
=== 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 0x7fc38cb6b250>

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: 1.0317 top1= 62.1875
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.3981 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7213 top1= 79.0164


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9826 top1= 49.3089


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7350 top1= 44.2408

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.2799 top1= 90.7812
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.1880 top1= 93.7500
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.1966 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6629 top1= 84.8658


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5309 top1= 49.8798


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5399 top1= 45.7632

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.1609 top1= 95.1562
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.1087 top1= 96.8750
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.1221 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5973 top1= 86.2280


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4717 top1= 50.1302


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6672 top1= 46.1538

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1163 top1= 96.5625
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.0791 top1= 97.9688
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.0772 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5345 top1= 87.0593


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6369 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7426 top1= 46.4443

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.0788 top1= 97.9688
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.0576 top1= 98.4375
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.0542 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4861 top1= 87.0292


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8053 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8289 top1= 46.6546

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0579 top1= 98.7500
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0400 top1= 99.0625
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0399 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4417 top1= 88.0108


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9837 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8482 top1= 46.9151

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0396 top1= 99.2188
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0259 top1= 99.5312
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0346 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4101 top1= 88.8221


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2092 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8105 top1= 46.7648

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0316 top1= 99.2188
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0222 top1= 99.8438
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0237 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3976 top1= 88.0609


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2657 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9467 top1= 47.0052

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0228 top1= 99.2188
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0182 top1= 99.5312
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0178 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3780 top1= 88.4315


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2552 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3009 top1= 46.8450

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0196 top1= 99.5312
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0106 top1=100.0000
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0214 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3805 top1= 87.9006


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0596 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.4880 top1= 46.9752

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0109 top1= 99.8438
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0097 top1= 99.8438
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0120 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3787 top1= 87.3698


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0502 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5516 top1= 46.9351

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0124 top1= 99.6875
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0121 top1= 99.8438
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0111 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3406 top1= 89.2027


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7353 top1= 50.6210


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5382 top1= 47.1655

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0056 top1=100.0000
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0048 top1=100.0000
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0117 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3404 top1= 88.9824


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7222 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3008 top1= 47.1955

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0037 top1=100.0000
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0033 top1=100.0000
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0071 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3266 top1= 89.7937


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7775 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1935 top1= 46.9050

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0100 top1= 99.8438
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0031 top1=100.0000
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0042 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3145 top1= 89.9740


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8781 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1336 top1= 47.1655

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0026 top1=100.0000
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3220 top1= 89.4832


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8992 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1213 top1= 47.1554

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0023 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3230 top1= 89.2628


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8472 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1733 top1= 47.2055

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0020 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3234 top1= 89.1627


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7883 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1361 top1= 47.1855

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0019 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3227 top1= 89.1727


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7043 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0461 top1= 47.1855

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0017 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3206 top1= 89.2328


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6055 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9554 top1= 47.1755

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0016 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3172 top1= 89.3329


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4997 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8554 top1= 47.1454

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0015 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3132 top1= 89.5533


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3846 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7438 top1= 47.1454

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0015 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3091 top1= 89.7536


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2610 top1= 50.7111


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6138 top1= 47.1354

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0015 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3047 top1= 89.9740


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1387 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4737 top1= 47.1354

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0015 top1=100.0000
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3008 top1= 90.1142


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0110 top1= 50.6911


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3177 top1= 47.1454

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0015 top1=100.0000
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2971 top1= 90.3245


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8799 top1= 50.7011


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1580 top1= 47.1354

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0015 top1=100.0000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2939 top1= 90.5349


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7508 top1= 50.7612


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9961 top1= 47.1755

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0015 top1=100.0000
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2907 top1= 90.6550


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6181 top1= 50.8413


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8354 top1= 47.1955

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0015 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2876 top1= 90.6951


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4889 top1= 51.0216


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6759 top1= 47.2055

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0015 top1=100.0000
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2851 top1= 90.7051


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3616 top1= 51.2019


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5219 top1= 47.2857

