
=== 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.DumbbellVariant object at 0x7f7edb9312b0>

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: 1.0400 top1= 62.3438
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3922 top1= 87.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6499 top1= 80.7893


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=7.0292 top1= 49.3490


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=6.3954 top1= 44.2208

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2721 top1= 91.2500
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1957 top1= 93.7500
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1935 top1= 94.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5026 top1= 87.0092


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4170 top1= 50.0200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3269 top1= 45.9235

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1548 top1= 95.4688
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1153 top1= 96.8750
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1489 top1= 95.4688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4060 top1= 87.9908


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0218 top1= 50.1903


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8263 top1= 46.6747

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1299 top1= 95.9375
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0857 top1= 97.1875
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.1115 top1= 96.7188

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3532 top1= 88.7821


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8610 top1= 52.0232


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5662 top1= 48.4075

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.1072 top1= 97.5000
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0643 top1= 98.4375
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0859 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3258 top1= 89.3229


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8135 top1= 53.2151


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3678 top1= 51.0517

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0796 top1= 98.1250
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0490 top1= 99.0625
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0697 top1= 97.6562

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3083 top1= 89.8938


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7301 top1= 54.7576


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2316 top1= 54.0865

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0596 top1= 98.7500
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0384 top1= 99.2188
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0564 top1= 97.9688

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2966 top1= 90.3546


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7023 top1= 56.2901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1726 top1= 55.4387

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0469 top1= 99.2188
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0257 top1= 99.6875
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0407 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2844 top1= 90.4748


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6534 top1= 56.8409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3130 top1= 55.0681

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0442 top1= 99.0625
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0254 top1= 99.2188
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0612 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2798 top1= 90.6951


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6562 top1= 57.3217


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4414 top1= 54.8177

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0672 top1= 97.8125
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0374 top1= 98.9062
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0474 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2948 top1= 89.8738


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4009 top1= 58.5036


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4007 top1= 56.6006

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0366 top1= 98.7500
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0312 top1= 98.9062
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0488 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2790 top1= 90.7252


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1808 top1= 60.3866


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2366 top1= 55.6891

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0281 top1= 99.5312
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0129 top1= 99.8438
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0170 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2462 top1= 92.0172


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3515 top1= 60.4367


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2328 top1= 56.0397

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0213 top1= 99.3750
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0158 top1=100.0000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0107 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2439 top1= 92.1975


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1695 top1= 62.4199


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0995 top1= 58.2031

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0122 top1= 99.5312
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0104 top1= 99.8438
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0131 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2407 top1= 92.1975


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3125 top1= 61.2881


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0144 top1= 59.4852

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0084 top1=100.0000
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0056 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0085 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2325 top1= 92.6382


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0942 top1= 62.5801


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.9068 top1= 61.7388

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0073 top1= 99.8438
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0074 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0060 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2423 top1= 92.4079


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0705 top1= 62.6903


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0091 top1= 62.0292

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0077 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0061 top1= 99.8438
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0052 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2379 top1= 92.6783


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8403 top1= 65.3145


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.8225 top1= 64.9139

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0045 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0046 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0057 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2407 top1= 92.6883


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.8282 top1= 65.7752


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7818 top1= 66.3462

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0052 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0049 top1= 99.8438
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0039 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2497 top1= 92.4679


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.7119 top1= 67.1074


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6299 top1= 68.3293

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0075 top1= 99.8438
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0063 top1= 99.8438
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0043 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2396 top1= 92.8886


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6767 top1= 67.8085


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7958 top1= 66.1458

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0029 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2378 top1= 92.9688


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6143 top1= 68.6198


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6490 top1= 68.4696

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0021 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0038 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2393 top1= 92.9287


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6166 top1= 69.0204


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7502 top1= 67.7484

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0032 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0022 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0070 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2315 top1= 93.1791


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5723 top1= 69.7616


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.5116 top1= 70.1823

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0025 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0035 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2305 top1= 93.3494


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5268 top1= 70.4527


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4619 top1= 70.7432

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0035 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0044 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2293 top1= 93.3794


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4949 top1= 70.9335


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3644 top1= 71.9752

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2308 top1= 93.4095


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4407 top1= 71.7748


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3336 top1= 72.1855

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0032 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0068 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2285 top1= 93.4495


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.4271 top1= 72.1354


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3853 top1= 72.0954

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0016 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2333 top1= 93.3894


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3832 top1= 72.6863


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4675 top1= 70.9836

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0044 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0019 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0028 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2326 top1= 93.4595


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3713 top1= 72.8966


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.4513 top1= 71.9451

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0013 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2419 top1= 93.3393


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.3469 top1= 73.4275


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6508 top1= 70.3025

