
=== 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 LabelFlippingWorker
=> Add worker LabelFlippingWorker

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7fb10ddcc7c0>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.3109 top1=  9.6875

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 1 has targets: tensor([2, 1, 4, 4, 0], device='cuda:0')
Worker 2 has targets: tensor([3, 1, 4, 1, 3], device='cuda:0')
Worker 3 has targets: tensor([2, 3, 0, 0, 1], device='cuda:0')
Worker 4 has targets: tensor([2, 1, 1, 4, 2], device='cuda:0')
Worker 5 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')
Worker 6 has targets: tensor([9, 9, 6, 7, 9], device='cuda:0')
Worker 7 has targets: tensor([7, 5, 7, 9, 5], device='cuda:0')
Worker 8 has targets: tensor([8, 9, 9, 5, 7], device='cuda:0')
Worker 9 has targets: tensor([8, 8, 7, 5, 9], device='cuda:0')
Worker 10 has targets: tensor([6, 9, 7, 7, 8], device='cuda:0')
Worker 11 has targets: tensor([3, 2, 3, 1, 3], device='cuda:0')


[E 1B10 |   4224/60000 (  7%) ] Loss: 1.0205 top1= 62.8125
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.3315 top1= 89.3750
[E 1B30 |  11904/60000 ( 20%) ] Loss: 0.5475 top1= 85.0000
[E 1B40 |  15744/60000 ( 26%) ] Loss: 0.3228 top1= 88.1250
[E 1B50 |  19584/60000 ( 33%) ] Loss: 0.2046 top1= 92.5000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7054 top1= 85.5168


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7795 top1= 49.7596


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8727 top1= 45.3125

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.1921 top1= 93.4375
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.1731 top1= 95.3125
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1068 top1= 96.8750
[E 2B30 |  11904/60000 ( 20%) ] Loss: 0.1537 top1= 93.7500
[E 2B40 |  15744/60000 ( 26%) ] Loss: 0.1276 top1= 95.0000
[E 2B50 |  19584/60000 ( 33%) ] Loss: 0.0694 top1= 98.4375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6059 top1= 87.6202


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7863 top1= 50.3105


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6590 top1= 46.2240

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.0981 top1= 97.1875
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.0887 top1= 97.1875
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0683 top1= 97.8125
[E 3B30 |  11904/60000 ( 20%) ] Loss: 0.0932 top1= 95.9375
[E 3B40 |  15744/60000 ( 26%) ] Loss: 0.0732 top1= 97.1875
[E 3B50 |  19584/60000 ( 33%) ] Loss: 0.0412 top1= 99.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5007 top1= 88.9523


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8027 top1= 50.5409


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7641 top1= 46.5745

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0604 top1= 98.4375
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0552 top1= 97.8125
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0366 top1= 99.0625
[E 4B30 |  11904/60000 ( 20%) ] Loss: 0.0509 top1= 98.1250
[E 4B40 |  15744/60000 ( 26%) ] Loss: 0.0462 top1= 98.7500
[E 4B50 |  19584/60000 ( 33%) ] Loss: 0.0259 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4185 top1= 89.9038


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8255 top1= 50.5509


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9012 top1= 46.7548

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0363 top1= 99.3750
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0380 top1= 98.7500
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0243 top1= 99.6875
[E 5B30 |  11904/60000 ( 20%) ] Loss: 0.0265 top1= 99.3750
[E 5B40 |  15744/60000 ( 26%) ] Loss: 0.0251 top1= 99.3750
[E 5B50 |  19584/60000 ( 33%) ] Loss: 0.0162 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3683 top1= 90.3045


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7937 top1= 50.6010


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8045 top1= 47.0853

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0191 top1= 99.3750
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0250 top1= 99.3750
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0136 top1=100.0000
[E 6B30 |  11904/60000 ( 20%) ] Loss: 0.0156 top1=100.0000
[E 6B40 |  15744/60000 ( 26%) ] Loss: 0.0161 top1=100.0000
[E 6B50 |  19584/60000 ( 33%) ] Loss: 0.0138 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3366 top1= 90.2444


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8100 top1= 50.5709


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7707 top1= 47.0453

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0101 top1=100.0000
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0116 top1= 99.6875
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0074 top1=100.0000
[E 7B30 |  11904/60000 ( 20%) ] Loss: 0.0165 top1= 99.6875
[E 7B40 |  15744/60000 ( 26%) ] Loss: 0.0155 top1= 99.3750
[E 7B50 |  19584/60000 ( 33%) ] Loss: 0.0079 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3217 top1= 90.3846


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6795 top1= 50.5909


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6470 top1= 47.1354

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0084 top1=100.0000
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0090 top1=100.0000
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0065 top1=100.0000
[E 8B30 |  11904/60000 ( 20%) ] Loss: 0.0092 top1=100.0000
[E 8B40 |  15744/60000 ( 26%) ] Loss: 0.0152 top1= 99.3750
[E 8B50 |  19584/60000 ( 33%) ] Loss: 0.0093 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3234 top1= 90.0641


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6337 top1= 50.6110


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9323 top1= 47.0954

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0075 top1=100.0000
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0066 top1=100.0000
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0078 top1=100.0000
[E 9B30 |  11904/60000 ( 20%) ] Loss: 0.0119 top1=100.0000
[E 9B40 |  15744/60000 ( 26%) ] Loss: 0.0044 top1=100.0000
[E 9B50 |  19584/60000 ( 33%) ] Loss: 0.0058 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3214 top1= 89.8337


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5115 top1= 50.7312


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7741 top1= 47.0152

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0036 top1=100.0000
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0062 top1=100.0000
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0081 top1=100.0000
[E10B30 |  11904/60000 ( 20%) ] Loss: 0.0165 top1= 99.3750
[E10B40 |  15744/60000 ( 26%) ] Loss: 0.0077 top1=100.0000
[E10B50 |  19584/60000 ( 33%) ] Loss: 0.0066 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3024 top1= 90.7752


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5165 top1= 50.7412


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7320 top1= 47.3458

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0058 top1=100.0000
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0089 top1=100.0000
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0194 top1= 99.3750
[E11B30 |  11904/60000 ( 20%) ] Loss: 0.0130 top1=100.0000
[E11B40 |  15744/60000 ( 26%) ] Loss: 0.0061 top1=100.0000
[E11B50 |  19584/60000 ( 33%) ] Loss: 0.0042 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3062 top1= 90.4247


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.6818 top1= 50.7812


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7308 top1= 47.4058

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0044 top1=100.0000
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0036 top1=100.0000
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0024 top1=100.0000
[E12B30 |  11904/60000 ( 20%) ] Loss: 0.0095 top1=100.0000
[E12B40 |  15744/60000 ( 26%) ] Loss: 0.0060 top1=100.0000
[E12B50 |  19584/60000 ( 33%) ] Loss: 0.0130 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2904 top1= 90.9455


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5274 top1= 51.3822


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7046 top1= 47.4359

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0032 top1=100.0000
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0037 top1=100.0000
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0091 top1= 99.6875
[E13B30 |  11904/60000 ( 20%) ] Loss: 0.0070 top1= 99.6875
[E13B40 |  15744/60000 ( 26%) ] Loss: 0.0036 top1=100.0000
[E13B50 |  19584/60000 ( 33%) ] Loss: 0.0040 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2951 top1= 90.9455


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.7801 top1= 50.9816


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9479 top1= 47.4659

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0049 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0141 top1= 99.3750
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0032 top1=100.0000
[E14B30 |  11904/60000 ( 20%) ] Loss: 0.0046 top1=100.0000
[E14B40 |  15744/60000 ( 26%) ] Loss: 0.0126 top1= 99.6875
[E14B50 |  19584/60000 ( 33%) ] Loss: 0.0032 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2712 top1= 91.5665


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5878 top1= 51.1118


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6772 top1= 47.5060

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0038 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0045 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0028 top1=100.0000
[E15B30 |  11904/60000 ( 20%) ] Loss: 0.0073 top1= 99.6875
[E15B40 |  15744/60000 ( 26%) ] Loss: 0.0030 top1=100.0000
[E15B50 |  19584/60000 ( 33%) ] Loss: 0.0044 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2830 top1= 91.2159


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.2351 top1= 51.9331


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8630 top1= 47.3858

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0037 top1=100.0000
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0026 top1=100.0000
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0023 top1=100.0000
[E16B30 |  11904/60000 ( 20%) ] Loss: 0.0029 top1=100.0000
[E16B40 |  15744/60000 ( 26%) ] Loss: 0.0036 top1=100.0000
[E16B50 |  19584/60000 ( 33%) ] Loss: 0.0034 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2798 top1= 91.1258


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.1479 top1= 52.5841


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6270 top1= 47.8866

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0025 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0022 top1=100.0000
[E17B30 |  11904/60000 ( 20%) ] Loss: 0.0035 top1=100.0000
[E17B40 |  15744/60000 ( 26%) ] Loss: 0.0020 top1=100.0000
[E17B50 |  19584/60000 ( 33%) ] Loss: 0.0022 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2749 top1= 91.4463


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0687 top1= 52.9447


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3984 top1= 48.2171

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0028 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0037 top1=100.0000
[E18B30 |  11904/60000 ( 20%) ] Loss: 0.0033 top1=100.0000
[E18B40 |  15744/60000 ( 26%) ] Loss: 0.0054 top1= 99.6875
[E18B50 |  19584/60000 ( 33%) ] Loss: 0.0036 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2801 top1= 91.0156


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.0020 top1= 53.5056


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5898 top1= 47.7865

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0027 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0031 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0053 top1=100.0000
[E19B30 |  11904/60000 ( 20%) ] Loss: 0.0067 top1= 99.6875
[E19B40 |  15744/60000 ( 26%) ] Loss: 0.0052 top1=100.0000
[E19B50 |  19584/60000 ( 33%) ] Loss: 0.0079 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3330 top1= 89.2929


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9379 top1= 53.8862


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.9114 top1= 47.6863

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0617 top1= 98.4375
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0685 top1= 98.4375
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.1226 top1= 98.1250
[E20B30 |  11904/60000 ( 20%) ] Loss: 0.1400 top1= 95.9375
[E20B40 |  15744/60000 ( 26%) ] Loss: 0.1092 top1= 97.1875
[E20B50 |  19584/60000 ( 33%) ] Loss: 0.1174 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2320 top1= 60.8574


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9172 top1= 53.9864


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1865 top1= 47.1454

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0256 top1= 98.7500
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0801 top1= 97.5000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0380 top1= 98.4375
[E21B30 |  11904/60000 ( 20%) ] Loss: 0.0377 top1= 99.0625
[E21B40 |  15744/60000 ( 26%) ] Loss: 0.0158 top1= 99.6875
[E21B50 |  19584/60000 ( 33%) ] Loss: 0.0221 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=1.2611 top1= 60.9675


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7815 top1= 54.6775


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7542 top1= 47.5861

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0038 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0147 top1= 99.3750
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0034 top1=100.0000
[E22B30 |  11904/60000 ( 20%) ] Loss: 0.0034 top1=100.0000
[E22B40 |  15744/60000 ( 26%) ] Loss: 0.0048 top1=100.0000
[E22B50 |  19584/60000 ( 33%) ] Loss: 0.0021 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7959 top1= 72.8566


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6895 top1= 55.5288


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5840 top1= 47.7163

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0028 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0019 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0016 top1=100.0000
[E23B30 |  11904/60000 ( 20%) ] Loss: 0.0030 top1=100.0000
[E23B40 |  15744/60000 ( 26%) ] Loss: 0.0027 top1=100.0000
[E23B50 |  19584/60000 ( 33%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5109 top1= 83.4535


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6192 top1= 56.1699


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1972 top1= 48.0268

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0017 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E24B30 |  11904/60000 ( 20%) ] Loss: 0.0025 top1=100.0000
[E24B40 |  15744/60000 ( 26%) ] Loss: 0.0019 top1=100.0000
[E24B50 |  19584/60000 ( 33%) ] Loss: 0.0019 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4280 top1= 86.3582


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.5398 top1= 56.7808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.1215 top1= 48.2472

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0015 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E25B30 |  11904/60000 ( 20%) ] Loss: 0.0023 top1=100.0000
[E25B40 |  15744/60000 ( 26%) ] Loss: 0.0016 top1=100.0000
[E25B50 |  19584/60000 ( 33%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3751 top1= 88.1310


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.4490 top1= 57.6222


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0413 top1= 48.4976

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0014 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E26B30 |  11904/60000 ( 20%) ] Loss: 0.0021 top1=100.0000
[E26B40 |  15744/60000 ( 26%) ] Loss: 0.0014 top1=100.0000
[E26B50 |  19584/60000 ( 33%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3341 top1= 89.4732


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3618 top1= 58.3333


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.9538 top1= 48.8682

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0014 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0013 top1=100.0000
[E27B30 |  11904/60000 ( 20%) ] Loss: 0.0020 top1=100.0000
[E27B40 |  15744/60000 ( 26%) ] Loss: 0.0013 top1=100.0000
[E27B50 |  19584/60000 ( 33%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3030 top1= 90.5749


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2596 top1= 59.1546


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.8489 top1= 49.1587

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0013 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E28B30 |  11904/60000 ( 20%) ] Loss: 0.0020 top1=100.0000
[E28B40 |  15744/60000 ( 26%) ] Loss: 0.0013 top1=100.0000
[E28B50 |  19584/60000 ( 33%) ] Loss: 0.0017 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2783 top1= 91.3662


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1647 top1= 59.9760


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7257 top1= 49.6795

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0018 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0013 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0014 top1=100.0000
[E29B30 |  11904/60000 ( 20%) ] Loss: 0.0020 top1=100.0000
[E29B40 |  15744/60000 ( 26%) ] Loss: 0.0013 top1=100.0000
[E29B50 |  19584/60000 ( 33%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2577 top1= 91.9471


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1155 top1= 60.2264


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.5888 top1= 50.4307

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0013 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0015 top1=100.0000
[E30B30 |  11904/60000 ( 20%) ] Loss: 0.0020 top1=100.0000
[E30B40 |  15744/60000 ( 26%) ] Loss: 0.0012 top1=100.0000
[E30B50 |  19584/60000 ( 33%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2437 top1= 92.3878


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0443 top1= 60.9575


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4594 top1= 51.3421

