
=== 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 0x7fb800a41250>

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: 1.0299 top1= 62.3438
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.3950 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7208 top1= 78.7460


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9966 top1= 49.2889


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.8497 top1= 44.2508

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.2851 top1= 90.6250
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.1926 top1= 93.7500
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.1966 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6659 top1= 84.8858


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4970 top1= 49.8297


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5333 top1= 45.7833

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.1616 top1= 94.8438
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.1093 top1= 96.7188
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.1209 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5960 top1= 85.9175


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4435 top1= 50.1302


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6646 top1= 46.1639

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1176 top1= 96.5625
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.0783 top1= 97.6562
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.0779 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5354 top1= 86.8690


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5937 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7140 top1= 46.4543

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.0794 top1= 98.2812
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.0578 top1= 98.4375
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.0551 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4823 top1= 87.3498


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7459 top1= 50.4607


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8104 top1= 46.6446

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0576 top1= 99.0625
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0406 top1= 98.9062
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0407 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4435 top1= 87.9708


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9169 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7909 top1= 46.8950

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0403 top1= 99.3750
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0266 top1= 99.5312
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0361 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4099 top1= 88.6418


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1197 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7273 top1= 46.7147

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0331 top1= 99.2188
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0236 top1= 99.3750
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0259 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3912 top1= 88.4916


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.2055 top1= 50.5008


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7228 top1= 47.0252

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0217 top1= 99.2188
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0184 top1= 99.5312
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0188 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3759 top1= 88.2612


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.1701 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9925 top1= 46.7748

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0233 top1= 99.3750
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0118 top1= 99.8438
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0176 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3613 top1= 88.7720


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.9415 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1688 top1= 46.9651

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0094 top1= 99.8438
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0096 top1=100.0000
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0221 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3648 top1= 88.1010


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5957 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2434 top1= 47.0453

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0148 top1= 99.5312
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0121 top1= 99.8438
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0106 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3420 top1= 89.2628


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5469 top1= 50.6811


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.1884 top1= 47.1354

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0046 top1=100.0000
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0058 top1=100.0000
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0108 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3256 top1= 89.7837


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4898 top1= 50.6711


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0337 top1= 47.0453

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0055 top1=100.0000
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0031 top1=100.0000
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0054 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3179 top1= 89.9539


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4975 top1= 50.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9932 top1= 47.1554

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0044 top1=100.0000
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0030 top1=100.0000
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0036 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3165 top1= 89.5933


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6688 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.0358 top1= 47.0453

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0024 top1=100.0000
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3094 top1= 89.7536


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6491 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.9575 top1= 47.1554

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0019 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3119 top1= 89.6735


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6003 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8955 top1= 47.2055

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0020 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3117 top1= 89.6234


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5294 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.7758 top1= 47.1855

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0019 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3103 top1= 89.6534


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4414 top1= 50.7512


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6487 top1= 47.2055

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0018 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3080 top1= 89.6735


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3382 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.5073 top1= 47.1855

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0018 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3050 top1= 89.7937


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2268 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3632 top1= 47.1655

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0017 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3018 top1= 89.9339


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1041 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2159 top1= 47.1655

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0017 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2987 top1= 90.0240


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9790 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0587 top1= 47.1454

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0017 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2952 top1= 90.0541


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8532 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8951 top1= 47.1554

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0017 top1=100.0000
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2919 top1= 90.1643


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7186 top1= 50.7612


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7414 top1= 47.1655

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0017 top1=100.0000
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2889 top1= 90.4447


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5880 top1= 50.8814


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5754 top1= 47.1855

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0017 top1=100.0000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2857 top1= 90.5749


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4615 top1= 50.9716


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4232 top1= 47.2356

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0018 top1=100.0000
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2827 top1= 90.7051


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3325 top1= 51.2019


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2676 top1= 47.3658

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0018 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2798 top1= 90.8554


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2111 top1= 51.4323


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1266 top1= 47.5661

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0018 top1=100.0000
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2773 top1= 91.0256


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0957 top1= 51.6627


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9909 top1= 47.8065

