58.2933

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0080 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0086 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0072 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2797 top1= 90.8153


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7396 top1= 60.5369


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4356 top1= 60.8273

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0079 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0099 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0068 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2702 top1= 91.2059


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4560 top1= 63.9323


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3167 top1= 63.6418

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0070 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0093 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0065 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2659 top1= 91.4563


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3514 top1= 65.4848


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2053 top1= 66.5966

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0068 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0080 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0062 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2566 top1= 91.7167


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2775 top1= 66.6466


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1377 top1= 68.2893

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0075 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0076 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0055 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2536 top1= 91.8670


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1876 top1= 68.3894


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0687 top1= 69.9820

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0065 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0068 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0052 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2510 top1= 91.9371


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1162 top1= 69.9219


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0046 top1= 71.6146

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0062 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0064 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0050 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2499 top1= 91.9171


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0627 top1= 70.9836


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9369 top1= 73.2772

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0057 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0059 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0047 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2490 top1= 92.0573


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0129 top1= 72.0353


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8934 top1= 74.3289

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0054 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0057 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0045 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2482 top1= 92.1474


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9750 top1= 72.9067


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8630 top1= 75.0701

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0052 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0055 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0043 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2469 top1= 92.2175


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9447 top1= 73.5577


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8341 top1= 76.0116

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0050 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0053 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0042 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2460 top1= 92.2676


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9156 top1= 74.0485


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8133 top1= 76.5124

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0049 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0052 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0041 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2450 top1= 92.3377


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8897 top1= 74.6795


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7926 top1= 77.3337

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0047 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0051 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0041 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2443 top1= 92.3678


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8672 top1= 75.0801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7739 top1= 77.7244

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0047 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0050 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0040 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2438 top1= 92.3978


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8468 top1= 75.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7640 top1= 78.1050

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0046 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0049 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0040 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2431 top1= 92.4679


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8313 top1= 75.8113


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7520 top1= 78.3454

