
=== 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 0x7f486e8ad730>

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: 0.2780 top1= 92.8125
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.1084 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.0182 top1= 35.9075


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.5175 top1= 46.4643


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3683 top1= 39.5333

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.2253 top1= 96.2500
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.0634 top1= 97.8125
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.0709 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7522 top1= 51.0116


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7290 top1= 46.8850


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5825 top1= 43.0789

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1221 top1= 97.5000
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.0510 top1= 98.1250
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0401 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3999 top1= 51.9531


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9405 top1= 47.2256


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0994 top1= 51.3121

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0770 top1= 98.4375
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0365 top1= 99.0625
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0288 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3908 top1= 51.7228


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7729 top1= 47.4359


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9421 top1= 53.6458

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0592 top1= 99.0625
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0343 top1= 98.7500
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0262 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3442 top1= 52.3838


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7352 top1= 47.4359


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9736 top1= 53.4856

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0611 top1= 99.0625
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0291 top1= 99.0625
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0259 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4415 top1= 51.9832


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6935 top1= 47.5060


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8015 top1= 54.6174

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0635 top1= 98.7500
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0328 top1= 99.0625
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0265 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.5057 top1= 51.3221


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6702 top1= 47.5661


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7609 top1= 54.9880

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0555 top1= 99.0625
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0329 top1= 98.7500
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0524 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3407 top1= 53.0449


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6476 top1= 47.5761


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8842 top1= 56.4303

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0653 top1= 98.7500
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0276 top1= 99.0625
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0243 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4624 top1= 51.3321


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6241 top1= 47.5761


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6823 top1= 59.3850

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0760 top1= 98.7500
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0269 top1= 99.0625
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0226 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4281 top1= 52.9447


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5750 top1= 47.6462


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6001 top1= 56.4804

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0544 top1= 99.0625
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0258 top1= 99.0625
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0229 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4184 top1= 53.2151


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5578 top1= 47.6763


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6028 top1= 56.7408

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0882 top1= 98.4375
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0268 top1= 99.0625
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0238 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4553 top1= 53.0248


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5601 top1= 47.5861


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5369 top1= 58.6839

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0745 top1= 98.4375
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0254 top1= 99.0625
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0219 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3483 top1= 54.0966


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5280 top1= 47.7063


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6722 top1= 55.0881

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0521 top1= 99.0625
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0254 top1= 99.0625
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0220 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3756 top1= 54.0765


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5307 top1= 47.6362


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6294 top1= 54.9980

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0544 top1= 99.0625
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0254 top1= 99.0625
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0217 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3432 top1= 54.0264


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5292 top1= 47.6162


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6472 top1= 56.5805

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0529 top1= 99.0625
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0241 top1= 99.0625
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0213 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3998 top1= 54.4271


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5268 top1= 47.6462


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6238 top1= 55.2083

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0539 top1= 99.0625
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0286 top1= 98.7500
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0211 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.5042 top1= 53.6058


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5242 top1= 47.6262


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4690 top1= 58.5537

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0926 top1= 98.4375
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0261 top1= 99.0625
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0205 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3727 top1= 54.4271


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5180 top1= 47.6362


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5707 top1= 61.2079

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0629 top1= 98.4375
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0254 top1= 99.0625
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0220 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3917 top1= 53.0549


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4944 top1= 47.6562


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4493 top1= 64.8438

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0665 top1= 98.7500
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0243 top1= 99.0625
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0222 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1841 top1= 55.9896


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4617 top1= 47.7564


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8034 top1= 57.9728

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0527 top1= 99.0625
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0235 top1= 99.0625
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0210 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3362 top1= 53.7760


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4569 top1= 47.7464


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5420 top1= 59.2248

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0561 top1= 98.7500
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0259 top1= 99.0625
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0213 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3155 top1= 54.3369


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4558 top1= 47.6963


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5957 top1= 59.8057

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0645 top1= 98.7500
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0223 top1= 99.0625
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0196 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2871 top1= 55.2584


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4448 top1= 47.7564


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7045 top1= 55.7492

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0534 top1= 98.7500
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0233 top1= 99.0625
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0190 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2729 top1= 55.3886


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4454 top1= 47.7364


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7251 top1= 56.1498

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0536 top1= 98.7500
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0227 top1= 99.0625
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0194 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2726 top1= 55.6390


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4416 top1= 47.7264


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7368 top1= 55.5489

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0538 top1= 98.7500
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0228 top1= 99.0625
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0189 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2711 top1= 55.7392


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4432 top1= 47.7163


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7422 top1= 55.3285

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0534 top1= 98.7500
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0225 top1= 99.0625
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0193 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2719 top1= 55.8193


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4392 top1= 47.7163


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7437 top1= 55.1783

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0532 top1= 98.7500
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0226 top1= 99.0625
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0187 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2714 top1= 55.8494


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4412 top1= 47.6763


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7434 top1= 55.1382

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0534 top1= 98.4375
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0223 top1= 99.0625
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0191 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2702 top1= 55.9495


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4392 top1= 47.6763


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7479 top1= 55.0481

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0526 top1= 98.4375
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0225 top1= 99.0625
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0185 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2694 top1= 55.9996


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4408 top1= 47.6462


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7483 top1= 54.9079

Train epoch 31
[E31B0  |    384/60000 (  1%) ] Loss: 0.0536 top1= 98.7500
[E31B10 |   4224/60000 (  7%) ] Loss: 0.0222 top1= 99.0625
[E31B20 |   8064/60000 ( 13%) ] Loss: 0.0190 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2669 top1= 56.0697


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4380 top1= 47.6462


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7556 top1= 54.8177

Train epoch 32
[E32B0  |    384/60000 (  1%) ] Loss: 0.0522 top1= 98.4375
[E32B10 |   4224/60000 (  7%) ] Loss: 0.0222 top1= 99.0625
[E32B20 |   8064/60000 ( 13%) ] Loss: 0.0185 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2662 top1= 56.1298


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4360 top1= 47.6262


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7528 top1= 54.7877

Train epoch 33
[E33B0  |    384/60000 (  1%) ] Loss: 0.0527 top1= 98.4375
[E33B10 |   4224/60000 (  7%) ] Loss: 0.0222 top1= 99.0625
[E33B20 |   8064/60000 ( 13%) ] Loss: 0.0187 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2668 top1= 56.0998


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4383 top1= 47.6162


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7562 top1= 54.7376

Train epoch 34
[E34B0  |    384/60000 (  1%) ] Loss: 0.0529 top1= 98.4375
[E34B10 |   4224/60000 (  7%) ] Loss: 0.0220 top1= 99.0625
[E34B20 |   8064/60000 ( 13%) ] Loss: 0.0182 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2657 top1= 56.1498


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4369 top1= 47.6162


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7547 top1= 54.7877

Train epoch 35
[E35B0  |    384/60000 (  1%) ] Loss: 0.0526 top1= 98.4375
[E35B10 |   4224/60000 (  7%) ] Loss: 0.0220 top1= 99.0625
[E35B20 |   8064/60000 ( 13%) ] Loss: 0.0187 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2659 top1= 56.2500


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4374 top1= 47.6262


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7551 top1= 54.7476

Train epoch 36
[E36B0  |    384/60000 (  1%) ] Loss: 0.0522 top1= 98.4375
[E36B10 |   4224/60000 (  7%) ] Loss: 0.0220 top1= 99.0625
[E36B20 |   8064/60000 ( 13%) ] Loss: 0.0182 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2634 top1= 56.2300


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4341 top1= 47.5761


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7539 top1= 54.7977

Train epoch 37
[E37B0  |    384/60000 (  1%) ] Loss: 0.0524 top1= 98.4375
[E37B10 |   4224/60000 (  7%) ] Loss: 0.0223 top1= 99.0625
[E37B20 |   8064/60000 ( 13%) ] Loss: 0.0184 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2649 top1= 56.2700


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4389 top1= 47.5861


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7581 top1= 54.7376

Train epoch 38
[E38B0  |    384/60000 (  1%) ] Loss: 0.0525 top1= 98.4375
[E38B10 |   4224/60000 (  7%) ] Loss: 0.0221 top1= 99.0625
[E38B20 |   8064/60000 ( 13%) ] Loss: 0.0181 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2623 top1= 56.3702


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4331 top1= 47.5962


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7549 top1= 54.6575

Train epoch 39
[E39B0  |    384/60000 (  1%) ] Loss: 0.0522 top1= 98.4375
[E39B10 |   4224/60000 (  7%) ] Loss: 0.0222 top1= 99.0625
[E39B20 |   8064/60000 ( 13%) ] Loss: 0.0185 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2636 top1= 56.3401


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4361 top1= 47.5962


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7588 top1= 54.6074

Train epoch 40
[E40B0  |    384/60000 (  1%) ] Loss: 0.0516 top1= 98.4375
[E40B10 |   4224/60000 (  7%) ] Loss: 0.0222 top1= 99.0625
[E40B20 |   8064/60000 ( 13%) ] Loss: 0.0181 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2608 top1= 56.4704


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4346 top1= 47.5561


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7612 top1= 54.5573

Train epoch 41
[E41B0  |    384/60000 (  1%) ] Loss: 0.0522 top1= 98.4375
[E41B10 |   4224/60000 (  7%) ] Loss: 0.0222 top1= 99.0625
[E41B20 |   8064/60000 ( 13%) ] Loss: 0.0182 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2625 top1= 56.4904


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4371 top1= 47.5861


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7581 top1= 54.5373

Train epoch 42
[E42B0  |    384/60000 (  1%) ] Loss: 0.0518 top1= 98.4375
[E42B10 |   4224/60000 (  7%) ] Loss: 0.0222 top1= 99.0625
[E42B20 |   8064/60000 ( 13%) ] Loss: 0.0182 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2586 top1= 56.5805


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4357 top1= 47.5661


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7621 top1= 54.4872

Train epoch 43
[E43B0  |    384/60000 (  1%) ] Loss: 0.0518 top1= 98.4375
[E43B10 |   4224/60000 (  7%) ] Loss: 0.0220 top1= 99.0625
[E43B20 |   8064/60000 ( 13%) ] Loss: 0.0180 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2604 top1= 56.6006


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4378 top1= 47.5361


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7634 top1= 54.5573

Train epoch 44
[E44B0  |    384/60000 (  1%) ] Loss: 0.0518 top1= 98.4375
[E44B10 |   4224/60000 (  7%) ] Loss: 0.0220 top1= 99.0625
[E44B20 |   8064/60000 ( 13%) ] Loss: 0.0183 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2576 top1= 56.6807


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4358 top1= 47.5962


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7674 top1= 54.3970

Train epoch 45
[E45B0  |    384/60000 (  1%) ] Loss: 0.0514 top1= 98.4375
[E45B10 |   4224/60000 (  7%) ] Loss: 0.0217 top1= 99.0625
[E45B20 |   8064/60000 ( 13%) ] Loss: 0.0178 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2572 top1= 56.6907


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4308 top1= 47.5260


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7624 top1= 54.5473

Train epoch 46
[E46B0  |    384/60000 (  1%) ] Loss: 0.0519 top1= 98.4375
[E46B10 |   4224/60000 (  7%) ] Loss: 0.0222 top1= 99.0625
[E46B20 |   8064/60000 ( 13%) ] Loss: 0.0182 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2587 top1= 56.7107


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4369 top1= 47.5461


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7654 top1= 54.4171

Train epoch 47
[E47B0  |    384/60000 (  1%) ] Loss: 0.0514 top1= 98.4375
[E47B10 |   4224/60000 (  7%) ] Loss: 0.0215 top1= 99.0625
[E47B20 |   8064/60000 ( 13%) ] Loss: 0.0177 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2550 top1= 56.8209


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4325 top1= 47.5160


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7625 top1= 54.4872

Train epoch 48
[E48B0  |    384/60000 (  1%) ] Loss: 0.0516 top1= 98.4375
[E48B10 |   4224/60000 (  7%) ] Loss: 0.0215 top1= 99.0625
[E48B20 |   8064/60000 ( 13%) ] Loss: 0.0181 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2551 top1= 56.8309


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4355 top1= 47.5361


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7707 top1= 54.3770

Train epoch 49
[E49B0  |    384/60000 (  1%) ] Loss: 0.0513 top1= 98.4375
[E49B10 |   4224/60000 (  7%) ] Loss: 0.0220 top1= 99.0625
[E49B20 |   8064/60000 ( 13%) ] Loss: 0.0177 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2547 top1= 56.8309


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4314 top1= 47.5361


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7661 top1= 54.3870

Train epoch 50
[E50B0  |    384/60000 (  1%) ] Loss: 0.0512 top1= 98.4375
[E50B10 |   4224/60000 (  7%) ] Loss: 0.0221 top1= 99.0625
[E50B20 |   8064/60000 ( 13%) ] Loss: 0.0182 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2551 top1= 56.8510


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4338 top1= 47.5260


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7683 top1= 54.3570

