
=== 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 0x7f40202d06d0>

Train epoch 1
[E 1B0  |    320/60000 (  1%) ] Loss: 2.3027 top1= 10.3125

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([3, 1, 1, 4, 4], device='cuda:0')
Worker 1 has targets: tensor([4, 0, 2, 4, 1], device='cuda:0')
Worker 2 has targets: tensor([1, 2, 2, 4, 0], device='cuda:0')
Worker 3 has targets: tensor([4, 1, 3, 4, 2], device='cuda:0')
Worker 4 has targets: tensor([4, 2, 1, 3, 0], device='cuda:0')
Worker 5 has targets: tensor([7, 5, 6, 6, 9], device='cuda:0')
Worker 6 has targets: tensor([9, 6, 7, 6, 8], device='cuda:0')
Worker 7 has targets: tensor([7, 8, 6, 5, 7], device='cuda:0')
Worker 8 has targets: tensor([7, 8, 5, 8, 9], device='cuda:0')
Worker 9 has targets: tensor([6, 8, 8, 6, 7], device='cuda:0')


[E 1B10 |   3520/60000 (  6%) ] Loss: 1.0591 top1= 63.4375
[E 1B20 |   6720/60000 ( 11%) ] Loss: 0.3839 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5867 top1= 82.7123


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3600 top1= 49.3590


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6538 top1= 44.4812

Train epoch 2
[E 2B0  |    320/60000 (  1%) ] Loss: 0.3187 top1= 91.2500
[E 2B10 |   3520/60000 (  6%) ] Loss: 0.2300 top1= 92.1875
[E 2B20 |   6720/60000 ( 11%) ] Loss: 0.2462 top1= 91.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4327 top1= 87.1595


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0774 top1= 53.6458


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0706 top1= 50.4006

Train epoch 3
[E 3B0  |    320/60000 (  1%) ] Loss: 0.2059 top1= 94.3750
[E 3B10 |   3520/60000 (  6%) ] Loss: 0.1622 top1= 95.0000
[E 3B20 |   6720/60000 ( 11%) ] Loss: 0.1613 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3679 top1= 88.4816


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7793 top1= 57.9026


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9163 top1= 53.5056

Train epoch 4
[E 4B0  |    320/60000 (  1%) ] Loss: 0.1438 top1= 96.8750
[E 4B10 |   3520/60000 (  6%) ] Loss: 0.0786 top1= 97.8125
[E 4B20 |   6720/60000 ( 11%) ] Loss: 0.0816 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3410 top1= 89.3530


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6152 top1= 61.2280


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7712 top1= 56.2600

Train epoch 5
[E 5B0  |    320/60000 (  1%) ] Loss: 0.0969 top1= 98.1250
[E 5B10 |   3520/60000 (  6%) ] Loss: 0.0427 top1= 99.0625
[E 5B20 |   6720/60000 ( 11%) ] Loss: 0.0570 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3155 top1= 90.1643


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4939 top1= 63.6719


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5742 top1= 59.4050

Train epoch 6
[E 6B0  |    320/60000 (  1%) ] Loss: 0.0686 top1= 98.4375
[E 6B10 |   3520/60000 (  6%) ] Loss: 0.0344 top1= 99.6875
[E 6B20 |   6720/60000 ( 11%) ] Loss: 0.0409 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3219 top1= 89.9740


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4798 top1= 65.8353


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6684 top1= 59.5052

Train epoch 7
[E 7B0  |    320/60000 (  1%) ] Loss: 0.0535 top1= 98.7500
[E 7B10 |   3520/60000 (  6%) ] Loss: 0.0611 top1= 97.1875
[E 7B20 |   6720/60000 ( 11%) ] Loss: 0.0693 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3509 top1= 89.2127


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4605 top1= 67.1675


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6697 top1= 60.1963

Train epoch 8
[E 8B0  |    320/60000 (  1%) ] Loss: 0.1321 top1= 95.0000
[E 8B10 |   3520/60000 (  6%) ] Loss: 0.0714 top1= 97.5000
[E 8B20 |   6720/60000 ( 11%) ] Loss: 0.0371 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3003 top1= 90.6450


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4138 top1= 68.2091


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5766 top1= 59.7756

Train epoch 9
[E 9B0  |    320/60000 (  1%) ] Loss: 0.0426 top1= 98.4375
[E 9B10 |   3520/60000 (  6%) ] Loss: 0.0384 top1= 98.7500
[E 9B20 |   6720/60000 ( 11%) ] Loss: 0.0205 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2905 top1= 90.9255


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3938 top1= 68.8201


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3225 top1= 65.1843

Train epoch 10
[E10B0  |    320/60000 (  1%) ] Loss: 0.0208 top1= 99.6875
[E10B10 |   3520/60000 (  6%) ] Loss: 0.0295 top1= 99.6875
[E10B20 |   6720/60000 ( 11%) ] Loss: 0.0242 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2743 top1= 91.6066


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2768 top1= 70.5028


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1388 top1= 69.7817

Train epoch 11
[E11B0  |    320/60000 (  1%) ] Loss: 0.0122 top1=100.0000
[E11B10 |   3520/60000 (  6%) ] Loss: 0.0131 top1= 99.6875
[E11B20 |   6720/60000 ( 11%) ] Loss: 0.0178 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2828 top1= 91.4663


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1315 top1= 72.4960


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1238 top1= 72.5661

Train epoch 12
[E12B0  |    320/60000 (  1%) ] Loss: 0.0105 top1= 99.6875
[E12B10 |   3520/60000 (  6%) ] Loss: 0.0142 top1= 99.6875
[E12B20 |   6720/60000 ( 11%) ] Loss: 0.0138 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2712 top1= 91.9171


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9352 top1= 76.5325


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0921 top1= 73.1270

Train epoch 13
[E13B0  |    320/60000 (  1%) ] Loss: 0.0063 top1=100.0000
[E13B10 |   3520/60000 (  6%) ] Loss: 0.0047 top1=100.0000
[E13B20 |   6720/60000 ( 11%) ] Loss: 0.0049 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2649 top1= 92.3377


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8656 top1= 78.1450


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8939 top1= 76.9732

Train epoch 14
[E14B0  |    320/60000 (  1%) ] Loss: 0.0042 top1=100.0000
[E14B10 |   3520/60000 (  6%) ] Loss: 0.0197 top1= 99.3750
[E14B20 |   6720/60000 ( 11%) ] Loss: 0.0059 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2667 top1= 92.6983


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8305 top1= 79.3269


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7718 top1= 80.0280

Train epoch 15
[E15B0  |    320/60000 (  1%) ] Loss: 0.0046 top1=100.0000
[E15B10 |   3520/60000 (  6%) ] Loss: 0.0045 top1=100.0000
[E15B20 |   6720/60000 ( 11%) ] Loss: 0.0036 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2669 top1= 92.9387


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7714 top1= 80.8393


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7369 top1= 81.4002

Train epoch 16
[E16B0  |    320/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E16B10 |   3520/60000 (  6%) ] Loss: 0.0033 top1=100.0000
[E16B20 |   6720/60000 ( 11%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2682 top1= 92.9988


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7456 top1= 81.7208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7290 top1= 81.9712

Train epoch 17
[E17B0  |    320/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E17B10 |   3520/60000 (  6%) ] Loss: 0.0028 top1=100.0000
[E17B20 |   6720/60000 ( 11%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2716 top1= 92.9888


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7160 top1= 82.6923


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7556 top1= 81.6707

Train epoch 18
[E18B0  |    320/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E18B10 |   3520/60000 (  6%) ] Loss: 0.0024 top1=100.0000
[E18B20 |   6720/60000 ( 11%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2742 top1= 93.0088


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6952 top1= 83.2031


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7469 top1= 82.0913

Train epoch 19
[E19B0  |    320/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E19B10 |   3520/60000 (  6%) ] Loss: 0.0020 top1=100.0000
[E19B20 |   6720/60000 ( 11%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2758 top1= 93.0789


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6849 top1= 83.7039


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7266 top1= 82.6222

Train epoch 20
[E20B0  |    320/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E20B10 |   3520/60000 (  6%) ] Loss: 0.0017 top1=100.0000
[E20B20 |   6720/60000 ( 11%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2771 top1= 93.0990


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6822 top1= 83.9643


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6951 top1= 83.4235

Train epoch 21
[E21B0  |    320/60000 (  1%) ] Loss: 0.0015 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=0.2785 top1= 93.0990


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6788 top1= 84.2548


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6648 top1= 84.0845

Train epoch 22
[E22B0  |    320/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E22B10 |   3520/60000 (  6%) ] Loss: 0.0015 top1=100.0000
[E22B20 |   6720/60000 ( 11%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2799 top1= 93.1791


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6701 top1= 84.6054


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6438 top1= 84.7155

Train epoch 23
[E23B0  |    320/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E23B10 |   3520/60000 (  6%) ] Loss: 0.0014 top1=100.0000
[E23B20 |   6720/60000 ( 11%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2813 top1= 93.1991


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6581 top1= 84.9359


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6305 top1= 85.0962

Train epoch 24
[E24B0  |    320/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E24B10 |   3520/60000 (  6%) ] Loss: 0.0013 top1=100.0000
[E24B20 |   6720/60000 ( 11%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2827 top1= 93.2392


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6442 top1= 85.3566


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6208 top1= 85.3365

Train epoch 25
[E25B0  |    320/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E25B10 |   3520/60000 (  6%) ] Loss: 0.0012 top1=100.0000
[E25B20 |   6720/60000 ( 11%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2839 top1= 93.2592


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6314 top1= 85.6771


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6123 top1= 85.5569

Train epoch 26
[E26B0  |    320/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E26B10 |   3520/60000 (  6%) ] Loss: 0.0011 top1=100.0000
[E26B20 |   6720/60000 ( 11%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2852 top1= 93.2792


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6210 top1= 86.0276


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6039 top1= 85.9075

Train epoch 27
[E27B0  |    320/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E27B10 |   3520/60000 (  6%) ] Loss: 0.0011 top1=100.0000
[E27B20 |   6720/60000 ( 11%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2864 top1= 93.2792


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6111 top1= 86.3582


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5959 top1= 86.1879

Train epoch 28
[E28B0  |    320/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E28B10 |   3520/60000 (  6%) ] Loss: 0.0010 top1=100.0000
[E28B20 |   6720/60000 ( 11%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2876 top1= 93.3193


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6021 top1= 86.6186


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5880 top1= 86.4283

Train epoch 29
[E29B0  |    320/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E29B10 |   3520/60000 (  6%) ] Loss: 0.0010 top1=100.0000
[E29B20 |   6720/60000 ( 11%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2887 top1= 93.3894


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5942 top1= 86.8389


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5809 top1= 86.6787

Train epoch 30
[E30B0  |    320/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E30B10 |   3520/60000 (  6%) ] Loss: 0.0009 top1=100.0000
[E30B20 |   6720/60000 ( 11%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2898 top1= 93.4095


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5864 top1= 87.0292


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5739 top1= 86.8990

