
=== 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 BitFlippingWorker
=> Add worker BitFlippingWorker

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7f94a210e7c0>

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([3, 0, 2, 2, 1], device='cuda:0')
Worker 11 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')


[E 1B10 |   4224/60000 (  7%) ] Loss: 1.0620 top1= 64.3750
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2776 top1= 91.5625
[E 1B30 |  11904/60000 ( 20%) ] Loss: 0.4228 top1= 86.8750
[E 1B40 |  15744/60000 ( 26%) ] Loss: 0.2655 top1= 89.6875
[E 1B50 |  19584/60000 ( 33%) ] Loss: 0.1928 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5522 top1= 86.2981


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6136 top1= 49.8097


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3516 top1= 45.7332

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.1896 top1= 95.3125
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.2153 top1= 93.4375
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1534 top1= 95.9375
[E 2B30 |  11904/60000 ( 20%) ] Loss: 0.2405 top1= 93.1250
[E 2B40 |  15744/60000 ( 26%) ] Loss: 0.1810 top1= 93.4375
[E 2B50 |  19584/60000 ( 33%) ] Loss: 0.1337 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4523 top1= 88.2512


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3210 top1= 52.2236


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0299 top1= 48.0669

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1452 top1= 95.6250
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1827 top1= 93.4375
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.1255 top1= 96.5625
[E 3B30 |  11904/60000 ( 20%) ] Loss: 0.2049 top1= 94.3750
[E 3B40 |  15744/60000 ( 26%) ] Loss: 0.1529 top1= 95.9375
[E 3B50 |  19584/60000 ( 33%) ] Loss: 0.1111 top1= 96.5625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4328 top1= 88.7220


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2537 top1= 52.6442


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0211 top1= 48.2272

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.1235 top1= 96.2500
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.1559 top1= 94.6875
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.1153 top1= 96.2500
[E 4B30 |  11904/60000 ( 20%) ] Loss: 0.1899 top1= 94.0625
[E 4B40 |  15744/60000 ( 26%) ] Loss: 0.1392 top1= 96.2500
[E 4B50 |  19584/60000 ( 33%) ] Loss: 0.1051 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4417 top1= 88.6518


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.2202 top1= 52.3137


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0273 top1= 48.1470

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.1140 top1= 96.8750
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.1456 top1= 95.0000
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.1189 top1= 96.8750
[E 5B30 |  11904/60000 ( 20%) ] Loss: 0.1862 top1= 95.0000
[E 5B40 |  15744/60000 ( 26%) ] Loss: 0.1378 top1= 97.1875
[E 5B50 |  19584/60000 ( 33%) ] Loss: 0.1041 top1= 96.8750

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4732 top1= 88.2111


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1882 top1= 52.0232


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0835 top1= 47.4760

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.1125 top1= 97.1875
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.1418 top1= 94.3750
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.1259 top1= 96.8750
[E 6B30 |  11904/60000 ( 20%) ] Loss: 0.1944 top1= 94.6875
[E 6B40 |  15744/60000 ( 26%) ] Loss: 0.1477 top1= 95.9375
[E 6B50 |  19584/60000 ( 33%) ] Loss: 0.1067 top1= 97.1875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5149 top1= 87.6102


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1744 top1= 51.3622


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1221 top1= 46.7849

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.1195 top1= 96.8750
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.1575 top1= 95.0000
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.1252 top1= 96.8750
[E 7B30 |  11904/60000 ( 20%) ] Loss: 0.2008 top1= 94.6875
[E 7B40 |  15744/60000 ( 26%) ] Loss: 0.1657 top1= 94.6875
[E 7B50 |  19584/60000 ( 33%) ] Loss: 0.1173 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5598 top1= 86.8990


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1746 top1= 50.4708


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2016 top1= 46.0837

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.1263 top1= 96.8750
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.1842 top1= 93.7500
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.1286 top1= 96.2500
[E 8B30 |  11904/60000 ( 20%) ] Loss: 0.2226 top1= 94.6875
[E 8B40 |  15744/60000 ( 26%) ] Loss: 0.1833 top1= 94.3750
[E 8B50 |  19584/60000 ( 33%) ] Loss: 0.1343 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6052 top1= 86.1078


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1677 top1= 50.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2503 top1= 45.8734

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.1322 top1= 96.8750
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.2071 top1= 93.4375
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.1336 top1= 96.2500
[E 9B30 |  11904/60000 ( 20%) ] Loss: 0.2340 top1= 94.0625
[E 9B40 |  15744/60000 ( 26%) ] Loss: 0.1972 top1= 93.4375
[E 9B50 |  19584/60000 ( 33%) ] Loss: 0.1445 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6352 top1= 85.5369


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1244 top1= 50.0200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2840 top1= 45.8233

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.1389 top1= 96.8750
[E10B10 |   4224/60000 (  7%) ] Loss: 0.2124 top1= 94.0625
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.1317 top1= 96.5625
[E10B30 |  11904/60000 ( 20%) ] Loss: 0.2383 top1= 94.3750
[E10B40 |  15744/60000 ( 26%) ] Loss: 0.1995 top1= 93.1250
[E10B50 |  19584/60000 ( 33%) ] Loss: 0.1476 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6520 top1= 85.1562


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1078 top1= 49.9800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3321 top1= 45.7232

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.1441 top1= 96.2500
[E11B10 |   4224/60000 (  7%) ] Loss: 0.2281 top1= 93.4375
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.1324 top1= 96.2500
[E11B30 |  11904/60000 ( 20%) ] Loss: 0.2355 top1= 94.0625
[E11B40 |  15744/60000 ( 26%) ] Loss: 0.2076 top1= 92.8125
[E11B50 |  19584/60000 ( 33%) ] Loss: 0.1524 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6640 top1= 85.0260


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0893 top1= 49.9199


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3046 top1= 45.7232

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.1494 top1= 96.5625
[E12B10 |   4224/60000 (  7%) ] Loss: 0.2318 top1= 93.4375
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.1327 top1= 96.8750
[E12B30 |  11904/60000 ( 20%) ] Loss: 0.2399 top1= 94.0625
[E12B40 |  15744/60000 ( 26%) ] Loss: 0.2133 top1= 92.8125
[E12B50 |  19584/60000 ( 33%) ] Loss: 0.1516 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6700 top1= 84.8357


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0676 top1= 49.9800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3011 top1= 45.6530

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.1515 top1= 97.1875
[E13B10 |   4224/60000 (  7%) ] Loss: 0.2314 top1= 93.4375
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.1365 top1= 96.8750
[E13B30 |  11904/60000 ( 20%) ] Loss: 0.2397 top1= 94.3750
[E13B40 |  15744/60000 ( 26%) ] Loss: 0.2125 top1= 92.8125
[E13B50 |  19584/60000 ( 33%) ] Loss: 0.1601 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6761 top1= 84.6054


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0624 top1= 50.0300


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2739 top1= 45.5128

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.1535 top1= 96.8750
[E14B10 |   4224/60000 (  7%) ] Loss: 0.2278 top1= 93.4375
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.1348 top1= 96.8750
[E14B30 |  11904/60000 ( 20%) ] Loss: 0.2387 top1= 94.6875
[E14B40 |  15744/60000 ( 26%) ] Loss: 0.2090 top1= 92.8125
[E14B50 |  19584/60000 ( 33%) ] Loss: 0.1574 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6811 top1= 84.7055


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0586 top1= 50.0300


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2687 top1= 45.5128

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.1529 top1= 96.2500
[E15B10 |   4224/60000 (  7%) ] Loss: 0.2249 top1= 93.1250
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.1360 top1= 97.1875
[E15B30 |  11904/60000 ( 20%) ] Loss: 0.2323 top1= 94.6875
[E15B40 |  15744/60000 ( 26%) ] Loss: 0.2039 top1= 92.8125
[E15B50 |  19584/60000 ( 33%) ] Loss: 0.1558 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6857 top1= 84.3650


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0614 top1= 50.0601


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2665 top1= 45.4728

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.1539 top1= 96.2500
[E16B10 |   4224/60000 (  7%) ] Loss: 0.2315 top1= 93.1250
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.1357 top1= 97.1875
[E16B30 |  11904/60000 ( 20%) ] Loss: 0.2332 top1= 94.3750
[E16B40 |  15744/60000 ( 26%) ] Loss: 0.2006 top1= 92.8125
[E16B50 |  19584/60000 ( 33%) ] Loss: 0.1546 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6860 top1= 84.5152


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0667 top1= 50.0901


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2457 top1= 45.4127

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.1586 top1= 95.9375
[E17B10 |   4224/60000 (  7%) ] Loss: 0.2338 top1= 93.1250
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.1341 top1= 97.1875
[E17B30 |  11904/60000 ( 20%) ] Loss: 0.2342 top1= 93.4375
[E17B40 |  15744/60000 ( 26%) ] Loss: 0.1943 top1= 92.1875
[E17B50 |  19584/60000 ( 33%) ] Loss: 0.1538 top1= 95.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6872 top1= 84.5052


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0754 top1= 50.0100


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2483 top1= 45.2424

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.1645 top1= 95.6250
[E18B10 |   4224/60000 (  7%) ] Loss: 0.2350 top1= 92.5000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.1353 top1= 96.8750
[E18B30 |  11904/60000 ( 20%) ] Loss: 0.2396 top1= 94.0625
[E18B40 |  15744/60000 ( 26%) ] Loss: 0.1955 top1= 92.5000
[E18B50 |  19584/60000 ( 33%) ] Loss: 0.1454 top1= 95.3125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6873 top1= 84.7456


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0863 top1= 50.0200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2352 top1= 45.4527

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.1578 top1= 95.9375
[E19B10 |   4224/60000 (  7%) ] Loss: 0.2272 top1= 92.5000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.1351 top1= 97.5000
[E19B30 |  11904/60000 ( 20%) ] Loss: 0.2345 top1= 94.3750
[E19B40 |  15744/60000 ( 26%) ] Loss: 0.1886 top1= 92.5000
[E19B50 |  19584/60000 ( 33%) ] Loss: 0.1512 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6958 top1= 84.0345


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1120 top1= 50.0100


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2348 top1= 45.1923

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.1653 top1= 95.3125
[E20B10 |   4224/60000 (  7%) ] Loss: 0.2243 top1= 92.5000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.1378 top1= 97.1875
[E20B30 |  11904/60000 ( 20%) ] Loss: 0.2348 top1= 94.6875
[E20B40 |  15744/60000 ( 26%) ] Loss: 0.1827 top1= 93.1250
[E20B50 |  19584/60000 ( 33%) ] Loss: 0.1497 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6975 top1= 84.2849


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1060 top1= 50.0000


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2346 top1= 45.0621

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.1621 top1= 95.3125
[E21B10 |   4224/60000 (  7%) ] Loss: 0.2283 top1= 92.5000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.1384 top1= 96.8750
[E21B30 |  11904/60000 ( 20%) ] Loss: 0.2398 top1= 94.0625
[E21B40 |  15744/60000 ( 26%) ] Loss: 0.1859 top1= 93.4375
[E21B50 |  19584/60000 ( 33%) ] Loss: 0.1448 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6996 top1= 83.9343


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1288 top1= 50.0200


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2262 top1= 45.4427

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.1587 top1= 95.6250
[E22B10 |   4224/60000 (  7%) ] Loss: 0.2246 top1= 92.8125
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.1454 top1= 97.1875
[E22B30 |  11904/60000 ( 20%) ] Loss: 0.2342 top1= 94.3750
[E22B40 |  15744/60000 ( 26%) ] Loss: 0.1827 top1= 93.7500
[E22B50 |  19584/60000 ( 33%) ] Loss: 0.1502 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6980 top1= 83.8341


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1218 top1= 49.9800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2392 top1= 45.3425

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.1595 top1= 95.6250
[E23B10 |   4224/60000 (  7%) ] Loss: 0.2279 top1= 92.1875
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.1396 top1= 97.1875
[E23B30 |  11904/60000 ( 20%) ] Loss: 0.2385 top1= 94.3750
[E23B40 |  15744/60000 ( 26%) ] Loss: 0.1835 top1= 93.4375
[E23B50 |  19584/60000 ( 33%) ] Loss: 0.1574 top1= 95.6250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7010 top1= 83.5337


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1306 top1= 49.9900


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2095 top1= 45.3225

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.1596 top1= 96.2500
[E24B10 |   4224/60000 (  7%) ] Loss: 0.2222 top1= 92.5000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.1423 top1= 96.8750
[E24B30 |  11904/60000 ( 20%) ] Loss: 0.2389 top1= 94.0625
[E24B40 |  15744/60000 ( 26%) ] Loss: 0.1878 top1= 93.4375
[E24B50 |  19584/60000 ( 33%) ] Loss: 0.1546 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7008 top1= 84.0745


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1125 top1= 49.9399


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2323 top1= 45.4026

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.1602 top1= 95.9375
[E25B10 |   4224/60000 (  7%) ] Loss: 0.2213 top1= 92.5000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.1451 top1= 97.1875
[E25B30 |  11904/60000 ( 20%) ] Loss: 0.2385 top1= 94.3750
[E25B40 |  15744/60000 ( 26%) ] Loss: 0.1874 top1= 94.0625
[E25B50 |  19584/60000 ( 33%) ] Loss: 0.1514 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7016 top1= 83.9443


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1065 top1= 49.9700


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2211 top1= 45.4327

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.1579 top1= 95.9375
[E26B10 |   4224/60000 (  7%) ] Loss: 0.2234 top1= 92.5000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.1451 top1= 96.8750
[E26B30 |  11904/60000 ( 20%) ] Loss: 0.2359 top1= 94.3750
[E26B40 |  15744/60000 ( 26%) ] Loss: 0.1897 top1= 94.0625
[E26B50 |  19584/60000 ( 33%) ] Loss: 0.1534 top1= 95.9375

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7033 top1= 83.9143


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1014 top1= 49.9800


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2314 top1= 45.4627

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.1551 top1= 96.2500
[E27B10 |   4224/60000 (  7%) ] Loss: 0.2213 top1= 92.5000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.1461 top1= 96.8750
[E27B30 |  11904/60000 ( 20%) ] Loss: 0.2287 top1= 94.0625
[E27B40 |  15744/60000 ( 26%) ] Loss: 0.1890 top1= 93.7500
[E27B50 |  19584/60000 ( 33%) ] Loss: 0.1542 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7095 top1= 83.7139


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1104 top1= 49.9700


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1764 top1= 45.1623

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.1624 top1= 95.9375
[E28B10 |   4224/60000 (  7%) ] Loss: 0.2223 top1= 92.5000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.1494 top1= 96.5625
[E28B30 |  11904/60000 ( 20%) ] Loss: 0.2335 top1= 94.0625
[E28B40 |  15744/60000 ( 26%) ] Loss: 0.1891 top1= 93.1250
[E28B50 |  19584/60000 ( 33%) ] Loss: 0.1490 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7070 top1= 84.0144


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.0950 top1= 49.9399


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1779 top1= 45.2324

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.1594 top1= 96.2500
[E29B10 |   4224/60000 (  7%) ] Loss: 0.2254 top1= 92.5000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.1453 top1= 96.8750
[E29B30 |  11904/60000 ( 20%) ] Loss: 0.2333 top1= 94.6875
[E29B40 |  15744/60000 ( 26%) ] Loss: 0.1894 top1= 93.4375
[E29B50 |  19584/60000 ( 33%) ] Loss: 0.1521 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7065 top1= 83.9042


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1010 top1= 49.9399


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2071 top1= 45.2324

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.1532 top1= 96.8750
[E30B10 |   4224/60000 (  7%) ] Loss: 0.2172 top1= 92.1875
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.1451 top1= 96.8750
[E30B30 |  11904/60000 ( 20%) ] Loss: 0.2359 top1= 94.3750
[E30B40 |  15744/60000 ( 26%) ] Loss: 0.1881 top1= 93.4375
[E30B50 |  19584/60000 ( 33%) ] Loss: 0.1467 top1= 96.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.7074 top1= 83.9443


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1018 top1= 49.9399


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.2054 top1= 45.2724

