
=== 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 0x7f004450e7f0>

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: 1.3824 top1= 51.8750
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.8261 top1= 75.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3690 top1= 77.5341


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0925 top1= 48.1571


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9340 top1= 42.3578

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.4904 top1= 85.6250
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.4279 top1= 87.1875
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.2254 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0357 top1= 81.2400


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7869 top1= 49.4191


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6090 top1= 44.3810

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.2823 top1= 91.5625
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.3174 top1= 90.6250
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.2043 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9099 top1= 83.8542


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0786 top1= 49.6695


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9193 top1= 44.6514

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.2410 top1= 92.5000
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.2244 top1= 92.5000
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.1710 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8562 top1= 84.3650


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2838 top1= 49.7396


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1387 top1= 45.3526

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.1816 top1= 95.9375
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.1800 top1= 93.7500
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.1385 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8126 top1= 84.1847


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2689 top1= 49.9700


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1943 top1= 45.5329

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.1538 top1= 95.0000
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.1466 top1= 94.0625
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.1107 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7760 top1= 85.3466


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4085 top1= 50.1402


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2401 top1= 45.7432

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.1500 top1= 95.9375
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.1324 top1= 95.0000
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.1169 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7405 top1= 85.4167


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5908 top1= 50.1603


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5346 top1= 45.7131

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.1271 top1= 96.2500
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.1184 top1= 95.0000
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0977 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7324 top1= 85.4067


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5913 top1= 50.2304


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4031 top1= 45.9535

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.1119 top1= 96.8750
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.1204 top1= 96.2500
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0720 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7153 top1= 85.8774


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5659 top1= 50.1803


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4238 top1= 46.1338

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.1055 top1= 96.2500
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0975 top1= 96.5625
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0686 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7098 top1= 85.7873


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6179 top1= 50.3405


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4790 top1= 46.1739

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0896 top1= 96.8750
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0876 top1= 96.5625
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0828 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6934 top1= 86.3181


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6466 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5294 top1= 46.2841

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0867 top1= 96.8750
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0773 top1= 97.8125
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0626 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6680 top1= 86.9992


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6452 top1= 50.2804


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6118 top1= 46.3842

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0692 top1= 97.5000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0776 top1= 97.1875
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0588 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6580 top1= 86.5284


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8249 top1= 50.4307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8010 top1= 46.3542

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0689 top1= 97.5000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0575 top1= 97.8125
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0521 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6404 top1= 87.3097


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8323 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7122 top1= 46.4543

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0673 top1= 98.1250
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0653 top1= 98.1250
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0449 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6446 top1= 87.2196


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8482 top1= 50.4407


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7333 top1= 46.5645

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0629 top1= 98.1250
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0617 top1= 98.4375
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0326 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6321 top1= 87.2696


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9269 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6896 top1= 46.5946

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0490 top1= 98.7500
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0534 top1= 98.4375
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0357 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6267 top1= 87.3598


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8138 top1= 50.4307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7836 top1= 46.6647

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0461 top1= 99.3750
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0439 top1= 98.7500
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0406 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6227 top1= 87.7905


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8671 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8660 top1= 46.6546

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0527 top1= 98.4375
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0404 top1= 99.0625
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0267 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6016 top1= 87.9708


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0181 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0576 top1= 46.8149

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0415 top1= 98.7500
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0381 top1= 99.3750
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0248 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5972 top1= 88.0709


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0463 top1= 50.4307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0552 top1= 46.8149

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0498 top1= 98.4375
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0413 top1= 99.0625
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0213 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5957 top1= 87.9908


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1126 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0086 top1= 46.8550

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0405 top1= 98.4375
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0340 top1= 99.0625
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0191 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5871 top1= 88.2612


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1172 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9908 top1= 47.0052

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0380 top1= 99.0625
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0361 top1= 98.7500
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0192 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5883 top1= 87.9607


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0568 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0166 top1= 46.9451

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0401 top1= 99.0625
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0290 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0204 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5821 top1= 88.0809


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0372 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0549 top1= 47.0152

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0323 top1= 99.0625
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0272 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0138 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5613 top1= 88.3413


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1703 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2381 top1= 47.0954

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0223 top1= 99.3750
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0187 top1= 99.6875
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0137 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5639 top1= 87.8405


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2081 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2947 top1= 46.9952

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0310 top1= 99.3750
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0240 top1= 99.3750
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0150 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5518 top1= 88.8922


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1828 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1767 top1= 47.1254

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0223 top1= 99.3750
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0238 top1= 99.0625
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0116 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5473 top1= 88.6919


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2208 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1492 top1= 47.2356

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0265 top1= 99.3750
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0216 top1= 99.0625
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0129 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5579 top1= 88.4515


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2955 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1963 top1= 47.1955

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0244 top1= 99.6875
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0166 top1= 99.6875
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0113 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5403 top1= 88.9523


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1529 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2057 top1= 47.1855

