
=== 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 0x7f171563e6d0>

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: 0.6190 top1= 78.1250
[E 1B20 |   6720/60000 ( 11%) ] Loss: 0.3917 top1= 88.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9953 top1= 28.7460


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2716 top1= 28.9363


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4061 top1= 30.8794

Train epoch 2
[E 2B0  |    320/60000 (  1%) ] Loss: 0.3553 top1= 87.8125
[E 2B10 |   3520/60000 (  6%) ] Loss: 0.1358 top1= 97.1875
[E 2B20 |   6720/60000 ( 11%) ] Loss: 0.0797 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9097 top1= 30.6591


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7478 top1= 28.3854


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6537 top1= 25.1302

Train epoch 3
[E 3B0  |    320/60000 (  1%) ] Loss: 0.1513 top1= 96.5625
[E 3B10 |   3520/60000 (  6%) ] Loss: 0.1068 top1= 96.8750
[E 3B20 |   6720/60000 ( 11%) ] Loss: 0.0712 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9074 top1= 30.1583


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2447 top1= 28.5958


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8178 top1= 27.2436

Train epoch 4
[E 4B0  |    320/60000 (  1%) ] Loss: 0.1264 top1= 97.1875
[E 4B10 |   3520/60000 (  6%) ] Loss: 0.0531 top1= 97.8125
[E 4B20 |   6720/60000 ( 11%) ] Loss: 0.0504 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8997 top1= 30.2784


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3786 top1= 28.8061


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8640 top1= 28.0649

Train epoch 5
[E 5B0  |    320/60000 (  1%) ] Loss: 0.1124 top1= 96.8750
[E 5B10 |   3520/60000 (  6%) ] Loss: 0.0798 top1= 98.4375
[E 5B20 |   6720/60000 ( 11%) ] Loss: 0.0517 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8433 top1= 31.8910


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3636 top1= 30.1082


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9678 top1= 27.4139

Train epoch 6
[E 6B0  |    320/60000 (  1%) ] Loss: 0.0865 top1= 98.1250
[E 6B10 |   3520/60000 (  6%) ] Loss: 0.0621 top1= 98.1250
[E 6B20 |   6720/60000 ( 11%) ] Loss: 0.0735 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8491 top1= 32.0112


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5690 top1= 30.6490


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0751 top1= 29.9479

Train epoch 7
[E 7B0  |    320/60000 (  1%) ] Loss: 0.1008 top1= 96.8750
[E 7B10 |   3520/60000 (  6%) ] Loss: 0.0497 top1= 98.7500
[E 7B20 |   6720/60000 ( 11%) ] Loss: 0.0486 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8672 top1= 31.8510


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8147 top1= 28.7660


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1581 top1= 30.2083

Train epoch 8
[E 8B0  |    320/60000 (  1%) ] Loss: 0.0589 top1= 98.7500
[E 8B10 |   3520/60000 (  6%) ] Loss: 0.0755 top1= 97.1875
[E 8B20 |   6720/60000 ( 11%) ] Loss: 0.0180 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8162 top1= 34.3149


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7526 top1= 29.0565


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2838 top1= 26.7929

Train epoch 9
[E 9B0  |    320/60000 (  1%) ] Loss: 0.0488 top1= 98.7500
[E 9B10 |   3520/60000 (  6%) ] Loss: 0.0185 top1= 99.6875
[E 9B20 |   6720/60000 ( 11%) ] Loss: 0.0485 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8656 top1= 33.4635


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0004 top1= 29.3169


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3738 top1= 28.7260

Train epoch 10
[E10B0  |    320/60000 (  1%) ] Loss: 0.0778 top1= 97.8125
[E10B10 |   3520/60000 (  6%) ] Loss: 0.1573 top1= 95.3125
[E10B20 |   6720/60000 ( 11%) ] Loss: 0.0996 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8994 top1= 33.0729


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0819 top1= 29.8277


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4299 top1= 28.3654

Train epoch 11
[E11B0  |    320/60000 (  1%) ] Loss: 0.0865 top1= 97.1875
[E11B10 |   3520/60000 (  6%) ] Loss: 0.0205 top1= 99.6875
[E11B20 |   6720/60000 ( 11%) ] Loss: 0.0207 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8678 top1= 34.9259


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1510 top1= 28.5256


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5103 top1= 27.9447

Train epoch 12
[E12B0  |    320/60000 (  1%) ] Loss: 0.0604 top1= 98.4375
[E12B10 |   3520/60000 (  6%) ] Loss: 0.0195 top1=100.0000
[E12B20 |   6720/60000 ( 11%) ] Loss: 0.0685 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7746 top1= 36.0477


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8989 top1= 30.0681


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6072 top1= 28.6659

Train epoch 13
[E13B0  |    320/60000 (  1%) ] Loss: 0.0703 top1= 98.1250
[E13B10 |   3520/60000 (  6%) ] Loss: 0.0469 top1= 99.0625
[E13B20 |   6720/60000 ( 11%) ] Loss: 0.0083 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8786 top1= 34.4651


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3669 top1= 29.0966


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6882 top1= 28.5657

Train epoch 14
[E14B0  |    320/60000 (  1%) ] Loss: 0.0603 top1= 98.7500
[E14B10 |   3520/60000 (  6%) ] Loss: 0.0181 top1= 99.6875
[E14B20 |   6720/60000 ( 11%) ] Loss: 0.0241 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9307 top1= 34.3450


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6580 top1= 27.9147


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8040 top1= 28.1851

Train epoch 15
[E15B0  |    320/60000 (  1%) ] Loss: 0.0417 top1= 99.0625
[E15B10 |   3520/60000 (  6%) ] Loss: 0.0429 top1= 98.7500
[E15B20 |   6720/60000 ( 11%) ] Loss: 0.0370 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9115 top1= 34.3450


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5773 top1= 29.8077


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7304 top1= 27.8746

Train epoch 16
[E16B0  |    320/60000 (  1%) ] Loss: 0.0675 top1= 97.8125
[E16B10 |   3520/60000 (  6%) ] Loss: 0.0167 top1= 99.3750
[E16B20 |   6720/60000 ( 11%) ] Loss: 0.0180 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8830 top1= 34.7356


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4133 top1= 29.9479


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7951 top1= 27.4139

Train epoch 17
[E17B0  |    320/60000 (  1%) ] Loss: 0.0603 top1= 98.1250
[E17B10 |   3520/60000 (  6%) ] Loss: 0.0196 top1=100.0000
[E17B20 |   6720/60000 ( 11%) ] Loss: 0.0468 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8799 top1= 34.7656


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3967 top1= 29.0865


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8284 top1= 27.1134

Train epoch 18
[E18B0  |    320/60000 (  1%) ] Loss: 0.0355 top1= 99.3750
[E18B10 |   3520/60000 (  6%) ] Loss: 0.0227 top1= 99.6875
[E18B20 |   6720/60000 ( 11%) ] Loss: 0.0696 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8950 top1= 35.5669


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6080 top1= 29.5773


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9802 top1= 26.6927

Train epoch 19
[E19B0  |    320/60000 (  1%) ] Loss: 0.0610 top1= 98.1250
[E19B10 |   3520/60000 (  6%) ] Loss: 0.0755 top1= 96.2500
[E19B20 |   6720/60000 ( 11%) ] Loss: 0.0287 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9439 top1= 34.6454


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7992 top1= 28.6258


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9592 top1= 29.6775

Train epoch 20
[E20B0  |    320/60000 (  1%) ] Loss: 0.0644 top1= 98.7500
[E20B10 |   3520/60000 (  6%) ] Loss: 0.0221 top1= 99.0625
[E20B20 |   6720/60000 ( 11%) ] Loss: 0.0246 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8991 top1= 35.3966


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7522 top1= 29.6174


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0305 top1= 29.8077

Train epoch 21
[E21B0  |    320/60000 (  1%) ] Loss: 0.0503 top1= 99.0625
[E21B10 |   3520/60000 (  6%) ] Loss: 0.0902 top1= 96.8750
[E21B20 |   6720/60000 ( 11%) ] Loss: 0.0304 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9785 top1= 33.3033


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8822 top1= 28.8161


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7829 top1= 31.6006

Train epoch 22
[E22B0  |    320/60000 (  1%) ] Loss: 0.1511 top1= 97.8125
[E22B10 |   3520/60000 (  6%) ] Loss: 0.0587 top1= 97.5000
[E22B20 |   6720/60000 ( 11%) ] Loss: 0.0325 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9563 top1= 35.3766


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9871 top1= 26.8329


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2181 top1= 29.4872

Train epoch 23
[E23B0  |    320/60000 (  1%) ] Loss: 0.0530 top1= 98.7500
[E23B10 |   3520/60000 (  6%) ] Loss: 0.0064 top1=100.0000
[E23B20 |   6720/60000 ( 11%) ] Loss: 0.0348 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8585 top1= 35.2965


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5317 top1= 30.4387


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1080 top1= 29.8277

Train epoch 24
[E24B0  |    320/60000 (  1%) ] Loss: 0.0378 top1= 99.0625
[E24B10 |   3520/60000 (  6%) ] Loss: 0.0520 top1= 98.4375
[E24B20 |   6720/60000 ( 11%) ] Loss: 0.0497 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7981 top1= 39.4832


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5199 top1= 28.6158


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2550 top1= 28.8662

Train epoch 25
[E25B0  |    320/60000 (  1%) ] Loss: 0.0499 top1= 98.7500
[E25B10 |   3520/60000 (  6%) ] Loss: 0.0663 top1= 97.5000
[E25B20 |   6720/60000 ( 11%) ] Loss: 0.0335 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8730 top1= 36.1178


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8069 top1= 28.6759


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9803 top1= 29.5473

Train epoch 26
[E26B0  |    320/60000 (  1%) ] Loss: 0.0342 top1= 98.7500
[E26B10 |   3520/60000 (  6%) ] Loss: 0.0458 top1= 98.4375
[E26B20 |   6720/60000 ( 11%) ] Loss: 0.0508 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.8991 top1= 34.2548


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9667 top1= 28.1751


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8500 top1= 36.3882

Train epoch 27
[E27B0  |    320/60000 (  1%) ] Loss: 0.1954 top1= 98.7500
[E27B10 |   3520/60000 (  6%) ] Loss: 0.1141 top1= 95.6250
[E27B20 |   6720/60000 ( 11%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9409 top1= 35.3666


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0365 top1= 28.9764


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0859 top1= 29.3269

Train epoch 28
[E28B0  |    320/60000 (  1%) ] Loss: 0.0443 top1= 99.0625
[E28B10 |   3520/60000 (  6%) ] Loss: 0.0571 top1= 97.8125
[E28B20 |   6720/60000 ( 11%) ] Loss: 0.0259 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7998 top1= 37.8606


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6632 top1= 30.2684


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3299 top1= 29.8878

Train epoch 29
[E29B0  |    320/60000 (  1%) ] Loss: 0.0389 top1= 99.3750
[E29B10 |   3520/60000 (  6%) ] Loss: 0.0111 top1= 99.6875
[E29B20 |   6720/60000 ( 11%) ] Loss: 0.0602 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9700 top1= 35.9976


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0854 top1= 29.1166


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3747 top1= 28.0649

Train epoch 30
[E30B0  |    320/60000 (  1%) ] Loss: 0.0942 top1= 96.8750
[E30B10 |   3520/60000 (  6%) ] Loss: 0.0257 top1= 99.0625
[E30B20 |   6720/60000 ( 11%) ] Loss: 0.0412 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.9281 top1= 36.6486


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0053 top1= 30.3586


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3429 top1= 27.8245

