
=== 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 ByzantineWorker(index=20)
=> Add worker ByzantineWorker(index=21)

=== Start adding graph ===
<codes.graph_utils.Dumbbell object at 0x7f9cf4441490>

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: 1.0403 top1= 61.8750
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3939 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6497 top1= 81.2500


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.3756 top1= 49.3490


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.7162 top1= 44.2308

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2839 top1= 90.7812
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1910 top1= 94.3750
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1982 top1= 94.2188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5294 top1= 86.7188


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7972 top1= 49.9599


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7038 top1= 45.8333

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1555 top1= 95.1562
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1111 top1= 97.1875
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1503 top1= 95.7812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4240 top1= 87.8005


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0959 top1= 49.7496


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8235 top1= 46.5244

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1379 top1= 95.7812
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0867 top1= 97.5000
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1186 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3588 top1= 88.8822


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7446 top1= 52.1534


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4722 top1= 49.0685

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1133 top1= 96.2500
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0666 top1= 98.2812
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0962 top1= 97.0312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3195 top1= 89.6935


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6388 top1= 54.0865


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3283 top1= 51.5224

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0845 top1= 97.8125
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0494 top1= 99.0625
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0742 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2982 top1= 90.2344


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5585 top1= 55.9195


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2060 top1= 54.6775

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0614 top1= 98.4375
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0348 top1= 99.3750
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0570 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2916 top1= 90.4247


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6284 top1= 56.8710


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1736 top1= 55.8594

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0486 top1= 98.9062
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0261 top1= 99.6875
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0459 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2764 top1= 90.7752


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3932 top1= 58.5236


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3731 top1= 55.0681

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0375 top1= 99.0625
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0278 top1= 99.2188
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0553 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2806 top1= 90.7151


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3477 top1= 59.2548


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5005 top1= 54.6474

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0434 top1= 98.9062
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0267 top1= 99.2188
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0416 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2840 top1= 90.6050


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2812 top1= 59.4551


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2823 top1= 57.5120

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0517 top1= 97.6562
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0441 top1= 98.4375
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0341 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2477 top1= 91.6667


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1597 top1= 59.7756


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0071 top1= 59.0445

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0241 top1= 99.5312
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0176 top1= 99.5312
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0270 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2442 top1= 91.7768


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2286 top1= 60.6270


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4646 top1= 52.6643

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0657 top1= 97.6562
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0258 top1= 99.2188
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0150 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2404 top1= 92.1274


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.9855 top1= 63.4716


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8851 top1= 59.5653

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0194 top1= 99.2188
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0164 top1= 99.6875
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0211 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2309 top1= 92.3678


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8735 top1= 63.7119


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9625 top1= 60.2364

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0165 top1= 99.5312
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0092 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0111 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2212 top1= 92.9387


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8317 top1= 64.2929


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6592 top1= 65.1142

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0101 top1= 99.8438
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0049 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0056 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2182 top1= 93.1190


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6283 top1= 66.3361


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5802 top1= 66.5565

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0043 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0049 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0055 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2174 top1= 93.3293


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5542 top1= 67.6683


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4494 top1= 69.0405

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0032 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0040 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0050 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2186 top1= 93.2692


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4762 top1= 68.8702


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4071 top1= 70.0621

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0029 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0046 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2169 top1= 93.5096


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4398 top1= 69.7115


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2648 top1= 71.9752

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0023 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2175 top1= 93.5797


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3869 top1= 70.6230


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2563 top1= 72.6262

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0021 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2193 top1= 93.5397


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3728 top1= 71.2240


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2693 top1= 72.9868

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0021 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2193 top1= 93.6098


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3276 top1= 72.0753


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2167 top1= 74.1587

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0018 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2205 top1= 93.6398


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2932 top1= 72.7664


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1988 top1= 74.7796

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0015 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2218 top1= 93.6799


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2607 top1= 73.3073


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1641 top1= 75.4808

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0014 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2224 top1= 93.7300


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2289 top1= 73.8281


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1513 top1= 75.9215

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2234 top1= 93.7700


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2047 top1= 74.2188


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1355 top1= 76.4123

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2238 top1= 93.7901


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1801 top1= 74.7897


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1210 top1= 76.8129

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0012 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2246 top1= 93.8001


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1581 top1= 75.2404


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1135 top1= 77.1434

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0012 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0011 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2252 top1= 93.8201


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1378 top1= 75.7212


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1041 top1= 77.4139

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0011 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0010 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0011 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2258 top1= 93.8602


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1190 top1= 76.1418


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.0970 top1= 77.6743

