
=== 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 0x7fd3912fd250>

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: 1.0410 top1= 62.1875
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.3924 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6496 top1= 81.1398


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0616 top1= 49.3690


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3737 top1= 44.2408

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.2740 top1= 91.0938
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.1928 top1= 93.5938
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.1952 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5028 top1= 86.9491


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4125 top1= 50.0501


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3547 top1= 45.8734

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.1564 top1= 95.3125
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.1165 top1= 97.0312
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.1503 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4054 top1= 88.1510


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0394 top1= 50.1202


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8657 top1= 46.6346

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1334 top1= 95.4688
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.0841 top1= 97.6562
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.1132 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3562 top1= 88.7520


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8697 top1= 52.0433


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5949 top1= 48.9183

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.1052 top1= 97.0312
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.0629 top1= 98.5938
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.0910 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3244 top1= 89.4231


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7999 top1= 53.2752


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4401 top1= 50.9315

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0831 top1= 98.2812
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0474 top1= 99.0625
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0693 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3061 top1= 89.9139


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7390 top1= 54.8478


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2633 top1= 54.1466

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0607 top1= 98.5938
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0366 top1= 99.0625
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0607 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2992 top1= 90.1843


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7315 top1= 56.0597


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1675 top1= 55.7592

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0450 top1= 99.0625
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0265 top1= 99.6875
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0430 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2845 top1= 90.6550


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5980 top1= 57.5421


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3107 top1= 54.6074

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0439 top1= 99.0625
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0260 top1= 99.0625
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0666 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2779 top1= 90.6250


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6435 top1= 57.6623


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4608 top1= 54.2167

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0609 top1= 97.9688
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0460 top1= 98.5938
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0534 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2719 top1= 90.7151


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4055 top1= 58.4135


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3206 top1= 56.4103

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0321 top1= 98.9062
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0214 top1= 99.2188
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0290 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2644 top1= 91.1158


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2593 top1= 60.2764


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2574 top1= 55.0180

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0220 top1= 99.5312
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0151 top1= 99.8438
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0152 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2505 top1= 91.8970


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3245 top1= 61.1478


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1786 top1= 56.6707

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0222 top1= 99.2188
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0164 top1= 99.6875
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0129 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2408 top1= 92.3077


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1978 top1= 62.3297


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0415 top1= 58.7039

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0107 top1= 99.8438
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0101 top1=100.0000
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0109 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2388 top1= 92.1975


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5686 top1= 60.5669


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0131 top1= 59.3349

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0087 top1= 99.8438
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0092 top1= 99.8438
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0100 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2395 top1= 92.3277


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1834 top1= 62.7003


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0708 top1= 59.4651

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0098 top1= 99.8438
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0066 top1=100.0000
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0115 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2496 top1= 92.2776


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1155 top1= 62.7103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8085 top1= 64.7236

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0136 top1= 99.5312
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0073 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0077 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2432 top1= 92.4679


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9328 top1= 64.8738


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7838 top1= 63.5016

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0094 top1= 99.6875
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0056 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0094 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2333 top1= 92.7284


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8962 top1= 65.6450


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8747 top1= 63.0008

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0119 top1= 99.6875
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0037 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0048 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2430 top1= 92.6382


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7738 top1= 66.8169


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9324 top1= 63.8522

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0071 top1= 99.8438
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0044 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0054 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2451 top1= 92.7284


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7053 top1= 67.9788


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7371 top1= 67.3277

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0104 top1= 99.8438
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0024 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0091 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2421 top1= 92.8586


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6165 top1= 68.9603


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7123 top1= 67.4980

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0032 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0032 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0070 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2434 top1= 92.7885


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6322 top1= 69.2308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5408 top1= 69.6414

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0047 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0033 top1=100.0000
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2431 top1= 92.9087


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5886 top1= 69.7015


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4198 top1= 70.7632

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0039 top1=100.0000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0021 top1=100.0000
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0036 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2473 top1= 92.8085


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5145 top1= 70.7332


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7250 top1= 68.1190

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0021 top1=100.0000
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0052 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2314 top1= 93.2492


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5320 top1= 70.7432


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5125 top1= 69.9419

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0014 top1=100.0000
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2321 top1= 93.2993


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4729 top1= 71.6947


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4324 top1= 71.7047

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0012 top1=100.0000
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2342 top1= 93.3494


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4614 top1= 71.9852


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3465 top1= 73.1270

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2344 top1= 93.3293


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4129 top1= 72.7264


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3369 top1= 73.4575

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0010 top1=100.0000
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0011 top1=100.0000
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2347 top1= 93.3894


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3944 top1= 73.0068


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3207 top1= 73.9583

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

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2350 top1= 93.3794


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3691 top1= 73.4475


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3077 top1= 74.3890

