
=== 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 0x7f4b81350730>

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: 0.2925 top1= 92.8125
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.0765 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.7772 top1= 37.2396


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1460 top1= 47.2155


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4712 top1= 47.6162

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.1573 top1= 95.9375
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.0610 top1= 98.4375
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.0573 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3322 top1= 52.0132


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1321 top1= 48.0669


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6102 top1= 49.8498

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.0805 top1= 97.1875
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.0300 top1= 99.0625
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0191 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9008 top1= 67.3778


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2465 top1= 48.1571


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3563 top1= 52.1835

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0542 top1= 98.1250
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0304 top1= 99.0625
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0365 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8073 top1= 71.7248


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8145 top1= 48.6378


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9808 top1= 54.3369

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0532 top1= 98.1250
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0224 top1= 99.3750
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0129 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6161 top1= 79.4271


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8069 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9095 top1= 58.8442

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0393 top1= 98.7500
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0439 top1= 99.0625
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0187 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7582 top1= 74.3590


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5676 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7587 top1= 62.0793

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0318 top1= 99.3750
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0384 top1= 99.3750
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0123 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6347 top1= 79.0365


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6901 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6097 top1= 62.0994

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0272 top1= 99.3750
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0406 top1= 99.3750
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0135 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6470 top1= 79.0966


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4168 top1= 51.0216


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5816 top1= 62.1294

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0391 top1= 98.7500
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0165 top1= 99.6875
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0401 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6451 top1= 78.4956


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9768 top1= 50.9916


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6523 top1= 65.7953

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0096 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0242 top1= 99.3750
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0115 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6600 top1= 79.4271


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6230 top1= 52.8245


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6087 top1= 65.3446

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0332 top1= 98.7500
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0105 top1= 99.6875
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0204 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6892 top1= 78.8462


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6193 top1= 54.9079


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3749 top1= 67.9087

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0184 top1= 99.3750
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0174 top1= 99.6875
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0058 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5529 top1= 82.9828


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7084 top1= 54.3069


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6586 top1= 64.9439

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0268 top1= 99.0625
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0175 top1= 99.3750
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0247 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6249 top1= 81.2600


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6133 top1= 55.0481


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3102 top1= 68.6899

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0555 top1= 99.3750
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0049 top1=100.0000
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0147 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6900 top1= 79.2969


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2991 top1= 55.7392


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2595 top1= 59.3450

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0376 top1= 98.4375
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0339 top1= 99.0625
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0486 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5214 top1= 84.5753


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5527 top1= 54.2268


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4250 top1= 66.4764

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0340 top1= 99.6875
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0081 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0098 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5338 top1= 83.1330


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8263 top1= 52.4940


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4375 top1= 68.0990

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0077 top1= 99.6875
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0181 top1= 99.3750
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0080 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5697 top1= 83.6438


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5654 top1= 54.4171


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9916 top1= 76.4523

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0131 top1= 99.3750
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0057 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0188 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5678 top1= 82.9928


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1048 top1= 59.1947


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3359 top1= 60.2264

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0040 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0035 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0098 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5907 top1= 83.5637


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2837 top1= 57.5821


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7797 top1= 64.6935

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0084 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0071 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0062 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5988 top1= 83.1831


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6124 top1= 56.4603


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3653 top1= 71.4443

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0046 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0087 top1= 99.3750
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6561 top1= 82.5921


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6108 top1= 61.0076


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9397 top1= 63.6919

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0328 top1= 99.0625
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0112 top1= 99.6875
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0270 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4691 top1= 86.8490


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3339 top1= 60.6571


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7970 top1= 67.7684

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0036 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0045 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0034 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5649 top1= 84.7055


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4812 top1= 59.3049


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0430 top1= 76.9131

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0051 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0051 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0067 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5701 top1= 85.2364


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9211 top1= 58.6138


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2386 top1= 73.5577

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0290 top1= 99.0625
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0230 top1= 99.3750
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0165 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4886 top1= 87.3898


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8744 top1= 60.9675


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5005 top1= 71.1438

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0181 top1= 99.0625
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0202 top1= 99.3750
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0367 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6151 top1= 85.0260


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6304 top1= 68.5096


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5947 top1= 73.0369

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0264 top1= 99.3750
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0196 top1= 99.3750
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0106 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5372 top1= 86.2480


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0997 top1= 64.6134


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3326 top1= 67.8886

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0336 top1= 99.0625
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0037 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0451 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5374 top1= 85.4768


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3242 top1= 61.8990


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0528 top1= 67.8085

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0259 top1= 99.3750
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0126 top1= 99.6875
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0105 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4064 top1= 88.4716


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3019 top1= 60.7973


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4626 top1= 71.0637

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0058 top1= 99.6875
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0208 top1= 99.6875
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4247 top1= 88.1611


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9985 top1= 64.1927


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9539 top1= 79.9179

Train epoch 31
[E31B0  |    384/60000 (  1%) ] Loss: 0.0047 top1=100.0000
[E31B10 |   4224/60000 (  7%) ] Loss: 0.0025 top1=100.0000
[E31B20 |   8064/60000 ( 13%) ] Loss: 0.0056 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3834 top1= 89.6434


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6920 top1= 66.5665


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2258 top1= 77.3337

Train epoch 32
[E32B0  |    384/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E32B10 |   4224/60000 (  7%) ] Loss: 0.0025 top1=100.0000
[E32B20 |   8064/60000 ( 13%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4734 top1= 87.6803


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9812 top1= 64.0625


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9264 top1= 80.8594

Train epoch 33
[E33B0  |    384/60000 (  1%) ] Loss: 0.0181 top1= 99.6875
[E33B10 |   4224/60000 (  7%) ] Loss: 0.0037 top1=100.0000
[E33B20 |   8064/60000 ( 13%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4570 top1= 88.2712


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1833 top1= 63.9623


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8416 top1= 81.7508

Train epoch 34
[E34B0  |    384/60000 (  1%) ] Loss: 0.0080 top1= 99.3750
[E34B10 |   4224/60000 (  7%) ] Loss: 0.0016 top1=100.0000
[E34B20 |   8064/60000 ( 13%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4526 top1= 88.8021


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7119 top1= 68.5697


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4750 top1= 73.9483

Train epoch 35
[E35B0  |    384/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E35B10 |   4224/60000 (  7%) ] Loss: 0.0154 top1= 99.6875
[E35B20 |   8064/60000 ( 13%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4190 top1= 89.3930


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5132 top1= 71.9351


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2603 top1= 75.7712

Train epoch 36
[E36B0  |    384/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E36B10 |   4224/60000 (  7%) ] Loss: 0.0015 top1=100.0000
[E36B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4261 top1= 89.3830


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6205 top1= 70.3726


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9372 top1= 81.6106

Train epoch 37
[E37B0  |    384/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E37B10 |   4224/60000 (  7%) ] Loss: 0.0017 top1=100.0000
[E37B20 |   8064/60000 ( 13%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4074 top1= 89.8538


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4262 top1= 72.9667


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7786 top1= 83.3834

Train epoch 38
[E38B0  |    384/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E38B10 |   4224/60000 (  7%) ] Loss: 0.0029 top1=100.0000
[E38B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3901 top1= 90.3145


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1862 top1= 76.1118


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7725 top1= 83.1731

Train epoch 39
[E39B0  |    384/60000 (  1%) ] Loss: 0.0052 top1= 99.6875
[E39B10 |   4224/60000 (  7%) ] Loss: 0.0007 top1=100.0000
[E39B20 |   8064/60000 ( 13%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4029 top1= 90.2544


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1095 top1= 77.6242


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8626 top1= 82.5721

Train epoch 40
[E40B0  |    384/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E40B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E40B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3870 top1= 90.9255


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1353 top1= 77.5240


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8081 top1= 83.3634

Train epoch 41
[E41B0  |    384/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E41B10 |   4224/60000 (  7%) ] Loss: 0.0012 top1=100.0000
[E41B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4378 top1= 89.4832


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1376 top1= 77.7043


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8193 top1= 83.5437

Train epoch 42
[E42B0  |    384/60000 (  1%) ] Loss: 0.0038 top1=100.0000
[E42B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E42B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4353 top1= 90.0541


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1602 top1= 77.4940


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0754 top1= 80.1883

Train epoch 43
[E43B0  |    384/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E43B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E43B20 |   8064/60000 ( 13%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4057 top1= 90.1643


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1323 top1= 77.9447


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8304 top1= 83.6438

Train epoch 44
[E44B0  |    384/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E44B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E44B20 |   8064/60000 ( 13%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4289 top1= 90.2544


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0699 top1= 78.8562


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0898 top1= 80.1783

Train epoch 45
[E45B0  |    384/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E45B10 |   4224/60000 (  7%) ] Loss: 0.0007 top1=100.0000
[E45B20 |   8064/60000 ( 13%) ] Loss: 0.0044 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4375 top1= 90.0341


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0985 top1= 78.5657


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8727 top1= 83.0929

Train epoch 46
[E46B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E46B10 |   4224/60000 (  7%) ] Loss: 0.0374 top1= 99.6875
[E46B20 |   8064/60000 ( 13%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4184 top1= 90.4547


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2853 top1= 75.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9710 top1= 81.3101

Train epoch 47
[E47B0  |    384/60000 (  1%) ] Loss: 0.0067 top1= 99.3750
[E47B10 |   4224/60000 (  7%) ] Loss: 0.0021 top1=100.0000
[E47B20 |   8064/60000 ( 13%) ] Loss: 0.0293 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4283 top1= 90.2143


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1938 top1= 77.0433


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4298 top1= 75.1002

Train epoch 48
[E48B0  |    384/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E48B10 |   4224/60000 (  7%) ] Loss: 0.0106 top1= 99.3750
[E48B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4096 top1= 90.3345


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4728 top1= 73.6178


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9056 top1= 81.2500

Train epoch 49
[E49B0  |    384/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E49B10 |   4224/60000 (  7%) ] Loss: 0.0007 top1=100.0000
[E49B20 |   8064/60000 ( 13%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4176 top1= 90.4748


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3660 top1= 74.5192


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8644 top1= 83.0929

Train epoch 50
[E50B0  |    384/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E50B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E50B20 |   8064/60000 ( 13%) ] Loss: 0.0033 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4252 top1= 90.5849


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7249 top1= 70.8934


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3574 top1= 78.4956

