
=== 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.DumbbellVariant object at 0x7f20e98722b0>

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: 1.4961 top1= 47.3438
[E 1B20 |  14784/60000 ( 25%) ] Loss: 1.0899 top1= 65.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3504 top1= 79.0465


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1463 top1= 48.2873


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4820 top1= 43.0889

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.8024 top1= 74.0625
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.6088 top1= 81.2500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.5681 top1= 82.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9422 top1= 74.3189


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6739 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5006 top1= 44.0204

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.5329 top1= 82.6562
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.4198 top1= 86.2500
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.4551 top1= 85.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7688 top1= 75.8514


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4934 top1= 55.2083


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3454 top1= 44.7015

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.3874 top1= 87.9688
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.3470 top1= 88.2812
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.4301 top1= 87.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6938 top1= 76.6126


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2685 top1= 59.6254


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3624 top1= 45.4427

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.3973 top1= 87.6562
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.3660 top1= 89.2188
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.3616 top1= 88.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5770 top1= 81.9611


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3355 top1= 60.1663


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9964 top1= 47.0453

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.3048 top1= 90.4688
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.2657 top1= 91.8750
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.3697 top1= 89.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5286 top1= 84.8658


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1835 top1= 62.1795


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7029 top1= 49.5192

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.3340 top1= 90.7812
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.2170 top1= 92.9688
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.3282 top1= 90.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4751 top1= 85.6270


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2319 top1= 62.3097


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7049 top1= 50.5609

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.2473 top1= 92.3438
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.2143 top1= 93.5938
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.2704 top1= 92.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4412 top1= 86.7588


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1462 top1= 64.1927


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5821 top1= 51.9932

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.2256 top1= 93.2812
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.2120 top1= 94.0625
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.2364 top1= 93.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3907 top1= 88.5617


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1043 top1= 64.5533


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4032 top1= 55.1482

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1839 top1= 94.3750
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.2086 top1= 93.5938
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.2265 top1= 93.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3726 top1= 88.7520


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1290 top1= 64.9038


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4200 top1= 55.8794

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1645 top1= 95.3125
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.2116 top1= 94.3750
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.2504 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3567 top1= 89.4531


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1160 top1= 64.8838


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3387 top1= 57.2716

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1472 top1= 96.5625
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.1701 top1= 95.1562
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.2148 top1= 93.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3452 top1= 89.8738


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1100 top1= 65.2744


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1745 top1= 60.6470

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.2840 top1= 92.6562
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.1581 top1= 95.3125
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1806 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3269 top1= 90.0441


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0263 top1= 66.7969


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2758 top1= 59.4050

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.1402 top1= 96.2500
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.1877 top1= 96.2500
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.2099 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3219 top1= 90.3746


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0449 top1= 66.5865


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2336 top1= 59.7957

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.1298 top1= 96.8750
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.1192 top1= 96.8750
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.1626 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2973 top1= 90.9956


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0151 top1= 67.1875


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1003 top1= 63.6518

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.1480 top1= 95.9375
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.1050 top1= 97.5000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.1506 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2869 top1= 91.1258


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0070 top1= 67.8986


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1773 top1= 62.9908

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.1224 top1= 96.2500
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0999 top1= 97.3438
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.2482 top1= 93.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2954 top1= 90.8754


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9655 top1= 68.3193


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2268 top1= 61.2480

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.2005 top1= 94.0625
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.1329 top1= 96.0938
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.1329 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2760 top1= 91.7167


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9923 top1= 68.2192


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0847 top1= 64.3129

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.1173 top1= 96.7188
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0923 top1= 98.4375
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.1337 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2709 top1= 91.5465


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9698 top1= 69.0805


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1181 top1= 64.5833

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.1732 top1= 94.8438
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.1546 top1= 95.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.1957 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2777 top1= 91.4563


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9164 top1= 69.9419


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1794 top1= 62.4099

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.1196 top1= 96.2500
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0847 top1= 98.2812
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.1190 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2582 top1= 92.0773


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8946 top1= 70.5128


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0379 top1= 66.4263

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.1183 top1= 96.8750
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0746 top1= 98.2812
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.1122 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2518 top1= 92.1975


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8945 top1= 71.1238


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0723 top1= 66.6166

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0985 top1= 97.0312
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0966 top1= 97.8125
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.1454 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2478 top1= 92.3177


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9306 top1= 70.2524


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0887 top1= 66.2260

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.1226 top1= 96.7188
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0863 top1= 98.5938
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.1193 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2398 top1= 92.6282


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9082 top1= 70.9535


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9595 top1= 69.4311

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0994 top1= 97.1875
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0893 top1= 98.1250
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.1910 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2503 top1= 92.3177


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9390 top1= 70.4227


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1640 top1= 64.6835

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0930 top1= 97.0312
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0795 top1= 97.9688
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0902 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2343 top1= 92.6683


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8878 top1= 71.4343


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0263 top1= 68.0389

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0883 top1= 97.8125
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0623 top1= 98.7500
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0959 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2280 top1= 92.8586


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8615 top1= 72.2155


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9885 top1= 69.1206

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0831 top1= 97.6562
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0663 top1= 98.4375
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0837 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2246 top1= 92.9387


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8113 top1= 73.2973


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9954 top1= 69.8718

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0742 top1= 97.9688
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0516 top1= 98.9062
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0810 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2182 top1= 93.1290


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9056 top1= 71.6847


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9879 top1= 69.7616

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0951 top1= 97.3438
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0550 top1= 98.5938
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0871 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2176 top1= 93.0389


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7908 top1= 74.1787


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9932 top1= 69.5012

