
=== 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 0x7f1b0c3119d0>

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: 1.0780 top1= 65.0000
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2790 top1= 91.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5743 top1= 83.2432


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4440 top1= 48.9884


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3471 top1= 43.9503

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3399 top1= 91.2500
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.3292 top1= 89.3750
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1810 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4618 top1= 87.2897


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9788 top1= 53.7360


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0068 top1= 47.9267

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1743 top1= 94.3750
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1793 top1= 94.3750
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1251 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4127 top1= 87.9107


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7981 top1= 55.9896


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9808 top1= 49.6494

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1452 top1= 95.6250
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.1281 top1= 95.6250
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0974 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3887 top1= 88.3914


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7261 top1= 56.6807


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8798 top1= 51.4123

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.1143 top1= 97.1875
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0969 top1= 96.5625
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0764 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3769 top1= 88.5216


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7201 top1= 56.8510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8636 top1= 51.5725

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.1037 top1= 97.1875
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0801 top1= 98.1250
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0648 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3690 top1= 88.8321


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6747 top1= 57.3017


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8712 top1= 52.1134

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0898 top1= 97.8125
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0700 top1= 98.1250
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0594 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3662 top1= 88.9824


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7049 top1= 57.0312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8265 top1= 52.7444

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0828 top1= 98.1250
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0697 top1= 98.1250
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0521 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3663 top1= 88.9623


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7162 top1= 56.9211


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8335 top1= 52.5240

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0774 top1= 98.7500
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0662 top1= 98.7500
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0521 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3638 top1= 89.1627


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7050 top1= 56.6607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8145 top1= 52.4539

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0770 top1= 98.4375
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0641 top1= 98.7500
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0495 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3732 top1= 88.8522


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6986 top1= 56.6907


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8594 top1= 52.0433

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0738 top1= 98.7500
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0655 top1= 98.4375
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0585 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3868 top1= 88.4415


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7731 top1= 55.9796


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9114 top1= 51.2620

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0766 top1= 98.4375
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0658 top1= 99.0625
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0517 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3931 top1= 88.4415


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8312 top1= 55.2584


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8352 top1= 51.8229

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0726 top1= 98.7500
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0759 top1= 98.4375
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0604 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4052 top1= 88.0409


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8375 top1= 54.8678


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7806 top1= 51.6326

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0790 top1= 98.4375
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0866 top1= 98.1250
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0606 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4134 top1= 88.1711


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8811 top1= 54.3970


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7354 top1= 51.6827

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0686 top1= 98.7500
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0808 top1= 98.1250
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0626 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4240 top1= 88.1811


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9359 top1= 53.9363


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8921 top1= 50.1903

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0779 top1= 97.8125
[E16B10 |   4224/60000 (  7%) ] Loss: 0.1018 top1= 97.1875
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0736 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4343 top1= 88.3514


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9273 top1= 53.8562


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0787 top1= 48.2973

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.1050 top1= 96.5625
[E17B10 |   4224/60000 (  7%) ] Loss: 0.1196 top1= 96.5625
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0764 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4685 top1= 86.7788


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8941 top1= 53.6258


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1162 top1= 46.4643

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.1462 top1= 94.6875
[E18B10 |   4224/60000 (  7%) ] Loss: 0.1432 top1= 94.6875
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.1050 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4757 top1= 86.4683


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8704 top1= 53.4956


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1541 top1= 47.4058

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.1040 top1= 97.5000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.1178 top1= 96.2500
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.1165 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5020 top1= 85.8273


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8918 top1= 52.8546


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2160 top1= 45.9836

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.1479 top1= 95.3125
[E20B10 |   4224/60000 (  7%) ] Loss: 0.1234 top1= 95.3125
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.1323 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5174 top1= 85.3966


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8701 top1= 52.6743


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2136 top1= 45.7031

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.1292 top1= 96.5625
[E21B10 |   4224/60000 (  7%) ] Loss: 0.1215 top1= 95.9375
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.1041 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5111 top1= 85.5669


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8578 top1= 52.5841


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1430 top1= 46.4643

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.1202 top1= 96.2500
[E22B10 |   4224/60000 (  7%) ] Loss: 0.1304 top1= 95.9375
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.1125 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4918 top1= 86.8590


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8538 top1= 52.4840


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0720 top1= 46.8349

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.1127 top1= 96.8750
[E23B10 |   4224/60000 (  7%) ] Loss: 0.1356 top1= 96.5625
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0947 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5004 top1= 86.6787


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8489 top1= 52.3738


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0849 top1= 46.3141

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.1222 top1= 96.8750
[E24B10 |   4224/60000 (  7%) ] Loss: 0.1266 top1= 95.9375
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0969 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4882 top1= 87.5401


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8485 top1= 52.1935


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0935 top1= 46.0837

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.1147 top1= 96.5625
[E25B10 |   4224/60000 (  7%) ] Loss: 0.1351 top1= 95.6250
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.1057 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5184 top1= 86.0176


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8165 top1= 52.2636


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2657 top1= 44.5312

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.1445 top1= 95.6250
[E26B10 |   4224/60000 (  7%) ] Loss: 0.1660 top1= 94.3750
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.1199 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5191 top1= 85.8874


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8336 top1= 52.0633


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2002 top1= 45.8033

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.1242 top1= 96.5625
[E27B10 |   4224/60000 (  7%) ] Loss: 0.1320 top1= 96.2500
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.1612 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5346 top1= 85.6170


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8043 top1= 51.9231


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2113 top1= 45.3125

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.1354 top1= 95.6250
[E28B10 |   4224/60000 (  7%) ] Loss: 0.1310 top1= 95.9375
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.1399 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5389 top1= 85.4467


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8319 top1= 52.0633


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1002 top1= 46.3141

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.1210 top1= 97.1875
[E29B10 |   4224/60000 (  7%) ] Loss: 0.1217 top1= 96.2500
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.1032 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5230 top1= 86.1579


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8114 top1= 51.5925


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1416 top1= 46.1538

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.1168 top1= 96.2500
[E30B10 |   4224/60000 (  7%) ] Loss: 0.1218 top1= 96.5625
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.1093 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5263 top1= 85.9575


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8304 top1= 51.3021


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2157 top1= 45.4327

