
=== 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 0x7fd86b0946d0>

Train epoch 1
[E 1B0  |    320/60000 (  1%) ] Loss: 2.3027 top1= 10.3125

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([3, 1, 1, 4, 4], device='cuda:0')
Worker 1 has targets: tensor([4, 0, 2, 4, 1], device='cuda:0')
Worker 2 has targets: tensor([1, 2, 2, 4, 0], device='cuda:0')
Worker 3 has targets: tensor([4, 1, 3, 4, 2], device='cuda:0')
Worker 4 has targets: tensor([4, 2, 1, 3, 0], device='cuda:0')
Worker 5 has targets: tensor([7, 5, 6, 6, 9], device='cuda:0')
Worker 6 has targets: tensor([9, 6, 7, 6, 8], device='cuda:0')
Worker 7 has targets: tensor([7, 8, 6, 5, 7], device='cuda:0')
Worker 8 has targets: tensor([7, 8, 5, 8, 9], device='cuda:0')
Worker 9 has targets: tensor([6, 8, 8, 6, 7], device='cuda:0')


[E 1B10 |   3520/60000 (  6%) ] Loss: 1.0386 top1= 63.4375
[E 1B20 |   6720/60000 ( 11%) ] Loss: 0.3837 top1= 88.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7249 top1= 79.3169


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.8838 top1= 49.2588


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5204 top1= 44.1406

Train epoch 2
[E 2B0  |    320/60000 (  1%) ] Loss: 0.3821 top1= 89.6875
[E 2B10 |   3520/60000 (  6%) ] Loss: 0.2290 top1= 92.8125
[E 2B20 |   6720/60000 ( 11%) ] Loss: 0.1885 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6543 top1= 84.9058


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.5324 top1= 49.8397


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3489 top1= 45.0220

Train epoch 3
[E 3B0  |    320/60000 (  1%) ] Loss: 0.1777 top1= 95.0000
[E 3B10 |   3520/60000 (  6%) ] Loss: 0.1183 top1= 96.8750
[E 3B20 |   6720/60000 ( 11%) ] Loss: 0.1012 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5650 top1= 87.0192


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7590 top1= 50.0401


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5059 top1= 45.5829

Train epoch 4
[E 4B0  |    320/60000 (  1%) ] Loss: 0.1039 top1= 97.5000
[E 4B10 |   3520/60000 (  6%) ] Loss: 0.0620 top1= 98.1250
[E 4B20 |   6720/60000 ( 11%) ] Loss: 0.0571 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5085 top1= 86.7588


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0793 top1= 50.1202


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.6610 top1= 45.7732

Train epoch 5
[E 5B0  |    320/60000 (  1%) ] Loss: 0.0679 top1= 98.7500
[E 5B10 |   3520/60000 (  6%) ] Loss: 0.0387 top1= 99.0625
[E 5B20 |   6720/60000 ( 11%) ] Loss: 0.0303 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4773 top1= 86.4683


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0567 top1= 50.2003


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.8972 top1= 46.0938

Train epoch 6
[E 6B0  |    320/60000 (  1%) ] Loss: 0.0518 top1= 99.0625
[E 6B10 |   3520/60000 (  6%) ] Loss: 0.0280 top1= 99.6875
[E 6B20 |   6720/60000 ( 11%) ] Loss: 0.0209 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4269 top1= 87.4499


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0003 top1= 50.3706


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0905 top1= 46.2039

Train epoch 7
[E 7B0  |    320/60000 (  1%) ] Loss: 0.0365 top1= 99.3750
[E 7B10 |   3520/60000 (  6%) ] Loss: 0.0249 top1= 99.6875
[E 7B20 |   6720/60000 ( 11%) ] Loss: 0.0236 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4055 top1= 87.5000


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8997 top1= 50.3405


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0016 top1= 46.3942

Train epoch 8
[E 8B0  |    320/60000 (  1%) ] Loss: 0.0201 top1= 99.6875
[E 8B10 |   3520/60000 (  6%) ] Loss: 0.0249 top1= 99.6875
[E 8B20 |   6720/60000 ( 11%) ] Loss: 0.0485 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3973 top1= 87.6402


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.8733 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7504 top1= 46.5545

Train epoch 9
[E 9B0  |    320/60000 (  1%) ] Loss: 0.0130 top1= 99.6875
[E 9B10 |   3520/60000 (  6%) ] Loss: 0.0144 top1=100.0000
[E 9B20 |   6720/60000 ( 11%) ] Loss: 0.0085 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3770 top1= 88.1811


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9118 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3406 top1= 46.5345

Train epoch 10
[E10B0  |    320/60000 (  1%) ] Loss: 0.0090 top1=100.0000
[E10B10 |   3520/60000 (  6%) ] Loss: 0.0103 top1=100.0000
[E10B20 |   6720/60000 ( 11%) ] Loss: 0.0098 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3642 top1= 88.6919


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7356 top1= 50.4006


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2136 top1= 46.3842

Train epoch 11
[E11B0  |    320/60000 (  1%) ] Loss: 0.0079 top1=100.0000
[E11B10 |   3520/60000 (  6%) ] Loss: 0.0049 top1=100.0000
[E11B20 |   6720/60000 ( 11%) ] Loss: 0.0049 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3614 top1= 88.4215


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.6022 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3231 top1= 46.4944

Train epoch 12
[E12B0  |    320/60000 (  1%) ] Loss: 0.0052 top1=100.0000
[E12B10 |   3520/60000 (  6%) ] Loss: 0.0051 top1=100.0000
[E12B20 |   6720/60000 ( 11%) ] Loss: 0.0043 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3508 top1= 88.9123


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3347 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2071 top1= 46.5345

Train epoch 13
[E13B0  |    320/60000 (  1%) ] Loss: 0.0032 top1=100.0000
[E13B10 |   3520/60000 (  6%) ] Loss: 0.0060 top1=100.0000
[E13B20 |   6720/60000 ( 11%) ] Loss: 0.0043 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3419 top1= 89.1627


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0758 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9851 top1= 46.5645

Train epoch 14
[E14B0  |    320/60000 (  1%) ] Loss: 0.0034 top1=100.0000
[E14B10 |   3520/60000 (  6%) ] Loss: 0.0049 top1=100.0000
[E14B20 |   6720/60000 ( 11%) ] Loss: 0.0040 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3383 top1= 89.2027


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8282 top1= 50.9115


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7207 top1= 46.6246

Train epoch 15
[E15B0  |    320/60000 (  1%) ] Loss: 0.0042 top1=100.0000
[E15B10 |   3520/60000 (  6%) ] Loss: 0.0041 top1=100.0000
[E15B20 |   6720/60000 ( 11%) ] Loss: 0.0035 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3358 top1= 89.2127


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6088 top1= 51.6226


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4548 top1= 46.9351

Train epoch 16
[E16B0  |    320/60000 (  1%) ] Loss: 0.0041 top1=100.0000
[E16B10 |   3520/60000 (  6%) ] Loss: 0.0044 top1=100.0000
[E16B20 |   6720/60000 ( 11%) ] Loss: 0.0029 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3342 top1= 89.3329


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4063 top1= 52.4840


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2007 top1= 47.5561

Train epoch 17
[E17B0  |    320/60000 (  1%) ] Loss: 0.0033 top1=100.0000
[E17B10 |   3520/60000 (  6%) ] Loss: 0.0044 top1=100.0000
[E17B20 |   6720/60000 ( 11%) ] Loss: 0.0030 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3322 top1= 89.3129


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2213 top1= 53.5857


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9601 top1= 48.5176

Train epoch 18
[E18B0  |    320/60000 (  1%) ] Loss: 0.0035 top1=100.0000
[E18B10 |   3520/60000 (  6%) ] Loss: 0.0038 top1=100.0000
[E18B20 |   6720/60000 ( 11%) ] Loss: 0.0030 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3302 top1= 89.4231


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0268 top1= 54.7977


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7634 top1= 49.6695

Train epoch 19
[E19B0  |    320/60000 (  1%) ] Loss: 0.0034 top1=100.0000
[E19B10 |   3520/60000 (  6%) ] Loss: 0.0037 top1=100.0000
[E19B20 |   6720/60000 ( 11%) ] Loss: 0.0031 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3286 top1= 89.5733


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8386 top1= 56.0697


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5708 top1= 50.9315

Train epoch 20
[E20B0  |    320/60000 (  1%) ] Loss: 0.0034 top1=100.0000
[E20B10 |   3520/60000 (  6%) ] Loss: 0.0039 top1=100.0000
[E20B20 |   6720/60000 ( 11%) ] Loss: 0.0033 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3277 top1= 89.8037


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6632 top1= 57.5220


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3927 top1= 52.5441

Train epoch 21
[E21B0  |    320/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E21B10 |   3520/60000 (  6%) ] Loss: 0.0037 top1=100.0000
[E21B20 |   6720/60000 ( 11%) ] Loss: 0.0033 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3259 top1= 89.9239


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5066 top1= 58.9143


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2400 top1= 54.5373

Train epoch 22
[E22B0  |    320/60000 (  1%) ] Loss: 0.0032 top1=100.0000
[E22B10 |   3520/60000 (  6%) ] Loss: 0.0036 top1=100.0000
[E22B20 |   6720/60000 ( 11%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3249 top1= 90.1042


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3586 top1= 60.5569


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0887 top1= 56.6406

Train epoch 23
[E23B0  |    320/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E23B10 |   3520/60000 (  6%) ] Loss: 0.0035 top1=100.0000
[E23B20 |   6720/60000 ( 11%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3236 top1= 90.2744


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2337 top1= 61.7588


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9684 top1= 58.5337

Train epoch 24
[E24B0  |    320/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E24B10 |   3520/60000 (  6%) ] Loss: 0.0035 top1=100.0000
[E24B20 |   6720/60000 ( 11%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3232 top1= 90.3546


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1035 top1= 63.1310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8310 top1= 60.6571

Train epoch 25
[E25B0  |    320/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E25B10 |   3520/60000 (  6%) ] Loss: 0.0033 top1=100.0000
[E25B20 |   6720/60000 ( 11%) ] Loss: 0.0031 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3221 top1= 90.5449


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0001 top1= 64.4431


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7194 top1= 62.7204

Train epoch 26
[E26B0  |    320/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E26B10 |   3520/60000 (  6%) ] Loss: 0.0032 top1=100.0000
[E26B20 |   6720/60000 ( 11%) ] Loss: 0.0030 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3216 top1= 90.5849


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8939 top1= 65.7151


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6110 top1= 64.9339

Train epoch 27
[E27B0  |    320/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E27B10 |   3520/60000 (  6%) ] Loss: 0.0029 top1=100.0000
[E27B20 |   6720/60000 ( 11%) ] Loss: 0.0029 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3204 top1= 90.8053


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7982 top1= 66.9571


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5169 top1= 66.7869

Train epoch 28
[E28B0  |    320/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E28B10 |   3520/60000 (  6%) ] Loss: 0.0027 top1=100.0000
[E28B20 |   6720/60000 ( 11%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3196 top1= 91.0557


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7037 top1= 68.0689


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4421 top1= 68.4395

Train epoch 29
[E29B0  |    320/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E29B10 |   3520/60000 (  6%) ] Loss: 0.0024 top1=100.0000
[E29B20 |   6720/60000 ( 11%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3190 top1= 91.1859


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6102 top1= 69.2107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3735 top1= 70.0721

Train epoch 30
[E30B0  |    320/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E30B10 |   3520/60000 (  6%) ] Loss: 0.0023 top1=100.0000
[E30B20 |   6720/60000 ( 11%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3186 top1= 91.3762


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5274 top1= 70.2123


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3090 top1= 71.4143

