
=== 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 0x7f819646d730>

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: 1.0369 top1= 61.7188
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.4004 top1= 88.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7370 top1= 78.2352


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.1292 top1= 49.2788


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7707 top1= 44.2208

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.2859 top1= 90.7812
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.1924 top1= 93.7500
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.1985 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6901 top1= 84.0946


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6220 top1= 49.7897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4842 top1= 45.7632

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.1628 top1= 94.6875
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.1095 top1= 96.8750
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.1245 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6248 top1= 85.3666


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5646 top1= 50.1402


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6445 top1= 46.1538

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1176 top1= 96.7188
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.0802 top1= 97.9688
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.0799 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5756 top1= 85.6571


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7560 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6283 top1= 46.4543

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.0818 top1= 98.1250
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.0631 top1= 98.2812
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.0578 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5363 top1= 86.2480


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8811 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7584 top1= 46.7248

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0580 top1= 98.5938
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0430 top1= 98.5938
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0489 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5007 top1= 86.9591


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0031 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8123 top1= 46.7648

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0456 top1= 99.2188
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0302 top1= 99.3750
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0333 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4812 top1= 86.4583


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1194 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0673 top1= 46.9451

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0349 top1= 99.3750
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0228 top1= 99.3750
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0257 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4658 top1= 85.9575


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1829 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5931 top1= 46.7648

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0317 top1= 99.0625
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0147 top1= 99.8438
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0233 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4762 top1= 85.1362


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2052 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8355 top1= 46.8550

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0206 top1= 99.5312
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0143 top1= 99.6875
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0125 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4636 top1= 85.1062


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.3996 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1933 top1= 46.7849

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0129 top1= 99.8438
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0101 top1=100.0000
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0104 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4507 top1= 85.6070


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.5622 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.2952 top1= 47.0353

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0071 top1= 99.8438
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0080 top1=100.0000
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0160 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4319 top1= 86.3482


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7979 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1755 top1= 47.0252

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0065 top1=100.0000
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0046 top1=100.0000
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0203 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4113 top1= 87.0393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1029 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9542 top1= 47.1855

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0040 top1=100.0000
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0033 top1=100.0000
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0088 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3908 top1= 88.3514


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3661 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9028 top1= 46.5445

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0237 top1= 99.2188
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0038 top1=100.0000
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0048 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3937 top1= 87.7604


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5333 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5131 top1= 47.2656

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0028 top1=100.0000
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0035 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4036 top1= 86.8089


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.7171 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8114 top1= 47.2456

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0025 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4225 top1= 85.7672


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8487 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1880 top1= 47.1855

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0019 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4173 top1= 85.9175


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9800 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3980 top1= 47.2055

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0014 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3957 top1= 86.8089


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1108 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5703 top1= 47.2756

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0012 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3905 top1= 87.1094


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.2346 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7115 top1= 47.2957

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0009 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0010 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3924 top1= 86.8990


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.3483 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8542 top1= 47.2756

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0009 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3919 top1= 86.9091


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.4459 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9823 top1= 47.2756

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0008 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3916 top1= 86.9191


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.5457 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0917 top1= 47.2857

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0007 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3915 top1= 86.9291


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.6314 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1935 top1= 47.2756

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0007 top1=100.0000
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3914 top1= 86.9291


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.7206 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2846 top1= 47.2756

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0006 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0006 top1=100.0000
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0007 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3915 top1= 86.9091


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.7966 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.3702 top1= 47.2756

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0006 top1=100.0000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3913 top1= 86.8990


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.8721 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.4499 top1= 47.2756

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0005 top1=100.0000
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3915 top1= 86.8990


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9453 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5264 top1= 47.2756

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0005 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0005 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0006 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3916 top1= 86.8890


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.0134 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5980 top1= 47.2756

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0004 top1=100.0000
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0005 top1=100.0000
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0005 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3916 top1= 86.8990


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.0803 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.6641 top1= 47.2756

