
=== 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 0x7fe636c5e730>

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: 0.2961 top1= 92.8125
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.0740 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.7663 top1= 37.0292


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1750 top1= 47.2857


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5572 top1= 46.7047

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.1565 top1= 96.2500
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.0604 top1= 98.4375
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.0634 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3372 top1= 52.0032


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1218 top1= 47.8265


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7210 top1= 49.9700

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.0815 top1= 97.8125
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.0327 top1= 99.0625
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0223 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9202 top1= 66.7969


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2917 top1= 48.2672


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4273 top1= 52.2035

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0576 top1= 98.1250
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0334 top1= 99.0625
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0401 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7980 top1= 72.4259


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8372 top1= 49.3189


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0497 top1= 54.7276

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0367 top1= 98.4375
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0257 top1= 99.0625
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0130 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7819 top1= 74.6595


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0560 top1= 49.5092


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7476 top1= 60.5268

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0161 top1= 99.3750
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0243 top1= 99.0625
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0222 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7875 top1= 74.1286


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6765 top1= 49.6294


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7722 top1= 62.5901

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0363 top1= 98.7500
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0228 top1= 99.3750
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0059 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5799 top1= 81.1498


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2461 top1= 53.0449


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5356 top1= 65.3045

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0248 top1= 99.3750
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0308 top1= 99.0625
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0472 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7277 top1= 76.9231


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5651 top1= 52.8846


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3123 top1= 66.9571

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0251 top1= 99.0625
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0128 top1= 99.6875
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0086 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5487 top1= 82.3518


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7102 top1= 51.9231


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5683 top1= 65.3846

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0159 top1= 99.6875
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0099 top1=100.0000
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0081 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6498 top1= 79.9279


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6312 top1= 53.5958


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8087 top1= 63.7520

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0204 top1= 99.3750
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0150 top1= 99.3750
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0076 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5731 top1= 81.8209


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8410 top1= 54.4972


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1466 top1= 65.9555

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0158 top1= 99.6875
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0120 top1= 99.6875
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0153 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6046 top1= 81.6506


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0000 top1= 55.5689


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6676 top1= 64.4231

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0320 top1= 98.4375
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0170 top1= 99.6875
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0413 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5583 top1= 83.9143


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7018 top1= 59.2248


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8120 top1= 62.1394

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0188 top1= 99.3750
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0071 top1= 99.6875
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0094 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6301 top1= 81.5605


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4930 top1= 55.1382


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3739 top1= 60.4567

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0423 top1= 98.1250
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0119 top1= 99.6875
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0309 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5619 top1= 83.4034


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5967 top1= 55.3886


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3040 top1= 61.0076

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0305 top1= 98.4375
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0086 top1= 99.6875
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0036 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6019 top1= 82.7624


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6376 top1= 56.7909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0245 top1= 60.5168

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0211 top1= 99.3750
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0238 top1= 99.6875
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0201 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5227 top1= 84.6955


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6401 top1= 54.9679


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3027 top1= 72.6462

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0148 top1= 99.6875
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0038 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0044 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5510 top1= 84.5052


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5083 top1= 59.8758


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2797 top1= 70.8433

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0097 top1= 99.6875
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0059 top1= 99.6875
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0098 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4497 top1= 87.0493


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9298 top1= 63.1510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1638 top1= 75.3506

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0137 top1= 99.3750
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0022 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0057 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7172 top1= 80.3385


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1594 top1= 64.0024


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4460 top1= 72.5962

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0062 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0064 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0048 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5078 top1= 85.4968


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9346 top1= 55.3586


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4458 top1= 70.3125

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0076 top1= 99.6875
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0025 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0307 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5785 top1= 84.0244


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8736 top1= 56.7808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4393 top1= 74.4792

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0296 top1= 99.6875
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0044 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0196 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5612 top1= 83.8341


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8528 top1= 53.2752


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4917 top1= 71.5745

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0181 top1= 99.3750
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0070 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0063 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5847 top1= 84.4651


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4848 top1= 59.5252


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1987 top1= 75.6010

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0119 top1= 99.6875
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0095 top1= 99.6875
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0158 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4691 top1= 87.1194


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2570 top1= 61.4183


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6319 top1= 70.8133

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0186 top1= 99.3750
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0121 top1= 99.3750
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0323 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5381 top1= 85.9876


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9951 top1= 63.9022


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4261 top1= 75.0501

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0205 top1= 99.0625
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0044 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0112 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5245 top1= 86.7488


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3117 top1= 61.6086


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2420 top1= 76.5124

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0027 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0272 top1= 99.0625
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0161 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4905 top1= 87.0393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2147 top1= 61.3482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1075 top1= 77.1635

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0041 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0228 top1= 99.0625
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5435 top1= 85.4768


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2873 top1= 61.0377


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6966 top1= 69.9319

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0055 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0585 top1= 98.1250
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0084 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4853 top1= 87.1094


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1587 top1= 62.0192


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4721 top1= 71.3842

Train epoch 31
[E31B0  |    384/60000 (  1%) ] Loss: 0.0334 top1= 99.3750
[E31B10 |   4224/60000 (  7%) ] Loss: 0.0102 top1= 99.3750
[E31B20 |   8064/60000 ( 13%) ] Loss: 0.0227 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4479 top1= 88.2512


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0547 top1= 63.2612


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9875 top1= 78.1050

Train epoch 32
[E32B0  |    384/60000 (  1%) ] Loss: 0.0053 top1=100.0000
[E32B10 |   4224/60000 (  7%) ] Loss: 0.0068 top1=100.0000
[E32B20 |   8064/60000 ( 13%) ] Loss: 0.0073 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4135 top1= 89.0425


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8268 top1= 65.6050


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9921 top1= 77.7644

Train epoch 33
[E33B0  |    384/60000 (  1%) ] Loss: 0.0098 top1= 99.0625
[E33B10 |   4224/60000 (  7%) ] Loss: 0.0051 top1=100.0000
[E33B20 |   8064/60000 ( 13%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4362 top1= 88.4215


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9808 top1= 64.2027


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1770 top1= 77.9147

Train epoch 34
[E34B0  |    384/60000 (  1%) ] Loss: 0.0042 top1=100.0000
[E34B10 |   4224/60000 (  7%) ] Loss: 0.0022 top1=100.0000
[E34B20 |   8064/60000 ( 13%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3881 top1= 89.6234


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7246 top1= 66.1959


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9357 top1= 80.7893

Train epoch 35
[E35B0  |    384/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E35B10 |   4224/60000 (  7%) ] Loss: 0.0018 top1=100.0000
[E35B20 |   8064/60000 ( 13%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4038 top1= 89.8638


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4208 top1= 72.3658


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7826 top1= 83.4635

Train epoch 36
[E36B0  |    384/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E36B10 |   4224/60000 (  7%) ] Loss: 0.0020 top1=100.0000
[E36B20 |   8064/60000 ( 13%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4029 top1= 90.0641


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2815 top1= 75.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6809 top1= 85.1362

Train epoch 37
[E37B0  |    384/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E37B10 |   4224/60000 (  7%) ] Loss: 0.0014 top1=100.0000
[E37B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4073 top1= 89.9740


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2655 top1= 75.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6524 top1= 86.1478

Train epoch 38
[E38B0  |    384/60000 (  1%) ] Loss: 0.0058 top1= 99.6875
[E38B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E38B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4052 top1= 90.1342


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2057 top1= 76.6026


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6437 top1= 86.2380

Train epoch 39
[E39B0  |    384/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E39B10 |   4224/60000 (  7%) ] Loss: 0.0031 top1=100.0000
[E39B20 |   8064/60000 ( 13%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4684 top1= 88.3714


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0715 top1= 66.5465


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7579 top1= 84.3950

Train epoch 40
[E40B0  |    384/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E40B10 |   4224/60000 (  7%) ] Loss: 0.0046 top1= 99.6875
[E40B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3962 top1= 90.3145


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5520 top1= 71.4744


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8190 top1= 82.4720

Train epoch 41
[E41B0  |    384/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E41B10 |   4224/60000 (  7%) ] Loss: 0.0012 top1=100.0000
[E41B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4159 top1= 90.1843


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3999 top1= 73.5978


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6873 top1= 85.7672

Train epoch 42
[E42B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E42B10 |   4224/60000 (  7%) ] Loss: 0.0013 top1=100.0000
[E42B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4115 top1= 90.1843


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1262 top1= 77.8045


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7618 top1= 84.6554

Train epoch 43
[E43B0  |    384/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E43B10 |   4224/60000 (  7%) ] Loss: 0.0011 top1=100.0000
[E43B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4198 top1= 90.1843


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0738 top1= 78.5056


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8211 top1= 83.8742

Train epoch 44
[E44B0  |    384/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E44B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E44B20 |   8064/60000 ( 13%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4232 top1= 90.1542


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0662 top1= 78.8462


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7855 top1= 84.5152

Train epoch 45
[E45B0  |    384/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E45B10 |   4224/60000 (  7%) ] Loss: 0.0007 top1=100.0000
[E45B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4249 top1= 90.0741


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0501 top1= 79.2268


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7807 top1= 84.6354

Train epoch 46
[E46B0  |    384/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E46B10 |   4224/60000 (  7%) ] Loss: 0.0007 top1=100.0000
[E46B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4168 top1= 90.4247


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0428 top1= 79.4972


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7571 top1= 85.0561

Train epoch 47
[E47B0  |    384/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E47B10 |   4224/60000 (  7%) ] Loss: 0.0007 top1=100.0000
[E47B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3966 top1= 91.1759


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0449 top1= 79.6575


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7095 top1= 85.9776

Train epoch 48
[E48B0  |    384/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E48B10 |   4224/60000 (  7%) ] Loss: 0.0055 top1= 99.6875
[E48B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4386 top1= 90.2043


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1691 top1= 77.9447


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6492 top1= 86.8890

Train epoch 49
[E49B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E49B10 |   4224/60000 (  7%) ] Loss: 0.0012 top1=100.0000
[E49B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4358 top1= 90.2744


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0559 top1= 79.7877


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7367 top1= 85.5769

Train epoch 50
[E50B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E50B10 |   4224/60000 (  7%) ] Loss: 0.0007 top1=100.0000
[E50B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4408 top1= 90.2544


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0102 top1= 80.6390


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8032 top1= 84.5553

