
=== 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 0x7f37d75c32b0>

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: 1.1197 top1= 60.7812
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3948 top1= 87.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7786 top1= 79.5673


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7437 top1= 49.1887


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4025 top1= 43.8301

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2784 top1= 90.7812
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.2149 top1= 93.9062
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.2099 top1= 94.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7781 top1= 84.9259


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7086 top1= 49.8698


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7458 top1= 45.5929

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1880 top1= 94.8438
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1548 top1= 95.9375
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1745 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7197 top1= 86.1478


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4067 top1= 49.9599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5831 top1= 45.7332

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1705 top1= 95.3125
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1357 top1= 96.7188
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1552 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6856 top1= 86.4383


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2536 top1= 50.0401


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4482 top1= 45.9435

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1514 top1= 95.6250
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.1253 top1= 96.4062
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1399 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6701 top1= 86.5485


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1597 top1= 50.0000


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3945 top1= 45.9034

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1476 top1= 95.0000
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.1197 top1= 97.1875
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.1353 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6705 top1= 85.8173


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0951 top1= 49.9399


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3892 top1= 45.9335

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.1401 top1= 95.3125
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.1145 top1= 97.0312
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.1295 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6735 top1= 85.1362


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0746 top1= 49.7897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4278 top1= 45.9235

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.1400 top1= 95.4688
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.1129 top1= 97.6562
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.1226 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6750 top1= 84.5353


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0604 top1= 49.6995


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4512 top1= 45.9335

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.1372 top1= 95.9375
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.1066 top1= 97.6562
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.1184 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6803 top1= 83.8742


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0834 top1= 49.8297


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4499 top1= 45.9836

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.1270 top1= 96.7188
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.1006 top1= 97.8125
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.1113 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6727 top1= 84.5853


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0442 top1= 50.1903


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4796 top1= 45.9034

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.1179 top1= 96.5625
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0938 top1= 98.1250
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.1064 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6763 top1= 84.0345


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0205 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4827 top1= 45.9535

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.1106 top1= 96.8750
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0869 top1= 98.1250
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.1022 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6655 top1= 84.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9932 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5166 top1= 46.0337

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.1025 top1= 97.3438
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0861 top1= 97.5000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.1010 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6720 top1= 84.1947


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9684 top1= 50.2804


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4929 top1= 46.1438

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.1010 top1= 97.9688
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0815 top1= 97.9688
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.1061 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6740 top1= 84.0645


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9302 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4854 top1= 46.2240

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0949 top1= 97.9688
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0800 top1= 98.2812
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.1014 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6772 top1= 83.5036


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9538 top1= 50.2103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5063 top1= 46.3141

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0988 top1= 97.8125
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0803 top1= 98.4375
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.1074 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6792 top1= 83.6739


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9327 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4642 top1= 46.2340

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0971 top1= 97.6562
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0889 top1= 97.5000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.1027 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6673 top1= 84.5052


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9301 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4280 top1= 46.0136

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.1039 top1= 97.0312
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0862 top1= 98.4375
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.1101 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6826 top1= 83.1831


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9356 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3968 top1= 46.2340

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0981 top1= 97.1875
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0909 top1= 97.8125
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.1173 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6982 top1= 81.3702


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9139 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2361 top1= 46.2440

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0990 top1= 97.1875
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0897 top1= 97.3438
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.1033 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7278 top1= 80.7392


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8848 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2540 top1= 45.5329

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.1302 top1= 96.2500
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.1037 top1= 97.1875
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.1251 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7158 top1= 82.0212


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9613 top1= 50.2103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3487 top1= 45.4928

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.1461 top1= 95.1562
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.1343 top1= 95.9375
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.1157 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7149 top1= 84.7256


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9183 top1= 49.1787


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2653 top1= 46.2640

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.1380 top1= 95.6250
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.1001 top1= 96.7188
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.1437 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6869 top1= 83.2332


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9350 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4350 top1= 46.0537

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.1031 top1= 96.5625
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0840 top1= 97.1875
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0913 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6878 top1= 84.9259


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9038 top1= 50.4407


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3249 top1= 46.3742

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0904 top1= 97.9688
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0824 top1= 97.8125
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0862 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6893 top1= 84.1847


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9222 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3242 top1= 46.3241

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0983 top1= 97.5000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0816 top1= 98.1250
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0996 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6877 top1= 83.6739


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9414 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2352 top1= 46.2941

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0929 top1= 98.1250
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0795 top1= 98.1250
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0938 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6863 top1= 83.8442


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9358 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1869 top1= 46.3341

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0962 top1= 97.8125
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0810 top1= 97.8125
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0950 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6940 top1= 83.3033


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9877 top1= 50.2804


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2159 top1= 45.8333

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.1104 top1= 96.8750
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0918 top1= 97.8125
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0988 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6967 top1= 82.9627


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0157 top1= 50.1703


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3980 top1= 45.5228

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.1225 top1= 95.6250
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.1127 top1= 96.7188
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.1408 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6877 top1= 84.8257


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9329 top1= 50.2103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9848 top1= 46.3642

