
=== 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 0x7f46d911d6d0>

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: 1.3923 top1= 54.5312
[E 1B20 |  13440/60000 ( 22%) ] Loss: 0.8231 top1= 73.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3654 top1= 77.7344


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1970 top1= 48.5877


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9863 top1= 43.4195

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.5050 top1= 83.5938
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.3441 top1= 88.7500
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.3484 top1= 90.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0363 top1= 81.5905


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.9601 top1= 49.3189


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5441 top1= 44.5012

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.2711 top1= 91.2500
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.2382 top1= 90.4688
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.2475 top1= 93.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.9066 top1= 82.3017


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2550 top1= 49.6494


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9488 top1= 44.7716

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.2288 top1= 93.1250
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.1689 top1= 94.5312
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.1903 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8203 top1= 82.6222


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7209 top1= 49.7796


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5005 top1= 44.9720

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.1796 top1= 94.0625
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.1696 top1= 93.4375
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.1822 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8083 top1= 83.0829


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7618 top1= 49.9299


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3251 top1= 45.3025

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.1580 top1= 96.2500
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.1424 top1= 95.0000
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.1647 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7640 top1= 84.1847


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7136 top1= 50.0200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3739 top1= 45.6631

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.1647 top1= 95.0000
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.1355 top1= 95.1562
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.1522 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7356 top1= 84.0345


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9306 top1= 50.0701


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5108 top1= 45.7432

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.1440 top1= 96.0938
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.1216 top1= 96.0938
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.1345 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7133 top1= 84.7857


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9655 top1= 50.1302


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5058 top1= 45.9335

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.1305 top1= 96.7188
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.1061 top1= 96.4062
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.1504 top1= 96.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6983 top1= 84.5553


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9706 top1= 50.1803


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.5166 top1= 46.0938

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.1294 top1= 95.7812
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.1001 top1= 96.8750
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.1082 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6724 top1= 85.2063


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1204 top1= 50.2604


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7840 top1= 46.1538

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.1025 top1= 97.5000
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0982 top1= 96.0938
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.1002 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6694 top1= 85.3766


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0616 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7313 top1= 46.2740

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0975 top1= 97.1875
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.1036 top1= 96.4062
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.1019 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6604 top1= 85.6871


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.0591 top1= 50.2504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7540 top1= 46.3442

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0919 top1= 97.9688
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0861 top1= 97.3438
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.1028 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6370 top1= 86.0276


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1739 top1= 50.3405


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9818 top1= 46.3642

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0889 top1= 97.8125
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0734 top1= 97.1875
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0776 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6279 top1= 86.0577


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2041 top1= 50.3606


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9205 top1= 46.4543

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0916 top1= 97.8125
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0734 top1= 97.1875
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0814 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6225 top1= 86.2380


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1696 top1= 50.2905


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.9282 top1= 46.5144

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0773 top1= 97.9688
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0577 top1= 98.2812
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0719 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6005 top1= 86.6386


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3055 top1= 50.3506


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1538 top1= 46.5545

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0746 top1= 98.2812
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0577 top1= 98.1250
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0873 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6062 top1= 86.4383


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1980 top1= 50.3806


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1426 top1= 46.5745

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0752 top1= 98.1250
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0741 top1= 96.8750
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0654 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5968 top1= 86.5986


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1920 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0772 top1= 46.6246

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0710 top1= 97.9688
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0494 top1= 98.2812
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0564 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5828 top1= 86.4884


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3563 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3555 top1= 46.6246

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0601 top1= 98.1250
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0395 top1= 98.7500
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0692 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5823 top1= 86.3682


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3079 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3106 top1= 46.6446

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0746 top1= 97.6562
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0508 top1= 98.2812
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0553 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5748 top1= 86.8189


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2716 top1= 50.4207


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2412 top1= 46.7748

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0610 top1= 98.5938
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0441 top1= 97.9688
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0554 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5565 top1= 87.1595


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.3747 top1= 50.4507


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4895 top1= 46.7648

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0528 top1= 98.9062
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0338 top1= 99.3750
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0505 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5589 top1= 86.9291


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4264 top1= 50.5208


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4914 top1= 46.7949

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0882 top1= 97.5000
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0312 top1= 99.3750
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0663 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5650 top1= 86.6286


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4007 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4302 top1= 46.7949

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0571 top1= 98.7500
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0323 top1= 99.2188
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0480 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5495 top1= 86.6787


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4930 top1= 50.4908


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6307 top1= 46.8650

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0542 top1= 98.5938
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0268 top1= 99.0625
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0526 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5406 top1= 86.5284


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.4517 top1= 50.5108


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6860 top1= 46.8149

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.0538 top1= 98.7500
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.0253 top1= 99.3750
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0360 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5395 top1= 86.9892


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5588 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.6189 top1= 46.8650

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0491 top1= 99.3750
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.0337 top1= 98.7500
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0370 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5290 top1= 87.1795


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.6083 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8050 top1= 46.9351

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0451 top1= 99.0625
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0270 top1= 99.3750
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0432 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5347 top1= 86.8289


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.5590 top1= 50.5308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8830 top1= 46.9351

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0506 top1= 99.0625
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0230 top1= 99.3750
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0357 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5314 top1= 86.7588


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.7031 top1= 50.5609


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.8559 top1= 46.9451

