
=== 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 0x7efdaef32490>

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: 1.0541 top1= 61.7188
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3919 top1= 87.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6704 top1= 81.1599


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.1018 top1= 49.2989


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.5315 top1= 44.3510

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2809 top1= 91.0938
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1936 top1= 94.3750
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.2018 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5686 top1= 86.2780


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8102 top1= 49.9399


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7325 top1= 45.8634

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1597 top1= 94.5312
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1194 top1= 97.1875
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1566 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4575 top1= 87.5701


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1564 top1= 49.8698


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9644 top1= 46.2740

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1432 top1= 95.6250
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0962 top1= 97.0312
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1246 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3883 top1= 88.3614


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7877 top1= 50.8814


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6384 top1= 47.4860

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1212 top1= 97.0312
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0786 top1= 97.6562
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.1049 top1= 96.4062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3476 top1= 89.1026


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7025 top1= 51.9732


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5073 top1= 48.7780

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.1014 top1= 97.1875
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0599 top1= 98.7500
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0827 top1= 97.3438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3191 top1= 89.8538


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6398 top1= 53.0749


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4474 top1= 49.8698

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0850 top1= 98.5938
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0490 top1= 99.2188
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0732 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3036 top1= 89.9038


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6541 top1= 53.9363


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3228 top1= 51.3121

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0696 top1= 98.7500
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0420 top1= 99.0625
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0634 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2958 top1= 90.1242


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6406 top1= 54.5373


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2236 top1= 52.9948

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0587 top1= 99.0625
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0377 top1= 98.9062
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0504 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3004 top1= 90.1042


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5975 top1= 55.3385


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2514 top1= 54.2768

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0570 top1= 97.8125
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0377 top1= 99.3750
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0482 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2966 top1= 90.1643


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4863 top1= 56.1398


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1286 top1= 54.7376

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0435 top1= 99.0625
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0365 top1= 99.0625
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0465 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2840 top1= 90.5248


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4102 top1= 57.0413


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2369 top1= 53.9062

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0337 top1= 99.3750
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0270 top1= 99.5312
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0513 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2767 top1= 90.6951


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2604 top1= 57.6222


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2829 top1= 53.1350

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0324 top1= 99.0625
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0325 top1= 98.9062
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0552 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2920 top1= 90.1142


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0761 top1= 58.3333


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4108 top1= 53.4956

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0522 top1= 98.2812
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0337 top1= 99.0625
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0480 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2710 top1= 90.9455


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1795 top1= 56.8610


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3503 top1= 52.4139

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0460 top1= 98.4375
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0392 top1= 98.5938
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0384 top1= 99.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2689 top1= 91.0958


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0055 top1= 57.4419


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0537 top1= 54.5773

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0451 top1= 98.5938
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0231 top1= 99.6875
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0334 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2652 top1= 91.2159


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1226 top1= 57.4018


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1828 top1= 53.6258

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0245 top1= 99.3750
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0242 top1= 99.3750
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0406 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2704 top1= 91.0557


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0038 top1= 59.1146


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1364 top1= 54.0064

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0210 top1= 99.3750
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0158 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0197 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2707 top1= 91.0958


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9531 top1= 59.6454


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0012 top1= 53.9463

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0291 top1= 99.0625
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0195 top1= 99.8438
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0210 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2783 top1= 90.5849


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9521 top1= 59.5753


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2515 top1= 51.7929

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0381 top1= 98.9062
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0226 top1= 99.5312
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0199 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2731 top1= 90.7452


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8996 top1= 60.0661


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2607 top1= 52.2636

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0196 top1= 99.6875
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0219 top1= 99.6875
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0207 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2642 top1= 91.0857


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9245 top1= 59.8958


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2266 top1= 52.1635

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0191 top1= 99.5312
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0159 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0149 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2604 top1= 91.3862


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9366 top1= 59.8558


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1267 top1= 52.7544

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0175 top1= 99.6875
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0169 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0168 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2572 top1= 91.4163


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9538 top1= 59.7957


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2410 top1= 51.9932

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0257 top1= 99.6875
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0166 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0157 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2524 top1= 91.6266


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9571 top1= 59.7857


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1679 top1= 53.0248

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0158 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0176 top1= 99.6875
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0178 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2550 top1= 91.4864


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9506 top1= 59.3750


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1588 top1= 53.4956

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0186 top1= 99.8438
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0230 top1= 99.8438
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0213 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2581 top1= 91.3962


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9841 top1= 59.1246


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2610 top1= 52.4038

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0241 top1= 99.5312
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0141 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0183 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2548 top1= 91.5064


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9630 top1= 59.0745


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2329 top1= 51.9331

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0217 top1= 99.8438
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0147 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0190 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2588 top1= 91.5565


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9774 top1= 58.9944


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2069 top1= 52.4439

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0203 top1= 99.8438
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0200 top1= 99.8438
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0186 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2551 top1= 91.7768


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9768 top1= 58.8442


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0802 top1= 52.9547

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0121 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0205 top1= 99.6875
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0192 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2632 top1= 91.1158


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9964 top1= 58.5136


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3360 top1= 51.2720

