
=== 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 0x7f81f99916d0>

Train epoch 1
[E 1B0  |    640/60000 (  1%) ] Loss: 2.3007 top1=  9.6875

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([3, 4, 1, 4, 4], device='cuda:0')
Worker 1 has targets: tensor([0, 3, 1, 1, 2], device='cuda:0')
Worker 2 has targets: tensor([2, 4, 1, 2, 4], device='cuda:0')
Worker 3 has targets: tensor([3, 2, 3, 2, 2], device='cuda:0')
Worker 4 has targets: tensor([3, 2, 2, 2, 2], device='cuda:0')
Worker 5 has targets: tensor([4, 2, 0, 3, 2], device='cuda:0')
Worker 6 has targets: tensor([4, 0, 0, 4, 2], device='cuda:0')
Worker 7 has targets: tensor([4, 3, 2, 0, 3], device='cuda:0')
Worker 8 has targets: tensor([0, 2, 2, 4, 4], device='cuda:0')
Worker 9 has targets: tensor([1, 4, 1, 4, 0], device='cuda:0')
Worker 10 has targets: tensor([8, 5, 5, 9, 8], device='cuda:0')
Worker 11 has targets: tensor([6, 7, 8, 8, 6], device='cuda:0')
Worker 12 has targets: tensor([8, 8, 6, 6, 6], device='cuda:0')
Worker 13 has targets: tensor([6, 6, 8, 5, 6], device='cuda:0')
Worker 14 has targets: tensor([8, 8, 8, 7, 5], device='cuda:0')
Worker 15 has targets: tensor([7, 8, 6, 7, 8], device='cuda:0')
Worker 16 has targets: tensor([7, 9, 9, 9, 9], device='cuda:0')
Worker 17 has targets: tensor([7, 8, 5, 8, 5], device='cuda:0')
Worker 18 has targets: tensor([6, 7, 5, 8, 9], device='cuda:0')
Worker 19 has targets: tensor([6, 9, 8, 7, 5], device='cuda:0')


[E 1B10 |   7040/60000 ( 12%) ] Loss: 1.0223 top1= 65.0000
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.3549 top1= 89.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6953 top1= 77.9647


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.9821 top1= 49.4491


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8649 top1= 43.8702

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.2361 top1= 92.6562
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.2062 top1= 92.6562
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.1751 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6235 top1= 83.6338


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0699 top1= 50.1202


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4035 top1= 45.6330

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.1453 top1= 95.7812
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.1226 top1= 95.6250
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.1147 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5187 top1= 86.1178


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.3468 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8081 top1= 46.1939

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1051 top1= 96.7188
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.0898 top1= 96.7188
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.0808 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4343 top1= 88.0909


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8533 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3821 top1= 46.4844

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.0772 top1= 97.9688
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.0721 top1= 97.5000
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.0585 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3756 top1= 89.0825


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4932 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0731 top1= 46.6647

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0627 top1= 98.2812
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0608 top1= 97.8125
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0445 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3353 top1= 89.9539


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2291 top1= 51.9932


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7953 top1= 47.3658

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0518 top1= 98.2812
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0484 top1= 98.1250
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0327 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3090 top1= 90.0341


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1475 top1= 53.0749


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7202 top1= 48.5677

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0442 top1= 98.4375
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0366 top1= 99.3750
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0268 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2925 top1= 90.3946


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0642 top1= 53.6558


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7235 top1= 49.8097

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0387 top1= 98.9062
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0248 top1= 99.6875
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0196 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2912 top1= 90.3946


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0462 top1= 54.2167


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4892 top1= 52.2636

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0303 top1= 99.2188
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0246 top1= 99.3750
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0220 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3010 top1= 90.2344


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0235 top1= 54.9880


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3130 top1= 55.0080

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0376 top1= 99.0625
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0321 top1= 99.2188
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0395 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2831 top1= 90.7151


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8940 top1= 55.9495


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4397 top1= 53.9263

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0353 top1= 98.9062
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0286 top1= 99.3750
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0127 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2801 top1= 90.9155


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7702 top1= 56.3301


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3182 top1= 53.3253

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0249 top1= 99.2188
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0207 top1= 99.5312
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0216 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2812 top1= 90.3045


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4709 top1= 58.3233


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0685 top1= 57.3518

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0294 top1= 99.2188
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0241 top1= 99.2188
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0080 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2679 top1= 91.2059


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5311 top1= 58.2432


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9345 top1= 59.0845

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0191 top1= 99.5312
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0262 top1= 99.2188
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0117 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2780 top1= 91.3662


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5746 top1= 58.8942


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8840 top1= 60.2163

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0124 top1= 99.8438
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0121 top1=100.0000
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0162 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2677 top1= 91.3261


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6142 top1= 58.6338


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7415 top1= 63.3413

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0288 top1= 99.0625
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0272 top1= 99.0625
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0043 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2447 top1= 92.0072


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2870 top1= 59.8858


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8384 top1= 61.6587

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0090 top1= 99.6875
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0105 top1= 99.8438
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0097 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2273 top1= 92.8185


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0992 top1= 61.5885


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8982 top1= 60.9976

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0060 top1= 99.8438
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0033 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0053 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2373 top1= 92.4279


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9011 top1= 62.7905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6457 top1= 65.5549

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0085 top1= 99.8438
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0051 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0029 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2283 top1= 92.8085


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9586 top1= 63.2612


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5820 top1= 66.8970

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0036 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2242 top1= 93.0188


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8471 top1= 64.2829


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5524 top1= 66.9972

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0043 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2242 top1= 93.1290


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8381 top1= 64.5933


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4816 top1= 68.3193

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0020 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2249 top1= 93.1691


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7845 top1= 65.2244


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3851 top1= 69.7817

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0018 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2252 top1= 93.2993


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7508 top1= 65.6951


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3534 top1= 71.1238

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0018 top1=100.0000
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2262 top1= 93.3494


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7264 top1= 66.2961


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3085 top1= 71.9351

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0015 top1=100.0000
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2270 top1= 93.4295


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6979 top1= 66.7768


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2746 top1= 72.7364

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: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2276 top1= 93.4495


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6707 top1= 67.2075


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2466 top1= 73.4575

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0014 top1=100.0000
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2280 top1= 93.4896


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6457 top1= 67.6683


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2255 top1= 73.9183

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0013 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2286 top1= 93.4996


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6194 top1= 68.2492


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2054 top1= 74.5493

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0012 top1=100.0000
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0010 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2290 top1= 93.5196


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5972 top1= 68.6398


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1884 top1= 74.9700

