
=== 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 0x7f9f444bf6d0>

Train epoch 1
[E 1B0  |    320/60000 (  1%) ] Loss: 2.3054 top1= 10.0000

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


[E 1B10 |   3520/60000 (  6%) ] Loss: 0.2413 top1= 91.8750
[E 1B20 |   6720/60000 ( 11%) ] Loss: 0.1890 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.7638 top1= 56.5705


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4449 top1= 26.9732


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1049 top1= 10.4267

Train epoch 2
[E 2B0  |    320/60000 (  1%) ] Loss: 0.1382 top1= 95.3125
[E 2B10 |   3520/60000 (  6%) ] Loss: 0.0849 top1= 98.7500
[E 2B20 |   6720/60000 ( 11%) ] Loss: 0.0608 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6848 top1= 43.9203


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9663 top1= 47.9868


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9523 top1= 40.8954

Train epoch 3
[E 3B0  |    320/60000 (  1%) ] Loss: 0.1136 top1= 97.8125
[E 3B10 |   3520/60000 (  6%) ] Loss: 0.0591 top1= 98.4375
[E 3B20 |   6720/60000 ( 11%) ] Loss: 0.0320 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6623 top1= 45.7632


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5072 top1= 49.2188


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3733 top1= 42.4479

Train epoch 4
[E 4B0  |    320/60000 (  1%) ] Loss: 0.0948 top1= 97.8125
[E 4B10 |   3520/60000 (  6%) ] Loss: 0.0267 top1= 99.3750
[E 4B20 |   6720/60000 ( 11%) ] Loss: 0.0126 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6407 top1= 47.1755


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.8902 top1= 49.2788


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4655 top1= 44.5713

Train epoch 5
[E 5B0  |    320/60000 (  1%) ] Loss: 0.0655 top1= 97.5000
[E 5B10 |   3520/60000 (  6%) ] Loss: 0.0234 top1= 99.3750
[E 5B20 |   6720/60000 ( 11%) ] Loss: 0.0100 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.6028 top1= 48.8782


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=6.0060 top1= 49.6494


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4300 top1= 47.5060

Train epoch 6
[E 6B0  |    320/60000 (  1%) ] Loss: 0.0280 top1= 99.0625
[E 6B10 |   3520/60000 (  6%) ] Loss: 0.0161 top1= 99.3750
[E 6B20 |   6720/60000 ( 11%) ] Loss: 0.0079 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3794 top1= 52.8145


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6326 top1= 49.6394


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4563 top1= 48.8081

Train epoch 7
[E 7B0  |    320/60000 (  1%) ] Loss: 0.0164 top1= 99.3750
[E 7B10 |   3520/60000 (  6%) ] Loss: 0.0073 top1=100.0000
[E 7B20 |   6720/60000 ( 11%) ] Loss: 0.0099 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3066 top1= 54.3770


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2126 top1= 49.2288


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2942 top1= 50.7111

Train epoch 8
[E 8B0  |    320/60000 (  1%) ] Loss: 0.0247 top1= 99.3750
[E 8B10 |   3520/60000 (  6%) ] Loss: 0.0558 top1= 98.7500
[E 8B20 |   6720/60000 ( 11%) ] Loss: 0.0145 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0481 top1= 61.4083


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1632 top1= 49.4191


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0259 top1= 47.9667

Train epoch 9
[E 9B0  |    320/60000 (  1%) ] Loss: 0.0468 top1= 99.0625
[E 9B10 |   3520/60000 (  6%) ] Loss: 0.0175 top1= 98.7500
[E 9B20 |   6720/60000 ( 11%) ] Loss: 0.0503 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8941 top1= 66.9772


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4328 top1= 49.8498


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5199 top1= 50.8213

Train epoch 10
[E10B0  |    320/60000 (  1%) ] Loss: 0.0179 top1= 99.6875
[E10B10 |   3520/60000 (  6%) ] Loss: 0.0093 top1=100.0000
[E10B20 |   6720/60000 ( 11%) ] Loss: 0.0130 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0128 top1= 65.3446


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8865 top1= 49.6695


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9205 top1= 44.9319

Train epoch 11
[E11B0  |    320/60000 (  1%) ] Loss: 0.0100 top1= 99.6875
[E11B10 |   3520/60000 (  6%) ] Loss: 0.0049 top1=100.0000
[E11B20 |   6720/60000 ( 11%) ] Loss: 0.0090 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9754 top1= 67.4679


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8694 top1= 49.7897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6853 top1= 48.3173

Train epoch 12
[E12B0  |    320/60000 (  1%) ] Loss: 0.0223 top1= 99.0625
[E12B10 |   3520/60000 (  6%) ] Loss: 0.0067 top1= 99.6875
[E12B20 |   6720/60000 ( 11%) ] Loss: 0.0078 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9075 top1= 68.3794


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8106 top1= 48.5777


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9012 top1= 44.6314

Train epoch 13
[E13B0  |    320/60000 (  1%) ] Loss: 0.0210 top1= 99.3750
[E13B10 |   3520/60000 (  6%) ] Loss: 0.0062 top1=100.0000
[E13B20 |   6720/60000 ( 11%) ] Loss: 0.0163 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6884 top1= 75.5709


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9549 top1= 48.9483


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3413 top1= 54.8678

Train epoch 14
[E14B0  |    320/60000 (  1%) ] Loss: 0.0334 top1= 98.7500
[E14B10 |   3520/60000 (  6%) ] Loss: 0.0045 top1=100.0000
[E14B20 |   6720/60000 ( 11%) ] Loss: 0.0186 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6461 top1= 77.2736


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5140 top1= 49.9499


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7550 top1= 52.6542

Train epoch 15
[E15B0  |    320/60000 (  1%) ] Loss: 0.0195 top1= 99.3750
[E15B10 |   3520/60000 (  6%) ] Loss: 0.0133 top1= 99.3750
[E15B20 |   6720/60000 ( 11%) ] Loss: 0.0121 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7600 top1= 74.8798


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4613 top1= 50.0801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5375 top1= 56.4103

Train epoch 16
[E16B0  |    320/60000 (  1%) ] Loss: 0.0122 top1= 99.6875
[E16B10 |   3520/60000 (  6%) ] Loss: 0.0193 top1= 99.3750
[E16B20 |   6720/60000 ( 11%) ] Loss: 0.0035 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7755 top1= 73.6679


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2848 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2415 top1= 55.6390

Train epoch 17
[E17B0  |    320/60000 (  1%) ] Loss: 0.0106 top1= 99.3750
[E17B10 |   3520/60000 (  6%) ] Loss: 0.0030 top1=100.0000
[E17B20 |   6720/60000 ( 11%) ] Loss: 0.0153 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6514 top1= 77.5140


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4804 top1= 49.8197


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4270 top1= 57.2115

Train epoch 18
[E18B0  |    320/60000 (  1%) ] Loss: 0.0081 top1=100.0000
[E18B10 |   3520/60000 (  6%) ] Loss: 0.0055 top1=100.0000
[E18B20 |   6720/60000 ( 11%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6754 top1= 77.2837


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1702 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0306 top1= 61.1178

Train epoch 19
[E19B0  |    320/60000 (  1%) ] Loss: 0.0092 top1=100.0000
[E19B10 |   3520/60000 (  6%) ] Loss: 0.0025 top1=100.0000
[E19B20 |   6720/60000 ( 11%) ] Loss: 0.0065 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7781 top1= 75.1302


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4741 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9086 top1= 61.1378

Train epoch 20
[E20B0  |    320/60000 (  1%) ] Loss: 0.0041 top1=100.0000
[E20B10 |   3520/60000 (  6%) ] Loss: 0.0170 top1= 99.6875
[E20B20 |   6720/60000 ( 11%) ] Loss: 0.0262 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4808 top1= 84.3550


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6444 top1= 52.9447


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2072 top1= 57.9227

Train epoch 21
[E21B0  |    320/60000 (  1%) ] Loss: 0.0061 top1= 99.6875
[E21B10 |   3520/60000 (  6%) ] Loss: 0.0063 top1= 99.6875
[E21B20 |   6720/60000 ( 11%) ] Loss: 0.0123 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5547 top1= 82.1514


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9605 top1= 51.8129


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1321 top1= 60.6370

Train epoch 22
[E22B0  |    320/60000 (  1%) ] Loss: 0.0095 top1= 99.6875
[E22B10 |   3520/60000 (  6%) ] Loss: 0.0060 top1= 99.6875
[E22B20 |   6720/60000 ( 11%) ] Loss: 0.0078 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6121 top1= 79.9780


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2796 top1= 51.1619


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7628 top1= 63.9623

Train epoch 23
[E23B0  |    320/60000 (  1%) ] Loss: 0.0230 top1= 99.3750
[E23B10 |   3520/60000 (  6%) ] Loss: 0.2746 top1= 98.1250
[E23B20 |   6720/60000 ( 11%) ] Loss: 0.0232 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7253 top1= 75.1102


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7091 top1= 49.9099


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6105 top1= 59.6054

Train epoch 24
[E24B0  |    320/60000 (  1%) ] Loss: 0.0350 top1= 99.6875
[E24B10 |   3520/60000 (  6%) ] Loss: 0.0028 top1=100.0000
[E24B20 |   6720/60000 ( 11%) ] Loss: 0.0121 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7226 top1= 76.3221


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5791 top1= 51.8029


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0877 top1= 60.3566

Train epoch 25
[E25B0  |    320/60000 (  1%) ] Loss: 0.0289 top1= 99.6875
[E25B10 |   3520/60000 (  6%) ] Loss: 0.0116 top1= 99.6875
[E25B20 |   6720/60000 ( 11%) ] Loss: 0.0038 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6687 top1= 78.3754


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5651 top1= 51.7328


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1925 top1= 59.0244

Train epoch 26
[E26B0  |    320/60000 (  1%) ] Loss: 0.0037 top1=100.0000
[E26B10 |   3520/60000 (  6%) ] Loss: 0.0041 top1=100.0000
[E26B20 |   6720/60000 ( 11%) ] Loss: 0.0054 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7116 top1= 77.3938


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9056 top1= 51.6326


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8611 top1= 64.3730

Train epoch 27
[E27B0  |    320/60000 (  1%) ] Loss: 0.0169 top1= 99.3750
[E27B10 |   3520/60000 (  6%) ] Loss: 0.0039 top1=100.0000
[E27B20 |   6720/60000 ( 11%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8416 top1= 74.8297


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8156 top1= 52.2937


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7962 top1= 62.7003

Train epoch 28
[E28B0  |    320/60000 (  1%) ] Loss: 0.0398 top1= 98.7500
[E28B10 |   3520/60000 (  6%) ] Loss: 0.0028 top1=100.0000
[E28B20 |   6720/60000 ( 11%) ] Loss: 0.0096 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6065 top1= 80.8393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5969 top1= 53.5256


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3885 top1= 68.5196

Train epoch 29
[E29B0  |    320/60000 (  1%) ] Loss: 0.0088 top1= 99.6875
[E29B10 |   3520/60000 (  6%) ] Loss: 0.0043 top1=100.0000
[E29B20 |   6720/60000 ( 11%) ] Loss: 0.0109 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5809 top1= 81.3502


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3228 top1= 54.1567


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9081 top1= 62.5200

Train epoch 30
[E30B0  |    320/60000 (  1%) ] Loss: 0.0070 top1=100.0000
[E30B10 |   3520/60000 (  6%) ] Loss: 0.0010 top1=100.0000
[E30B20 |   6720/60000 ( 11%) ] Loss: 0.0125 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5388 top1= 82.7023


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9343 top1= 53.9263


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6098 top1= 66.0457

