
=== 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 0x7f5bbc1946d0>

Train epoch 1
[E 1B0  |    640/60000 (  1%) ] Loss: 2.3080 top1=  8.4375

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([4, 0, 4, 4, 4], device='cuda:0')
Worker 1 has targets: tensor([2, 6, 1, 4, 8], device='cuda:0')
Worker 2 has targets: tensor([3, 0, 3, 2, 7], device='cuda:0')
Worker 3 has targets: tensor([1, 4, 8, 2, 8], device='cuda:0')
Worker 4 has targets: tensor([9, 5, 0, 1, 3], device='cuda:0')
Worker 5 has targets: tensor([5, 6, 2, 4, 3], device='cuda:0')
Worker 6 has targets: tensor([2, 5, 0, 9, 9], device='cuda:0')
Worker 7 has targets: tensor([2, 2, 1, 9, 5], device='cuda:0')
Worker 8 has targets: tensor([3, 8, 7, 0, 3], device='cuda:0')
Worker 9 has targets: tensor([1, 7, 1, 7, 2], device='cuda:0')
Worker 10 has targets: tensor([8, 4, 4, 3, 9], device='cuda:0')
Worker 11 has targets: tensor([3, 4, 7, 7, 9], device='cuda:0')
Worker 12 has targets: tensor([7, 4, 3, 9, 4], device='cuda:0')
Worker 13 has targets: tensor([4, 5, 0, 7, 1], device='cuda:0')
Worker 14 has targets: tensor([4, 2, 3, 5, 5], device='cuda:0')
Worker 15 has targets: tensor([4, 7, 5, 4, 7], device='cuda:0')
Worker 16 has targets: tensor([1, 1, 5, 7, 9], device='cuda:0')
Worker 17 has targets: tensor([8, 7, 2, 2, 0], device='cuda:0')
Worker 18 has targets: tensor([7, 8, 0, 0, 6], device='cuda:0')
Worker 19 has targets: tensor([9, 9, 5, 2, 8], device='cuda:0')


[E 1B10 |   7040/60000 ( 12%) ] Loss: 2.0008 top1= 36.8750
[E 1B20 |  13440/60000 ( 22%) ] Loss: 1.1562 top1= 61.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5342 top1= 85.2865


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5337 top1= 85.0461


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5510 top1= 84.7556

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 0.7871 top1= 74.2188
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.6428 top1= 77.6562
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.4631 top1= 86.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3559 top1= 89.3329


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3643 top1= 89.1927


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3476 top1= 89.4631

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.1917 top1= 94.8438
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.2208 top1= 90.7812
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.1937 top1= 93.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3103 top1= 90.5649


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3121 top1= 90.7352


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3128 top1= 90.5449

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.1006 top1= 96.8750
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.1175 top1= 97.0312
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.0629 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3134 top1= 90.9054


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3240 top1= 90.5950


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3092 top1= 90.9255

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.0705 top1= 97.9688
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.0757 top1= 97.6562
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.0344 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3117 top1= 91.2460


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3111 top1= 91.3962


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3225 top1= 90.7652

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.0193 top1= 99.6875
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.0284 top1= 99.2188
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.0271 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3097 top1= 91.5465


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3105 top1= 91.5465


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3184 top1= 91.3862

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.0107 top1= 99.6875
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.0197 top1= 99.0625
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.0206 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3183 top1= 91.6466


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3189 top1= 91.7067


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3236 top1= 91.4663

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.0131 top1= 99.5312
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.0052 top1= 99.8438
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.0078 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3223 top1= 91.7468


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3251 top1= 91.7668


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3242 top1= 91.5164

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.0056 top1=100.0000
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.0028 top1=100.0000
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.0041 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3225 top1= 91.7869


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3259 top1= 91.8970


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3267 top1= 91.5765

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.0029 top1=100.0000
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.0058 top1= 99.8438
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.0106 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3248 top1= 91.8970


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3291 top1= 92.0573


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3261 top1= 91.7969

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.0014 top1=100.0000
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3302 top1= 91.9772


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3328 top1= 92.0673


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3319 top1= 91.8169

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.0019 top1=100.0000
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3292 top1= 92.0673


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3326 top1= 92.0573


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3310 top1= 91.9471

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.0015 top1=100.0000
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3305 top1= 92.1575


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3344 top1= 92.1374


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3315 top1= 92.0473

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.0017 top1=100.0000
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3324 top1= 92.2175


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3368 top1= 92.2877


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3329 top1= 92.1675

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.0019 top1=100.0000
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3333 top1= 92.3377


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3386 top1= 92.3878


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3330 top1= 92.3478

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.0021 top1=100.0000
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.0021 top1=100.0000
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3343 top1= 92.3978


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3398 top1= 92.4880


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3339 top1= 92.4579

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.0023 top1=100.0000
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3350 top1= 92.5581


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3412 top1= 92.5481


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3339 top1= 92.5381

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.0025 top1=100.0000
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3353 top1= 92.6583


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3414 top1= 92.7484


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3344 top1= 92.6883

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.0028 top1=100.0000
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.0033 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3345 top1= 92.7384


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3421 top1= 92.7484


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3326 top1= 92.7183

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.0030 top1=100.0000
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.0031 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3334 top1= 92.8986


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3405 top1= 92.8486


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3323 top1= 92.9087

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.0034 top1=100.0000
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.0039 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3313 top1= 93.0188


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3391 top1= 93.0389


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3295 top1= 92.9688

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.0035 top1=100.0000
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.0031 top1=100.0000
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.0033 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3277 top1= 93.0789


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3330 top1= 93.0188


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3275 top1= 93.0389

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.0037 top1=100.0000
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.0078 top1= 99.8438
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.0128 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3223 top1= 93.2592


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3315 top1= 93.0990


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3194 top1= 93.1891

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.0096 top1= 99.6875
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.0275 top1= 98.9062
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.0352 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3062 top1= 93.3794


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3099 top1= 93.3894


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3114 top1= 93.4295

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.0333 top1= 99.3750
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.0128 top1= 99.6875
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.0499 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2841 top1= 93.6398


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2926 top1= 93.3994


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2825 top1= 93.6599

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.0400 top1= 98.9062
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.0570 top1= 98.4375
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.0559 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2749 top1= 93.6799


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2868 top1= 93.5597


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2726 top1= 93.6298

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.1097 top1= 97.1875
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.1404 top1= 97.1875
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.0692 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2561 top1= 93.9203


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2750 top1= 93.6999


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2492 top1= 93.7700

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.0555 top1= 98.2812
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.1052 top1= 97.6562
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.0624 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2419 top1= 93.9804


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2656 top1= 93.9103


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2370 top1= 93.6098

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.0614 top1= 97.9688
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.0365 top1= 98.9062
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.0617 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2358 top1= 94.1607


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2603 top1= 94.0705


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2241 top1= 94.0905

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.0785 top1= 98.1250
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.0489 top1= 98.5938
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.0455 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2277 top1= 94.3710


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.2582 top1= 94.2107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2113 top1= 94.3910

