
=== 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 0x7f01a9633490>

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: 1.0303 top1= 62.5000
[E 1B20 |  14784/60000 ( 25%) ] Loss: 0.3959 top1= 88.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7156 top1= 78.8462


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=8.8092 top1= 49.3089


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.7568 top1= 44.2208

Train epoch 2
[E 2B0  |    704/60000 (  1%) ] Loss: 0.2829 top1= 90.7812
[E 2B10 |   7744/60000 ( 13%) ] Loss: 0.1944 top1= 93.9062
[E 2B20 |  14784/60000 ( 25%) ] Loss: 0.1959 top1= 94.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6474 top1= 84.9359


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2838 top1= 49.8297


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.4201 top1= 45.8534

Train epoch 3
[E 3B0  |    704/60000 (  1%) ] Loss: 0.1601 top1= 94.8438
[E 3B10 |   7744/60000 ( 13%) ] Loss: 0.1091 top1= 96.7188
[E 3B20 |  14784/60000 ( 25%) ] Loss: 0.1240 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5662 top1= 86.2480


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1285 top1= 50.1202


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.3773 top1= 46.2139

Train epoch 4
[E 4B0  |    704/60000 (  1%) ] Loss: 0.1192 top1= 96.4062
[E 4B10 |   7744/60000 ( 13%) ] Loss: 0.0787 top1= 98.1250
[E 4B20 |  14784/60000 ( 25%) ] Loss: 0.0811 top1= 97.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4994 top1= 87.1294


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1659 top1= 50.3305


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2833 top1= 46.4543

Train epoch 5
[E 5B0  |    704/60000 (  1%) ] Loss: 0.0826 top1= 98.1250
[E 5B10 |   7744/60000 ( 13%) ] Loss: 0.0593 top1= 98.4375
[E 5B20 |  14784/60000 ( 25%) ] Loss: 0.0572 top1= 98.2812

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4455 top1= 87.7204


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2038 top1= 50.4307


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.2653 top1= 46.4944

Train epoch 6
[E 6B0  |    704/60000 (  1%) ] Loss: 0.0641 top1= 98.7500
[E 6B10 |   7744/60000 ( 13%) ] Loss: 0.0442 top1= 98.7500
[E 6B20 |  14784/60000 ( 25%) ] Loss: 0.0427 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4105 top1= 87.9307


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1918 top1= 50.5308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.1629 top1= 46.7348

Train epoch 7
[E 7B0  |    704/60000 (  1%) ] Loss: 0.0457 top1= 98.9062
[E 7B10 |   7744/60000 ( 13%) ] Loss: 0.0314 top1= 99.3750
[E 7B20 |  14784/60000 ( 25%) ] Loss: 0.0323 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3696 top1= 88.9824


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2433 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=5.0795 top1= 46.8349

Train epoch 8
[E 8B0  |    704/60000 (  1%) ] Loss: 0.0283 top1= 99.5312
[E 8B10 |   7744/60000 ( 13%) ] Loss: 0.0209 top1= 99.6875
[E 8B20 |  14784/60000 ( 25%) ] Loss: 0.0241 top1= 99.5312

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3438 top1= 89.6234


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.2569 top1= 50.5809


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.7368 top1= 47.0152

Train epoch 9
[E 9B0  |    704/60000 (  1%) ] Loss: 0.0203 top1= 99.5312
[E 9B10 |   7744/60000 ( 13%) ] Loss: 0.0166 top1= 99.6875
[E 9B20 |  14784/60000 ( 25%) ] Loss: 0.0421 top1= 98.9062

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3350 top1= 89.8438


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=5.1483 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.3840 top1= 46.7248

Train epoch 10
[E10B0  |    704/60000 (  1%) ] Loss: 0.0254 top1= 99.0625
[E10B10 |   7744/60000 ( 13%) ] Loss: 0.0194 top1= 99.8438
[E10B20 |  14784/60000 ( 25%) ] Loss: 0.0255 top1= 99.3750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3386 top1= 89.0925


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.9683 top1= 50.5308


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.0086 top1= 46.6847

Train epoch 11
[E11B0  |    704/60000 (  1%) ] Loss: 0.0222 top1= 99.6875
[E11B10 |   7744/60000 ( 13%) ] Loss: 0.0160 top1= 99.6875
[E11B20 |  14784/60000 ( 25%) ] Loss: 0.0142 top1= 99.8438

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3099 top1= 89.7636


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.7191 top1= 50.6310


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1606 top1= 47.0252

Train epoch 12
[E12B0  |    704/60000 (  1%) ] Loss: 0.0157 top1= 99.5312
[E12B10 |   7744/60000 ( 13%) ] Loss: 0.0109 top1= 99.8438
[E12B20 |  14784/60000 ( 25%) ] Loss: 0.0137 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2971 top1= 90.3245


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.4310 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=4.1723 top1= 47.1354

Train epoch 13
[E13B0  |    704/60000 (  1%) ] Loss: 0.0070 top1=100.0000
[E13B10 |   7744/60000 ( 13%) ] Loss: 0.0073 top1=100.0000
[E13B20 |  14784/60000 ( 25%) ] Loss: 0.0270 top1= 98.5938

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2981 top1= 90.2644


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.1911 top1= 50.6611


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9798 top1= 47.1454

Train epoch 14
[E14B0  |    704/60000 (  1%) ] Loss: 0.0103 top1= 99.6875
[E14B10 |   7744/60000 ( 13%) ] Loss: 0.0079 top1= 99.8438
[E14B20 |  14784/60000 ( 25%) ] Loss: 0.0098 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2803 top1= 90.9455


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0568 top1= 50.7712


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7647 top1= 47.2456

Train epoch 15
[E15B0  |    704/60000 (  1%) ] Loss: 0.0064 top1=100.0000
[E15B10 |   7744/60000 ( 13%) ] Loss: 0.0073 top1=100.0000
[E15B20 |  14784/60000 ( 25%) ] Loss: 0.0065 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2735 top1= 90.9054


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8648 top1= 50.9515


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6930 top1= 47.4559

Train epoch 16
[E16B0  |    704/60000 (  1%) ] Loss: 0.0041 top1=100.0000
[E16B10 |   7744/60000 ( 13%) ] Loss: 0.0031 top1=100.0000
[E16B20 |  14784/60000 ( 25%) ] Loss: 0.0044 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2798 top1= 90.5449


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6528 top1= 51.4223


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6286 top1= 47.7764

Train epoch 17
[E17B0  |    704/60000 (  1%) ] Loss: 0.0045 top1=100.0000
[E17B10 |   7744/60000 ( 13%) ] Loss: 0.0036 top1=100.0000
[E17B20 |  14784/60000 ( 25%) ] Loss: 0.0049 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2680 top1= 90.9455


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5627 top1= 51.6727


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4993 top1= 48.2272

Train epoch 18
[E18B0  |    704/60000 (  1%) ] Loss: 0.0032 top1=100.0000
[E18B10 |   7744/60000 ( 13%) ] Loss: 0.0025 top1=100.0000
[E18B20 |  14784/60000 ( 25%) ] Loss: 0.0040 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2613 top1= 91.3261


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.4528 top1= 52.1935


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3945 top1= 48.7179

Train epoch 19
[E19B0  |    704/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E19B10 |   7744/60000 ( 13%) ] Loss: 0.0028 top1=100.0000
[E19B20 |  14784/60000 ( 25%) ] Loss: 0.0036 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2561 top1= 91.5465


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3914 top1= 52.8446


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.2635 top1= 49.3289

Train epoch 20
[E20B0  |    704/60000 (  1%) ] Loss: 0.0030 top1=100.0000
[E20B10 |   7744/60000 ( 13%) ] Loss: 0.0028 top1=100.0000
[E20B20 |  14784/60000 ( 25%) ] Loss: 0.0035 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2539 top1= 91.6366


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3023 top1= 53.4355


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1573 top1= 50.0801

Train epoch 21
[E21B0  |    704/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E21B10 |   7744/60000 ( 13%) ] Loss: 0.0028 top1=100.0000
[E21B20 |  14784/60000 ( 25%) ] Loss: 0.0034 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2534 top1= 91.6466


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1924 top1= 53.9062


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0648 top1= 50.8814

Train epoch 22
[E22B0  |    704/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E22B10 |   7744/60000 ( 13%) ] Loss: 0.0027 top1=100.0000
[E22B20 |  14784/60000 ( 25%) ] Loss: 0.0034 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2528 top1= 91.6366


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1062 top1= 54.5873


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9824 top1= 51.5024

Train epoch 23
[E23B0  |    704/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E23B10 |   7744/60000 ( 13%) ] Loss: 0.0027 top1=100.0000
[E23B20 |  14784/60000 ( 25%) ] Loss: 0.0033 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2519 top1= 91.6967


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0385 top1= 55.3686


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9067 top1= 52.2937

Train epoch 24
[E24B0  |    704/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E24B10 |   7744/60000 ( 13%) ] Loss: 0.0026 top1=100.0000
[E24B20 |  14784/60000 ( 25%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2515 top1= 91.7768


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9740 top1= 55.9295


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8378 top1= 52.9347

Train epoch 25
[E25B0  |    704/60000 (  1%) ] Loss: 0.0027 top1=100.0000
[E25B10 |   7744/60000 ( 13%) ] Loss: 0.0026 top1=100.0000
[E25B20 |  14784/60000 ( 25%) ] Loss: 0.0031 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2509 top1= 91.8670


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9159 top1= 56.5004


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7694 top1= 53.7861

Train epoch 26
[E26B0  |    704/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E26B10 |   7744/60000 ( 13%) ] Loss: 0.0025 top1=100.0000
[E26B20 |  14784/60000 ( 25%) ] Loss: 0.0030 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2509 top1= 91.9071


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8585 top1= 57.1514


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7030 top1= 54.4972

Train epoch 27
[E27B0  |    704/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E27B10 |   7744/60000 ( 13%) ] Loss: 0.0024 top1=100.0000
[E27B20 |  14784/60000 ( 25%) ] Loss: 0.0029 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2504 top1= 92.0072


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.8019 top1= 57.7925


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.6464 top1= 55.1983

Train epoch 28
[E28B0  |    704/60000 (  1%) ] Loss: 0.0025 top1=100.0000
[E28B10 |   7744/60000 ( 13%) ] Loss: 0.0023 top1=100.0000
[E28B20 |  14784/60000 ( 25%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2504 top1= 92.0072


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7440 top1= 58.3534


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5790 top1= 56.0296

Train epoch 29
[E29B0  |    704/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E29B10 |   7744/60000 ( 13%) ] Loss: 0.0022 top1=100.0000
[E29B20 |  14784/60000 ( 25%) ] Loss: 0.0027 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2501 top1= 92.1374


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6843 top1= 59.0044


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5328 top1= 56.7408

Train epoch 30
[E30B0  |    704/60000 (  1%) ] Loss: 0.0023 top1=100.0000
[E30B10 |   7744/60000 ( 13%) ] Loss: 0.0022 top1=100.0000
[E30B20 |  14784/60000 ( 25%) ] Loss: 0.0026 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2503 top1= 92.2676


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6248 top1= 59.5252


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4664 top1= 57.4920

