
=== 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 0x7f2ec8e0a6d0>

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: 0.9816 top1= 73.4375
[E 1B20 |   6720/60000 ( 11%) ] Loss: 0.2251 top1= 92.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9809 top1= 48.0068


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7268 top1= 48.8782


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3582 top1= 48.9683

Train epoch 2
[E 2B0  |    320/60000 (  1%) ] Loss: 0.1738 top1= 95.3125
[E 2B10 |   3520/60000 (  6%) ] Loss: 0.1423 top1= 95.6250
[E 2B20 |   6720/60000 ( 11%) ] Loss: 0.1221 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1917 top1= 62.6202


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4051 top1= 48.4375


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8232 top1= 52.1635

Train epoch 3
[E 3B0  |    320/60000 (  1%) ] Loss: 0.1420 top1= 95.9375
[E 3B10 |   3520/60000 (  6%) ] Loss: 0.1620 top1= 94.3750
[E 3B20 |   6720/60000 ( 11%) ] Loss: 0.1040 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0713 top1= 69.9619


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6607 top1= 49.1086


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2104 top1= 55.4688

Train epoch 4
[E 4B0  |    320/60000 (  1%) ] Loss: 0.1358 top1= 96.5625
[E 4B10 |   3520/60000 (  6%) ] Loss: 0.0677 top1= 98.4375
[E 4B20 |   6720/60000 ( 11%) ] Loss: 0.1070 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6640 top1= 77.8045


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8630 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0084 top1= 58.7640

Train epoch 5
[E 5B0  |    320/60000 (  1%) ] Loss: 0.1109 top1= 96.8750
[E 5B10 |   3520/60000 (  6%) ] Loss: 0.0680 top1= 96.2500
[E 5B20 |   6720/60000 ( 11%) ] Loss: 0.0752 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5916 top1= 81.4704


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7289 top1= 55.7392


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8556 top1= 61.0777

Train epoch 6
[E 6B0  |    320/60000 (  1%) ] Loss: 0.0804 top1= 98.4375
[E 6B10 |   3520/60000 (  6%) ] Loss: 0.0683 top1= 98.1250
[E 6B20 |   6720/60000 ( 11%) ] Loss: 0.0532 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6358 top1= 80.3185


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6923 top1= 57.1615


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7063 top1= 62.9107

Train epoch 7
[E 7B0  |    320/60000 (  1%) ] Loss: 0.0696 top1= 98.1250
[E 7B10 |   3520/60000 (  6%) ] Loss: 0.0779 top1= 97.1875
[E 7B20 |   6720/60000 ( 11%) ] Loss: 0.0475 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6941 top1= 79.9179


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5886 top1= 58.4936


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7295 top1= 63.1611

Train epoch 8
[E 8B0  |    320/60000 (  1%) ] Loss: 0.0877 top1= 97.1875
[E 8B10 |   3520/60000 (  6%) ] Loss: 0.0201 top1= 99.6875
[E 8B20 |   6720/60000 ( 11%) ] Loss: 0.0194 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4647 top1= 85.9976


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2653 top1= 57.5220


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2988 top1= 68.7700

Train epoch 9
[E 9B0  |    320/60000 (  1%) ] Loss: 0.0385 top1= 97.8125
[E 9B10 |   3520/60000 (  6%) ] Loss: 0.0198 top1= 99.3750
[E 9B20 |   6720/60000 ( 11%) ] Loss: 0.0185 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4161 top1= 87.5601


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2318 top1= 57.7224


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3713 top1= 70.2424

Train epoch 10
[E10B0  |    320/60000 (  1%) ] Loss: 0.0297 top1= 99.3750
[E10B10 |   3520/60000 (  6%) ] Loss: 0.0065 top1=100.0000
[E10B20 |   6720/60000 ( 11%) ] Loss: 0.0063 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3702 top1= 88.9523


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8698 top1= 62.8506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2992 top1= 70.8934

Train epoch 11
[E11B0  |    320/60000 (  1%) ] Loss: 0.0120 top1= 99.6875
[E11B10 |   3520/60000 (  6%) ] Loss: 0.0065 top1=100.0000
[E11B20 |   6720/60000 ( 11%) ] Loss: 0.0082 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3806 top1= 89.1727


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8978 top1= 65.0140


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0332 top1= 76.3722

Train epoch 12
[E12B0  |    320/60000 (  1%) ] Loss: 0.0112 top1= 99.6875
[E12B10 |   3520/60000 (  6%) ] Loss: 0.0164 top1= 99.3750
[E12B20 |   6720/60000 ( 11%) ] Loss: 0.0053 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3942 top1= 88.7720


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6602 top1= 65.9255


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9445 top1= 78.8762

Train epoch 13
[E13B0  |    320/60000 (  1%) ] Loss: 0.0218 top1= 99.3750
[E13B10 |   3520/60000 (  6%) ] Loss: 0.0042 top1=100.0000
[E13B20 |   6720/60000 ( 11%) ] Loss: 0.0038 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4033 top1= 89.1126


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8621 top1= 69.0705


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0008 top1= 78.0449

Train epoch 14
[E14B0  |    320/60000 (  1%) ] Loss: 0.0178 top1= 99.0625
[E14B10 |   3520/60000 (  6%) ] Loss: 0.0065 top1=100.0000
[E14B20 |   6720/60000 ( 11%) ] Loss: 0.0443 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4470 top1= 87.9708


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6537 top1= 68.0288


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8779 top1= 80.9095

Train epoch 15
[E15B0  |    320/60000 (  1%) ] Loss: 0.0086 top1= 99.6875
[E15B10 |   3520/60000 (  6%) ] Loss: 0.0039 top1=100.0000
[E15B20 |   6720/60000 ( 11%) ] Loss: 0.0248 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4268 top1= 88.9423


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9333 top1= 67.7484


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7762 top1= 82.6322

Train epoch 16
[E16B0  |    320/60000 (  1%) ] Loss: 0.0129 top1= 99.6875
[E16B10 |   3520/60000 (  6%) ] Loss: 0.0034 top1=100.0000
[E16B20 |   6720/60000 ( 11%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3439 top1= 90.5248


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1336 top1= 75.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7766 top1= 82.4619

Train epoch 17
[E17B0  |    320/60000 (  1%) ] Loss: 0.0075 top1= 99.6875
[E17B10 |   3520/60000 (  6%) ] Loss: 0.0024 top1=100.0000
[E17B20 |   6720/60000 ( 11%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3492 top1= 90.7452


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0953 top1= 76.4523


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8026 top1= 82.5821

Train epoch 18
[E18B0  |    320/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E18B10 |   3520/60000 (  6%) ] Loss: 0.0024 top1=100.0000
[E18B20 |   6720/60000 ( 11%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3371 top1= 91.3361


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0652 top1= 77.3438


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6907 top1= 84.3750

Train epoch 19
[E19B0  |    320/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E19B10 |   3520/60000 (  6%) ] Loss: 0.0022 top1=100.0000
[E19B20 |   6720/60000 ( 11%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3238 top1= 91.8069


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0490 top1= 77.8846


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6763 top1= 85.1062

Train epoch 20
[E20B0  |    320/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E20B10 |   3520/60000 (  6%) ] Loss: 0.0017 top1=100.0000
[E20B20 |   6720/60000 ( 11%) ] Loss: 0.0031 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3193 top1= 92.0974


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9783 top1= 79.1567


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6729 top1= 85.4567

Train epoch 21
[E21B0  |    320/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E21B10 |   3520/60000 (  6%) ] Loss: 0.0016 top1=100.0000
[E21B20 |   6720/60000 ( 11%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3181 top1= 92.2075


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9304 top1= 80.4888


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6725 top1= 85.6270

Train epoch 22
[E22B0  |    320/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E22B10 |   3520/60000 (  6%) ] Loss: 0.0014 top1=100.0000
[E22B20 |   6720/60000 ( 11%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3213 top1= 92.2877


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8943 top1= 81.3902


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6427 top1= 86.2480

Train epoch 23
[E23B0  |    320/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E23B10 |   3520/60000 (  6%) ] Loss: 0.0011 top1=100.0000
[E23B20 |   6720/60000 ( 11%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3190 top1= 92.4279


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8487 top1= 82.1514


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6470 top1= 86.3181

Train epoch 24
[E24B0  |    320/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E24B10 |   3520/60000 (  6%) ] Loss: 0.0010 top1=100.0000
[E24B20 |   6720/60000 ( 11%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3197 top1= 92.5280


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8147 top1= 82.9427


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6399 top1= 86.4984

Train epoch 25
[E25B0  |    320/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E25B10 |   3520/60000 (  6%) ] Loss: 0.0009 top1=100.0000
[E25B20 |   6720/60000 ( 11%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3206 top1= 92.5681


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7885 top1= 83.5136


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6331 top1= 86.6787

Train epoch 26
[E26B0  |    320/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E26B10 |   3520/60000 (  6%) ] Loss: 0.0009 top1=100.0000
[E26B20 |   6720/60000 ( 11%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3218 top1= 92.6382


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7721 top1= 84.0044


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6228 top1= 86.9291

Train epoch 27
[E27B0  |    320/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E27B10 |   3520/60000 (  6%) ] Loss: 0.0008 top1=100.0000
[E27B20 |   6720/60000 ( 11%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3231 top1= 92.6883


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7594 top1= 84.3450


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6112 top1= 87.2897

Train epoch 28
[E28B0  |    320/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E28B10 |   3520/60000 (  6%) ] Loss: 0.0008 top1=100.0000
[E28B20 |   6720/60000 ( 11%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3244 top1= 92.6683


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7480 top1= 84.5553


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6009 top1= 87.5701

Train epoch 29
[E29B0  |    320/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E29B10 |   3520/60000 (  6%) ] Loss: 0.0007 top1=100.0000
[E29B20 |   6720/60000 ( 11%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3256 top1= 92.6883


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7350 top1= 84.8157


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5924 top1= 87.7905

Train epoch 30
[E30B0  |    320/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E30B10 |   3520/60000 (  6%) ] Loss: 0.0007 top1=100.0000
[E30B20 |   6720/60000 ( 11%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3268 top1= 92.7183


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7231 top1= 85.1062


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5852 top1= 87.9507

