
=== 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)

=== Start adding graph ===
<codes.graph_utils.Dumbbell object at 0x7f08af6b86d0>

Train epoch 1
[E 1B0  |    320/60000 (  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')


[E 1B10 |   3520/60000 (  6%) ] Loss: 0.9939 top1= 70.9375
[E 1B20 |   6720/60000 ( 11%) ] Loss: 0.3866 top1= 88.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=2.0064 top1= 46.3642


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.6318 top1= 47.7163


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8830 top1= 42.7584

Train epoch 2
[E 2B0  |    320/60000 (  1%) ] Loss: 0.3213 top1= 89.3750
[E 2B10 |   3520/60000 (  6%) ] Loss: 0.2216 top1= 92.1875
[E 2B20 |   6720/60000 ( 11%) ] Loss: 0.2838 top1= 91.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.5296 top1= 59.3750


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2974 top1= 49.6595


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0638 top1= 47.9567

Train epoch 3
[E 3B0  |    320/60000 (  1%) ] Loss: 0.2269 top1= 93.4375
[E 3B10 |   3520/60000 (  6%) ] Loss: 0.1860 top1= 93.1250
[E 3B20 |   6720/60000 ( 11%) ] Loss: 0.1802 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2578 top1= 64.1827


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6990 top1= 49.3690


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3801 top1= 47.5561

Train epoch 4
[E 4B0  |    320/60000 (  1%) ] Loss: 0.1894 top1= 94.0625
[E 4B10 |   3520/60000 (  6%) ] Loss: 0.1263 top1= 96.5625
[E 4B20 |   6720/60000 ( 11%) ] Loss: 0.1679 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2956 top1= 64.0825


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7507 top1= 49.8498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8584 top1= 52.3538

Train epoch 5
[E 5B0  |    320/60000 (  1%) ] Loss: 0.0930 top1= 96.2500
[E 5B10 |   3520/60000 (  6%) ] Loss: 0.1149 top1= 96.8750
[E 5B20 |   6720/60000 ( 11%) ] Loss: 0.1415 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2944 top1= 66.7668


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9479 top1= 50.0200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8644 top1= 53.2652

Train epoch 6
[E 6B0  |    320/60000 (  1%) ] Loss: 0.0702 top1= 97.8125
[E 6B10 |   3520/60000 (  6%) ] Loss: 0.0549 top1= 98.4375
[E 6B20 |   6720/60000 ( 11%) ] Loss: 0.0765 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2055 top1= 69.2308


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3369 top1= 50.1202


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2620 top1= 52.2937

Train epoch 7
[E 7B0  |    320/60000 (  1%) ] Loss: 0.0649 top1= 98.1250
[E 7B10 |   3520/60000 (  6%) ] Loss: 0.0588 top1= 98.4375
[E 7B20 |   6720/60000 ( 11%) ] Loss: 0.0450 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2708 top1= 69.5813


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5566 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2683 top1= 54.1266

Train epoch 8
[E 8B0  |    320/60000 (  1%) ] Loss: 0.0318 top1= 98.7500
[E 8B10 |   3520/60000 (  6%) ] Loss: 0.0279 top1= 99.3750
[E 8B20 |   6720/60000 ( 11%) ] Loss: 0.0309 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3469 top1= 69.4511


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5707 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1693 top1= 54.1567

Train epoch 9
[E 9B0  |    320/60000 (  1%) ] Loss: 0.0178 top1=100.0000
[E 9B10 |   3520/60000 (  6%) ] Loss: 0.0336 top1= 99.0625
[E 9B20 |   6720/60000 ( 11%) ] Loss: 0.0184 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4956 top1= 67.4079


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4544 top1= 49.6995


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2675 top1= 54.4371

Train epoch 10
[E10B0  |    320/60000 (  1%) ] Loss: 0.0451 top1= 99.0625
[E10B10 |   3520/60000 (  6%) ] Loss: 0.0258 top1= 99.0625
[E10B20 |   6720/60000 ( 11%) ] Loss: 0.0629 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1922 top1= 70.1322


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5804 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6904 top1= 54.3470

Train epoch 11
[E11B0  |    320/60000 (  1%) ] Loss: 0.0121 top1=100.0000
[E11B10 |   3520/60000 (  6%) ] Loss: 0.0108 top1=100.0000
[E11B20 |   6720/60000 ( 11%) ] Loss: 0.0381 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0735 top1= 71.7047


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4700 top1= 50.1302


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4262 top1= 54.5473

Train epoch 12
[E12B0  |    320/60000 (  1%) ] Loss: 0.0265 top1= 99.0625
[E12B10 |   3520/60000 (  6%) ] Loss: 0.0137 top1=100.0000
[E12B20 |   6720/60000 ( 11%) ] Loss: 0.0089 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0649 top1= 72.5361


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6528 top1= 50.2103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2867 top1= 54.4571

Train epoch 13
[E13B0  |    320/60000 (  1%) ] Loss: 0.0133 top1= 99.6875
[E13B10 |   3520/60000 (  6%) ] Loss: 0.0079 top1=100.0000
[E13B20 |   6720/60000 ( 11%) ] Loss: 0.0044 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9151 top1= 75.5809


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5403 top1= 50.3906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4082 top1= 54.4171

Train epoch 14
[E14B0  |    320/60000 (  1%) ] Loss: 0.0055 top1=100.0000
[E14B10 |   3520/60000 (  6%) ] Loss: 0.0063 top1=100.0000
[E14B20 |   6720/60000 ( 11%) ] Loss: 0.0053 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8984 top1= 76.3722


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5075 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2700 top1= 54.6775

Train epoch 15
[E15B0  |    320/60000 (  1%) ] Loss: 0.0047 top1=100.0000
[E15B10 |   3520/60000 (  6%) ] Loss: 0.0108 top1= 99.6875
[E15B20 |   6720/60000 ( 11%) ] Loss: 0.0060 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8208 top1= 78.3053


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3352 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8902 top1= 53.5457

Train epoch 16
[E16B0  |    320/60000 (  1%) ] Loss: 0.0047 top1=100.0000
[E16B10 |   3520/60000 (  6%) ] Loss: 0.0072 top1= 99.6875
[E16B20 |   6720/60000 ( 11%) ] Loss: 0.0035 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7935 top1= 79.2167


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2569 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0228 top1= 52.6943

Train epoch 17
[E17B0  |    320/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E17B10 |   3520/60000 (  6%) ] Loss: 0.0058 top1=100.0000
[E17B20 |   6720/60000 ( 11%) ] Loss: 0.0029 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7106 top1= 80.6891


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1775 top1= 50.8914


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8780 top1= 52.1735

Train epoch 18
[E18B0  |    320/60000 (  1%) ] Loss: 0.0038 top1=100.0000
[E18B10 |   3520/60000 (  6%) ] Loss: 0.0032 top1=100.0000
[E18B20 |   6720/60000 ( 11%) ] Loss: 0.0049 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6318 top1= 82.2917


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0453 top1= 51.3321


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0037 top1= 51.9231

Train epoch 19
[E19B0  |    320/60000 (  1%) ] Loss: 0.0099 top1= 99.6875
[E19B10 |   3520/60000 (  6%) ] Loss: 0.0023 top1=100.0000
[E19B20 |   6720/60000 ( 11%) ] Loss: 0.0031 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5827 top1= 83.8942


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7783 top1= 51.9932


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6236 top1= 52.7043

Train epoch 20
[E20B0  |    320/60000 (  1%) ] Loss: 0.0032 top1=100.0000
[E20B10 |   3520/60000 (  6%) ] Loss: 0.0031 top1=100.0000
[E20B20 |   6720/60000 ( 11%) ] Loss: 0.0056 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5524 top1= 84.8558


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5765 top1= 52.8045


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2655 top1= 56.0196

Train epoch 21
[E21B0  |    320/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E21B10 |   3520/60000 (  6%) ] Loss: 0.0041 top1=100.0000
[E21B20 |   6720/60000 ( 11%) ] Loss: 0.0029 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5639 top1= 84.7155


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4691 top1= 53.6659


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7359 top1= 59.6755

Train epoch 22
[E22B0  |    320/60000 (  1%) ] Loss: 0.0064 top1= 99.6875
[E22B10 |   3520/60000 (  6%) ] Loss: 0.0039 top1=100.0000
[E22B20 |   6720/60000 ( 11%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5467 top1= 85.4067


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3625 top1= 54.7175


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5087 top1= 60.6571

Train epoch 23
[E23B0  |    320/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E23B10 |   3520/60000 (  6%) ] Loss: 0.0033 top1=100.0000
[E23B20 |   6720/60000 ( 11%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5178 top1= 86.2280


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0964 top1= 56.4904


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3199 top1= 60.7171

Train epoch 24
[E24B0  |    320/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E24B10 |   3520/60000 (  6%) ] Loss: 0.0040 top1=100.0000
[E24B20 |   6720/60000 ( 11%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5068 top1= 86.7889


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9919 top1= 57.5821


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1239 top1= 62.9107

Train epoch 25
[E25B0  |    320/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E25B10 |   3520/60000 (  6%) ] Loss: 0.0043 top1=100.0000
[E25B20 |   6720/60000 ( 11%) ] Loss: 0.0040 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4653 top1= 87.9808


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7732 top1= 59.8357


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2407 top1= 62.9808

Train epoch 26
[E26B0  |    320/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E26B10 |   3520/60000 (  6%) ] Loss: 0.0029 top1=100.0000
[E26B20 |   6720/60000 ( 11%) ] Loss: 0.0039 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4285 top1= 88.8822


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6698 top1= 60.6671


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1171 top1= 64.4732

Train epoch 27
[E27B0  |    320/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E27B10 |   3520/60000 (  6%) ] Loss: 0.0029 top1=100.0000
[E27B20 |   6720/60000 ( 11%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4318 top1= 88.5517


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4443 top1= 63.0809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5607 top1= 63.6118

Train epoch 28
[E28B0  |    320/60000 (  1%) ] Loss: 0.0032 top1=100.0000
[E28B10 |   3520/60000 (  6%) ] Loss: 0.0021 top1=100.0000
[E28B20 |   6720/60000 ( 11%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4501 top1= 88.3113


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3824 top1= 63.5016


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2950 top1= 65.3045

Train epoch 29
[E29B0  |    320/60000 (  1%) ] Loss: 0.0044 top1= 99.6875
[E29B10 |   3520/60000 (  6%) ] Loss: 0.0039 top1=100.0000
[E29B20 |   6720/60000 ( 11%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4607 top1= 88.0409


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4628 top1= 63.6218


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3003 top1= 64.6935

Train epoch 30
[E30B0  |    320/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E30B10 |   3520/60000 (  6%) ] Loss: 0.0106 top1= 99.6875
[E30B20 |   6720/60000 ( 11%) ] Loss: 0.0042 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4512 top1= 88.3914


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4453 top1= 64.0825


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5094 top1= 63.8121

