
=== 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)
=> Add worker BitFlippingWorker
=> Add worker BitFlippingWorker

=== Start adding graph ===
<codes.graph_utils.Dumbbell object at 0x7feac96d6490>

Train epoch 1
[E 1B0  |    704/60000 (  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')
Worker 20 has targets: tensor([3, 2, 2, 4, 3], device='cuda:0')
Worker 21 has targets: tensor([8, 9, 7, 7, 9], device='cuda:0')


[E 1B10 |   7744/60000 ( 13%) ] Loss: 1.0657 top1= 62.0312
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3900 top1= 87.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.8214 top1= 69.5713


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9885 top1= 49.2388


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.2134 top1= 44.1807

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2791 top1= 90.7812
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1996 top1= 93.7500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.2084 top1= 94.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6133 top1= 78.5757


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6226 top1= 50.8213


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4982 top1= 45.9235

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1710 top1= 95.1562
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1313 top1= 96.4062
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1609 top1= 95.1562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4712 top1= 84.5252


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3652 top1= 53.7760


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0204 top1= 46.2841

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1399 top1= 95.3125
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.1060 top1= 97.0312
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1283 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4053 top1= 87.0693


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2925 top1= 54.9980


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7711 top1= 46.8349

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1171 top1= 96.7188
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0842 top1= 97.9688
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1075 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3667 top1= 88.0609


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2850 top1= 55.5389


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5872 top1= 47.9567

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0952 top1= 98.1250
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0693 top1= 98.2812
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0897 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3418 top1= 88.9423


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3177 top1= 55.9095


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5441 top1= 48.7179

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0792 top1= 98.5938
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0615 top1= 98.4375
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0803 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3267 top1= 89.4631


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3361 top1= 55.9395


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4771 top1= 49.6695

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0662 top1= 98.7500
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0532 top1= 98.7500
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0726 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3213 top1= 89.6134


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3294 top1= 55.8994


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4305 top1= 49.8498

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0588 top1= 98.7500
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0517 top1= 98.7500
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0629 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3183 top1= 89.6434


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3090 top1= 56.1799


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4782 top1= 50.4908

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0546 top1= 98.7500
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0477 top1= 98.9062
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0535 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3159 top1= 89.5333


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2431 top1= 56.6206


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5686 top1= 49.6194

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0528 top1= 98.9062
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0409 top1= 98.9062
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0506 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3166 top1= 89.4030


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2644 top1= 56.2500


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5857 top1= 49.1386

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0515 top1= 98.9062
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0414 top1= 98.9062
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0570 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3331 top1= 88.3714


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2223 top1= 56.1098


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7507 top1= 47.9868

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0842 top1= 97.1875
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0446 top1= 98.4375
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0563 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3517 top1= 87.4199


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2305 top1= 55.9595


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6263 top1= 49.2889

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0889 top1= 97.1875
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0577 top1= 98.2812
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0644 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3420 top1= 88.1911


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1880 top1= 56.2700


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6258 top1= 48.5377

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0546 top1= 98.5938
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0297 top1= 99.6875
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0534 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3223 top1= 89.3329


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1265 top1= 56.5605


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4029 top1= 50.5208

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0493 top1= 98.9062
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0363 top1= 99.2188
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0472 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3130 top1= 89.6735


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1236 top1= 56.5705


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3318 top1= 50.6110

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0357 top1= 99.5312
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0352 top1= 99.3750
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0518 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3186 top1= 89.3329


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2119 top1= 55.7893


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4458 top1= 50.9816

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0500 top1= 98.9062
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0352 top1= 99.5312
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0512 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3208 top1= 89.1727


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1676 top1= 55.7692


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5445 top1= 49.7496

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0538 top1= 98.7500
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0262 top1= 99.6875
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0393 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3210 top1= 89.4231


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1606 top1= 55.8594


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4199 top1= 49.9199

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0535 top1= 99.0625
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0290 top1= 99.6875
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0381 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3291 top1= 89.1727


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1182 top1= 56.0597


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4106 top1= 50.4407

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0637 top1= 98.4375
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0334 top1= 99.8438
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0404 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3239 top1= 89.1426


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1833 top1= 55.3285


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4262 top1= 50.1703

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0363 top1= 99.5312
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0426 top1= 99.0625
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0404 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3264 top1= 89.0425


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1966 top1= 54.7776


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3640 top1= 49.8698

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0474 top1= 98.5938
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0530 top1= 98.9062
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0576 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3472 top1= 87.9307


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1919 top1= 54.0565


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6265 top1= 47.3257

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0706 top1= 97.5000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0361 top1= 99.6875
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0693 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3477 top1= 88.6218


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1566 top1= 54.8377


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4874 top1= 49.0485

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0500 top1= 99.0625
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0351 top1= 99.5312
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0482 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3303 top1= 89.3229


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0958 top1= 55.3786


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4125 top1= 49.3790

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0403 top1= 99.2188
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0398 top1= 99.2188
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0524 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3212 top1= 90.0240


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2008 top1= 54.1166


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4086 top1= 48.9483

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0325 top1= 99.6875
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0419 top1= 99.2188
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0449 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3391 top1= 89.4832


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2351 top1= 53.8662


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2665 top1= 49.7596

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0496 top1= 99.0625
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0479 top1= 98.9062
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0459 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3613 top1= 88.7720


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2534 top1= 52.6843


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3654 top1= 48.6679

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0930 top1= 96.8750
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0528 top1= 98.9062
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0497 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3432 top1= 89.1827


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1420 top1= 53.8862


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4542 top1= 48.3974

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0362 top1= 99.6875
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0360 top1= 99.6875
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0536 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3397 top1= 88.9423


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1172 top1= 54.1667


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5090 top1= 48.0569

