
=== 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 SGDMWorker(index=10, momentum=0.9)
=> Add worker SGDMWorker(index=11, momentum=0.9)
=> Add worker SGDMWorker(index=12, momentum=0.9)
=> Add worker SGDMWorker(index=13, momentum=0.9)
=> Add worker SGDMWorker(index=14, momentum=0.9)
=> Add worker SGDMWorker(index=15, momentum=0.9)
=> Add worker SGDMWorker(index=16, momentum=0.9)
=> Add worker SGDMWorker(index=17, momentum=0.9)
=> Add worker SGDMWorker(index=18, momentum=0.9)
=> Add worker SGDMWorker(index=19, momentum=0.9)

=== Start adding graph ===
<codes.graph_utils.Dumbbell object at 0x7f607e8476d0>

Train epoch 1
[E 1B0  |    640/60000 (  1%) ] Loss: 2.3066 top1=  9.2188

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([3, 2, 2, 4, 3], device='cuda:0')
Worker 1 has targets: tensor([1, 0, 0, 4, 0], device='cuda:0')
Worker 2 has targets: tensor([4, 1, 0, 1, 0], device='cuda:0')
Worker 3 has targets: tensor([0, 1, 4, 1, 3], device='cuda:0')
Worker 4 has targets: tensor([0, 4, 1, 2, 4], device='cuda:0')
Worker 5 has targets: tensor([2, 2, 4, 4, 4], device='cuda:0')
Worker 6 has targets: tensor([1, 1, 4, 4, 3], device='cuda:0')
Worker 7 has targets: tensor([4, 4, 1, 3, 0], device='cuda:0')
Worker 8 has targets: tensor([1, 3, 1, 0, 4], device='cuda:0')
Worker 9 has targets: tensor([1, 3, 3, 3, 1], device='cuda:0')
Worker 10 has targets: tensor([8, 9, 7, 7, 9], device='cuda:0')
Worker 11 has targets: tensor([8, 9, 6, 6, 7], device='cuda:0')
Worker 12 has targets: tensor([8, 6, 5, 7, 8], device='cuda:0')
Worker 13 has targets: tensor([7, 6, 9, 6, 5], device='cuda:0')
Worker 14 has targets: tensor([8, 5, 8, 6, 7], device='cuda:0')
Worker 15 has targets: tensor([9, 5, 6, 8, 6], device='cuda:0')
Worker 16 has targets: tensor([7, 7, 8, 5, 8], device='cuda:0')
Worker 17 has targets: tensor([9, 7, 5, 6, 6], device='cuda:0')
Worker 18 has targets: tensor([7, 7, 7, 6, 6], device='cuda:0')
Worker 19 has targets: tensor([5, 7, 9, 9, 7], device='cuda:0')


[E 1B10 |   7040/60000 ( 12%) ] Loss: 1.0287 top1= 62.0312
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.4242 top1= 87.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7158 top1= 80.9696


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3457 top1= 49.2989


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9465 top1= 44.4311

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.3777 top1= 89.0625
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.2315 top1= 92.6562
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.2055 top1= 93.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6876 top1= 86.1779


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1483 top1= 49.8898


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5971 top1= 45.8333

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.1554 top1= 95.6250
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.1089 top1= 96.7188
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.1240 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6249 top1= 87.3898


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4708 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8377 top1= 46.3442

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1013 top1= 97.8125
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.0769 top1= 97.8125
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.0817 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5610 top1= 87.8906


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7880 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0853 top1= 46.5845

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.0762 top1= 98.2812
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.0567 top1= 98.4375
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.0561 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5132 top1= 88.1410


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9914 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3935 top1= 46.7047

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0567 top1= 98.9062
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0404 top1= 98.7500
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0396 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4739 top1= 88.4916


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1657 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6927 top1= 46.7448

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0425 top1= 99.2188
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0277 top1= 99.3750
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0295 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4460 top1= 88.3714


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3399 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1032 top1= 46.8049

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0308 top1= 99.5312
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0194 top1= 99.6875
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0204 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4275 top1= 88.1210


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5568 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4606 top1= 46.8750

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0213 top1= 99.6875
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0144 top1= 99.6875
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0147 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4125 top1= 88.0609


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7806 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6879 top1= 46.9151

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0132 top1= 99.6875
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0114 top1= 99.8438
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0119 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3888 top1= 88.5317


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0625 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8442 top1= 47.0954

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0083 top1= 99.8438
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0086 top1=100.0000
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0124 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3695 top1= 88.8221


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3261 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8012 top1= 47.0954

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0062 top1=100.0000
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0056 top1=100.0000
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0177 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3591 top1= 89.0224


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5365 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6280 top1= 47.1955

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0043 top1=100.0000
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0040 top1=100.0000
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0064 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3504 top1= 89.3830


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.6805 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6308 top1= 46.5545

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0250 top1= 99.2188
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0041 top1=100.0000
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0067 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3430 top1= 89.5533


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8007 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2713 top1= 47.1955

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0072 top1= 99.8438
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0060 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3493 top1= 88.9123


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.8806 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3456 top1= 47.2055

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0060 top1= 99.8438
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0029 top1=100.0000
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0036 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3424 top1= 88.9824


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9292 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5759 top1= 47.2456

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0023 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3369 top1= 89.0024


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9880 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.6971 top1= 47.2456

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0017 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3296 top1= 89.2628


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0383 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8340 top1= 47.2556

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0015 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3220 top1= 89.5533


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0742 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9200 top1= 47.2656

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0013 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3185 top1= 89.6134


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0963 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9655 top1= 47.2556

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0012 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3166 top1= 89.5733


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1115 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.0086 top1= 47.2456

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0011 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3147 top1= 89.6034


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1212 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.0423 top1= 47.2656

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0011 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3129 top1= 89.6534


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1168 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.0602 top1= 47.2756

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0010 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3110 top1= 89.6735


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1085 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.0659 top1= 47.2756

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0010 top1=100.0000
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3095 top1= 89.6835


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0939 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.0645 top1= 47.2756

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0009 top1=100.0000
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3078 top1= 89.7236


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0803 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.0534 top1= 47.2556

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0009 top1=100.0000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3064 top1= 89.7636


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0541 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.0420 top1= 47.2356

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0008 top1=100.0000
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3049 top1= 89.8337


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0301 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.0233 top1= 47.2356

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0008 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3034 top1= 89.9038


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0018 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9999 top1= 47.2356

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0008 top1=100.0000
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3022 top1= 89.8938


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9660 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9751 top1= 47.2356

