
=== 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 0x7fbccd9ed730>

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: 1.0465 top1= 60.9375
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.4163 top1= 87.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7471 top1= 77.7444


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.0963 top1= 49.2889


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5314 top1= 44.2308

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.2884 top1= 90.7812
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.1966 top1= 93.7500
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.2058 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6993 top1= 83.8341


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5070 top1= 49.6995


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3319 top1= 45.8033

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.1674 top1= 94.6875
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.1162 top1= 96.5625
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.1286 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6380 top1= 84.6755


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5581 top1= 50.2103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5076 top1= 46.1438

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1189 top1= 96.8750
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.0834 top1= 97.5000
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.0886 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5873 top1= 85.6470


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7635 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5257 top1= 46.5044

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.0853 top1= 98.1250
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.0662 top1= 98.1250
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.0710 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5514 top1= 85.9776


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8113 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6955 top1= 46.6146

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0654 top1= 98.7500
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0474 top1= 98.4375
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0575 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5345 top1= 85.2764


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8234 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7775 top1= 46.7849

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0514 top1= 98.9062
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0365 top1= 98.7500
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0437 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5263 top1= 84.2248


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8092 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2624 top1= 46.7548

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0431 top1= 98.9062
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0253 top1= 99.2188
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0314 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5287 top1= 83.1430


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8461 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7044 top1= 46.8049

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0348 top1= 99.3750
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0237 top1= 99.3750
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0234 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5291 top1= 82.6522


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0825 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8997 top1= 46.6747

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0286 top1= 99.2188
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0165 top1= 99.6875
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0218 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5281 top1= 82.1514


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1551 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1729 top1= 46.7248

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0232 top1= 99.3750
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0136 top1= 99.8438
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0209 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4978 top1= 83.6038


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.4459 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.9771 top1= 46.9551

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0133 top1= 99.6875
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0177 top1= 99.5312
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0379 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4539 top1= 85.7973


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.7195 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5022 top1= 47.0853

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0109 top1= 99.6875
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0071 top1=100.0000
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0387 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4267 top1= 87.5100


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.9597 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9922 top1= 46.6446

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0265 top1= 98.9062
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0137 top1= 99.5312
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0143 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4493 top1= 85.5569


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1405 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1121 top1= 47.0954

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0053 top1= 99.8438
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0043 top1=100.0000
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0058 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4444 top1= 85.4868


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3208 top1= 50.6410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5236 top1= 47.2155

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0039 top1=100.0000
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0050 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4541 top1= 84.6454


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.4920 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8683 top1= 47.2055

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0028 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0040 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4510 top1= 84.5453


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.6092 top1= 50.6510


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.1328 top1= 47.2556

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0023 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4323 top1= 85.5869


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.7170 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3381 top1= 47.3057

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0020 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4321 top1= 85.4367


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8425 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.5178 top1= 47.3057

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0016 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4362 top1= 85.1763


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.9722 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.6760 top1= 47.2857

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0014 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4363 top1= 85.1663


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.0836 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8065 top1= 47.2857

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0012 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4363 top1= 85.1062


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.1862 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.9222 top1= 47.2957

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0011 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4357 top1= 85.1562


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.2866 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.0310 top1= 47.2957

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: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4362 top1= 85.1262


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.3756 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.1331 top1= 47.2957

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=0.4364 top1= 85.1062


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.4669 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.2262 top1= 47.2957

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=0.4367 top1= 85.0861


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.5534 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.3139 top1= 47.2857

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0008 top1=100.0000
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0008 top1=100.0000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4366 top1= 85.1262


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.6343 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.3966 top1= 47.2857

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0008 top1=100.0000
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0009 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4368 top1= 85.0962


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.7158 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.4744 top1= 47.2857

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0007 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4371 top1= 85.0962


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.7845 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.5467 top1= 47.2857

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0007 top1=100.0000
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0007 top1=100.0000
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0008 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4374 top1= 85.0661


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.8535 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=8.6174 top1= 47.2957

