
=== 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.Dumbbell object at 0x7fa87572c730>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.3054 top1= 10.0000

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([0, 0, 0, 0, 0], device='cuda:0')
Worker 1 has targets: tensor([1, 1, 1, 1, 1], device='cuda:0')
Worker 2 has targets: tensor([1, 2, 2, 2, 2], device='cuda:0')
Worker 3 has targets: tensor([2, 3, 3, 3, 3], device='cuda:0')
Worker 4 has targets: tensor([3, 4, 4, 4, 4], device='cuda:0')
Worker 5 has targets: tensor([4, 5, 5, 5, 5], device='cuda:0')
Worker 6 has targets: tensor([6, 6, 6, 6, 6], device='cuda:0')
Worker 7 has targets: tensor([7, 7, 7, 7, 7], device='cuda:0')
Worker 8 has targets: tensor([7, 8, 8, 8, 8], device='cuda:0')
Worker 9 has targets: tensor([8, 9, 9, 9, 9], device='cuda:0')
Worker 10 has targets: tensor([0, 0, 0, 0, 0], device='cuda:0')
Worker 11 has targets: tensor([1, 1, 1, 1, 1], device='cuda:0')


[E 1B10 |   4224/60000 (  7%) ] Loss: 0.2803 top1= 92.8125
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.0960 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.7218 top1= 38.0008


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9435 top1= 45.9135


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1934 top1= 44.3009

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.1630 top1= 96.5625
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.0496 top1= 99.0625
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.0733 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4324 top1= 52.0933


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3300 top1= 48.0068


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5399 top1= 45.0821

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1297 top1= 96.8750
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.0369 top1= 98.7500
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0246 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9466 top1= 67.3778


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3099 top1= 48.0168


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0893 top1= 50.6210

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0594 top1= 98.1250
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0429 top1= 99.0625
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0288 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7531 top1= 74.0385


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7304 top1= 48.8081


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9367 top1= 53.0549

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0458 top1= 98.7500
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0233 top1= 99.0625
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0129 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7017 top1= 75.9415


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6832 top1= 49.2488


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7235 top1= 57.1615

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0297 top1= 99.0625
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0346 top1= 99.0625
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0152 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6574 top1= 77.9046


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5143 top1= 50.1202


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6389 top1= 59.3349

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0252 top1= 99.0625
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0164 top1= 99.3750
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0106 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6046 top1= 80.0381


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2777 top1= 50.7612


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5349 top1= 61.9391

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0213 top1= 99.0625
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0148 top1= 99.6875
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0191 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5814 top1= 80.8093


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1625 top1= 52.4239


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4927 top1= 63.6819

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0391 top1= 99.0625
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0157 top1= 99.6875
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0173 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5680 top1= 81.3001


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3579 top1= 51.9531


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5668 top1= 62.8706

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0211 top1= 99.3750
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0577 top1= 99.0625
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0106 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6875 top1= 76.9932


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7030 top1= 50.8013


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2718 top1= 68.6799

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0285 top1= 98.4375
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0407 top1= 98.4375
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0459 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5345 top1= 83.1530


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3203 top1= 56.1599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0747 top1= 53.7360

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0428 top1= 98.7500
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0186 top1= 99.6875
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0108 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6186 top1= 79.5172


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0929 top1= 51.2019


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6666 top1= 63.1711

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0221 top1= 99.6875
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0035 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0081 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6236 top1= 80.0280


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6330 top1= 54.2268


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2606 top1= 69.8618

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0350 top1= 99.0625
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0055 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0370 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5177 top1= 83.2532


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6239 top1= 52.8045


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3997 top1= 67.7484

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0135 top1= 99.0625
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0095 top1= 99.6875
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0138 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4984 top1= 84.3650


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5557 top1= 54.6975


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3588 top1= 69.5513

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0297 top1= 99.6875
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0043 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0039 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4963 top1= 84.4151


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0897 top1= 56.7708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7110 top1= 65.5549

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0133 top1= 99.6875
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0047 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0038 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4850 top1= 84.4151


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3329 top1= 56.1899


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5699 top1= 66.4563

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0038 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0028 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4748 top1= 85.3866


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3444 top1= 56.4603


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3873 top1= 71.9251

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0105 top1= 99.6875
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0156 top1= 99.3750
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0173 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4691 top1= 86.0877


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2714 top1= 58.6238


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4141 top1= 68.8602

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0032 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0162 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5710 top1= 83.3834


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8580 top1= 56.2800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2310 top1= 73.5777

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0132 top1= 99.6875
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0017 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5291 top1= 85.0361


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1514 top1= 57.6522


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2400 top1= 74.0084

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0322 top1= 98.7500
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0084 top1= 99.6875
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0039 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7158 top1= 80.3786


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5482 top1= 57.1414


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2849 top1= 74.4792

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0253 top1= 99.3750
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0039 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0191 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6380 top1= 82.1214


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1960 top1= 52.6042


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2295 top1= 74.1286

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0491 top1= 98.7500
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0022 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0193 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5055 top1= 84.9860


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3463 top1= 58.8041


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2608 top1= 74.0986

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0043 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0160 top1= 99.3750
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0155 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4878 top1= 86.1278


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8310 top1= 57.4619


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6737 top1= 69.5212

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0224 top1= 99.3750
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0061 top1= 99.6875
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0047 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4876 top1= 85.9575


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4044 top1= 57.7825


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1812 top1= 74.5994

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0033 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0277 top1= 99.3750
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0036 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8193 top1= 78.6959


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4462 top1= 53.9062


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1545 top1= 76.9732

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0095 top1= 99.3750
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0079 top1= 99.6875
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0035 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6608 top1= 82.4619


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5264 top1= 61.4884


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9727 top1= 78.5357

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0113 top1= 99.3750
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0249 top1= 99.3750
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0067 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5341 top1= 85.6871


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1415 top1= 62.2796


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8737 top1= 79.7977

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0077 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0078 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5371 top1= 85.2764


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2147 top1= 62.2897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0023 top1= 79.1567

Train epoch 31
[E31B0  |    384/60000 (  1%) ] Loss: 0.0078 top1=100.0000
[E31B10 |   4224/60000 (  7%) ] Loss: 0.0162 top1= 99.6875
[E31B20 |   8064/60000 ( 13%) ] Loss: 0.0065 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5403 top1= 84.9459


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0237 top1= 63.3413


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4827 top1= 70.1322

Train epoch 32
[E32B0  |    384/60000 (  1%) ] Loss: 0.0152 top1= 99.3750
[E32B10 |   4224/60000 (  7%) ] Loss: 0.0022 top1=100.0000
[E32B20 |   8064/60000 ( 13%) ] Loss: 0.0323 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5394 top1= 85.5168


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8144 top1= 55.6290


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2867 top1= 73.5877

Train epoch 33
[E33B0  |    384/60000 (  1%) ] Loss: 0.0142 top1= 99.6875
[E33B10 |   4224/60000 (  7%) ] Loss: 0.0018 top1=100.0000
[E33B20 |   8064/60000 ( 13%) ] Loss: 0.0048 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4402 top1= 87.7604


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5246 top1= 59.8558


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6352 top1= 67.6382

Train epoch 34
[E34B0  |    384/60000 (  1%) ] Loss: 0.0036 top1=100.0000
[E34B10 |   4224/60000 (  7%) ] Loss: 0.0238 top1= 99.0625
[E34B20 |   8064/60000 ( 13%) ] Loss: 0.0059 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4428 top1= 88.0208


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3337 top1= 59.6154


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3502 top1= 73.7079

Train epoch 35
[E35B0  |    384/60000 (  1%) ] Loss: 0.0065 top1=100.0000
[E35B10 |   4224/60000 (  7%) ] Loss: 0.0050 top1=100.0000
[E35B20 |   8064/60000 ( 13%) ] Loss: 0.0068 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4672 top1= 87.3698


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4865 top1= 61.9792


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2243 top1= 65.0341

Train epoch 36
[E36B0  |    384/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E36B10 |   4224/60000 (  7%) ] Loss: 0.0018 top1=100.0000
[E36B20 |   8064/60000 ( 13%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4587 top1= 88.0809


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5366 top1= 59.6554


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0918 top1= 75.7111

Train epoch 37
[E37B0  |    384/60000 (  1%) ] Loss: 0.0253 top1= 99.3750
[E37B10 |   4224/60000 (  7%) ] Loss: 0.0110 top1= 99.6875
[E37B20 |   8064/60000 ( 13%) ] Loss: 0.0054 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5055 top1= 86.6286


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3753 top1= 63.1811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2557 top1= 72.3858

Train epoch 38
[E38B0  |    384/60000 (  1%) ] Loss: 0.0083 top1= 99.6875
[E38B10 |   4224/60000 (  7%) ] Loss: 0.0172 top1= 98.7500
[E38B20 |   8064/60000 ( 13%) ] Loss: 0.0085 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4563 top1= 87.5200


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9063 top1= 65.4046


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0898 top1= 75.1502

Train epoch 39
[E39B0  |    384/60000 (  1%) ] Loss: 0.0041 top1= 99.6875
[E39B10 |   4224/60000 (  7%) ] Loss: 0.0014 top1=100.0000
[E39B20 |   8064/60000 ( 13%) ] Loss: 0.0082 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5396 top1= 86.4683


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7685 top1= 66.7167


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4926 top1= 71.9251

Train epoch 40
[E40B0  |    384/60000 (  1%) ] Loss: 0.0328 top1= 98.7500
[E40B10 |   4224/60000 (  7%) ] Loss: 0.0126 top1= 99.6875
[E40B20 |   8064/60000 ( 13%) ] Loss: 0.0296 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4551 top1= 88.0308


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0422 top1= 62.9708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9582 top1= 79.6675

Train epoch 41
[E41B0  |    384/60000 (  1%) ] Loss: 0.0105 top1= 99.3750
[E41B10 |   4224/60000 (  7%) ] Loss: 0.0027 top1=100.0000
[E41B20 |   8064/60000 ( 13%) ] Loss: 0.0147 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4747 top1= 87.9507


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6714 top1= 67.4479


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1895 top1= 76.2119

Train epoch 42
[E42B0  |    384/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E42B10 |   4224/60000 (  7%) ] Loss: 0.0031 top1=100.0000
[E42B20 |   8064/60000 ( 13%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5052 top1= 86.9792


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9920 top1= 63.0909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9678 top1= 79.5773

Train epoch 43
[E43B0  |    384/60000 (  1%) ] Loss: 0.0057 top1= 99.6875
[E43B10 |   4224/60000 (  7%) ] Loss: 0.0030 top1=100.0000
[E43B20 |   8064/60000 ( 13%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5457 top1= 86.7989


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6205 top1= 69.7015


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7534 top1= 82.6222

Train epoch 44
[E44B0  |    384/60000 (  1%) ] Loss: 0.1135 top1= 99.0625
[E44B10 |   4224/60000 (  7%) ] Loss: 0.0047 top1= 99.6875
[E44B20 |   8064/60000 ( 13%) ] Loss: 0.0048 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9084 top1= 79.9479


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7860 top1= 52.5841


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8136 top1= 68.5296

Train epoch 45
[E45B0  |    384/60000 (  1%) ] Loss: 0.0073 top1= 99.6875
[E45B10 |   4224/60000 (  7%) ] Loss: 0.0229 top1= 99.3750
[E45B20 |   8064/60000 ( 13%) ] Loss: 0.0034 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6059 top1= 84.5653


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8409 top1= 58.5036


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3258 top1= 75.9816

Train epoch 46
[E46B0  |    384/60000 (  1%) ] Loss: 0.0044 top1=100.0000
[E46B10 |   4224/60000 (  7%) ] Loss: 0.0159 top1= 99.3750
[E46B20 |   8064/60000 ( 13%) ] Loss: 0.0187 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5032 top1= 87.2296


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4407 top1= 68.9002


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1376 top1= 77.2135

Train epoch 47
[E47B0  |    384/60000 (  1%) ] Loss: 0.0046 top1=100.0000
[E47B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E47B20 |   8064/60000 ( 13%) ] Loss: 0.0260 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4336 top1= 88.8922


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0343 top1= 64.9940


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0655 top1= 78.5156

Train epoch 48
[E48B0  |    384/60000 (  1%) ] Loss: 0.0141 top1= 99.6875
[E48B10 |   4224/60000 (  7%) ] Loss: 0.0045 top1=100.0000
[E48B20 |   8064/60000 ( 13%) ] Loss: 0.0113 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3942 top1= 89.6134


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5601 top1= 70.2724


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9352 top1= 81.0096

Train epoch 49
[E49B0  |    384/60000 (  1%) ] Loss: 0.0115 top1= 99.6875
[E49B10 |   4224/60000 (  7%) ] Loss: 0.0047 top1=100.0000
[E49B20 |   8064/60000 ( 13%) ] Loss: 0.0029 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4634 top1= 88.4515


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7268 top1= 67.5080


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1137 top1= 78.4355

Train epoch 50
[E50B0  |    384/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E50B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E50B20 |   8064/60000 ( 13%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3861 top1= 90.0240


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3274 top1= 72.6663


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8946 top1= 81.3301

