
=== 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 0x7fd9a42aa730>

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: 1.9342 top1= 44.0625
[E 1B20 |  13440/60000 ( 22%) ] Loss: 1.0407 top1= 65.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8062 top1= 70.0521


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9533 top1= 64.3730


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8555 top1= 71.8149

Train epoch 2
[E 2B0  |    640/60000 (  1%) ] Loss: 1.0328 top1= 65.6250
[E 2B10 |   7040/60000 ( 12%) ] Loss: 0.7045 top1= 77.6562
[E 2B20 |  13440/60000 ( 22%) ] Loss: 0.6092 top1= 81.0938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3697 top1= 89.1026


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4160 top1= 87.1995


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3916 top1= 88.2412

Train epoch 3
[E 3B0  |    640/60000 (  1%) ] Loss: 0.4315 top1= 87.8125
[E 3B10 |   7040/60000 ( 12%) ] Loss: 0.4929 top1= 84.0625
[E 3B20 |  13440/60000 ( 22%) ] Loss: 0.4830 top1= 84.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3593 top1= 88.8321


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4445 top1= 85.0461


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3132 top1= 90.5849

Train epoch 4
[E 4B0  |    640/60000 (  1%) ] Loss: 0.4071 top1= 87.8125
[E 4B10 |   7040/60000 ( 12%) ] Loss: 0.3637 top1= 88.2812
[E 4B20 |  13440/60000 ( 22%) ] Loss: 0.3895 top1= 89.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3064 top1= 91.2059


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3084 top1= 91.3762


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3175 top1= 90.9956

Train epoch 5
[E 5B0  |    640/60000 (  1%) ] Loss: 0.3488 top1= 91.7188
[E 5B10 |   7040/60000 ( 12%) ] Loss: 0.3464 top1= 89.6875
[E 5B20 |  13440/60000 ( 22%) ] Loss: 0.4268 top1= 89.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3004 top1= 91.8470


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3447 top1= 90.8053


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3153 top1= 91.6166

Train epoch 6
[E 6B0  |    640/60000 (  1%) ] Loss: 0.3639 top1= 92.0312
[E 6B10 |   7040/60000 ( 12%) ] Loss: 0.3607 top1= 90.6250
[E 6B20 |  13440/60000 ( 22%) ] Loss: 0.4725 top1= 89.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2990 top1= 92.0473


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3191 top1= 91.9872


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.2985 top1= 92.4679

Train epoch 7
[E 7B0  |    640/60000 (  1%) ] Loss: 0.3693 top1= 91.5625
[E 7B10 |   7040/60000 ( 12%) ] Loss: 0.4044 top1= 91.4062
[E 7B20 |  13440/60000 ( 22%) ] Loss: 0.4445 top1= 89.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3231 top1= 91.8770


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3421 top1= 91.7268


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3288 top1= 91.8970

Train epoch 8
[E 8B0  |    640/60000 (  1%) ] Loss: 0.3808 top1= 91.4062
[E 8B10 |   7040/60000 ( 12%) ] Loss: 0.3837 top1= 91.8750
[E 8B20 |  13440/60000 ( 22%) ] Loss: 0.4170 top1= 89.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3217 top1= 92.0573


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3189 top1= 92.1474


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3269 top1= 92.2075

Train epoch 9
[E 9B0  |    640/60000 (  1%) ] Loss: 0.3707 top1= 91.4062
[E 9B10 |   7040/60000 ( 12%) ] Loss: 0.3749 top1= 91.0938
[E 9B20 |  13440/60000 ( 22%) ] Loss: 0.4348 top1= 90.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3285 top1= 91.9872


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3203 top1= 92.3478


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3317 top1= 92.2676

Train epoch 10
[E10B0  |    640/60000 (  1%) ] Loss: 0.3746 top1= 91.7188
[E10B10 |   7040/60000 ( 12%) ] Loss: 0.3912 top1= 91.7188
[E10B20 |  13440/60000 ( 22%) ] Loss: 0.4298 top1= 90.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3293 top1= 92.0673


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3263 top1= 92.3478


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3373 top1= 92.3678

Train epoch 11
[E11B0  |    640/60000 (  1%) ] Loss: 0.3810 top1= 91.8750
[E11B10 |   7040/60000 ( 12%) ] Loss: 0.3971 top1= 91.5625
[E11B20 |  13440/60000 ( 22%) ] Loss: 0.4326 top1= 90.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3339 top1= 92.0272


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3310 top1= 92.3578


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3399 top1= 92.3778

Train epoch 12
[E12B0  |    640/60000 (  1%) ] Loss: 0.3856 top1= 91.8750
[E12B10 |   7040/60000 ( 12%) ] Loss: 0.4027 top1= 91.7188
[E12B20 |  13440/60000 ( 22%) ] Loss: 0.4363 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3375 top1= 92.0072


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3349 top1= 92.3678


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3427 top1= 92.3377

Train epoch 13
[E13B0  |    640/60000 (  1%) ] Loss: 0.3902 top1= 91.8750
[E13B10 |   7040/60000 ( 12%) ] Loss: 0.4057 top1= 91.7188
[E13B20 |  13440/60000 ( 22%) ] Loss: 0.4399 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3399 top1= 92.0172


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3366 top1= 92.3578


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3455 top1= 92.3277

Train epoch 14
[E14B0  |    640/60000 (  1%) ] Loss: 0.3939 top1= 91.8750
[E14B10 |   7040/60000 ( 12%) ] Loss: 0.4082 top1= 91.8750
[E14B20 |  13440/60000 ( 22%) ] Loss: 0.4429 top1= 90.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3410 top1= 92.0573


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3365 top1= 92.4179


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3481 top1= 92.3077

Train epoch 15
[E15B0  |    640/60000 (  1%) ] Loss: 0.3965 top1= 92.1875
[E15B10 |   7040/60000 ( 12%) ] Loss: 0.4121 top1= 91.8750
[E15B20 |  13440/60000 ( 22%) ] Loss: 0.4457 top1= 90.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3412 top1= 92.0873


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3353 top1= 92.4479


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3499 top1= 92.2877

Train epoch 16
[E16B0  |    640/60000 (  1%) ] Loss: 0.3981 top1= 92.0312
[E16B10 |   7040/60000 ( 12%) ] Loss: 0.4160 top1= 91.8750
[E16B20 |  13440/60000 ( 22%) ] Loss: 0.4484 top1= 90.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3437 top1= 92.0873


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3384 top1= 92.4379


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3523 top1= 92.2877

Train epoch 17
[E17B0  |    640/60000 (  1%) ] Loss: 0.4021 top1= 92.0312
[E17B10 |   7040/60000 ( 12%) ] Loss: 0.4192 top1= 91.8750
[E17B20 |  13440/60000 ( 22%) ] Loss: 0.4510 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3456 top1= 92.0873


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3402 top1= 92.4379


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3545 top1= 92.2576

Train epoch 18
[E18B0  |    640/60000 (  1%) ] Loss: 0.4053 top1= 92.0312
[E18B10 |   7040/60000 ( 12%) ] Loss: 0.4227 top1= 91.8750
[E18B20 |  13440/60000 ( 22%) ] Loss: 0.4539 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3476 top1= 92.0873


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3420 top1= 92.4679


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3562 top1= 92.2676

Train epoch 19
[E19B0  |    640/60000 (  1%) ] Loss: 0.4082 top1= 91.8750
[E19B10 |   7040/60000 ( 12%) ] Loss: 0.4257 top1= 91.8750
[E19B20 |  13440/60000 ( 22%) ] Loss: 0.4562 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3496 top1= 92.0873


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3444 top1= 92.4379


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3583 top1= 92.2476

Train epoch 20
[E20B0  |    640/60000 (  1%) ] Loss: 0.4114 top1= 91.8750
[E20B10 |   7040/60000 ( 12%) ] Loss: 0.4282 top1= 91.7188
[E20B20 |  13440/60000 ( 22%) ] Loss: 0.4584 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3511 top1= 92.0673


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3459 top1= 92.4379


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3602 top1= 92.2476

Train epoch 21
[E21B0  |    640/60000 (  1%) ] Loss: 0.4139 top1= 91.8750
[E21B10 |   7040/60000 ( 12%) ] Loss: 0.4309 top1= 91.7188
[E21B20 |  13440/60000 ( 22%) ] Loss: 0.4610 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3531 top1= 92.0873


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3481 top1= 92.4379


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3617 top1= 92.2476

Train epoch 22
[E22B0  |    640/60000 (  1%) ] Loss: 0.4166 top1= 91.8750
[E22B10 |   7040/60000 ( 12%) ] Loss: 0.4339 top1= 91.7188
[E22B20 |  13440/60000 ( 22%) ] Loss: 0.4630 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3548 top1= 92.0873


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3501 top1= 92.4379


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3635 top1= 92.2376

Train epoch 23
[E23B0  |    640/60000 (  1%) ] Loss: 0.4192 top1= 91.8750
[E23B10 |   7040/60000 ( 12%) ] Loss: 0.4363 top1= 91.7188
[E23B20 |  13440/60000 ( 22%) ] Loss: 0.4650 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3565 top1= 92.0673


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3520 top1= 92.4379


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3652 top1= 92.2576

Train epoch 24
[E24B0  |    640/60000 (  1%) ] Loss: 0.4216 top1= 91.8750
[E24B10 |   7040/60000 ( 12%) ] Loss: 0.4387 top1= 91.7188
[E24B20 |  13440/60000 ( 22%) ] Loss: 0.4676 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3580 top1= 92.0873


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3531 top1= 92.4079


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3662 top1= 92.2776

Train epoch 25
[E25B0  |    640/60000 (  1%) ] Loss: 0.4231 top1= 91.8750
[E25B10 |   7040/60000 ( 12%) ] Loss: 0.4412 top1= 91.7188
[E25B20 |  13440/60000 ( 22%) ] Loss: 0.4693 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3594 top1= 92.0773


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3548 top1= 92.4079


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3678 top1= 92.2576

Train epoch 26
[E26B0  |    640/60000 (  1%) ] Loss: 0.4254 top1= 91.8750
[E26B10 |   7040/60000 ( 12%) ] Loss: 0.4432 top1= 91.7188
[E26B20 |  13440/60000 ( 22%) ] Loss: 0.4709 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3608 top1= 92.0773


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3564 top1= 92.4079


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3694 top1= 92.2576

Train epoch 27
[E27B0  |    640/60000 (  1%) ] Loss: 0.4276 top1= 91.8750
[E27B10 |   7040/60000 ( 12%) ] Loss: 0.4450 top1= 91.7188
[E27B20 |  13440/60000 ( 22%) ] Loss: 0.4724 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3617 top1= 92.0573


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3573 top1= 92.4079


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3708 top1= 92.2676

Train epoch 28
[E28B0  |    640/60000 (  1%) ] Loss: 0.4293 top1= 91.8750
[E28B10 |   7040/60000 ( 12%) ] Loss: 0.4469 top1= 91.7188
[E28B20 |  13440/60000 ( 22%) ] Loss: 0.4739 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3631 top1= 92.0373


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3588 top1= 92.4079


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3722 top1= 92.2476

Train epoch 29
[E29B0  |    640/60000 (  1%) ] Loss: 0.4312 top1= 91.8750
[E29B10 |   7040/60000 ( 12%) ] Loss: 0.4487 top1= 91.5625
[E29B20 |  13440/60000 ( 22%) ] Loss: 0.4758 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3646 top1= 92.0573


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3603 top1= 92.4079


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3733 top1= 92.2476

Train epoch 30
[E30B0  |    640/60000 (  1%) ] Loss: 0.4330 top1= 91.8750
[E30B10 |   7040/60000 ( 12%) ] Loss: 0.4509 top1= 91.7188
[E30B20 |  13440/60000 ( 22%) ] Loss: 0.4773 top1= 90.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3658 top1= 92.0573


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.3617 top1= 92.4079


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.3746 top1= 92.2376

