
=== 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 0x7f7fa9978250>

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: 1.0344 top1= 62.3438
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.3909 top1= 88.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6586 top1= 81.0797


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.5571 top1= 49.3890


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.8768 top1= 44.2007

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.2799 top1= 90.6250
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.1913 top1= 94.0625
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.1989 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5301 top1= 86.8189


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9420 top1= 49.9900


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9472 top1= 45.8534

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.1549 top1= 95.0000
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.1093 top1= 96.5625
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.1425 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4397 top1= 87.3397


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5224 top1= 49.6995


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2215 top1= 46.3041

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1310 top1= 95.7812
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.0802 top1= 97.9688
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.1118 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3789 top1= 88.4615


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2537 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9835 top1= 46.9852

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.0992 top1= 97.0312
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.0615 top1= 98.2812
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.0901 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3416 top1= 89.1727


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0581 top1= 51.7528


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7563 top1= 48.8982

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0715 top1= 97.9688
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0431 top1= 99.3750
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0700 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3179 top1= 89.5933


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9669 top1= 52.6643


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6941 top1= 50.3806

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0512 top1= 98.7500
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0335 top1= 99.3750
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0555 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3049 top1= 89.9339


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9335 top1= 53.9263


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6577 top1= 51.2720

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0450 top1= 99.0625
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0299 top1= 99.3750
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0447 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2999 top1= 90.0441


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8934 top1= 54.9079


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6715 top1= 52.3438

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0356 top1= 99.0625
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0273 top1= 99.3750
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0414 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2945 top1= 90.4647


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7660 top1= 55.7893


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2805 top1= 54.7376

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0212 top1= 99.5312
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0387 top1= 98.9062
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0492 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2774 top1= 90.6150


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5676 top1= 57.3217


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7184 top1= 50.8914

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0748 top1= 98.1250
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0414 top1= 98.7500
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0308 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2747 top1= 90.7352


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7230 top1= 57.6923


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5679 top1= 52.4840

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0337 top1= 98.9062
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0165 top1= 99.6875
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0277 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2634 top1= 91.1558


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6469 top1= 58.3934


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6084 top1= 53.1150

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0167 top1= 99.3750
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0155 top1= 99.5312
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0174 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2428 top1= 92.1174


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3587 top1= 60.3766


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2476 top1= 56.0597

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0100 top1= 99.8438
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0111 top1=100.0000
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0213 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2418 top1= 92.1575


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7152 top1= 58.6338


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1377 top1= 58.1931

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0095 top1=100.0000
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0068 top1= 99.8438
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0064 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2352 top1= 92.4179


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3684 top1= 60.5369


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1294 top1= 58.9243

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0064 top1=100.0000
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0066 top1=100.0000
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0149 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2290 top1= 92.5581


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2731 top1= 61.8089


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1844 top1= 58.4936

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0130 top1= 99.6875
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0054 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0046 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2345 top1= 92.6082


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1727 top1= 62.8906


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9507 top1= 62.1695

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0038 top1=100.0000
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0043 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0047 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2329 top1= 92.7183


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1374 top1= 63.2913


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8531 top1= 63.4916

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0031 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0060 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2327 top1= 92.8586


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9844 top1= 64.1927


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7234 top1= 64.8538

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0027 top1=100.0000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0026 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2325 top1= 92.8986


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9868 top1= 64.5733


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6519 top1= 65.4347

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0023 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0029 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2297 top1= 93.0589


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9579 top1= 65.1142


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6162 top1= 66.4062

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0033 top1= 99.8438
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2303 top1= 93.0088


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9072 top1= 65.7752


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7183 top1= 66.2961

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0019 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2367 top1= 92.8385


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8617 top1= 66.5465


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8653 top1= 65.8153

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0036 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0016 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2327 top1= 93.0088


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8259 top1= 67.1374


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7333 top1= 67.3177

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0020 top1=100.0000
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0023 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2318 top1= 93.2091


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7828 top1= 67.6983


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6102 top1= 68.2893

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0015 top1=100.0000
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2337 top1= 93.2192


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7418 top1= 68.3193


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5862 top1= 69.4010

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0016 top1=100.0000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2356 top1= 93.1991


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7114 top1= 68.8001


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5588 top1= 69.8317

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0015 top1=100.0000
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2369 top1= 93.2192


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6806 top1= 69.3309


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5214 top1= 70.6731

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0013 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2385 top1= 93.2292


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6547 top1= 69.7216


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4941 top1= 71.3341

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0012 top1=100.0000
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2394 top1= 93.2492


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6246 top1= 70.1723


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4723 top1= 71.9551

