
=== 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 0x7f76c4ac27c0>

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: 1.0175 top1= 63.1250
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.3327 top1= 89.0625
[E 1B30 |  11904/60000 ( 20%) ] Loss: 0.5430 top1= 85.0000
[E 1B40 |  15744/60000 ( 26%) ] Loss: 0.3212 top1= 87.8125
[E 1B50 |  19584/60000 ( 33%) ] Loss: 0.2062 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7102 top1= 85.7171


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7510 top1= 49.7596


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9341 top1= 45.2925

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.1884 top1= 94.0625
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.1758 top1= 95.3125
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1064 top1= 96.8750
[E 2B30 |  11904/60000 ( 20%) ] Loss: 0.1528 top1= 93.7500
[E 2B40 |  15744/60000 ( 26%) ] Loss: 0.1266 top1= 95.0000
[E 2B50 |  19584/60000 ( 33%) ] Loss: 0.0685 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6264 top1= 87.4900


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7907 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6911 top1= 46.3241

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.0929 top1= 97.1875
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.0890 top1= 96.8750
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0655 top1= 98.1250
[E 3B30 |  11904/60000 ( 20%) ] Loss: 0.0911 top1= 96.2500
[E 3B40 |  15744/60000 ( 26%) ] Loss: 0.0723 top1= 97.5000
[E 3B50 |  19584/60000 ( 33%) ] Loss: 0.0418 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5193 top1= 89.0024


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9051 top1= 50.5108


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9293 top1= 46.6847

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0573 top1= 98.7500
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0540 top1= 97.8125
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0348 top1= 99.6875
[E 4B30 |  11904/60000 ( 20%) ] Loss: 0.0485 top1= 98.1250
[E 4B40 |  15744/60000 ( 26%) ] Loss: 0.0444 top1= 99.3750
[E 4B50 |  19584/60000 ( 33%) ] Loss: 0.0276 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4363 top1= 90.0341


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0564 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0936 top1= 46.9852

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0346 top1= 99.3750
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0391 top1= 99.0625
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0247 top1= 99.6875
[E 5B30 |  11904/60000 ( 20%) ] Loss: 0.0259 top1= 99.6875
[E 5B40 |  15744/60000 ( 26%) ] Loss: 0.0263 top1= 99.3750
[E 5B50 |  19584/60000 ( 33%) ] Loss: 0.0178 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3885 top1= 90.6350


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1436 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0491 top1= 47.0954

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0191 top1= 99.6875
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0217 top1= 99.6875
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0130 top1=100.0000
[E 6B30 |  11904/60000 ( 20%) ] Loss: 0.0204 top1=100.0000
[E 6B40 |  15744/60000 ( 26%) ] Loss: 0.0187 top1= 99.6875
[E 6B50 |  19584/60000 ( 33%) ] Loss: 0.0119 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3627 top1= 90.6350


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1052 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0262 top1= 47.0052

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0122 top1= 99.6875
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0140 top1= 99.6875
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0087 top1=100.0000
[E 7B30 |  11904/60000 ( 20%) ] Loss: 0.0156 top1= 99.6875
[E 7B40 |  15744/60000 ( 26%) ] Loss: 0.0223 top1= 99.3750
[E 7B50 |  19584/60000 ( 33%) ] Loss: 0.0103 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3409 top1= 90.8654


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9402 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0352 top1= 47.0553

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0102 top1=100.0000
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0090 top1=100.0000
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0097 top1=100.0000
[E 8B30 |  11904/60000 ( 20%) ] Loss: 0.0123 top1=100.0000
[E 8B40 |  15744/60000 ( 26%) ] Loss: 0.0082 top1=100.0000
[E 8B50 |  19584/60000 ( 33%) ] Loss: 0.0112 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3270 top1= 90.7853


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7829 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0506 top1= 46.9651

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0095 top1=100.0000
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0089 top1=100.0000
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0113 top1=100.0000
[E 9B30 |  11904/60000 ( 20%) ] Loss: 0.0147 top1= 99.6875
[E 9B40 |  15744/60000 ( 26%) ] Loss: 0.0090 top1=100.0000
[E 9B50 |  19584/60000 ( 33%) ] Loss: 0.0052 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3097 top1= 91.1258


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7356 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8773 top1= 47.1354

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0064 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0129 top1=100.0000
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0145 top1=100.0000
[E10B30 |  11904/60000 ( 20%) ] Loss: 0.0105 top1=100.0000
[E10B40 |  15744/60000 ( 26%) ] Loss: 0.0086 top1=100.0000
[E10B50 |  19584/60000 ( 33%) ] Loss: 0.0071 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2954 top1= 91.4864


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5845 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6872 top1= 47.2656

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0075 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0105 top1=100.0000
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0056 top1=100.0000
[E11B30 |  11904/60000 ( 20%) ] Loss: 0.0104 top1=100.0000
[E11B40 |  15744/60000 ( 26%) ] Loss: 0.0111 top1=100.0000
[E11B50 |  19584/60000 ( 33%) ] Loss: 0.0072 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2938 top1= 91.3462


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4073 top1= 50.7712


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4614 top1= 47.1655

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0069 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0063 top1=100.0000
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0053 top1=100.0000
[E12B30 |  11904/60000 ( 20%) ] Loss: 0.0063 top1=100.0000
[E12B40 |  15744/60000 ( 26%) ] Loss: 0.0143 top1= 99.6875
[E12B50 |  19584/60000 ( 33%) ] Loss: 0.0062 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2949 top1= 91.1358


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2362 top1= 50.9115


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4688 top1= 47.3157

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0058 top1=100.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0054 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0058 top1=100.0000
[E13B30 |  11904/60000 ( 20%) ] Loss: 0.0099 top1= 99.6875
[E13B40 |  15744/60000 ( 26%) ] Loss: 0.0146 top1=100.0000
[E13B50 |  19584/60000 ( 33%) ] Loss: 0.0093 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2918 top1= 90.8854


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1303 top1= 51.2119


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4111 top1= 47.3057

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0057 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0068 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0073 top1=100.0000
[E14B30 |  11904/60000 ( 20%) ] Loss: 0.0079 top1=100.0000
[E14B40 |  15744/60000 ( 26%) ] Loss: 0.0073 top1=100.0000
[E14B50 |  19584/60000 ( 33%) ] Loss: 0.0061 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2924 top1= 90.7652


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9932 top1= 51.4824


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2197 top1= 47.2957

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0060 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0064 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0047 top1=100.0000
[E15B30 |  11904/60000 ( 20%) ] Loss: 0.0133 top1=100.0000
[E15B40 |  15744/60000 ( 26%) ] Loss: 0.0173 top1= 99.6875
[E15B50 |  19584/60000 ( 33%) ] Loss: 0.0054 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2871 top1= 90.9455


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8922 top1= 51.9030


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1033 top1= 47.2957

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0058 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0109 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0066 top1=100.0000
[E16B30 |  11904/60000 ( 20%) ] Loss: 0.0091 top1=100.0000
[E16B40 |  15744/60000 ( 26%) ] Loss: 0.0067 top1=100.0000
[E16B50 |  19584/60000 ( 33%) ] Loss: 0.0091 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2860 top1= 91.0457


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7925 top1= 52.3738


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0367 top1= 47.5661

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0070 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0097 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0072 top1=100.0000
[E17B30 |  11904/60000 ( 20%) ] Loss: 0.0082 top1=100.0000
[E17B40 |  15744/60000 ( 26%) ] Loss: 0.0128 top1= 99.6875
[E17B50 |  19584/60000 ( 33%) ] Loss: 0.0052 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2820 top1= 90.9255


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7020 top1= 52.9247


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0245 top1= 48.1571

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0049 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0073 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0058 top1=100.0000
[E18B30 |  11904/60000 ( 20%) ] Loss: 0.0055 top1=100.0000
[E18B40 |  15744/60000 ( 26%) ] Loss: 0.0069 top1=100.0000
[E18B50 |  19584/60000 ( 33%) ] Loss: 0.0046 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2742 top1= 91.1158


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6181 top1= 53.5256


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9139 top1= 48.6679

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0045 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0060 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0056 top1=100.0000
[E19B30 |  11904/60000 ( 20%) ] Loss: 0.0062 top1=100.0000
[E19B40 |  15744/60000 ( 26%) ] Loss: 0.0062 top1=100.0000
[E19B50 |  19584/60000 ( 33%) ] Loss: 0.0050 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2702 top1= 91.2961


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5588 top1= 54.0465


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8701 top1= 48.7179

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0047 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0055 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0044 top1=100.0000
[E20B30 |  11904/60000 ( 20%) ] Loss: 0.0076 top1=100.0000
[E20B40 |  15744/60000 ( 26%) ] Loss: 0.0082 top1=100.0000
[E20B50 |  19584/60000 ( 33%) ] Loss: 0.0052 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2609 top1= 91.6466


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5061 top1= 54.6875


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6624 top1= 49.5593

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0048 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0054 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0047 top1=100.0000
[E21B30 |  11904/60000 ( 20%) ] Loss: 0.0088 top1=100.0000
[E21B40 |  15744/60000 ( 26%) ] Loss: 0.0069 top1=100.0000
[E21B50 |  19584/60000 ( 33%) ] Loss: 0.0045 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2576 top1= 91.7869


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4541 top1= 55.3385


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6296 top1= 49.7196

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0049 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0052 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0046 top1=100.0000
[E22B30 |  11904/60000 ( 20%) ] Loss: 0.0068 top1=100.0000
[E22B40 |  15744/60000 ( 26%) ] Loss: 0.0068 top1=100.0000
[E22B50 |  19584/60000 ( 33%) ] Loss: 0.0044 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2509 top1= 91.9371


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3886 top1= 55.9696


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5537 top1= 50.0501

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0051 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0056 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0049 top1=100.0000
[E23B30 |  11904/60000 ( 20%) ] Loss: 0.0066 top1=100.0000
[E23B40 |  15744/60000 ( 26%) ] Loss: 0.0061 top1=100.0000
[E23B50 |  19584/60000 ( 33%) ] Loss: 0.0047 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2440 top1= 92.3277


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3408 top1= 56.4002


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5178 top1= 50.5008

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0048 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0075 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0053 top1=100.0000
[E24B30 |  11904/60000 ( 20%) ] Loss: 0.0065 top1=100.0000
[E24B40 |  15744/60000 ( 26%) ] Loss: 0.0060 top1=100.0000
[E24B50 |  19584/60000 ( 33%) ] Loss: 0.0048 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2432 top1= 92.3678


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3062 top1= 56.7508


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5238 top1= 50.4708

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0048 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0066 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0069 top1=100.0000
[E25B30 |  11904/60000 ( 20%) ] Loss: 0.0064 top1=100.0000
[E25B40 |  15744/60000 ( 26%) ] Loss: 0.0056 top1=100.0000
[E25B50 |  19584/60000 ( 33%) ] Loss: 0.0052 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2408 top1= 92.4379


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2655 top1= 57.2917


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4571 top1= 50.9315

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0047 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0055 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0048 top1=100.0000
[E26B30 |  11904/60000 ( 20%) ] Loss: 0.0069 top1=100.0000
[E26B40 |  15744/60000 ( 26%) ] Loss: 0.0056 top1=100.0000
[E26B50 |  19584/60000 ( 33%) ] Loss: 0.0051 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2378 top1= 92.5280


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2310 top1= 57.6222


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4455 top1= 51.1218

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0047 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0060 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0048 top1=100.0000
[E27B30 |  11904/60000 ( 20%) ] Loss: 0.0079 top1=100.0000
[E27B40 |  15744/60000 ( 26%) ] Loss: 0.0058 top1=100.0000
[E27B50 |  19584/60000 ( 33%) ] Loss: 0.0047 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2327 top1= 92.6783


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2024 top1= 58.0529


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3572 top1= 51.8029

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0049 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0056 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0052 top1=100.0000
[E28B30 |  11904/60000 ( 20%) ] Loss: 0.0079 top1=100.0000
[E28B40 |  15744/60000 ( 26%) ] Loss: 0.0067 top1=100.0000
[E28B50 |  19584/60000 ( 33%) ] Loss: 0.0049 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2311 top1= 92.7684


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1684 top1= 58.3433


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2378 top1= 52.4840

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0046 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0048 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0051 top1=100.0000
[E29B30 |  11904/60000 ( 20%) ] Loss: 0.0076 top1=100.0000
[E29B40 |  15744/60000 ( 26%) ] Loss: 0.0055 top1=100.0000
[E29B50 |  19584/60000 ( 33%) ] Loss: 0.0049 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2297 top1= 92.7985


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1291 top1= 58.6839


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2594 top1= 52.4339

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0043 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0047 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0047 top1=100.0000
[E30B30 |  11904/60000 ( 20%) ] Loss: 0.0070 top1=100.0000
[E30B40 |  15744/60000 ( 26%) ] Loss: 0.0066 top1=100.0000
[E30B50 |  19584/60000 ( 33%) ] Loss: 0.0048 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2282 top1= 92.8686


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1131 top1= 58.9944


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2149 top1= 52.8045

