
=== 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 0x7f2d5fbfd6d0>

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: 0.4311 top1= 90.3125
[E 1B20 |   6720/60000 ( 11%) ] Loss: 0.0798 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=3.0813 top1= 40.3245


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.5820 top1= 47.2055


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3493 top1= 45.3826

Train epoch 2
[E 2B0  |    320/60000 (  1%) ] Loss: 0.1706 top1= 95.9375
[E 2B10 |   3520/60000 (  6%) ] Loss: 0.0559 top1= 98.7500
[E 2B20 |   6720/60000 ( 11%) ] Loss: 0.0839 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7041 top1= 52.9948


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1496 top1= 48.2672


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4233 top1= 50.7312

Train epoch 3
[E 3B0  |    320/60000 (  1%) ] Loss: 0.0739 top1= 98.1250
[E 3B10 |   3520/60000 (  6%) ] Loss: 0.0514 top1= 98.1250
[E 3B20 |   6720/60000 ( 11%) ] Loss: 0.0315 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4395 top1= 60.8373


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7138 top1= 47.8966


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5990 top1= 51.0016

Train epoch 4
[E 4B0  |    320/60000 (  1%) ] Loss: 0.0622 top1= 98.4375
[E 4B10 |   3520/60000 (  6%) ] Loss: 0.0369 top1= 99.3750
[E 4B20 |   6720/60000 ( 11%) ] Loss: 0.0340 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4799 top1= 62.6302


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3878 top1= 50.1102


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3030 top1= 52.3337

Train epoch 5
[E 5B0  |    320/60000 (  1%) ] Loss: 0.0591 top1= 97.8125
[E 5B10 |   3520/60000 (  6%) ] Loss: 0.0478 top1= 98.7500
[E 5B20 |   6720/60000 ( 11%) ] Loss: 0.0526 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1836 top1= 67.3277


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7630 top1= 51.9331


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9995 top1= 60.0461

Train epoch 6
[E 6B0  |    320/60000 (  1%) ] Loss: 0.0904 top1= 97.5000
[E 6B10 |   3520/60000 (  6%) ] Loss: 0.0170 top1=100.0000
[E 6B20 |   6720/60000 ( 11%) ] Loss: 0.0727 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9606 top1= 73.4776


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5532 top1= 50.1803


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1599 top1= 59.9860

Train epoch 7
[E 7B0  |    320/60000 (  1%) ] Loss: 0.0915 top1= 96.5625
[E 7B10 |   3520/60000 (  6%) ] Loss: 0.0424 top1= 98.7500
[E 7B20 |   6720/60000 ( 11%) ] Loss: 0.0626 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0107 top1= 70.2724


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9237 top1= 49.5793


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8155 top1= 61.6186

Train epoch 8
[E 8B0  |    320/60000 (  1%) ] Loss: 0.0324 top1= 99.0625
[E 8B10 |   3520/60000 (  6%) ] Loss: 0.0226 top1= 99.3750
[E 8B20 |   6720/60000 ( 11%) ] Loss: 0.0311 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1336 top1= 70.3125


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5450 top1= 56.8610


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4885 top1= 65.8253

Train epoch 9
[E 9B0  |    320/60000 (  1%) ] Loss: 0.0328 top1= 98.1250
[E 9B10 |   3520/60000 (  6%) ] Loss: 0.0165 top1= 99.6875
[E 9B20 |   6720/60000 ( 11%) ] Loss: 0.0241 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9009 top1= 75.1903


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5464 top1= 55.0280


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7949 top1= 60.7572

Train epoch 10
[E10B0  |    320/60000 (  1%) ] Loss: 0.0261 top1= 99.3750
[E10B10 |   3520/60000 (  6%) ] Loss: 0.0120 top1= 99.6875
[E10B20 |   6720/60000 ( 11%) ] Loss: 0.0206 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9041 top1= 75.4207


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1826 top1= 53.5657


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6807 top1= 64.1927

Train epoch 11
[E11B0  |    320/60000 (  1%) ] Loss: 0.0284 top1= 99.0625
[E11B10 |   3520/60000 (  6%) ] Loss: 0.0101 top1=100.0000
[E11B20 |   6720/60000 ( 11%) ] Loss: 0.0134 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0672 top1= 73.0168


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9905 top1= 56.4503


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0690 top1= 61.4884

Train epoch 12
[E12B0  |    320/60000 (  1%) ] Loss: 0.0469 top1= 98.4375
[E12B10 |   3520/60000 (  6%) ] Loss: 0.0158 top1= 99.6875
[E12B20 |   6720/60000 ( 11%) ] Loss: 0.0195 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9094 top1= 76.6927


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9490 top1= 57.3017


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4619 top1= 69.3209

Train epoch 13
[E13B0  |    320/60000 (  1%) ] Loss: 0.0281 top1= 99.0625
[E13B10 |   3520/60000 (  6%) ] Loss: 0.0102 top1= 99.6875
[E13B20 |   6720/60000 ( 11%) ] Loss: 0.0104 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6456 top1= 82.9227


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7502 top1= 55.1482


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4701 top1= 70.1222

Train epoch 14
[E14B0  |    320/60000 (  1%) ] Loss: 0.0151 top1= 99.0625
[E14B10 |   3520/60000 (  6%) ] Loss: 0.0133 top1= 99.6875
[E14B20 |   6720/60000 ( 11%) ] Loss: 0.0564 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5783 top1= 83.6138


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7742 top1= 54.1567


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6164 top1= 68.2392

Train epoch 15
[E15B0  |    320/60000 (  1%) ] Loss: 0.0144 top1= 99.6875
[E15B10 |   3520/60000 (  6%) ] Loss: 0.0160 top1= 99.3750
[E15B20 |   6720/60000 ( 11%) ] Loss: 0.0134 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6711 top1= 82.5321


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8761 top1= 55.9095


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2545 top1= 74.2087

Train epoch 16
[E16B0  |    320/60000 (  1%) ] Loss: 0.0070 top1=100.0000
[E16B10 |   3520/60000 (  6%) ] Loss: 0.0049 top1=100.0000
[E16B20 |   6720/60000 ( 11%) ] Loss: 0.0243 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5398 top1= 85.5970


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4442 top1= 58.7740


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2937 top1= 74.1787

Train epoch 17
[E17B0  |    320/60000 (  1%) ] Loss: 0.0214 top1= 99.3750
[E17B10 |   3520/60000 (  6%) ] Loss: 0.0058 top1=100.0000
[E17B20 |   6720/60000 ( 11%) ] Loss: 0.0099 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6143 top1= 83.5938


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3528 top1= 61.8089


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0203 top1= 64.4531

Train epoch 18
[E18B0  |    320/60000 (  1%) ] Loss: 0.0121 top1= 99.6875
[E18B10 |   3520/60000 (  6%) ] Loss: 0.0115 top1= 99.3750
[E18B20 |   6720/60000 ( 11%) ] Loss: 0.0079 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6638 top1= 83.2031


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0016 top1= 58.2632


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3667 top1= 74.6494

Train epoch 19
[E19B0  |    320/60000 (  1%) ] Loss: 0.0064 top1= 99.6875
[E19B10 |   3520/60000 (  6%) ] Loss: 0.0085 top1= 99.6875
[E19B20 |   6720/60000 ( 11%) ] Loss: 0.0144 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6921 top1= 83.5637


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4466 top1= 61.4984


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1923 top1= 76.1018

Train epoch 20
[E20B0  |    320/60000 (  1%) ] Loss: 0.0113 top1= 99.6875
[E20B10 |   3520/60000 (  6%) ] Loss: 0.0212 top1= 99.6875
[E20B20 |   6720/60000 ( 11%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6388 top1= 84.1546


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8717 top1= 58.6639


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3590 top1= 75.0501

Train epoch 21
[E21B0  |    320/60000 (  1%) ] Loss: 0.0070 top1=100.0000
[E21B10 |   3520/60000 (  6%) ] Loss: 0.0154 top1= 99.3750
[E21B20 |   6720/60000 ( 11%) ] Loss: 0.0093 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5139 top1= 87.0092


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9148 top1= 66.0657


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6648 top1= 72.0653

Train epoch 22
[E22B0  |    320/60000 (  1%) ] Loss: 0.0561 top1= 97.8125
[E22B10 |   3520/60000 (  6%) ] Loss: 0.0094 top1= 99.6875
[E22B20 |   6720/60000 ( 11%) ] Loss: 0.0114 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5316 top1= 86.1378


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0260 top1= 58.6538


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1996 top1= 75.7011

Train epoch 23
[E23B0  |    320/60000 (  1%) ] Loss: 0.0067 top1= 99.6875
[E23B10 |   3520/60000 (  6%) ] Loss: 0.0091 top1= 99.3750
[E23B20 |   6720/60000 ( 11%) ] Loss: 0.0070 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5508 top1= 85.9876


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4151 top1= 63.0409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0060 top1= 69.6214

Train epoch 24
[E24B0  |    320/60000 (  1%) ] Loss: 0.0114 top1= 99.6875
[E24B10 |   3520/60000 (  6%) ] Loss: 0.0308 top1= 99.0625
[E24B20 |   6720/60000 ( 11%) ] Loss: 0.0059 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4853 top1= 87.3898


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5570 top1= 61.5585


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6359 top1= 71.3742

Train epoch 25
[E25B0  |    320/60000 (  1%) ] Loss: 0.0222 top1= 99.3750
[E25B10 |   3520/60000 (  6%) ] Loss: 0.0200 top1= 99.3750
[E25B20 |   6720/60000 ( 11%) ] Loss: 0.0212 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5265 top1= 86.5885


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7259 top1= 67.9087


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0895 top1= 79.2268

Train epoch 26
[E26B0  |    320/60000 (  1%) ] Loss: 0.0092 top1= 99.6875
[E26B10 |   3520/60000 (  6%) ] Loss: 0.0064 top1=100.0000
[E26B20 |   6720/60000 ( 11%) ] Loss: 0.0088 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4621 top1= 88.2011


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8957 top1= 66.3562


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3795 top1= 76.9631

Train epoch 27
[E27B0  |    320/60000 (  1%) ] Loss: 0.0037 top1=100.0000
[E27B10 |   3520/60000 (  6%) ] Loss: 0.0163 top1= 99.0625
[E27B20 |   6720/60000 ( 11%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5199 top1= 87.2897


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8354 top1= 64.4531


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3895 top1= 74.4391

Train epoch 28
[E28B0  |    320/60000 (  1%) ] Loss: 0.0318 top1= 99.6875
[E28B10 |   3520/60000 (  6%) ] Loss: 0.0022 top1=100.0000
[E28B20 |   6720/60000 ( 11%) ] Loss: 0.0038 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4136 top1= 89.4131


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4051 top1= 62.1094


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2297 top1= 76.4323

Train epoch 29
[E29B0  |    320/60000 (  1%) ] Loss: 0.0040 top1=100.0000
[E29B10 |   3520/60000 (  6%) ] Loss: 0.0081 top1= 99.6875
[E29B20 |   6720/60000 ( 11%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4098 top1= 89.5533


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8561 top1= 68.0489


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2545 top1= 76.3922

Train epoch 30
[E30B0  |    320/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E30B10 |   3520/60000 (  6%) ] Loss: 0.0038 top1=100.0000
[E30B20 |   6720/60000 ( 11%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4245 top1= 89.2829


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6809 top1= 69.4010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1431 top1= 77.5441

