
=== 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 0x7f34298e9730>

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: 0.2820 top1= 92.8125
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.0956 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.7390 top1= 38.1010


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9088 top1= 46.3341


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1418 top1= 45.1723

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.1602 top1= 96.2500
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.0525 top1= 98.7500
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.0611 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3428 top1= 53.1651


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2277 top1= 47.8666


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4337 top1= 48.5377

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.0957 top1= 96.5625
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.0332 top1= 99.0625
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0266 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9724 top1= 66.5064


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2048 top1= 48.1070


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0226 top1= 51.0317

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0606 top1= 98.1250
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0346 top1= 99.0625
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0305 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7400 top1= 74.6795


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7196 top1= 48.4075


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0990 top1= 52.9247

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0578 top1= 98.4375
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0140 top1= 99.6875
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0089 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6957 top1= 76.0517


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7513 top1= 48.7380


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7170 top1= 57.0513

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0336 top1= 98.7500
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0345 top1= 99.3750
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0131 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6253 top1= 79.4772


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4035 top1= 51.4824


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5705 top1= 60.7272

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0166 top1= 99.6875
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0228 top1= 99.6875
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0261 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6787 top1= 78.0449


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2947 top1= 51.2019


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4976 top1= 64.5633

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0258 top1= 99.6875
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0191 top1= 99.6875
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0117 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6416 top1= 79.0365


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5611 top1= 50.8714


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7191 top1= 61.1879

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0432 top1= 98.7500
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0255 top1= 99.0625
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0174 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5491 top1= 81.3602


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4948 top1= 53.3053


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5103 top1= 66.5164

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0485 top1= 99.3750
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0098 top1= 99.6875
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0198 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5280 top1= 82.8325


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1726 top1= 54.3069


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5809 top1= 63.3514

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0160 top1= 99.0625
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0036 top1=100.0000
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0093 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6534 top1= 79.5974


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3098 top1= 57.3317


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3586 top1= 66.9471

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0224 top1= 99.3750
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0116 top1= 99.6875
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0515 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8176 top1= 75.8113


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1948 top1= 52.9647


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6658 top1= 65.0140

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0582 top1= 98.1250
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0028 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0147 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8850 top1= 74.3389


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5108 top1= 57.0413


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0505 top1= 59.2548

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0417 top1= 98.1250
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0163 top1= 99.0625
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0227 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6074 top1= 81.5405


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0740 top1= 53.5857


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4847 top1= 63.6118

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0154 top1= 99.3750
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0053 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0127 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5231 top1= 83.8041


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1037 top1= 55.5589


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1034 top1= 72.6562

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0208 top1= 99.6875
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0081 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0332 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7878 top1= 76.6927


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4172 top1= 54.0565


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0920 top1= 74.5593

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0599 top1= 98.7500
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0201 top1= 99.3750
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0131 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4977 top1= 83.9744


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4745 top1= 54.2268


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4418 top1= 68.2292

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0192 top1= 99.6875
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0066 top1= 99.6875
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0110 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5652 top1= 82.1615


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9827 top1= 55.3686


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9711 top1= 64.0425

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0130 top1= 99.6875
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0078 top1= 99.6875
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0117 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5207 top1= 83.5136


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8177 top1= 53.3654


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1622 top1= 63.2011

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0089 top1= 99.6875
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0115 top1= 99.6875
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0152 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5914 top1= 82.5521


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2754 top1= 52.6142


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1239 top1= 74.7095

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0068 top1= 99.6875
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0027 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0114 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4536 top1= 86.6186


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3338 top1= 59.3650


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6696 top1= 67.8385

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0050 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0069 top1= 99.6875
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0060 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4403 top1= 86.7588


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0290 top1= 60.8974


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8875 top1= 65.8554

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0081 top1= 99.6875
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0054 top1= 99.6875
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0076 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4605 top1= 86.2680


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7491 top1= 61.7889


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0265 top1= 77.2236

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0029 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0098 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5186 top1= 85.2163


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5318 top1= 58.1931


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4368 top1= 70.3025

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0084 top1= 99.6875
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0034 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0044 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4552 top1= 86.9191


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9153 top1= 61.7989


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2258 top1= 74.5793

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0057 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0034 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0044 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5712 top1= 84.4251


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9715 top1= 64.0224


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4604 top1= 71.7748

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0181 top1= 99.6875
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0233 top1= 99.6875
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0055 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4945 top1= 85.9175


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3137 top1= 58.8041


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4978 top1= 73.6078

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0105 top1= 99.6875
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0175 top1= 99.0625
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0111 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5690 top1= 84.6154


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3310 top1= 59.3950


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7373 top1= 71.4243

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0110 top1= 99.6875
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0161 top1= 99.6875
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0042 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4643 top1= 87.2296


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4917 top1= 60.9976


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8145 top1= 66.6266

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0085 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0105 top1= 99.3750
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0145 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5935 top1= 83.8742


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1177 top1= 60.5669


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4220 top1= 72.3558

Train epoch 31
[E31B0  |    384/60000 (  1%) ] Loss: 0.0367 top1= 99.0625
[E31B10 |   4224/60000 (  7%) ] Loss: 0.0004 top1=100.0000
[E31B20 |   8064/60000 ( 13%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5768 top1= 84.2849


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8032 top1= 58.9443


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4676 top1= 66.7268

Train epoch 32
[E32B0  |    384/60000 (  1%) ] Loss: 0.0044 top1=100.0000
[E32B10 |   4224/60000 (  7%) ] Loss: 0.0015 top1=100.0000
[E32B20 |   8064/60000 ( 13%) ] Loss: 0.0085 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5837 top1= 84.1146


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0076 top1= 59.4752


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5463 top1= 71.1038

Train epoch 33
[E33B0  |    384/60000 (  1%) ] Loss: 0.0445 top1= 99.3750
[E33B10 |   4224/60000 (  7%) ] Loss: 0.0030 top1=100.0000
[E33B20 |   8064/60000 ( 13%) ] Loss: 0.0073 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4718 top1= 86.8089


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3055 top1= 61.8490


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5868 top1= 70.8033

Train epoch 34
[E34B0  |    384/60000 (  1%) ] Loss: 0.0137 top1= 99.6875
[E34B10 |   4224/60000 (  7%) ] Loss: 0.0096 top1= 99.3750
[E34B20 |   8064/60000 ( 13%) ] Loss: 0.0065 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4320 top1= 88.0409


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1317 top1= 62.7204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6005 top1= 71.2240

Train epoch 35
[E35B0  |    384/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E35B10 |   4224/60000 (  7%) ] Loss: 0.0100 top1= 99.6875
[E35B20 |   8064/60000 ( 13%) ] Loss: 0.0166 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4852 top1= 87.0192


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1223 top1= 61.5685


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6082 top1= 69.5913

Train epoch 36
[E36B0  |    384/60000 (  1%) ] Loss: 0.0128 top1= 99.6875
[E36B10 |   4224/60000 (  7%) ] Loss: 0.0061 top1= 99.6875
[E36B20 |   8064/60000 ( 13%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4727 top1= 87.1094


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1303 top1= 62.7204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7350 top1= 71.6246

Train epoch 37
[E37B0  |    384/60000 (  1%) ] Loss: 0.0047 top1= 99.6875
[E37B10 |   4224/60000 (  7%) ] Loss: 0.0054 top1= 99.6875
[E37B20 |   8064/60000 ( 13%) ] Loss: 0.0035 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4950 top1= 86.8790


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8447 top1= 59.4752


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2446 top1= 76.5625

Train epoch 38
[E38B0  |    384/60000 (  1%) ] Loss: 0.0036 top1=100.0000
[E38B10 |   4224/60000 (  7%) ] Loss: 0.0038 top1=100.0000
[E38B20 |   8064/60000 ( 13%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4332 top1= 88.1410


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5597 top1= 68.3193


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0587 top1= 79.4471

Train epoch 39
[E39B0  |    384/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E39B10 |   4224/60000 (  7%) ] Loss: 0.0017 top1=100.0000
[E39B20 |   8064/60000 ( 13%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4163 top1= 89.1827


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5323 top1= 69.2208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0190 top1= 79.7175

Train epoch 40
[E40B0  |    384/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E40B10 |   4224/60000 (  7%) ] Loss: 0.0133 top1= 99.6875
[E40B20 |   8064/60000 ( 13%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4482 top1= 88.4716


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0356 top1= 63.1711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9494 top1= 80.3385

Train epoch 41
[E41B0  |    384/60000 (  1%) ] Loss: 0.0122 top1= 99.6875
[E41B10 |   4224/60000 (  7%) ] Loss: 0.0004 top1=100.0000
[E41B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4145 top1= 89.5333


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5237 top1= 69.6114


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9597 top1= 80.4487

Train epoch 42
[E42B0  |    384/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E42B10 |   4224/60000 (  7%) ] Loss: 0.0009 top1=100.0000
[E42B20 |   8064/60000 ( 13%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4211 top1= 89.3229


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3645 top1= 72.9868


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7939 top1= 82.8526

Train epoch 43
[E43B0  |    384/60000 (  1%) ] Loss: 0.0045 top1=100.0000
[E43B10 |   4224/60000 (  7%) ] Loss: 0.0017 top1=100.0000
[E43B20 |   8064/60000 ( 13%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4182 top1= 89.7636


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3248 top1= 73.6779


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1870 top1= 78.9764

Train epoch 44
[E44B0  |    384/60000 (  1%) ] Loss: 0.0176 top1= 99.6875
[E44B10 |   4224/60000 (  7%) ] Loss: 0.0005 top1=100.0000
[E44B20 |   8064/60000 ( 13%) ] Loss: 0.0048 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4499 top1= 88.9223


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2587 top1= 75.0200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0141 top1= 80.1983

Train epoch 45
[E45B0  |    384/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E45B10 |   4224/60000 (  7%) ] Loss: 0.0017 top1=100.0000
[E45B20 |   8064/60000 ( 13%) ] Loss: 0.0110 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4573 top1= 89.3730


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3585 top1= 73.9383


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2192 top1= 77.1434

Train epoch 46
[E46B0  |    384/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E46B10 |   4224/60000 (  7%) ] Loss: 0.0036 top1=100.0000
[E46B20 |   8064/60000 ( 13%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4508 top1= 88.9423


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2465 top1= 74.9199


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0724 top1= 79.4671

Train epoch 47
[E47B0  |    384/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E47B10 |   4224/60000 (  7%) ] Loss: 0.0008 top1=100.0000
[E47B20 |   8064/60000 ( 13%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3974 top1= 90.3546


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3480 top1= 74.5092


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9369 top1= 81.0597

Train epoch 48
[E48B0  |    384/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E48B10 |   4224/60000 (  7%) ] Loss: 0.0043 top1=100.0000
[E48B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4414 top1= 89.7837


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3379 top1= 74.4591


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9919 top1= 80.9996

Train epoch 49
[E49B0  |    384/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E49B10 |   4224/60000 (  7%) ] Loss: 0.0010 top1=100.0000
[E49B20 |   8064/60000 ( 13%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4084 top1= 90.2143


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2034 top1= 76.7127


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8713 top1= 82.1615

Train epoch 50
[E50B0  |    384/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E50B10 |   4224/60000 (  7%) ] Loss: 0.0007 top1=100.0000
[E50B20 |   8064/60000 ( 13%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4187 top1= 90.3345


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1566 top1= 77.5541


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9303 top1= 82.2416

