
=== 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 ByzantineWorker(index=10)
=> Add worker ByzantineWorker(index=11)

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7fbc148a2b80>

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: 1.0004 top1= 64.0625
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2635 top1= 91.8750
[E 1B30 |  11904/60000 ( 20%) ] Loss: 0.4897 top1= 85.3125
[E 1B40 |  15744/60000 ( 26%) ] Loss: 0.2760 top1= 90.6250
[E 1B50 |  19584/60000 ( 33%) ] Loss: 0.1862 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7174 top1= 84.0044


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2822 top1= 49.7796


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7539 top1= 45.5429

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.1722 top1= 94.3750
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.1679 top1= 95.0000
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1224 top1= 96.2500
[E 2B30 |  11904/60000 ( 20%) ] Loss: 0.1503 top1= 95.3125
[E 2B40 |  15744/60000 ( 26%) ] Loss: 0.1272 top1= 95.3125
[E 2B50 |  19584/60000 ( 33%) ] Loss: 0.0768 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5960 top1= 86.0577


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1854 top1= 50.3405


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7606 top1= 46.1939

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.0938 top1= 96.5625
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.0888 top1= 96.5625
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0652 top1= 98.4375
[E 3B30 |  11904/60000 ( 20%) ] Loss: 0.0989 top1= 96.5625
[E 3B40 |  15744/60000 ( 26%) ] Loss: 0.0670 top1= 97.5000
[E 3B50 |  19584/60000 ( 33%) ] Loss: 0.0370 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4896 top1= 87.5401


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4473 top1= 50.5308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0952 top1= 46.3442

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0561 top1= 99.0625
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0491 top1= 98.4375
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0273 top1=100.0000
[E 4B30 |  11904/60000 ( 20%) ] Loss: 0.0467 top1= 98.4375
[E 4B40 |  15744/60000 ( 26%) ] Loss: 0.0406 top1= 98.7500
[E 4B50 |  19584/60000 ( 33%) ] Loss: 0.0225 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3963 top1= 89.6735


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7668 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3562 top1= 47.0052

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0291 top1= 99.3750
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0410 top1= 98.4375
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0176 top1= 99.6875
[E 5B30 |  11904/60000 ( 20%) ] Loss: 0.0240 top1= 99.6875
[E 5B40 |  15744/60000 ( 26%) ] Loss: 0.0219 top1= 99.6875
[E 5B50 |  19584/60000 ( 33%) ] Loss: 0.0185 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3495 top1= 90.2644


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9765 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3821 top1= 47.1554

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0175 top1= 99.3750
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0236 top1= 99.3750
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0074 top1=100.0000
[E 6B30 |  11904/60000 ( 20%) ] Loss: 0.0131 top1=100.0000
[E 6B40 |  15744/60000 ( 26%) ] Loss: 0.0151 top1= 99.3750
[E 6B50 |  19584/60000 ( 33%) ] Loss: 0.0096 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3361 top1= 90.2043


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9509 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6057 top1= 47.0453

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0077 top1= 99.6875
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0095 top1= 99.6875
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0055 top1=100.0000
[E 7B30 |  11904/60000 ( 20%) ] Loss: 0.0181 top1= 99.3750
[E 7B40 |  15744/60000 ( 26%) ] Loss: 0.0100 top1= 99.6875
[E 7B50 |  19584/60000 ( 33%) ] Loss: 0.0080 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3105 top1= 90.9956


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8259 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8857 top1= 47.1454

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0077 top1=100.0000
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0107 top1= 99.6875
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0090 top1=100.0000
[E 8B30 |  11904/60000 ( 20%) ] Loss: 0.0048 top1=100.0000
[E 8B40 |  15744/60000 ( 26%) ] Loss: 0.0050 top1=100.0000
[E 8B50 |  19584/60000 ( 33%) ] Loss: 0.0059 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2939 top1= 91.0557


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2136 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7972 top1= 47.2055

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0101 top1= 99.6875
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0039 top1=100.0000
[E 9B30 |  11904/60000 ( 20%) ] Loss: 0.0029 top1=100.0000
[E 9B40 |  15744/60000 ( 26%) ] Loss: 0.0051 top1=100.0000
[E 9B50 |  19584/60000 ( 33%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2920 top1= 91.0056


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4513 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8640 top1= 47.2756

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0026 top1=100.0000
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0024 top1=100.0000
[E10B30 |  11904/60000 ( 20%) ] Loss: 0.0132 top1= 99.6875
[E10B40 |  15744/60000 ( 26%) ] Loss: 0.0026 top1=100.0000
[E10B50 |  19584/60000 ( 33%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2956 top1= 90.4748


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6983 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6409 top1= 47.4259

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0015 top1=100.0000
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E11B30 |  11904/60000 ( 20%) ] Loss: 0.0028 top1=100.0000
[E11B40 |  15744/60000 ( 26%) ] Loss: 0.0027 top1=100.0000
[E11B50 |  19584/60000 ( 33%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3218 top1= 89.3029


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9208 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6745 top1= 47.2456

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0015 top1=100.0000
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0010 top1=100.0000
[E12B30 |  11904/60000 ( 20%) ] Loss: 0.0027 top1=100.0000
[E12B40 |  15744/60000 ( 26%) ] Loss: 0.0010 top1=100.0000
[E12B50 |  19584/60000 ( 33%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3178 top1= 89.4932


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0813 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7553 top1= 47.3658

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0012 top1=100.0000
[E13B30 |  11904/60000 ( 20%) ] Loss: 0.0012 top1=100.0000
[E13B40 |  15744/60000 ( 26%) ] Loss: 0.0007 top1=100.0000
[E13B50 |  19584/60000 ( 33%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2982 top1= 90.0641


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2130 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0020 top1= 47.4559

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0007 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000
[E14B30 |  11904/60000 ( 20%) ] Loss: 0.0011 top1=100.0000
[E14B40 |  15744/60000 ( 26%) ] Loss: 0.0006 top1=100.0000
[E14B50 |  19584/60000 ( 33%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2953 top1= 90.0541


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3226 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1537 top1= 47.4960

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0006 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000
[E15B30 |  11904/60000 ( 20%) ] Loss: 0.0009 top1=100.0000
[E15B40 |  15744/60000 ( 26%) ] Loss: 0.0006 top1=100.0000
[E15B50 |  19584/60000 ( 33%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2943 top1= 90.0841


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4201 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2758 top1= 47.4960

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000
[E16B30 |  11904/60000 ( 20%) ] Loss: 0.0008 top1=100.0000
[E16B40 |  15744/60000 ( 26%) ] Loss: 0.0006 top1=100.0000
[E16B50 |  19584/60000 ( 33%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2949 top1= 90.0741


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5051 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3675 top1= 47.4659

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0004 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0004 top1=100.0000
[E17B30 |  11904/60000 ( 20%) ] Loss: 0.0007 top1=100.0000
[E17B40 |  15744/60000 ( 26%) ] Loss: 0.0005 top1=100.0000
[E17B50 |  19584/60000 ( 33%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2962 top1= 90.1142


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5837 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4411 top1= 47.4760

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0004 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0004 top1=100.0000
[E18B30 |  11904/60000 ( 20%) ] Loss: 0.0006 top1=100.0000
[E18B40 |  15744/60000 ( 26%) ] Loss: 0.0004 top1=100.0000
[E18B50 |  19584/60000 ( 33%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2975 top1= 90.0741


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.6563 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5054 top1= 47.4659

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0003 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0004 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0003 top1=100.0000
[E19B30 |  11904/60000 ( 20%) ] Loss: 0.0005 top1=100.0000
[E19B40 |  15744/60000 ( 26%) ] Loss: 0.0004 top1=100.0000
[E19B50 |  19584/60000 ( 33%) ] Loss: 0.0004 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2984 top1= 90.0641


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7229 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5653 top1= 47.4659

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0003 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0003 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0003 top1=100.0000
[E20B30 |  11904/60000 ( 20%) ] Loss: 0.0005 top1=100.0000
[E20B40 |  15744/60000 ( 26%) ] Loss: 0.0004 top1=100.0000
[E20B50 |  19584/60000 ( 33%) ] Loss: 0.0003 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2993 top1= 90.0240


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7850 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6209 top1= 47.4659

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0003 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0003 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0003 top1=100.0000
[E21B30 |  11904/60000 ( 20%) ] Loss: 0.0004 top1=100.0000
[E21B40 |  15744/60000 ( 26%) ] Loss: 0.0003 top1=100.0000
[E21B50 |  19584/60000 ( 33%) ] Loss: 0.0003 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3001 top1= 89.9539


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8432 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6722 top1= 47.4659

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0003 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0003 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0003 top1=100.0000
[E22B30 |  11904/60000 ( 20%) ] Loss: 0.0004 top1=100.0000
[E22B40 |  15744/60000 ( 26%) ] Loss: 0.0003 top1=100.0000
[E22B50 |  19584/60000 ( 33%) ] Loss: 0.0003 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3007 top1= 89.9339


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8969 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7204 top1= 47.4659

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0002 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0003 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0002 top1=100.0000
[E23B30 |  11904/60000 ( 20%) ] Loss: 0.0004 top1=100.0000
[E23B40 |  15744/60000 ( 26%) ] Loss: 0.0003 top1=100.0000
[E23B50 |  19584/60000 ( 33%) ] Loss: 0.0003 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3015 top1= 89.9439


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9501 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7647 top1= 47.4659

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0002 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0002 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0002 top1=100.0000
[E24B30 |  11904/60000 ( 20%) ] Loss: 0.0003 top1=100.0000
[E24B40 |  15744/60000 ( 26%) ] Loss: 0.0003 top1=100.0000
[E24B50 |  19584/60000 ( 33%) ] Loss: 0.0002 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3020 top1= 89.9339


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9964 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8068 top1= 47.4659

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0002 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0002 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0002 top1=100.0000
[E25B30 |  11904/60000 ( 20%) ] Loss: 0.0003 top1=100.0000
[E25B40 |  15744/60000 ( 26%) ] Loss: 0.0002 top1=100.0000
[E25B50 |  19584/60000 ( 33%) ] Loss: 0.0002 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3026 top1= 89.9239


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0425 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8470 top1= 47.4659

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0002 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0002 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0002 top1=100.0000
[E26B30 |  11904/60000 ( 20%) ] Loss: 0.0003 top1=100.0000
[E26B40 |  15744/60000 ( 26%) ] Loss: 0.0002 top1=100.0000
[E26B50 |  19584/60000 ( 33%) ] Loss: 0.0002 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3030 top1= 89.9339


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0842 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8849 top1= 47.4760

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0002 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0002 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0002 top1=100.0000
[E27B30 |  11904/60000 ( 20%) ] Loss: 0.0003 top1=100.0000
[E27B40 |  15744/60000 ( 26%) ] Loss: 0.0002 top1=100.0000
[E27B50 |  19584/60000 ( 33%) ] Loss: 0.0002 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3035 top1= 89.9239


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1266 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9213 top1= 47.4760

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0002 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0002 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0002 top1=100.0000
[E28B30 |  11904/60000 ( 20%) ] Loss: 0.0003 top1=100.0000
[E28B40 |  15744/60000 ( 26%) ] Loss: 0.0002 top1=100.0000
[E28B50 |  19584/60000 ( 33%) ] Loss: 0.0002 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3041 top1= 89.9339


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1656 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9553 top1= 47.4760

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0002 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0002 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0002 top1=100.0000
[E29B30 |  11904/60000 ( 20%) ] Loss: 0.0003 top1=100.0000
[E29B40 |  15744/60000 ( 26%) ] Loss: 0.0002 top1=100.0000
[E29B50 |  19584/60000 ( 33%) ] Loss: 0.0002 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3045 top1= 89.9339


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2031 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9894 top1= 47.4760

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0002 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0002 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0002 top1=100.0000
[E30B30 |  11904/60000 ( 20%) ] Loss: 0.0002 top1=100.0000
[E30B40 |  15744/60000 ( 26%) ] Loss: 0.0002 top1=100.0000
[E30B50 |  19584/60000 ( 33%) ] Loss: 0.0002 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3050 top1= 89.9239


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.2393 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0211 top1= 47.4760

