
=== 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 0x7f1614f09250>

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: 1.4669 top1= 51.2500
[E 1B20 |  13440/60000 ( 22%) ] Loss: 1.0309 top1= 65.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4558 top1= 52.9848


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0269 top1= 48.3974


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7517 top1= 43.0288

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.7136 top1= 76.7188
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.6781 top1= 80.3125
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.5453 top1= 83.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3661 top1= 49.1787


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5187 top1= 53.5457


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2685 top1= 44.2909

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.4411 top1= 87.8125
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.4898 top1= 85.3125
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.4363 top1= 86.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4181 top1= 48.3073


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3282 top1= 58.6939


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8513 top1= 44.9119

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.4129 top1= 89.2188
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.3576 top1= 89.0625
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.3858 top1= 89.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.4981 top1= 47.3257


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2323 top1= 61.8189


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3380 top1= 45.3425

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.4476 top1= 86.0938
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.3391 top1= 90.3125
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.3892 top1= 87.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3827 top1= 49.6795


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2296 top1= 61.9992


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0879 top1= 45.5529

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.3735 top1= 88.7500
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.3038 top1= 90.4688
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.3600 top1= 89.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3571 top1= 50.1302


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2772 top1= 62.1895


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1768 top1= 45.7031

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.3157 top1= 90.9375
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.2666 top1= 92.6562
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.4584 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3605 top1= 50.0100


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2768 top1= 62.7504


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2933 top1= 46.0036

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.3227 top1= 89.8438
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.3075 top1= 90.1562
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.3521 top1= 90.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3434 top1= 50.4808


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2383 top1= 63.0108


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2172 top1= 46.1238

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.4276 top1= 87.9688
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.3343 top1= 89.3750
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.3529 top1= 89.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3301 top1= 50.6611


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2610 top1= 63.1010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2000 top1= 46.2841

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.2753 top1= 91.4062
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.2903 top1= 90.4688
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.3378 top1= 89.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3804 top1= 49.7997


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2029 top1= 64.3429


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4209 top1= 46.4042

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.2434 top1= 93.4375
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.2710 top1= 93.5938
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.3629 top1= 88.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3182 top1= 51.0817


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1707 top1= 64.1727


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3056 top1= 46.3842

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.3369 top1= 89.8438
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.2360 top1= 93.4375
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.3503 top1= 89.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2639 top1= 53.1350


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2190 top1= 64.5533


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2202 top1= 46.5044

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.2650 top1= 92.0312
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.2445 top1= 93.9062
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.3955 top1= 87.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.3059 top1= 51.9131


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1573 top1= 65.7752


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3903 top1= 46.6146

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.2847 top1= 92.0312
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.2687 top1= 91.5625
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.3306 top1= 90.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1866 top1= 54.9880


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2390 top1= 64.3730


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2173 top1= 46.4744

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.2624 top1= 92.1875
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.2301 top1= 92.8125
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.3220 top1= 91.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2326 top1= 54.2969


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2344 top1= 64.6334


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3292 top1= 46.7348

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.2494 top1= 92.8125
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.3439 top1= 90.4688
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.2640 top1= 91.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2800 top1= 53.4856


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1012 top1= 66.8169


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4368 top1= 46.7348

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.2498 top1= 93.1250
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.2148 top1= 94.2188
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.2963 top1= 91.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1847 top1= 56.8209


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1723 top1= 65.7051


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3191 top1= 46.8149

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.2688 top1= 91.2500
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.1667 top1= 95.1562
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.2848 top1= 92.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1909 top1= 56.4704


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1906 top1= 65.9355


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3829 top1= 46.8750

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.2522 top1= 91.8750
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.2590 top1= 91.5625
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.3898 top1= 89.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1431 top1= 57.9227


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1490 top1= 66.6567


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2853 top1= 46.8049

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.3347 top1= 90.9375
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.2640 top1= 91.4062
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.3885 top1= 89.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0639 top1= 60.0962


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2453 top1= 64.9539


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1404 top1= 46.9451

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.2605 top1= 91.8750
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.2349 top1= 92.1875
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.3047 top1= 90.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1196 top1= 59.3149


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1848 top1= 65.7752


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2699 top1= 47.0252

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.2875 top1= 91.2500
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.2240 top1= 93.2812
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.2322 top1= 93.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1590 top1= 58.5337


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0442 top1= 67.5381


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4093 top1= 47.0052

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.2025 top1= 94.5312
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.2306 top1= 93.1250
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.2718 top1= 91.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1057 top1= 60.4868


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2027 top1= 65.3045


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3763 top1= 46.9952

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.2255 top1= 92.8125
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.2501 top1= 93.4375
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.2617 top1= 92.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0921 top1= 61.0978


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2580 top1= 65.2043


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.2945 top1= 47.1655

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.2224 top1= 93.5938
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.1915 top1= 95.9375
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.3563 top1= 88.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0636 top1= 61.6286


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1598 top1= 66.6066


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3365 top1= 47.0753

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.2234 top1= 93.5938
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.3342 top1= 89.0625
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.2291 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0567 top1= 62.0192


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2182 top1= 66.5565


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3290 top1= 47.1955

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.1964 top1= 93.7500
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.2677 top1= 91.7188
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.2415 top1= 93.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0338 top1= 62.6803


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2414 top1= 65.7652


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3573 top1= 47.2356

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.1763 top1= 95.1562
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.1996 top1= 93.4375
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.2697 top1= 92.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.1095 top1= 60.5669


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1864 top1= 67.1374


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4880 top1= 47.2556

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.2235 top1= 93.5938
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.1692 top1= 96.0938
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.2130 top1= 93.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0463 top1= 62.5801


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1852 top1= 66.7568


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4354 top1= 47.2556

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.1782 top1= 94.0625
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.2587 top1= 91.0938
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.2172 top1= 93.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.0232 top1= 63.2212


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2963 top1= 65.8754


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.4411 top1= 47.3257

